commit 2351f0250a22bfe68559b8a8f142e7d711b1ed7d Author: ModelHub XC Date: Tue Jun 30 02:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jaredfern/canoe-1_1 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d4afa5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-422/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e2765d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +library_name: transformers +tags: +- generated_from_trainer +- open-r1 +licence: license +--- + +# Model Card for None + +This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + +This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). + +### Framework versions + +- TRL: 0.14.0 +- Transformers: 4.57.6 +- Pytorch: 2.6.0 +- Datasets: 4.8.5 +- Tokenizers: 0.22.2 + +## Citations + +Cite GRPO as: + +```bibtex +@article{zhihong2024deepseekmath, + title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, + author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, + year = 2024, + eprint = {arXiv:2402.03300}, +} + +``` + +Cite TRL as: + +```bibtex +@misc{vonwerra2022trl, + title = {{TRL: Transformer Reinforcement Learning}}, + author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec}, + year = 2020, + journal = {GitHub repository}, + publisher = {GitHub}, + howpublished = {\url{https://github.com/huggingface/trl}} +} +``` \ No newline at end of file diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..11a2873 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "total_flos": 0.0, + "train_loss": 0.07021697652106884, + "train_runtime": 419033.0805, + "train_samples": 26956, + "train_samples_per_second": 0.129, + "train_steps_per_second": 0.001 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..33089ac --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/checkpoint-422/chat_template.jinja b/checkpoint-422/chat_template.jinja new file mode 100644 index 0000000..33089ac --- /dev/null +++ b/checkpoint-422/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/checkpoint-422/config.json b/checkpoint-422/config.json new file mode 100644 index 0000000..b584256 --- /dev/null +++ b/checkpoint-422/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/checkpoint-422/generation_config.json b/checkpoint-422/generation_config.json new file mode 100644 index 0000000..b9c76a3 --- /dev/null +++ b/checkpoint-422/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128009, + 128001, + 128008, + 128009 + ], + "pad_token_id": 128009, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.6" +} diff --git a/checkpoint-422/global_step421/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-422/global_step421/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000..cc2ac59 --- /dev/null +++ b/checkpoint-422/global_step421/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18accc548303bab3b65e410a617bd7a8641d194978f28a86304a0688f981e2c4 +size 24090789950 diff --git a/checkpoint-422/global_step421/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-422/global_step421/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000..ebb76e9 --- /dev/null +++ b/checkpoint-422/global_step421/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a80d0999d896ab5a06a0fbe4c9256d9eb5fac0bc1164266f0f97db821afe01 +size 24090789950 diff --git a/checkpoint-422/global_step421/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-422/global_step421/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000..456de4e --- /dev/null +++ b/checkpoint-422/global_step421/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a397bc656b4a965b43b4809ff2c3095a27082b53fb060639b56161c0fdfadb +size 24090789950 diff --git a/checkpoint-422/global_step421/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/checkpoint-422/global_step421/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000..c966602 --- /dev/null +++ b/checkpoint-422/global_step421/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f5b97a3bdca68532e51a306efeab7c5a069ab86d358df92e373766defb0abb +size 24090789950 diff --git a/checkpoint-422/global_step421/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-422/global_step421/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000..cca68bf --- /dev/null +++ b/checkpoint-422/global_step421/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07dbae83e5e7649405e3d469c139dacf10a188f06f223e436cdc9b4effe33de +size 148773 diff --git a/checkpoint-422/global_step421/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-422/global_step421/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000..74b503f --- /dev/null +++ b/checkpoint-422/global_step421/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5d074991399e10395def23e7a771e74f6e38ff73b5f21a9d80a8d1a9f64dee +size 148773 diff --git a/checkpoint-422/global_step421/zero_pp_rank_2_mp_rank_00_model_states.pt b/checkpoint-422/global_step421/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000..7edd712 --- /dev/null +++ b/checkpoint-422/global_step421/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12dc2d6fd0db29ee6a80aa0b6ea3871cc253fec050c6beae6fbf971b7468bcc5 +size 148773 diff --git a/checkpoint-422/global_step421/zero_pp_rank_3_mp_rank_00_model_states.pt b/checkpoint-422/global_step421/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000..e05eac0 --- /dev/null +++ b/checkpoint-422/global_step421/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea92f572b1f48568664e582fd9840991892ec696f1f73a3091eb4ee304fea57 +size 148773 diff --git a/checkpoint-422/latest b/checkpoint-422/latest new file mode 100644 index 0000000..49908ad --- /dev/null +++ b/checkpoint-422/latest @@ -0,0 +1 @@ +global_step421 \ No newline at end of file diff --git a/checkpoint-422/pytorch_model-00001-of-00004.bin b/checkpoint-422/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..bab9d86 --- /dev/null +++ b/checkpoint-422/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdf60dbbda44f160be0c8820338d5594a499a7a646293eb2429bdc176cbb264 +size 4976717314 diff --git a/checkpoint-422/pytorch_model-00002-of-00004.bin b/checkpoint-422/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..7b8f57e --- /dev/null +++ b/checkpoint-422/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65fa1a703a4fdbec3410bb2785e4271a30dec45b5d027c9174f8407d45640e8 +size 4999826246 diff --git a/checkpoint-422/pytorch_model-00003-of-00004.bin b/checkpoint-422/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..01082bc --- /dev/null +++ b/checkpoint-422/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8576907561d4e633def10d0fcef201a98dcfe394ab30037f764c4fb3263c7d39 +size 4915938762 diff --git a/checkpoint-422/pytorch_model-00004-of-00004.bin b/checkpoint-422/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..6faf37a --- /dev/null +++ b/checkpoint-422/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f275b89cce74d491e663e2d7a079886ce8833d5fe4fc29ada554fe3001218c3 +size 1168140873 diff --git a/checkpoint-422/pytorch_model.bin.index.json b/checkpoint-422/pytorch_model.bin.index.json new file mode 100644 index 0000000..3c202ae --- /dev/null +++ b/checkpoint-422/pytorch_model.bin.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.norm.weight": "pytorch_model-00004-of-00004.bin" + } +} diff --git a/checkpoint-422/rng_state_0.pth b/checkpoint-422/rng_state_0.pth new file mode 100644 index 0000000..cd3c55a --- /dev/null +++ b/checkpoint-422/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc6bbe58bf74f555a0ba8fc836f0d43f418cbd572fcd05fc7a6722ab4596ede +size 15024 diff --git a/checkpoint-422/rng_state_1.pth b/checkpoint-422/rng_state_1.pth new file mode 100644 index 0000000..c03cb36 --- /dev/null +++ b/checkpoint-422/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed0e34232b6403e33d178cd8717833e1d39f629663937291c029b1885144f97 +size 15024 diff --git a/checkpoint-422/rng_state_2.pth b/checkpoint-422/rng_state_2.pth new file mode 100644 index 0000000..2e29f16 --- /dev/null +++ b/checkpoint-422/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694fae111ccbcdd714cd5a6835c9c72377c7c00b743c0cff85dbfe15c7e0d482 +size 15024 diff --git a/checkpoint-422/rng_state_3.pth b/checkpoint-422/rng_state_3.pth new file mode 100644 index 0000000..c8ebadf --- /dev/null +++ b/checkpoint-422/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:846fdf3d31d003e77eb37c4e4f42e9b6c7b99aa5c4a762bb9537f4968eaf9229 +size 15024 diff --git a/checkpoint-422/scheduler.pt b/checkpoint-422/scheduler.pt new file mode 100644 index 0000000..39339a7 --- /dev/null +++ b/checkpoint-422/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a612a8d20c5acc65a92454729f636db6df853e02d5b1501c743ef5a6c88898 +size 1064 diff --git a/checkpoint-422/special_tokens_map.json b/checkpoint-422/special_tokens_map.json new file mode 100644 index 0000000..b43be96 --- /dev/null +++ b/checkpoint-422/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/checkpoint-422/tokenizer.json b/checkpoint-422/tokenizer.json new file mode 100644 index 0000000..92cc72b --- /dev/null +++ b/checkpoint-422/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26 +size 17210084 diff --git a/checkpoint-422/tokenizer_config.json b/checkpoint-422/tokenizer_config.json new file mode 100644 index 0000000..3beeacc --- /dev/null +++ b/checkpoint-422/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/checkpoint-422/trainer_state.json b/checkpoint-422/trainer_state.json new file mode 100644 index 0000000..f67ec92 --- /dev/null +++ b/checkpoint-422/trainer_state.json @@ -0,0 +1,1309 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 422, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "completion_length": 343.505859375, + "epoch": 0.0047484790028194095, + "grad_norm": 10.941497736666665, + "kl": 1.436471939086914e-05, + "learning_rate": 0.0, + "loss": 0.0, + "reward": 2.490234375, + "reward_std": 0.557172168046236, + "rewards/accuracy_reward": 0.66796875, + "rewards/format_reward": 0.806640625, + "rewards/influence_reward": 0.53515625, + "rewards/len_reward": 0.48046875, + "step": 1 + }, + { + "completion_length": 341.50390625, + "epoch": 0.023742395014097046, + "grad_norm": 6.812195416096856, + "kl": 0.0044515132904052734, + "learning_rate": 9.302325581395349e-08, + "loss": 0.0002, + "reward": 2.46826171875, + "reward_std": 0.5800532991997898, + "rewards/accuracy_reward": 0.66259765625, + "rewards/format_reward": 0.8154296875, + "rewards/influence_reward": 0.537109375, + "rewards/len_reward": 0.453125, + "step": 5 + }, + { + "completion_length": 355.537890625, + "epoch": 0.04748479002819409, + "grad_norm": 8.69360815652138, + "kl": 0.008914566040039063, + "learning_rate": 2.0930232558139536e-07, + "loss": 0.0004, + "reward": 2.44375, + "reward_std": 0.6262629209086299, + "rewards/accuracy_reward": 0.653125, + "rewards/format_reward": 0.804296875, + "rewards/influence_reward": 0.519140625, + "rewards/len_reward": 0.4671875, + "step": 10 + }, + { + "completion_length": 359.13984375, + "epoch": 0.07122718504229114, + "grad_norm": 9.167296678106975, + "kl": 0.1373016357421875, + "learning_rate": 3.2558139534883724e-07, + "loss": 0.0055, + "reward": 2.444140625, + "reward_std": 0.5922891769558192, + "rewards/accuracy_reward": 0.666015625, + "rewards/format_reward": 0.79921875, + "rewards/influence_reward": 0.525390625, + "rewards/len_reward": 0.453515625, + "step": 15 + }, + { + "completion_length": 351.53828125, + "epoch": 0.09496958005638818, + "grad_norm": 20.494707498797204, + "kl": 0.620166015625, + "learning_rate": 4.4186046511627905e-07, + "loss": 0.0248, + "reward": 2.49609375, + "reward_std": 0.6080626923590898, + "rewards/accuracy_reward": 0.655078125, + "rewards/format_reward": 0.81171875, + "rewards/influence_reward": 0.533984375, + "rewards/len_reward": 0.4953125, + "step": 20 + }, + { + "completion_length": 350.94140625, + "epoch": 0.11871197507048524, + "grad_norm": 58.39828164144229, + "kl": 4.012548828125, + "learning_rate": 5.581395348837209e-07, + "loss": 0.1604, + "reward": 2.5171875, + "reward_std": 0.5175810419023037, + "rewards/accuracy_reward": 0.652734375, + "rewards/format_reward": 0.86015625, + "rewards/influence_reward": 0.5484375, + "rewards/len_reward": 0.455859375, + "step": 25 + }, + { + "completion_length": 344.183203125, + "epoch": 0.14245437008458228, + "grad_norm": 10.671491690481664, + "kl": 1.959765625, + "learning_rate": 6.744186046511627e-07, + "loss": 0.0784, + "reward": 2.559375, + "reward_std": 0.49339695163071157, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.8859375, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.484375, + "step": 30 + }, + { + "completion_length": 312.225390625, + "epoch": 0.16619676509867934, + "grad_norm": 6.830335531593763, + "kl": 1.739990234375, + "learning_rate": 7.906976744186046e-07, + "loss": 0.0696, + "reward": 2.652734375, + "reward_std": 0.4439069716259837, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.9421875, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.51015625, + "step": 35 + }, + { + "completion_length": 284.68359375, + "epoch": 0.18993916011277637, + "grad_norm": 14.080133543924038, + "kl": 1.54609375, + "learning_rate": 9.069767441860464e-07, + "loss": 0.0619, + "reward": 2.736328125, + "reward_std": 0.48739379905164243, + "rewards/accuracy_reward": 0.658203125, + "rewards/format_reward": 0.94453125, + "rewards/influence_reward": 0.5828125, + "rewards/len_reward": 0.55078125, + "step": 40 + }, + { + "completion_length": 276.867578125, + "epoch": 0.21368155512687342, + "grad_norm": 35.20677672719882, + "kl": 1.3846435546875, + "learning_rate": 9.999828225438954e-07, + "loss": 0.0554, + "reward": 2.808203125, + "reward_std": 0.46657639369368553, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.954296875, + "rewards/influence_reward": 0.573046875, + "rewards/len_reward": 0.6453125, + "step": 45 + }, + { + "completion_length": 273.9359375, + "epoch": 0.23742395014097048, + "grad_norm": 3.603130834120874, + "kl": 1.1903564453125, + "learning_rate": 9.993817354984484e-07, + "loss": 0.0476, + "reward": 2.736328125, + "reward_std": 0.4892417475581169, + "rewards/accuracy_reward": 0.63984375, + "rewards/format_reward": 0.940625, + "rewards/influence_reward": 0.554296875, + "rewards/len_reward": 0.6015625, + "step": 50 + }, + { + "completion_length": 271.577734375, + "epoch": 0.26116634515506754, + "grad_norm": 2.2725600898834406, + "kl": 1.1795166015625, + "learning_rate": 9.979229555432882e-07, + "loss": 0.0472, + "reward": 2.798828125, + "reward_std": 0.46620402578264475, + "rewards/accuracy_reward": 0.65, + "rewards/format_reward": 0.951171875, + "rewards/influence_reward": 0.5890625, + "rewards/len_reward": 0.60859375, + "step": 55 + }, + { + "completion_length": 286.709375, + "epoch": 0.28490874016916456, + "grad_norm": 4.953405517687021, + "kl": 1.2238525390625, + "learning_rate": 9.95608988146948e-07, + "loss": 0.0489, + "reward": 2.83984375, + "reward_std": 0.47557592410594224, + "rewards/accuracy_reward": 0.676953125, + "rewards/format_reward": 0.94140625, + "rewards/influence_reward": 0.602734375, + "rewards/len_reward": 0.61875, + "step": 60 + }, + { + "completion_length": 277.02578125, + "epoch": 0.3086511351832616, + "grad_norm": 3.0787337409013547, + "kl": 1.3475830078125, + "learning_rate": 9.924438075705754e-07, + "loss": 0.0539, + "reward": 2.82109375, + "reward_std": 0.45666036382317543, + "rewards/accuracy_reward": 0.678515625, + "rewards/format_reward": 0.938671875, + "rewards/influence_reward": 0.605859375, + "rewards/len_reward": 0.598046875, + "step": 65 + }, + { + "completion_length": 285.7953125, + "epoch": 0.3323935301973587, + "grad_norm": 4.0730313066810995, + "kl": 1.3648681640625, + "learning_rate": 9.884328500421004e-07, + "loss": 0.0546, + "reward": 2.772265625, + "reward_std": 0.44936057794839146, + "rewards/accuracy_reward": 0.64375, + "rewards/format_reward": 0.9421875, + "rewards/influence_reward": 0.58046875, + "rewards/len_reward": 0.605859375, + "step": 70 + }, + { + "completion_length": 292.43828125, + "epoch": 0.3561359252114557, + "grad_norm": 3.1544402674020002, + "kl": 1.1553466796875, + "learning_rate": 9.835830044194623e-07, + "loss": 0.0462, + "reward": 2.688671875, + "reward_std": 0.4725625243037939, + "rewards/accuracy_reward": 0.6109375, + "rewards/format_reward": 0.9296875, + "rewards/influence_reward": 0.532421875, + "rewards/len_reward": 0.615625, + "step": 75 + }, + { + "completion_length": 286.590234375, + "epoch": 0.37987832022555273, + "grad_norm": 4.765364778587015, + "kl": 1.1624267578125, + "learning_rate": 9.779026003589303e-07, + "loss": 0.0465, + "reward": 2.708984375, + "reward_std": 0.4846075477078557, + "rewards/accuracy_reward": 0.6375, + "rewards/format_reward": 0.930078125, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.584765625, + "step": 80 + }, + { + "completion_length": 290.792578125, + "epoch": 0.4036207152396498, + "grad_norm": 9.253671242707203, + "kl": 1.3268310546875, + "learning_rate": 9.714013940088387e-07, + "loss": 0.0531, + "reward": 2.683203125, + "reward_std": 0.4955078672617674, + "rewards/accuracy_reward": 0.630859375, + "rewards/format_reward": 0.926953125, + "rewards/influence_reward": 0.55625, + "rewards/len_reward": 0.569140625, + "step": 85 + }, + { + "completion_length": 281.421484375, + "epoch": 0.42736311025374685, + "grad_norm": 3.4409983083101086, + "kl": 1.6419921875, + "learning_rate": 9.640905512533092e-07, + "loss": 0.0657, + "reward": 2.748046875, + "reward_std": 0.4972141746431589, + "rewards/accuracy_reward": 0.632421875, + "rewards/format_reward": 0.945703125, + "rewards/influence_reward": 0.561328125, + "rewards/len_reward": 0.60859375, + "step": 90 + }, + { + "completion_length": 267.971875, + "epoch": 0.4511055052678439, + "grad_norm": 2.2522797459391732, + "kl": 1.63046875, + "learning_rate": 9.55982628534738e-07, + "loss": 0.0652, + "reward": 2.778125, + "reward_std": 0.4521504515781999, + "rewards/accuracy_reward": 0.6265625, + "rewards/format_reward": 0.943359375, + "rewards/influence_reward": 0.56796875, + "rewards/len_reward": 0.640234375, + "step": 95 + }, + { + "completion_length": 267.776953125, + "epoch": 0.47484790028194096, + "grad_norm": 2.4372708411881794, + "kl": 1.320361328125, + "learning_rate": 9.470915512879851e-07, + "loss": 0.0528, + "reward": 2.808984375, + "reward_std": 0.4696818504482508, + "rewards/accuracy_reward": 0.650390625, + "rewards/format_reward": 0.941015625, + "rewards/influence_reward": 0.58515625, + "rewards/len_reward": 0.632421875, + "step": 100 + }, + { + "completion_length": 283.4515625, + "epoch": 0.498590295296038, + "grad_norm": 3.8496772212244457, + "kl": 1.447314453125, + "learning_rate": 9.374325900233086e-07, + "loss": 0.0579, + "reward": 2.8171875, + "reward_std": 0.45389450453221797, + "rewards/accuracy_reward": 0.660546875, + "rewards/format_reward": 0.953515625, + "rewards/influence_reward": 0.585546875, + "rewards/len_reward": 0.617578125, + "step": 105 + }, + { + "completion_length": 294.027734375, + "epoch": 0.5223326903101351, + "grad_norm": 3.309296740246584, + "kl": 1.67744140625, + "learning_rate": 9.270223340991146e-07, + "loss": 0.0671, + "reward": 2.75546875, + "reward_std": 0.4890925087034702, + "rewards/accuracy_reward": 0.646875, + "rewards/format_reward": 0.95625, + "rewards/influence_reward": 0.56953125, + "rewards/len_reward": 0.5828125, + "step": 110 + }, + { + "completion_length": 295.9484375, + "epoch": 0.5460750853242321, + "grad_norm": 4.3161975783345845, + "kl": 1.809423828125, + "learning_rate": 9.158786632295775e-07, + "loss": 0.0724, + "reward": 2.72734375, + "reward_std": 0.46550923883914946, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.954296875, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.57265625, + "step": 115 + }, + { + "completion_length": 297.998046875, + "epoch": 0.5698174803383291, + "grad_norm": 5.658396439699509, + "kl": 1.731787109375, + "learning_rate": 9.040207167760585e-07, + "loss": 0.0693, + "reward": 2.66875, + "reward_std": 0.4691320048645139, + "rewards/accuracy_reward": 0.621875, + "rewards/format_reward": 0.945703125, + "rewards/influence_reward": 0.54765625, + "rewards/len_reward": 0.553515625, + "step": 120 + }, + { + "completion_length": 308.9625, + "epoch": 0.5935598753524262, + "grad_norm": 2.884522521427685, + "kl": 1.869189453125, + "learning_rate": 8.9146886087507e-07, + "loss": 0.0748, + "reward": 2.70234375, + "reward_std": 0.42319196127355097, + "rewards/accuracy_reward": 0.6296875, + "rewards/format_reward": 0.946875, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.579296875, + "step": 125 + }, + { + "completion_length": 300.675390625, + "epoch": 0.6173022703665232, + "grad_norm": 4.353864200081107, + "kl": 1.741796875, + "learning_rate": 8.782446534592411e-07, + "loss": 0.0697, + "reward": 2.71953125, + "reward_std": 0.46506577655673026, + "rewards/accuracy_reward": 0.640234375, + "rewards/format_reward": 0.943359375, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.57421875, + "step": 130 + }, + { + "completion_length": 301.005859375, + "epoch": 0.6410446653806202, + "grad_norm": 2.418685025022163, + "kl": 1.816259765625, + "learning_rate": 8.643708072313617e-07, + "loss": 0.0726, + "reward": 2.6859375, + "reward_std": 0.4477614754810929, + "rewards/accuracy_reward": 0.6265625, + "rewards/format_reward": 0.953125, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.559765625, + "step": 135 + }, + { + "completion_length": 299.0046875, + "epoch": 0.6647870603947174, + "grad_norm": 2.3934470580786984, + "kl": 1.63916015625, + "learning_rate": 8.498711506550983e-07, + "loss": 0.0656, + "reward": 2.665234375, + "reward_std": 0.42022476736456155, + "rewards/accuracy_reward": 0.593359375, + "rewards/format_reward": 0.965234375, + "rewards/influence_reward": 0.522265625, + "rewards/len_reward": 0.584375, + "step": 140 + }, + { + "completion_length": 310.663671875, + "epoch": 0.6885294554088144, + "grad_norm": 5.124954589573938, + "kl": 1.480908203125, + "learning_rate": 8.347705870293799e-07, + "loss": 0.0592, + "reward": 2.5953125, + "reward_std": 0.466478811763227, + "rewards/accuracy_reward": 0.591796875, + "rewards/format_reward": 0.955859375, + "rewards/influence_reward": 0.511328125, + "rewards/len_reward": 0.536328125, + "step": 145 + }, + { + "completion_length": 304.512109375, + "epoch": 0.7122718504229114, + "grad_norm": 2.7544392716511696, + "kl": 1.58447265625, + "learning_rate": 8.190950517167437e-07, + "loss": 0.0634, + "reward": 2.71015625, + "reward_std": 0.44989644438028337, + "rewards/accuracy_reward": 0.643359375, + "rewards/format_reward": 0.955859375, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.54921875, + "step": 150 + }, + { + "completion_length": 307.515625, + "epoch": 0.7360142454370084, + "grad_norm": 3.2720338878640036, + "kl": 1.801708984375, + "learning_rate": 8.028714675991006e-07, + "loss": 0.0721, + "reward": 2.696875, + "reward_std": 0.463063583150506, + "rewards/accuracy_reward": 0.639453125, + "rewards/format_reward": 0.953515625, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.551171875, + "step": 155 + }, + { + "completion_length": 306.36328125, + "epoch": 0.7597566404511055, + "grad_norm": 4.11327264014585, + "kl": 1.860302734375, + "learning_rate": 7.861276988374301e-07, + "loss": 0.0744, + "reward": 2.70234375, + "reward_std": 0.4653250968083739, + "rewards/accuracy_reward": 0.632421875, + "rewards/format_reward": 0.955078125, + "rewards/influence_reward": 0.55078125, + "rewards/len_reward": 0.5640625, + "step": 160 + }, + { + "completion_length": 299.812890625, + "epoch": 0.7834990354652025, + "grad_norm": 4.8236586704402855, + "kl": 2.14326171875, + "learning_rate": 7.688925030148148e-07, + "loss": 0.0857, + "reward": 2.673828125, + "reward_std": 0.44505598582327366, + "rewards/accuracy_reward": 0.621875, + "rewards/format_reward": 0.959765625, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.535546875, + "step": 165 + }, + { + "completion_length": 305.41484375, + "epoch": 0.8072414304792996, + "grad_norm": 1.849946965836104, + "kl": 2.1720703125, + "learning_rate": 7.51195481745018e-07, + "loss": 0.0869, + "reward": 2.708984375, + "reward_std": 0.43415932413190605, + "rewards/accuracy_reward": 0.62265625, + "rewards/format_reward": 0.958203125, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.56640625, + "step": 170 + }, + { + "completion_length": 301.258203125, + "epoch": 0.8309838254933967, + "grad_norm": 2.440806378569226, + "kl": 1.9740234375, + "learning_rate": 7.330670298314281e-07, + "loss": 0.0789, + "reward": 2.70859375, + "reward_std": 0.46049848962575196, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.951953125, + "rewards/influence_reward": 0.538671875, + "rewards/len_reward": 0.590625, + "step": 175 + }, + { + "completion_length": 301.55, + "epoch": 0.8547262205074937, + "grad_norm": 5.1360667348261915, + "kl": 2.40302734375, + "learning_rate": 7.145382830636924e-07, + "loss": 0.0962, + "reward": 2.7078125, + "reward_std": 0.44812944661825893, + "rewards/accuracy_reward": 0.625390625, + "rewards/format_reward": 0.959375, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.56953125, + "step": 180 + }, + { + "completion_length": 296.28515625, + "epoch": 0.8784686155215907, + "grad_norm": 3.0756451628776627, + "kl": 2.0728515625, + "learning_rate": 6.956410647417016e-07, + "loss": 0.0829, + "reward": 2.679296875, + "reward_std": 0.44053732715547084, + "rewards/accuracy_reward": 0.624609375, + "rewards/format_reward": 0.95, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.551953125, + "step": 185 + }, + { + "completion_length": 290.825, + "epoch": 0.9022110105356878, + "grad_norm": 2.58004505898485, + "kl": 1.95107421875, + "learning_rate": 6.764078310187667e-07, + "loss": 0.078, + "reward": 2.743359375, + "reward_std": 0.45461403094232083, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.9625, + "rewards/influence_reward": 0.560546875, + "rewards/len_reward": 0.59296875, + "step": 190 + }, + { + "completion_length": 301.6453125, + "epoch": 0.9259534055497848, + "grad_norm": 3.359431223961218, + "kl": 1.895068359375, + "learning_rate": 6.568716151578653e-07, + "loss": 0.0758, + "reward": 2.6140625, + "reward_std": 0.45234644059091805, + "rewards/accuracy_reward": 0.591015625, + "rewards/format_reward": 0.95703125, + "rewards/influence_reward": 0.521875, + "rewards/len_reward": 0.544140625, + "step": 195 + }, + { + "completion_length": 300.809765625, + "epoch": 0.9496958005638819, + "grad_norm": 2.072678305669791, + "kl": 1.892919921875, + "learning_rate": 6.370659707966967e-07, + "loss": 0.0757, + "reward": 2.6984375, + "reward_std": 0.4385804546996951, + "rewards/accuracy_reward": 0.602734375, + "rewards/format_reward": 0.957421875, + "rewards/influence_reward": 0.5296875, + "rewards/len_reward": 0.60859375, + "step": 200 + }, + { + "completion_length": 295.50078125, + "epoch": 0.973438195577979, + "grad_norm": 2.641906292114807, + "kl": 1.882763671875, + "learning_rate": 6.170249143189878e-07, + "loss": 0.0753, + "reward": 2.726953125, + "reward_std": 0.45993594732135534, + "rewards/accuracy_reward": 0.61875, + "rewards/format_reward": 0.965625, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.5890625, + "step": 205 + }, + { + "completion_length": 294.291796875, + "epoch": 0.997180590592076, + "grad_norm": 3.1118319118270263, + "kl": 1.721240234375, + "learning_rate": 5.967828664310282e-07, + "loss": 0.0689, + "reward": 2.689453125, + "reward_std": 0.4471969947218895, + "rewards/accuracy_reward": 0.618359375, + "rewards/format_reward": 0.96171875, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.552734375, + "step": 210 + }, + { + "completion_length": 298.9141156462585, + "epoch": 1.0189939160112775, + "grad_norm": 1.4510607380023717, + "kl": 1.6323341836734695, + "learning_rate": 5.763745930437786e-07, + "loss": 0.0657, + "reward": 2.7891156462585034, + "reward_std": 0.4109960768093057, + "rewards/accuracy_reward": 0.6547619047619048, + "rewards/format_reward": 0.9596088435374149, + "rewards/influence_reward": 0.5778061224489796, + "rewards/len_reward": 0.5969387755102041, + "step": 215 + }, + { + "completion_length": 292.062109375, + "epoch": 1.0427363110253747, + "grad_norm": 2.3079311627757115, + "kl": 1.639599609375, + "learning_rate": 5.558351455620851e-07, + "loss": 0.0656, + "reward": 2.71171875, + "reward_std": 0.40011929515749217, + "rewards/accuracy_reward": 0.61640625, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.537890625, + "rewards/len_reward": 0.587109375, + "step": 220 + }, + { + "completion_length": 297.239453125, + "epoch": 1.0664787060394718, + "grad_norm": 1.8840863111335822, + "kl": 2.28310546875, + "learning_rate": 5.351998006835562e-07, + "loss": 0.0914, + "reward": 2.684375, + "reward_std": 0.45486766248941424, + "rewards/accuracy_reward": 0.603515625, + "rewards/format_reward": 0.962890625, + "rewards/influence_reward": 0.537890625, + "rewards/len_reward": 0.580078125, + "step": 225 + }, + { + "completion_length": 288.18125, + "epoch": 1.0902211010535687, + "grad_norm": 2.0051543482646657, + "kl": 1.657861328125, + "learning_rate": 5.145039998104975e-07, + "loss": 0.0663, + "reward": 2.69765625, + "reward_std": 0.4361386923119426, + "rewards/accuracy_reward": 0.622265625, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.553515625, + "step": 230 + }, + { + "completion_length": 287.385546875, + "epoch": 1.1139634960676659, + "grad_norm": 1.4748593771929919, + "kl": 1.78935546875, + "learning_rate": 4.937832881789634e-07, + "loss": 0.0716, + "reward": 2.787109375, + "reward_std": 0.4470808956772089, + "rewards/accuracy_reward": 0.64296875, + "rewards/format_reward": 0.969921875, + "rewards/influence_reward": 0.569921875, + "rewards/len_reward": 0.604296875, + "step": 235 + }, + { + "completion_length": 288.096484375, + "epoch": 1.1377058910817628, + "grad_norm": 10.954523562177771, + "kl": 1.878369140625, + "learning_rate": 4.730732538094749e-07, + "loss": 0.0751, + "reward": 2.716796875, + "reward_std": 0.4533087441697717, + "rewards/accuracy_reward": 0.608203125, + "rewards/format_reward": 0.96484375, + "rewards/influence_reward": 0.543359375, + "rewards/len_reward": 0.600390625, + "step": 240 + }, + { + "completion_length": 286.948828125, + "epoch": 1.16144828609586, + "grad_norm": 3.7350800690768913, + "kl": 1.802978515625, + "learning_rate": 4.524094663842527e-07, + "loss": 0.0721, + "reward": 2.716015625, + "reward_std": 0.46027831770479677, + "rewards/accuracy_reward": 0.605078125, + "rewards/format_reward": 0.96640625, + "rewards/influence_reward": 0.529296875, + "rewards/len_reward": 0.615234375, + "step": 245 + }, + { + "completion_length": 298.440234375, + "epoch": 1.1851906811099568, + "grad_norm": 1.7998199572787943, + "kl": 1.9130859375, + "learning_rate": 4.3182741615594863e-07, + "loss": 0.0765, + "reward": 2.73046875, + "reward_std": 0.4339360993355513, + "rewards/accuracy_reward": 0.629296875, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.55546875, + "rewards/len_reward": 0.576953125, + "step": 250 + }, + { + "completion_length": 297.07421875, + "epoch": 1.208933076124054, + "grad_norm": 2.1433576353118755, + "kl": 2.023828125, + "learning_rate": 4.1136245299279625e-07, + "loss": 0.081, + "reward": 2.69375, + "reward_std": 0.4361835679039359, + "rewards/accuracy_reward": 0.6046875, + "rewards/format_reward": 0.962109375, + "rewards/influence_reward": 0.5265625, + "rewards/len_reward": 0.600390625, + "step": 255 + }, + { + "completion_length": 283.55859375, + "epoch": 1.2326754711381511, + "grad_norm": 3.56858833503255, + "kl": 1.9943359375, + "learning_rate": 3.910497256648742e-07, + "loss": 0.0798, + "reward": 2.776171875, + "reward_std": 0.41840124800801276, + "rewards/accuracy_reward": 0.62421875, + "rewards/format_reward": 0.975, + "rewards/influence_reward": 0.55703125, + "rewards/len_reward": 0.619921875, + "step": 260 + }, + { + "completion_length": 285.401953125, + "epoch": 1.256417866152248, + "grad_norm": 3.0202540131791316, + "kl": 1.812353515625, + "learning_rate": 3.7092412147575756e-07, + "loss": 0.0725, + "reward": 2.667578125, + "reward_std": 0.4479133376851678, + "rewards/accuracy_reward": 0.5859375, + "rewards/format_reward": 0.97109375, + "rewards/influence_reward": 0.51328125, + "rewards/len_reward": 0.597265625, + "step": 265 + }, + { + "completion_length": 296.51953125, + "epoch": 1.2801602611663452, + "grad_norm": 6.685851651155463, + "kl": 1.824169921875, + "learning_rate": 3.510202063432397e-07, + "loss": 0.073, + "reward": 2.68125, + "reward_std": 0.45598011631518603, + "rewards/accuracy_reward": 0.59453125, + "rewards/format_reward": 0.97109375, + "rewards/influence_reward": 0.526171875, + "rewards/len_reward": 0.589453125, + "step": 270 + }, + { + "completion_length": 297.57734375, + "epoch": 1.3039026561804423, + "grad_norm": 2.291528264931079, + "kl": 1.847607421875, + "learning_rate": 3.3137216543203747e-07, + "loss": 0.0739, + "reward": 2.69765625, + "reward_std": 0.41086965166032313, + "rewards/accuracy_reward": 0.59140625, + "rewards/format_reward": 0.9765625, + "rewards/influence_reward": 0.53046875, + "rewards/len_reward": 0.59921875, + "step": 275 + }, + { + "completion_length": 290.746875, + "epoch": 1.3276450511945392, + "grad_norm": 1.8784141288314866, + "kl": 1.92822265625, + "learning_rate": 3.1201374444044414e-07, + "loss": 0.0771, + "reward": 2.68671875, + "reward_std": 0.43726298715919254, + "rewards/accuracy_reward": 0.606640625, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.5296875, + "rewards/len_reward": 0.581640625, + "step": 280 + }, + { + "completion_length": 285.90390625, + "epoch": 1.3513874462086364, + "grad_norm": 3.8666864047404657, + "kl": 2.049609375, + "learning_rate": 2.929781916417696e-07, + "loss": 0.082, + "reward": 2.79140625, + "reward_std": 0.4504884161055088, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.56875, + "rewards/len_reward": 0.611328125, + "step": 285 + }, + { + "completion_length": 278.126171875, + "epoch": 1.3751298412227333, + "grad_norm": 2.7940015666308584, + "kl": 1.9935546875, + "learning_rate": 2.742982007801121e-07, + "loss": 0.0797, + "reward": 2.714453125, + "reward_std": 0.40985080897808074, + "rewards/accuracy_reward": 0.605859375, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.553125, + "rewards/len_reward": 0.5796875, + "step": 290 + }, + { + "completion_length": 282.807421875, + "epoch": 1.3988722362368304, + "grad_norm": 2.1190543029510374, + "kl": 2.0150390625, + "learning_rate": 2.5600585491854113e-07, + "loss": 0.0806, + "reward": 2.736328125, + "reward_std": 0.4611986864358187, + "rewards/accuracy_reward": 0.625, + "rewards/format_reward": 0.966015625, + "rewards/influence_reward": 0.5453125, + "rewards/len_reward": 0.6, + "step": 295 + }, + { + "completion_length": 285.337890625, + "epoch": 1.4226146312509274, + "grad_norm": 2.0524239671070235, + "kl": 2.023779296875, + "learning_rate": 2.3813257133612823e-07, + "loss": 0.081, + "reward": 2.7375, + "reward_std": 0.4188694503158331, + "rewards/accuracy_reward": 0.615625, + "rewards/format_reward": 0.96796875, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.607421875, + "step": 300 + }, + { + "completion_length": 280.583203125, + "epoch": 1.4463570262650245, + "grad_norm": 2.4639075460957103, + "kl": 1.916455078125, + "learning_rate": 2.207090475684702e-07, + "loss": 0.0766, + "reward": 2.778515625, + "reward_std": 0.4049776840955019, + "rewards/accuracy_reward": 0.621484375, + "rewards/format_reward": 0.978125, + "rewards/influence_reward": 0.55703125, + "rewards/len_reward": 0.621875, + "step": 305 + }, + { + "completion_length": 279.21640625, + "epoch": 1.4700994212791216, + "grad_norm": 1.9580691543159996, + "kl": 1.886328125, + "learning_rate": 2.0376520868437836e-07, + "loss": 0.0754, + "reward": 2.69140625, + "reward_std": 0.4295359971001744, + "rewards/accuracy_reward": 0.584765625, + "rewards/format_reward": 0.9734375, + "rewards/influence_reward": 0.512109375, + "rewards/len_reward": 0.62109375, + "step": 310 + }, + { + "completion_length": 287.18671875, + "epoch": 1.4938418162932185, + "grad_norm": 2.334280950294775, + "kl": 1.902001953125, + "learning_rate": 1.8733015588928547e-07, + "loss": 0.0761, + "reward": 2.748046875, + "reward_std": 0.4672464972361922, + "rewards/accuracy_reward": 0.620703125, + "rewards/format_reward": 0.979296875, + "rewards/influence_reward": 0.544140625, + "rewards/len_reward": 0.60390625, + "step": 315 + }, + { + "completion_length": 279.612109375, + "epoch": 1.5175842113073155, + "grad_norm": 2.383804496413666, + "kl": 1.881494140625, + "learning_rate": 1.7143211654364758e-07, + "loss": 0.0753, + "reward": 2.704296875, + "reward_std": 0.46042243372648956, + "rewards/accuracy_reward": 0.609375, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.540234375, + "rewards/len_reward": 0.57890625, + "step": 320 + }, + { + "completion_length": 276.201171875, + "epoch": 1.5413266063214128, + "grad_norm": 1.8621036607786687, + "kl": 2.042041015625, + "learning_rate": 1.5609839568218247e-07, + "loss": 0.0817, + "reward": 2.78984375, + "reward_std": 0.4288489479571581, + "rewards/accuracy_reward": 0.640625, + "rewards/format_reward": 0.97890625, + "rewards/influence_reward": 0.5796875, + "rewards/len_reward": 0.590625, + "step": 325 + }, + { + "completion_length": 285.061328125, + "epoch": 1.5650690013355097, + "grad_norm": 2.541259800858008, + "kl": 2.11279296875, + "learning_rate": 1.413553291172106e-07, + "loss": 0.0845, + "reward": 2.744140625, + "reward_std": 0.43316187243908644, + "rewards/accuracy_reward": 0.624609375, + "rewards/format_reward": 0.961328125, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.594921875, + "step": 330 + }, + { + "completion_length": 286.321875, + "epoch": 1.5888113963496067, + "grad_norm": 2.4383264225155825, + "kl": 2.04287109375, + "learning_rate": 1.2722823820664575e-07, + "loss": 0.0817, + "reward": 2.7609375, + "reward_std": 0.42981729917228223, + "rewards/accuracy_reward": 0.623828125, + "rewards/format_reward": 0.973046875, + "rewards/influence_reward": 0.549609375, + "rewards/len_reward": 0.614453125, + "step": 335 + }, + { + "completion_length": 281.6328125, + "epoch": 1.6125537913637038, + "grad_norm": 2.1689228150160225, + "kl": 2.00263671875, + "learning_rate": 1.1374138636432051e-07, + "loss": 0.0801, + "reward": 2.738671875, + "reward_std": 0.4134707026183605, + "rewards/accuracy_reward": 0.61015625, + "rewards/format_reward": 0.97421875, + "rewards/influence_reward": 0.54609375, + "rewards/len_reward": 0.608203125, + "step": 340 + }, + { + "completion_length": 292.502734375, + "epoch": 1.636296186377801, + "grad_norm": 4.449673329252311, + "kl": 1.98564453125, + "learning_rate": 1.0091793738734111e-07, + "loss": 0.0794, + "reward": 2.7078125, + "reward_std": 0.4420934099704027, + "rewards/accuracy_reward": 0.5953125, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.52890625, + "rewards/len_reward": 0.61328125, + "step": 345 + }, + { + "completion_length": 284.086328125, + "epoch": 1.6600385813918979, + "grad_norm": 2.2530249348579403, + "kl": 1.920751953125, + "learning_rate": 8.877991567204351e-08, + "loss": 0.0768, + "reward": 2.77578125, + "reward_std": 0.40416364911943675, + "rewards/accuracy_reward": 0.6421875, + "rewards/format_reward": 0.97265625, + "rewards/influence_reward": 0.559765625, + "rewards/len_reward": 0.601171875, + "step": 350 + }, + { + "completion_length": 286.23359375, + "epoch": 1.683780976405995, + "grad_norm": 11.607212223835898, + "kl": 1.99482421875, + "learning_rate": 7.734816838688246e-08, + "loss": 0.0798, + "reward": 2.7375, + "reward_std": 0.42118714693933723, + "rewards/accuracy_reward": 0.609375, + "rewards/format_reward": 0.972265625, + "rewards/influence_reward": 0.54375, + "rewards/len_reward": 0.612109375, + "step": 355 + }, + { + "completion_length": 288.31875, + "epoch": 1.7075233714200921, + "grad_norm": 2.560035528567494, + "kl": 1.884912109375, + "learning_rate": 6.664232966721995e-08, + "loss": 0.0754, + "reward": 2.655078125, + "reward_std": 0.44481576029211284, + "rewards/accuracy_reward": 0.591796875, + "rewards/format_reward": 0.9671875, + "rewards/influence_reward": 0.51796875, + "rewards/len_reward": 0.578125, + "step": 360 + }, + { + "completion_length": 292.05546875, + "epoch": 1.731265766434189, + "grad_norm": 2.703658020341151, + "kl": 1.88125, + "learning_rate": 5.668078689351008e-08, + "loss": 0.0753, + "reward": 2.731640625, + "reward_std": 0.4349971186369658, + "rewards/accuracy_reward": 0.603515625, + "rewards/format_reward": 0.97265625, + "rewards/influence_reward": 0.535546875, + "rewards/len_reward": 0.619921875, + "step": 365 + }, + { + "completion_length": 289.07265625, + "epoch": 1.755008161448286, + "grad_norm": 2.15796183633457, + "kl": 1.920556640625, + "learning_rate": 4.748064911079669e-08, + "loss": 0.0768, + "reward": 2.773046875, + "reward_std": 0.45684912260621785, + "rewards/accuracy_reward": 0.634375, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.569140625, + "rewards/len_reward": 0.60078125, + "step": 370 + }, + { + "completion_length": 297.7921875, + "epoch": 1.7787505564623831, + "grad_norm": 1.9525269307848967, + "kl": 1.950634765625, + "learning_rate": 3.905771764376553e-08, + "loss": 0.078, + "reward": 2.762890625, + "reward_std": 0.43305158857256176, + "rewards/accuracy_reward": 0.616796875, + "rewards/format_reward": 0.970703125, + "rewards/influence_reward": 0.544921875, + "rewards/len_reward": 0.63046875, + "step": 375 + }, + { + "completion_length": 286.23125, + "epoch": 1.8024929514764803, + "grad_norm": 1.8795557235019384, + "kl": 1.94345703125, + "learning_rate": 3.142645895781715e-08, + "loss": 0.0777, + "reward": 2.705859375, + "reward_std": 0.4185318287461996, + "rewards/accuracy_reward": 0.6078125, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.53125, + "rewards/len_reward": 0.59765625, + "step": 380 + }, + { + "completion_length": 284.5234375, + "epoch": 1.8262353464905772, + "grad_norm": 1.8303802044437847, + "kl": 1.9130859375, + "learning_rate": 2.459997981277423e-08, + "loss": 0.0765, + "reward": 2.743359375, + "reward_std": 0.42376566473394633, + "rewards/accuracy_reward": 0.6296875, + "rewards/format_reward": 0.973828125, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.583203125, + "step": 385 + }, + { + "completion_length": 287.645703125, + "epoch": 1.8499777415046743, + "grad_norm": 2.1486695226548314, + "kl": 1.919140625, + "learning_rate": 1.859000475189687e-08, + "loss": 0.0767, + "reward": 2.70625, + "reward_std": 0.43876812513917685, + "rewards/accuracy_reward": 0.62109375, + "rewards/format_reward": 0.965625, + "rewards/influence_reward": 0.5328125, + "rewards/len_reward": 0.58671875, + "step": 390 + }, + { + "completion_length": 289.16953125, + "epoch": 1.8737201365187715, + "grad_norm": 2.3275579827754704, + "kl": 1.96728515625, + "learning_rate": 1.3406855964866404e-08, + "loss": 0.0787, + "reward": 2.69453125, + "reward_std": 0.44194721039384605, + "rewards/accuracy_reward": 0.603125, + "rewards/format_reward": 0.971875, + "rewards/influence_reward": 0.533984375, + "rewards/len_reward": 0.585546875, + "step": 395 + }, + { + "completion_length": 285.14296875, + "epoch": 1.8974625315328684, + "grad_norm": 2.1178151388074538, + "kl": 1.926513671875, + "learning_rate": 9.059435559326256e-09, + "loss": 0.077, + "reward": 2.69609375, + "reward_std": 0.4095570512115955, + "rewards/accuracy_reward": 0.604296875, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.529296875, + "rewards/len_reward": 0.5921875, + "step": 400 + }, + { + "completion_length": 291.73046875, + "epoch": 1.9212049265469653, + "grad_norm": 3.0382797909309063, + "kl": 1.9125, + "learning_rate": 5.555210271427191e-09, + "loss": 0.0765, + "reward": 2.74375, + "reward_std": 0.45224274341017007, + "rewards/accuracy_reward": 0.627734375, + "rewards/format_reward": 0.968359375, + "rewards/influence_reward": 0.544140625, + "rewards/len_reward": 0.603515625, + "step": 405 + }, + { + "completion_length": 285.82109375, + "epoch": 1.9449473215610624, + "grad_norm": 2.223879198885574, + "kl": 1.93515625, + "learning_rate": 2.900198641635876e-09, + "loss": 0.0774, + "reward": 2.766015625, + "reward_std": 0.4194388585165143, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.973046875, + "rewards/influence_reward": 0.558203125, + "rewards/len_reward": 0.607421875, + "step": 410 + }, + { + "completion_length": 284.583203125, + "epoch": 1.9686897165751596, + "grad_norm": 2.3711705196769834, + "kl": 1.942138671875, + "learning_rate": 1.0989606778344373e-09, + "loss": 0.0777, + "reward": 2.782421875, + "reward_std": 0.42840481735765934, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.568359375, + "rewards/len_reward": 0.6078125, + "step": 415 + }, + { + "completion_length": 297.46796875, + "epoch": 1.9924321115892565, + "grad_norm": 18.12331360764631, + "kl": 1.966943359375, + "learning_rate": 1.5459002346324136e-10, + "loss": 0.0787, + "reward": 2.726171875, + "reward_std": 0.4440956773236394, + "rewards/accuracy_reward": 0.6171875, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.5265625, + "rewards/len_reward": 0.613671875, + "step": 420 + } + ], + "logging_steps": 5, + "max_steps": 422, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 10, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-422/training_args.bin b/checkpoint-422/training_args.bin new file mode 100644 index 0000000..a00094f --- /dev/null +++ b/checkpoint-422/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9febc05b21a9697f39aca7d2e016e5591fdde9dc93d33319026f426081ab2f5a +size 7288 diff --git a/checkpoint-422/zero_to_fp32.py b/checkpoint-422/zero_to_fp32.py new file mode 100644 index 0000000..e69ecd9 --- /dev/null +++ b/checkpoint-422/zero_to_fp32.py @@ -0,0 +1,674 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: +# python zero_to_fp32.py . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import json +from tqdm import tqdm +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + total_files = len(files) + state_dicts = [] + for f in files: + state_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + if zero_stage <= 2: + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + elif zero_stage == 3: + # if there is more than one param group, there will be multiple flattened tensors - one + # flattened tensor per group - for simplicity merge them into a single tensor + # + # XXX: could make the script more memory efficient for when there are multiple groups - it + # will require matching the sub-lists of param_shapes for each param group flattened tensor + + fp32_flat_groups = [ + torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts)) + ] + + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = fp32_flat_groups[0].numel() * world_size + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'): + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # XXX: memory usage doubles here + state_dict[name] = torch.cat( + tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)), + 0).narrow(0, 0, unpartitioned_numel).view(shape) + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + Returns: + - pytorch ``state_dict`` + + Note: this approach may not work if your application doesn't have sufficient free CPU memory and + you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + state_dict_split = split_torch_state_dict_into_shards(state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors} + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard, output_path, metadata={"format": "pt"}) + else: + torch.save(shard, output_path) + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument("output_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/config.json b/config.json new file mode 100644 index 0000000..06df27b --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b9c76a3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128009, + 128001, + 128008, + 128009 + ], + "pad_token_id": 128009, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.6" +} diff --git a/pytorch_model-00001-of-00004.bin b/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..bab9d86 --- /dev/null +++ b/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdf60dbbda44f160be0c8820338d5594a499a7a646293eb2429bdc176cbb264 +size 4976717314 diff --git a/pytorch_model-00002-of-00004.bin b/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..7b8f57e --- /dev/null +++ b/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65fa1a703a4fdbec3410bb2785e4271a30dec45b5d027c9174f8407d45640e8 +size 4999826246 diff --git a/pytorch_model-00003-of-00004.bin b/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..01082bc --- /dev/null +++ b/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8576907561d4e633def10d0fcef201a98dcfe394ab30037f764c4fb3263c7d39 +size 4915938762 diff --git a/pytorch_model-00004-of-00004.bin b/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..6faf37a --- /dev/null +++ b/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f275b89cce74d491e663e2d7a079886ce8833d5fe4fc29ada554fe3001218c3 +size 1168140873 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..3c202ae --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.norm.weight": "pytorch_model-00004-of-00004.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..b43be96 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..92cc72b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26 +size 17210084 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3beeacc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..11a2873 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "total_flos": 0.0, + "train_loss": 0.07021697652106884, + "train_runtime": 419033.0805, + "train_samples": 26956, + "train_samples_per_second": 0.129, + "train_steps_per_second": 0.001 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..33857c9 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1326 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 422, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "completion_length": 343.505859375, + "epoch": 0.0047484790028194095, + "grad_norm": 10.941497736666665, + "kl": 1.436471939086914e-05, + "learning_rate": 0.0, + "loss": 0.0, + "reward": 2.490234375, + "reward_std": 0.557172168046236, + "rewards/accuracy_reward": 0.66796875, + "rewards/format_reward": 0.806640625, + "rewards/influence_reward": 0.53515625, + "rewards/len_reward": 0.48046875, + "step": 1 + }, + { + "completion_length": 341.50390625, + "epoch": 0.023742395014097046, + "grad_norm": 6.812195416096856, + "kl": 0.0044515132904052734, + "learning_rate": 9.302325581395349e-08, + "loss": 0.0002, + "reward": 2.46826171875, + "reward_std": 0.5800532991997898, + "rewards/accuracy_reward": 0.66259765625, + "rewards/format_reward": 0.8154296875, + "rewards/influence_reward": 0.537109375, + "rewards/len_reward": 0.453125, + "step": 5 + }, + { + "completion_length": 355.537890625, + "epoch": 0.04748479002819409, + "grad_norm": 8.69360815652138, + "kl": 0.008914566040039063, + "learning_rate": 2.0930232558139536e-07, + "loss": 0.0004, + "reward": 2.44375, + "reward_std": 0.6262629209086299, + "rewards/accuracy_reward": 0.653125, + "rewards/format_reward": 0.804296875, + "rewards/influence_reward": 0.519140625, + "rewards/len_reward": 0.4671875, + "step": 10 + }, + { + "completion_length": 359.13984375, + "epoch": 0.07122718504229114, + "grad_norm": 9.167296678106975, + "kl": 0.1373016357421875, + "learning_rate": 3.2558139534883724e-07, + "loss": 0.0055, + "reward": 2.444140625, + "reward_std": 0.5922891769558192, + "rewards/accuracy_reward": 0.666015625, + "rewards/format_reward": 0.79921875, + "rewards/influence_reward": 0.525390625, + "rewards/len_reward": 0.453515625, + "step": 15 + }, + { + "completion_length": 351.53828125, + "epoch": 0.09496958005638818, + "grad_norm": 20.494707498797204, + "kl": 0.620166015625, + "learning_rate": 4.4186046511627905e-07, + "loss": 0.0248, + "reward": 2.49609375, + "reward_std": 0.6080626923590898, + "rewards/accuracy_reward": 0.655078125, + "rewards/format_reward": 0.81171875, + "rewards/influence_reward": 0.533984375, + "rewards/len_reward": 0.4953125, + "step": 20 + }, + { + "completion_length": 350.94140625, + "epoch": 0.11871197507048524, + "grad_norm": 58.39828164144229, + "kl": 4.012548828125, + "learning_rate": 5.581395348837209e-07, + "loss": 0.1604, + "reward": 2.5171875, + "reward_std": 0.5175810419023037, + "rewards/accuracy_reward": 0.652734375, + "rewards/format_reward": 0.86015625, + "rewards/influence_reward": 0.5484375, + "rewards/len_reward": 0.455859375, + "step": 25 + }, + { + "completion_length": 344.183203125, + "epoch": 0.14245437008458228, + "grad_norm": 10.671491690481664, + "kl": 1.959765625, + "learning_rate": 6.744186046511627e-07, + "loss": 0.0784, + "reward": 2.559375, + "reward_std": 0.49339695163071157, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.8859375, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.484375, + "step": 30 + }, + { + "completion_length": 312.225390625, + "epoch": 0.16619676509867934, + "grad_norm": 6.830335531593763, + "kl": 1.739990234375, + "learning_rate": 7.906976744186046e-07, + "loss": 0.0696, + "reward": 2.652734375, + "reward_std": 0.4439069716259837, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.9421875, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.51015625, + "step": 35 + }, + { + "completion_length": 284.68359375, + "epoch": 0.18993916011277637, + "grad_norm": 14.080133543924038, + "kl": 1.54609375, + "learning_rate": 9.069767441860464e-07, + "loss": 0.0619, + "reward": 2.736328125, + "reward_std": 0.48739379905164243, + "rewards/accuracy_reward": 0.658203125, + "rewards/format_reward": 0.94453125, + "rewards/influence_reward": 0.5828125, + "rewards/len_reward": 0.55078125, + "step": 40 + }, + { + "completion_length": 276.867578125, + "epoch": 0.21368155512687342, + "grad_norm": 35.20677672719882, + "kl": 1.3846435546875, + "learning_rate": 9.999828225438954e-07, + "loss": 0.0554, + "reward": 2.808203125, + "reward_std": 0.46657639369368553, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.954296875, + "rewards/influence_reward": 0.573046875, + "rewards/len_reward": 0.6453125, + "step": 45 + }, + { + "completion_length": 273.9359375, + "epoch": 0.23742395014097048, + "grad_norm": 3.603130834120874, + "kl": 1.1903564453125, + "learning_rate": 9.993817354984484e-07, + "loss": 0.0476, + "reward": 2.736328125, + "reward_std": 0.4892417475581169, + "rewards/accuracy_reward": 0.63984375, + "rewards/format_reward": 0.940625, + "rewards/influence_reward": 0.554296875, + "rewards/len_reward": 0.6015625, + "step": 50 + }, + { + "completion_length": 271.577734375, + "epoch": 0.26116634515506754, + "grad_norm": 2.2725600898834406, + "kl": 1.1795166015625, + "learning_rate": 9.979229555432882e-07, + "loss": 0.0472, + "reward": 2.798828125, + "reward_std": 0.46620402578264475, + "rewards/accuracy_reward": 0.65, + "rewards/format_reward": 0.951171875, + "rewards/influence_reward": 0.5890625, + "rewards/len_reward": 0.60859375, + "step": 55 + }, + { + "completion_length": 286.709375, + "epoch": 0.28490874016916456, + "grad_norm": 4.953405517687021, + "kl": 1.2238525390625, + "learning_rate": 9.95608988146948e-07, + "loss": 0.0489, + "reward": 2.83984375, + "reward_std": 0.47557592410594224, + "rewards/accuracy_reward": 0.676953125, + "rewards/format_reward": 0.94140625, + "rewards/influence_reward": 0.602734375, + "rewards/len_reward": 0.61875, + "step": 60 + }, + { + "completion_length": 277.02578125, + "epoch": 0.3086511351832616, + "grad_norm": 3.0787337409013547, + "kl": 1.3475830078125, + "learning_rate": 9.924438075705754e-07, + "loss": 0.0539, + "reward": 2.82109375, + "reward_std": 0.45666036382317543, + "rewards/accuracy_reward": 0.678515625, + "rewards/format_reward": 0.938671875, + "rewards/influence_reward": 0.605859375, + "rewards/len_reward": 0.598046875, + "step": 65 + }, + { + "completion_length": 285.7953125, + "epoch": 0.3323935301973587, + "grad_norm": 4.0730313066810995, + "kl": 1.3648681640625, + "learning_rate": 9.884328500421004e-07, + "loss": 0.0546, + "reward": 2.772265625, + "reward_std": 0.44936057794839146, + "rewards/accuracy_reward": 0.64375, + "rewards/format_reward": 0.9421875, + "rewards/influence_reward": 0.58046875, + "rewards/len_reward": 0.605859375, + "step": 70 + }, + { + "completion_length": 292.43828125, + "epoch": 0.3561359252114557, + "grad_norm": 3.1544402674020002, + "kl": 1.1553466796875, + "learning_rate": 9.835830044194623e-07, + "loss": 0.0462, + "reward": 2.688671875, + "reward_std": 0.4725625243037939, + "rewards/accuracy_reward": 0.6109375, + "rewards/format_reward": 0.9296875, + "rewards/influence_reward": 0.532421875, + "rewards/len_reward": 0.615625, + "step": 75 + }, + { + "completion_length": 286.590234375, + "epoch": 0.37987832022555273, + "grad_norm": 4.765364778587015, + "kl": 1.1624267578125, + "learning_rate": 9.779026003589303e-07, + "loss": 0.0465, + "reward": 2.708984375, + "reward_std": 0.4846075477078557, + "rewards/accuracy_reward": 0.6375, + "rewards/format_reward": 0.930078125, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.584765625, + "step": 80 + }, + { + "completion_length": 290.792578125, + "epoch": 0.4036207152396498, + "grad_norm": 9.253671242707203, + "kl": 1.3268310546875, + "learning_rate": 9.714013940088387e-07, + "loss": 0.0531, + "reward": 2.683203125, + "reward_std": 0.4955078672617674, + "rewards/accuracy_reward": 0.630859375, + "rewards/format_reward": 0.926953125, + "rewards/influence_reward": 0.55625, + "rewards/len_reward": 0.569140625, + "step": 85 + }, + { + "completion_length": 281.421484375, + "epoch": 0.42736311025374685, + "grad_norm": 3.4409983083101086, + "kl": 1.6419921875, + "learning_rate": 9.640905512533092e-07, + "loss": 0.0657, + "reward": 2.748046875, + "reward_std": 0.4972141746431589, + "rewards/accuracy_reward": 0.632421875, + "rewards/format_reward": 0.945703125, + "rewards/influence_reward": 0.561328125, + "rewards/len_reward": 0.60859375, + "step": 90 + }, + { + "completion_length": 267.971875, + "epoch": 0.4511055052678439, + "grad_norm": 2.2522797459391732, + "kl": 1.63046875, + "learning_rate": 9.55982628534738e-07, + "loss": 0.0652, + "reward": 2.778125, + "reward_std": 0.4521504515781999, + "rewards/accuracy_reward": 0.6265625, + "rewards/format_reward": 0.943359375, + "rewards/influence_reward": 0.56796875, + "rewards/len_reward": 0.640234375, + "step": 95 + }, + { + "completion_length": 267.776953125, + "epoch": 0.47484790028194096, + "grad_norm": 2.4372708411881794, + "kl": 1.320361328125, + "learning_rate": 9.470915512879851e-07, + "loss": 0.0528, + "reward": 2.808984375, + "reward_std": 0.4696818504482508, + "rewards/accuracy_reward": 0.650390625, + "rewards/format_reward": 0.941015625, + "rewards/influence_reward": 0.58515625, + "rewards/len_reward": 0.632421875, + "step": 100 + }, + { + "completion_length": 283.4515625, + "epoch": 0.498590295296038, + "grad_norm": 3.8496772212244457, + "kl": 1.447314453125, + "learning_rate": 9.374325900233086e-07, + "loss": 0.0579, + "reward": 2.8171875, + "reward_std": 0.45389450453221797, + "rewards/accuracy_reward": 0.660546875, + "rewards/format_reward": 0.953515625, + "rewards/influence_reward": 0.585546875, + "rewards/len_reward": 0.617578125, + "step": 105 + }, + { + "completion_length": 294.027734375, + "epoch": 0.5223326903101351, + "grad_norm": 3.309296740246584, + "kl": 1.67744140625, + "learning_rate": 9.270223340991146e-07, + "loss": 0.0671, + "reward": 2.75546875, + "reward_std": 0.4890925087034702, + "rewards/accuracy_reward": 0.646875, + "rewards/format_reward": 0.95625, + "rewards/influence_reward": 0.56953125, + "rewards/len_reward": 0.5828125, + "step": 110 + }, + { + "completion_length": 295.9484375, + "epoch": 0.5460750853242321, + "grad_norm": 4.3161975783345845, + "kl": 1.809423828125, + "learning_rate": 9.158786632295775e-07, + "loss": 0.0724, + "reward": 2.72734375, + "reward_std": 0.46550923883914946, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.954296875, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.57265625, + "step": 115 + }, + { + "completion_length": 297.998046875, + "epoch": 0.5698174803383291, + "grad_norm": 5.658396439699509, + "kl": 1.731787109375, + "learning_rate": 9.040207167760585e-07, + "loss": 0.0693, + "reward": 2.66875, + "reward_std": 0.4691320048645139, + "rewards/accuracy_reward": 0.621875, + "rewards/format_reward": 0.945703125, + "rewards/influence_reward": 0.54765625, + "rewards/len_reward": 0.553515625, + "step": 120 + }, + { + "completion_length": 308.9625, + "epoch": 0.5935598753524262, + "grad_norm": 2.884522521427685, + "kl": 1.869189453125, + "learning_rate": 8.9146886087507e-07, + "loss": 0.0748, + "reward": 2.70234375, + "reward_std": 0.42319196127355097, + "rewards/accuracy_reward": 0.6296875, + "rewards/format_reward": 0.946875, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.579296875, + "step": 125 + }, + { + "completion_length": 300.675390625, + "epoch": 0.6173022703665232, + "grad_norm": 4.353864200081107, + "kl": 1.741796875, + "learning_rate": 8.782446534592411e-07, + "loss": 0.0697, + "reward": 2.71953125, + "reward_std": 0.46506577655673026, + "rewards/accuracy_reward": 0.640234375, + "rewards/format_reward": 0.943359375, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.57421875, + "step": 130 + }, + { + "completion_length": 301.005859375, + "epoch": 0.6410446653806202, + "grad_norm": 2.418685025022163, + "kl": 1.816259765625, + "learning_rate": 8.643708072313617e-07, + "loss": 0.0726, + "reward": 2.6859375, + "reward_std": 0.4477614754810929, + "rewards/accuracy_reward": 0.6265625, + "rewards/format_reward": 0.953125, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.559765625, + "step": 135 + }, + { + "completion_length": 299.0046875, + "epoch": 0.6647870603947174, + "grad_norm": 2.3934470580786984, + "kl": 1.63916015625, + "learning_rate": 8.498711506550983e-07, + "loss": 0.0656, + "reward": 2.665234375, + "reward_std": 0.42022476736456155, + "rewards/accuracy_reward": 0.593359375, + "rewards/format_reward": 0.965234375, + "rewards/influence_reward": 0.522265625, + "rewards/len_reward": 0.584375, + "step": 140 + }, + { + "completion_length": 310.663671875, + "epoch": 0.6885294554088144, + "grad_norm": 5.124954589573938, + "kl": 1.480908203125, + "learning_rate": 8.347705870293799e-07, + "loss": 0.0592, + "reward": 2.5953125, + "reward_std": 0.466478811763227, + "rewards/accuracy_reward": 0.591796875, + "rewards/format_reward": 0.955859375, + "rewards/influence_reward": 0.511328125, + "rewards/len_reward": 0.536328125, + "step": 145 + }, + { + "completion_length": 304.512109375, + "epoch": 0.7122718504229114, + "grad_norm": 2.7544392716511696, + "kl": 1.58447265625, + "learning_rate": 8.190950517167437e-07, + "loss": 0.0634, + "reward": 2.71015625, + "reward_std": 0.44989644438028337, + "rewards/accuracy_reward": 0.643359375, + "rewards/format_reward": 0.955859375, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.54921875, + "step": 150 + }, + { + "completion_length": 307.515625, + "epoch": 0.7360142454370084, + "grad_norm": 3.2720338878640036, + "kl": 1.801708984375, + "learning_rate": 8.028714675991006e-07, + "loss": 0.0721, + "reward": 2.696875, + "reward_std": 0.463063583150506, + "rewards/accuracy_reward": 0.639453125, + "rewards/format_reward": 0.953515625, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.551171875, + "step": 155 + }, + { + "completion_length": 306.36328125, + "epoch": 0.7597566404511055, + "grad_norm": 4.11327264014585, + "kl": 1.860302734375, + "learning_rate": 7.861276988374301e-07, + "loss": 0.0744, + "reward": 2.70234375, + "reward_std": 0.4653250968083739, + "rewards/accuracy_reward": 0.632421875, + "rewards/format_reward": 0.955078125, + "rewards/influence_reward": 0.55078125, + "rewards/len_reward": 0.5640625, + "step": 160 + }, + { + "completion_length": 299.812890625, + "epoch": 0.7834990354652025, + "grad_norm": 4.8236586704402855, + "kl": 2.14326171875, + "learning_rate": 7.688925030148148e-07, + "loss": 0.0857, + "reward": 2.673828125, + "reward_std": 0.44505598582327366, + "rewards/accuracy_reward": 0.621875, + "rewards/format_reward": 0.959765625, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.535546875, + "step": 165 + }, + { + "completion_length": 305.41484375, + "epoch": 0.8072414304792996, + "grad_norm": 1.849946965836104, + "kl": 2.1720703125, + "learning_rate": 7.51195481745018e-07, + "loss": 0.0869, + "reward": 2.708984375, + "reward_std": 0.43415932413190605, + "rewards/accuracy_reward": 0.62265625, + "rewards/format_reward": 0.958203125, + "rewards/influence_reward": 0.56171875, + "rewards/len_reward": 0.56640625, + "step": 170 + }, + { + "completion_length": 301.258203125, + "epoch": 0.8309838254933967, + "grad_norm": 2.440806378569226, + "kl": 1.9740234375, + "learning_rate": 7.330670298314281e-07, + "loss": 0.0789, + "reward": 2.70859375, + "reward_std": 0.46049848962575196, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.951953125, + "rewards/influence_reward": 0.538671875, + "rewards/len_reward": 0.590625, + "step": 175 + }, + { + "completion_length": 301.55, + "epoch": 0.8547262205074937, + "grad_norm": 5.1360667348261915, + "kl": 2.40302734375, + "learning_rate": 7.145382830636924e-07, + "loss": 0.0962, + "reward": 2.7078125, + "reward_std": 0.44812944661825893, + "rewards/accuracy_reward": 0.625390625, + "rewards/format_reward": 0.959375, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.56953125, + "step": 180 + }, + { + "completion_length": 296.28515625, + "epoch": 0.8784686155215907, + "grad_norm": 3.0756451628776627, + "kl": 2.0728515625, + "learning_rate": 6.956410647417016e-07, + "loss": 0.0829, + "reward": 2.679296875, + "reward_std": 0.44053732715547084, + "rewards/accuracy_reward": 0.624609375, + "rewards/format_reward": 0.95, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.551953125, + "step": 185 + }, + { + "completion_length": 290.825, + "epoch": 0.9022110105356878, + "grad_norm": 2.58004505898485, + "kl": 1.95107421875, + "learning_rate": 6.764078310187667e-07, + "loss": 0.078, + "reward": 2.743359375, + "reward_std": 0.45461403094232083, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.9625, + "rewards/influence_reward": 0.560546875, + "rewards/len_reward": 0.59296875, + "step": 190 + }, + { + "completion_length": 301.6453125, + "epoch": 0.9259534055497848, + "grad_norm": 3.359431223961218, + "kl": 1.895068359375, + "learning_rate": 6.568716151578653e-07, + "loss": 0.0758, + "reward": 2.6140625, + "reward_std": 0.45234644059091805, + "rewards/accuracy_reward": 0.591015625, + "rewards/format_reward": 0.95703125, + "rewards/influence_reward": 0.521875, + "rewards/len_reward": 0.544140625, + "step": 195 + }, + { + "completion_length": 300.809765625, + "epoch": 0.9496958005638819, + "grad_norm": 2.072678305669791, + "kl": 1.892919921875, + "learning_rate": 6.370659707966967e-07, + "loss": 0.0757, + "reward": 2.6984375, + "reward_std": 0.4385804546996951, + "rewards/accuracy_reward": 0.602734375, + "rewards/format_reward": 0.957421875, + "rewards/influence_reward": 0.5296875, + "rewards/len_reward": 0.60859375, + "step": 200 + }, + { + "completion_length": 295.50078125, + "epoch": 0.973438195577979, + "grad_norm": 2.641906292114807, + "kl": 1.882763671875, + "learning_rate": 6.170249143189878e-07, + "loss": 0.0753, + "reward": 2.726953125, + "reward_std": 0.45993594732135534, + "rewards/accuracy_reward": 0.61875, + "rewards/format_reward": 0.965625, + "rewards/influence_reward": 0.553515625, + "rewards/len_reward": 0.5890625, + "step": 205 + }, + { + "completion_length": 294.291796875, + "epoch": 0.997180590592076, + "grad_norm": 3.1118319118270263, + "kl": 1.721240234375, + "learning_rate": 5.967828664310282e-07, + "loss": 0.0689, + "reward": 2.689453125, + "reward_std": 0.4471969947218895, + "rewards/accuracy_reward": 0.618359375, + "rewards/format_reward": 0.96171875, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.552734375, + "step": 210 + }, + { + "completion_length": 298.9141156462585, + "epoch": 1.0189939160112775, + "grad_norm": 1.4510607380023717, + "kl": 1.6323341836734695, + "learning_rate": 5.763745930437786e-07, + "loss": 0.0657, + "reward": 2.7891156462585034, + "reward_std": 0.4109960768093057, + "rewards/accuracy_reward": 0.6547619047619048, + "rewards/format_reward": 0.9596088435374149, + "rewards/influence_reward": 0.5778061224489796, + "rewards/len_reward": 0.5969387755102041, + "step": 215 + }, + { + "completion_length": 292.062109375, + "epoch": 1.0427363110253747, + "grad_norm": 2.3079311627757115, + "kl": 1.639599609375, + "learning_rate": 5.558351455620851e-07, + "loss": 0.0656, + "reward": 2.71171875, + "reward_std": 0.40011929515749217, + "rewards/accuracy_reward": 0.61640625, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.537890625, + "rewards/len_reward": 0.587109375, + "step": 220 + }, + { + "completion_length": 297.239453125, + "epoch": 1.0664787060394718, + "grad_norm": 1.8840863111335822, + "kl": 2.28310546875, + "learning_rate": 5.351998006835562e-07, + "loss": 0.0914, + "reward": 2.684375, + "reward_std": 0.45486766248941424, + "rewards/accuracy_reward": 0.603515625, + "rewards/format_reward": 0.962890625, + "rewards/influence_reward": 0.537890625, + "rewards/len_reward": 0.580078125, + "step": 225 + }, + { + "completion_length": 288.18125, + "epoch": 1.0902211010535687, + "grad_norm": 2.0051543482646657, + "kl": 1.657861328125, + "learning_rate": 5.145039998104975e-07, + "loss": 0.0663, + "reward": 2.69765625, + "reward_std": 0.4361386923119426, + "rewards/accuracy_reward": 0.622265625, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.552734375, + "rewards/len_reward": 0.553515625, + "step": 230 + }, + { + "completion_length": 287.385546875, + "epoch": 1.1139634960676659, + "grad_norm": 1.4748593771929919, + "kl": 1.78935546875, + "learning_rate": 4.937832881789634e-07, + "loss": 0.0716, + "reward": 2.787109375, + "reward_std": 0.4470808956772089, + "rewards/accuracy_reward": 0.64296875, + "rewards/format_reward": 0.969921875, + "rewards/influence_reward": 0.569921875, + "rewards/len_reward": 0.604296875, + "step": 235 + }, + { + "completion_length": 288.096484375, + "epoch": 1.1377058910817628, + "grad_norm": 10.954523562177771, + "kl": 1.878369140625, + "learning_rate": 4.730732538094749e-07, + "loss": 0.0751, + "reward": 2.716796875, + "reward_std": 0.4533087441697717, + "rewards/accuracy_reward": 0.608203125, + "rewards/format_reward": 0.96484375, + "rewards/influence_reward": 0.543359375, + "rewards/len_reward": 0.600390625, + "step": 240 + }, + { + "completion_length": 286.948828125, + "epoch": 1.16144828609586, + "grad_norm": 3.7350800690768913, + "kl": 1.802978515625, + "learning_rate": 4.524094663842527e-07, + "loss": 0.0721, + "reward": 2.716015625, + "reward_std": 0.46027831770479677, + "rewards/accuracy_reward": 0.605078125, + "rewards/format_reward": 0.96640625, + "rewards/influence_reward": 0.529296875, + "rewards/len_reward": 0.615234375, + "step": 245 + }, + { + "completion_length": 298.440234375, + "epoch": 1.1851906811099568, + "grad_norm": 1.7998199572787943, + "kl": 1.9130859375, + "learning_rate": 4.3182741615594863e-07, + "loss": 0.0765, + "reward": 2.73046875, + "reward_std": 0.4339360993355513, + "rewards/accuracy_reward": 0.629296875, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.55546875, + "rewards/len_reward": 0.576953125, + "step": 250 + }, + { + "completion_length": 297.07421875, + "epoch": 1.208933076124054, + "grad_norm": 2.1433576353118755, + "kl": 2.023828125, + "learning_rate": 4.1136245299279625e-07, + "loss": 0.081, + "reward": 2.69375, + "reward_std": 0.4361835679039359, + "rewards/accuracy_reward": 0.6046875, + "rewards/format_reward": 0.962109375, + "rewards/influence_reward": 0.5265625, + "rewards/len_reward": 0.600390625, + "step": 255 + }, + { + "completion_length": 283.55859375, + "epoch": 1.2326754711381511, + "grad_norm": 3.56858833503255, + "kl": 1.9943359375, + "learning_rate": 3.910497256648742e-07, + "loss": 0.0798, + "reward": 2.776171875, + "reward_std": 0.41840124800801276, + "rewards/accuracy_reward": 0.62421875, + "rewards/format_reward": 0.975, + "rewards/influence_reward": 0.55703125, + "rewards/len_reward": 0.619921875, + "step": 260 + }, + { + "completion_length": 285.401953125, + "epoch": 1.256417866152248, + "grad_norm": 3.0202540131791316, + "kl": 1.812353515625, + "learning_rate": 3.7092412147575756e-07, + "loss": 0.0725, + "reward": 2.667578125, + "reward_std": 0.4479133376851678, + "rewards/accuracy_reward": 0.5859375, + "rewards/format_reward": 0.97109375, + "rewards/influence_reward": 0.51328125, + "rewards/len_reward": 0.597265625, + "step": 265 + }, + { + "completion_length": 296.51953125, + "epoch": 1.2801602611663452, + "grad_norm": 6.685851651155463, + "kl": 1.824169921875, + "learning_rate": 3.510202063432397e-07, + "loss": 0.073, + "reward": 2.68125, + "reward_std": 0.45598011631518603, + "rewards/accuracy_reward": 0.59453125, + "rewards/format_reward": 0.97109375, + "rewards/influence_reward": 0.526171875, + "rewards/len_reward": 0.589453125, + "step": 270 + }, + { + "completion_length": 297.57734375, + "epoch": 1.3039026561804423, + "grad_norm": 2.291528264931079, + "kl": 1.847607421875, + "learning_rate": 3.3137216543203747e-07, + "loss": 0.0739, + "reward": 2.69765625, + "reward_std": 0.41086965166032313, + "rewards/accuracy_reward": 0.59140625, + "rewards/format_reward": 0.9765625, + "rewards/influence_reward": 0.53046875, + "rewards/len_reward": 0.59921875, + "step": 275 + }, + { + "completion_length": 290.746875, + "epoch": 1.3276450511945392, + "grad_norm": 1.8784141288314866, + "kl": 1.92822265625, + "learning_rate": 3.1201374444044414e-07, + "loss": 0.0771, + "reward": 2.68671875, + "reward_std": 0.43726298715919254, + "rewards/accuracy_reward": 0.606640625, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.5296875, + "rewards/len_reward": 0.581640625, + "step": 280 + }, + { + "completion_length": 285.90390625, + "epoch": 1.3513874462086364, + "grad_norm": 3.8666864047404657, + "kl": 2.049609375, + "learning_rate": 2.929781916417696e-07, + "loss": 0.082, + "reward": 2.79140625, + "reward_std": 0.4504884161055088, + "rewards/accuracy_reward": 0.635546875, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.56875, + "rewards/len_reward": 0.611328125, + "step": 285 + }, + { + "completion_length": 278.126171875, + "epoch": 1.3751298412227333, + "grad_norm": 2.7940015666308584, + "kl": 1.9935546875, + "learning_rate": 2.742982007801121e-07, + "loss": 0.0797, + "reward": 2.714453125, + "reward_std": 0.40985080897808074, + "rewards/accuracy_reward": 0.605859375, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.553125, + "rewards/len_reward": 0.5796875, + "step": 290 + }, + { + "completion_length": 282.807421875, + "epoch": 1.3988722362368304, + "grad_norm": 2.1190543029510374, + "kl": 2.0150390625, + "learning_rate": 2.5600585491854113e-07, + "loss": 0.0806, + "reward": 2.736328125, + "reward_std": 0.4611986864358187, + "rewards/accuracy_reward": 0.625, + "rewards/format_reward": 0.966015625, + "rewards/influence_reward": 0.5453125, + "rewards/len_reward": 0.6, + "step": 295 + }, + { + "completion_length": 285.337890625, + "epoch": 1.4226146312509274, + "grad_norm": 2.0524239671070235, + "kl": 2.023779296875, + "learning_rate": 2.3813257133612823e-07, + "loss": 0.081, + "reward": 2.7375, + "reward_std": 0.4188694503158331, + "rewards/accuracy_reward": 0.615625, + "rewards/format_reward": 0.96796875, + "rewards/influence_reward": 0.546484375, + "rewards/len_reward": 0.607421875, + "step": 300 + }, + { + "completion_length": 280.583203125, + "epoch": 1.4463570262650245, + "grad_norm": 2.4639075460957103, + "kl": 1.916455078125, + "learning_rate": 2.207090475684702e-07, + "loss": 0.0766, + "reward": 2.778515625, + "reward_std": 0.4049776840955019, + "rewards/accuracy_reward": 0.621484375, + "rewards/format_reward": 0.978125, + "rewards/influence_reward": 0.55703125, + "rewards/len_reward": 0.621875, + "step": 305 + }, + { + "completion_length": 279.21640625, + "epoch": 1.4700994212791216, + "grad_norm": 1.9580691543159996, + "kl": 1.886328125, + "learning_rate": 2.0376520868437836e-07, + "loss": 0.0754, + "reward": 2.69140625, + "reward_std": 0.4295359971001744, + "rewards/accuracy_reward": 0.584765625, + "rewards/format_reward": 0.9734375, + "rewards/influence_reward": 0.512109375, + "rewards/len_reward": 0.62109375, + "step": 310 + }, + { + "completion_length": 287.18671875, + "epoch": 1.4938418162932185, + "grad_norm": 2.334280950294775, + "kl": 1.902001953125, + "learning_rate": 1.8733015588928547e-07, + "loss": 0.0761, + "reward": 2.748046875, + "reward_std": 0.4672464972361922, + "rewards/accuracy_reward": 0.620703125, + "rewards/format_reward": 0.979296875, + "rewards/influence_reward": 0.544140625, + "rewards/len_reward": 0.60390625, + "step": 315 + }, + { + "completion_length": 279.612109375, + "epoch": 1.5175842113073155, + "grad_norm": 2.383804496413666, + "kl": 1.881494140625, + "learning_rate": 1.7143211654364758e-07, + "loss": 0.0753, + "reward": 2.704296875, + "reward_std": 0.46042243372648956, + "rewards/accuracy_reward": 0.609375, + "rewards/format_reward": 0.97578125, + "rewards/influence_reward": 0.540234375, + "rewards/len_reward": 0.57890625, + "step": 320 + }, + { + "completion_length": 276.201171875, + "epoch": 1.5413266063214128, + "grad_norm": 1.8621036607786687, + "kl": 2.042041015625, + "learning_rate": 1.5609839568218247e-07, + "loss": 0.0817, + "reward": 2.78984375, + "reward_std": 0.4288489479571581, + "rewards/accuracy_reward": 0.640625, + "rewards/format_reward": 0.97890625, + "rewards/influence_reward": 0.5796875, + "rewards/len_reward": 0.590625, + "step": 325 + }, + { + "completion_length": 285.061328125, + "epoch": 1.5650690013355097, + "grad_norm": 2.541259800858008, + "kl": 2.11279296875, + "learning_rate": 1.413553291172106e-07, + "loss": 0.0845, + "reward": 2.744140625, + "reward_std": 0.43316187243908644, + "rewards/accuracy_reward": 0.624609375, + "rewards/format_reward": 0.961328125, + "rewards/influence_reward": 0.56328125, + "rewards/len_reward": 0.594921875, + "step": 330 + }, + { + "completion_length": 286.321875, + "epoch": 1.5888113963496067, + "grad_norm": 2.4383264225155825, + "kl": 2.04287109375, + "learning_rate": 1.2722823820664575e-07, + "loss": 0.0817, + "reward": 2.7609375, + "reward_std": 0.42981729917228223, + "rewards/accuracy_reward": 0.623828125, + "rewards/format_reward": 0.973046875, + "rewards/influence_reward": 0.549609375, + "rewards/len_reward": 0.614453125, + "step": 335 + }, + { + "completion_length": 281.6328125, + "epoch": 1.6125537913637038, + "grad_norm": 2.1689228150160225, + "kl": 2.00263671875, + "learning_rate": 1.1374138636432051e-07, + "loss": 0.0801, + "reward": 2.738671875, + "reward_std": 0.4134707026183605, + "rewards/accuracy_reward": 0.61015625, + "rewards/format_reward": 0.97421875, + "rewards/influence_reward": 0.54609375, + "rewards/len_reward": 0.608203125, + "step": 340 + }, + { + "completion_length": 292.502734375, + "epoch": 1.636296186377801, + "grad_norm": 4.449673329252311, + "kl": 1.98564453125, + "learning_rate": 1.0091793738734111e-07, + "loss": 0.0794, + "reward": 2.7078125, + "reward_std": 0.4420934099704027, + "rewards/accuracy_reward": 0.5953125, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.52890625, + "rewards/len_reward": 0.61328125, + "step": 345 + }, + { + "completion_length": 284.086328125, + "epoch": 1.6600385813918979, + "grad_norm": 2.2530249348579403, + "kl": 1.920751953125, + "learning_rate": 8.877991567204351e-08, + "loss": 0.0768, + "reward": 2.77578125, + "reward_std": 0.40416364911943675, + "rewards/accuracy_reward": 0.6421875, + "rewards/format_reward": 0.97265625, + "rewards/influence_reward": 0.559765625, + "rewards/len_reward": 0.601171875, + "step": 350 + }, + { + "completion_length": 286.23359375, + "epoch": 1.683780976405995, + "grad_norm": 11.607212223835898, + "kl": 1.99482421875, + "learning_rate": 7.734816838688246e-08, + "loss": 0.0798, + "reward": 2.7375, + "reward_std": 0.42118714693933723, + "rewards/accuracy_reward": 0.609375, + "rewards/format_reward": 0.972265625, + "rewards/influence_reward": 0.54375, + "rewards/len_reward": 0.612109375, + "step": 355 + }, + { + "completion_length": 288.31875, + "epoch": 1.7075233714200921, + "grad_norm": 2.560035528567494, + "kl": 1.884912109375, + "learning_rate": 6.664232966721995e-08, + "loss": 0.0754, + "reward": 2.655078125, + "reward_std": 0.44481576029211284, + "rewards/accuracy_reward": 0.591796875, + "rewards/format_reward": 0.9671875, + "rewards/influence_reward": 0.51796875, + "rewards/len_reward": 0.578125, + "step": 360 + }, + { + "completion_length": 292.05546875, + "epoch": 1.731265766434189, + "grad_norm": 2.703658020341151, + "kl": 1.88125, + "learning_rate": 5.668078689351008e-08, + "loss": 0.0753, + "reward": 2.731640625, + "reward_std": 0.4349971186369658, + "rewards/accuracy_reward": 0.603515625, + "rewards/format_reward": 0.97265625, + "rewards/influence_reward": 0.535546875, + "rewards/len_reward": 0.619921875, + "step": 365 + }, + { + "completion_length": 289.07265625, + "epoch": 1.755008161448286, + "grad_norm": 2.15796183633457, + "kl": 1.920556640625, + "learning_rate": 4.748064911079669e-08, + "loss": 0.0768, + "reward": 2.773046875, + "reward_std": 0.45684912260621785, + "rewards/accuracy_reward": 0.634375, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.569140625, + "rewards/len_reward": 0.60078125, + "step": 370 + }, + { + "completion_length": 297.7921875, + "epoch": 1.7787505564623831, + "grad_norm": 1.9525269307848967, + "kl": 1.950634765625, + "learning_rate": 3.905771764376553e-08, + "loss": 0.078, + "reward": 2.762890625, + "reward_std": 0.43305158857256176, + "rewards/accuracy_reward": 0.616796875, + "rewards/format_reward": 0.970703125, + "rewards/influence_reward": 0.544921875, + "rewards/len_reward": 0.63046875, + "step": 375 + }, + { + "completion_length": 286.23125, + "epoch": 1.8024929514764803, + "grad_norm": 1.8795557235019384, + "kl": 1.94345703125, + "learning_rate": 3.142645895781715e-08, + "loss": 0.0777, + "reward": 2.705859375, + "reward_std": 0.4185318287461996, + "rewards/accuracy_reward": 0.6078125, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.53125, + "rewards/len_reward": 0.59765625, + "step": 380 + }, + { + "completion_length": 284.5234375, + "epoch": 1.8262353464905772, + "grad_norm": 1.8303802044437847, + "kl": 1.9130859375, + "learning_rate": 2.459997981277423e-08, + "loss": 0.0765, + "reward": 2.743359375, + "reward_std": 0.42376566473394633, + "rewards/accuracy_reward": 0.6296875, + "rewards/format_reward": 0.973828125, + "rewards/influence_reward": 0.556640625, + "rewards/len_reward": 0.583203125, + "step": 385 + }, + { + "completion_length": 287.645703125, + "epoch": 1.8499777415046743, + "grad_norm": 2.1486695226548314, + "kl": 1.919140625, + "learning_rate": 1.859000475189687e-08, + "loss": 0.0767, + "reward": 2.70625, + "reward_std": 0.43876812513917685, + "rewards/accuracy_reward": 0.62109375, + "rewards/format_reward": 0.965625, + "rewards/influence_reward": 0.5328125, + "rewards/len_reward": 0.58671875, + "step": 390 + }, + { + "completion_length": 289.16953125, + "epoch": 1.8737201365187715, + "grad_norm": 2.3275579827754704, + "kl": 1.96728515625, + "learning_rate": 1.3406855964866404e-08, + "loss": 0.0787, + "reward": 2.69453125, + "reward_std": 0.44194721039384605, + "rewards/accuracy_reward": 0.603125, + "rewards/format_reward": 0.971875, + "rewards/influence_reward": 0.533984375, + "rewards/len_reward": 0.585546875, + "step": 395 + }, + { + "completion_length": 285.14296875, + "epoch": 1.8974625315328684, + "grad_norm": 2.1178151388074538, + "kl": 1.926513671875, + "learning_rate": 9.059435559326256e-09, + "loss": 0.077, + "reward": 2.69609375, + "reward_std": 0.4095570512115955, + "rewards/accuracy_reward": 0.604296875, + "rewards/format_reward": 0.9703125, + "rewards/influence_reward": 0.529296875, + "rewards/len_reward": 0.5921875, + "step": 400 + }, + { + "completion_length": 291.73046875, + "epoch": 1.9212049265469653, + "grad_norm": 3.0382797909309063, + "kl": 1.9125, + "learning_rate": 5.555210271427191e-09, + "loss": 0.0765, + "reward": 2.74375, + "reward_std": 0.45224274341017007, + "rewards/accuracy_reward": 0.627734375, + "rewards/format_reward": 0.968359375, + "rewards/influence_reward": 0.544140625, + "rewards/len_reward": 0.603515625, + "step": 405 + }, + { + "completion_length": 285.82109375, + "epoch": 1.9449473215610624, + "grad_norm": 2.223879198885574, + "kl": 1.93515625, + "learning_rate": 2.900198641635876e-09, + "loss": 0.0774, + "reward": 2.766015625, + "reward_std": 0.4194388585165143, + "rewards/accuracy_reward": 0.62734375, + "rewards/format_reward": 0.973046875, + "rewards/influence_reward": 0.558203125, + "rewards/len_reward": 0.607421875, + "step": 410 + }, + { + "completion_length": 284.583203125, + "epoch": 1.9686897165751596, + "grad_norm": 2.3711705196769834, + "kl": 1.942138671875, + "learning_rate": 1.0989606778344373e-09, + "loss": 0.0777, + "reward": 2.782421875, + "reward_std": 0.42840481735765934, + "rewards/accuracy_reward": 0.637109375, + "rewards/format_reward": 0.969140625, + "rewards/influence_reward": 0.568359375, + "rewards/len_reward": 0.6078125, + "step": 415 + }, + { + "completion_length": 297.46796875, + "epoch": 1.9924321115892565, + "grad_norm": 18.12331360764631, + "kl": 1.966943359375, + "learning_rate": 1.5459002346324136e-10, + "loss": 0.0787, + "reward": 2.726171875, + "reward_std": 0.4440956773236394, + "rewards/accuracy_reward": 0.6171875, + "rewards/format_reward": 0.96875, + "rewards/influence_reward": 0.5265625, + "rewards/len_reward": 0.613671875, + "step": 420 + }, + { + "completion_length": 282.22058823529414, + "epoch": 2.0, + "kl": 1.9358149509803921, + "reward": 2.8063725490196076, + "reward_std": 0.42265554269154865, + "rewards/accuracy_reward": 0.6323529411764706, + "rewards/format_reward": 0.9816176470588235, + "rewards/influence_reward": 0.5637254901960784, + "rewards/len_reward": 0.6286764705882353, + "step": 422, + "total_flos": 0.0, + "train_loss": 0.07021697652106884, + "train_runtime": 419033.0805, + "train_samples_per_second": 0.129, + "train_steps_per_second": 0.001 + } + ], + "logging_steps": 5, + "max_steps": 422, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 10, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "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..a00094f --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9febc05b21a9697f39aca7d2e016e5591fdde9dc93d33319026f426081ab2f5a +size 7288