Add files using upload-large-folder tool

README.md

@@ -0,0 +1,66 @@
+# Fine-tuned Models
+
+This repository accompanies our paper: **[How Large Language Models Balance Internal Knowledge with User and Document Assertions](https://arxiv.org/abs/2604.22193)**
+
+Our code is available at: [GitHub Repository](https://github.com/shuowl/llm-source-balancing)
+
+This directory contains supervised fine-tuned models for our three-source interaction experiments. The models are trained on data constructed from either CommonsenseQA (CSQA) or GSM8K, using different source-interaction variants described in the paper.
+
+## Model Naming Convention
+
+Each model folder follows the format:
+
+`{dataset}__{base_model}__{training_variant}_r{rank}_bs{batch_size}_lr{learning_rate}_e{epochs}`
+
+Example:
+
+`csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3`
+
+### Fields
+
+- **dataset**
+  - `csqa`: training data constructed from the CommonsenseQA dataset.
+  - `gsm8k`: training data constructed from the multiple-choice GSM8K dataset.
+
+- **base_model**
+  - `llama3_8b_instruct`: Llama 3 8B Instruct model.
+  - `qwen3_8b`: Qwen3 8B non-thinking instruction model.
+
+- **training_variant**
+  - `all_variants`: mixed SFT using all source-interaction probe variants, including bare, single-source, and double-source patterns.
+  - `bare100`: standard SFT using only bare prompts without external user or document assertions.
+
+- **r**
+  - LoRA rank. For example, `r8` means LoRA rank 8.
+
+- **bs**
+  - Training batch size. For example, `bs4` means batch size 4.
+
+- **lr**
+  - Learning rate. For example, `lr1e5` means learning rate `1e-5`.
+
+- **e**
+  - Number of training epochs. For example, `e3` means 3 epochs.
+
+## Training Variants
+
+### `bare100`
+
+This setting fine-tunes the model only on standard question-answer examples without external assertions. It corresponds to the standard SFT baseline.
+
+### `all_variants`
+
+This setting fine-tunes the model on diverse source-interaction patterns. The training data includes the bare prompt, single-source prompts, and double-source prompts involving user and document assertions. These variants are designed to teach the model to better distinguish helpful external information from harmful or misleading information.
+
+For details about the probe construction and SFT setup, see the methodology and fine-tuning sections of the paper.
+
+## Available Models
+
+- `csqa__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3`
+- `csqa__llama3_8b_instruct__bare100_r8_bs4_lr1e5_e3`
+- `csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3`
+- `csqa__qwen3_8b__bare100_r8_bs4_lr1e5_e3`
+- `gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3`
+- `gsm8k__llama3_8b_instruct__bare100_r8_bs4_lr1e5_e3`
+- `gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3`
+- `gsm8k__qwen3_8b__bare100_r8_bs4_lr1e5_e3`

csqa__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json

@@ -0,0 +1,685 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 37.80012893676758,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 6.0686,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 39.88420104980469,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 5.9851,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 44.61463165283203,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 5.809,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 52.375526428222656,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 5.2936,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 56.54472732543945,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 3.6564,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 4.893699645996094,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 0.9929,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 4.38793420791626,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 0.6096,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 5.497848987579346,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 0.5668,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.2072407007217407,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.2634,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.7709367275238037,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.1972,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 0.8148612380027771,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.2005,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.6053568124771118,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.2067,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 0.5733060836791992,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.1845,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 0.5413147807121277,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.1846,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.5612006187438965,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.1682,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.5495957732200623,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.1782,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 0.6474818587303162,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.1753,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.8423108458518982,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.1924,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 0.5483237504959106,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.1811,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 0.671990156173706,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.168,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 0.939056932926178,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1745,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 0.7187698483467102,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.1841,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 0.5241701602935791,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.1648,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.6630734205245972,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.1461,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.1286036968231201,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.1625,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 0.5125612616539001,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.1795,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 0.858910322189331,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.1742,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 0.6850348711013794,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1918,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 0.7184205651283264,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.1904,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.0153907537460327,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1624,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.048191785812378,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.1888,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 0.6901400685310364,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.1536,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.686369001865387,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1491,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 0.9062027931213379,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.149,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 0.5785990357398987,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.1888,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.661888599395752,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1655,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 0.6389531493186951,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1619,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.0746989250183105,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1576,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.8966940641403198,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1438,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 0.6431125402450562,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1492,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.0681558847427368,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1414,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.6957165002822876,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1602,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 0.930090606212616,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1494,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 0.6608450412750244,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1756,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 0.7900845408439636,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1417,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 0.6088914275169373,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1417,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 1.0221658945083618,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1411,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 0.949171781539917,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1625,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.0847721099853516,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.1373,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 0.8148903250694275,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1319,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6994309425354004,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.1242,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 1.0713452100753784,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.1354,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.23827064037323,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.1553,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.3071824312210083,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1598,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.4454975128173828,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.1878,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 0.9927931427955627,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1571,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.0181673765182495,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1463,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.098183035850525,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1284,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 0.9349597096443176,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1265,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.7482240796089172,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.116,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 1.1793172359466553,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1282,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 0.657133936882019,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.1501,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.6432955861091614,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1354,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 0.861251711845398,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.1439,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.8403468728065491,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.1326,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.5765302181243896,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.0974,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.6433290243148804,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1325,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.6270760297775269,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1208,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.1694698333740234,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1089,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 1.1193510293960571,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.1458,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 1.203051209449768,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1296,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 0.6728342175483704,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.114,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.1375242471694946,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1383,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 0.5893566012382507,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.1291,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.8352311849594116,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1479,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 0.634758710861206,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.1153,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.1101970672607422,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1522,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 0.8607526421546936,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1333,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 0.8799166083335876,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1111,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 0.9858982563018799,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1345,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 0.8103428483009338,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1425,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.104451060295105,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1332,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 0.788467288017273,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1167,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 1.0944404602050781,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1305,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.3954204320907593,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1264,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.0658373832702637,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1196,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.1783170700073242,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1359,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 0.7922008633613586,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1214,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 0.68011075258255,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1298,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 0.8950837254524231,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1106,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 0.6562188863754272,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1087,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.1354018449783325,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1348,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 0.6269157528877258,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1287,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4737480102602342e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.4737480102602342e+17,
+    "train_loss": 0.4462493950058731,
+    "train_runtime": 438.8238,
+    "train_samples_per_second": 68.365,
+    "train_steps_per_second": 2.14
+}

csqa__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json

@@ -0,0 +1,694 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 37.80012893676758,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 6.0686,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 39.88420104980469,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 5.9851,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 44.61463165283203,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 5.809,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 52.375526428222656,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 5.2936,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 56.54472732543945,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 3.6564,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 4.893699645996094,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 0.9929,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 4.38793420791626,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 0.6096,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 5.497848987579346,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 0.5668,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.2072407007217407,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.2634,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.7709367275238037,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.1972,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 0.8148612380027771,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.2005,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.6053568124771118,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.2067,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 0.5733060836791992,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.1845,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 0.5413147807121277,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.1846,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.5612006187438965,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.1682,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.5495957732200623,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.1782,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 0.6474818587303162,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.1753,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 0.8423108458518982,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.1924,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 0.5483237504959106,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.1811,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 0.671990156173706,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.168,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 0.939056932926178,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1745,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 0.7187698483467102,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.1841,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 0.5241701602935791,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.1648,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.6630734205245972,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.1461,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.1286036968231201,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.1625,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 0.5125612616539001,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.1795,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 0.858910322189331,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.1742,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 0.6850348711013794,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1918,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 0.7184205651283264,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.1904,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.0153907537460327,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1624,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 1.048191785812378,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.1888,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 0.6901400685310364,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.1536,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 0.686369001865387,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1491,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 0.9062027931213379,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.149,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 0.5785990357398987,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.1888,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.661888599395752,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1655,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 0.6389531493186951,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1619,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.0746989250183105,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1576,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 0.8966940641403198,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1438,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 0.6431125402450562,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1492,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.0681558847427368,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1414,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 0.6957165002822876,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1602,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 0.930090606212616,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1494,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 0.6608450412750244,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1756,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 0.7900845408439636,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1417,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 0.6088914275169373,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1417,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 1.0221658945083618,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1411,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 0.949171781539917,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1625,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.0847721099853516,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.1373,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 0.8148903250694275,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1319,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 0.6994309425354004,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.1242,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 1.0713452100753784,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.1354,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.23827064037323,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.1553,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.3071824312210083,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1598,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.4454975128173828,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.1878,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 0.9927931427955627,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1571,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.0181673765182495,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1463,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.098183035850525,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1284,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 0.9349597096443176,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1265,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 0.7482240796089172,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.116,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 1.1793172359466553,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1282,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 0.657133936882019,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.1501,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 0.6432955861091614,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1354,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 0.861251711845398,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.1439,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.8403468728065491,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.1326,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 0.5765302181243896,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.0974,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.6433290243148804,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1325,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.6270760297775269,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1208,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.1694698333740234,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1089,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 1.1193510293960571,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.1458,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 1.203051209449768,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1296,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 0.6728342175483704,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.114,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.1375242471694946,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1383,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 0.5893566012382507,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.1291,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 0.8352311849594116,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1479,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 0.634758710861206,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.1153,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.1101970672607422,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1522,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 0.8607526421546936,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1333,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 0.8799166083335876,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1111,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 0.9858982563018799,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1345,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 0.8103428483009338,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1425,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.104451060295105,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1332,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 0.788467288017273,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1167,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 1.0944404602050781,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1305,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.3954204320907593,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1264,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.0658373832702637,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1196,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.1783170700073242,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1359,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 0.7922008633613586,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1214,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 0.68011075258255,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1298,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 0.8950837254524231,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1106,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 0.6562188863754272,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1087,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.1354018449783325,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1348,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 0.6269157528877258,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1287,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "step": 939,
+      "total_flos": 1.4737480102602342e+17,
+      "train_loss": 0.4462493950058731,
+      "train_runtime": 438.8238,
+      "train_samples_per_second": 68.365,
+      "train_steps_per_second": 2.14
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4737480102602342e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: other
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the gsm8k__llama3_8b_instruct__n5000_t1t2_s0_all_variants_r8_bs4_lr1e5_e3_f_lora_sft dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja

@@ -0,0 +1,5 @@
+{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

gsm8k__llama3_8b_instruct__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json

@@ -0,0 +1,2076 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}

gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json

@@ -0,0 +1,685 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 35.79402542114258,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 7.3919,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 36.77469253540039,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 7.0359,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 40.99972152709961,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 6.9921,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 49.52562713623047,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 6.5551,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 59.437801361083984,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 5.3668,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 10.833108901977539,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 2.6404,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 9.128503799438477,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 1.866,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 9.038158416748047,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 1.4561,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.0058175325393677,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.5983,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 0.7958039045333862,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.3144,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 0.9172451496124268,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.3144,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.4298181533813477,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.289,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 1.4510711431503296,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.2795,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.142468810081482,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.2769,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 0.9017572999000549,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.2694,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 1.0272343158721924,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.2392,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 1.8809442520141602,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.2475,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 1.6700209379196167,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.2578,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.370553970336914,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.226,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 1.4001033306121826,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.2596,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.3764418363571167,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.2192,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.9179826974868774,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.2033,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.1372401714324951,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.2089,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 1.5574877262115479,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.2463,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.3536542654037476,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.2278,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.0997065305709839,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.2214,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.4929256439208984,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.2174,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 2.4552018642425537,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.2152,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.2356972694396973,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.2211,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.7548859119415283,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.2197,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 0.9072297215461731,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.2139,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 1.63068425655365,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.1859,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 1.5345515012741089,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1856,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 2.2955808639526367,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.1882,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 1.3718390464782715,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.1766,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 1.113899827003479,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1704,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 1.1651688814163208,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1779,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.719167947769165,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1777,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 1.2484666109085083,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1774,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 1.3962974548339844,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1927,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.5849448442459106,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1914,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 1.8310660123825073,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1673,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 1.3905104398727417,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1536,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.9447040557861328,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1573,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 1.4818346500396729,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1603,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.1600804328918457,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1551,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 2.9012856483459473,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1754,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.0623652935028076,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1628,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 1.3735458850860596,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.1531,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.697476863861084,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1569,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 1.541796088218689,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.1783,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 1.4641832113265991,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.1777,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 1.3036147356033325,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.1623,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.5076384544372559,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.151,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.6333284378051758,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.1369,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 2.0575339794158936,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.169,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.734142541885376,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1433,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.332359790802002,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1449,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 1.586766242980957,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.19,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 2.4383113384246826,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.1578,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 2.4130022525787354,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.156,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 1.2345256805419922,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.1504,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 1.9932875633239746,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1455,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 1.835963487625122,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.1204,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.755791425704956,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.1178,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 2.678736925125122,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.1404,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 2.085559844970703,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1202,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.4684470891952515,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1341,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.6354056596755981,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1428,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 1.114701271057129,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.1539,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 1.5211584568023682,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1028,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 2.1317594051361084,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.1218,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.4380273818969727,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1126,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 2.2737293243408203,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.1325,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 1.8511089086532593,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1391,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 2.697937488555908,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.1557,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 2.199148178100586,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1446,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 2.242133378982544,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1247,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 1.9420392513275146,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1495,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 1.448190450668335,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1485,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 1.655364990234375,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1135,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.7582699060440063,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.113,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 1.6522595882415771,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1302,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 2.7253308296203613,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1237,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.4822920560836792,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.118,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.5610301494598389,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1209,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.367651104927063,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1368,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 1.8491425514221191,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1472,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 2.327012300491333,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.131,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 1.0758401155471802,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1458,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 1.7079511880874634,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1283,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 2.184250831604004,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1409,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 2.2639594078063965,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1349,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6306592117253734e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

gsm8k__qwen3_8b__all_variants_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.308634334766039e+17,
+    "train_loss": 0.5363643305243267,
+    "train_runtime": 511.0643,
+    "train_samples_per_second": 58.701,
+    "train_steps_per_second": 1.837
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/checkpoint-939/trainer_state.json

@@ -0,0 +1,685 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 36.410274505615234,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 7.1209,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 37.63100814819336,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 7.2267,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 41.07283401489258,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 6.5,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 51.47338104248047,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 6.3324,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 60.280338287353516,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 4.6183,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 8.116122245788574,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 1.6932,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 9.122518539428711,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 1.3005,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 5.51691198348999,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 0.8908,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.3988447189331055,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.4659,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 1.105976939201355,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.297,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 2.0398294925689697,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.2801,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.383219599723816,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.2822,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 1.2371200323104858,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.2579,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.1922509670257568,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.2709,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 1.0999534130096436,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.2366,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 1.537858009338379,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.2469,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 1.8496414422988892,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.2415,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 2.05474853515625,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.2319,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.7304996252059937,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.2219,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 2.3161749839782715,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.2455,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.0786621570587158,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1984,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.7829115390777588,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.2247,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.377816081047058,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.216,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 1.7096017599105835,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.2329,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.0227816104888916,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.2069,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.6906803846359253,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.2306,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.5907845497131348,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.2121,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.287027359008789,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1957,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.7103077173233032,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.2115,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.0848621129989624,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1916,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 0.9332998991012573,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.2101,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 1.788713812828064,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.2052,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 1.7265129089355469,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1794,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 2.1850712299346924,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.1782,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 2.2435545921325684,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.2045,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.9983278512954712,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1723,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 2.049156427383423,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1585,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.4727146625518799,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1923,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 1.0040885210037231,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1571,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 2.1113643646240234,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1873,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.9584604501724243,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1567,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 1.1953130960464478,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1791,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 0.9742574691772461,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1375,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.4377895593643188,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1597,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 2.0562143325805664,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1457,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.3355144262313843,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1602,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 2.0422887802124023,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1629,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.4472697973251343,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1725,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 2.439272403717041,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.158,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.484682321548462,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1409,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 1.997353196144104,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.15,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 2.168736457824707,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.156,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 2.148578643798828,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.151,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.6990174055099487,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1351,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.0067726373672485,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.143,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 1.456082820892334,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1553,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.8530573844909668,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1478,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.2424077987670898,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1494,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 2.3341331481933594,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1635,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 2.3153064250946045,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.1421,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 2.261147975921631,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1602,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 1.7530509233474731,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.138,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 1.6593139171600342,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1544,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 1.8170461654663086,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.115,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.9878774285316467,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.131,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 1.4698379039764404,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.1357,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.6788400411605835,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1331,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.5114609003067017,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1268,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.3070710897445679,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1268,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 3.3000214099884033,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.123,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 2.6892614364624023,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1033,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 1.186232566833496,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.1367,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.3642523288726807,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1111,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 1.6318737268447876,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.1358,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 2.2662744522094727,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1434,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 1.9114540815353394,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.1702,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.686519742012024,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1262,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 2.728212833404541,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1267,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 1.376016616821289,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1193,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 1.355202555656433,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1362,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 1.6334112882614136,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1186,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.3374873399734497,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1233,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 2.329509735107422,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1339,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 1.7785120010375977,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1163,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.338930368423462,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1277,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.281558632850647,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1218,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.581589937210083,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1299,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 1.4902228116989136,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1164,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 2.3329508304595947,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1189,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 1.161344051361084,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1175,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 1.952156901359558,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1217,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.557270884513855,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1239,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 1.0891914367675781,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1458,
+      "step": 930
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.308634334766039e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.308634334766039e+17,
+    "train_loss": 0.5363643305243267,
+    "train_runtime": 511.0643,
+    "train_samples_per_second": 58.701,
+    "train_steps_per_second": 1.837
+}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_log.jsonl

@@ -0,0 +1,94 @@
+{"current_steps": 10, "total_steps": 939, "loss": 7.1209, "lr": 9.574468085106384e-07, "epoch": 0.03194888178913738, "percentage": 1.06, "elapsed_time": "0:00:05", "remaining_time": "0:09:15"}
+{"current_steps": 20, "total_steps": 939, "loss": 7.2267, "lr": 2.021276595744681e-06, "epoch": 0.06389776357827476, "percentage": 2.13, "elapsed_time": "0:00:11", "remaining_time": "0:08:38"}
+{"current_steps": 30, "total_steps": 939, "loss": 6.5, "lr": 3.0851063829787237e-06, "epoch": 0.09584664536741214, "percentage": 3.19, "elapsed_time": "0:00:16", "remaining_time": "0:08:24"}
+{"current_steps": 40, "total_steps": 939, "loss": 6.3324, "lr": 4.148936170212766e-06, "epoch": 0.12779552715654952, "percentage": 4.26, "elapsed_time": "0:00:21", "remaining_time": "0:08:12"}
+{"current_steps": 50, "total_steps": 939, "loss": 4.6183, "lr": 5.212765957446809e-06, "epoch": 0.1597444089456869, "percentage": 5.32, "elapsed_time": "0:00:27", "remaining_time": "0:08:05"}
+{"current_steps": 60, "total_steps": 939, "loss": 1.6932, "lr": 6.276595744680851e-06, "epoch": 0.19169329073482427, "percentage": 6.39, "elapsed_time": "0:00:32", "remaining_time": "0:07:56"}
+{"current_steps": 70, "total_steps": 939, "loss": 1.3005, "lr": 7.340425531914894e-06, "epoch": 0.22364217252396165, "percentage": 7.45, "elapsed_time": "0:00:37", "remaining_time": "0:07:50"}
+{"current_steps": 80, "total_steps": 939, "loss": 0.8908, "lr": 8.404255319148937e-06, "epoch": 0.25559105431309903, "percentage": 8.52, "elapsed_time": "0:00:42", "remaining_time": "0:07:41"}
+{"current_steps": 90, "total_steps": 939, "loss": 0.4659, "lr": 9.46808510638298e-06, "epoch": 0.28753993610223644, "percentage": 9.58, "elapsed_time": "0:00:48", "remaining_time": "0:07:34"}
+{"current_steps": 100, "total_steps": 939, "loss": 0.297, "lr": 9.999136119166803e-06, "epoch": 0.3194888178913738, "percentage": 10.65, "elapsed_time": "0:00:53", "remaining_time": "0:07:28"}
+{"current_steps": 110, "total_steps": 939, "loss": 0.2801, "lr": 9.9922268634943e-06, "epoch": 0.3514376996805112, "percentage": 11.71, "elapsed_time": "0:00:58", "remaining_time": "0:07:22"}
+{"current_steps": 120, "total_steps": 939, "loss": 0.2822, "lr": 9.978417901361958e-06, "epoch": 0.38338658146964855, "percentage": 12.78, "elapsed_time": "0:01:03", "remaining_time": "0:07:15"}
+{"current_steps": 130, "total_steps": 939, "loss": 0.2579, "lr": 9.95772831799724e-06, "epoch": 0.41533546325878595, "percentage": 13.84, "elapsed_time": "0:01:09", "remaining_time": "0:07:10"}
+{"current_steps": 140, "total_steps": 939, "loss": 0.2709, "lr": 9.930186708264902e-06, "epoch": 0.4472843450479233, "percentage": 14.91, "elapsed_time": "0:01:14", "remaining_time": "0:07:05"}
+{"current_steps": 150, "total_steps": 939, "loss": 0.2366, "lr": 9.895831137146319e-06, "epoch": 0.4792332268370607, "percentage": 15.97, "elapsed_time": "0:01:19", "remaining_time": "0:06:58"}
+{"current_steps": 160, "total_steps": 939, "loss": 0.2469, "lr": 9.854709087130261e-06, "epoch": 0.5111821086261981, "percentage": 17.04, "elapsed_time": "0:01:24", "remaining_time": "0:06:52"}
+{"current_steps": 170, "total_steps": 939, "loss": 0.2415, "lr": 9.80687739258782e-06, "epoch": 0.5431309904153354, "percentage": 18.1, "elapsed_time": "0:01:29", "remaining_time": "0:06:47"}
+{"current_steps": 180, "total_steps": 939, "loss": 0.2319, "lr": 9.7524021612222e-06, "epoch": 0.5750798722044729, "percentage": 19.17, "elapsed_time": "0:01:35", "remaining_time": "0:06:42"}
+{"current_steps": 190, "total_steps": 939, "loss": 0.2219, "lr": 9.691358682701927e-06, "epoch": 0.6070287539936102, "percentage": 20.23, "elapsed_time": "0:01:40", "remaining_time": "0:06:36"}
+{"current_steps": 200, "total_steps": 939, "loss": 0.2455, "lr": 9.623831324603755e-06, "epoch": 0.6389776357827476, "percentage": 21.3, "elapsed_time": "0:01:45", "remaining_time": "0:06:31"}
+{"current_steps": 210, "total_steps": 939, "loss": 0.1984, "lr": 9.549913415809084e-06, "epoch": 0.670926517571885, "percentage": 22.36, "elapsed_time": "0:01:51", "remaining_time": "0:06:26"}
+{"current_steps": 220, "total_steps": 939, "loss": 0.2247, "lr": 9.469707117515068e-06, "epoch": 0.7028753993610224, "percentage": 23.43, "elapsed_time": "0:01:56", "remaining_time": "0:06:20"}
+{"current_steps": 230, "total_steps": 939, "loss": 0.216, "lr": 9.383323282038632e-06, "epoch": 0.7348242811501597, "percentage": 24.49, "elapsed_time": "0:02:01", "remaining_time": "0:06:14"}
+{"current_steps": 240, "total_steps": 939, "loss": 0.2329, "lr": 9.29088129960862e-06, "epoch": 0.7667731629392971, "percentage": 25.56, "elapsed_time": "0:02:06", "remaining_time": "0:06:09"}
+{"current_steps": 250, "total_steps": 939, "loss": 0.2069, "lr": 9.192508933357753e-06, "epoch": 0.7987220447284346, "percentage": 26.62, "elapsed_time": "0:02:12", "remaining_time": "0:06:03"}
+{"current_steps": 260, "total_steps": 939, "loss": 0.2306, "lr": 9.088342142742493e-06, "epoch": 0.8306709265175719, "percentage": 27.69, "elapsed_time": "0:02:17", "remaining_time": "0:05:58"}
+{"current_steps": 270, "total_steps": 939, "loss": 0.2121, "lr": 8.978524895634842e-06, "epoch": 0.8626198083067093, "percentage": 28.75, "elapsed_time": "0:02:22", "remaining_time": "0:05:52"}
+{"current_steps": 280, "total_steps": 939, "loss": 0.1957, "lr": 8.86320896934581e-06, "epoch": 0.8945686900958466, "percentage": 29.82, "elapsed_time": "0:02:27", "remaining_time": "0:05:47"}
+{"current_steps": 290, "total_steps": 939, "loss": 0.2115, "lr": 8.742553740855507e-06, "epoch": 0.9265175718849841, "percentage": 30.88, "elapsed_time": "0:02:32", "remaining_time": "0:05:41"}
+{"current_steps": 300, "total_steps": 939, "loss": 0.1916, "lr": 8.616725966539831e-06, "epoch": 0.9584664536741214, "percentage": 31.95, "elapsed_time": "0:02:37", "remaining_time": "0:05:36"}
+{"current_steps": 310, "total_steps": 939, "loss": 0.2101, "lr": 8.485899551698166e-06, "epoch": 0.9904153354632588, "percentage": 33.01, "elapsed_time": "0:02:43", "remaining_time": "0:05:31"}
+{"current_steps": 320, "total_steps": 939, "loss": 0.2052, "lr": 8.350255310200611e-06, "epoch": 1.0223642172523961, "percentage": 34.08, "elapsed_time": "0:02:48", "remaining_time": "0:05:26"}
+{"current_steps": 330, "total_steps": 939, "loss": 0.1794, "lr": 8.209980714586955e-06, "epoch": 1.0543130990415335, "percentage": 35.14, "elapsed_time": "0:02:54", "remaining_time": "0:05:21"}
+{"current_steps": 340, "total_steps": 939, "loss": 0.1782, "lr": 8.065269636962765e-06, "epoch": 1.0862619808306708, "percentage": 36.21, "elapsed_time": "0:02:59", "remaining_time": "0:05:16"}
+{"current_steps": 350, "total_steps": 939, "loss": 0.2045, "lr": 7.916322081050708e-06, "epoch": 1.1182108626198084, "percentage": 37.27, "elapsed_time": "0:03:04", "remaining_time": "0:05:10"}
+{"current_steps": 360, "total_steps": 939, "loss": 0.1723, "lr": 7.76334390576742e-06, "epoch": 1.1501597444089458, "percentage": 38.34, "elapsed_time": "0:03:09", "remaining_time": "0:05:05"}
+{"current_steps": 370, "total_steps": 939, "loss": 0.1585, "lr": 7.60654654070796e-06, "epoch": 1.182108626198083, "percentage": 39.4, "elapsed_time": "0:03:14", "remaining_time": "0:04:59"}
+{"current_steps": 380, "total_steps": 939, "loss": 0.1923, "lr": 7.446146693931111e-06, "epoch": 1.2140575079872205, "percentage": 40.47, "elapsed_time": "0:03:20", "remaining_time": "0:04:54"}
+{"current_steps": 390, "total_steps": 939, "loss": 0.1571, "lr": 7.282366052449351e-06, "epoch": 1.2460063897763578, "percentage": 41.53, "elapsed_time": "0:03:25", "remaining_time": "0:04:48"}
+{"current_steps": 400, "total_steps": 939, "loss": 0.1873, "lr": 7.115430975837457e-06, "epoch": 1.2779552715654952, "percentage": 42.6, "elapsed_time": "0:03:30", "remaining_time": "0:04:43"}
+{"current_steps": 410, "total_steps": 939, "loss": 0.1567, "lr": 6.945572183383229e-06, "epoch": 1.3099041533546325, "percentage": 43.66, "elapsed_time": "0:03:35", "remaining_time": "0:04:38"}
+{"current_steps": 420, "total_steps": 939, "loss": 0.1791, "lr": 6.773024435212678e-06, "epoch": 1.34185303514377, "percentage": 44.73, "elapsed_time": "0:03:41", "remaining_time": "0:04:33"}
+{"current_steps": 430, "total_steps": 939, "loss": 0.1375, "lr": 6.598026207830428e-06, "epoch": 1.3738019169329074, "percentage": 45.79, "elapsed_time": "0:03:46", "remaining_time": "0:04:27"}
+{"current_steps": 440, "total_steps": 939, "loss": 0.1597, "lr": 6.4208193645237314e-06, "epoch": 1.4057507987220448, "percentage": 46.86, "elapsed_time": "0:03:51", "remaining_time": "0:04:22"}
+{"current_steps": 450, "total_steps": 939, "loss": 0.1457, "lr": 6.241648821085666e-06, "epoch": 1.4376996805111821, "percentage": 47.92, "elapsed_time": "0:03:56", "remaining_time": "0:04:17"}
+{"current_steps": 460, "total_steps": 939, "loss": 0.1602, "lr": 6.060762207319479e-06, "epoch": 1.4696485623003195, "percentage": 48.99, "elapsed_time": "0:04:02", "remaining_time": "0:04:12"}
+{"current_steps": 470, "total_steps": 939, "loss": 0.1629, "lr": 5.878409524791931e-06, "epoch": 1.5015974440894568, "percentage": 50.05, "elapsed_time": "0:04:07", "remaining_time": "0:04:06"}
+{"current_steps": 480, "total_steps": 939, "loss": 0.1725, "lr": 5.694842801308651e-06, "epoch": 1.5335463258785942, "percentage": 51.12, "elapsed_time": "0:04:12", "remaining_time": "0:04:01"}
+{"current_steps": 490, "total_steps": 939, "loss": 0.158, "lr": 5.510315742589042e-06, "epoch": 1.5654952076677318, "percentage": 52.18, "elapsed_time": "0:04:17", "remaining_time": "0:03:56"}
+{"current_steps": 500, "total_steps": 939, "loss": 0.1409, "lr": 5.325083381622165e-06, "epoch": 1.5974440894568689, "percentage": 53.25, "elapsed_time": "0:04:23", "remaining_time": "0:03:51"}
+{"current_steps": 510, "total_steps": 939, "loss": 0.15, "lr": 5.139401726188208e-06, "epoch": 1.6293929712460065, "percentage": 54.31, "elapsed_time": "0:04:28", "remaining_time": "0:03:45"}
+{"current_steps": 520, "total_steps": 939, "loss": 0.156, "lr": 4.953527405032723e-06, "epoch": 1.6613418530351438, "percentage": 55.38, "elapsed_time": "0:04:33", "remaining_time": "0:03:40"}
+{"current_steps": 530, "total_steps": 939, "loss": 0.151, "lr": 4.767717313182611e-06, "epoch": 1.6932907348242812, "percentage": 56.44, "elapsed_time": "0:04:38", "remaining_time": "0:03:35"}
+{"current_steps": 540, "total_steps": 939, "loss": 0.1351, "lr": 4.582228256894093e-06, "epoch": 1.7252396166134185, "percentage": 57.51, "elapsed_time": "0:04:44", "remaining_time": "0:03:30"}
+{"current_steps": 550, "total_steps": 939, "loss": 0.143, "lr": 4.397316598723385e-06, "epoch": 1.7571884984025559, "percentage": 58.57, "elapsed_time": "0:04:49", "remaining_time": "0:03:24"}
+{"current_steps": 560, "total_steps": 939, "loss": 0.1553, "lr": 4.2132379032105695e-06, "epoch": 1.7891373801916934, "percentage": 59.64, "elapsed_time": "0:04:54", "remaining_time": "0:03:19"}
+{"current_steps": 570, "total_steps": 939, "loss": 0.1478, "lr": 4.030246583666437e-06, "epoch": 1.8210862619808306, "percentage": 60.7, "elapsed_time": "0:05:00", "remaining_time": "0:03:14"}
+{"current_steps": 580, "total_steps": 939, "loss": 0.1494, "lr": 3.848595550550401e-06, "epoch": 1.8530351437699681, "percentage": 61.77, "elapsed_time": "0:05:05", "remaining_time": "0:03:09"}
+{"current_steps": 590, "total_steps": 939, "loss": 0.1635, "lr": 3.668535861925509e-06, "epoch": 1.8849840255591053, "percentage": 62.83, "elapsed_time": "0:05:11", "remaining_time": "0:03:03"}
+{"current_steps": 600, "total_steps": 939, "loss": 0.1421, "lr": 3.4903163764736104e-06, "epoch": 1.9169329073482428, "percentage": 63.9, "elapsed_time": "0:05:16", "remaining_time": "0:02:58"}
+{"current_steps": 610, "total_steps": 939, "loss": 0.1602, "lr": 3.314183409550293e-06, "epoch": 1.9488817891373802, "percentage": 64.96, "elapsed_time": "0:05:21", "remaining_time": "0:02:53"}
+{"current_steps": 620, "total_steps": 939, "loss": 0.138, "lr": 3.140380392754901e-06, "epoch": 1.9808306709265175, "percentage": 66.03, "elapsed_time": "0:05:27", "remaining_time": "0:02:48"}
+{"current_steps": 630, "total_steps": 939, "loss": 0.1544, "lr": 2.969147537486175e-06, "epoch": 2.012779552715655, "percentage": 67.09, "elapsed_time": "0:05:32", "remaining_time": "0:02:43"}
+{"current_steps": 640, "total_steps": 939, "loss": 0.115, "lr": 2.800721502948506e-06, "epoch": 2.0447284345047922, "percentage": 68.16, "elapsed_time": "0:05:37", "remaining_time": "0:02:37"}
+{"current_steps": 650, "total_steps": 939, "loss": 0.131, "lr": 2.635335069067617e-06, "epoch": 2.07667731629393, "percentage": 69.22, "elapsed_time": "0:05:43", "remaining_time": "0:02:32"}
+{"current_steps": 660, "total_steps": 939, "loss": 0.1357, "lr": 2.4732168147677927e-06, "epoch": 2.108626198083067, "percentage": 70.29, "elapsed_time": "0:05:48", "remaining_time": "0:02:27"}
+{"current_steps": 670, "total_steps": 939, "loss": 0.1331, "lr": 2.314590802055232e-06, "epoch": 2.1405750798722045, "percentage": 71.35, "elapsed_time": "0:05:53", "remaining_time": "0:02:21"}
+{"current_steps": 680, "total_steps": 939, "loss": 0.1268, "lr": 2.159676266344222e-06, "epoch": 2.1725239616613417, "percentage": 72.42, "elapsed_time": "0:05:58", "remaining_time": "0:02:16"}
+{"current_steps": 690, "total_steps": 939, "loss": 0.1268, "lr": 2.0086873134540626e-06, "epoch": 2.2044728434504792, "percentage": 73.48, "elapsed_time": "0:06:03", "remaining_time": "0:02:11"}
+{"current_steps": 700, "total_steps": 939, "loss": 0.123, "lr": 1.8618326236955908e-06, "epoch": 2.236421725239617, "percentage": 74.55, "elapsed_time": "0:06:09", "remaining_time": "0:02:06"}
+{"current_steps": 710, "total_steps": 939, "loss": 0.1033, "lr": 1.7193151634562071e-06, "epoch": 2.268370607028754, "percentage": 75.61, "elapsed_time": "0:06:14", "remaining_time": "0:02:00"}
+{"current_steps": 720, "total_steps": 939, "loss": 0.1367, "lr": 1.581331904682089e-06, "epoch": 2.3003194888178915, "percentage": 76.68, "elapsed_time": "0:06:19", "remaining_time": "0:01:55"}
+{"current_steps": 730, "total_steps": 939, "loss": 0.1111, "lr": 1.4480735526452427e-06, "epoch": 2.3322683706070286, "percentage": 77.74, "elapsed_time": "0:06:24", "remaining_time": "0:01:50"}
+{"current_steps": 740, "total_steps": 939, "loss": 0.1358, "lr": 1.319724282371664e-06, "epoch": 2.364217252396166, "percentage": 78.81, "elapsed_time": "0:06:29", "remaining_time": "0:01:44"}
+{"current_steps": 750, "total_steps": 939, "loss": 0.1434, "lr": 1.1964614840949002e-06, "epoch": 2.3961661341853033, "percentage": 79.87, "elapsed_time": "0:06:34", "remaining_time": "0:01:39"}
+{"current_steps": 760, "total_steps": 939, "loss": 0.1702, "lr": 1.078455518086784e-06, "epoch": 2.428115015974441, "percentage": 80.94, "elapsed_time": "0:06:40", "remaining_time": "0:01:34"}
+{"current_steps": 770, "total_steps": 939, "loss": 0.1262, "lr": 9.658694792042284e-07, "epoch": 2.460063897763578, "percentage": 82.0, "elapsed_time": "0:06:45", "remaining_time": "0:01:29"}
+{"current_steps": 780, "total_steps": 939, "loss": 0.1267, "lr": 8.58858971477457e-07, "epoch": 2.4920127795527156, "percentage": 83.07, "elapsed_time": "0:06:51", "remaining_time": "0:01:23"}
+{"current_steps": 790, "total_steps": 939, "loss": 0.1193, "lr": 7.575718930512516e-07, "epoch": 2.523961661341853, "percentage": 84.13, "elapsed_time": "0:06:56", "remaining_time": "0:01:18"}
+{"current_steps": 800, "total_steps": 939, "loss": 0.1362, "lr": 6.621482317764105e-07, "epoch": 2.5559105431309903, "percentage": 85.2, "elapsed_time": "0:07:01", "remaining_time": "0:01:13"}
+{"current_steps": 810, "total_steps": 939, "loss": 0.1186, "lr": 5.727198717339511e-07, "epoch": 2.587859424920128, "percentage": 86.26, "elapsed_time": "0:07:06", "remaining_time": "0:01:07"}
+{"current_steps": 820, "total_steps": 939, "loss": 0.1233, "lr": 4.894104109594466e-07, "epoch": 2.619808306709265, "percentage": 87.33, "elapsed_time": "0:07:11", "remaining_time": "0:01:02"}
+{"current_steps": 830, "total_steps": 939, "loss": 0.1339, "lr": 4.123349906194357e-07, "epoch": 2.6517571884984026, "percentage": 88.39, "elapsed_time": "0:07:17", "remaining_time": "0:00:57"}
+{"current_steps": 840, "total_steps": 939, "loss": 0.1163, "lr": 3.416001358759635e-07, "epoch": 2.68370607028754, "percentage": 89.46, "elapsed_time": "0:07:23", "remaining_time": "0:00:52"}
+{"current_steps": 850, "total_steps": 939, "loss": 0.1277, "lr": 2.7730360865923954e-07, "epoch": 2.7156549520766773, "percentage": 90.52, "elapsed_time": "0:07:28", "remaining_time": "0:00:46"}
+{"current_steps": 860, "total_steps": 939, "loss": 0.1218, "lr": 2.1953427255185122e-07, "epoch": 2.747603833865815, "percentage": 91.59, "elapsed_time": "0:07:33", "remaining_time": "0:00:41"}
+{"current_steps": 870, "total_steps": 939, "loss": 0.1299, "lr": 1.6837196997130434e-07, "epoch": 2.779552715654952, "percentage": 92.65, "elapsed_time": "0:07:38", "remaining_time": "0:00:36"}
+{"current_steps": 880, "total_steps": 939, "loss": 0.1164, "lr": 1.2388741182062348e-07, "epoch": 2.8115015974440896, "percentage": 93.72, "elapsed_time": "0:07:43", "remaining_time": "0:00:31"}
+{"current_steps": 890, "total_steps": 939, "loss": 0.1189, "lr": 8.614207975952083e-08, "epoch": 2.8434504792332267, "percentage": 94.78, "elapsed_time": "0:07:49", "remaining_time": "0:00:25"}
+{"current_steps": 900, "total_steps": 939, "loss": 0.1175, "lr": 5.518814123121885e-08, "epoch": 2.8753993610223643, "percentage": 95.85, "elapsed_time": "0:07:54", "remaining_time": "0:00:20"}
+{"current_steps": 910, "total_steps": 939, "loss": 0.1217, "lr": 3.10683773623488e-08, "epoch": 2.9073482428115014, "percentage": 96.91, "elapsed_time": "0:07:59", "remaining_time": "0:00:15"}
+{"current_steps": 920, "total_steps": 939, "loss": 0.1239, "lr": 1.3816123835588835e-08, "epoch": 2.939297124600639, "percentage": 97.98, "elapsed_time": "0:08:05", "remaining_time": "0:00:10"}
+{"current_steps": 930, "total_steps": 939, "loss": 0.1458, "lr": 3.4552248167507576e-09, "epoch": 2.9712460063897765, "percentage": 99.04, "elapsed_time": "0:08:10", "remaining_time": "0:00:04"}
+{"current_steps": 939, "total_steps": 939, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:08:16", "remaining_time": "0:00:00"}

gsm8k__qwen3_8b__bare_100_r8_bs4_lr1e5_e3/lora/sft/trainer_state.json

@@ -0,0 +1,694 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03194888178913738,
+      "grad_norm": 36.410274505615234,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 7.1209,
+      "step": 10
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 37.63100814819336,
+      "learning_rate": 2.021276595744681e-06,
+      "loss": 7.2267,
+      "step": 20
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 41.07283401489258,
+      "learning_rate": 3.0851063829787237e-06,
+      "loss": 6.5,
+      "step": 30
+    },
+    {
+      "epoch": 0.12779552715654952,
+      "grad_norm": 51.47338104248047,
+      "learning_rate": 4.148936170212766e-06,
+      "loss": 6.3324,
+      "step": 40
+    },
+    {
+      "epoch": 0.1597444089456869,
+      "grad_norm": 60.280338287353516,
+      "learning_rate": 5.212765957446809e-06,
+      "loss": 4.6183,
+      "step": 50
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 8.116122245788574,
+      "learning_rate": 6.276595744680851e-06,
+      "loss": 1.6932,
+      "step": 60
+    },
+    {
+      "epoch": 0.22364217252396165,
+      "grad_norm": 9.122518539428711,
+      "learning_rate": 7.340425531914894e-06,
+      "loss": 1.3005,
+      "step": 70
+    },
+    {
+      "epoch": 0.25559105431309903,
+      "grad_norm": 5.51691198348999,
+      "learning_rate": 8.404255319148937e-06,
+      "loss": 0.8908,
+      "step": 80
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 1.3988447189331055,
+      "learning_rate": 9.46808510638298e-06,
+      "loss": 0.4659,
+      "step": 90
+    },
+    {
+      "epoch": 0.3194888178913738,
+      "grad_norm": 1.105976939201355,
+      "learning_rate": 9.999136119166803e-06,
+      "loss": 0.297,
+      "step": 100
+    },
+    {
+      "epoch": 0.3514376996805112,
+      "grad_norm": 2.0398294925689697,
+      "learning_rate": 9.9922268634943e-06,
+      "loss": 0.2801,
+      "step": 110
+    },
+    {
+      "epoch": 0.38338658146964855,
+      "grad_norm": 1.383219599723816,
+      "learning_rate": 9.978417901361958e-06,
+      "loss": 0.2822,
+      "step": 120
+    },
+    {
+      "epoch": 0.41533546325878595,
+      "grad_norm": 1.2371200323104858,
+      "learning_rate": 9.95772831799724e-06,
+      "loss": 0.2579,
+      "step": 130
+    },
+    {
+      "epoch": 0.4472843450479233,
+      "grad_norm": 1.1922509670257568,
+      "learning_rate": 9.930186708264902e-06,
+      "loss": 0.2709,
+      "step": 140
+    },
+    {
+      "epoch": 0.4792332268370607,
+      "grad_norm": 1.0999534130096436,
+      "learning_rate": 9.895831137146319e-06,
+      "loss": 0.2366,
+      "step": 150
+    },
+    {
+      "epoch": 0.5111821086261981,
+      "grad_norm": 1.537858009338379,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.2469,
+      "step": 160
+    },
+    {
+      "epoch": 0.5431309904153354,
+      "grad_norm": 1.8496414422988892,
+      "learning_rate": 9.80687739258782e-06,
+      "loss": 0.2415,
+      "step": 170
+    },
+    {
+      "epoch": 0.5750798722044729,
+      "grad_norm": 2.05474853515625,
+      "learning_rate": 9.7524021612222e-06,
+      "loss": 0.2319,
+      "step": 180
+    },
+    {
+      "epoch": 0.6070287539936102,
+      "grad_norm": 1.7304996252059937,
+      "learning_rate": 9.691358682701927e-06,
+      "loss": 0.2219,
+      "step": 190
+    },
+    {
+      "epoch": 0.6389776357827476,
+      "grad_norm": 2.3161749839782715,
+      "learning_rate": 9.623831324603755e-06,
+      "loss": 0.2455,
+      "step": 200
+    },
+    {
+      "epoch": 0.670926517571885,
+      "grad_norm": 1.0786621570587158,
+      "learning_rate": 9.549913415809084e-06,
+      "loss": 0.1984,
+      "step": 210
+    },
+    {
+      "epoch": 0.7028753993610224,
+      "grad_norm": 1.7829115390777588,
+      "learning_rate": 9.469707117515068e-06,
+      "loss": 0.2247,
+      "step": 220
+    },
+    {
+      "epoch": 0.7348242811501597,
+      "grad_norm": 1.377816081047058,
+      "learning_rate": 9.383323282038632e-06,
+      "loss": 0.216,
+      "step": 230
+    },
+    {
+      "epoch": 0.7667731629392971,
+      "grad_norm": 1.7096017599105835,
+      "learning_rate": 9.29088129960862e-06,
+      "loss": 0.2329,
+      "step": 240
+    },
+    {
+      "epoch": 0.7987220447284346,
+      "grad_norm": 1.0227816104888916,
+      "learning_rate": 9.192508933357753e-06,
+      "loss": 0.2069,
+      "step": 250
+    },
+    {
+      "epoch": 0.8306709265175719,
+      "grad_norm": 1.6906803846359253,
+      "learning_rate": 9.088342142742493e-06,
+      "loss": 0.2306,
+      "step": 260
+    },
+    {
+      "epoch": 0.8626198083067093,
+      "grad_norm": 1.5907845497131348,
+      "learning_rate": 8.978524895634842e-06,
+      "loss": 0.2121,
+      "step": 270
+    },
+    {
+      "epoch": 0.8945686900958466,
+      "grad_norm": 1.287027359008789,
+      "learning_rate": 8.86320896934581e-06,
+      "loss": 0.1957,
+      "step": 280
+    },
+    {
+      "epoch": 0.9265175718849841,
+      "grad_norm": 1.7103077173233032,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.2115,
+      "step": 290
+    },
+    {
+      "epoch": 0.9584664536741214,
+      "grad_norm": 1.0848621129989624,
+      "learning_rate": 8.616725966539831e-06,
+      "loss": 0.1916,
+      "step": 300
+    },
+    {
+      "epoch": 0.9904153354632588,
+      "grad_norm": 0.9332998991012573,
+      "learning_rate": 8.485899551698166e-06,
+      "loss": 0.2101,
+      "step": 310
+    },
+    {
+      "epoch": 1.0223642172523961,
+      "grad_norm": 1.788713812828064,
+      "learning_rate": 8.350255310200611e-06,
+      "loss": 0.2052,
+      "step": 320
+    },
+    {
+      "epoch": 1.0543130990415335,
+      "grad_norm": 1.7265129089355469,
+      "learning_rate": 8.209980714586955e-06,
+      "loss": 0.1794,
+      "step": 330
+    },
+    {
+      "epoch": 1.0862619808306708,
+      "grad_norm": 2.1850712299346924,
+      "learning_rate": 8.065269636962765e-06,
+      "loss": 0.1782,
+      "step": 340
+    },
+    {
+      "epoch": 1.1182108626198084,
+      "grad_norm": 2.2435545921325684,
+      "learning_rate": 7.916322081050708e-06,
+      "loss": 0.2045,
+      "step": 350
+    },
+    {
+      "epoch": 1.1501597444089458,
+      "grad_norm": 0.9983278512954712,
+      "learning_rate": 7.76334390576742e-06,
+      "loss": 0.1723,
+      "step": 360
+    },
+    {
+      "epoch": 1.182108626198083,
+      "grad_norm": 2.049156427383423,
+      "learning_rate": 7.60654654070796e-06,
+      "loss": 0.1585,
+      "step": 370
+    },
+    {
+      "epoch": 1.2140575079872205,
+      "grad_norm": 1.4727146625518799,
+      "learning_rate": 7.446146693931111e-06,
+      "loss": 0.1923,
+      "step": 380
+    },
+    {
+      "epoch": 1.2460063897763578,
+      "grad_norm": 1.0040885210037231,
+      "learning_rate": 7.282366052449351e-06,
+      "loss": 0.1571,
+      "step": 390
+    },
+    {
+      "epoch": 1.2779552715654952,
+      "grad_norm": 2.1113643646240234,
+      "learning_rate": 7.115430975837457e-06,
+      "loss": 0.1873,
+      "step": 400
+    },
+    {
+      "epoch": 1.3099041533546325,
+      "grad_norm": 1.9584604501724243,
+      "learning_rate": 6.945572183383229e-06,
+      "loss": 0.1567,
+      "step": 410
+    },
+    {
+      "epoch": 1.34185303514377,
+      "grad_norm": 1.1953130960464478,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.1791,
+      "step": 420
+    },
+    {
+      "epoch": 1.3738019169329074,
+      "grad_norm": 0.9742574691772461,
+      "learning_rate": 6.598026207830428e-06,
+      "loss": 0.1375,
+      "step": 430
+    },
+    {
+      "epoch": 1.4057507987220448,
+      "grad_norm": 1.4377895593643188,
+      "learning_rate": 6.4208193645237314e-06,
+      "loss": 0.1597,
+      "step": 440
+    },
+    {
+      "epoch": 1.4376996805111821,
+      "grad_norm": 2.0562143325805664,
+      "learning_rate": 6.241648821085666e-06,
+      "loss": 0.1457,
+      "step": 450
+    },
+    {
+      "epoch": 1.4696485623003195,
+      "grad_norm": 1.3355144262313843,
+      "learning_rate": 6.060762207319479e-06,
+      "loss": 0.1602,
+      "step": 460
+    },
+    {
+      "epoch": 1.5015974440894568,
+      "grad_norm": 2.0422887802124023,
+      "learning_rate": 5.878409524791931e-06,
+      "loss": 0.1629,
+      "step": 470
+    },
+    {
+      "epoch": 1.5335463258785942,
+      "grad_norm": 1.4472697973251343,
+      "learning_rate": 5.694842801308651e-06,
+      "loss": 0.1725,
+      "step": 480
+    },
+    {
+      "epoch": 1.5654952076677318,
+      "grad_norm": 2.439272403717041,
+      "learning_rate": 5.510315742589042e-06,
+      "loss": 0.158,
+      "step": 490
+    },
+    {
+      "epoch": 1.5974440894568689,
+      "grad_norm": 1.484682321548462,
+      "learning_rate": 5.325083381622165e-06,
+      "loss": 0.1409,
+      "step": 500
+    },
+    {
+      "epoch": 1.6293929712460065,
+      "grad_norm": 1.997353196144104,
+      "learning_rate": 5.139401726188208e-06,
+      "loss": 0.15,
+      "step": 510
+    },
+    {
+      "epoch": 1.6613418530351438,
+      "grad_norm": 2.168736457824707,
+      "learning_rate": 4.953527405032723e-06,
+      "loss": 0.156,
+      "step": 520
+    },
+    {
+      "epoch": 1.6932907348242812,
+      "grad_norm": 2.148578643798828,
+      "learning_rate": 4.767717313182611e-06,
+      "loss": 0.151,
+      "step": 530
+    },
+    {
+      "epoch": 1.7252396166134185,
+      "grad_norm": 1.6990174055099487,
+      "learning_rate": 4.582228256894093e-06,
+      "loss": 0.1351,
+      "step": 540
+    },
+    {
+      "epoch": 1.7571884984025559,
+      "grad_norm": 1.0067726373672485,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.143,
+      "step": 550
+    },
+    {
+      "epoch": 1.7891373801916934,
+      "grad_norm": 1.456082820892334,
+      "learning_rate": 4.2132379032105695e-06,
+      "loss": 0.1553,
+      "step": 560
+    },
+    {
+      "epoch": 1.8210862619808306,
+      "grad_norm": 1.8530573844909668,
+      "learning_rate": 4.030246583666437e-06,
+      "loss": 0.1478,
+      "step": 570
+    },
+    {
+      "epoch": 1.8530351437699681,
+      "grad_norm": 1.2424077987670898,
+      "learning_rate": 3.848595550550401e-06,
+      "loss": 0.1494,
+      "step": 580
+    },
+    {
+      "epoch": 1.8849840255591053,
+      "grad_norm": 2.3341331481933594,
+      "learning_rate": 3.668535861925509e-06,
+      "loss": 0.1635,
+      "step": 590
+    },
+    {
+      "epoch": 1.9169329073482428,
+      "grad_norm": 2.3153064250946045,
+      "learning_rate": 3.4903163764736104e-06,
+      "loss": 0.1421,
+      "step": 600
+    },
+    {
+      "epoch": 1.9488817891373802,
+      "grad_norm": 2.261147975921631,
+      "learning_rate": 3.314183409550293e-06,
+      "loss": 0.1602,
+      "step": 610
+    },
+    {
+      "epoch": 1.9808306709265175,
+      "grad_norm": 1.7530509233474731,
+      "learning_rate": 3.140380392754901e-06,
+      "loss": 0.138,
+      "step": 620
+    },
+    {
+      "epoch": 2.012779552715655,
+      "grad_norm": 1.6593139171600342,
+      "learning_rate": 2.969147537486175e-06,
+      "loss": 0.1544,
+      "step": 630
+    },
+    {
+      "epoch": 2.0447284345047922,
+      "grad_norm": 1.8170461654663086,
+      "learning_rate": 2.800721502948506e-06,
+      "loss": 0.115,
+      "step": 640
+    },
+    {
+      "epoch": 2.07667731629393,
+      "grad_norm": 0.9878774285316467,
+      "learning_rate": 2.635335069067617e-06,
+      "loss": 0.131,
+      "step": 650
+    },
+    {
+      "epoch": 2.108626198083067,
+      "grad_norm": 1.4698379039764404,
+      "learning_rate": 2.4732168147677927e-06,
+      "loss": 0.1357,
+      "step": 660
+    },
+    {
+      "epoch": 2.1405750798722045,
+      "grad_norm": 1.6788400411605835,
+      "learning_rate": 2.314590802055232e-06,
+      "loss": 0.1331,
+      "step": 670
+    },
+    {
+      "epoch": 2.1725239616613417,
+      "grad_norm": 1.5114609003067017,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.1268,
+      "step": 680
+    },
+    {
+      "epoch": 2.2044728434504792,
+      "grad_norm": 1.3070710897445679,
+      "learning_rate": 2.0086873134540626e-06,
+      "loss": 0.1268,
+      "step": 690
+    },
+    {
+      "epoch": 2.236421725239617,
+      "grad_norm": 3.3000214099884033,
+      "learning_rate": 1.8618326236955908e-06,
+      "loss": 0.123,
+      "step": 700
+    },
+    {
+      "epoch": 2.268370607028754,
+      "grad_norm": 2.6892614364624023,
+      "learning_rate": 1.7193151634562071e-06,
+      "loss": 0.1033,
+      "step": 710
+    },
+    {
+      "epoch": 2.3003194888178915,
+      "grad_norm": 1.186232566833496,
+      "learning_rate": 1.581331904682089e-06,
+      "loss": 0.1367,
+      "step": 720
+    },
+    {
+      "epoch": 2.3322683706070286,
+      "grad_norm": 1.3642523288726807,
+      "learning_rate": 1.4480735526452427e-06,
+      "loss": 0.1111,
+      "step": 730
+    },
+    {
+      "epoch": 2.364217252396166,
+      "grad_norm": 1.6318737268447876,
+      "learning_rate": 1.319724282371664e-06,
+      "loss": 0.1358,
+      "step": 740
+    },
+    {
+      "epoch": 2.3961661341853033,
+      "grad_norm": 2.2662744522094727,
+      "learning_rate": 1.1964614840949002e-06,
+      "loss": 0.1434,
+      "step": 750
+    },
+    {
+      "epoch": 2.428115015974441,
+      "grad_norm": 1.9114540815353394,
+      "learning_rate": 1.078455518086784e-06,
+      "loss": 0.1702,
+      "step": 760
+    },
+    {
+      "epoch": 2.460063897763578,
+      "grad_norm": 1.686519742012024,
+      "learning_rate": 9.658694792042284e-07,
+      "loss": 0.1262,
+      "step": 770
+    },
+    {
+      "epoch": 2.4920127795527156,
+      "grad_norm": 2.728212833404541,
+      "learning_rate": 8.58858971477457e-07,
+      "loss": 0.1267,
+      "step": 780
+    },
+    {
+      "epoch": 2.523961661341853,
+      "grad_norm": 1.376016616821289,
+      "learning_rate": 7.575718930512516e-07,
+      "loss": 0.1193,
+      "step": 790
+    },
+    {
+      "epoch": 2.5559105431309903,
+      "grad_norm": 1.355202555656433,
+      "learning_rate": 6.621482317764105e-07,
+      "loss": 0.1362,
+      "step": 800
+    },
+    {
+      "epoch": 2.587859424920128,
+      "grad_norm": 1.6334112882614136,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.1186,
+      "step": 810
+    },
+    {
+      "epoch": 2.619808306709265,
+      "grad_norm": 1.3374873399734497,
+      "learning_rate": 4.894104109594466e-07,
+      "loss": 0.1233,
+      "step": 820
+    },
+    {
+      "epoch": 2.6517571884984026,
+      "grad_norm": 2.329509735107422,
+      "learning_rate": 4.123349906194357e-07,
+      "loss": 0.1339,
+      "step": 830
+    },
+    {
+      "epoch": 2.68370607028754,
+      "grad_norm": 1.7785120010375977,
+      "learning_rate": 3.416001358759635e-07,
+      "loss": 0.1163,
+      "step": 840
+    },
+    {
+      "epoch": 2.7156549520766773,
+      "grad_norm": 1.338930368423462,
+      "learning_rate": 2.7730360865923954e-07,
+      "loss": 0.1277,
+      "step": 850
+    },
+    {
+      "epoch": 2.747603833865815,
+      "grad_norm": 1.281558632850647,
+      "learning_rate": 2.1953427255185122e-07,
+      "loss": 0.1218,
+      "step": 860
+    },
+    {
+      "epoch": 2.779552715654952,
+      "grad_norm": 1.581589937210083,
+      "learning_rate": 1.6837196997130434e-07,
+      "loss": 0.1299,
+      "step": 870
+    },
+    {
+      "epoch": 2.8115015974440896,
+      "grad_norm": 1.4902228116989136,
+      "learning_rate": 1.2388741182062348e-07,
+      "loss": 0.1164,
+      "step": 880
+    },
+    {
+      "epoch": 2.8434504792332267,
+      "grad_norm": 2.3329508304595947,
+      "learning_rate": 8.614207975952083e-08,
+      "loss": 0.1189,
+      "step": 890
+    },
+    {
+      "epoch": 2.8753993610223643,
+      "grad_norm": 1.161344051361084,
+      "learning_rate": 5.518814123121885e-08,
+      "loss": 0.1175,
+      "step": 900
+    },
+    {
+      "epoch": 2.9073482428115014,
+      "grad_norm": 1.952156901359558,
+      "learning_rate": 3.10683773623488e-08,
+      "loss": 0.1217,
+      "step": 910
+    },
+    {
+      "epoch": 2.939297124600639,
+      "grad_norm": 1.557270884513855,
+      "learning_rate": 1.3816123835588835e-08,
+      "loss": 0.1239,
+      "step": 920
+    },
+    {
+      "epoch": 2.9712460063897765,
+      "grad_norm": 1.0891914367675781,
+      "learning_rate": 3.4552248167507576e-09,
+      "loss": 0.1458,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "step": 939,
+      "total_flos": 2.308634334766039e+17,
+      "train_loss": 0.5363643305243267,
+      "train_runtime": 511.0643,
+      "train_samples_per_second": 58.701,
+      "train_steps_per_second": 1.837
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.308634334766039e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}