commit 236351d263366fedda0b2239982b31cee30da21c Author: ModelHub XC Date: Sat Aug 29 02:30:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: rl-research/DR-Tulu-SFT-8B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39c613a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..7123095 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen3-8B +tags: +- llama-factory +- full +- generated_from_trainer +datasets: +- rl-research/dr-tulu-sft-data +--- + +> [!NOTE] +> For full information, go check out the Dr Tulu paper [here](https://arxiv.org/abs/2511.19399). + +Figure 1 + + +# DR Tulu SFT 8B + +This is the SFT checkpoint of DR Tulu, an open deep research agent trained on top of [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). + +This model has undergone SFT training on [this dataset](https://huggingface.co/datasets/rl-research/dr-tulu-sft-data). +For more details on DR Tulu please **read our [paper](https://allenai.org/papers/drtulu)**! + + +# Inference and Usage + +**This model has been trained for tool-use using the dr-agent-lib framework**. +As such, running it out of the box with HuggingFace or vLLM will not work well! + +See [our github](https://github.com/rlresearch/dr-tulu) for more details on installation and how to run our model. +Or check out our [demo](https://dr-tulu.github.io/)! + +# Evaluation Results + +We provide evaluation instructions in [our github](https://github.com/rlresearch/dr-tulu). + + +| Benchmark | SQAv2 | HealthBench | ResearchQA | DeepResearch Bench | SimpleQA | 2Wiki | WebWalker | Average | +|:----------|:------:|:----------:|:---------:|:-------------------:|:------:|:-------:|-------:|-------:| +| [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) (naive rag) | 40.4 | 16.5 | 56.1 | 33.3 | 52.6 | 18.9 | 8.8 | 32.4 | +| [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) (our search pipeline) | 57.2 | 5.9 | 46.3 | 18.2 | 70.5 | 44.0 | 27.9 | 38.6 | +| [DR-Tulu-SFT-8B](https://huggingface.co/rl-research/DR-Tulu-SFT-8B) (**this model**) | 72.3 | 38.1 | 68.5 | 39.0 | 75.5 | 66.5 | 31.9 | 56.0 | +| [DR-Tulu-8B](https://huggingface.co/rl-research/DR-Tulu-8B) | **86.7** | **43.7** | **71.1** | **41.8** | **80.1** | **68.0** | **39.1** | **61.5** | + +For more baselines, explanations of this table, and analysis of results, check out the [Dr Tulu paper](https://allenai.org/papers/drtulu)! + +# Intended uses & limitations + +This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with [Ai2's Responsible Use Guidelines](https://allenai.org/responsible-use). + +## Training + +The following hyperparameters were used during training: +- learning_rate: 4e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 16 +- total_train_batch_size: 128 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.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 + +For futher details, check out the [Dr Tulu paper](https://allenai.org/papers/drtulu). + +# Links +- 📝 [DR Tulu Paper](https://allenai.org/papers/drtulu) +- ⚙️ [DR Tulu demo](https://dr-tulu.github.io/) +- 💻 [DR Tulu code](https://github.com/rlresearch/DR-Tulu) +- 🤖 [DR Tulu collection](https://huggingface.co/collections/rl-research/dr-tulu) + + +# Citation +``` +@article{shao2025dr, + title={DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research}, + author={Shao, Rulin and Asai, Akari and Shen, Shannon Zejiang and Ivison, Hamish and Kishore, Varsha and Zhuo, Jingming and Zhao, Xinran and Park, Molly and Finlayson, Samuel G and Sontag, David and others}, + journal={arXiv preprint arXiv:2511.19399}, + year={2025} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..b8d5f73 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 5.0, + "total_flos": 1235947560108032.0, + "train_loss": 0.7053156269921197, + "train_runtime": 61423.1886, + "train_samples_per_second": 1.307, + "train_steps_per_second": 0.01 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4e9672b --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.4", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/dr_tulu_logo.png b/dr_tulu_logo.png new file mode 100644 index 0000000..0050f0d Binary files /dev/null and b/dr_tulu_logo.png differ diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6b204b4 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.52.4" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..bb38b21 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7f00da443080e247922ca914a47f1817d87eb1ada9e564fb61987ea6c475d7 +size 4902257696 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..59ca93a --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39ab65e4573ae4eb34f770daa79de17ab00052177e391b742d3d4e014a29bea +size 4915960368 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..0f66965 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c6e0c29659ce473e29f86e3d53132dd8f47b77637fde31426364b589356d79 +size 4983068496 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..28a1b26 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e836bdbc6067f77c9049642596fe8b9efc560308817f675d11395722665a72f +size 1580230264 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..10c7a17 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_size": 16381470720 + }, + "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0209709 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..b8d5f73 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 5.0, + "total_flos": 1235947560108032.0, + "train_loss": 0.7053156269921197, + "train_runtime": 61423.1886, + "train_samples_per_second": 1.307, + "train_steps_per_second": 0.01 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..c898e24 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,127 @@ +{"current_steps": 5, "total_steps": 630, "loss": 1.6286, "lr": 2.53968253968254e-06, "epoch": 0.039860488290981565, "percentage": 0.79, "elapsed_time": "0:09:30", "remaining_time": "19:48:14"} +{"current_steps": 10, "total_steps": 630, "loss": 1.4713, "lr": 5.7142857142857145e-06, "epoch": 0.07972097658196313, "percentage": 1.59, "elapsed_time": "0:17:45", "remaining_time": "18:21:13"} +{"current_steps": 15, "total_steps": 630, "loss": 1.3152, "lr": 8.888888888888888e-06, "epoch": 0.11958146487294469, "percentage": 2.38, "elapsed_time": "0:26:00", "remaining_time": "17:46:17"} +{"current_steps": 20, "total_steps": 630, "loss": 1.2185, "lr": 1.2063492063492064e-05, "epoch": 0.15944195316392626, "percentage": 3.17, "elapsed_time": "0:34:11", "remaining_time": "17:23:05"} +{"current_steps": 25, "total_steps": 630, "loss": 1.1579, "lr": 1.523809523809524e-05, "epoch": 0.19930244145490783, "percentage": 3.97, "elapsed_time": "0:42:47", "remaining_time": "17:15:34"} +{"current_steps": 30, "total_steps": 630, "loss": 1.1295, "lr": 1.8412698412698415e-05, "epoch": 0.23916292974588937, "percentage": 4.76, "elapsed_time": "0:50:41", "remaining_time": "16:53:43"} +{"current_steps": 35, "total_steps": 630, "loss": 1.1069, "lr": 2.158730158730159e-05, "epoch": 0.279023418036871, "percentage": 5.56, "elapsed_time": "0:59:09", "remaining_time": "16:45:46"} +{"current_steps": 40, "total_steps": 630, "loss": 1.0887, "lr": 2.4761904761904766e-05, "epoch": 0.3188839063278525, "percentage": 6.35, "elapsed_time": "1:07:29", "remaining_time": "16:35:29"} +{"current_steps": 45, "total_steps": 630, "loss": 1.0869, "lr": 2.7936507936507936e-05, "epoch": 0.35874439461883406, "percentage": 7.14, "elapsed_time": "1:15:51", "remaining_time": "16:26:04"} +{"current_steps": 50, "total_steps": 630, "loss": 1.0774, "lr": 3.111111111111112e-05, "epoch": 0.39860488290981566, "percentage": 7.94, "elapsed_time": "1:24:06", "remaining_time": "16:15:43"} +{"current_steps": 55, "total_steps": 630, "loss": 1.0636, "lr": 3.4285714285714284e-05, "epoch": 0.4384653712007972, "percentage": 8.73, "elapsed_time": "1:32:28", "remaining_time": "16:06:46"} +{"current_steps": 60, "total_steps": 630, "loss": 1.0535, "lr": 3.7460317460317464e-05, "epoch": 0.47832585949177875, "percentage": 9.52, "elapsed_time": "1:40:28", "remaining_time": "15:54:34"} +{"current_steps": 65, "total_steps": 630, "loss": 1.0297, "lr": 3.9999693004141615e-05, "epoch": 0.5181863477827603, "percentage": 10.32, "elapsed_time": "1:48:18", "remaining_time": "15:41:24"} +{"current_steps": 70, "total_steps": 630, "loss": 1.0337, "lr": 3.998894913865352e-05, "epoch": 0.558046836073742, "percentage": 11.11, "elapsed_time": "1:56:11", "remaining_time": "15:29:31"} +{"current_steps": 75, "total_steps": 630, "loss": 1.0063, "lr": 3.9962864903591375e-05, "epoch": 0.5979073243647235, "percentage": 11.9, "elapsed_time": "2:04:23", "remaining_time": "15:20:32"} +{"current_steps": 80, "total_steps": 630, "loss": 1.0237, "lr": 3.992146031710637e-05, "epoch": 0.637767812655705, "percentage": 12.7, "elapsed_time": "2:12:30", "remaining_time": "15:11:00"} +{"current_steps": 85, "total_steps": 630, "loss": 1.0145, "lr": 3.9864767154838864e-05, "epoch": 0.6776283009466866, "percentage": 13.49, "elapsed_time": "2:20:38", "remaining_time": "15:01:43"} +{"current_steps": 90, "total_steps": 630, "loss": 1.0296, "lr": 3.9792828925532376e-05, "epoch": 0.7174887892376681, "percentage": 14.29, "elapsed_time": "2:28:57", "remaining_time": "14:53:45"} +{"current_steps": 95, "total_steps": 630, "loss": 1.0059, "lr": 3.970570083764316e-05, "epoch": 0.7573492775286498, "percentage": 15.08, "elapsed_time": "2:36:55", "remaining_time": "14:43:46"} +{"current_steps": 100, "total_steps": 630, "loss": 1.004, "lr": 3.9603449756970877e-05, "epoch": 0.7972097658196313, "percentage": 15.87, "elapsed_time": "2:45:03", "remaining_time": "14:34:48"} +{"current_steps": 105, "total_steps": 630, "loss": 0.9936, "lr": 3.948615415534294e-05, "epoch": 0.8370702541106129, "percentage": 16.67, "elapsed_time": "2:53:00", "remaining_time": "14:25:02"} +{"current_steps": 110, "total_steps": 630, "loss": 1.006, "lr": 3.9353904050391874e-05, "epoch": 0.8769307424015944, "percentage": 17.46, "elapsed_time": "3:00:58", "remaining_time": "14:15:30"} +{"current_steps": 115, "total_steps": 630, "loss": 1.0033, "lr": 3.9206800936472e-05, "epoch": 0.916791230692576, "percentage": 18.25, "elapsed_time": "3:09:06", "remaining_time": "14:06:53"} +{"current_steps": 120, "total_steps": 630, "loss": 0.9917, "lr": 3.904495770676831e-05, "epoch": 0.9566517189835575, "percentage": 19.05, "elapsed_time": "3:17:14", "remaining_time": "13:58:17"} +{"current_steps": 125, "total_steps": 630, "loss": 1.0137, "lr": 3.886849856665746e-05, "epoch": 0.9965122072745392, "percentage": 19.84, "elapsed_time": "3:24:59", "remaining_time": "13:48:08"} +{"current_steps": 130, "total_steps": 630, "loss": 0.885, "lr": 3.8677558938387276e-05, "epoch": 1.0318883906327851, "percentage": 20.63, "elapsed_time": "3:32:02", "remaining_time": "13:35:34"} +{"current_steps": 135, "total_steps": 630, "loss": 0.8679, "lr": 3.8472285357147966e-05, "epoch": 1.0717488789237668, "percentage": 21.43, "elapsed_time": "3:40:19", "remaining_time": "13:27:50"} +{"current_steps": 140, "total_steps": 630, "loss": 0.8733, "lr": 3.825283535861476e-05, "epoch": 1.1116093672147485, "percentage": 22.22, "elapsed_time": "3:48:17", "remaining_time": "13:19:01"} +{"current_steps": 145, "total_steps": 630, "loss": 0.8434, "lr": 3.801937735804838e-05, "epoch": 1.15146985550573, "percentage": 23.02, "elapsed_time": "3:56:16", "remaining_time": "13:10:18"} +{"current_steps": 150, "total_steps": 630, "loss": 0.8461, "lr": 3.777209052104598e-05, "epoch": 1.1913303437967115, "percentage": 23.81, "elapsed_time": "4:04:33", "remaining_time": "13:02:36"} +{"current_steps": 155, "total_steps": 630, "loss": 0.8606, "lr": 3.7511164626041823e-05, "epoch": 1.2311908320876932, "percentage": 24.6, "elapsed_time": "4:12:47", "remaining_time": "12:54:41"} +{"current_steps": 160, "total_steps": 630, "loss": 0.8555, "lr": 3.7236799918663284e-05, "epoch": 1.2710513203786746, "percentage": 25.4, "elapsed_time": "4:20:55", "remaining_time": "12:46:27"} +{"current_steps": 165, "total_steps": 630, "loss": 0.8437, "lr": 3.6949206958053825e-05, "epoch": 1.310911808669656, "percentage": 26.19, "elapsed_time": "4:29:02", "remaining_time": "12:38:13"} +{"current_steps": 170, "total_steps": 630, "loss": 0.8566, "lr": 3.6648606455280944e-05, "epoch": 1.3507722969606377, "percentage": 26.98, "elapsed_time": "4:37:23", "remaining_time": "12:30:34"} +{"current_steps": 175, "total_steps": 630, "loss": 0.8665, "lr": 3.633522910395314e-05, "epoch": 1.3906327852516194, "percentage": 27.78, "elapsed_time": "4:45:40", "remaining_time": "12:22:45"} +{"current_steps": 180, "total_steps": 630, "loss": 0.8363, "lr": 3.6009315403175786e-05, "epoch": 1.4304932735426008, "percentage": 28.57, "elapsed_time": "4:54:01", "remaining_time": "12:15:03"} +{"current_steps": 185, "total_steps": 630, "loss": 0.853, "lr": 3.567111547298194e-05, "epoch": 1.4703537618335825, "percentage": 29.37, "elapsed_time": "5:02:16", "remaining_time": "12:07:06"} +{"current_steps": 190, "total_steps": 630, "loss": 0.8496, "lr": 3.532088886237956e-05, "epoch": 1.5102142501245641, "percentage": 30.16, "elapsed_time": "5:10:16", "remaining_time": "11:58:30"} +{"current_steps": 195, "total_steps": 630, "loss": 0.8636, "lr": 3.495890435016258e-05, "epoch": 1.5500747384155455, "percentage": 30.95, "elapsed_time": "5:18:11", "remaining_time": "11:49:47"} +{"current_steps": 200, "total_steps": 630, "loss": 0.8538, "lr": 3.458543973863859e-05, "epoch": 1.5899352267065272, "percentage": 31.75, "elapsed_time": "5:26:21", "remaining_time": "11:41:39"} +{"current_steps": 205, "total_steps": 630, "loss": 0.8591, "lr": 3.420078164043161e-05, "epoch": 1.6297957149975089, "percentage": 32.54, "elapsed_time": "5:34:27", "remaining_time": "11:33:23"} +{"current_steps": 210, "total_steps": 630, "loss": 0.8401, "lr": 3.38052252585233e-05, "epoch": 1.6696562032884903, "percentage": 33.33, "elapsed_time": "5:42:38", "remaining_time": "11:25:16"} +{"current_steps": 215, "total_steps": 630, "loss": 0.8476, "lr": 3.339907415970168e-05, "epoch": 1.7095166915794717, "percentage": 34.13, "elapsed_time": "5:50:36", "remaining_time": "11:16:44"} +{"current_steps": 220, "total_steps": 630, "loss": 0.8413, "lr": 3.298264004159104e-05, "epoch": 1.7493771798704534, "percentage": 34.92, "elapsed_time": "5:58:48", "remaining_time": "11:08:41"} +{"current_steps": 225, "total_steps": 630, "loss": 0.8534, "lr": 3.255624249344198e-05, "epoch": 1.789237668161435, "percentage": 35.71, "elapsed_time": "6:06:41", "remaining_time": "11:00:03"} +{"current_steps": 230, "total_steps": 630, "loss": 0.8734, "lr": 3.212020875086495e-05, "epoch": 1.8290981564524165, "percentage": 36.51, "elapsed_time": "6:14:37", "remaining_time": "10:51:31"} +{"current_steps": 235, "total_steps": 630, "loss": 0.8619, "lr": 3.1674873444695804e-05, "epoch": 1.8689586447433981, "percentage": 37.3, "elapsed_time": "6:22:31", "remaining_time": "10:42:57"} +{"current_steps": 240, "total_steps": 630, "loss": 0.8604, "lr": 3.122057834418582e-05, "epoch": 1.9088191330343798, "percentage": 38.1, "elapsed_time": "6:30:54", "remaining_time": "10:35:14"} +{"current_steps": 245, "total_steps": 630, "loss": 0.8712, "lr": 3.075767209471345e-05, "epoch": 1.9486796213253612, "percentage": 38.89, "elapsed_time": "6:39:27", "remaining_time": "10:27:43"} +{"current_steps": 250, "total_steps": 630, "loss": 0.8449, "lr": 3.0286509950219077e-05, "epoch": 1.9885401096163426, "percentage": 39.68, "elapsed_time": "6:47:40", "remaining_time": "10:19:40"} +{"current_steps": 255, "total_steps": 630, "loss": 0.7382, "lr": 2.9807453500567937e-05, "epoch": 2.023916292974589, "percentage": 40.48, "elapsed_time": "6:54:34", "remaining_time": "10:09:40"} +{"current_steps": 260, "total_steps": 630, "loss": 0.6794, "lr": 2.9320870394050783e-05, "epoch": 2.0637767812655703, "percentage": 41.27, "elapsed_time": "7:02:33", "remaining_time": "10:01:20"} +{"current_steps": 265, "total_steps": 630, "loss": 0.6878, "lr": 2.8827134055234883e-05, "epoch": 2.103637269556552, "percentage": 42.06, "elapsed_time": "7:10:35", "remaining_time": "9:53:04"} +{"current_steps": 270, "total_steps": 630, "loss": 0.6895, "lr": 2.8326623398382174e-05, "epoch": 2.1434977578475336, "percentage": 42.86, "elapsed_time": "7:18:38", "remaining_time": "9:44:51"} +{"current_steps": 275, "total_steps": 630, "loss": 0.6684, "lr": 2.781972253665431e-05, "epoch": 2.183358246138515, "percentage": 43.65, "elapsed_time": "7:27:05", "remaining_time": "9:37:08"} +{"current_steps": 280, "total_steps": 630, "loss": 0.6719, "lr": 2.7306820487327906e-05, "epoch": 2.223218734429497, "percentage": 44.44, "elapsed_time": "7:34:55", "remaining_time": "9:28:38"} +{"current_steps": 285, "total_steps": 630, "loss": 0.6735, "lr": 2.6788310873246133e-05, "epoch": 2.2630792227204783, "percentage": 45.24, "elapsed_time": "7:43:00", "remaining_time": "9:20:28"} +{"current_steps": 290, "total_steps": 630, "loss": 0.6757, "lr": 2.62645916207358e-05, "epoch": 2.30293971101146, "percentage": 46.03, "elapsed_time": "7:50:55", "remaining_time": "9:12:07"} +{"current_steps": 295, "total_steps": 630, "loss": 0.6544, "lr": 2.5736064654221808e-05, "epoch": 2.3428001993024417, "percentage": 46.83, "elapsed_time": "7:59:00", "remaining_time": "9:03:57"} +{"current_steps": 300, "total_steps": 630, "loss": 0.6612, "lr": 2.5203135587773196e-05, "epoch": 2.382660687593423, "percentage": 47.62, "elapsed_time": "8:07:03", "remaining_time": "8:55:45"} +{"current_steps": 305, "total_steps": 630, "loss": 0.6763, "lr": 2.4666213413817696e-05, "epoch": 2.4225211758844045, "percentage": 48.41, "elapsed_time": "8:15:04", "remaining_time": "8:47:32"} +{"current_steps": 310, "total_steps": 630, "loss": 0.6563, "lr": 2.4125710189263555e-05, "epoch": 2.4623816641753864, "percentage": 49.21, "elapsed_time": "8:23:10", "remaining_time": "8:39:24"} +{"current_steps": 315, "total_steps": 630, "loss": 0.65, "lr": 2.3582040719269504e-05, "epoch": 2.502242152466368, "percentage": 50.0, "elapsed_time": "8:31:26", "remaining_time": "8:31:26"} +{"current_steps": 320, "total_steps": 630, "loss": 0.6679, "lr": 2.3035622238905694e-05, "epoch": 2.5421026407573493, "percentage": 50.79, "elapsed_time": "8:39:34", "remaining_time": "8:23:20"} +{"current_steps": 325, "total_steps": 630, "loss": 0.6738, "lr": 2.2486874092949708e-05, "epoch": 2.5819631290483307, "percentage": 51.59, "elapsed_time": "8:47:51", "remaining_time": "8:15:22"} +{"current_steps": 330, "total_steps": 630, "loss": 0.6887, "lr": 2.1936217414063584e-05, "epoch": 2.621823617339312, "percentage": 52.38, "elapsed_time": "8:55:58", "remaining_time": "8:07:14"} +{"current_steps": 335, "total_steps": 630, "loss": 0.6709, "lr": 2.138407479959869e-05, "epoch": 2.661684105630294, "percentage": 53.17, "elapsed_time": "9:04:39", "remaining_time": "7:59:37"} +{"current_steps": 340, "total_steps": 630, "loss": 0.665, "lr": 2.0830869987276537e-05, "epoch": 2.7015445939212754, "percentage": 53.97, "elapsed_time": "9:12:46", "remaining_time": "7:51:29"} +{"current_steps": 345, "total_steps": 630, "loss": 0.6528, "lr": 2.027702752999444e-05, "epoch": 2.741405082212257, "percentage": 54.76, "elapsed_time": "9:20:36", "remaining_time": "7:43:07"} +{"current_steps": 350, "total_steps": 630, "loss": 0.6771, "lr": 1.9722972470005573e-05, "epoch": 2.7812655705032387, "percentage": 55.56, "elapsed_time": "9:28:50", "remaining_time": "7:35:04"} +{"current_steps": 355, "total_steps": 630, "loss": 0.6638, "lr": 1.916913001272347e-05, "epoch": 2.82112605879422, "percentage": 56.35, "elapsed_time": "9:37:03", "remaining_time": "7:27:00"} +{"current_steps": 360, "total_steps": 630, "loss": 0.6753, "lr": 1.8615925200401318e-05, "epoch": 2.8609865470852016, "percentage": 57.14, "elapsed_time": "9:45:07", "remaining_time": "7:18:50"} +{"current_steps": 365, "total_steps": 630, "loss": 0.6681, "lr": 1.806378258593642e-05, "epoch": 2.9008470353761835, "percentage": 57.94, "elapsed_time": "9:53:46", "remaining_time": "7:11:06"} +{"current_steps": 370, "total_steps": 630, "loss": 0.6658, "lr": 1.7513125907050302e-05, "epoch": 2.940707523667165, "percentage": 58.73, "elapsed_time": "10:02:04", "remaining_time": "7:03:04"} +{"current_steps": 375, "total_steps": 630, "loss": 0.667, "lr": 1.6964377761094313e-05, "epoch": 2.9805680119581464, "percentage": 59.52, "elapsed_time": "10:10:18", "remaining_time": "6:55:00"} +{"current_steps": 380, "total_steps": 630, "loss": 0.612, "lr": 1.6417959280730506e-05, "epoch": 3.0159441953163926, "percentage": 60.32, "elapsed_time": "10:17:35", "remaining_time": "6:46:18"} +{"current_steps": 385, "total_steps": 630, "loss": 0.5282, "lr": 1.5874289810736452e-05, "epoch": 3.055804683607374, "percentage": 61.11, "elapsed_time": "10:25:36", "remaining_time": "6:38:06"} +{"current_steps": 390, "total_steps": 630, "loss": 0.4945, "lr": 1.5333786586182308e-05, "epoch": 3.095665171898356, "percentage": 61.9, "elapsed_time": "10:33:32", "remaining_time": "6:29:52"} +{"current_steps": 395, "total_steps": 630, "loss": 0.5178, "lr": 1.4796864412226812e-05, "epoch": 3.1355256601893373, "percentage": 62.7, "elapsed_time": "10:41:15", "remaining_time": "6:21:30"} +{"current_steps": 400, "total_steps": 630, "loss": 0.5015, "lr": 1.4263935345778202e-05, "epoch": 3.1753861484803187, "percentage": 63.49, "elapsed_time": "10:49:18", "remaining_time": "6:13:21"} +{"current_steps": 405, "total_steps": 630, "loss": 0.4988, "lr": 1.37354083792642e-05, "epoch": 3.2152466367713006, "percentage": 64.29, "elapsed_time": "10:57:40", "remaining_time": "6:05:22"} +{"current_steps": 410, "total_steps": 630, "loss": 0.4966, "lr": 1.3211689126753879e-05, "epoch": 3.255107125062282, "percentage": 65.08, "elapsed_time": "11:05:40", "remaining_time": "5:57:11"} +{"current_steps": 415, "total_steps": 630, "loss": 0.5081, "lr": 1.26931795126721e-05, "epoch": 3.2949676133532635, "percentage": 65.87, "elapsed_time": "11:14:03", "remaining_time": "5:49:12"} +{"current_steps": 420, "total_steps": 630, "loss": 0.5088, "lr": 1.2180277463345697e-05, "epoch": 3.334828101644245, "percentage": 66.67, "elapsed_time": "11:22:01", "remaining_time": "5:41:00"} +{"current_steps": 425, "total_steps": 630, "loss": 0.5023, "lr": 1.167337660161783e-05, "epoch": 3.374688589935227, "percentage": 67.46, "elapsed_time": "11:30:24", "remaining_time": "5:33:01"} +{"current_steps": 430, "total_steps": 630, "loss": 0.5054, "lr": 1.1172865944765122e-05, "epoch": 3.4145490782262082, "percentage": 68.25, "elapsed_time": "11:38:22", "remaining_time": "5:24:49"} +{"current_steps": 435, "total_steps": 630, "loss": 0.5078, "lr": 1.067912960594923e-05, "epoch": 3.4544095665171897, "percentage": 69.05, "elapsed_time": "11:46:31", "remaining_time": "5:16:43"} +{"current_steps": 440, "total_steps": 630, "loss": 0.5008, "lr": 1.0192546499432066e-05, "epoch": 3.4942700548081715, "percentage": 69.84, "elapsed_time": "11:54:41", "remaining_time": "5:08:37"} +{"current_steps": 445, "total_steps": 630, "loss": 0.5117, "lr": 9.713490049780931e-06, "epoch": 3.534130543099153, "percentage": 70.63, "elapsed_time": "12:02:51", "remaining_time": "5:00:31"} +{"current_steps": 450, "total_steps": 630, "loss": 0.5004, "lr": 9.242327905286552e-06, "epoch": 3.5739910313901344, "percentage": 71.43, "elapsed_time": "12:11:04", "remaining_time": "4:52:25"} +{"current_steps": 455, "total_steps": 630, "loss": 0.4899, "lr": 8.779421655814189e-06, "epoch": 3.6138515196811163, "percentage": 72.22, "elapsed_time": "12:19:29", "remaining_time": "4:44:25"} +{"current_steps": 460, "total_steps": 630, "loss": 0.4925, "lr": 8.325126555304208e-06, "epoch": 3.6537120079720977, "percentage": 73.02, "elapsed_time": "12:27:28", "remaining_time": "4:36:14"} +{"current_steps": 465, "total_steps": 630, "loss": 0.4936, "lr": 7.879791249135059e-06, "epoch": 3.693572496263079, "percentage": 73.81, "elapsed_time": "12:35:53", "remaining_time": "4:28:13"} +{"current_steps": 470, "total_steps": 630, "loss": 0.5071, "lr": 7.443757506558033e-06, "epoch": 3.733432984554061, "percentage": 74.6, "elapsed_time": "12:43:46", "remaining_time": "4:20:00"} +{"current_steps": 475, "total_steps": 630, "loss": 0.4902, "lr": 7.0173599584089625e-06, "epoch": 3.7732934728450425, "percentage": 75.4, "elapsed_time": "12:52:03", "remaining_time": "4:11:56"} +{"current_steps": 480, "total_steps": 630, "loss": 0.505, "lr": 6.600925840298331e-06, "epoch": 3.813153961136024, "percentage": 76.19, "elapsed_time": "13:00:27", "remaining_time": "4:03:53"} +{"current_steps": 485, "total_steps": 630, "loss": 0.5208, "lr": 6.1947747414767035e-06, "epoch": 3.8530144494270053, "percentage": 76.98, "elapsed_time": "13:08:34", "remaining_time": "3:55:45"} +{"current_steps": 490, "total_steps": 630, "loss": 0.5301, "lr": 5.799218359568395e-06, "epoch": 3.892874937717987, "percentage": 77.78, "elapsed_time": "13:16:37", "remaining_time": "3:47:36"} +{"current_steps": 495, "total_steps": 630, "loss": 0.4855, "lr": 5.414560261361415e-06, "epoch": 3.9327354260089686, "percentage": 78.57, "elapsed_time": "13:24:42", "remaining_time": "3:39:27"} +{"current_steps": 500, "total_steps": 630, "loss": 0.4872, "lr": 5.041095649837429e-06, "epoch": 3.97259591429995, "percentage": 79.37, "elapsed_time": "13:33:11", "remaining_time": "3:31:25"} +{"current_steps": 505, "total_steps": 630, "loss": 0.4901, "lr": 4.679111137620442e-06, "epoch": 4.007972097658197, "percentage": 80.16, "elapsed_time": "13:40:20", "remaining_time": "3:23:03"} +{"current_steps": 510, "total_steps": 630, "loss": 0.4086, "lr": 4.328884527018067e-06, "epoch": 4.047832585949178, "percentage": 80.95, "elapsed_time": "13:48:37", "remaining_time": "3:14:58"} +{"current_steps": 515, "total_steps": 630, "loss": 0.4042, "lr": 3.990684596824219e-06, "epoch": 4.08769307424016, "percentage": 81.75, "elapsed_time": "13:56:58", "remaining_time": "3:06:53"} +{"current_steps": 520, "total_steps": 630, "loss": 0.4028, "lr": 3.6647708960468696e-06, "epoch": 4.127553562531141, "percentage": 82.54, "elapsed_time": "14:05:15", "remaining_time": "2:58:48"} +{"current_steps": 525, "total_steps": 630, "loss": 0.3937, "lr": 3.3513935447190595e-06, "epoch": 4.1674140508221225, "percentage": 83.33, "elapsed_time": "14:13:27", "remaining_time": "2:50:41"} +{"current_steps": 530, "total_steps": 630, "loss": 0.3941, "lr": 3.050793041946183e-06, "epoch": 4.207274539113104, "percentage": 84.13, "elapsed_time": "14:21:35", "remaining_time": "2:42:33"} +{"current_steps": 535, "total_steps": 630, "loss": 0.3913, "lr": 2.763200081336721e-06, "epoch": 4.247135027404085, "percentage": 84.92, "elapsed_time": "14:29:47", "remaining_time": "2:34:26"} +{"current_steps": 540, "total_steps": 630, "loss": 0.3993, "lr": 2.488835373958185e-06, "epoch": 4.286995515695067, "percentage": 85.71, "elapsed_time": "14:37:58", "remaining_time": "2:26:19"} +{"current_steps": 545, "total_steps": 630, "loss": 0.4047, "lr": 2.2279094789540244e-06, "epoch": 4.326856003986049, "percentage": 86.51, "elapsed_time": "14:46:00", "remaining_time": "2:18:11"} +{"current_steps": 550, "total_steps": 630, "loss": 0.402, "lr": 1.9806226419516195e-06, "epoch": 4.36671649227703, "percentage": 87.3, "elapsed_time": "14:54:15", "remaining_time": "2:10:04"} +{"current_steps": 555, "total_steps": 630, "loss": 0.4037, "lr": 1.7471646413852439e-06, "epoch": 4.406576980568012, "percentage": 88.1, "elapsed_time": "15:02:13", "remaining_time": "2:01:55"} +{"current_steps": 560, "total_steps": 630, "loss": 0.3975, "lr": 1.527714642852045e-06, "epoch": 4.446437468858994, "percentage": 88.89, "elapsed_time": "15:10:17", "remaining_time": "1:53:47"} +{"current_steps": 565, "total_steps": 630, "loss": 0.3902, "lr": 1.3224410616127292e-06, "epoch": 4.486297957149975, "percentage": 89.68, "elapsed_time": "15:18:48", "remaining_time": "1:45:42"} +{"current_steps": 570, "total_steps": 630, "loss": 0.3955, "lr": 1.1315014333425455e-06, "epoch": 4.526158445440957, "percentage": 90.48, "elapsed_time": "15:27:01", "remaining_time": "1:37:34"} +{"current_steps": 575, "total_steps": 630, "loss": 0.3925, "lr": 9.550422932316938e-07, "epoch": 4.566018933731939, "percentage": 91.27, "elapsed_time": "15:35:06", "remaining_time": "1:29:26"} +{"current_steps": 580, "total_steps": 630, "loss": 0.3929, "lr": 7.931990635280052e-07, "epoch": 4.60587942202292, "percentage": 92.06, "elapsed_time": "15:42:58", "remaining_time": "1:21:17"} +{"current_steps": 585, "total_steps": 630, "loss": 0.4068, "lr": 6.460959496081276e-07, "epoch": 4.645739910313901, "percentage": 92.86, "elapsed_time": "15:51:29", "remaining_time": "1:13:11"} +{"current_steps": 590, "total_steps": 630, "loss": 0.3962, "lr": 5.13845844657066e-07, "epoch": 4.685600398604883, "percentage": 93.65, "elapsed_time": "15:59:50", "remaining_time": "1:05:04"} +{"current_steps": 595, "total_steps": 630, "loss": 0.3912, "lr": 3.965502430291235e-07, "epoch": 4.725460886895864, "percentage": 94.44, "elapsed_time": "16:07:43", "remaining_time": "0:56:55"} +{"current_steps": 600, "total_steps": 630, "loss": 0.3801, "lr": 2.942991623568436e-07, "epoch": 4.765321375186846, "percentage": 95.24, "elapsed_time": "16:15:51", "remaining_time": "0:48:47"} +{"current_steps": 605, "total_steps": 630, "loss": 0.369, "lr": 2.0717107446762696e-07, "epoch": 4.805181863477827, "percentage": 96.03, "elapsed_time": "16:24:11", "remaining_time": "0:40:40"} +{"current_steps": 610, "total_steps": 630, "loss": 0.3982, "lr": 1.3523284516113955e-07, "epoch": 4.845042351768809, "percentage": 96.83, "elapsed_time": "16:31:56", "remaining_time": "0:32:31"} +{"current_steps": 615, "total_steps": 630, "loss": 0.3916, "lr": 7.853968289363245e-08, "epoch": 4.884902840059791, "percentage": 97.62, "elapsed_time": "16:40:16", "remaining_time": "0:24:23"} +{"current_steps": 620, "total_steps": 630, "loss": 0.3978, "lr": 3.7135096408631443e-08, "epoch": 4.924763328350773, "percentage": 98.41, "elapsed_time": "16:48:22", "remaining_time": "0:16:15"} +{"current_steps": 625, "total_steps": 630, "loss": 0.389, "lr": 1.1050861346488806e-08, "epoch": 4.964623816641754, "percentage": 99.21, "elapsed_time": "16:56:29", "remaining_time": "0:08:07"} +{"current_steps": 630, "total_steps": 630, "loss": 0.4095, "lr": 3.069958583856725e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "17:03:41", "remaining_time": "0:00:00"} +{"current_steps": 630, "total_steps": 630, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "17:03:41", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..824e47e --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,925 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.0, + "eval_steps": 500, + "global_step": 630, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.039860488290981565, + "grad_norm": 11.324122796709977, + "learning_rate": 2.53968253968254e-06, + "loss": 1.6286, + "step": 5 + }, + { + "epoch": 0.07972097658196313, + "grad_norm": 1.991457650057207, + "learning_rate": 5.7142857142857145e-06, + "loss": 1.4713, + "step": 10 + }, + { + "epoch": 0.11958146487294469, + "grad_norm": 1.0610273535036991, + "learning_rate": 8.888888888888888e-06, + "loss": 1.3152, + "step": 15 + }, + { + "epoch": 0.15944195316392626, + "grad_norm": 0.7999727467798167, + "learning_rate": 1.2063492063492064e-05, + "loss": 1.2185, + "step": 20 + }, + { + "epoch": 0.19930244145490783, + "grad_norm": 0.6462858961182688, + "learning_rate": 1.523809523809524e-05, + "loss": 1.1579, + "step": 25 + }, + { + "epoch": 0.23916292974588937, + "grad_norm": 0.47561233028025485, + "learning_rate": 1.8412698412698415e-05, + "loss": 1.1295, + "step": 30 + }, + { + "epoch": 0.279023418036871, + "grad_norm": 0.4460008015131473, + "learning_rate": 2.158730158730159e-05, + "loss": 1.1069, + "step": 35 + }, + { + "epoch": 0.3188839063278525, + "grad_norm": 0.35932407714480935, + "learning_rate": 2.4761904761904766e-05, + "loss": 1.0887, + "step": 40 + }, + { + "epoch": 0.35874439461883406, + "grad_norm": 0.3717286127467533, + "learning_rate": 2.7936507936507936e-05, + "loss": 1.0869, + "step": 45 + }, + { + "epoch": 0.39860488290981566, + "grad_norm": 0.38261468570309465, + "learning_rate": 3.111111111111112e-05, + "loss": 1.0774, + "step": 50 + }, + { + "epoch": 0.4384653712007972, + "grad_norm": 0.383323190556911, + "learning_rate": 3.4285714285714284e-05, + "loss": 1.0636, + "step": 55 + }, + { + "epoch": 0.47832585949177875, + "grad_norm": 0.4100491937186789, + "learning_rate": 3.7460317460317464e-05, + "loss": 1.0535, + "step": 60 + }, + { + "epoch": 0.5181863477827603, + "grad_norm": 0.3975249651869064, + "learning_rate": 3.9999693004141615e-05, + "loss": 1.0297, + "step": 65 + }, + { + "epoch": 0.558046836073742, + "grad_norm": 0.3819095926536229, + "learning_rate": 3.998894913865352e-05, + "loss": 1.0337, + "step": 70 + }, + { + "epoch": 0.5979073243647235, + "grad_norm": 0.36490844056440797, + "learning_rate": 3.9962864903591375e-05, + "loss": 1.0063, + "step": 75 + }, + { + "epoch": 0.637767812655705, + "grad_norm": 0.4076298707032981, + "learning_rate": 3.992146031710637e-05, + "loss": 1.0237, + "step": 80 + }, + { + "epoch": 0.6776283009466866, + "grad_norm": 0.37566110161128824, + "learning_rate": 3.9864767154838864e-05, + "loss": 1.0145, + "step": 85 + }, + { + "epoch": 0.7174887892376681, + "grad_norm": 0.34530643882424805, + "learning_rate": 3.9792828925532376e-05, + "loss": 1.0296, + "step": 90 + }, + { + "epoch": 0.7573492775286498, + "grad_norm": 0.3432558970267317, + "learning_rate": 3.970570083764316e-05, + "loss": 1.0059, + "step": 95 + }, + { + "epoch": 0.7972097658196313, + "grad_norm": 0.3408833181353496, + "learning_rate": 3.9603449756970877e-05, + "loss": 1.004, + "step": 100 + }, + { + "epoch": 0.8370702541106129, + "grad_norm": 0.3589480700028462, + "learning_rate": 3.948615415534294e-05, + "loss": 0.9936, + "step": 105 + }, + { + "epoch": 0.8769307424015944, + "grad_norm": 0.33854687709123976, + "learning_rate": 3.9353904050391874e-05, + "loss": 1.006, + "step": 110 + }, + { + "epoch": 0.916791230692576, + "grad_norm": 0.3606947276733311, + "learning_rate": 3.9206800936472e-05, + "loss": 1.0033, + "step": 115 + }, + { + "epoch": 0.9566517189835575, + "grad_norm": 0.3524202550527317, + "learning_rate": 3.904495770676831e-05, + "loss": 0.9917, + "step": 120 + }, + { + "epoch": 0.9965122072745392, + "grad_norm": 0.3695008401673435, + "learning_rate": 3.886849856665746e-05, + "loss": 1.0137, + "step": 125 + }, + { + "epoch": 1.0318883906327851, + "grad_norm": 0.5103901242908977, + "learning_rate": 3.8677558938387276e-05, + "loss": 0.885, + "step": 130 + }, + { + "epoch": 1.0717488789237668, + "grad_norm": 0.39411785206718664, + "learning_rate": 3.8472285357147966e-05, + "loss": 0.8679, + "step": 135 + }, + { + "epoch": 1.1116093672147485, + "grad_norm": 0.3898193416463423, + "learning_rate": 3.825283535861476e-05, + "loss": 0.8733, + "step": 140 + }, + { + "epoch": 1.15146985550573, + "grad_norm": 0.7348802698342378, + "learning_rate": 3.801937735804838e-05, + "loss": 0.8434, + "step": 145 + }, + { + "epoch": 1.1913303437967115, + "grad_norm": 0.36945102723915507, + "learning_rate": 3.777209052104598e-05, + "loss": 0.8461, + "step": 150 + }, + { + "epoch": 1.2311908320876932, + "grad_norm": 0.4602742420015167, + "learning_rate": 3.7511164626041823e-05, + "loss": 0.8606, + "step": 155 + }, + { + "epoch": 1.2710513203786746, + "grad_norm": 0.35621072409911864, + "learning_rate": 3.7236799918663284e-05, + "loss": 0.8555, + "step": 160 + }, + { + "epoch": 1.310911808669656, + "grad_norm": 0.42801215480497146, + "learning_rate": 3.6949206958053825e-05, + "loss": 0.8437, + "step": 165 + }, + { + "epoch": 1.3507722969606377, + "grad_norm": 0.36223537090099234, + "learning_rate": 3.6648606455280944e-05, + "loss": 0.8566, + "step": 170 + }, + { + "epoch": 1.3906327852516194, + "grad_norm": 0.702392888184491, + "learning_rate": 3.633522910395314e-05, + "loss": 0.8665, + "step": 175 + }, + { + "epoch": 1.4304932735426008, + "grad_norm": 0.36020937464475294, + "learning_rate": 3.6009315403175786e-05, + "loss": 0.8363, + "step": 180 + }, + { + "epoch": 1.4703537618335825, + "grad_norm": 0.3500105740239205, + "learning_rate": 3.567111547298194e-05, + "loss": 0.853, + "step": 185 + }, + { + "epoch": 1.5102142501245641, + "grad_norm": 0.4768600668120408, + "learning_rate": 3.532088886237956e-05, + "loss": 0.8496, + "step": 190 + }, + { + "epoch": 1.5500747384155455, + "grad_norm": 0.36399360324025654, + "learning_rate": 3.495890435016258e-05, + "loss": 0.8636, + "step": 195 + }, + { + "epoch": 1.5899352267065272, + "grad_norm": 0.3380619981423237, + "learning_rate": 3.458543973863859e-05, + "loss": 0.8538, + "step": 200 + }, + { + "epoch": 1.6297957149975089, + "grad_norm": 0.3389261022528899, + "learning_rate": 3.420078164043161e-05, + "loss": 0.8591, + "step": 205 + }, + { + "epoch": 1.6696562032884903, + "grad_norm": 0.395644963130336, + "learning_rate": 3.38052252585233e-05, + "loss": 0.8401, + "step": 210 + }, + { + "epoch": 1.7095166915794717, + "grad_norm": 0.30378900619983906, + "learning_rate": 3.339907415970168e-05, + "loss": 0.8476, + "step": 215 + }, + { + "epoch": 1.7493771798704534, + "grad_norm": 0.3900044033629726, + "learning_rate": 3.298264004159104e-05, + "loss": 0.8413, + "step": 220 + }, + { + "epoch": 1.789237668161435, + "grad_norm": 0.36925152268695366, + "learning_rate": 3.255624249344198e-05, + "loss": 0.8534, + "step": 225 + }, + { + "epoch": 1.8290981564524165, + "grad_norm": 0.3334498107167973, + "learning_rate": 3.212020875086495e-05, + "loss": 0.8734, + "step": 230 + }, + { + "epoch": 1.8689586447433981, + "grad_norm": 0.3231836736531515, + "learning_rate": 3.1674873444695804e-05, + "loss": 0.8619, + "step": 235 + }, + { + "epoch": 1.9088191330343798, + "grad_norm": 0.3352794024716405, + "learning_rate": 3.122057834418582e-05, + "loss": 0.8604, + "step": 240 + }, + { + "epoch": 1.9486796213253612, + "grad_norm": 0.34760623558396486, + "learning_rate": 3.075767209471345e-05, + "loss": 0.8712, + "step": 245 + }, + { + "epoch": 1.9885401096163426, + "grad_norm": 0.3494983937948561, + "learning_rate": 3.0286509950219077e-05, + "loss": 0.8449, + "step": 250 + }, + { + "epoch": 2.023916292974589, + "grad_norm": 0.6438619381464517, + "learning_rate": 2.9807453500567937e-05, + "loss": 0.7382, + "step": 255 + }, + { + "epoch": 2.0637767812655703, + "grad_norm": 0.48837947056765113, + "learning_rate": 2.9320870394050783e-05, + "loss": 0.6794, + "step": 260 + }, + { + "epoch": 2.103637269556552, + "grad_norm": 0.4249085778688401, + "learning_rate": 2.8827134055234883e-05, + "loss": 0.6878, + "step": 265 + }, + { + "epoch": 2.1434977578475336, + "grad_norm": 0.4112164304088742, + "learning_rate": 2.8326623398382174e-05, + "loss": 0.6895, + "step": 270 + }, + { + "epoch": 2.183358246138515, + "grad_norm": 0.4393590314899133, + "learning_rate": 2.781972253665431e-05, + "loss": 0.6684, + "step": 275 + }, + { + "epoch": 2.223218734429497, + "grad_norm": 0.37274870892195433, + "learning_rate": 2.7306820487327906e-05, + "loss": 0.6719, + "step": 280 + }, + { + "epoch": 2.2630792227204783, + "grad_norm": 0.38062444497520725, + "learning_rate": 2.6788310873246133e-05, + "loss": 0.6735, + "step": 285 + }, + { + "epoch": 2.30293971101146, + "grad_norm": 0.3754103984568679, + "learning_rate": 2.62645916207358e-05, + "loss": 0.6757, + "step": 290 + }, + { + "epoch": 2.3428001993024417, + "grad_norm": 0.38094693535399177, + "learning_rate": 2.5736064654221808e-05, + "loss": 0.6544, + "step": 295 + }, + { + "epoch": 2.382660687593423, + "grad_norm": 0.37267334400373975, + "learning_rate": 2.5203135587773196e-05, + "loss": 0.6612, + "step": 300 + }, + { + "epoch": 2.4225211758844045, + "grad_norm": 0.3511334496003159, + "learning_rate": 2.4666213413817696e-05, + "loss": 0.6763, + "step": 305 + }, + { + "epoch": 2.4623816641753864, + "grad_norm": 0.368576714561806, + "learning_rate": 2.4125710189263555e-05, + "loss": 0.6563, + "step": 310 + }, + { + "epoch": 2.502242152466368, + "grad_norm": 0.35196724604768753, + "learning_rate": 2.3582040719269504e-05, + "loss": 0.65, + "step": 315 + }, + { + "epoch": 2.5421026407573493, + "grad_norm": 0.3540473065272315, + "learning_rate": 2.3035622238905694e-05, + "loss": 0.6679, + "step": 320 + }, + { + "epoch": 2.5819631290483307, + "grad_norm": 0.3661596143769676, + "learning_rate": 2.2486874092949708e-05, + "loss": 0.6738, + "step": 325 + }, + { + "epoch": 2.621823617339312, + "grad_norm": 0.35913068756682465, + "learning_rate": 2.1936217414063584e-05, + "loss": 0.6887, + "step": 330 + }, + { + "epoch": 2.661684105630294, + "grad_norm": 0.36799867292080646, + "learning_rate": 2.138407479959869e-05, + "loss": 0.6709, + "step": 335 + }, + { + "epoch": 2.7015445939212754, + "grad_norm": 0.35691876781155074, + "learning_rate": 2.0830869987276537e-05, + "loss": 0.665, + "step": 340 + }, + { + "epoch": 2.741405082212257, + "grad_norm": 0.38987523468576574, + "learning_rate": 2.027702752999444e-05, + "loss": 0.6528, + "step": 345 + }, + { + "epoch": 2.7812655705032387, + "grad_norm": 0.38505381731754873, + "learning_rate": 1.9722972470005573e-05, + "loss": 0.6771, + "step": 350 + }, + { + "epoch": 2.82112605879422, + "grad_norm": 0.35842950010166197, + "learning_rate": 1.916913001272347e-05, + "loss": 0.6638, + "step": 355 + }, + { + "epoch": 2.8609865470852016, + "grad_norm": 0.37422580701088903, + "learning_rate": 1.8615925200401318e-05, + "loss": 0.6753, + "step": 360 + }, + { + "epoch": 2.9008470353761835, + "grad_norm": 0.36860495212005495, + "learning_rate": 1.806378258593642e-05, + "loss": 0.6681, + "step": 365 + }, + { + "epoch": 2.940707523667165, + "grad_norm": 0.3647903293380729, + "learning_rate": 1.7513125907050302e-05, + "loss": 0.6658, + "step": 370 + }, + { + "epoch": 2.9805680119581464, + "grad_norm": 0.35870478733795147, + "learning_rate": 1.6964377761094313e-05, + "loss": 0.667, + "step": 375 + }, + { + "epoch": 3.0159441953163926, + "grad_norm": 0.6451047782511159, + "learning_rate": 1.6417959280730506e-05, + "loss": 0.612, + "step": 380 + }, + { + "epoch": 3.055804683607374, + "grad_norm": 0.7456786595663745, + "learning_rate": 1.5874289810736452e-05, + "loss": 0.5282, + "step": 385 + }, + { + "epoch": 3.095665171898356, + "grad_norm": 0.4611479200453808, + "learning_rate": 1.5333786586182308e-05, + "loss": 0.4945, + "step": 390 + }, + { + "epoch": 3.1355256601893373, + "grad_norm": 0.4624423710225065, + "learning_rate": 1.4796864412226812e-05, + "loss": 0.5178, + "step": 395 + }, + { + "epoch": 3.1753861484803187, + "grad_norm": 0.3988674416095005, + "learning_rate": 1.4263935345778202e-05, + "loss": 0.5015, + "step": 400 + }, + { + "epoch": 3.2152466367713006, + "grad_norm": 0.4171540538418279, + "learning_rate": 1.37354083792642e-05, + "loss": 0.4988, + "step": 405 + }, + { + "epoch": 3.255107125062282, + "grad_norm": 0.4043531142190362, + "learning_rate": 1.3211689126753879e-05, + "loss": 0.4966, + "step": 410 + }, + { + "epoch": 3.2949676133532635, + "grad_norm": 0.406846754086433, + "learning_rate": 1.26931795126721e-05, + "loss": 0.5081, + "step": 415 + }, + { + "epoch": 3.334828101644245, + "grad_norm": 0.42193109699205417, + "learning_rate": 1.2180277463345697e-05, + "loss": 0.5088, + "step": 420 + }, + { + "epoch": 3.374688589935227, + "grad_norm": 0.4039970787325296, + "learning_rate": 1.167337660161783e-05, + "loss": 0.5023, + "step": 425 + }, + { + "epoch": 3.4145490782262082, + "grad_norm": 0.3891294704118612, + "learning_rate": 1.1172865944765122e-05, + "loss": 0.5054, + "step": 430 + }, + { + "epoch": 3.4544095665171897, + "grad_norm": 0.4123628750841747, + "learning_rate": 1.067912960594923e-05, + "loss": 0.5078, + "step": 435 + }, + { + "epoch": 3.4942700548081715, + "grad_norm": 0.4116103758152132, + "learning_rate": 1.0192546499432066e-05, + "loss": 0.5008, + "step": 440 + }, + { + "epoch": 3.534130543099153, + "grad_norm": 0.39334581361661547, + "learning_rate": 9.713490049780931e-06, + "loss": 0.5117, + "step": 445 + }, + { + "epoch": 3.5739910313901344, + "grad_norm": 0.3977163931160735, + "learning_rate": 9.242327905286552e-06, + "loss": 0.5004, + "step": 450 + }, + { + "epoch": 3.6138515196811163, + "grad_norm": 0.41291346064789947, + "learning_rate": 8.779421655814189e-06, + "loss": 0.4899, + "step": 455 + }, + { + "epoch": 3.6537120079720977, + "grad_norm": 0.39864981854696013, + "learning_rate": 8.325126555304208e-06, + "loss": 0.4925, + "step": 460 + }, + { + "epoch": 3.693572496263079, + "grad_norm": 0.3783439845572638, + "learning_rate": 7.879791249135059e-06, + "loss": 0.4936, + "step": 465 + }, + { + "epoch": 3.733432984554061, + "grad_norm": 0.36028247570266225, + "learning_rate": 7.443757506558033e-06, + "loss": 0.5071, + "step": 470 + }, + { + "epoch": 3.7732934728450425, + "grad_norm": 0.36974308586061955, + "learning_rate": 7.0173599584089625e-06, + "loss": 0.4902, + "step": 475 + }, + { + "epoch": 3.813153961136024, + "grad_norm": 0.3709767672807715, + "learning_rate": 6.600925840298331e-06, + "loss": 0.505, + "step": 480 + }, + { + "epoch": 3.8530144494270053, + "grad_norm": 0.3610583139391416, + "learning_rate": 6.1947747414767035e-06, + "loss": 0.5208, + "step": 485 + }, + { + "epoch": 3.892874937717987, + "grad_norm": 0.3791524633277678, + "learning_rate": 5.799218359568395e-06, + "loss": 0.5301, + "step": 490 + }, + { + "epoch": 3.9327354260089686, + "grad_norm": 0.363724718810471, + "learning_rate": 5.414560261361415e-06, + "loss": 0.4855, + "step": 495 + }, + { + "epoch": 3.97259591429995, + "grad_norm": 0.3867971355298049, + "learning_rate": 5.041095649837429e-06, + "loss": 0.4872, + "step": 500 + }, + { + "epoch": 4.007972097658197, + "grad_norm": 0.6922635714147061, + "learning_rate": 4.679111137620442e-06, + "loss": 0.4901, + "step": 505 + }, + { + "epoch": 4.047832585949178, + "grad_norm": 0.5464640833763156, + "learning_rate": 4.328884527018067e-06, + "loss": 0.4086, + "step": 510 + }, + { + "epoch": 4.08769307424016, + "grad_norm": 0.5514248166968356, + "learning_rate": 3.990684596824219e-06, + "loss": 0.4042, + "step": 515 + }, + { + "epoch": 4.127553562531141, + "grad_norm": 0.46194805338366773, + "learning_rate": 3.6647708960468696e-06, + "loss": 0.4028, + "step": 520 + }, + { + "epoch": 4.1674140508221225, + "grad_norm": 0.45065104707045, + "learning_rate": 3.3513935447190595e-06, + "loss": 0.3937, + "step": 525 + }, + { + "epoch": 4.207274539113104, + "grad_norm": 0.3884400001553067, + "learning_rate": 3.050793041946183e-06, + "loss": 0.3941, + "step": 530 + }, + { + "epoch": 4.247135027404085, + "grad_norm": 0.4057662200999109, + "learning_rate": 2.763200081336721e-06, + "loss": 0.3913, + "step": 535 + }, + { + "epoch": 4.286995515695067, + "grad_norm": 0.3927959847718352, + "learning_rate": 2.488835373958185e-06, + "loss": 0.3993, + "step": 540 + }, + { + "epoch": 4.326856003986049, + "grad_norm": 0.3915532354537384, + "learning_rate": 2.2279094789540244e-06, + "loss": 0.4047, + "step": 545 + }, + { + "epoch": 4.36671649227703, + "grad_norm": 0.37576385131138085, + "learning_rate": 1.9806226419516195e-06, + "loss": 0.402, + "step": 550 + }, + { + "epoch": 4.406576980568012, + "grad_norm": 0.3589030046466532, + "learning_rate": 1.7471646413852439e-06, + "loss": 0.4037, + "step": 555 + }, + { + "epoch": 4.446437468858994, + "grad_norm": 0.38802398319508147, + "learning_rate": 1.527714642852045e-06, + "loss": 0.3975, + "step": 560 + }, + { + "epoch": 4.486297957149975, + "grad_norm": 0.3781055143033295, + "learning_rate": 1.3224410616127292e-06, + "loss": 0.3902, + "step": 565 + }, + { + "epoch": 4.526158445440957, + "grad_norm": 0.380556572113873, + "learning_rate": 1.1315014333425455e-06, + "loss": 0.3955, + "step": 570 + }, + { + "epoch": 4.566018933731939, + "grad_norm": 0.37627984573745005, + "learning_rate": 9.550422932316938e-07, + "loss": 0.3925, + "step": 575 + }, + { + "epoch": 4.60587942202292, + "grad_norm": 0.36605761395168335, + "learning_rate": 7.931990635280052e-07, + "loss": 0.3929, + "step": 580 + }, + { + "epoch": 4.645739910313901, + "grad_norm": 0.37403610200301257, + "learning_rate": 6.460959496081276e-07, + "loss": 0.4068, + "step": 585 + }, + { + "epoch": 4.685600398604883, + "grad_norm": 0.3673645131484265, + "learning_rate": 5.13845844657066e-07, + "loss": 0.3962, + "step": 590 + }, + { + "epoch": 4.725460886895864, + "grad_norm": 0.39800543909133185, + "learning_rate": 3.965502430291235e-07, + "loss": 0.3912, + "step": 595 + }, + { + "epoch": 4.765321375186846, + "grad_norm": 0.37969719371341065, + "learning_rate": 2.942991623568436e-07, + "loss": 0.3801, + "step": 600 + }, + { + "epoch": 4.805181863477827, + "grad_norm": 0.3777219824944034, + "learning_rate": 2.0717107446762696e-07, + "loss": 0.369, + "step": 605 + }, + { + "epoch": 4.845042351768809, + "grad_norm": 0.3913050535737085, + "learning_rate": 1.3523284516113955e-07, + "loss": 0.3982, + "step": 610 + }, + { + "epoch": 4.884902840059791, + "grad_norm": 0.3712369916416077, + "learning_rate": 7.853968289363245e-08, + "loss": 0.3916, + "step": 615 + }, + { + "epoch": 4.924763328350773, + "grad_norm": 0.38101325204255376, + "learning_rate": 3.7135096408631443e-08, + "loss": 0.3978, + "step": 620 + }, + { + "epoch": 4.964623816641754, + "grad_norm": 0.37989319704275204, + "learning_rate": 1.1050861346488806e-08, + "loss": 0.389, + "step": 625 + }, + { + "epoch": 5.0, + "grad_norm": 0.5514474703259893, + "learning_rate": 3.069958583856725e-10, + "loss": 0.4095, + "step": 630 + }, + { + "epoch": 5.0, + "step": 630, + "total_flos": 1235947560108032.0, + "train_loss": 0.7053156269921197, + "train_runtime": 61423.1886, + "train_samples_per_second": 1.307, + "train_steps_per_second": 0.01 + } + ], + "logging_steps": 5, + "max_steps": 630, + "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": false, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1235947560108032.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..973297c --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f77071ace978330b77e4869dcfa3968b4c877144c8c7f3a5bd0c9b8cfeed0d +size 7953 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..502ffb8 Binary files /dev/null and b/training_loss.png differ diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833