Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nemo_nano_code_100k
+  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. -->
+
+# nemo_nano_code_100k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/nemo_nano_code_100k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- 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: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.956190476190476,
+    "total_flos": 8.641809758367515e+18,
+    "train_loss": 0.5190348960803105,
+    "train_runtime": 75842.3225,
+    "train_samples_per_second": 2.214,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080a28977fa5f6633e3343a64f50a33fff434e4ed59f7598dd0a28bfb4b779f7
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5e6d949df7f59821052bb2c0e559e6384b000755f8dbb16225d249b4c77c04
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8d247ac9eebdd0e7deedb87ea08eff12fe0a53bf82525dd38487664e7c9b63
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74492c8cced6dd1ffdf1280414e03b89e3b1b6aee6e5f6acbbb24ebc2d100ea
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

runs/May10_23-28-31_jrc0931/events.out.tfevents.1746912614.jrc0931.2374216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd0ca6dd9524f35646fe75598b3c69a8c7d7a63dc896c73cee94aeb35c1b62c
+size 73926

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-10 23:28:31", "end_time": "2025-05-11 20:34:28"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.956190476190476,
+    "total_flos": 8.641809758367515e+18,
+    "train_loss": 0.5190348960803105,
+    "train_runtime": 75842.3225,
+    "train_samples_per_second": 2.214,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,326 @@
+{"current_steps": 1, "total_steps": 325, "loss": 1.0212, "lr": 2.4242424242424244e-06, "epoch": 0.015238095238095238, "percentage": 0.31, "elapsed_time": "0:04:09", "remaining_time": "22:29:54"}
+{"current_steps": 2, "total_steps": 325, "loss": 1.0078, "lr": 4.848484848484849e-06, "epoch": 0.030476190476190476, "percentage": 0.62, "elapsed_time": "0:08:03", "remaining_time": "21:40:43"}
+{"current_steps": 3, "total_steps": 325, "loss": 0.9926, "lr": 7.272727272727273e-06, "epoch": 0.045714285714285714, "percentage": 0.92, "elapsed_time": "0:11:57", "remaining_time": "21:22:55"}
+{"current_steps": 4, "total_steps": 325, "loss": 0.9511, "lr": 9.696969696969698e-06, "epoch": 0.06095238095238095, "percentage": 1.23, "elapsed_time": "0:15:50", "remaining_time": "21:11:41"}
+{"current_steps": 5, "total_steps": 325, "loss": 0.924, "lr": 1.2121212121212122e-05, "epoch": 0.0761904761904762, "percentage": 1.54, "elapsed_time": "0:19:43", "remaining_time": "21:02:39"}
+{"current_steps": 6, "total_steps": 325, "loss": 0.9436, "lr": 1.4545454545454546e-05, "epoch": 0.09142857142857143, "percentage": 1.85, "elapsed_time": "0:23:36", "remaining_time": "20:55:35"}
+{"current_steps": 7, "total_steps": 325, "loss": 0.9199, "lr": 1.6969696969696972e-05, "epoch": 0.10666666666666667, "percentage": 2.15, "elapsed_time": "0:27:29", "remaining_time": "20:49:15"}
+{"current_steps": 8, "total_steps": 325, "loss": 0.9368, "lr": 1.9393939393939395e-05, "epoch": 0.1219047619047619, "percentage": 2.46, "elapsed_time": "0:31:23", "remaining_time": "20:43:43"}
+{"current_steps": 9, "total_steps": 325, "loss": 0.8624, "lr": 2.1818181818181818e-05, "epoch": 0.13714285714285715, "percentage": 2.77, "elapsed_time": "0:35:15", "remaining_time": "20:38:05"}
+{"current_steps": 10, "total_steps": 325, "loss": 0.8177, "lr": 2.4242424242424244e-05, "epoch": 0.1523809523809524, "percentage": 3.08, "elapsed_time": "0:39:08", "remaining_time": "20:33:00"}
+{"current_steps": 11, "total_steps": 325, "loss": 0.7966, "lr": 2.6666666666666667e-05, "epoch": 0.1676190476190476, "percentage": 3.38, "elapsed_time": "0:43:02", "remaining_time": "20:28:29"}
+{"current_steps": 12, "total_steps": 325, "loss": 0.7813, "lr": 2.9090909090909093e-05, "epoch": 0.18285714285714286, "percentage": 3.69, "elapsed_time": "0:46:55", "remaining_time": "20:23:57"}
+{"current_steps": 13, "total_steps": 325, "loss": 0.7453, "lr": 3.151515151515152e-05, "epoch": 0.1980952380952381, "percentage": 4.0, "elapsed_time": "0:50:48", "remaining_time": "20:19:15"}
+{"current_steps": 14, "total_steps": 325, "loss": 0.7371, "lr": 3.3939393939393945e-05, "epoch": 0.21333333333333335, "percentage": 4.31, "elapsed_time": "0:54:40", "remaining_time": "20:14:36"}
+{"current_steps": 15, "total_steps": 325, "loss": 0.7234, "lr": 3.6363636363636364e-05, "epoch": 0.22857142857142856, "percentage": 4.62, "elapsed_time": "0:58:34", "remaining_time": "20:10:27"}
+{"current_steps": 16, "total_steps": 325, "loss": 0.7143, "lr": 3.878787878787879e-05, "epoch": 0.2438095238095238, "percentage": 4.92, "elapsed_time": "1:02:27", "remaining_time": "20:06:14"}
+{"current_steps": 17, "total_steps": 325, "loss": 0.7091, "lr": 4.1212121212121216e-05, "epoch": 0.259047619047619, "percentage": 5.23, "elapsed_time": "1:06:20", "remaining_time": "20:01:51"}
+{"current_steps": 18, "total_steps": 325, "loss": 0.7033, "lr": 4.3636363636363636e-05, "epoch": 0.2742857142857143, "percentage": 5.54, "elapsed_time": "1:10:12", "remaining_time": "19:57:18"}
+{"current_steps": 19, "total_steps": 325, "loss": 0.693, "lr": 4.606060606060607e-05, "epoch": 0.2895238095238095, "percentage": 5.85, "elapsed_time": "1:14:04", "remaining_time": "19:52:59"}
+{"current_steps": 20, "total_steps": 325, "loss": 0.6782, "lr": 4.848484848484849e-05, "epoch": 0.3047619047619048, "percentage": 6.15, "elapsed_time": "1:17:58", "remaining_time": "19:49:02"}
+{"current_steps": 21, "total_steps": 325, "loss": 0.6734, "lr": 5.0909090909090914e-05, "epoch": 0.32, "percentage": 6.46, "elapsed_time": "1:21:51", "remaining_time": "19:44:54"}
+{"current_steps": 22, "total_steps": 325, "loss": 0.6701, "lr": 5.333333333333333e-05, "epoch": 0.3352380952380952, "percentage": 6.77, "elapsed_time": "1:25:44", "remaining_time": "19:40:55"}
+{"current_steps": 23, "total_steps": 325, "loss": 0.6747, "lr": 5.5757575757575766e-05, "epoch": 0.3504761904761905, "percentage": 7.08, "elapsed_time": "1:29:38", "remaining_time": "19:36:59"}
+{"current_steps": 24, "total_steps": 325, "loss": 0.6569, "lr": 5.8181818181818185e-05, "epoch": 0.3657142857142857, "percentage": 7.38, "elapsed_time": "1:33:31", "remaining_time": "19:32:57"}
+{"current_steps": 25, "total_steps": 325, "loss": 0.6672, "lr": 6.060606060606061e-05, "epoch": 0.38095238095238093, "percentage": 7.69, "elapsed_time": "1:37:24", "remaining_time": "19:28:48"}
+{"current_steps": 26, "total_steps": 325, "loss": 0.6575, "lr": 6.303030303030304e-05, "epoch": 0.3961904761904762, "percentage": 8.0, "elapsed_time": "1:41:15", "remaining_time": "19:24:31"}
+{"current_steps": 27, "total_steps": 325, "loss": 0.6439, "lr": 6.545454545454546e-05, "epoch": 0.4114285714285714, "percentage": 8.31, "elapsed_time": "1:45:08", "remaining_time": "19:20:23"}
+{"current_steps": 28, "total_steps": 325, "loss": 0.6421, "lr": 6.787878787878789e-05, "epoch": 0.4266666666666667, "percentage": 8.62, "elapsed_time": "1:49:00", "remaining_time": "19:16:14"}
+{"current_steps": 29, "total_steps": 325, "loss": 0.6446, "lr": 7.03030303030303e-05, "epoch": 0.4419047619047619, "percentage": 8.92, "elapsed_time": "1:52:54", "remaining_time": "19:12:23"}
+{"current_steps": 30, "total_steps": 325, "loss": 0.6418, "lr": 7.272727272727273e-05, "epoch": 0.45714285714285713, "percentage": 9.23, "elapsed_time": "1:56:47", "remaining_time": "19:08:23"}
+{"current_steps": 31, "total_steps": 325, "loss": 0.6318, "lr": 7.515151515151517e-05, "epoch": 0.4723809523809524, "percentage": 9.54, "elapsed_time": "2:00:40", "remaining_time": "19:04:24"}
+{"current_steps": 32, "total_steps": 325, "loss": 0.6356, "lr": 7.757575757575758e-05, "epoch": 0.4876190476190476, "percentage": 9.85, "elapsed_time": "2:04:32", "remaining_time": "19:00:18"}
+{"current_steps": 33, "total_steps": 325, "loss": 0.6315, "lr": 8e-05, "epoch": 0.5028571428571429, "percentage": 10.15, "elapsed_time": "2:08:26", "remaining_time": "18:56:27"}
+{"current_steps": 34, "total_steps": 325, "loss": 0.6212, "lr": 7.999768495280586e-05, "epoch": 0.518095238095238, "percentage": 10.46, "elapsed_time": "2:12:19", "remaining_time": "18:52:31"}
+{"current_steps": 35, "total_steps": 325, "loss": 0.6366, "lr": 7.999074007919565e-05, "epoch": 0.5333333333333333, "percentage": 10.77, "elapsed_time": "2:16:11", "remaining_time": "18:48:30"}
+{"current_steps": 36, "total_steps": 325, "loss": 0.6337, "lr": 7.997916618305483e-05, "epoch": 0.5485714285714286, "percentage": 11.08, "elapsed_time": "2:20:04", "remaining_time": "18:44:28"}
+{"current_steps": 37, "total_steps": 325, "loss": 0.6243, "lr": 7.996296460408921e-05, "epoch": 0.5638095238095238, "percentage": 11.38, "elapsed_time": "2:23:58", "remaining_time": "18:40:37"}
+{"current_steps": 38, "total_steps": 325, "loss": 0.6222, "lr": 7.994213721766979e-05, "epoch": 0.579047619047619, "percentage": 11.69, "elapsed_time": "2:27:51", "remaining_time": "18:36:42"}
+{"current_steps": 39, "total_steps": 325, "loss": 0.6185, "lr": 7.99166864346157e-05, "epoch": 0.5942857142857143, "percentage": 12.0, "elapsed_time": "2:31:44", "remaining_time": "18:32:45"}
+{"current_steps": 40, "total_steps": 325, "loss": 0.6222, "lr": 7.988661520091513e-05, "epoch": 0.6095238095238096, "percentage": 12.31, "elapsed_time": "2:35:38", "remaining_time": "18:28:55"}
+{"current_steps": 41, "total_steps": 325, "loss": 0.6131, "lr": 7.985192699738432e-05, "epoch": 0.6247619047619047, "percentage": 12.62, "elapsed_time": "2:39:31", "remaining_time": "18:24:57"}
+{"current_steps": 42, "total_steps": 325, "loss": 0.6326, "lr": 7.981262583926472e-05, "epoch": 0.64, "percentage": 12.92, "elapsed_time": "2:43:24", "remaining_time": "18:21:01"}
+{"current_steps": 43, "total_steps": 325, "loss": 0.6057, "lr": 7.976871627575808e-05, "epoch": 0.6552380952380953, "percentage": 13.23, "elapsed_time": "2:47:18", "remaining_time": "18:17:12"}
+{"current_steps": 44, "total_steps": 325, "loss": 0.6366, "lr": 7.972020338950004e-05, "epoch": 0.6704761904761904, "percentage": 13.54, "elapsed_time": "2:51:12", "remaining_time": "18:13:21"}
+{"current_steps": 45, "total_steps": 325, "loss": 0.624, "lr": 7.96670927959716e-05, "epoch": 0.6857142857142857, "percentage": 13.85, "elapsed_time": "2:55:04", "remaining_time": "18:09:21"}
+{"current_steps": 46, "total_steps": 325, "loss": 0.619, "lr": 7.960939064284934e-05, "epoch": 0.700952380952381, "percentage": 14.15, "elapsed_time": "2:58:58", "remaining_time": "18:05:30"}
+{"current_steps": 47, "total_steps": 325, "loss": 0.6108, "lr": 7.954710360929362e-05, "epoch": 0.7161904761904762, "percentage": 14.46, "elapsed_time": "3:02:51", "remaining_time": "18:01:33"}
+{"current_steps": 48, "total_steps": 325, "loss": 0.6126, "lr": 7.948023890517557e-05, "epoch": 0.7314285714285714, "percentage": 14.77, "elapsed_time": "3:06:43", "remaining_time": "17:57:35"}
+{"current_steps": 49, "total_steps": 325, "loss": 0.6093, "lr": 7.940880427024243e-05, "epoch": 0.7466666666666667, "percentage": 15.08, "elapsed_time": "3:10:36", "remaining_time": "17:53:37"}
+{"current_steps": 50, "total_steps": 325, "loss": 0.5995, "lr": 7.933280797322181e-05, "epoch": 0.7619047619047619, "percentage": 15.38, "elapsed_time": "3:14:30", "remaining_time": "17:49:46"}
+{"current_steps": 51, "total_steps": 325, "loss": 0.5967, "lr": 7.925225881086437e-05, "epoch": 0.7771428571428571, "percentage": 15.69, "elapsed_time": "3:18:23", "remaining_time": "17:45:51"}
+{"current_steps": 52, "total_steps": 325, "loss": 0.5981, "lr": 7.916716610692578e-05, "epoch": 0.7923809523809524, "percentage": 16.0, "elapsed_time": "3:22:16", "remaining_time": "17:41:54"}
+{"current_steps": 53, "total_steps": 325, "loss": 0.5896, "lr": 7.907753971108728e-05, "epoch": 0.8076190476190476, "percentage": 16.31, "elapsed_time": "3:26:08", "remaining_time": "17:37:55"}
+{"current_steps": 54, "total_steps": 325, "loss": 0.589, "lr": 7.898338999781567e-05, "epoch": 0.8228571428571428, "percentage": 16.62, "elapsed_time": "3:30:02", "remaining_time": "17:34:03"}
+{"current_steps": 55, "total_steps": 325, "loss": 0.5937, "lr": 7.888472786516246e-05, "epoch": 0.8380952380952381, "percentage": 16.92, "elapsed_time": "3:33:55", "remaining_time": "17:30:08"}
+{"current_steps": 56, "total_steps": 325, "loss": 0.5883, "lr": 7.87815647335023e-05, "epoch": 0.8533333333333334, "percentage": 17.23, "elapsed_time": "3:37:48", "remaining_time": "17:26:14"}
+{"current_steps": 57, "total_steps": 325, "loss": 0.5931, "lr": 7.86739125442111e-05, "epoch": 0.8685714285714285, "percentage": 17.54, "elapsed_time": "3:41:42", "remaining_time": "17:22:23"}
+{"current_steps": 58, "total_steps": 325, "loss": 0.589, "lr": 7.856178375828384e-05, "epoch": 0.8838095238095238, "percentage": 17.85, "elapsed_time": "3:45:35", "remaining_time": "17:18:29"}
+{"current_steps": 59, "total_steps": 325, "loss": 0.5754, "lr": 7.844519135489204e-05, "epoch": 0.8990476190476191, "percentage": 18.15, "elapsed_time": "3:49:27", "remaining_time": "17:14:32"}
+{"current_steps": 60, "total_steps": 325, "loss": 0.5894, "lr": 7.832414882988153e-05, "epoch": 0.9142857142857143, "percentage": 18.46, "elapsed_time": "3:53:20", "remaining_time": "17:10:34"}
+{"current_steps": 61, "total_steps": 325, "loss": 0.5885, "lr": 7.819867019421023e-05, "epoch": 0.9295238095238095, "percentage": 18.77, "elapsed_time": "3:57:14", "remaining_time": "17:06:43"}
+{"current_steps": 62, "total_steps": 325, "loss": 0.5834, "lr": 7.806876997232625e-05, "epoch": 0.9447619047619048, "percentage": 19.08, "elapsed_time": "4:01:07", "remaining_time": "17:02:49"}
+{"current_steps": 63, "total_steps": 325, "loss": 0.5783, "lr": 7.793446320048687e-05, "epoch": 0.96, "percentage": 19.38, "elapsed_time": "4:04:59", "remaining_time": "16:58:52"}
+{"current_steps": 64, "total_steps": 325, "loss": 0.5839, "lr": 7.779576542501781e-05, "epoch": 0.9752380952380952, "percentage": 19.69, "elapsed_time": "4:08:52", "remaining_time": "16:54:57"}
+{"current_steps": 65, "total_steps": 325, "loss": 0.575, "lr": 7.765269270051389e-05, "epoch": 0.9904761904761905, "percentage": 20.0, "elapsed_time": "4:12:46", "remaining_time": "16:51:05"}
+{"current_steps": 66, "total_steps": 325, "loss": 0.8303, "lr": 7.750526158798056e-05, "epoch": 1.0066666666666666, "percentage": 20.31, "elapsed_time": "4:17:19", "remaining_time": "16:49:47"}
+{"current_steps": 67, "total_steps": 325, "loss": 0.571, "lr": 7.735348915291701e-05, "epoch": 1.0219047619047619, "percentage": 20.62, "elapsed_time": "4:21:12", "remaining_time": "16:45:50"}
+{"current_steps": 68, "total_steps": 325, "loss": 0.5548, "lr": 7.719739296334073e-05, "epoch": 1.0371428571428571, "percentage": 20.92, "elapsed_time": "4:25:06", "remaining_time": "16:41:56"}
+{"current_steps": 69, "total_steps": 325, "loss": 0.5619, "lr": 7.7036991087754e-05, "epoch": 1.0523809523809524, "percentage": 21.23, "elapsed_time": "4:28:59", "remaining_time": "16:37:58"}
+{"current_steps": 70, "total_steps": 325, "loss": 0.5876, "lr": 7.687230209305242e-05, "epoch": 1.0676190476190477, "percentage": 21.54, "elapsed_time": "4:32:51", "remaining_time": "16:33:59"}
+{"current_steps": 71, "total_steps": 325, "loss": 0.5685, "lr": 7.670334504237575e-05, "epoch": 1.0828571428571427, "percentage": 21.85, "elapsed_time": "4:36:45", "remaining_time": "16:30:04"}
+{"current_steps": 72, "total_steps": 325, "loss": 0.5764, "lr": 7.65301394929013e-05, "epoch": 1.098095238095238, "percentage": 22.15, "elapsed_time": "4:40:38", "remaining_time": "16:26:07"}
+{"current_steps": 73, "total_steps": 325, "loss": 0.5602, "lr": 7.635270549358012e-05, "epoch": 1.1133333333333333, "percentage": 22.46, "elapsed_time": "4:44:31", "remaining_time": "16:22:10"}
+{"current_steps": 74, "total_steps": 325, "loss": 0.5765, "lr": 7.617106358281634e-05, "epoch": 1.1285714285714286, "percentage": 22.77, "elapsed_time": "4:48:23", "remaining_time": "16:18:11"}
+{"current_steps": 75, "total_steps": 325, "loss": 0.5583, "lr": 7.598523478608974e-05, "epoch": 1.1438095238095238, "percentage": 23.08, "elapsed_time": "4:52:17", "remaining_time": "16:14:19"}
+{"current_steps": 76, "total_steps": 325, "loss": 0.551, "lr": 7.579524061352206e-05, "epoch": 1.159047619047619, "percentage": 23.38, "elapsed_time": "4:56:11", "remaining_time": "16:10:25"}
+{"current_steps": 77, "total_steps": 325, "loss": 0.5659, "lr": 7.560110305738708e-05, "epoch": 1.1742857142857144, "percentage": 23.69, "elapsed_time": "5:00:05", "remaining_time": "16:06:31"}
+{"current_steps": 78, "total_steps": 325, "loss": 0.5379, "lr": 7.540284458956503e-05, "epoch": 1.1895238095238094, "percentage": 24.0, "elapsed_time": "5:03:58", "remaining_time": "16:02:34"}
+{"current_steps": 79, "total_steps": 325, "loss": 0.5476, "lr": 7.520048815894144e-05, "epoch": 1.2047619047619047, "percentage": 24.31, "elapsed_time": "5:07:51", "remaining_time": "15:58:37"}
+{"current_steps": 80, "total_steps": 325, "loss": 0.5551, "lr": 7.49940571887506e-05, "epoch": 1.22, "percentage": 24.62, "elapsed_time": "5:11:43", "remaining_time": "15:54:38"}
+{"current_steps": 81, "total_steps": 325, "loss": 0.5407, "lr": 7.478357557386444e-05, "epoch": 1.2352380952380952, "percentage": 24.92, "elapsed_time": "5:15:35", "remaining_time": "15:50:41"}
+{"current_steps": 82, "total_steps": 325, "loss": 0.5465, "lr": 7.456906767802658e-05, "epoch": 1.2504761904761905, "percentage": 25.23, "elapsed_time": "5:19:29", "remaining_time": "15:46:47"}
+{"current_steps": 83, "total_steps": 325, "loss": 0.55, "lr": 7.435055833103213e-05, "epoch": 1.2657142857142858, "percentage": 25.54, "elapsed_time": "5:23:23", "remaining_time": "15:42:54"}
+{"current_steps": 84, "total_steps": 325, "loss": 0.5412, "lr": 7.412807282585362e-05, "epoch": 1.2809523809523808, "percentage": 25.85, "elapsed_time": "5:27:17", "remaining_time": "15:39:00"}
+{"current_steps": 85, "total_steps": 325, "loss": 0.5398, "lr": 7.390163691571325e-05, "epoch": 1.2961904761904761, "percentage": 26.15, "elapsed_time": "5:31:10", "remaining_time": "15:35:03"}
+{"current_steps": 86, "total_steps": 325, "loss": 0.534, "lr": 7.367127681110199e-05, "epoch": 1.3114285714285714, "percentage": 26.46, "elapsed_time": "5:35:03", "remaining_time": "15:31:08"}
+{"current_steps": 87, "total_steps": 325, "loss": 0.5421, "lr": 7.343701917674547e-05, "epoch": 1.3266666666666667, "percentage": 26.77, "elapsed_time": "5:38:55", "remaining_time": "15:27:10"}
+{"current_steps": 88, "total_steps": 325, "loss": 0.5371, "lr": 7.319889112851771e-05, "epoch": 1.341904761904762, "percentage": 27.08, "elapsed_time": "5:42:49", "remaining_time": "15:23:16"}
+{"current_steps": 89, "total_steps": 325, "loss": 0.5377, "lr": 7.295692023030217e-05, "epoch": 1.3571428571428572, "percentage": 27.38, "elapsed_time": "5:46:42", "remaining_time": "15:19:21"}
+{"current_steps": 90, "total_steps": 325, "loss": 0.5479, "lr": 7.271113449080131e-05, "epoch": 1.3723809523809525, "percentage": 27.69, "elapsed_time": "5:50:35", "remaining_time": "15:15:24"}
+{"current_steps": 91, "total_steps": 325, "loss": 0.5452, "lr": 7.246156236029445e-05, "epoch": 1.3876190476190478, "percentage": 28.0, "elapsed_time": "5:54:27", "remaining_time": "15:11:28"}
+{"current_steps": 92, "total_steps": 325, "loss": 0.5401, "lr": 7.220823272734461e-05, "epoch": 1.4028571428571428, "percentage": 28.31, "elapsed_time": "5:58:20", "remaining_time": "15:07:33"}
+{"current_steps": 93, "total_steps": 325, "loss": 0.5394, "lr": 7.19511749154546e-05, "epoch": 1.418095238095238, "percentage": 28.62, "elapsed_time": "6:02:14", "remaining_time": "15:03:39"}
+{"current_steps": 94, "total_steps": 325, "loss": 0.5407, "lr": 7.169041867967272e-05, "epoch": 1.4333333333333333, "percentage": 28.92, "elapsed_time": "6:06:07", "remaining_time": "14:59:44"}
+{"current_steps": 95, "total_steps": 325, "loss": 0.5464, "lr": 7.142599420314857e-05, "epoch": 1.4485714285714286, "percentage": 29.23, "elapsed_time": "6:10:01", "remaining_time": "14:55:50"}
+{"current_steps": 96, "total_steps": 325, "loss": 0.5379, "lr": 7.115793209363929e-05, "epoch": 1.4638095238095237, "percentage": 29.54, "elapsed_time": "6:13:54", "remaining_time": "14:51:56"}
+{"current_steps": 97, "total_steps": 325, "loss": 0.5248, "lr": 7.088626337996657e-05, "epoch": 1.479047619047619, "percentage": 29.85, "elapsed_time": "6:17:47", "remaining_time": "14:48:00"}
+{"current_steps": 98, "total_steps": 325, "loss": 0.5403, "lr": 7.06110195084251e-05, "epoch": 1.4942857142857142, "percentage": 30.15, "elapsed_time": "6:21:41", "remaining_time": "14:44:07"}
+{"current_steps": 99, "total_steps": 325, "loss": 0.5356, "lr": 7.03322323391425e-05, "epoch": 1.5095238095238095, "percentage": 30.46, "elapsed_time": "6:25:34", "remaining_time": "14:40:11"}
+{"current_steps": 100, "total_steps": 325, "loss": 0.5367, "lr": 7.004993414239147e-05, "epoch": 1.5247619047619048, "percentage": 30.77, "elapsed_time": "6:29:27", "remaining_time": "14:36:16"}
+{"current_steps": 101, "total_steps": 325, "loss": 0.5301, "lr": 6.976415759485443e-05, "epoch": 1.54, "percentage": 31.08, "elapsed_time": "6:33:20", "remaining_time": "14:32:22"}
+{"current_steps": 102, "total_steps": 325, "loss": 0.5338, "lr": 6.947493577584111e-05, "epoch": 1.5552380952380953, "percentage": 31.38, "elapsed_time": "6:37:14", "remaining_time": "14:28:28"}
+{"current_steps": 103, "total_steps": 325, "loss": 0.5255, "lr": 6.918230216345951e-05, "epoch": 1.5704761904761906, "percentage": 31.69, "elapsed_time": "6:41:07", "remaining_time": "14:24:33"}
+{"current_steps": 104, "total_steps": 325, "loss": 0.5209, "lr": 6.888629063074082e-05, "epoch": 1.5857142857142859, "percentage": 32.0, "elapsed_time": "6:44:59", "remaining_time": "14:20:35"}
+{"current_steps": 105, "total_steps": 325, "loss": 0.5215, "lr": 6.858693544171845e-05, "epoch": 1.600952380952381, "percentage": 32.31, "elapsed_time": "6:48:51", "remaining_time": "14:16:39"}
+{"current_steps": 106, "total_steps": 325, "loss": 0.5301, "lr": 6.828427124746191e-05, "epoch": 1.6161904761904762, "percentage": 32.62, "elapsed_time": "6:52:45", "remaining_time": "14:12:46"}
+{"current_steps": 107, "total_steps": 325, "loss": 0.529, "lr": 6.797833308206588e-05, "epoch": 1.6314285714285715, "percentage": 32.92, "elapsed_time": "6:56:38", "remaining_time": "14:08:50"}
+{"current_steps": 108, "total_steps": 325, "loss": 0.533, "lr": 6.766915635859497e-05, "epoch": 1.6466666666666665, "percentage": 33.23, "elapsed_time": "7:00:30", "remaining_time": "14:04:55"}
+{"current_steps": 109, "total_steps": 325, "loss": 0.5297, "lr": 6.735677686498443e-05, "epoch": 1.6619047619047618, "percentage": 33.54, "elapsed_time": "7:04:23", "remaining_time": "14:00:59"}
+{"current_steps": 110, "total_steps": 325, "loss": 0.5264, "lr": 6.70412307598978e-05, "epoch": 1.677142857142857, "percentage": 33.85, "elapsed_time": "7:08:16", "remaining_time": "13:57:04"}
+{"current_steps": 111, "total_steps": 325, "loss": 0.5241, "lr": 6.672255456854135e-05, "epoch": 1.6923809523809523, "percentage": 34.15, "elapsed_time": "7:12:09", "remaining_time": "13:53:09"}
+{"current_steps": 112, "total_steps": 325, "loss": 0.5346, "lr": 6.640078517843619e-05, "epoch": 1.7076190476190476, "percentage": 34.46, "elapsed_time": "7:16:02", "remaining_time": "13:49:14"}
+{"current_steps": 113, "total_steps": 325, "loss": 0.5229, "lr": 6.60759598351485e-05, "epoch": 1.7228571428571429, "percentage": 34.77, "elapsed_time": "7:19:55", "remaining_time": "13:45:19"}
+{"current_steps": 114, "total_steps": 325, "loss": 0.5243, "lr": 6.57481161379783e-05, "epoch": 1.7380952380952381, "percentage": 35.08, "elapsed_time": "7:23:47", "remaining_time": "13:41:23"}
+{"current_steps": 115, "total_steps": 325, "loss": 0.5247, "lr": 6.54172920356071e-05, "epoch": 1.7533333333333334, "percentage": 35.38, "elapsed_time": "7:27:41", "remaining_time": "13:37:30"}
+{"current_steps": 116, "total_steps": 325, "loss": 0.5144, "lr": 6.508352582170543e-05, "epoch": 1.7685714285714287, "percentage": 35.69, "elapsed_time": "7:31:34", "remaining_time": "13:33:36"}
+{"current_steps": 117, "total_steps": 325, "loss": 0.5279, "lr": 6.474685613050014e-05, "epoch": 1.783809523809524, "percentage": 36.0, "elapsed_time": "7:35:26", "remaining_time": "13:29:40"}
+{"current_steps": 118, "total_steps": 325, "loss": 0.522, "lr": 6.440732193230241e-05, "epoch": 1.799047619047619, "percentage": 36.31, "elapsed_time": "7:39:19", "remaining_time": "13:25:45"}
+{"current_steps": 119, "total_steps": 325, "loss": 0.5206, "lr": 6.40649625289969e-05, "epoch": 1.8142857142857143, "percentage": 36.62, "elapsed_time": "7:43:11", "remaining_time": "13:21:49"}
+{"current_steps": 120, "total_steps": 325, "loss": 0.5233, "lr": 6.371981754949241e-05, "epoch": 1.8295238095238096, "percentage": 36.92, "elapsed_time": "7:47:04", "remaining_time": "13:17:55"}
+{"current_steps": 121, "total_steps": 325, "loss": 0.5265, "lr": 6.337192694513474e-05, "epoch": 1.8447619047619046, "percentage": 37.23, "elapsed_time": "7:50:58", "remaining_time": "13:14:02"}
+{"current_steps": 122, "total_steps": 325, "loss": 0.5165, "lr": 6.30213309850823e-05, "epoch": 1.8599999999999999, "percentage": 37.54, "elapsed_time": "7:54:51", "remaining_time": "13:10:07"}
+{"current_steps": 123, "total_steps": 325, "loss": 0.5158, "lr": 6.266807025164472e-05, "epoch": 1.8752380952380951, "percentage": 37.85, "elapsed_time": "7:58:44", "remaining_time": "13:06:13"}
+{"current_steps": 124, "total_steps": 325, "loss": 0.518, "lr": 6.231218563558551e-05, "epoch": 1.8904761904761904, "percentage": 38.15, "elapsed_time": "8:02:38", "remaining_time": "13:02:20"}
+{"current_steps": 125, "total_steps": 325, "loss": 0.5165, "lr": 6.195371833138878e-05, "epoch": 1.9057142857142857, "percentage": 38.46, "elapsed_time": "8:06:31", "remaining_time": "12:58:26"}
+{"current_steps": 126, "total_steps": 325, "loss": 0.5247, "lr": 6.159270983249084e-05, "epoch": 1.920952380952381, "percentage": 38.77, "elapsed_time": "8:10:25", "remaining_time": "12:54:33"}
+{"current_steps": 127, "total_steps": 325, "loss": 0.5197, "lr": 6.122920192647734e-05, "epoch": 1.9361904761904762, "percentage": 39.08, "elapsed_time": "8:14:18", "remaining_time": "12:50:38"}
+{"current_steps": 128, "total_steps": 325, "loss": 0.5256, "lr": 6.086323669024616e-05, "epoch": 1.9514285714285715, "percentage": 39.38, "elapsed_time": "8:18:10", "remaining_time": "12:46:44"}
+{"current_steps": 129, "total_steps": 325, "loss": 0.527, "lr": 6.049485648513696e-05, "epoch": 1.9666666666666668, "percentage": 39.69, "elapsed_time": "8:22:02", "remaining_time": "12:42:47"}
+{"current_steps": 130, "total_steps": 325, "loss": 0.5234, "lr": 6.012410395202774e-05, "epoch": 1.981904761904762, "percentage": 40.0, "elapsed_time": "8:25:54", "remaining_time": "12:38:52"}
+{"current_steps": 131, "total_steps": 325, "loss": 0.7009, "lr": 5.9751022006399095e-05, "epoch": 1.997142857142857, "percentage": 40.31, "elapsed_time": "8:29:34", "remaining_time": "12:34:38"}
+{"current_steps": 132, "total_steps": 325, "loss": 0.5404, "lr": 5.9375653833366585e-05, "epoch": 2.013333333333333, "percentage": 40.62, "elapsed_time": "8:33:53", "remaining_time": "12:31:22"}
+{"current_steps": 133, "total_steps": 325, "loss": 0.4877, "lr": 5.8998042882682024e-05, "epoch": 2.0285714285714285, "percentage": 40.92, "elapsed_time": "8:37:45", "remaining_time": "12:27:26"}
+{"current_steps": 134, "total_steps": 325, "loss": 0.4849, "lr": 5.861823286370396e-05, "epoch": 2.0438095238095237, "percentage": 41.23, "elapsed_time": "8:41:38", "remaining_time": "12:23:31"}
+{"current_steps": 135, "total_steps": 325, "loss": 0.4887, "lr": 5.823626774033836e-05, "epoch": 2.059047619047619, "percentage": 41.54, "elapsed_time": "8:45:31", "remaining_time": "12:19:37"}
+{"current_steps": 136, "total_steps": 325, "loss": 0.4881, "lr": 5.7852191725949564e-05, "epoch": 2.0742857142857143, "percentage": 41.85, "elapsed_time": "8:49:24", "remaining_time": "12:15:43"}
+{"current_steps": 137, "total_steps": 325, "loss": 0.4844, "lr": 5.746604927824257e-05, "epoch": 2.0895238095238096, "percentage": 42.15, "elapsed_time": "8:53:17", "remaining_time": "12:11:49"}
+{"current_steps": 138, "total_steps": 325, "loss": 0.4887, "lr": 5.707788509411685e-05, "epoch": 2.104761904761905, "percentage": 42.46, "elapsed_time": "8:57:10", "remaining_time": "12:07:54"}
+{"current_steps": 139, "total_steps": 325, "loss": 0.4908, "lr": 5.668774410449268e-05, "epoch": 2.12, "percentage": 42.77, "elapsed_time": "9:01:04", "remaining_time": "12:04:01"}
+{"current_steps": 140, "total_steps": 325, "loss": 0.4872, "lr": 5.629567146911023e-05, "epoch": 2.1352380952380954, "percentage": 43.08, "elapsed_time": "9:04:56", "remaining_time": "12:00:06"}
+{"current_steps": 141, "total_steps": 325, "loss": 0.4861, "lr": 5.590171257130225e-05, "epoch": 2.1504761904761907, "percentage": 43.38, "elapsed_time": "9:08:49", "remaining_time": "11:56:12"}
+{"current_steps": 142, "total_steps": 325, "loss": 0.4844, "lr": 5.550591301274073e-05, "epoch": 2.1657142857142855, "percentage": 43.69, "elapsed_time": "9:12:42", "remaining_time": "11:52:17"}
+{"current_steps": 143, "total_steps": 325, "loss": 0.4836, "lr": 5.5108318608158595e-05, "epoch": 2.1809523809523808, "percentage": 44.0, "elapsed_time": "9:16:35", "remaining_time": "11:48:23"}
+{"current_steps": 144, "total_steps": 325, "loss": 0.4796, "lr": 5.4708975380046356e-05, "epoch": 2.196190476190476, "percentage": 44.31, "elapsed_time": "9:20:28", "remaining_time": "11:44:29"}
+{"current_steps": 145, "total_steps": 325, "loss": 0.4863, "lr": 5.430792955332503e-05, "epoch": 2.2114285714285713, "percentage": 44.62, "elapsed_time": "9:24:21", "remaining_time": "11:40:34"}
+{"current_steps": 146, "total_steps": 325, "loss": 0.4809, "lr": 5.3905227549995366e-05, "epoch": 2.2266666666666666, "percentage": 44.92, "elapsed_time": "9:28:13", "remaining_time": "11:36:39"}
+{"current_steps": 147, "total_steps": 325, "loss": 0.4805, "lr": 5.350091598376454e-05, "epoch": 2.241904761904762, "percentage": 45.23, "elapsed_time": "9:32:06", "remaining_time": "11:32:44"}
+{"current_steps": 148, "total_steps": 325, "loss": 0.4831, "lr": 5.3095041654650384e-05, "epoch": 2.257142857142857, "percentage": 45.54, "elapsed_time": "9:35:58", "remaining_time": "11:28:49"}
+{"current_steps": 149, "total_steps": 325, "loss": 0.4816, "lr": 5.268765154356425e-05, "epoch": 2.2723809523809524, "percentage": 45.85, "elapsed_time": "9:39:49", "remaining_time": "11:24:54"}
+{"current_steps": 150, "total_steps": 325, "loss": 0.4788, "lr": 5.227879280687281e-05, "epoch": 2.2876190476190477, "percentage": 46.15, "elapsed_time": "9:43:42", "remaining_time": "11:20:59"}
+{"current_steps": 151, "total_steps": 325, "loss": 0.4851, "lr": 5.186851277093961e-05, "epoch": 2.302857142857143, "percentage": 46.46, "elapsed_time": "9:47:36", "remaining_time": "11:17:06"}
+{"current_steps": 152, "total_steps": 325, "loss": 0.4817, "lr": 5.1456858926646974e-05, "epoch": 2.318095238095238, "percentage": 46.77, "elapsed_time": "9:51:29", "remaining_time": "11:13:12"}
+{"current_steps": 153, "total_steps": 325, "loss": 0.4816, "lr": 5.104387892389877e-05, "epoch": 2.3333333333333335, "percentage": 47.08, "elapsed_time": "9:55:22", "remaining_time": "11:09:18"}
+{"current_steps": 154, "total_steps": 325, "loss": 0.4833, "lr": 5.062962056610478e-05, "epoch": 2.3485714285714288, "percentage": 47.38, "elapsed_time": "9:59:14", "remaining_time": "11:05:23"}
+{"current_steps": 155, "total_steps": 325, "loss": 0.4884, "lr": 5.021413180464748e-05, "epoch": 2.3638095238095236, "percentage": 47.69, "elapsed_time": "10:03:08", "remaining_time": "11:01:30"}
+{"current_steps": 156, "total_steps": 325, "loss": 0.4777, "lr": 4.979746073333145e-05, "epoch": 2.379047619047619, "percentage": 48.0, "elapsed_time": "10:07:01", "remaining_time": "10:57:36"}
+{"current_steps": 157, "total_steps": 325, "loss": 0.4867, "lr": 4.9379655582816396e-05, "epoch": 2.394285714285714, "percentage": 48.31, "elapsed_time": "10:10:53", "remaining_time": "10:53:41"}
+{"current_steps": 158, "total_steps": 325, "loss": 0.4766, "lr": 4.896076471503439e-05, "epoch": 2.4095238095238094, "percentage": 48.62, "elapsed_time": "10:14:46", "remaining_time": "10:49:47"}
+{"current_steps": 159, "total_steps": 325, "loss": 0.4884, "lr": 4.854083661759185e-05, "epoch": 2.4247619047619047, "percentage": 48.92, "elapsed_time": "10:18:38", "remaining_time": "10:45:52"}
+{"current_steps": 160, "total_steps": 325, "loss": 0.4834, "lr": 4.8119919898156934e-05, "epoch": 2.44, "percentage": 49.23, "elapsed_time": "10:22:31", "remaining_time": "10:41:58"}
+{"current_steps": 161, "total_steps": 325, "loss": 0.4779, "lr": 4.76980632788332e-05, "epoch": 2.455238095238095, "percentage": 49.54, "elapsed_time": "10:26:24", "remaining_time": "10:38:05"}
+{"current_steps": 162, "total_steps": 325, "loss": 0.4823, "lr": 4.7275315590519765e-05, "epoch": 2.4704761904761905, "percentage": 49.85, "elapsed_time": "10:30:18", "remaining_time": "10:34:11"}
+{"current_steps": 163, "total_steps": 325, "loss": 0.4781, "lr": 4.6851725767259106e-05, "epoch": 2.4857142857142858, "percentage": 50.15, "elapsed_time": "10:34:10", "remaining_time": "10:30:17"}
+{"current_steps": 164, "total_steps": 325, "loss": 0.4755, "lr": 4.642734284057283e-05, "epoch": 2.500952380952381, "percentage": 50.46, "elapsed_time": "10:38:03", "remaining_time": "10:26:23"}
+{"current_steps": 165, "total_steps": 325, "loss": 0.4796, "lr": 4.600221593378611e-05, "epoch": 2.5161904761904763, "percentage": 50.77, "elapsed_time": "10:41:58", "remaining_time": "10:22:31"}
+{"current_steps": 166, "total_steps": 325, "loss": 0.4784, "lr": 4.5576394256341596e-05, "epoch": 2.5314285714285716, "percentage": 51.08, "elapsed_time": "10:45:53", "remaining_time": "10:18:39"}
+{"current_steps": 167, "total_steps": 325, "loss": 0.4839, "lr": 4.514992709810324e-05, "epoch": 2.546666666666667, "percentage": 51.38, "elapsed_time": "10:49:46", "remaining_time": "10:14:45"}
+{"current_steps": 168, "total_steps": 325, "loss": 0.4899, "lr": 4.472286382365096e-05, "epoch": 2.5619047619047617, "percentage": 51.69, "elapsed_time": "10:53:40", "remaining_time": "10:10:52"}
+{"current_steps": 169, "total_steps": 325, "loss": 0.4865, "lr": 4.429525386656653e-05, "epoch": 2.5771428571428574, "percentage": 52.0, "elapsed_time": "10:57:33", "remaining_time": "10:06:58"}
+{"current_steps": 170, "total_steps": 325, "loss": 0.4841, "lr": 4.38671467237115e-05, "epoch": 2.5923809523809522, "percentage": 52.31, "elapsed_time": "11:01:26", "remaining_time": "10:03:04"}
+{"current_steps": 171, "total_steps": 325, "loss": 0.4792, "lr": 4.343859194949787e-05, "epoch": 2.6076190476190475, "percentage": 52.62, "elapsed_time": "11:05:17", "remaining_time": "9:59:09"}
+{"current_steps": 172, "total_steps": 325, "loss": 0.4788, "lr": 4.3009639150152e-05, "epoch": 2.6228571428571428, "percentage": 52.92, "elapsed_time": "11:09:09", "remaining_time": "9:55:14"}
+{"current_steps": 173, "total_steps": 325, "loss": 0.4827, "lr": 4.2580337977972664e-05, "epoch": 2.638095238095238, "percentage": 53.23, "elapsed_time": "11:13:04", "remaining_time": "9:51:22"}
+{"current_steps": 174, "total_steps": 325, "loss": 0.4885, "lr": 4.215073812558352e-05, "epoch": 2.6533333333333333, "percentage": 53.54, "elapsed_time": "11:16:57", "remaining_time": "9:47:28"}
+{"current_steps": 175, "total_steps": 325, "loss": 0.4772, "lr": 4.1720889320181224e-05, "epoch": 2.6685714285714286, "percentage": 53.85, "elapsed_time": "11:20:50", "remaining_time": "9:43:34"}
+{"current_steps": 176, "total_steps": 325, "loss": 0.4884, "lr": 4.1290841317779325e-05, "epoch": 2.683809523809524, "percentage": 54.15, "elapsed_time": "11:24:43", "remaining_time": "9:39:40"}
+{"current_steps": 177, "total_steps": 325, "loss": 0.4789, "lr": 4.0860643897448894e-05, "epoch": 2.699047619047619, "percentage": 54.46, "elapsed_time": "11:28:36", "remaining_time": "9:35:47"}
+{"current_steps": 178, "total_steps": 325, "loss": 0.4807, "lr": 4.043034685555647e-05, "epoch": 2.7142857142857144, "percentage": 54.77, "elapsed_time": "11:32:28", "remaining_time": "9:31:52"}
+{"current_steps": 179, "total_steps": 325, "loss": 0.481, "lr": 4e-05, "epoch": 2.7295238095238097, "percentage": 55.08, "elapsed_time": "11:36:22", "remaining_time": "9:27:59"}
+{"current_steps": 180, "total_steps": 325, "loss": 0.481, "lr": 3.9569653144443546e-05, "epoch": 2.744761904761905, "percentage": 55.38, "elapsed_time": "11:40:15", "remaining_time": "9:24:06"}
+{"current_steps": 181, "total_steps": 325, "loss": 0.4763, "lr": 3.913935610255112e-05, "epoch": 2.76, "percentage": 55.69, "elapsed_time": "11:44:08", "remaining_time": "9:20:12"}
+{"current_steps": 182, "total_steps": 325, "loss": 0.4819, "lr": 3.870915868222068e-05, "epoch": 2.7752380952380955, "percentage": 56.0, "elapsed_time": "11:48:01", "remaining_time": "9:16:18"}
+{"current_steps": 183, "total_steps": 325, "loss": 0.4738, "lr": 3.8279110679818775e-05, "epoch": 2.7904761904761903, "percentage": 56.31, "elapsed_time": "11:51:54", "remaining_time": "9:12:24"}
+{"current_steps": 184, "total_steps": 325, "loss": 0.4783, "lr": 3.78492618744165e-05, "epoch": 2.8057142857142856, "percentage": 56.62, "elapsed_time": "11:55:47", "remaining_time": "9:08:30"}
+{"current_steps": 185, "total_steps": 325, "loss": 0.4769, "lr": 3.7419662022027356e-05, "epoch": 2.820952380952381, "percentage": 56.92, "elapsed_time": "11:59:41", "remaining_time": "9:04:37"}
+{"current_steps": 186, "total_steps": 325, "loss": 0.4757, "lr": 3.6990360849848005e-05, "epoch": 2.836190476190476, "percentage": 57.23, "elapsed_time": "12:03:34", "remaining_time": "9:00:43"}
+{"current_steps": 187, "total_steps": 325, "loss": 0.4786, "lr": 3.656140805050215e-05, "epoch": 2.8514285714285714, "percentage": 57.54, "elapsed_time": "12:07:27", "remaining_time": "8:56:50"}
+{"current_steps": 188, "total_steps": 325, "loss": 0.4739, "lr": 3.6132853276288506e-05, "epoch": 2.8666666666666667, "percentage": 57.85, "elapsed_time": "12:11:19", "remaining_time": "8:52:56"}
+{"current_steps": 189, "total_steps": 325, "loss": 0.4768, "lr": 3.570474613343348e-05, "epoch": 2.881904761904762, "percentage": 58.15, "elapsed_time": "12:15:12", "remaining_time": "8:49:02"}
+{"current_steps": 190, "total_steps": 325, "loss": 0.4733, "lr": 3.527713617634904e-05, "epoch": 2.8971428571428572, "percentage": 58.46, "elapsed_time": "12:19:05", "remaining_time": "8:45:08"}
+{"current_steps": 191, "total_steps": 325, "loss": 0.4802, "lr": 3.4850072901896766e-05, "epoch": 2.9123809523809525, "percentage": 58.77, "elapsed_time": "12:22:57", "remaining_time": "8:41:14"}
+{"current_steps": 192, "total_steps": 325, "loss": 0.4834, "lr": 3.442360574365843e-05, "epoch": 2.9276190476190473, "percentage": 59.08, "elapsed_time": "12:26:49", "remaining_time": "8:37:19"}
+{"current_steps": 193, "total_steps": 325, "loss": 0.4747, "lr": 3.39977840662139e-05, "epoch": 2.942857142857143, "percentage": 59.38, "elapsed_time": "12:30:41", "remaining_time": "8:33:25"}
+{"current_steps": 194, "total_steps": 325, "loss": 0.4808, "lr": 3.3572657159427186e-05, "epoch": 2.958095238095238, "percentage": 59.69, "elapsed_time": "12:34:34", "remaining_time": "8:29:31"}
+{"current_steps": 195, "total_steps": 325, "loss": 0.4751, "lr": 3.31482742327409e-05, "epoch": 2.9733333333333336, "percentage": 60.0, "elapsed_time": "12:38:27", "remaining_time": "8:25:38"}
+{"current_steps": 196, "total_steps": 325, "loss": 0.4734, "lr": 3.272468440948025e-05, "epoch": 2.9885714285714284, "percentage": 60.31, "elapsed_time": "12:42:20", "remaining_time": "8:21:44"}
+{"current_steps": 197, "total_steps": 325, "loss": 0.6928, "lr": 3.230193672116681e-05, "epoch": 3.0047619047619047, "percentage": 60.62, "elapsed_time": "12:46:53", "remaining_time": "8:18:16"}
+{"current_steps": 198, "total_steps": 325, "loss": 0.4452, "lr": 3.188008010184306e-05, "epoch": 3.02, "percentage": 60.92, "elapsed_time": "12:50:45", "remaining_time": "8:14:22"}
+{"current_steps": 199, "total_steps": 325, "loss": 0.4546, "lr": 3.145916338240816e-05, "epoch": 3.0352380952380953, "percentage": 61.23, "elapsed_time": "12:54:38", "remaining_time": "8:10:28"}
+{"current_steps": 200, "total_steps": 325, "loss": 0.4452, "lr": 3.103923528496562e-05, "epoch": 3.0504761904761906, "percentage": 61.54, "elapsed_time": "12:58:31", "remaining_time": "8:06:34"}
+{"current_steps": 201, "total_steps": 325, "loss": 0.4483, "lr": 3.062034441718362e-05, "epoch": 3.065714285714286, "percentage": 61.85, "elapsed_time": "13:02:24", "remaining_time": "8:02:40"}
+{"current_steps": 202, "total_steps": 325, "loss": 0.4506, "lr": 3.0202539266668568e-05, "epoch": 3.080952380952381, "percentage": 62.15, "elapsed_time": "13:06:16", "remaining_time": "7:58:46"}
+{"current_steps": 203, "total_steps": 325, "loss": 0.4449, "lr": 2.9785868195352525e-05, "epoch": 3.0961904761904764, "percentage": 62.46, "elapsed_time": "13:10:09", "remaining_time": "7:54:52"}
+{"current_steps": 204, "total_steps": 325, "loss": 0.4512, "lr": 2.9370379433895228e-05, "epoch": 3.111428571428571, "percentage": 62.77, "elapsed_time": "13:14:01", "remaining_time": "7:50:57"}
+{"current_steps": 205, "total_steps": 325, "loss": 0.449, "lr": 2.8956121076101244e-05, "epoch": 3.1266666666666665, "percentage": 63.08, "elapsed_time": "13:17:53", "remaining_time": "7:47:03"}
+{"current_steps": 206, "total_steps": 325, "loss": 0.4439, "lr": 2.8543141073353026e-05, "epoch": 3.1419047619047618, "percentage": 63.38, "elapsed_time": "13:21:44", "remaining_time": "7:43:08"}
+{"current_steps": 207, "total_steps": 325, "loss": 0.4427, "lr": 2.8131487229060387e-05, "epoch": 3.157142857142857, "percentage": 63.69, "elapsed_time": "13:25:37", "remaining_time": "7:39:14"}
+{"current_steps": 208, "total_steps": 325, "loss": 0.4472, "lr": 2.7721207193127212e-05, "epoch": 3.1723809523809523, "percentage": 64.0, "elapsed_time": "13:29:31", "remaining_time": "7:35:21"}
+{"current_steps": 209, "total_steps": 325, "loss": 0.4453, "lr": 2.7312348456435766e-05, "epoch": 3.1876190476190476, "percentage": 64.31, "elapsed_time": "13:33:24", "remaining_time": "7:31:27"}
+{"current_steps": 210, "total_steps": 325, "loss": 0.4561, "lr": 2.6904958345349633e-05, "epoch": 3.202857142857143, "percentage": 64.62, "elapsed_time": "13:37:16", "remaining_time": "7:27:33"}
+{"current_steps": 211, "total_steps": 325, "loss": 0.444, "lr": 2.6499084016235475e-05, "epoch": 3.218095238095238, "percentage": 64.92, "elapsed_time": "13:41:08", "remaining_time": "7:23:39"}
+{"current_steps": 212, "total_steps": 325, "loss": 0.44, "lr": 2.609477245000464e-05, "epoch": 3.2333333333333334, "percentage": 65.23, "elapsed_time": "13:45:00", "remaining_time": "7:19:44"}
+{"current_steps": 213, "total_steps": 325, "loss": 0.4494, "lr": 2.569207044667498e-05, "epoch": 3.2485714285714287, "percentage": 65.54, "elapsed_time": "13:48:53", "remaining_time": "7:15:50"}
+{"current_steps": 214, "total_steps": 325, "loss": 0.4471, "lr": 2.529102461995364e-05, "epoch": 3.263809523809524, "percentage": 65.85, "elapsed_time": "13:52:45", "remaining_time": "7:11:56"}
+{"current_steps": 215, "total_steps": 325, "loss": 0.4486, "lr": 2.48916813918414e-05, "epoch": 3.279047619047619, "percentage": 66.15, "elapsed_time": "13:56:39", "remaining_time": "7:08:03"}
+{"current_steps": 216, "total_steps": 325, "loss": 0.445, "lr": 2.449408698725928e-05, "epoch": 3.2942857142857145, "percentage": 66.46, "elapsed_time": "14:00:32", "remaining_time": "7:04:09"}
+{"current_steps": 217, "total_steps": 325, "loss": 0.4415, "lr": 2.409828742869777e-05, "epoch": 3.3095238095238093, "percentage": 66.77, "elapsed_time": "14:04:25", "remaining_time": "7:00:15"}
+{"current_steps": 218, "total_steps": 325, "loss": 0.454, "lr": 2.370432853088978e-05, "epoch": 3.3247619047619046, "percentage": 67.08, "elapsed_time": "14:08:17", "remaining_time": "6:56:21"}
+{"current_steps": 219, "total_steps": 325, "loss": 0.4473, "lr": 2.3312255895507336e-05, "epoch": 3.34, "percentage": 67.38, "elapsed_time": "14:12:09", "remaining_time": "6:52:27"}
+{"current_steps": 220, "total_steps": 325, "loss": 0.4444, "lr": 2.2922114905883167e-05, "epoch": 3.355238095238095, "percentage": 67.69, "elapsed_time": "14:16:01", "remaining_time": "6:48:33"}
+{"current_steps": 221, "total_steps": 325, "loss": 0.4465, "lr": 2.2533950721757447e-05, "epoch": 3.3704761904761904, "percentage": 68.0, "elapsed_time": "14:19:52", "remaining_time": "6:44:39"}
+{"current_steps": 222, "total_steps": 325, "loss": 0.4484, "lr": 2.2147808274050436e-05, "epoch": 3.3857142857142857, "percentage": 68.31, "elapsed_time": "14:23:45", "remaining_time": "6:40:45"}
+{"current_steps": 223, "total_steps": 325, "loss": 0.4479, "lr": 2.1763732259661657e-05, "epoch": 3.400952380952381, "percentage": 68.62, "elapsed_time": "14:27:38", "remaining_time": "6:36:51"}
+{"current_steps": 224, "total_steps": 325, "loss": 0.4475, "lr": 2.138176713629605e-05, "epoch": 3.416190476190476, "percentage": 68.92, "elapsed_time": "14:31:32", "remaining_time": "6:32:58"}
+{"current_steps": 225, "total_steps": 325, "loss": 0.4421, "lr": 2.1001957117318002e-05, "epoch": 3.4314285714285715, "percentage": 69.23, "elapsed_time": "14:35:25", "remaining_time": "6:29:04"}
+{"current_steps": 226, "total_steps": 325, "loss": 0.4396, "lr": 2.0624346166633425e-05, "epoch": 3.4466666666666668, "percentage": 69.54, "elapsed_time": "14:39:17", "remaining_time": "6:25:10"}
+{"current_steps": 227, "total_steps": 325, "loss": 0.4491, "lr": 2.0248977993600912e-05, "epoch": 3.461904761904762, "percentage": 69.85, "elapsed_time": "14:43:09", "remaining_time": "6:21:16"}
+{"current_steps": 228, "total_steps": 325, "loss": 0.4448, "lr": 1.987589604797227e-05, "epoch": 3.4771428571428573, "percentage": 70.15, "elapsed_time": "14:47:01", "remaining_time": "6:17:22"}
+{"current_steps": 229, "total_steps": 325, "loss": 0.4489, "lr": 1.9505143514863056e-05, "epoch": 3.4923809523809526, "percentage": 70.46, "elapsed_time": "14:50:53", "remaining_time": "6:13:28"}
+{"current_steps": 230, "total_steps": 325, "loss": 0.4546, "lr": 1.913676330975385e-05, "epoch": 3.5076190476190474, "percentage": 70.77, "elapsed_time": "14:54:47", "remaining_time": "6:09:35"}
+{"current_steps": 231, "total_steps": 325, "loss": 0.447, "lr": 1.8770798073522657e-05, "epoch": 3.522857142857143, "percentage": 71.08, "elapsed_time": "14:58:41", "remaining_time": "6:05:41"}
+{"current_steps": 232, "total_steps": 325, "loss": 0.4543, "lr": 1.8407290167509163e-05, "epoch": 3.538095238095238, "percentage": 71.38, "elapsed_time": "15:02:33", "remaining_time": "6:01:48"}
+{"current_steps": 233, "total_steps": 325, "loss": 0.444, "lr": 1.8046281668611242e-05, "epoch": 3.5533333333333332, "percentage": 71.69, "elapsed_time": "15:06:26", "remaining_time": "5:57:54"}
+{"current_steps": 234, "total_steps": 325, "loss": 0.4451, "lr": 1.7687814364414508e-05, "epoch": 3.5685714285714285, "percentage": 72.0, "elapsed_time": "15:10:19", "remaining_time": "5:54:01"}
+{"current_steps": 235, "total_steps": 325, "loss": 0.4465, "lr": 1.73319297483553e-05, "epoch": 3.583809523809524, "percentage": 72.31, "elapsed_time": "15:14:13", "remaining_time": "5:50:07"}
+{"current_steps": 236, "total_steps": 325, "loss": 0.4406, "lr": 1.6978669014917723e-05, "epoch": 3.599047619047619, "percentage": 72.62, "elapsed_time": "15:18:05", "remaining_time": "5:46:13"}
+{"current_steps": 237, "total_steps": 325, "loss": 0.4539, "lr": 1.6628073054865262e-05, "epoch": 3.6142857142857143, "percentage": 72.92, "elapsed_time": "15:21:58", "remaining_time": "5:42:20"}
+{"current_steps": 238, "total_steps": 325, "loss": 0.4505, "lr": 1.6280182450507593e-05, "epoch": 3.6295238095238096, "percentage": 73.23, "elapsed_time": "15:25:51", "remaining_time": "5:38:26"}
+{"current_steps": 239, "total_steps": 325, "loss": 0.44, "lr": 1.593503747100309e-05, "epoch": 3.644761904761905, "percentage": 73.54, "elapsed_time": "15:29:44", "remaining_time": "5:34:33"}
+{"current_steps": 240, "total_steps": 325, "loss": 0.4401, "lr": 1.5592678067697594e-05, "epoch": 3.66, "percentage": 73.85, "elapsed_time": "15:33:37", "remaining_time": "5:30:39"}
+{"current_steps": 241, "total_steps": 325, "loss": 0.4526, "lr": 1.5253143869499875e-05, "epoch": 3.675238095238095, "percentage": 74.15, "elapsed_time": "15:37:29", "remaining_time": "5:26:45"}
+{"current_steps": 242, "total_steps": 325, "loss": 0.4472, "lr": 1.4916474178294578e-05, "epoch": 3.6904761904761907, "percentage": 74.46, "elapsed_time": "15:41:23", "remaining_time": "5:22:52"}
+{"current_steps": 243, "total_steps": 325, "loss": 0.4503, "lr": 1.4582707964392909e-05, "epoch": 3.7057142857142855, "percentage": 74.77, "elapsed_time": "15:45:16", "remaining_time": "5:18:58"}
+{"current_steps": 244, "total_steps": 325, "loss": 0.4507, "lr": 1.4251883862021715e-05, "epoch": 3.720952380952381, "percentage": 75.08, "elapsed_time": "15:49:09", "remaining_time": "5:15:05"}
+{"current_steps": 245, "total_steps": 325, "loss": 0.4509, "lr": 1.3924040164851497e-05, "epoch": 3.736190476190476, "percentage": 75.38, "elapsed_time": "15:53:03", "remaining_time": "5:11:12"}
+{"current_steps": 246, "total_steps": 325, "loss": 0.453, "lr": 1.359921482156382e-05, "epoch": 3.7514285714285713, "percentage": 75.69, "elapsed_time": "15:56:55", "remaining_time": "5:07:18"}
+{"current_steps": 247, "total_steps": 325, "loss": 0.4423, "lr": 1.3277445431458653e-05, "epoch": 3.7666666666666666, "percentage": 76.0, "elapsed_time": "16:00:48", "remaining_time": "5:03:24"}
+{"current_steps": 248, "total_steps": 325, "loss": 0.4465, "lr": 1.2958769240102206e-05, "epoch": 3.781904761904762, "percentage": 76.31, "elapsed_time": "16:04:40", "remaining_time": "4:59:30"}
+{"current_steps": 249, "total_steps": 325, "loss": 0.4495, "lr": 1.264322313501559e-05, "epoch": 3.797142857142857, "percentage": 76.62, "elapsed_time": "16:08:33", "remaining_time": "4:55:37"}
+{"current_steps": 250, "total_steps": 325, "loss": 0.4451, "lr": 1.2330843641405057e-05, "epoch": 3.8123809523809524, "percentage": 76.92, "elapsed_time": "16:12:25", "remaining_time": "4:51:43"}
+{"current_steps": 251, "total_steps": 325, "loss": 0.4473, "lr": 1.2021666917934125e-05, "epoch": 3.8276190476190477, "percentage": 77.23, "elapsed_time": "16:16:17", "remaining_time": "4:47:49"}
+{"current_steps": 252, "total_steps": 325, "loss": 0.4443, "lr": 1.1715728752538103e-05, "epoch": 3.842857142857143, "percentage": 77.54, "elapsed_time": "16:20:11", "remaining_time": "4:43:56"}
+{"current_steps": 253, "total_steps": 325, "loss": 0.4468, "lr": 1.1413064558281564e-05, "epoch": 3.8580952380952382, "percentage": 77.85, "elapsed_time": "16:24:03", "remaining_time": "4:40:02"}
+{"current_steps": 254, "total_steps": 325, "loss": 0.4426, "lr": 1.1113709369259187e-05, "epoch": 3.873333333333333, "percentage": 78.15, "elapsed_time": "16:27:56", "remaining_time": "4:36:09"}
+{"current_steps": 255, "total_steps": 325, "loss": 0.4493, "lr": 1.0817697836540493e-05, "epoch": 3.888571428571429, "percentage": 78.46, "elapsed_time": "16:31:49", "remaining_time": "4:32:16"}
+{"current_steps": 256, "total_steps": 325, "loss": 0.4415, "lr": 1.052506422415891e-05, "epoch": 3.9038095238095236, "percentage": 78.77, "elapsed_time": "16:35:44", "remaining_time": "4:28:22"}
+{"current_steps": 257, "total_steps": 325, "loss": 0.447, "lr": 1.0235842405145587e-05, "epoch": 3.919047619047619, "percentage": 79.08, "elapsed_time": "16:39:37", "remaining_time": "4:24:29"}
+{"current_steps": 258, "total_steps": 325, "loss": 0.4449, "lr": 9.950065857608537e-06, "epoch": 3.934285714285714, "percentage": 79.38, "elapsed_time": "16:43:30", "remaining_time": "4:20:36"}
+{"current_steps": 259, "total_steps": 325, "loss": 0.4378, "lr": 9.667767660857508e-06, "epoch": 3.9495238095238094, "percentage": 79.69, "elapsed_time": "16:47:23", "remaining_time": "4:16:42"}
+{"current_steps": 260, "total_steps": 325, "loss": 0.4485, "lr": 9.388980491574901e-06, "epoch": 3.9647619047619047, "percentage": 80.0, "elapsed_time": "16:51:15", "remaining_time": "4:12:48"}
+{"current_steps": 261, "total_steps": 325, "loss": 0.4518, "lr": 9.11373662003343e-06, "epoch": 3.98, "percentage": 80.31, "elapsed_time": "16:55:08", "remaining_time": "4:08:55"}
+{"current_steps": 262, "total_steps": 325, "loss": 0.559, "lr": 8.842067906360716e-06, "epoch": 3.9952380952380953, "percentage": 80.62, "elapsed_time": "16:58:48", "remaining_time": "4:04:58"}
+{"current_steps": 263, "total_steps": 325, "loss": 0.5283, "lr": 8.574005796851419e-06, "epoch": 4.011428571428572, "percentage": 80.92, "elapsed_time": "17:03:07", "remaining_time": "4:01:11"}
+{"current_steps": 264, "total_steps": 325, "loss": 0.4248, "lr": 8.309581320327282e-06, "epoch": 4.026666666666666, "percentage": 81.23, "elapsed_time": "17:07:00", "remaining_time": "3:57:18"}
+{"current_steps": 265, "total_steps": 325, "loss": 0.4208, "lr": 8.048825084545413e-06, "epoch": 4.041904761904762, "percentage": 81.54, "elapsed_time": "17:10:53", "remaining_time": "3:53:24"}
+{"current_steps": 266, "total_steps": 325, "loss": 0.4282, "lr": 7.791767272655403e-06, "epoch": 4.057142857142857, "percentage": 81.85, "elapsed_time": "17:14:46", "remaining_time": "3:49:31"}
+{"current_steps": 267, "total_steps": 325, "loss": 0.4275, "lr": 7.5384376397055644e-06, "epoch": 4.072380952380953, "percentage": 82.15, "elapsed_time": "17:18:39", "remaining_time": "3:45:37"}
+{"current_steps": 268, "total_steps": 325, "loss": 0.4296, "lr": 7.2888655091986995e-06, "epoch": 4.0876190476190475, "percentage": 82.46, "elapsed_time": "17:22:32", "remaining_time": "3:41:44"}
+{"current_steps": 269, "total_steps": 325, "loss": 0.4301, "lr": 7.043079769697833e-06, "epoch": 4.102857142857143, "percentage": 82.77, "elapsed_time": "17:26:24", "remaining_time": "3:37:50"}
+{"current_steps": 270, "total_steps": 325, "loss": 0.432, "lr": 6.801108871482287e-06, "epoch": 4.118095238095238, "percentage": 83.08, "elapsed_time": "17:30:18", "remaining_time": "3:33:57"}
+{"current_steps": 271, "total_steps": 325, "loss": 0.4313, "lr": 6.562980823254519e-06, "epoch": 4.133333333333334, "percentage": 83.38, "elapsed_time": "17:34:11", "remaining_time": "3:30:03"}
+{"current_steps": 272, "total_steps": 325, "loss": 0.4279, "lr": 6.328723188898029e-06, "epoch": 4.148571428571429, "percentage": 83.69, "elapsed_time": "17:38:03", "remaining_time": "3:26:09"}
+{"current_steps": 273, "total_steps": 325, "loss": 0.4259, "lr": 6.098363084286765e-06, "epoch": 4.163809523809523, "percentage": 84.0, "elapsed_time": "17:41:55", "remaining_time": "3:22:16"}
+{"current_steps": 274, "total_steps": 325, "loss": 0.4225, "lr": 5.8719271741464056e-06, "epoch": 4.179047619047619, "percentage": 84.31, "elapsed_time": "17:45:47", "remaining_time": "3:18:22"}
+{"current_steps": 275, "total_steps": 325, "loss": 0.4189, "lr": 5.6494416689678855e-06, "epoch": 4.194285714285714, "percentage": 84.62, "elapsed_time": "17:49:39", "remaining_time": "3:14:29"}
+{"current_steps": 276, "total_steps": 325, "loss": 0.4158, "lr": 5.430932321973425e-06, "epoch": 4.20952380952381, "percentage": 84.92, "elapsed_time": "17:53:31", "remaining_time": "3:10:35"}
+{"current_steps": 277, "total_steps": 325, "loss": 0.4299, "lr": 5.21642442613556e-06, "epoch": 4.2247619047619045, "percentage": 85.23, "elapsed_time": "17:57:24", "remaining_time": "3:06:41"}
+{"current_steps": 278, "total_steps": 325, "loss": 0.4243, "lr": 5.005942811249412e-06, "epoch": 4.24, "percentage": 85.54, "elapsed_time": "18:01:16", "remaining_time": "3:02:48"}
+{"current_steps": 279, "total_steps": 325, "loss": 0.4262, "lr": 4.799511841058575e-06, "epoch": 4.255238095238095, "percentage": 85.85, "elapsed_time": "18:05:07", "remaining_time": "2:58:54"}
+{"current_steps": 280, "total_steps": 325, "loss": 0.4247, "lr": 4.597155410434972e-06, "epoch": 4.270476190476191, "percentage": 86.15, "elapsed_time": "18:08:59", "remaining_time": "2:55:01"}
+{"current_steps": 281, "total_steps": 325, "loss": 0.4238, "lr": 4.398896942612934e-06, "epoch": 4.285714285714286, "percentage": 86.46, "elapsed_time": "18:12:52", "remaining_time": "2:51:07"}
+{"current_steps": 282, "total_steps": 325, "loss": 0.4391, "lr": 4.204759386477961e-06, "epoch": 4.300952380952381, "percentage": 86.77, "elapsed_time": "18:16:45", "remaining_time": "2:47:14"}
+{"current_steps": 283, "total_steps": 325, "loss": 0.4352, "lr": 4.01476521391027e-06, "epoch": 4.316190476190476, "percentage": 87.08, "elapsed_time": "18:20:38", "remaining_time": "2:43:20"}
+{"current_steps": 284, "total_steps": 325, "loss": 0.43, "lr": 3.828936417183671e-06, "epoch": 4.331428571428571, "percentage": 87.38, "elapsed_time": "18:24:32", "remaining_time": "2:39:27"}
+{"current_steps": 285, "total_steps": 325, "loss": 0.427, "lr": 3.6472945064198827e-06, "epoch": 4.346666666666667, "percentage": 87.69, "elapsed_time": "18:28:23", "remaining_time": "2:35:33"}
+{"current_steps": 286, "total_steps": 325, "loss": 0.4257, "lr": 3.4698605070987077e-06, "epoch": 4.3619047619047615, "percentage": 88.0, "elapsed_time": "18:32:16", "remaining_time": "2:31:40"}
+{"current_steps": 287, "total_steps": 325, "loss": 0.4357, "lr": 3.2966549576242477e-06, "epoch": 4.377142857142857, "percentage": 88.31, "elapsed_time": "18:36:08", "remaining_time": "2:27:46"}
+{"current_steps": 288, "total_steps": 325, "loss": 0.4272, "lr": 3.127697906947584e-06, "epoch": 4.392380952380952, "percentage": 88.62, "elapsed_time": "18:40:00", "remaining_time": "2:23:53"}
+{"current_steps": 289, "total_steps": 325, "loss": 0.4347, "lr": 2.963008912246008e-06, "epoch": 4.407619047619048, "percentage": 88.92, "elapsed_time": "18:43:52", "remaining_time": "2:19:59"}
+{"current_steps": 290, "total_steps": 325, "loss": 0.4294, "lr": 2.802607036659284e-06, "epoch": 4.422857142857143, "percentage": 89.23, "elapsed_time": "18:47:44", "remaining_time": "2:16:06"}
+{"current_steps": 291, "total_steps": 325, "loss": 0.4303, "lr": 2.646510847082997e-06, "epoch": 4.438095238095238, "percentage": 89.54, "elapsed_time": "18:51:37", "remaining_time": "2:12:13"}
+{"current_steps": 292, "total_steps": 325, "loss": 0.423, "lr": 2.494738412019442e-06, "epoch": 4.453333333333333, "percentage": 89.85, "elapsed_time": "18:55:30", "remaining_time": "2:08:19"}
+{"current_steps": 293, "total_steps": 325, "loss": 0.427, "lr": 2.3473072994861167e-06, "epoch": 4.468571428571429, "percentage": 90.15, "elapsed_time": "18:59:23", "remaining_time": "2:04:26"}
+{"current_steps": 294, "total_steps": 325, "loss": 0.4216, "lr": 2.2042345749821913e-06, "epoch": 4.483809523809524, "percentage": 90.46, "elapsed_time": "19:03:15", "remaining_time": "2:00:32"}
+{"current_steps": 295, "total_steps": 325, "loss": 0.4288, "lr": 2.065536799513135e-06, "epoch": 4.499047619047619, "percentage": 90.77, "elapsed_time": "19:07:08", "remaining_time": "1:56:39"}
+{"current_steps": 296, "total_steps": 325, "loss": 0.4235, "lr": 1.9312300276737516e-06, "epoch": 4.514285714285714, "percentage": 91.08, "elapsed_time": "19:10:59", "remaining_time": "1:52:45"}
+{"current_steps": 297, "total_steps": 325, "loss": 0.4293, "lr": 1.8013298057897932e-06, "epoch": 4.529523809523809, "percentage": 91.38, "elapsed_time": "19:14:52", "remaining_time": "1:48:52"}
+{"current_steps": 298, "total_steps": 325, "loss": 0.4238, "lr": 1.6758511701184809e-06, "epoch": 4.544761904761905, "percentage": 91.69, "elapsed_time": "19:18:46", "remaining_time": "1:44:59"}
+{"current_steps": 299, "total_steps": 325, "loss": 0.4384, "lr": 1.5548086451079747e-06, "epoch": 4.5600000000000005, "percentage": 92.0, "elapsed_time": "19:22:39", "remaining_time": "1:41:06"}
+{"current_steps": 300, "total_steps": 325, "loss": 0.4206, "lr": 1.4382162417161748e-06, "epoch": 4.575238095238095, "percentage": 92.31, "elapsed_time": "19:26:32", "remaining_time": "1:37:12"}
+{"current_steps": 301, "total_steps": 325, "loss": 0.4287, "lr": 1.3260874557889002e-06, "epoch": 4.59047619047619, "percentage": 92.62, "elapsed_time": "19:30:25", "remaining_time": "1:33:19"}
+{"current_steps": 302, "total_steps": 325, "loss": 0.4175, "lr": 1.2184352664977105e-06, "epoch": 4.605714285714286, "percentage": 92.92, "elapsed_time": "19:34:18", "remaining_time": "1:29:26"}
+{"current_steps": 303, "total_steps": 325, "loss": 0.4312, "lr": 1.115272134837544e-06, "epoch": 4.620952380952381, "percentage": 93.23, "elapsed_time": "19:38:11", "remaining_time": "1:25:32"}
+{"current_steps": 304, "total_steps": 325, "loss": 0.4346, "lr": 1.0166100021843283e-06, "epoch": 4.636190476190476, "percentage": 93.54, "elapsed_time": "19:42:03", "remaining_time": "1:21:39"}
+{"current_steps": 305, "total_steps": 325, "loss": 0.4286, "lr": 9.224602889127321e-07, "epoch": 4.651428571428571, "percentage": 93.85, "elapsed_time": "19:45:55", "remaining_time": "1:17:45"}
+{"current_steps": 306, "total_steps": 325, "loss": 0.4267, "lr": 8.328338930742296e-07, "epoch": 4.666666666666667, "percentage": 94.15, "elapsed_time": "19:49:47", "remaining_time": "1:13:52"}
+{"current_steps": 307, "total_steps": 325, "loss": 0.4276, "lr": 7.477411891356268e-07, "epoch": 4.681904761904762, "percentage": 94.46, "elapsed_time": "19:53:39", "remaining_time": "1:09:59"}
+{"current_steps": 308, "total_steps": 325, "loss": 0.4282, "lr": 6.671920267782029e-07, "epoch": 4.6971428571428575, "percentage": 94.77, "elapsed_time": "19:57:32", "remaining_time": "1:06:05"}
+{"current_steps": 309, "total_steps": 325, "loss": 0.4323, "lr": 5.911957297575743e-07, "epoch": 4.712380952380952, "percentage": 95.08, "elapsed_time": "20:01:24", "remaining_time": "1:02:12"}
+{"current_steps": 310, "total_steps": 325, "loss": 0.4256, "lr": 5.197610948244469e-07, "epoch": 4.727619047619047, "percentage": 95.38, "elapsed_time": "20:05:15", "remaining_time": "0:58:19"}
+{"current_steps": 311, "total_steps": 325, "loss": 0.4171, "lr": 4.5289639070638103e-07, "epoch": 4.742857142857143, "percentage": 95.69, "elapsed_time": "20:09:08", "remaining_time": "0:54:25"}
+{"current_steps": 312, "total_steps": 325, "loss": 0.428, "lr": 3.906093571506597e-07, "epoch": 4.758095238095238, "percentage": 96.0, "elapsed_time": "20:13:01", "remaining_time": "0:50:32"}
+{"current_steps": 313, "total_steps": 325, "loss": 0.4208, "lr": 3.329072040284009e-07, "epoch": 4.773333333333333, "percentage": 96.31, "elapsed_time": "20:16:54", "remaining_time": "0:46:39"}
+{"current_steps": 314, "total_steps": 325, "loss": 0.4332, "lr": 2.797966104999805e-07, "epoch": 4.788571428571428, "percentage": 96.62, "elapsed_time": "20:20:47", "remaining_time": "0:42:45"}
+{"current_steps": 315, "total_steps": 325, "loss": 0.4377, "lr": 2.3128372424192635e-07, "epoch": 4.803809523809524, "percentage": 96.92, "elapsed_time": "20:24:39", "remaining_time": "0:38:52"}
+{"current_steps": 316, "total_steps": 325, "loss": 0.4272, "lr": 1.8737416073529635e-07, "epoch": 4.819047619047619, "percentage": 97.23, "elapsed_time": "20:28:32", "remaining_time": "0:34:59"}
+{"current_steps": 317, "total_steps": 325, "loss": 0.4287, "lr": 1.4807300261568735e-07, "epoch": 4.8342857142857145, "percentage": 97.54, "elapsed_time": "20:32:24", "remaining_time": "0:31:06"}
+{"current_steps": 318, "total_steps": 325, "loss": 0.4337, "lr": 1.1338479908488798e-07, "epoch": 4.849523809523809, "percentage": 97.85, "elapsed_time": "20:36:17", "remaining_time": "0:27:12"}
+{"current_steps": 319, "total_steps": 325, "loss": 0.4262, "lr": 8.331356538431313e-08, "epoch": 4.864761904761905, "percentage": 98.15, "elapsed_time": "20:40:11", "remaining_time": "0:23:19"}
+{"current_steps": 320, "total_steps": 325, "loss": 0.4317, "lr": 5.7862782330215804e-08, "epoch": 4.88, "percentage": 98.46, "elapsed_time": "20:44:03", "remaining_time": "0:19:26"}
+{"current_steps": 321, "total_steps": 325, "loss": 0.4232, "lr": 3.703539591080052e-08, "epoch": 4.895238095238096, "percentage": 98.77, "elapsed_time": "20:47:55", "remaining_time": "0:15:33"}
+{"current_steps": 322, "total_steps": 325, "loss": 0.4297, "lr": 2.0833816945184936e-08, "epoch": 4.91047619047619, "percentage": 99.08, "elapsed_time": "20:51:48", "remaining_time": "0:11:39"}
+{"current_steps": 323, "total_steps": 325, "loss": 0.4276, "lr": 9.25992080436533e-09, "epoch": 4.925714285714285, "percentage": 99.38, "elapsed_time": "20:55:42", "remaining_time": "0:07:46"}
+{"current_steps": 324, "total_steps": 325, "loss": 0.4271, "lr": 2.315047194136888e-09, "epoch": 4.940952380952381, "percentage": 99.69, "elapsed_time": "20:59:35", "remaining_time": "0:03:53"}
+{"current_steps": 325, "total_steps": 325, "loss": 0.4248, "lr": 0.0, "epoch": 4.956190476190476, "percentage": 100.0, "elapsed_time": "21:03:28", "remaining_time": "0:00:00"}
+{"current_steps": 325, "total_steps": 325, "epoch": 4.956190476190476, "percentage": 100.0, "elapsed_time": "21:03:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2317 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.956190476190476,
+  "eval_steps": 500,
+  "global_step": 325,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015238095238095238,
+      "grad_norm": 6.41825703019793,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 1.0212,
+      "step": 1
+    },
+    {
+      "epoch": 0.030476190476190476,
+      "grad_norm": 6.32460329298527,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 1.0078,
+      "step": 2
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 5.823493836887707,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.9926,
+      "step": 3
+    },
+    {
+      "epoch": 0.06095238095238095,
+      "grad_norm": 4.215092249626398,
+      "learning_rate": 9.696969696969698e-06,
+      "loss": 0.9511,
+      "step": 4
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 2.755821783551069,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 0.924,
+      "step": 5
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 5.79854862437273,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.9436,
+      "step": 6
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 6.970153409745764,
+      "learning_rate": 1.6969696969696972e-05,
+      "loss": 0.9199,
+      "step": 7
+    },
+    {
+      "epoch": 0.1219047619047619,
+      "grad_norm": 6.398045150850651,
+      "learning_rate": 1.9393939393939395e-05,
+      "loss": 0.9368,
+      "step": 8
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 3.7323118823746717,
+      "learning_rate": 2.1818181818181818e-05,
+      "loss": 0.8624,
+      "step": 9
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 2.4649345087328935,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 0.8177,
+      "step": 10
+    },
+    {
+      "epoch": 0.1676190476190476,
+      "grad_norm": 2.624350847053939,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7966,
+      "step": 11
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 1.495708592085656,
+      "learning_rate": 2.9090909090909093e-05,
+      "loss": 0.7813,
+      "step": 12
+    },
+    {
+      "epoch": 0.1980952380952381,
+      "grad_norm": 1.4871227985381805,
+      "learning_rate": 3.151515151515152e-05,
+      "loss": 0.7453,
+      "step": 13
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.060287535099846,
+      "learning_rate": 3.3939393939393945e-05,
+      "loss": 0.7371,
+      "step": 14
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 1.4326857447271233,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.7234,
+      "step": 15
+    },
+    {
+      "epoch": 0.2438095238095238,
+      "grad_norm": 2.1165784341208105,
+      "learning_rate": 3.878787878787879e-05,
+      "loss": 0.7143,
+      "step": 16
+    },
+    {
+      "epoch": 0.259047619047619,
+      "grad_norm": 1.7376117944761271,
+      "learning_rate": 4.1212121212121216e-05,
+      "loss": 0.7091,
+      "step": 17
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 1.9235494481574669,
+      "learning_rate": 4.3636363636363636e-05,
+      "loss": 0.7033,
+      "step": 18
+    },
+    {
+      "epoch": 0.2895238095238095,
+      "grad_norm": 1.2885542410242774,
+      "learning_rate": 4.606060606060607e-05,
+      "loss": 0.693,
+      "step": 19
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 2.0682542365556746,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 0.6782,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.1294865223043438,
+      "learning_rate": 5.0909090909090914e-05,
+      "loss": 0.6734,
+      "step": 21
+    },
+    {
+      "epoch": 0.3352380952380952,
+      "grad_norm": 1.6892295840685134,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.6701,
+      "step": 22
+    },
+    {
+      "epoch": 0.3504761904761905,
+      "grad_norm": 1.7015145087043497,
+      "learning_rate": 5.5757575757575766e-05,
+      "loss": 0.6747,
+      "step": 23
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 1.105513245543281,
+      "learning_rate": 5.8181818181818185e-05,
+      "loss": 0.6569,
+      "step": 24
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.9301412200235886,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 0.6672,
+      "step": 25
+    },
+    {
+      "epoch": 0.3961904761904762,
+      "grad_norm": 1.5372986311163992,
+      "learning_rate": 6.303030303030304e-05,
+      "loss": 0.6575,
+      "step": 26
+    },
+    {
+      "epoch": 0.4114285714285714,
+      "grad_norm": 1.841770844497413,
+      "learning_rate": 6.545454545454546e-05,
+      "loss": 0.6439,
+      "step": 27
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.285994127925713,
+      "learning_rate": 6.787878787878789e-05,
+      "loss": 0.6421,
+      "step": 28
+    },
+    {
+      "epoch": 0.4419047619047619,
+      "grad_norm": 1.306641316576376,
+      "learning_rate": 7.03030303030303e-05,
+      "loss": 0.6446,
+      "step": 29
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 2.060289337588267,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.6418,
+      "step": 30
+    },
+    {
+      "epoch": 0.4723809523809524,
+      "grad_norm": 1.5995121846928928,
+      "learning_rate": 7.515151515151517e-05,
+      "loss": 0.6318,
+      "step": 31
+    },
+    {
+      "epoch": 0.4876190476190476,
+      "grad_norm": 1.5361156868763157,
+      "learning_rate": 7.757575757575758e-05,
+      "loss": 0.6356,
+      "step": 32
+    },
+    {
+      "epoch": 0.5028571428571429,
+      "grad_norm": 1.9790958633956652,
+      "learning_rate": 8e-05,
+      "loss": 0.6315,
+      "step": 33
+    },
+    {
+      "epoch": 0.518095238095238,
+      "grad_norm": 1.0983212679170282,
+      "learning_rate": 7.999768495280586e-05,
+      "loss": 0.6212,
+      "step": 34
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.356052428059575,
+      "learning_rate": 7.999074007919565e-05,
+      "loss": 0.6366,
+      "step": 35
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 1.9118106657858278,
+      "learning_rate": 7.997916618305483e-05,
+      "loss": 0.6337,
+      "step": 36
+    },
+    {
+      "epoch": 0.5638095238095238,
+      "grad_norm": 2.086875421088417,
+      "learning_rate": 7.996296460408921e-05,
+      "loss": 0.6243,
+      "step": 37
+    },
+    {
+      "epoch": 0.579047619047619,
+      "grad_norm": 1.6815412319889804,
+      "learning_rate": 7.994213721766979e-05,
+      "loss": 0.6222,
+      "step": 38
+    },
+    {
+      "epoch": 0.5942857142857143,
+      "grad_norm": 1.9619509595749545,
+      "learning_rate": 7.99166864346157e-05,
+      "loss": 0.6185,
+      "step": 39
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 1.1850043703613138,
+      "learning_rate": 7.988661520091513e-05,
+      "loss": 0.6222,
+      "step": 40
+    },
+    {
+      "epoch": 0.6247619047619047,
+      "grad_norm": 1.5413225249585591,
+      "learning_rate": 7.985192699738432e-05,
+      "loss": 0.6131,
+      "step": 41
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.2994933443512697,
+      "learning_rate": 7.981262583926472e-05,
+      "loss": 0.6326,
+      "step": 42
+    },
+    {
+      "epoch": 0.6552380952380953,
+      "grad_norm": 0.8610367129145644,
+      "learning_rate": 7.976871627575808e-05,
+      "loss": 0.6057,
+      "step": 43
+    },
+    {
+      "epoch": 0.6704761904761904,
+      "grad_norm": 2.630926210907478,
+      "learning_rate": 7.972020338950004e-05,
+      "loss": 0.6366,
+      "step": 44
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 1.542557855004854,
+      "learning_rate": 7.96670927959716e-05,
+      "loss": 0.624,
+      "step": 45
+    },
+    {
+      "epoch": 0.700952380952381,
+      "grad_norm": 1.9643148826366752,
+      "learning_rate": 7.960939064284934e-05,
+      "loss": 0.619,
+      "step": 46
+    },
+    {
+      "epoch": 0.7161904761904762,
+      "grad_norm": 1.248523269079334,
+      "learning_rate": 7.954710360929362e-05,
+      "loss": 0.6108,
+      "step": 47
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 1.225316205009982,
+      "learning_rate": 7.948023890517557e-05,
+      "loss": 0.6126,
+      "step": 48
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.4200551325493893,
+      "learning_rate": 7.940880427024243e-05,
+      "loss": 0.6093,
+      "step": 49
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 1.3484644010507392,
+      "learning_rate": 7.933280797322181e-05,
+      "loss": 0.5995,
+      "step": 50
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 1.317639647361387,
+      "learning_rate": 7.925225881086437e-05,
+      "loss": 0.5967,
+      "step": 51
+    },
+    {
+      "epoch": 0.7923809523809524,
+      "grad_norm": 1.5340582175990225,
+      "learning_rate": 7.916716610692578e-05,
+      "loss": 0.5981,
+      "step": 52
+    },
+    {
+      "epoch": 0.8076190476190476,
+      "grad_norm": 1.0386828999827622,
+      "learning_rate": 7.907753971108728e-05,
+      "loss": 0.5896,
+      "step": 53
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 1.5332648656890953,
+      "learning_rate": 7.898338999781567e-05,
+      "loss": 0.589,
+      "step": 54
+    },
+    {
+      "epoch": 0.8380952380952381,
+      "grad_norm": 1.1339766871931323,
+      "learning_rate": 7.888472786516246e-05,
+      "loss": 0.5937,
+      "step": 55
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.5164034405411189,
+      "learning_rate": 7.87815647335023e-05,
+      "loss": 0.5883,
+      "step": 56
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 0.9700436403678562,
+      "learning_rate": 7.86739125442111e-05,
+      "loss": 0.5931,
+      "step": 57
+    },
+    {
+      "epoch": 0.8838095238095238,
+      "grad_norm": 1.3463613799484717,
+      "learning_rate": 7.856178375828384e-05,
+      "loss": 0.589,
+      "step": 58
+    },
+    {
+      "epoch": 0.8990476190476191,
+      "grad_norm": 0.8752856535881799,
+      "learning_rate": 7.844519135489204e-05,
+      "loss": 0.5754,
+      "step": 59
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 1.1854440512880053,
+      "learning_rate": 7.832414882988153e-05,
+      "loss": 0.5894,
+      "step": 60
+    },
+    {
+      "epoch": 0.9295238095238095,
+      "grad_norm": 1.7051861411911757,
+      "learning_rate": 7.819867019421023e-05,
+      "loss": 0.5885,
+      "step": 61
+    },
+    {
+      "epoch": 0.9447619047619048,
+      "grad_norm": 0.6380913241526577,
+      "learning_rate": 7.806876997232625e-05,
+      "loss": 0.5834,
+      "step": 62
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3953430391233206,
+      "learning_rate": 7.793446320048687e-05,
+      "loss": 0.5783,
+      "step": 63
+    },
+    {
+      "epoch": 0.9752380952380952,
+      "grad_norm": 1.0079170376946163,
+      "learning_rate": 7.779576542501781e-05,
+      "loss": 0.5839,
+      "step": 64
+    },
+    {
+      "epoch": 0.9904761904761905,
+      "grad_norm": 1.1878161560623453,
+      "learning_rate": 7.765269270051389e-05,
+      "loss": 0.575,
+      "step": 65
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.495861192796852,
+      "learning_rate": 7.750526158798056e-05,
+      "loss": 0.8303,
+      "step": 66
+    },
+    {
+      "epoch": 1.0219047619047619,
+      "grad_norm": 1.3683956168224771,
+      "learning_rate": 7.735348915291701e-05,
+      "loss": 0.571,
+      "step": 67
+    },
+    {
+      "epoch": 1.0371428571428571,
+      "grad_norm": 0.8831683489698775,
+      "learning_rate": 7.719739296334073e-05,
+      "loss": 0.5548,
+      "step": 68
+    },
+    {
+      "epoch": 1.0523809523809524,
+      "grad_norm": 0.9884633873935289,
+      "learning_rate": 7.7036991087754e-05,
+      "loss": 0.5619,
+      "step": 69
+    },
+    {
+      "epoch": 1.0676190476190477,
+      "grad_norm": 1.658491152165491,
+      "learning_rate": 7.687230209305242e-05,
+      "loss": 0.5876,
+      "step": 70
+    },
+    {
+      "epoch": 1.0828571428571427,
+      "grad_norm": 0.8352075307968011,
+      "learning_rate": 7.670334504237575e-05,
+      "loss": 0.5685,
+      "step": 71
+    },
+    {
+      "epoch": 1.098095238095238,
+      "grad_norm": 1.429719144977111,
+      "learning_rate": 7.65301394929013e-05,
+      "loss": 0.5764,
+      "step": 72
+    },
+    {
+      "epoch": 1.1133333333333333,
+      "grad_norm": 0.9027318597099093,
+      "learning_rate": 7.635270549358012e-05,
+      "loss": 0.5602,
+      "step": 73
+    },
+    {
+      "epoch": 1.1285714285714286,
+      "grad_norm": 1.0536650805805048,
+      "learning_rate": 7.617106358281634e-05,
+      "loss": 0.5765,
+      "step": 74
+    },
+    {
+      "epoch": 1.1438095238095238,
+      "grad_norm": 0.8336607908560256,
+      "learning_rate": 7.598523478608974e-05,
+      "loss": 0.5583,
+      "step": 75
+    },
+    {
+      "epoch": 1.159047619047619,
+      "grad_norm": 0.7166113488943966,
+      "learning_rate": 7.579524061352206e-05,
+      "loss": 0.551,
+      "step": 76
+    },
+    {
+      "epoch": 1.1742857142857144,
+      "grad_norm": 0.8105369080449557,
+      "learning_rate": 7.560110305738708e-05,
+      "loss": 0.5659,
+      "step": 77
+    },
+    {
+      "epoch": 1.1895238095238094,
+      "grad_norm": 0.6283210931425559,
+      "learning_rate": 7.540284458956503e-05,
+      "loss": 0.5379,
+      "step": 78
+    },
+    {
+      "epoch": 1.2047619047619047,
+      "grad_norm": 0.8126105033449552,
+      "learning_rate": 7.520048815894144e-05,
+      "loss": 0.5476,
+      "step": 79
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.5252506521520861,
+      "learning_rate": 7.49940571887506e-05,
+      "loss": 0.5551,
+      "step": 80
+    },
+    {
+      "epoch": 1.2352380952380952,
+      "grad_norm": 0.6609919242663752,
+      "learning_rate": 7.478357557386444e-05,
+      "loss": 0.5407,
+      "step": 81
+    },
+    {
+      "epoch": 1.2504761904761905,
+      "grad_norm": 0.576238102776681,
+      "learning_rate": 7.456906767802658e-05,
+      "loss": 0.5465,
+      "step": 82
+    },
+    {
+      "epoch": 1.2657142857142858,
+      "grad_norm": 0.5233988001346253,
+      "learning_rate": 7.435055833103213e-05,
+      "loss": 0.55,
+      "step": 83
+    },
+    {
+      "epoch": 1.2809523809523808,
+      "grad_norm": 0.44023553757218015,
+      "learning_rate": 7.412807282585362e-05,
+      "loss": 0.5412,
+      "step": 84
+    },
+    {
+      "epoch": 1.2961904761904761,
+      "grad_norm": 0.4831178702636027,
+      "learning_rate": 7.390163691571325e-05,
+      "loss": 0.5398,
+      "step": 85
+    },
+    {
+      "epoch": 1.3114285714285714,
+      "grad_norm": 0.454634628403172,
+      "learning_rate": 7.367127681110199e-05,
+      "loss": 0.534,
+      "step": 86
+    },
+    {
+      "epoch": 1.3266666666666667,
+      "grad_norm": 0.44419681534445155,
+      "learning_rate": 7.343701917674547e-05,
+      "loss": 0.5421,
+      "step": 87
+    },
+    {
+      "epoch": 1.341904761904762,
+      "grad_norm": 0.4888479476988804,
+      "learning_rate": 7.319889112851771e-05,
+      "loss": 0.5371,
+      "step": 88
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.7143397739870562,
+      "learning_rate": 7.295692023030217e-05,
+      "loss": 0.5377,
+      "step": 89
+    },
+    {
+      "epoch": 1.3723809523809525,
+      "grad_norm": 0.9465106459896011,
+      "learning_rate": 7.271113449080131e-05,
+      "loss": 0.5479,
+      "step": 90
+    },
+    {
+      "epoch": 1.3876190476190478,
+      "grad_norm": 1.2678262246780991,
+      "learning_rate": 7.246156236029445e-05,
+      "loss": 0.5452,
+      "step": 91
+    },
+    {
+      "epoch": 1.4028571428571428,
+      "grad_norm": 0.6281248994163343,
+      "learning_rate": 7.220823272734461e-05,
+      "loss": 0.5401,
+      "step": 92
+    },
+    {
+      "epoch": 1.418095238095238,
+      "grad_norm": 0.34247752257094766,
+      "learning_rate": 7.19511749154546e-05,
+      "loss": 0.5394,
+      "step": 93
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.7014077226631056,
+      "learning_rate": 7.169041867967272e-05,
+      "loss": 0.5407,
+      "step": 94
+    },
+    {
+      "epoch": 1.4485714285714286,
+      "grad_norm": 0.9221215435654039,
+      "learning_rate": 7.142599420314857e-05,
+      "loss": 0.5464,
+      "step": 95
+    },
+    {
+      "epoch": 1.4638095238095237,
+      "grad_norm": 0.8724875653280793,
+      "learning_rate": 7.115793209363929e-05,
+      "loss": 0.5379,
+      "step": 96
+    },
+    {
+      "epoch": 1.479047619047619,
+      "grad_norm": 0.734302784896464,
+      "learning_rate": 7.088626337996657e-05,
+      "loss": 0.5248,
+      "step": 97
+    },
+    {
+      "epoch": 1.4942857142857142,
+      "grad_norm": 0.6804548302488894,
+      "learning_rate": 7.06110195084251e-05,
+      "loss": 0.5403,
+      "step": 98
+    },
+    {
+      "epoch": 1.5095238095238095,
+      "grad_norm": 0.8180102079360684,
+      "learning_rate": 7.03322323391425e-05,
+      "loss": 0.5356,
+      "step": 99
+    },
+    {
+      "epoch": 1.5247619047619048,
+      "grad_norm": 0.7089574204038593,
+      "learning_rate": 7.004993414239147e-05,
+      "loss": 0.5367,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.4534978500691297,
+      "learning_rate": 6.976415759485443e-05,
+      "loss": 0.5301,
+      "step": 101
+    },
+    {
+      "epoch": 1.5552380952380953,
+      "grad_norm": 0.5791842384826449,
+      "learning_rate": 6.947493577584111e-05,
+      "loss": 0.5338,
+      "step": 102
+    },
+    {
+      "epoch": 1.5704761904761906,
+      "grad_norm": 0.6373667696236239,
+      "learning_rate": 6.918230216345951e-05,
+      "loss": 0.5255,
+      "step": 103
+    },
+    {
+      "epoch": 1.5857142857142859,
+      "grad_norm": 0.5813750117468534,
+      "learning_rate": 6.888629063074082e-05,
+      "loss": 0.5209,
+      "step": 104
+    },
+    {
+      "epoch": 1.600952380952381,
+      "grad_norm": 0.5731639034091425,
+      "learning_rate": 6.858693544171845e-05,
+      "loss": 0.5215,
+      "step": 105
+    },
+    {
+      "epoch": 1.6161904761904762,
+      "grad_norm": 0.5351450945596543,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.5301,
+      "step": 106
+    },
+    {
+      "epoch": 1.6314285714285715,
+      "grad_norm": 0.6016816279659157,
+      "learning_rate": 6.797833308206588e-05,
+      "loss": 0.529,
+      "step": 107
+    },
+    {
+      "epoch": 1.6466666666666665,
+      "grad_norm": 0.7659521464895882,
+      "learning_rate": 6.766915635859497e-05,
+      "loss": 0.533,
+      "step": 108
+    },
+    {
+      "epoch": 1.6619047619047618,
+      "grad_norm": 0.9630524913355004,
+      "learning_rate": 6.735677686498443e-05,
+      "loss": 0.5297,
+      "step": 109
+    },
+    {
+      "epoch": 1.677142857142857,
+      "grad_norm": 1.1492200252998914,
+      "learning_rate": 6.70412307598978e-05,
+      "loss": 0.5264,
+      "step": 110
+    },
+    {
+      "epoch": 1.6923809523809523,
+      "grad_norm": 0.5857314920473611,
+      "learning_rate": 6.672255456854135e-05,
+      "loss": 0.5241,
+      "step": 111
+    },
+    {
+      "epoch": 1.7076190476190476,
+      "grad_norm": 0.48173626706101424,
+      "learning_rate": 6.640078517843619e-05,
+      "loss": 0.5346,
+      "step": 112
+    },
+    {
+      "epoch": 1.7228571428571429,
+      "grad_norm": 0.7730414410041352,
+      "learning_rate": 6.60759598351485e-05,
+      "loss": 0.5229,
+      "step": 113
+    },
+    {
+      "epoch": 1.7380952380952381,
+      "grad_norm": 0.6363250099986629,
+      "learning_rate": 6.57481161379783e-05,
+      "loss": 0.5243,
+      "step": 114
+    },
+    {
+      "epoch": 1.7533333333333334,
+      "grad_norm": 0.45624023704141803,
+      "learning_rate": 6.54172920356071e-05,
+      "loss": 0.5247,
+      "step": 115
+    },
+    {
+      "epoch": 1.7685714285714287,
+      "grad_norm": 0.4715396085670591,
+      "learning_rate": 6.508352582170543e-05,
+      "loss": 0.5144,
+      "step": 116
+    },
+    {
+      "epoch": 1.783809523809524,
+      "grad_norm": 0.5945001964397519,
+      "learning_rate": 6.474685613050014e-05,
+      "loss": 0.5279,
+      "step": 117
+    },
+    {
+      "epoch": 1.799047619047619,
+      "grad_norm": 0.5588842197173406,
+      "learning_rate": 6.440732193230241e-05,
+      "loss": 0.522,
+      "step": 118
+    },
+    {
+      "epoch": 1.8142857142857143,
+      "grad_norm": 0.36397509002448036,
+      "learning_rate": 6.40649625289969e-05,
+      "loss": 0.5206,
+      "step": 119
+    },
+    {
+      "epoch": 1.8295238095238096,
+      "grad_norm": 0.5225246500798869,
+      "learning_rate": 6.371981754949241e-05,
+      "loss": 0.5233,
+      "step": 120
+    },
+    {
+      "epoch": 1.8447619047619046,
+      "grad_norm": 0.6419719236551851,
+      "learning_rate": 6.337192694513474e-05,
+      "loss": 0.5265,
+      "step": 121
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.41672473350375433,
+      "learning_rate": 6.30213309850823e-05,
+      "loss": 0.5165,
+      "step": 122
+    },
+    {
+      "epoch": 1.8752380952380951,
+      "grad_norm": 0.29619919377664744,
+      "learning_rate": 6.266807025164472e-05,
+      "loss": 0.5158,
+      "step": 123
+    },
+    {
+      "epoch": 1.8904761904761904,
+      "grad_norm": 0.41731867813128104,
+      "learning_rate": 6.231218563558551e-05,
+      "loss": 0.518,
+      "step": 124
+    },
+    {
+      "epoch": 1.9057142857142857,
+      "grad_norm": 0.3648760435140768,
+      "learning_rate": 6.195371833138878e-05,
+      "loss": 0.5165,
+      "step": 125
+    },
+    {
+      "epoch": 1.920952380952381,
+      "grad_norm": 0.3531467699123105,
+      "learning_rate": 6.159270983249084e-05,
+      "loss": 0.5247,
+      "step": 126
+    },
+    {
+      "epoch": 1.9361904761904762,
+      "grad_norm": 0.45588003744063627,
+      "learning_rate": 6.122920192647734e-05,
+      "loss": 0.5197,
+      "step": 127
+    },
+    {
+      "epoch": 1.9514285714285715,
+      "grad_norm": 0.5510619573466758,
+      "learning_rate": 6.086323669024616e-05,
+      "loss": 0.5256,
+      "step": 128
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.5646853258922581,
+      "learning_rate": 6.049485648513696e-05,
+      "loss": 0.527,
+      "step": 129
+    },
+    {
+      "epoch": 1.981904761904762,
+      "grad_norm": 0.4479646401937566,
+      "learning_rate": 6.012410395202774e-05,
+      "loss": 0.5234,
+      "step": 130
+    },
+    {
+      "epoch": 1.997142857142857,
+      "grad_norm": 0.575986791359234,
+      "learning_rate": 5.9751022006399095e-05,
+      "loss": 0.7009,
+      "step": 131
+    },
+    {
+      "epoch": 2.013333333333333,
+      "grad_norm": 0.814219365805337,
+      "learning_rate": 5.9375653833366585e-05,
+      "loss": 0.5404,
+      "step": 132
+    },
+    {
+      "epoch": 2.0285714285714285,
+      "grad_norm": 0.8146199046124171,
+      "learning_rate": 5.8998042882682024e-05,
+      "loss": 0.4877,
+      "step": 133
+    },
+    {
+      "epoch": 2.0438095238095237,
+      "grad_norm": 0.7629490780519704,
+      "learning_rate": 5.861823286370396e-05,
+      "loss": 0.4849,
+      "step": 134
+    },
+    {
+      "epoch": 2.059047619047619,
+      "grad_norm": 0.6570978207497692,
+      "learning_rate": 5.823626774033836e-05,
+      "loss": 0.4887,
+      "step": 135
+    },
+    {
+      "epoch": 2.0742857142857143,
+      "grad_norm": 0.5305731216336181,
+      "learning_rate": 5.7852191725949564e-05,
+      "loss": 0.4881,
+      "step": 136
+    },
+    {
+      "epoch": 2.0895238095238096,
+      "grad_norm": 0.512493977688762,
+      "learning_rate": 5.746604927824257e-05,
+      "loss": 0.4844,
+      "step": 137
+    },
+    {
+      "epoch": 2.104761904761905,
+      "grad_norm": 0.4828622337949408,
+      "learning_rate": 5.707788509411685e-05,
+      "loss": 0.4887,
+      "step": 138
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.4884027438000281,
+      "learning_rate": 5.668774410449268e-05,
+      "loss": 0.4908,
+      "step": 139
+    },
+    {
+      "epoch": 2.1352380952380954,
+      "grad_norm": 0.42776751878992564,
+      "learning_rate": 5.629567146911023e-05,
+      "loss": 0.4872,
+      "step": 140
+    },
+    {
+      "epoch": 2.1504761904761907,
+      "grad_norm": 0.36115257273207996,
+      "learning_rate": 5.590171257130225e-05,
+      "loss": 0.4861,
+      "step": 141
+    },
+    {
+      "epoch": 2.1657142857142855,
+      "grad_norm": 0.38436733504559367,
+      "learning_rate": 5.550591301274073e-05,
+      "loss": 0.4844,
+      "step": 142
+    },
+    {
+      "epoch": 2.1809523809523808,
+      "grad_norm": 0.3435583779900254,
+      "learning_rate": 5.5108318608158595e-05,
+      "loss": 0.4836,
+      "step": 143
+    },
+    {
+      "epoch": 2.196190476190476,
+      "grad_norm": 0.2857883944660014,
+      "learning_rate": 5.4708975380046356e-05,
+      "loss": 0.4796,
+      "step": 144
+    },
+    {
+      "epoch": 2.2114285714285713,
+      "grad_norm": 0.31512140613431383,
+      "learning_rate": 5.430792955332503e-05,
+      "loss": 0.4863,
+      "step": 145
+    },
+    {
+      "epoch": 2.2266666666666666,
+      "grad_norm": 0.31769228977835245,
+      "learning_rate": 5.3905227549995366e-05,
+      "loss": 0.4809,
+      "step": 146
+    },
+    {
+      "epoch": 2.241904761904762,
+      "grad_norm": 0.27924100773876076,
+      "learning_rate": 5.350091598376454e-05,
+      "loss": 0.4805,
+      "step": 147
+    },
+    {
+      "epoch": 2.257142857142857,
+      "grad_norm": 0.2662485345450648,
+      "learning_rate": 5.3095041654650384e-05,
+      "loss": 0.4831,
+      "step": 148
+    },
+    {
+      "epoch": 2.2723809523809524,
+      "grad_norm": 0.23461248952656025,
+      "learning_rate": 5.268765154356425e-05,
+      "loss": 0.4816,
+      "step": 149
+    },
+    {
+      "epoch": 2.2876190476190477,
+      "grad_norm": 0.240243576104443,
+      "learning_rate": 5.227879280687281e-05,
+      "loss": 0.4788,
+      "step": 150
+    },
+    {
+      "epoch": 2.302857142857143,
+      "grad_norm": 0.24392104367270967,
+      "learning_rate": 5.186851277093961e-05,
+      "loss": 0.4851,
+      "step": 151
+    },
+    {
+      "epoch": 2.318095238095238,
+      "grad_norm": 0.19828908319240954,
+      "learning_rate": 5.1456858926646974e-05,
+      "loss": 0.4817,
+      "step": 152
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.2354905746190516,
+      "learning_rate": 5.104387892389877e-05,
+      "loss": 0.4816,
+      "step": 153
+    },
+    {
+      "epoch": 2.3485714285714288,
+      "grad_norm": 0.24408900516772156,
+      "learning_rate": 5.062962056610478e-05,
+      "loss": 0.4833,
+      "step": 154
+    },
+    {
+      "epoch": 2.3638095238095236,
+      "grad_norm": 0.22588988217182931,
+      "learning_rate": 5.021413180464748e-05,
+      "loss": 0.4884,
+      "step": 155
+    },
+    {
+      "epoch": 2.379047619047619,
+      "grad_norm": 0.20985654308992252,
+      "learning_rate": 4.979746073333145e-05,
+      "loss": 0.4777,
+      "step": 156
+    },
+    {
+      "epoch": 2.394285714285714,
+      "grad_norm": 0.24110384355800776,
+      "learning_rate": 4.9379655582816396e-05,
+      "loss": 0.4867,
+      "step": 157
+    },
+    {
+      "epoch": 2.4095238095238094,
+      "grad_norm": 0.20401637758198887,
+      "learning_rate": 4.896076471503439e-05,
+      "loss": 0.4766,
+      "step": 158
+    },
+    {
+      "epoch": 2.4247619047619047,
+      "grad_norm": 0.19932449853927872,
+      "learning_rate": 4.854083661759185e-05,
+      "loss": 0.4884,
+      "step": 159
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.24533376047455172,
+      "learning_rate": 4.8119919898156934e-05,
+      "loss": 0.4834,
+      "step": 160
+    },
+    {
+      "epoch": 2.455238095238095,
+      "grad_norm": 0.19336383545060395,
+      "learning_rate": 4.76980632788332e-05,
+      "loss": 0.4779,
+      "step": 161
+    },
+    {
+      "epoch": 2.4704761904761905,
+      "grad_norm": 0.19824370981981676,
+      "learning_rate": 4.7275315590519765e-05,
+      "loss": 0.4823,
+      "step": 162
+    },
+    {
+      "epoch": 2.4857142857142858,
+      "grad_norm": 0.20431330071012052,
+      "learning_rate": 4.6851725767259106e-05,
+      "loss": 0.4781,
+      "step": 163
+    },
+    {
+      "epoch": 2.500952380952381,
+      "grad_norm": 0.2082524151757895,
+      "learning_rate": 4.642734284057283e-05,
+      "loss": 0.4755,
+      "step": 164
+    },
+    {
+      "epoch": 2.5161904761904763,
+      "grad_norm": 0.2129960852067495,
+      "learning_rate": 4.600221593378611e-05,
+      "loss": 0.4796,
+      "step": 165
+    },
+    {
+      "epoch": 2.5314285714285716,
+      "grad_norm": 0.17147652502249622,
+      "learning_rate": 4.5576394256341596e-05,
+      "loss": 0.4784,
+      "step": 166
+    },
+    {
+      "epoch": 2.546666666666667,
+      "grad_norm": 0.2328806782705143,
+      "learning_rate": 4.514992709810324e-05,
+      "loss": 0.4839,
+      "step": 167
+    },
+    {
+      "epoch": 2.5619047619047617,
+      "grad_norm": 0.2628457128916824,
+      "learning_rate": 4.472286382365096e-05,
+      "loss": 0.4899,
+      "step": 168
+    },
+    {
+      "epoch": 2.5771428571428574,
+      "grad_norm": 0.20530497111629914,
+      "learning_rate": 4.429525386656653e-05,
+      "loss": 0.4865,
+      "step": 169
+    },
+    {
+      "epoch": 2.5923809523809522,
+      "grad_norm": 0.18615860925149122,
+      "learning_rate": 4.38671467237115e-05,
+      "loss": 0.4841,
+      "step": 170
+    },
+    {
+      "epoch": 2.6076190476190475,
+      "grad_norm": 0.181524499480342,
+      "learning_rate": 4.343859194949787e-05,
+      "loss": 0.4792,
+      "step": 171
+    },
+    {
+      "epoch": 2.6228571428571428,
+      "grad_norm": 0.2025029996461714,
+      "learning_rate": 4.3009639150152e-05,
+      "loss": 0.4788,
+      "step": 172
+    },
+    {
+      "epoch": 2.638095238095238,
+      "grad_norm": 0.19560730560439193,
+      "learning_rate": 4.2580337977972664e-05,
+      "loss": 0.4827,
+      "step": 173
+    },
+    {
+      "epoch": 2.6533333333333333,
+      "grad_norm": 0.16741577940585486,
+      "learning_rate": 4.215073812558352e-05,
+      "loss": 0.4885,
+      "step": 174
+    },
+    {
+      "epoch": 2.6685714285714286,
+      "grad_norm": 0.1739859347419123,
+      "learning_rate": 4.1720889320181224e-05,
+      "loss": 0.4772,
+      "step": 175
+    },
+    {
+      "epoch": 2.683809523809524,
+      "grad_norm": 0.19324214245630159,
+      "learning_rate": 4.1290841317779325e-05,
+      "loss": 0.4884,
+      "step": 176
+    },
+    {
+      "epoch": 2.699047619047619,
+      "grad_norm": 0.162133413448313,
+      "learning_rate": 4.0860643897448894e-05,
+      "loss": 0.4789,
+      "step": 177
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.1910560430197172,
+      "learning_rate": 4.043034685555647e-05,
+      "loss": 0.4807,
+      "step": 178
+    },
+    {
+      "epoch": 2.7295238095238097,
+      "grad_norm": 0.14823981314032625,
+      "learning_rate": 4e-05,
+      "loss": 0.481,
+      "step": 179
+    },
+    {
+      "epoch": 2.744761904761905,
+      "grad_norm": 0.1784212235327859,
+      "learning_rate": 3.9569653144443546e-05,
+      "loss": 0.481,
+      "step": 180
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.200733513756011,
+      "learning_rate": 3.913935610255112e-05,
+      "loss": 0.4763,
+      "step": 181
+    },
+    {
+      "epoch": 2.7752380952380955,
+      "grad_norm": 0.14938330915090647,
+      "learning_rate": 3.870915868222068e-05,
+      "loss": 0.4819,
+      "step": 182
+    },
+    {
+      "epoch": 2.7904761904761903,
+      "grad_norm": 0.1739261226284681,
+      "learning_rate": 3.8279110679818775e-05,
+      "loss": 0.4738,
+      "step": 183
+    },
+    {
+      "epoch": 2.8057142857142856,
+      "grad_norm": 0.19838890478019414,
+      "learning_rate": 3.78492618744165e-05,
+      "loss": 0.4783,
+      "step": 184
+    },
+    {
+      "epoch": 2.820952380952381,
+      "grad_norm": 0.1528772994448381,
+      "learning_rate": 3.7419662022027356e-05,
+      "loss": 0.4769,
+      "step": 185
+    },
+    {
+      "epoch": 2.836190476190476,
+      "grad_norm": 0.1919042097767604,
+      "learning_rate": 3.6990360849848005e-05,
+      "loss": 0.4757,
+      "step": 186
+    },
+    {
+      "epoch": 2.8514285714285714,
+      "grad_norm": 0.17566953990872838,
+      "learning_rate": 3.656140805050215e-05,
+      "loss": 0.4786,
+      "step": 187
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.1637970789000741,
+      "learning_rate": 3.6132853276288506e-05,
+      "loss": 0.4739,
+      "step": 188
+    },
+    {
+      "epoch": 2.881904761904762,
+      "grad_norm": 0.18549958217752188,
+      "learning_rate": 3.570474613343348e-05,
+      "loss": 0.4768,
+      "step": 189
+    },
+    {
+      "epoch": 2.8971428571428572,
+      "grad_norm": 0.18002674770058677,
+      "learning_rate": 3.527713617634904e-05,
+      "loss": 0.4733,
+      "step": 190
+    },
+    {
+      "epoch": 2.9123809523809525,
+      "grad_norm": 0.15898767756027013,
+      "learning_rate": 3.4850072901896766e-05,
+      "loss": 0.4802,
+      "step": 191
+    },
+    {
+      "epoch": 2.9276190476190473,
+      "grad_norm": 0.17974934358276728,
+      "learning_rate": 3.442360574365843e-05,
+      "loss": 0.4834,
+      "step": 192
+    },
+    {
+      "epoch": 2.942857142857143,
+      "grad_norm": 0.14203142815133346,
+      "learning_rate": 3.39977840662139e-05,
+      "loss": 0.4747,
+      "step": 193
+    },
+    {
+      "epoch": 2.958095238095238,
+      "grad_norm": 0.17952115377014885,
+      "learning_rate": 3.3572657159427186e-05,
+      "loss": 0.4808,
+      "step": 194
+    },
+    {
+      "epoch": 2.9733333333333336,
+      "grad_norm": 0.17353334331590287,
+      "learning_rate": 3.31482742327409e-05,
+      "loss": 0.4751,
+      "step": 195
+    },
+    {
+      "epoch": 2.9885714285714284,
+      "grad_norm": 0.1528037773950146,
+      "learning_rate": 3.272468440948025e-05,
+      "loss": 0.4734,
+      "step": 196
+    },
+    {
+      "epoch": 3.0047619047619047,
+      "grad_norm": 0.20480536463226645,
+      "learning_rate": 3.230193672116681e-05,
+      "loss": 0.6928,
+      "step": 197
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 0.19151123516717333,
+      "learning_rate": 3.188008010184306e-05,
+      "loss": 0.4452,
+      "step": 198
+    },
+    {
+      "epoch": 3.0352380952380953,
+      "grad_norm": 0.2104984649163227,
+      "learning_rate": 3.145916338240816e-05,
+      "loss": 0.4546,
+      "step": 199
+    },
+    {
+      "epoch": 3.0504761904761906,
+      "grad_norm": 0.19741714449829997,
+      "learning_rate": 3.103923528496562e-05,
+      "loss": 0.4452,
+      "step": 200
+    },
+    {
+      "epoch": 3.065714285714286,
+      "grad_norm": 0.19623857285807467,
+      "learning_rate": 3.062034441718362e-05,
+      "loss": 0.4483,
+      "step": 201
+    },
+    {
+      "epoch": 3.080952380952381,
+      "grad_norm": 0.25035024771569697,
+      "learning_rate": 3.0202539266668568e-05,
+      "loss": 0.4506,
+      "step": 202
+    },
+    {
+      "epoch": 3.0961904761904764,
+      "grad_norm": 0.16968910324281286,
+      "learning_rate": 2.9785868195352525e-05,
+      "loss": 0.4449,
+      "step": 203
+    },
+    {
+      "epoch": 3.111428571428571,
+      "grad_norm": 0.23581488026041375,
+      "learning_rate": 2.9370379433895228e-05,
+      "loss": 0.4512,
+      "step": 204
+    },
+    {
+      "epoch": 3.1266666666666665,
+      "grad_norm": 0.15672745746884265,
+      "learning_rate": 2.8956121076101244e-05,
+      "loss": 0.449,
+      "step": 205
+    },
+    {
+      "epoch": 3.1419047619047618,
+      "grad_norm": 0.20702186752340365,
+      "learning_rate": 2.8543141073353026e-05,
+      "loss": 0.4439,
+      "step": 206
+    },
+    {
+      "epoch": 3.157142857142857,
+      "grad_norm": 0.16133838526688454,
+      "learning_rate": 2.8131487229060387e-05,
+      "loss": 0.4427,
+      "step": 207
+    },
+    {
+      "epoch": 3.1723809523809523,
+      "grad_norm": 0.1854062242780086,
+      "learning_rate": 2.7721207193127212e-05,
+      "loss": 0.4472,
+      "step": 208
+    },
+    {
+      "epoch": 3.1876190476190476,
+      "grad_norm": 0.17182738319155882,
+      "learning_rate": 2.7312348456435766e-05,
+      "loss": 0.4453,
+      "step": 209
+    },
+    {
+      "epoch": 3.202857142857143,
+      "grad_norm": 0.16697225397908244,
+      "learning_rate": 2.6904958345349633e-05,
+      "loss": 0.4561,
+      "step": 210
+    },
+    {
+      "epoch": 3.218095238095238,
+      "grad_norm": 0.16821522604659328,
+      "learning_rate": 2.6499084016235475e-05,
+      "loss": 0.444,
+      "step": 211
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.14853827941880265,
+      "learning_rate": 2.609477245000464e-05,
+      "loss": 0.44,
+      "step": 212
+    },
+    {
+      "epoch": 3.2485714285714287,
+      "grad_norm": 0.1502037122279702,
+      "learning_rate": 2.569207044667498e-05,
+      "loss": 0.4494,
+      "step": 213
+    },
+    {
+      "epoch": 3.263809523809524,
+      "grad_norm": 0.16216155417715333,
+      "learning_rate": 2.529102461995364e-05,
+      "loss": 0.4471,
+      "step": 214
+    },
+    {
+      "epoch": 3.279047619047619,
+      "grad_norm": 0.1586744564208733,
+      "learning_rate": 2.48916813918414e-05,
+      "loss": 0.4486,
+      "step": 215
+    },
+    {
+      "epoch": 3.2942857142857145,
+      "grad_norm": 0.14092622353201845,
+      "learning_rate": 2.449408698725928e-05,
+      "loss": 0.445,
+      "step": 216
+    },
+    {
+      "epoch": 3.3095238095238093,
+      "grad_norm": 0.15562276697944483,
+      "learning_rate": 2.409828742869777e-05,
+      "loss": 0.4415,
+      "step": 217
+    },
+    {
+      "epoch": 3.3247619047619046,
+      "grad_norm": 0.14631955274946826,
+      "learning_rate": 2.370432853088978e-05,
+      "loss": 0.454,
+      "step": 218
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 0.14585582091880941,
+      "learning_rate": 2.3312255895507336e-05,
+      "loss": 0.4473,
+      "step": 219
+    },
+    {
+      "epoch": 3.355238095238095,
+      "grad_norm": 0.1458201114996886,
+      "learning_rate": 2.2922114905883167e-05,
+      "loss": 0.4444,
+      "step": 220
+    },
+    {
+      "epoch": 3.3704761904761904,
+      "grad_norm": 0.1402608135797642,
+      "learning_rate": 2.2533950721757447e-05,
+      "loss": 0.4465,
+      "step": 221
+    },
+    {
+      "epoch": 3.3857142857142857,
+      "grad_norm": 0.14672569191797688,
+      "learning_rate": 2.2147808274050436e-05,
+      "loss": 0.4484,
+      "step": 222
+    },
+    {
+      "epoch": 3.400952380952381,
+      "grad_norm": 0.15377591576947733,
+      "learning_rate": 2.1763732259661657e-05,
+      "loss": 0.4479,
+      "step": 223
+    },
+    {
+      "epoch": 3.416190476190476,
+      "grad_norm": 0.14739415052119614,
+      "learning_rate": 2.138176713629605e-05,
+      "loss": 0.4475,
+      "step": 224
+    },
+    {
+      "epoch": 3.4314285714285715,
+      "grad_norm": 0.14607883746358746,
+      "learning_rate": 2.1001957117318002e-05,
+      "loss": 0.4421,
+      "step": 225
+    },
+    {
+      "epoch": 3.4466666666666668,
+      "grad_norm": 0.1465432249850391,
+      "learning_rate": 2.0624346166633425e-05,
+      "loss": 0.4396,
+      "step": 226
+    },
+    {
+      "epoch": 3.461904761904762,
+      "grad_norm": 0.12349201931738121,
+      "learning_rate": 2.0248977993600912e-05,
+      "loss": 0.4491,
+      "step": 227
+    },
+    {
+      "epoch": 3.4771428571428573,
+      "grad_norm": 0.14981067132432477,
+      "learning_rate": 1.987589604797227e-05,
+      "loss": 0.4448,
+      "step": 228
+    },
+    {
+      "epoch": 3.4923809523809526,
+      "grad_norm": 0.1137656845152472,
+      "learning_rate": 1.9505143514863056e-05,
+      "loss": 0.4489,
+      "step": 229
+    },
+    {
+      "epoch": 3.5076190476190474,
+      "grad_norm": 0.1398849247762614,
+      "learning_rate": 1.913676330975385e-05,
+      "loss": 0.4546,
+      "step": 230
+    },
+    {
+      "epoch": 3.522857142857143,
+      "grad_norm": 0.12820525613752842,
+      "learning_rate": 1.8770798073522657e-05,
+      "loss": 0.447,
+      "step": 231
+    },
+    {
+      "epoch": 3.538095238095238,
+      "grad_norm": 0.13773852598915348,
+      "learning_rate": 1.8407290167509163e-05,
+      "loss": 0.4543,
+      "step": 232
+    },
+    {
+      "epoch": 3.5533333333333332,
+      "grad_norm": 0.12262425169332791,
+      "learning_rate": 1.8046281668611242e-05,
+      "loss": 0.444,
+      "step": 233
+    },
+    {
+      "epoch": 3.5685714285714285,
+      "grad_norm": 0.11207677036541486,
+      "learning_rate": 1.7687814364414508e-05,
+      "loss": 0.4451,
+      "step": 234
+    },
+    {
+      "epoch": 3.583809523809524,
+      "grad_norm": 0.11456531045490899,
+      "learning_rate": 1.73319297483553e-05,
+      "loss": 0.4465,
+      "step": 235
+    },
+    {
+      "epoch": 3.599047619047619,
+      "grad_norm": 0.12011483524657235,
+      "learning_rate": 1.6978669014917723e-05,
+      "loss": 0.4406,
+      "step": 236
+    },
+    {
+      "epoch": 3.6142857142857143,
+      "grad_norm": 0.11200693227331737,
+      "learning_rate": 1.6628073054865262e-05,
+      "loss": 0.4539,
+      "step": 237
+    },
+    {
+      "epoch": 3.6295238095238096,
+      "grad_norm": 0.11945653235133909,
+      "learning_rate": 1.6280182450507593e-05,
+      "loss": 0.4505,
+      "step": 238
+    },
+    {
+      "epoch": 3.644761904761905,
+      "grad_norm": 0.11328522908106976,
+      "learning_rate": 1.593503747100309e-05,
+      "loss": 0.44,
+      "step": 239
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 0.11584353620347927,
+      "learning_rate": 1.5592678067697594e-05,
+      "loss": 0.4401,
+      "step": 240
+    },
+    {
+      "epoch": 3.675238095238095,
+      "grad_norm": 0.11338268232248719,
+      "learning_rate": 1.5253143869499875e-05,
+      "loss": 0.4526,
+      "step": 241
+    },
+    {
+      "epoch": 3.6904761904761907,
+      "grad_norm": 0.11825521687064344,
+      "learning_rate": 1.4916474178294578e-05,
+      "loss": 0.4472,
+      "step": 242
+    },
+    {
+      "epoch": 3.7057142857142855,
+      "grad_norm": 0.10393717835800384,
+      "learning_rate": 1.4582707964392909e-05,
+      "loss": 0.4503,
+      "step": 243
+    },
+    {
+      "epoch": 3.720952380952381,
+      "grad_norm": 0.11344323679399201,
+      "learning_rate": 1.4251883862021715e-05,
+      "loss": 0.4507,
+      "step": 244
+    },
+    {
+      "epoch": 3.736190476190476,
+      "grad_norm": 0.11795276330820621,
+      "learning_rate": 1.3924040164851497e-05,
+      "loss": 0.4509,
+      "step": 245
+    },
+    {
+      "epoch": 3.7514285714285713,
+      "grad_norm": 0.10446068928724489,
+      "learning_rate": 1.359921482156382e-05,
+      "loss": 0.453,
+      "step": 246
+    },
+    {
+      "epoch": 3.7666666666666666,
+      "grad_norm": 0.11963166659223025,
+      "learning_rate": 1.3277445431458653e-05,
+      "loss": 0.4423,
+      "step": 247
+    },
+    {
+      "epoch": 3.781904761904762,
+      "grad_norm": 0.11133235152901447,
+      "learning_rate": 1.2958769240102206e-05,
+      "loss": 0.4465,
+      "step": 248
+    },
+    {
+      "epoch": 3.797142857142857,
+      "grad_norm": 0.10488189725095455,
+      "learning_rate": 1.264322313501559e-05,
+      "loss": 0.4495,
+      "step": 249
+    },
+    {
+      "epoch": 3.8123809523809524,
+      "grad_norm": 0.09788048647298295,
+      "learning_rate": 1.2330843641405057e-05,
+      "loss": 0.4451,
+      "step": 250
+    },
+    {
+      "epoch": 3.8276190476190477,
+      "grad_norm": 0.1068932171231341,
+      "learning_rate": 1.2021666917934125e-05,
+      "loss": 0.4473,
+      "step": 251
+    },
+    {
+      "epoch": 3.842857142857143,
+      "grad_norm": 0.09965606097681808,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.4443,
+      "step": 252
+    },
+    {
+      "epoch": 3.8580952380952382,
+      "grad_norm": 0.10053631876045145,
+      "learning_rate": 1.1413064558281564e-05,
+      "loss": 0.4468,
+      "step": 253
+    },
+    {
+      "epoch": 3.873333333333333,
+      "grad_norm": 0.09801079877642455,
+      "learning_rate": 1.1113709369259187e-05,
+      "loss": 0.4426,
+      "step": 254
+    },
+    {
+      "epoch": 3.888571428571429,
+      "grad_norm": 0.09483370655189176,
+      "learning_rate": 1.0817697836540493e-05,
+      "loss": 0.4493,
+      "step": 255
+    },
+    {
+      "epoch": 3.9038095238095236,
+      "grad_norm": 0.09358289511323944,
+      "learning_rate": 1.052506422415891e-05,
+      "loss": 0.4415,
+      "step": 256
+    },
+    {
+      "epoch": 3.919047619047619,
+      "grad_norm": 0.09937735008586661,
+      "learning_rate": 1.0235842405145587e-05,
+      "loss": 0.447,
+      "step": 257
+    },
+    {
+      "epoch": 3.934285714285714,
+      "grad_norm": 0.09713725112426527,
+      "learning_rate": 9.950065857608537e-06,
+      "loss": 0.4449,
+      "step": 258
+    },
+    {
+      "epoch": 3.9495238095238094,
+      "grad_norm": 0.10061824714900855,
+      "learning_rate": 9.667767660857508e-06,
+      "loss": 0.4378,
+      "step": 259
+    },
+    {
+      "epoch": 3.9647619047619047,
+      "grad_norm": 0.09975526240303212,
+      "learning_rate": 9.388980491574901e-06,
+      "loss": 0.4485,
+      "step": 260
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.09583315993538538,
+      "learning_rate": 9.11373662003343e-06,
+      "loss": 0.4518,
+      "step": 261
+    },
+    {
+      "epoch": 3.9952380952380953,
+      "grad_norm": 0.12153372041343533,
+      "learning_rate": 8.842067906360716e-06,
+      "loss": 0.559,
+      "step": 262
+    },
+    {
+      "epoch": 4.011428571428572,
+      "grad_norm": 0.14086095004056465,
+      "learning_rate": 8.574005796851419e-06,
+      "loss": 0.5283,
+      "step": 263
+    },
+    {
+      "epoch": 4.026666666666666,
+      "grad_norm": 0.11788004209905123,
+      "learning_rate": 8.309581320327282e-06,
+      "loss": 0.4248,
+      "step": 264
+    },
+    {
+      "epoch": 4.041904761904762,
+      "grad_norm": 0.11207857563036874,
+      "learning_rate": 8.048825084545413e-06,
+      "loss": 0.4208,
+      "step": 265
+    },
+    {
+      "epoch": 4.057142857142857,
+      "grad_norm": 0.11130142780853505,
+      "learning_rate": 7.791767272655403e-06,
+      "loss": 0.4282,
+      "step": 266
+    },
+    {
+      "epoch": 4.072380952380953,
+      "grad_norm": 0.11636579346899405,
+      "learning_rate": 7.5384376397055644e-06,
+      "loss": 0.4275,
+      "step": 267
+    },
+    {
+      "epoch": 4.0876190476190475,
+      "grad_norm": 0.12911191155727517,
+      "learning_rate": 7.2888655091986995e-06,
+      "loss": 0.4296,
+      "step": 268
+    },
+    {
+      "epoch": 4.102857142857143,
+      "grad_norm": 0.1207757027022162,
+      "learning_rate": 7.043079769697833e-06,
+      "loss": 0.4301,
+      "step": 269
+    },
+    {
+      "epoch": 4.118095238095238,
+      "grad_norm": 0.10942499693335449,
+      "learning_rate": 6.801108871482287e-06,
+      "loss": 0.432,
+      "step": 270
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 0.11446276362313004,
+      "learning_rate": 6.562980823254519e-06,
+      "loss": 0.4313,
+      "step": 271
+    },
+    {
+      "epoch": 4.148571428571429,
+      "grad_norm": 0.11355557887705738,
+      "learning_rate": 6.328723188898029e-06,
+      "loss": 0.4279,
+      "step": 272
+    },
+    {
+      "epoch": 4.163809523809523,
+      "grad_norm": 0.1062761145201427,
+      "learning_rate": 6.098363084286765e-06,
+      "loss": 0.4259,
+      "step": 273
+    },
+    {
+      "epoch": 4.179047619047619,
+      "grad_norm": 0.10273617911128365,
+      "learning_rate": 5.8719271741464056e-06,
+      "loss": 0.4225,
+      "step": 274
+    },
+    {
+      "epoch": 4.194285714285714,
+      "grad_norm": 0.10086062111767927,
+      "learning_rate": 5.6494416689678855e-06,
+      "loss": 0.4189,
+      "step": 275
+    },
+    {
+      "epoch": 4.20952380952381,
+      "grad_norm": 0.09559781846200713,
+      "learning_rate": 5.430932321973425e-06,
+      "loss": 0.4158,
+      "step": 276
+    },
+    {
+      "epoch": 4.2247619047619045,
+      "grad_norm": 0.09465874774217785,
+      "learning_rate": 5.21642442613556e-06,
+      "loss": 0.4299,
+      "step": 277
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.09527880228230132,
+      "learning_rate": 5.005942811249412e-06,
+      "loss": 0.4243,
+      "step": 278
+    },
+    {
+      "epoch": 4.255238095238095,
+      "grad_norm": 0.09428002792877421,
+      "learning_rate": 4.799511841058575e-06,
+      "loss": 0.4262,
+      "step": 279
+    },
+    {
+      "epoch": 4.270476190476191,
+      "grad_norm": 0.09763553814742547,
+      "learning_rate": 4.597155410434972e-06,
+      "loss": 0.4247,
+      "step": 280
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.09287137908820702,
+      "learning_rate": 4.398896942612934e-06,
+      "loss": 0.4238,
+      "step": 281
+    },
+    {
+      "epoch": 4.300952380952381,
+      "grad_norm": 0.09888369046987704,
+      "learning_rate": 4.204759386477961e-06,
+      "loss": 0.4391,
+      "step": 282
+    },
+    {
+      "epoch": 4.316190476190476,
+      "grad_norm": 0.09609824332962343,
+      "learning_rate": 4.01476521391027e-06,
+      "loss": 0.4352,
+      "step": 283
+    },
+    {
+      "epoch": 4.331428571428571,
+      "grad_norm": 0.09233308942677047,
+      "learning_rate": 3.828936417183671e-06,
+      "loss": 0.43,
+      "step": 284
+    },
+    {
+      "epoch": 4.346666666666667,
+      "grad_norm": 0.0890288964909307,
+      "learning_rate": 3.6472945064198827e-06,
+      "loss": 0.427,
+      "step": 285
+    },
+    {
+      "epoch": 4.3619047619047615,
+      "grad_norm": 0.08989519773450554,
+      "learning_rate": 3.4698605070987077e-06,
+      "loss": 0.4257,
+      "step": 286
+    },
+    {
+      "epoch": 4.377142857142857,
+      "grad_norm": 0.09526649707374434,
+      "learning_rate": 3.2966549576242477e-06,
+      "loss": 0.4357,
+      "step": 287
+    },
+    {
+      "epoch": 4.392380952380952,
+      "grad_norm": 0.09131870660723178,
+      "learning_rate": 3.127697906947584e-06,
+      "loss": 0.4272,
+      "step": 288
+    },
+    {
+      "epoch": 4.407619047619048,
+      "grad_norm": 0.08945756240639792,
+      "learning_rate": 2.963008912246008e-06,
+      "loss": 0.4347,
+      "step": 289
+    },
+    {
+      "epoch": 4.422857142857143,
+      "grad_norm": 0.08483664610068463,
+      "learning_rate": 2.802607036659284e-06,
+      "loss": 0.4294,
+      "step": 290
+    },
+    {
+      "epoch": 4.438095238095238,
+      "grad_norm": 0.08486549550090346,
+      "learning_rate": 2.646510847082997e-06,
+      "loss": 0.4303,
+      "step": 291
+    },
+    {
+      "epoch": 4.453333333333333,
+      "grad_norm": 0.084355078151828,
+      "learning_rate": 2.494738412019442e-06,
+      "loss": 0.423,
+      "step": 292
+    },
+    {
+      "epoch": 4.468571428571429,
+      "grad_norm": 0.08518364314817348,
+      "learning_rate": 2.3473072994861167e-06,
+      "loss": 0.427,
+      "step": 293
+    },
+    {
+      "epoch": 4.483809523809524,
+      "grad_norm": 0.08287931866258626,
+      "learning_rate": 2.2042345749821913e-06,
+      "loss": 0.4216,
+      "step": 294
+    },
+    {
+      "epoch": 4.499047619047619,
+      "grad_norm": 0.08289838691379334,
+      "learning_rate": 2.065536799513135e-06,
+      "loss": 0.4288,
+      "step": 295
+    },
+    {
+      "epoch": 4.514285714285714,
+      "grad_norm": 0.0850326818939402,
+      "learning_rate": 1.9312300276737516e-06,
+      "loss": 0.4235,
+      "step": 296
+    },
+    {
+      "epoch": 4.529523809523809,
+      "grad_norm": 0.08392478938826013,
+      "learning_rate": 1.8013298057897932e-06,
+      "loss": 0.4293,
+      "step": 297
+    },
+    {
+      "epoch": 4.544761904761905,
+      "grad_norm": 0.0892781985318678,
+      "learning_rate": 1.6758511701184809e-06,
+      "loss": 0.4238,
+      "step": 298
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.08180406525124756,
+      "learning_rate": 1.5548086451079747e-06,
+      "loss": 0.4384,
+      "step": 299
+    },
+    {
+      "epoch": 4.575238095238095,
+      "grad_norm": 0.08011550631601072,
+      "learning_rate": 1.4382162417161748e-06,
+      "loss": 0.4206,
+      "step": 300
+    },
+    {
+      "epoch": 4.59047619047619,
+      "grad_norm": 0.08066581660175723,
+      "learning_rate": 1.3260874557889002e-06,
+      "loss": 0.4287,
+      "step": 301
+    },
+    {
+      "epoch": 4.605714285714286,
+      "grad_norm": 0.0806215224586864,
+      "learning_rate": 1.2184352664977105e-06,
+      "loss": 0.4175,
+      "step": 302
+    },
+    {
+      "epoch": 4.620952380952381,
+      "grad_norm": 0.07969848747023248,
+      "learning_rate": 1.115272134837544e-06,
+      "loss": 0.4312,
+      "step": 303
+    },
+    {
+      "epoch": 4.636190476190476,
+      "grad_norm": 0.0797095157185979,
+      "learning_rate": 1.0166100021843283e-06,
+      "loss": 0.4346,
+      "step": 304
+    },
+    {
+      "epoch": 4.651428571428571,
+      "grad_norm": 0.0792961159548818,
+      "learning_rate": 9.224602889127321e-07,
+      "loss": 0.4286,
+      "step": 305
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.08285323866652071,
+      "learning_rate": 8.328338930742296e-07,
+      "loss": 0.4267,
+      "step": 306
+    },
+    {
+      "epoch": 4.681904761904762,
+      "grad_norm": 0.07823875843722773,
+      "learning_rate": 7.477411891356268e-07,
+      "loss": 0.4276,
+      "step": 307
+    },
+    {
+      "epoch": 4.6971428571428575,
+      "grad_norm": 0.07763022247982207,
+      "learning_rate": 6.671920267782029e-07,
+      "loss": 0.4282,
+      "step": 308
+    },
+    {
+      "epoch": 4.712380952380952,
+      "grad_norm": 0.07871343041787499,
+      "learning_rate": 5.911957297575743e-07,
+      "loss": 0.4323,
+      "step": 309
+    },
+    {
+      "epoch": 4.727619047619047,
+      "grad_norm": 0.07681136995775628,
+      "learning_rate": 5.197610948244469e-07,
+      "loss": 0.4256,
+      "step": 310
+    },
+    {
+      "epoch": 4.742857142857143,
+      "grad_norm": 0.07665250706053243,
+      "learning_rate": 4.5289639070638103e-07,
+      "loss": 0.4171,
+      "step": 311
+    },
+    {
+      "epoch": 4.758095238095238,
+      "grad_norm": 0.07835687105047397,
+      "learning_rate": 3.906093571506597e-07,
+      "loss": 0.428,
+      "step": 312
+    },
+    {
+      "epoch": 4.773333333333333,
+      "grad_norm": 0.07949715755664716,
+      "learning_rate": 3.329072040284009e-07,
+      "loss": 0.4208,
+      "step": 313
+    },
+    {
+      "epoch": 4.788571428571428,
+      "grad_norm": 0.0773084553588578,
+      "learning_rate": 2.797966104999805e-07,
+      "loss": 0.4332,
+      "step": 314
+    },
+    {
+      "epoch": 4.803809523809524,
+      "grad_norm": 0.07795013678746698,
+      "learning_rate": 2.3128372424192635e-07,
+      "loss": 0.4377,
+      "step": 315
+    },
+    {
+      "epoch": 4.819047619047619,
+      "grad_norm": 0.07666311315306534,
+      "learning_rate": 1.8737416073529635e-07,
+      "loss": 0.4272,
+      "step": 316
+    },
+    {
+      "epoch": 4.8342857142857145,
+      "grad_norm": 0.07693103942282913,
+      "learning_rate": 1.4807300261568735e-07,
+      "loss": 0.4287,
+      "step": 317
+    },
+    {
+      "epoch": 4.849523809523809,
+      "grad_norm": 0.08092920067828374,
+      "learning_rate": 1.1338479908488798e-07,
+      "loss": 0.4337,
+      "step": 318
+    },
+    {
+      "epoch": 4.864761904761905,
+      "grad_norm": 0.07921080037622698,
+      "learning_rate": 8.331356538431313e-08,
+      "loss": 0.4262,
+      "step": 319
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.08216408996820164,
+      "learning_rate": 5.7862782330215804e-08,
+      "loss": 0.4317,
+      "step": 320
+    },
+    {
+      "epoch": 4.895238095238096,
+      "grad_norm": 0.07591222440722502,
+      "learning_rate": 3.703539591080052e-08,
+      "loss": 0.4232,
+      "step": 321
+    },
+    {
+      "epoch": 4.91047619047619,
+      "grad_norm": 0.08045135907636206,
+      "learning_rate": 2.0833816945184936e-08,
+      "loss": 0.4297,
+      "step": 322
+    },
+    {
+      "epoch": 4.925714285714285,
+      "grad_norm": 0.07684321088822434,
+      "learning_rate": 9.25992080436533e-09,
+      "loss": 0.4276,
+      "step": 323
+    },
+    {
+      "epoch": 4.940952380952381,
+      "grad_norm": 0.07680665420588856,
+      "learning_rate": 2.315047194136888e-09,
+      "loss": 0.4271,
+      "step": 324
+    },
+    {
+      "epoch": 4.956190476190476,
+      "grad_norm": 0.07663586105720761,
+      "learning_rate": 0.0,
+      "loss": 0.4248,
+      "step": 325
+    },
+    {
+      "epoch": 4.956190476190476,
+      "step": 325,
+      "total_flos": 8.641809758367515e+18,
+      "train_loss": 0.5190348960803105,
+      "train_runtime": 75842.3225,
+      "train_samples_per_second": 2.214,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 325,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.641809758367515e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f642af834941fc6bfdbb96bfb9a1a20001ee4d72947818fc929129d8b1acc3
+size 7288