Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,48 @@ 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
+distillm/results/qwen1.5/distillm_0.5B_1.8B_on_srkl/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/fdd_0.5B_1.8B/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/sft/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_0.5B_1.8B_on_v5/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_0.5B_1.8B_on_v5/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a1/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a1/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a1/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a1/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a1/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a2/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a2/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a2/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a2/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a2/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a3/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a3/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a3/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a3/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a3/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a4/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a4/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a4/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a4/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spandistillm_a4/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spanfdd_0.5B_1.8B/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen1.5/spanfdd_0.5B_1.8B/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b_old/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b_old/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b_old/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b_old/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/fdd_3b_old/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b/2142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b/2856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b/3570/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b_old/1428/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen2.5/spanfdd_3b_old/714/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+distillm/results/qwen3-8B-lora/tokenizer.json filter=lfs diff=lfs merge=lfs -text

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/2856/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/2856/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/2856/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9a751d7d1e4f0ca34f60d512cab63a9df88d57ce55e0a3b72f9a3e588c587c
+size 248898556

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/2856/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/2856/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/3570/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/3570/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/3570/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2691ddfd76e6752faa3161d05c82b68cff673059d8607e8772522cb39e1e568
+size 248898556

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/3570/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/3570/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/distill_0.1B_1.5B_on_srkl/args.json

@@ -0,0 +1 @@
+{"model_path": "openai-community/gpt2", "ckpt_name": "gpt2-base", "model_type": "gpt2", "teacher_model_type": null, "n_gpu": 1, "n_nodes": 1, "teacher_model_path": "MiniLLM/teacher-gpt2-1.5B", "teacher_ckpt_name": "xlarge-sft", "teacher_model_fp16": true, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "bf16": false, "type": "adaptive-srkl", "do_train": true, "do_valid": true, "do_eval": false, "base_path": "./distillm-master", "load": null, "save": "./distillm-master/results/gpt2/train/distill_0.1B_1.5B_on_srkl", "log_interval": 4, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./distillm-master/processed_data/dolly/full/gpt2/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": 1000, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 1, "max_prompt_length": 128, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "batch_size": 8, "eval_batch_size": 64, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 256, "seed": 42, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 5, "training_epochs": 10000, "gradient_accumulation_steps": 2, "gradient_checkpointing": false, "attn_dtype": null, "lr": 0.0001, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": 1.0, "warmup_iters": 0, "warmup_ratio": 0.0, "lr_decay_iters": null, "lr_decay_style": "cosine", "scheduler_name": "constant_trm", "w_span_loss": 1.0, "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": true, "gen_top_p": 1.0, "gen_num_beams": 1, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "student_layer_mapping": [-1], "teacher_layer_mapping": [-1], "split_layer_mapping": [0, 0, 0, 0], "top_k": 0, "top_p": 1.0, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 1.0, "peft": null, "peft_lora_r": 16, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "deepspeed": true, "deepspeed_config": "./distillm-master/configs/deepspeed/ds_config.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 1}

distillm/results/gpt2/train/fdd_0.1B_1.5B/3570/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

distillm/results/gpt2/train/fdd_0.1B_1.5B/3570/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

distillm/results/gpt2/train/fdd_0.1B_1.5B/3570/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4491cd1e5268a437f0bcf832a4668b6c224d208a029fc4dabee8d8f26f987e4
+size 248898556

distillm/results/gpt2/train/fdd_0.1B_1.5B/3570/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/fdd_0.1B_1.5B/3570/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/fdd_0.1B_1.5B/args.json

@@ -0,0 +1 @@
+{"model_path": "openai-community/gpt2", "ckpt_name": "gpt2-base", "model_type": "gpt2", "teacher_model_type": null, "n_gpu": 1, "n_nodes": 1, "teacher_model_path": "MiniLLM/teacher-gpt2-1.5B", "teacher_ckpt_name": "xlarge-sft", "teacher_model_fp16": true, "model_parallel": false, "model_parallel_size": null, "no_value": false, "dropout_path_rate": null, "fp32": false, "bf16": false, "type": "adaptive-srkl", "do_train": true, "do_valid": true, "do_eval": false, "base_path": "./distillm-master", "load": null, "save": "./distillm-master/results/gpt2/train/fdd_0.1B_1.5B", "log_interval": 4, "mid_log_num": -1, "save_interval": -1, "eval_interval": -1, "local_rank": 0, "save_additional_suffix": "", "save_rollout": false, "eb_sample_times": 3, "data_dir": "./distillm-master/processed_data/dolly/full/gpt2/", "processed_data_dir": null, "force_process": false, "force_process_demo": false, "data_process_workers": -1, "train_num": -1, "train_ratio": 1, "dev_num": 1000, "dev_ratio": 1, "gen_num": -1, "data_names": null, "prompt_type": null, "num_workers": 1, "max_prompt_length": 128, "min_prompt_length": 128, "json_data": false, "bin_data": false, "txt_data": false, "prompt_data_dir": null, "lm_data_dir": null, "eval_ppl": false, "eval_rw": false, "eval_gen": true, "only_prompt": false, "batch_size": 16, "eval_batch_size": 64, "clip_grad": 1.0, "total_iters": null, "train_iters_per_epoch": -1, "max_length": 256, "seed": 42, "seed_order": 42, "seed_data": 42, "seed_ppo": 42, "seed_lm": 7, "epochs": 5, "training_epochs": 10000, "gradient_accumulation_steps": 1, "gradient_checkpointing": false, "attn_dtype": null, "lr": 0.0001, "lr_min": 1e-07, "weight_decay": 0.01, "loss_scale": 65536, "kd_ratio": 1.0, "warmup_iters": 0, "warmup_ratio": 0.1, "lr_decay_iters": null, "lr_decay_style": "cosine", "scheduler_name": "constant_trm", "w_span_loss": 1.0, "reward_scaling": null, "cliprange_reward": 1, "ppo_epochs": null, "num_rollouts": 256, "num_rollouts_per_device": null, "cliprange": 0.2, "chunk_size": null, "gamma": 0.95, "length_norm": false, "single_step_reg": false, "teacher_mixed_alpha": null, "lm_coef": 1, "skew_alpha": 0.1, "student_gen": true, "gen_top_p": 1.0, "gen_num_beams": 1, "mixed_alpha": 0.5, "loss_eps": 0.1, "init_threshold": 0.0, "capacity": 1000, "replay_ratio": "decreasing", "student_layer_mapping": [4, 6, 8], "teacher_layer_mapping": [16, 24, 32], "split_layer_mapping": [0, 0, 0, 0], "top_k": 0, "top_p": 1.0, "do_sample": true, "no_repeat_ngram_size": 6, "repetition_penalty": null, "num_beams": 1, "temperature": 1.0, "peft": null, "peft_lora_r": 16, "peft_lora_alpha": 64, "peft_lora_dropout": 0.1, "peft_name": null, "peft_path": null, "teacher_peft_name": null, "teacher_peft_path": null, "deepspeed": true, "deepspeed_config": "./distillm-master/configs/deepspeed/ds_config.json", "deepscale": false, "deepscale_config": null, "rank": 0, "world_size": 1}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b182acda70e98919c4cde9e621f3d20d9261f6467c7d59efbfe0c0dab8f8ab4
+size 256281854

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570_w_2.0/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "is_model_parallel": false,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50257
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570_w_2.0/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570_w_2.0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db8d7ef0c60a83997707157123d8d53192f30546f60b0fa6d61bc25892aacb1
+size 256281854

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570_w_2.0/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

distillm/results/gpt2/train/spandistill_0.1B_1.5B_on_v5/3570_w_2.0/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}