初始化项目，由ModelHub XC社区提供模型

Model: nbtpj/summ_gpt2_inst_cnnxsumsam
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: gpt2
+library_name: transformers
+model_name: summ_gpt2_inst_cnnxsumsam
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for summ_gpt2_inst_cnnxsumsam
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="nbtpj/summ_gpt2_inst_cnnxsumsam", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 4.57.3
+- Pytorch: 2.9.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

checkpoint-10904/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-10904/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

checkpoint-10904/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682128d38388b5c35f3d841f63df0e045a64be9bf103e12dfa3ac4036ac79df6
+size 497774208

checkpoint-10904/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46401320e32e818770650aa4d0280f7bf8e018d397b1aa21adbdebcb0b7895cc
+size 995644811

checkpoint-10904/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d911cd62b0c7da74ff05ce1279daf4f030c798f8db0f2bfb481231aae2f4e2
+size 14645

checkpoint-10904/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9688a20320146ba9e7761e040d688f6c6d02ee0fb9f076fefed9b05d332ec87
+size 1465

checkpoint-10904/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-10904/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-10904/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

checkpoint-16356/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-16356/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

checkpoint-16356/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f0f24015be6efde91a88a712316a753207836fcd586f5638376b5f133d607a
+size 497774208

checkpoint-16356/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07c106123c5b6b5721e8860116ca6046f9365a8d2778f3a8ea388b16de6c063
+size 995644811

checkpoint-16356/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e75c0c9c8a53907e4e789efd88669467307e368b14505f8abb018c9d2de871
+size 14645

checkpoint-16356/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155477148d606e22de656926b79d3e5a09d7032278ff9c4b6e32a676d1bf3013
+size 1465

checkpoint-16356/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-16356/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-16356/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

checkpoint-21808/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-21808/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

checkpoint-21808/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dccd16caef578cbb4657835b5fe256550766c65a0ed3bd3a5cd5bc131a37f2
+size 497774208

checkpoint-21808/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc8c000d0823878ae53ed06ef8ba6cc2427fa90ecf657d82bf1bf9849778290
+size 995644811

checkpoint-21808/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281dcc5acbacd57a0b6fa5e2a74e2d52b386210e9d670850327bd2ce97dc555b
+size 14645

checkpoint-21808/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59250c4a0489296f84910fe84e9ec3b3055eb3ba1e3165431ca5f46a7c145ea
+size 1465

checkpoint-21808/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-21808/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-21808/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

checkpoint-27260/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-27260/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

checkpoint-27260/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eefa3a15b7c22657770c8c2bcf67a43a625ceae58ffbe447bb5862c82a997d5
+size 497774208

checkpoint-27260/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918f5430245a9e35b1620468272d8b80b7292512b0414e81e013ef3b0a7a9432
+size 995644811

checkpoint-27260/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a13e4cad8dc4fd38766be2d14824cccbc9b35c5eb29e0ee2a611d0944cd9862
+size 14645

checkpoint-27260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fce38c19cc6a90d9bd4f69bd08eb393c5090f8f577e63687702849249fc3500
+size 1465

checkpoint-27260/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-27260/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-27260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

checkpoint-5452/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-5452/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

checkpoint-5452/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c38542388e982ffe1ddf113752f342e46427e67b9dc52a9cfe17b3674351fc
+size 497774208

checkpoint-5452/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e6d281dfe059ed484d7efa8b072adb90cbd2e1b8b92817ab467963ef9d3039
+size 995644811

checkpoint-5452/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c3d61c20a89c5db8872e9db1a4e77957946f7012662827e40c5dec345b5448
+size 14645

checkpoint-5452/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5bf1d0ccd7d31ad6d317a5a1d7834e2ccae1bc9ca3f1c69638644f9af0c8749
+size 1465

checkpoint-5452/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-5452/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-5452/trainer_state.json

@@ -0,0 +1,915 @@
+{
+  "best_global_step": 5452,
+  "best_metric": 2.662151575088501,
+  "best_model_checkpoint": "/common/home/users/m/mq.nguyen.2023/scratchDirectory/finetune/train_nbtpj_summ_gpt2_inst_cnnxsumsam/checkpoint-5452",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5452,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009172208209126348,
+      "grad_norm": 7.051512241363525,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 6.4476,
+      "num_tokens": 3070741.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.018344416418252695,
+      "grad_norm": 6.664697170257568,
+      "learning_rate": 1.98e-05,
+      "loss": 5.4332,
+      "num_tokens": 6150092.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.02751662462737904,
+      "grad_norm": 5.514298439025879,
+      "learning_rate": 1.9999839379410334e-05,
+      "loss": 4.9984,
+      "num_tokens": 9221796.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.03668883283650539,
+      "grad_norm": 4.882246494293213,
+      "learning_rate": 1.9999344344268732e-05,
+      "loss": 4.7556,
+      "num_tokens": 12294380.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.04586104104563173,
+      "grad_norm": 4.8477373123168945,
+      "learning_rate": 1.9998514844235922e-05,
+      "loss": 4.6238,
+      "num_tokens": 15366995.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.05503324925475808,
+      "grad_norm": 4.187108516693115,
+      "learning_rate": 1.9997350907057584e-05,
+      "loss": 4.5485,
+      "num_tokens": 18447066.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.06420545746388442,
+      "grad_norm": 5.372704982757568,
+      "learning_rate": 1.9995852571665885e-05,
+      "loss": 4.4819,
+      "num_tokens": 21511375.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.07337766567301078,
+      "grad_norm": 5.349086761474609,
+      "learning_rate": 1.9994019888178163e-05,
+      "loss": 4.3881,
+      "num_tokens": 24591962.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.08254987388213712,
+      "grad_norm": 4.023826599121094,
+      "learning_rate": 1.9991852917895272e-05,
+      "loss": 4.3618,
+      "num_tokens": 27676055.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.09172208209126347,
+      "grad_norm": 3.742589235305786,
+      "learning_rate": 1.9989351733299514e-05,
+      "loss": 4.3175,
+      "num_tokens": 30745102.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.10089429030038982,
+      "grad_norm": 3.394568681716919,
+      "learning_rate": 1.9986516418052213e-05,
+      "loss": 4.2946,
+      "num_tokens": 33797572.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.11006649850951616,
+      "grad_norm": 3.7485358715057373,
+      "learning_rate": 1.998334706699093e-05,
+      "loss": 4.2073,
+      "num_tokens": 36862581.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.1192387067186425,
+      "grad_norm": 3.286533832550049,
+      "learning_rate": 1.997984378612628e-05,
+      "loss": 4.1903,
+      "num_tokens": 39940075.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 3.757556676864624,
+      "learning_rate": 1.997600669263839e-05,
+      "loss": 4.1797,
+      "num_tokens": 43022248.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.13758312313689522,
+      "grad_norm": 3.648007392883301,
+      "learning_rate": 1.9971835914872985e-05,
+      "loss": 4.1506,
+      "num_tokens": 46088933.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.14675533134602156,
+      "grad_norm": 3.151127815246582,
+      "learning_rate": 1.996733159233708e-05,
+      "loss": 4.0749,
+      "num_tokens": 49170683.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.1559275395551479,
+      "grad_norm": 3.370467185974121,
+      "learning_rate": 1.9962493875694335e-05,
+      "loss": 4.0687,
+      "num_tokens": 52242629.0,
+      "step": 850
+    },
+    {
+      "epoch": 0.16509974776427425,
+      "grad_norm": 3.516242027282715,
+      "learning_rate": 1.995732292675999e-05,
+      "loss": 3.9537,
+      "num_tokens": 55316954.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.1742719559734006,
+      "grad_norm": 3.9187300205230713,
+      "learning_rate": 1.9951818918495474e-05,
+      "loss": 3.9209,
+      "num_tokens": 58384220.0,
+      "step": 950
+    },
+    {
+      "epoch": 0.18344416418252693,
+      "grad_norm": 3.647482395172119,
+      "learning_rate": 1.9945982035002613e-05,
+      "loss": 3.8353,
+      "num_tokens": 61463865.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1926163723916533,
+      "grad_norm": 4.165699005126953,
+      "learning_rate": 1.9939812471517463e-05,
+      "loss": 3.8031,
+      "num_tokens": 64528502.0,
+      "step": 1050
+    },
+    {
+      "epoch": 0.20178858060077964,
+      "grad_norm": 3.750986099243164,
+      "learning_rate": 1.99333104344038e-05,
+      "loss": 3.723,
+      "num_tokens": 67601444.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.21096078880990599,
+      "grad_norm": 4.958056926727295,
+      "learning_rate": 1.9926476141146186e-05,
+      "loss": 3.6597,
+      "num_tokens": 70661859.0,
+      "step": 1150
+    },
+    {
+      "epoch": 0.22013299701903233,
+      "grad_norm": 3.76973295211792,
+      "learning_rate": 1.9919309820342735e-05,
+      "loss": 3.5977,
+      "num_tokens": 73730542.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.22930520522815867,
+      "grad_norm": 4.332479953765869,
+      "learning_rate": 1.991181171169743e-05,
+      "loss": 3.5533,
+      "num_tokens": 76796322.0,
+      "step": 1250
+    },
+    {
+      "epoch": 0.238477413437285,
+      "grad_norm": 3.7759413719177246,
+      "learning_rate": 1.9903982066012126e-05,
+      "loss": 3.5245,
+      "num_tokens": 79858262.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.24764962164641138,
+      "grad_norm": 3.8706881999969482,
+      "learning_rate": 1.9895821145178148e-05,
+      "loss": 3.4821,
+      "num_tokens": 82926316.0,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 3.8657612800598145,
+      "learning_rate": 1.9887329222167548e-05,
+      "loss": 3.3993,
+      "num_tokens": 85997475.0,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2659940380646641,
+      "grad_norm": 3.64652156829834,
+      "learning_rate": 1.9878506581023957e-05,
+      "loss": 3.4047,
+      "num_tokens": 89061497.0,
+      "step": 1450
+    },
+    {
+      "epoch": 0.27516624627379044,
+      "grad_norm": 3.8434200286865234,
+      "learning_rate": 1.98693535168531e-05,
+      "loss": 3.3561,
+      "num_tokens": 92130920.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2843384544829168,
+      "grad_norm": 3.7041072845458984,
+      "learning_rate": 1.9859870335812904e-05,
+      "loss": 3.2907,
+      "num_tokens": 95201616.0,
+      "step": 1550
+    },
+    {
+      "epoch": 0.2935106626920431,
+      "grad_norm": 3.672961711883545,
+      "learning_rate": 1.9850057355103283e-05,
+      "loss": 3.2824,
+      "num_tokens": 98262928.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.30268287090116947,
+      "grad_norm": 4.109488487243652,
+      "learning_rate": 1.9839914902955514e-05,
+      "loss": 3.2584,
+      "num_tokens": 101331029.0,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3118550791102958,
+      "grad_norm": 3.8466403484344482,
+      "learning_rate": 1.982944331862125e-05,
+      "loss": 3.2185,
+      "num_tokens": 104400096.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.32102728731942215,
+      "grad_norm": 3.791473150253296,
+      "learning_rate": 1.9818642952361188e-05,
+      "loss": 3.2011,
+      "num_tokens": 107470267.0,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3301994955285485,
+      "grad_norm": 4.251014232635498,
+      "learning_rate": 1.9807514165433342e-05,
+      "loss": 3.1644,
+      "num_tokens": 110539470.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.33937170373767483,
+      "grad_norm": 3.785540819168091,
+      "learning_rate": 1.979605733008098e-05,
+      "loss": 3.129,
+      "num_tokens": 113605849.0,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3485439119468012,
+      "grad_norm": 3.8080990314483643,
+      "learning_rate": 1.978427282952014e-05,
+      "loss": 3.1142,
+      "num_tokens": 116669302.0,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3577161201559275,
+      "grad_norm": 4.565866470336914,
+      "learning_rate": 1.977216105792684e-05,
+      "loss": 3.0942,
+      "num_tokens": 119736059.0,
+      "step": 1950
+    },
+    {
+      "epoch": 0.36688832836505386,
+      "grad_norm": 3.6725170612335205,
+      "learning_rate": 1.9759722420423875e-05,
+      "loss": 3.0913,
+      "num_tokens": 122795575.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37606053657418026,
+      "grad_norm": 4.128929138183594,
+      "learning_rate": 1.974695733306728e-05,
+      "loss": 3.0232,
+      "num_tokens": 125860925.0,
+      "step": 2050
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 4.008982181549072,
+      "learning_rate": 1.9733866222832404e-05,
+      "loss": 3.0281,
+      "num_tokens": 128939549.0,
+      "step": 2100
+    },
+    {
+      "epoch": 0.39440495299243294,
+      "grad_norm": 3.8258960247039795,
+      "learning_rate": 1.972044952759963e-05,
+      "loss": 3.005,
+      "num_tokens": 132002665.0,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4035771612015593,
+      "grad_norm": 3.722099781036377,
+      "learning_rate": 1.970670769613974e-05,
+      "loss": 2.9717,
+      "num_tokens": 135066326.0,
+      "step": 2200
+    },
+    {
+      "epoch": 0.41274936941068563,
+      "grad_norm": 3.6987600326538086,
+      "learning_rate": 1.9692641188098886e-05,
+      "loss": 2.9571,
+      "num_tokens": 138128630.0,
+      "step": 2250
+    },
+    {
+      "epoch": 0.42192157761981197,
+      "grad_norm": 6.789268493652344,
+      "learning_rate": 1.9678250473983223e-05,
+      "loss": 2.9399,
+      "num_tokens": 141192291.0,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4310937858289383,
+      "grad_norm": 4.319190979003906,
+      "learning_rate": 1.966353603514317e-05,
+      "loss": 2.9201,
+      "num_tokens": 144272511.0,
+      "step": 2350
+    },
+    {
+      "epoch": 0.44026599403806466,
+      "grad_norm": 4.209902763366699,
+      "learning_rate": 1.9648498363757325e-05,
+      "loss": 2.924,
+      "num_tokens": 147343206.0,
+      "step": 2400
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 3.9288434982299805,
+      "learning_rate": 1.9633137962815973e-05,
+      "loss": 2.8886,
+      "num_tokens": 150412293.0,
+      "step": 2450
+    },
+    {
+      "epoch": 0.45861041045631734,
+      "grad_norm": 4.768758296966553,
+      "learning_rate": 1.9617455346104283e-05,
+      "loss": 2.8774,
+      "num_tokens": 153481791.0,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4677826186654437,
+      "grad_norm": 4.089212894439697,
+      "learning_rate": 1.9601451038185117e-05,
+      "loss": 2.8393,
+      "num_tokens": 156551627.0,
+      "step": 2550
+    },
+    {
+      "epoch": 0.47695482687457,
+      "grad_norm": 3.6109139919281006,
+      "learning_rate": 1.958512557438149e-05,
+      "loss": 2.8697,
+      "num_tokens": 159628649.0,
+      "step": 2600
+    },
+    {
+      "epoch": 0.4861270350836964,
+      "grad_norm": 4.69704008102417,
+      "learning_rate": 1.9568479500758648e-05,
+      "loss": 2.8156,
+      "num_tokens": 162692475.0,
+      "step": 2650
+    },
+    {
+      "epoch": 0.49529924329282277,
+      "grad_norm": 3.726196527481079,
+      "learning_rate": 1.9551513374105823e-05,
+      "loss": 2.8183,
+      "num_tokens": 165764216.0,
+      "step": 2700
+    },
+    {
+      "epoch": 0.504471451501949,
+      "grad_norm": 3.8877694606781006,
+      "learning_rate": 1.9534227761917585e-05,
+      "loss": 2.8098,
+      "num_tokens": 168832733.0,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 4.2488112449646,
+      "learning_rate": 1.9516623242374888e-05,
+      "loss": 2.8193,
+      "num_tokens": 171887021.0,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5228158679202017,
+      "grad_norm": 3.4136576652526855,
+      "learning_rate": 1.949870040432571e-05,
+      "loss": 2.7806,
+      "num_tokens": 174960619.0,
+      "step": 2850
+    },
+    {
+      "epoch": 0.5319880761293282,
+      "grad_norm": 4.282463550567627,
+      "learning_rate": 1.948045984726537e-05,
+      "loss": 2.779,
+      "num_tokens": 178028517.0,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5411602843384545,
+      "grad_norm": 4.703866958618164,
+      "learning_rate": 1.9461902181316455e-05,
+      "loss": 2.761,
+      "num_tokens": 181092191.0,
+      "step": 2950
+    },
+    {
+      "epoch": 0.5503324925475809,
+      "grad_norm": 3.5504965782165527,
+      "learning_rate": 1.9443028027208443e-05,
+      "loss": 2.7438,
+      "num_tokens": 184160542.0,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5595047007567072,
+      "grad_norm": 4.609411239624023,
+      "learning_rate": 1.9423838016256913e-05,
+      "loss": 2.7322,
+      "num_tokens": 187232548.0,
+      "step": 3050
+    },
+    {
+      "epoch": 0.5686769089658336,
+      "grad_norm": 3.5375072956085205,
+      "learning_rate": 1.9404332790342446e-05,
+      "loss": 2.7147,
+      "num_tokens": 190297910.0,
+      "step": 3100
+    },
+    {
+      "epoch": 0.5778491171749599,
+      "grad_norm": 3.5921809673309326,
+      "learning_rate": 1.9384513001889144e-05,
+      "loss": 2.7105,
+      "num_tokens": 193364684.0,
+      "step": 3150
+    },
+    {
+      "epoch": 0.5870213253840862,
+      "grad_norm": 3.7573354244232178,
+      "learning_rate": 1.936437931384281e-05,
+      "loss": 2.7081,
+      "num_tokens": 196431776.0,
+      "step": 3200
+    },
+    {
+      "epoch": 0.5961935335932126,
+      "grad_norm": 4.44867467880249,
+      "learning_rate": 1.934393239964878e-05,
+      "loss": 2.6803,
+      "num_tokens": 199500117.0,
+      "step": 3250
+    },
+    {
+      "epoch": 0.6053657418023389,
+      "grad_norm": 3.4919068813323975,
+      "learning_rate": 1.9323172943229386e-05,
+      "loss": 2.6674,
+      "num_tokens": 202569017.0,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6145379500114653,
+      "grad_norm": 3.851284980773926,
+      "learning_rate": 1.930210163896109e-05,
+      "loss": 2.6882,
+      "num_tokens": 205635983.0,
+      "step": 3350
+    },
+    {
+      "epoch": 0.6237101582205916,
+      "grad_norm": 5.8265910148620605,
+      "learning_rate": 1.9280719191651252e-05,
+      "loss": 2.648,
+      "num_tokens": 208697081.0,
+      "step": 3400
+    },
+    {
+      "epoch": 0.632882366429718,
+      "grad_norm": 3.4978857040405273,
+      "learning_rate": 1.925902631651456e-05,
+      "loss": 2.6435,
+      "num_tokens": 211770956.0,
+      "step": 3450
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 3.321568250656128,
+      "learning_rate": 1.9237023739149094e-05,
+      "loss": 2.6556,
+      "num_tokens": 214830999.0,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6512267828479706,
+      "grad_norm": 3.848578691482544,
+      "learning_rate": 1.9214712195512074e-05,
+      "loss": 2.6334,
+      "num_tokens": 217899025.0,
+      "step": 3550
+    },
+    {
+      "epoch": 0.660398991057097,
+      "grad_norm": 3.511373996734619,
+      "learning_rate": 1.919209243189524e-05,
+      "loss": 2.6138,
+      "num_tokens": 220972192.0,
+      "step": 3600
+    },
+    {
+      "epoch": 0.6695711992662233,
+      "grad_norm": 3.4985859394073486,
+      "learning_rate": 1.9169165204899866e-05,
+      "loss": 2.6251,
+      "num_tokens": 224041762.0,
+      "step": 3650
+    },
+    {
+      "epoch": 0.6787434074753497,
+      "grad_norm": 5.905818462371826,
+      "learning_rate": 1.9145931281411485e-05,
+      "loss": 2.6089,
+      "num_tokens": 227110870.0,
+      "step": 3700
+    },
+    {
+      "epoch": 0.687915615684476,
+      "grad_norm": 8.281390190124512,
+      "learning_rate": 1.9122391438574226e-05,
+      "loss": 2.6084,
+      "num_tokens": 230193112.0,
+      "step": 3750
+    },
+    {
+      "epoch": 0.6970878238936024,
+      "grad_norm": 3.555816888809204,
+      "learning_rate": 1.9098546463764802e-05,
+      "loss": 2.6074,
+      "num_tokens": 233261587.0,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7062600321027287,
+      "grad_norm": 4.379006862640381,
+      "learning_rate": 1.9074397154566203e-05,
+      "loss": 2.5825,
+      "num_tokens": 236318086.0,
+      "step": 3850
+    },
+    {
+      "epoch": 0.715432240311855,
+      "grad_norm": 4.370838642120361,
+      "learning_rate": 1.9049944318740998e-05,
+      "loss": 2.6007,
+      "num_tokens": 239390375.0,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7246044485209814,
+      "grad_norm": 3.347520112991333,
+      "learning_rate": 1.902518877420432e-05,
+      "loss": 2.5861,
+      "num_tokens": 242454603.0,
+      "step": 3950
+    },
+    {
+      "epoch": 0.7337766567301077,
+      "grad_norm": 3.8170406818389893,
+      "learning_rate": 1.900013134899651e-05,
+      "loss": 2.5956,
+      "num_tokens": 245520349.0,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7429488649392341,
+      "grad_norm": 4.084133625030518,
+      "learning_rate": 1.8974772881255423e-05,
+      "loss": 2.5744,
+      "num_tokens": 248591742.0,
+      "step": 4050
+    },
+    {
+      "epoch": 0.7521210731483605,
+      "grad_norm": 4.162419319152832,
+      "learning_rate": 1.8949114219188386e-05,
+      "loss": 2.5557,
+      "num_tokens": 251668641.0,
+      "step": 4100
+    },
+    {
+      "epoch": 0.7612932813574869,
+      "grad_norm": 4.139531135559082,
+      "learning_rate": 1.8923156221043834e-05,
+      "loss": 2.5529,
+      "num_tokens": 254744782.0,
+      "step": 4150
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 3.5236408710479736,
+      "learning_rate": 1.8896899755082594e-05,
+      "loss": 2.5342,
+      "num_tokens": 257825042.0,
+      "step": 4200
+    },
+    {
+      "epoch": 0.7796376977757395,
+      "grad_norm": 7.408937931060791,
+      "learning_rate": 1.8870345699548856e-05,
+      "loss": 2.5367,
+      "num_tokens": 260890737.0,
+      "step": 4250
+    },
+    {
+      "epoch": 0.7888099059848659,
+      "grad_norm": 4.408638000488281,
+      "learning_rate": 1.8843494942640782e-05,
+      "loss": 2.5397,
+      "num_tokens": 263956000.0,
+      "step": 4300
+    },
+    {
+      "epoch": 0.7979821141939922,
+      "grad_norm": 3.64819073677063,
+      "learning_rate": 1.8816348382480807e-05,
+      "loss": 2.5326,
+      "num_tokens": 267024229.0,
+      "step": 4350
+    },
+    {
+      "epoch": 0.8071543224031186,
+      "grad_norm": 3.3967065811157227,
+      "learning_rate": 1.8788906927085596e-05,
+      "loss": 2.5291,
+      "num_tokens": 270093879.0,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 3.771216869354248,
+      "learning_rate": 1.876117149433567e-05,
+      "loss": 2.5167,
+      "num_tokens": 273153385.0,
+      "step": 4450
+    },
+    {
+      "epoch": 0.8254987388213713,
+      "grad_norm": 3.552034854888916,
+      "learning_rate": 1.87331430119447e-05,
+      "loss": 2.516,
+      "num_tokens": 276228897.0,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8346709470304976,
+      "grad_norm": 4.362802982330322,
+      "learning_rate": 1.870482241742849e-05,
+      "loss": 2.5083,
+      "num_tokens": 279299108.0,
+      "step": 4550
+    },
+    {
+      "epoch": 0.8438431552396239,
+      "grad_norm": 3.8707432746887207,
+      "learning_rate": 1.867621065807361e-05,
+      "loss": 2.4962,
+      "num_tokens": 282367606.0,
+      "step": 4600
+    },
+    {
+      "epoch": 0.8530153634487503,
+      "grad_norm": 3.7560534477233887,
+      "learning_rate": 1.8647308690905695e-05,
+      "loss": 2.5022,
+      "num_tokens": 285431292.0,
+      "step": 4650
+    },
+    {
+      "epoch": 0.8621875716578766,
+      "grad_norm": 4.073310375213623,
+      "learning_rate": 1.8618117482657473e-05,
+      "loss": 2.5052,
+      "num_tokens": 288509576.0,
+      "step": 4700
+    },
+    {
+      "epoch": 0.871359779867003,
+      "grad_norm": 4.2512288093566895,
+      "learning_rate": 1.858863800973638e-05,
+      "loss": 2.4922,
+      "num_tokens": 291577926.0,
+      "step": 4750
+    },
+    {
+      "epoch": 0.8805319880761293,
+      "grad_norm": 3.6681947708129883,
+      "learning_rate": 1.8558871258191943e-05,
+      "loss": 2.4687,
+      "num_tokens": 294652257.0,
+      "step": 4800
+    },
+    {
+      "epoch": 0.8897041962852557,
+      "grad_norm": 3.7940540313720703,
+      "learning_rate": 1.8528818223682777e-05,
+      "loss": 2.4622,
+      "num_tokens": 297724675.0,
+      "step": 4850
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 4.411775588989258,
+      "learning_rate": 1.849847991144328e-05,
+      "loss": 2.472,
+      "num_tokens": 300795065.0,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9080486127035083,
+      "grad_norm": 3.331857442855835,
+      "learning_rate": 1.8467857336250015e-05,
+      "loss": 2.4734,
+      "num_tokens": 303858894.0,
+      "step": 4950
+    },
+    {
+      "epoch": 0.9172208209126347,
+      "grad_norm": 5.33769416809082,
+      "learning_rate": 1.8436951522387766e-05,
+      "loss": 2.4534,
+      "num_tokens": 306912692.0,
+      "step": 5000
+    },
+    {
+      "epoch": 0.926393029121761,
+      "grad_norm": 3.5148868560791016,
+      "learning_rate": 1.8405763503615285e-05,
+      "loss": 2.4871,
+      "num_tokens": 310002551.0,
+      "step": 5050
+    },
+    {
+      "epoch": 0.9355652373308874,
+      "grad_norm": 3.6607162952423096,
+      "learning_rate": 1.8374294323130697e-05,
+      "loss": 2.4801,
+      "num_tokens": 313070094.0,
+      "step": 5100
+    },
+    {
+      "epoch": 0.9447374455400137,
+      "grad_norm": 6.60593318939209,
+      "learning_rate": 1.8342545033536622e-05,
+      "loss": 2.431,
+      "num_tokens": 316134272.0,
+      "step": 5150
+    },
+    {
+      "epoch": 0.95390965374914,
+      "grad_norm": 3.5577642917633057,
+      "learning_rate": 1.8310516696804953e-05,
+      "loss": 2.425,
+      "num_tokens": 319208656.0,
+      "step": 5200
+    },
+    {
+      "epoch": 0.9630818619582665,
+      "grad_norm": 3.443085193634033,
+      "learning_rate": 1.8278210384241353e-05,
+      "loss": 2.419,
+      "num_tokens": 322277785.0,
+      "step": 5250
+    },
+    {
+      "epoch": 0.9722540701673928,
+      "grad_norm": 4.775812149047852,
+      "learning_rate": 1.8245627176449395e-05,
+      "loss": 2.4398,
+      "num_tokens": 325343977.0,
+      "step": 5300
+    },
+    {
+      "epoch": 0.9814262783765192,
+      "grad_norm": 3.54435133934021,
+      "learning_rate": 1.8212768163294453e-05,
+      "loss": 2.4288,
+      "num_tokens": 328414604.0,
+      "step": 5350
+    },
+    {
+      "epoch": 0.9905984865856455,
+      "grad_norm": 3.6476333141326904,
+      "learning_rate": 1.8179634443867207e-05,
+      "loss": 2.4228,
+      "num_tokens": 331477653.0,
+      "step": 5400
+    },
+    {
+      "epoch": 0.9997706947947719,
+      "grad_norm": 4.548381805419922,
+      "learning_rate": 1.814622712644691e-05,
+      "loss": 2.4154,
+      "num_tokens": 334553911.0,
+      "step": 5450
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.662151575088501,
+      "eval_num_tokens": 334630136.0,
+      "eval_runtime": 5.3343,
+      "eval_samples_per_second": 90.922,
+      "eval_steps_per_second": 5.811,
+      "step": 5452
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 27260,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.70773805085696e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5452/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dccd16caef578cbb4657835b5fe256550766c65a0ed3bd3a5cd5bc131a37f2
+size 497774208

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "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,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b211df72d081c3ad5c55f8c4ba38067df1f9443b6eb976f02ad04316854a87
+size 6417

training_summary.json

@@ -0,0 +1,40 @@
+{
+  "best_eval_loss": 2.3043127059936523,
+  "total_evaluations": 5,
+  "eval_history": [
+    {
+      "step": 5452,
+      "eval_loss": 2.662151575088501,
+      "epoch": 1.0
+    },
+    {
+      "step": 10904,
+      "eval_loss": 2.4245221614837646,
+      "epoch": 2.0
+    },
+    {
+      "step": 16356,
+      "eval_loss": 2.342665433883667,
+      "epoch": 3.0
+    },
+    {
+      "step": 21808,
+      "eval_loss": 2.3043127059936523,
+      "epoch": 4.0
+    },
+    {
+      "step": 27260,
+      "eval_loss": 2.3054072856903076,
+      "epoch": 5.0
+    }
+  ],
+  "model_name": "gpt2",
+  "hub_repo_id": "nbtpj/summ_gpt2_inst_cnnxsumsam",
+  "training_args": {
+    "batch_size": 16,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 2e-05,
+    "num_epochs": 5,
+    "use_lora": false
+  }
+}