commit 0a3cd7b7bca25ed37bd0b0a76e58ce9c8e051e82 Author: ModelHub XC Date: Fri Apr 10 15:44:08 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.06 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a09fe2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: meta-llama/Llama-3.1-8B-Instruct +datasets: Neelectric/OpenR1-Math-220k_all_SDFT_nr +library_name: transformers +model_name: Llama-3.1-8B-Instruct_SDFT_mathv00.06 +tags: +- generated_from_trainer +- open-r1 +- trl +- sdft +licence: license +--- + +# Model Card for Llama-3.1-8B-Instruct_SDFT_mathv00.06 + +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) on the [Neelectric/OpenR1-Math-220k_all_SDFT_nr](https://huggingface.co/datasets/Neelectric/OpenR1-Math-220k_all_SDFT_nr) dataset. +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="Neelectric/Llama-3.1-8B-Instruct_SDFT_mathv00.06", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + +[Visualize in Weights & Biases](https://wandb.ai/neelectric/open-r1_math/runs/i58cg3rj) + + + +This model was trained with SDFT, a method introduced in [Self-Training with On-Policy Self-Distillation for Language Model Alignment](https://huggingface.co/papers/2601.19897). + +### Framework versions + +- TRL: 1.1.0.dev0 +- Transformers: 4.57.6 +- Pytorch: 2.9.0 +- Datasets: 4.8.4 +- Tokenizers: 0.22.2 + +## Citations + +Cite SDFT as: + +```bibtex +@article{hubotter2026selftraining, + title = {{Self-Training with On-Policy Self-Distillation for Language Model Alignment}}, + author = {Jonas H\"ubotter and Frederike L\"ubeck and Lejs Behric and Anton Baumann and Marco Bagatella and Daniel Marta and Ido Hakimi and Idan Shenfeld and Thomas Kleine Buening and Carlos Guestrin and Andreas Krause}, + year = 2026, + eprint = {arXiv:2601.19897} +} +``` + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..77ebd61 --- /dev/null +++ b/all_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 3.0, + "total_flos": 0.0, + "train_loss": 0.07083441573637131, + "train_runtime": 38065.4229, + "train_samples": 225129, + "train_samples_per_second": 17.743, + "train_steps_per_second": 0.035 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..0ab931a --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,121 @@ +{{- 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 = "You are a helpful AI Assistant that provides well-reasoned and detailed responses. You first think about the reasoning process as an internal monologue and then provide the user with the answer. Respond in the following format: +... + + +... +" %} +{%- 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) %} + {%- if message['role'] == 'assistant' %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} + {% generation %} + {{- message['content'] | trim + '<|eot_id|>' }} + {% endgeneration %} + {%- else %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- endif %} + {%- 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 %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {% generation %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- "<|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 %} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {% endgeneration %} + {%- 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 %} \ No newline at end of file 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..50f6077 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128009, + "pad_token_id": 128009, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.6" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..3a809c5 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2774eacdb00111527f344b46f2e3ff9982cf377d7134700b308d0dad44026e +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..76b0c1b --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9f5740344c66c8dcb44e4a5182a0a57ccb045a52bc26d2005fb16b8e7271d5 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..c55241a --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10aa85ff6ab49f8b8643d0356538e0efa575c5b5e64450bc236cc3a645bf40c4 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..9261df8 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b786a90f5e782e9f713ab0d386fba69bc65e7be66541cca4ed682011b29aaaaa +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5c64f1e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 8030261248, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..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..356db7b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce9b61086126b8dd5c77f984b948929028bb0f4429feed6eb1ddcb791362b38 +size 17210183 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..77ebd61 --- /dev/null +++ b/train_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 3.0, + "total_flos": 0.0, + "train_loss": 0.07083441573637131, + "train_runtime": 38065.4229, + "train_samples": 225129, + "train_samples_per_second": 17.743, + "train_steps_per_second": 0.035 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..801b2bc --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,9262 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1317, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.002277904328018223, + "grad_norm": 3.693197250366211, + "learning_rate": 0.0, + "loss": 0.1525, + "step": 1 + }, + { + "epoch": 0.004555808656036446, + "grad_norm": 3.6627023220062256, + "learning_rate": 7.575757575757576e-09, + "loss": 0.158, + "step": 2 + }, + { + "epoch": 0.00683371298405467, + "grad_norm": 3.707599639892578, + "learning_rate": 1.5151515151515152e-08, + "loss": 0.1585, + "step": 3 + }, + { + "epoch": 0.009111617312072893, + "grad_norm": 3.752378463745117, + "learning_rate": 2.2727272727272725e-08, + "loss": 0.1573, + "step": 4 + }, + { + "epoch": 0.011389521640091117, + "grad_norm": 3.5427136421203613, + "learning_rate": 3.0303030303030305e-08, + "loss": 0.1568, + "step": 5 + }, + { + "epoch": 0.01366742596810934, + "grad_norm": 3.8243350982666016, + "learning_rate": 3.787878787878788e-08, + "loss": 0.1627, + "step": 6 + }, + { + "epoch": 0.015945330296127564, + "grad_norm": 3.695244312286377, + "learning_rate": 4.545454545454545e-08, + "loss": 0.1573, + "step": 7 + }, + { + "epoch": 0.018223234624145785, + "grad_norm": 3.882723331451416, + "learning_rate": 5.303030303030303e-08, + "loss": 0.1546, + "step": 8 + }, + { + "epoch": 0.02050113895216401, + "grad_norm": 3.683401584625244, + "learning_rate": 6.060606060606061e-08, + "loss": 0.1569, + "step": 9 + }, + { + "epoch": 0.022779043280182234, + "grad_norm": 3.588951826095581, + "learning_rate": 6.818181818181817e-08, + "loss": 0.1583, + "step": 10 + }, + { + "epoch": 0.025056947608200455, + "grad_norm": 3.6290993690490723, + "learning_rate": 7.575757575757576e-08, + "loss": 0.1546, + "step": 11 + }, + { + "epoch": 0.02733485193621868, + "grad_norm": 3.4766926765441895, + "learning_rate": 8.333333333333333e-08, + "loss": 0.159, + "step": 12 + }, + { + "epoch": 0.029612756264236904, + "grad_norm": 3.5064921379089355, + "learning_rate": 9.09090909090909e-08, + "loss": 0.1558, + "step": 13 + }, + { + "epoch": 0.03189066059225513, + "grad_norm": 3.8152694702148438, + "learning_rate": 9.848484848484848e-08, + "loss": 0.1588, + "step": 14 + }, + { + "epoch": 0.03416856492027335, + "grad_norm": 3.3115503787994385, + "learning_rate": 1.0606060606060605e-07, + "loss": 0.1499, + "step": 15 + }, + { + "epoch": 0.03644646924829157, + "grad_norm": 3.404592275619507, + "learning_rate": 1.1363636363636363e-07, + "loss": 0.155, + "step": 16 + }, + { + "epoch": 0.0387243735763098, + "grad_norm": 3.8576135635375977, + "learning_rate": 1.2121212121212122e-07, + "loss": 0.1586, + "step": 17 + }, + { + "epoch": 0.04100227790432802, + "grad_norm": 3.6521520614624023, + "learning_rate": 1.2878787878787877e-07, + "loss": 0.1631, + "step": 18 + }, + { + "epoch": 0.04328018223234624, + "grad_norm": 3.5314364433288574, + "learning_rate": 1.3636363636363635e-07, + "loss": 0.1525, + "step": 19 + }, + { + "epoch": 0.04555808656036447, + "grad_norm": 3.4354398250579834, + "learning_rate": 1.4393939393939395e-07, + "loss": 0.1521, + "step": 20 + }, + { + "epoch": 0.04783599088838269, + "grad_norm": 3.7880332469940186, + "learning_rate": 1.5151515151515152e-07, + "loss": 0.1565, + "step": 21 + }, + { + "epoch": 0.05011389521640091, + "grad_norm": 3.274695873260498, + "learning_rate": 1.5909090909090907e-07, + "loss": 0.1516, + "step": 22 + }, + { + "epoch": 0.05239179954441914, + "grad_norm": 3.331993579864502, + "learning_rate": 1.6666666666666665e-07, + "loss": 0.1509, + "step": 23 + }, + { + "epoch": 0.05466970387243736, + "grad_norm": 3.499872922897339, + "learning_rate": 1.7424242424242425e-07, + "loss": 0.154, + "step": 24 + }, + { + "epoch": 0.05694760820045558, + "grad_norm": 3.3702392578125, + "learning_rate": 1.818181818181818e-07, + "loss": 0.1469, + "step": 25 + }, + { + "epoch": 0.05922551252847381, + "grad_norm": 3.099013566970825, + "learning_rate": 1.8939393939393938e-07, + "loss": 0.1482, + "step": 26 + }, + { + "epoch": 0.06150341685649203, + "grad_norm": 3.0089797973632812, + "learning_rate": 1.9696969696969696e-07, + "loss": 0.1464, + "step": 27 + }, + { + "epoch": 0.06378132118451026, + "grad_norm": 2.8868448734283447, + "learning_rate": 2.0454545454545456e-07, + "loss": 0.1469, + "step": 28 + }, + { + "epoch": 0.06605922551252848, + "grad_norm": 2.715088367462158, + "learning_rate": 2.121212121212121e-07, + "loss": 0.1415, + "step": 29 + }, + { + "epoch": 0.0683371298405467, + "grad_norm": 2.7959978580474854, + "learning_rate": 2.1969696969696968e-07, + "loss": 0.146, + "step": 30 + }, + { + "epoch": 0.07061503416856492, + "grad_norm": 2.9696195125579834, + "learning_rate": 2.2727272727272726e-07, + "loss": 0.1448, + "step": 31 + }, + { + "epoch": 0.07289293849658314, + "grad_norm": 2.8655238151550293, + "learning_rate": 2.3484848484848486e-07, + "loss": 0.1498, + "step": 32 + }, + { + "epoch": 0.07517084282460136, + "grad_norm": 2.750391721725464, + "learning_rate": 2.4242424242424244e-07, + "loss": 0.1457, + "step": 33 + }, + { + "epoch": 0.0774487471526196, + "grad_norm": 2.0881235599517822, + "learning_rate": 2.5e-07, + "loss": 0.1329, + "step": 34 + }, + { + "epoch": 0.07972665148063782, + "grad_norm": 1.7994139194488525, + "learning_rate": 2.5757575757575754e-07, + "loss": 0.1358, + "step": 35 + }, + { + "epoch": 0.08200455580865604, + "grad_norm": 1.597785234451294, + "learning_rate": 2.6515151515151514e-07, + "loss": 0.1331, + "step": 36 + }, + { + "epoch": 0.08428246013667426, + "grad_norm": 1.5115468502044678, + "learning_rate": 2.727272727272727e-07, + "loss": 0.1286, + "step": 37 + }, + { + "epoch": 0.08656036446469248, + "grad_norm": 1.3598073720932007, + "learning_rate": 2.8030303030303024e-07, + "loss": 0.1268, + "step": 38 + }, + { + "epoch": 0.0888382687927107, + "grad_norm": 1.4490768909454346, + "learning_rate": 2.878787878787879e-07, + "loss": 0.126, + "step": 39 + }, + { + "epoch": 0.09111617312072894, + "grad_norm": 1.3516889810562134, + "learning_rate": 2.9545454545454545e-07, + "loss": 0.129, + "step": 40 + }, + { + "epoch": 0.09339407744874716, + "grad_norm": 1.3587911128997803, + "learning_rate": 3.0303030303030305e-07, + "loss": 0.1287, + "step": 41 + }, + { + "epoch": 0.09567198177676538, + "grad_norm": 1.3211842775344849, + "learning_rate": 3.106060606060606e-07, + "loss": 0.1295, + "step": 42 + }, + { + "epoch": 0.0979498861047836, + "grad_norm": 1.1991353034973145, + "learning_rate": 3.1818181818181815e-07, + "loss": 0.1248, + "step": 43 + }, + { + "epoch": 0.10022779043280182, + "grad_norm": 1.2104594707489014, + "learning_rate": 3.2575757575757575e-07, + "loss": 0.1246, + "step": 44 + }, + { + "epoch": 0.10250569476082004, + "grad_norm": 1.2491683959960938, + "learning_rate": 3.333333333333333e-07, + "loss": 0.1244, + "step": 45 + }, + { + "epoch": 0.10478359908883828, + "grad_norm": 1.1087615489959717, + "learning_rate": 3.4090909090909085e-07, + "loss": 0.1263, + "step": 46 + }, + { + "epoch": 0.1070615034168565, + "grad_norm": 0.9333842992782593, + "learning_rate": 3.484848484848485e-07, + "loss": 0.1173, + "step": 47 + }, + { + "epoch": 0.10933940774487472, + "grad_norm": 0.9401147365570068, + "learning_rate": 3.5606060606060606e-07, + "loss": 0.1165, + "step": 48 + }, + { + "epoch": 0.11161731207289294, + "grad_norm": 1.0419429540634155, + "learning_rate": 3.636363636363636e-07, + "loss": 0.1105, + "step": 49 + }, + { + "epoch": 0.11389521640091116, + "grad_norm": 1.0624477863311768, + "learning_rate": 3.712121212121212e-07, + "loss": 0.1111, + "step": 50 + }, + { + "epoch": 0.11617312072892938, + "grad_norm": 0.9938150644302368, + "learning_rate": 3.7878787878787876e-07, + "loss": 0.1105, + "step": 51 + }, + { + "epoch": 0.11845102505694761, + "grad_norm": 0.9886028170585632, + "learning_rate": 3.8636363636363636e-07, + "loss": 0.1115, + "step": 52 + }, + { + "epoch": 0.12072892938496584, + "grad_norm": 0.9165894389152527, + "learning_rate": 3.939393939393939e-07, + "loss": 0.1046, + "step": 53 + }, + { + "epoch": 0.12300683371298406, + "grad_norm": 0.8841789364814758, + "learning_rate": 4.0151515151515146e-07, + "loss": 0.1065, + "step": 54 + }, + { + "epoch": 0.1252847380410023, + "grad_norm": 0.8651257753372192, + "learning_rate": 4.090909090909091e-07, + "loss": 0.1081, + "step": 55 + }, + { + "epoch": 0.1275626423690205, + "grad_norm": 0.7827234268188477, + "learning_rate": 4.1666666666666667e-07, + "loss": 0.1048, + "step": 56 + }, + { + "epoch": 0.12984054669703873, + "grad_norm": 0.7238534092903137, + "learning_rate": 4.242424242424242e-07, + "loss": 0.1073, + "step": 57 + }, + { + "epoch": 0.13211845102505695, + "grad_norm": 0.6830411553382874, + "learning_rate": 4.318181818181818e-07, + "loss": 0.1056, + "step": 58 + }, + { + "epoch": 0.13439635535307518, + "grad_norm": 0.672331690788269, + "learning_rate": 4.3939393939393937e-07, + "loss": 0.1082, + "step": 59 + }, + { + "epoch": 0.1366742596810934, + "grad_norm": 0.658761739730835, + "learning_rate": 4.469696969696969e-07, + "loss": 0.108, + "step": 60 + }, + { + "epoch": 0.13895216400911162, + "grad_norm": 0.6729574203491211, + "learning_rate": 4.545454545454545e-07, + "loss": 0.1047, + "step": 61 + }, + { + "epoch": 0.14123006833712984, + "grad_norm": 0.6613078713417053, + "learning_rate": 4.6212121212121207e-07, + "loss": 0.1069, + "step": 62 + }, + { + "epoch": 0.14350797266514806, + "grad_norm": 0.7041091322898865, + "learning_rate": 4.696969696969697e-07, + "loss": 0.0996, + "step": 63 + }, + { + "epoch": 0.14578587699316628, + "grad_norm": 0.6291015148162842, + "learning_rate": 4.772727272727273e-07, + "loss": 0.0986, + "step": 64 + }, + { + "epoch": 0.1480637813211845, + "grad_norm": 0.5931835174560547, + "learning_rate": 4.848484848484849e-07, + "loss": 0.0999, + "step": 65 + }, + { + "epoch": 0.15034168564920272, + "grad_norm": 0.6072292327880859, + "learning_rate": 4.924242424242424e-07, + "loss": 0.0994, + "step": 66 + }, + { + "epoch": 0.15261958997722094, + "grad_norm": 0.5499963164329529, + "learning_rate": 5e-07, + "loss": 0.0966, + "step": 67 + }, + { + "epoch": 0.1548974943052392, + "grad_norm": 0.5744556188583374, + "learning_rate": 5.075757575757576e-07, + "loss": 0.0978, + "step": 68 + }, + { + "epoch": 0.1571753986332574, + "grad_norm": 0.5759721994400024, + "learning_rate": 5.151515151515151e-07, + "loss": 0.0986, + "step": 69 + }, + { + "epoch": 0.15945330296127563, + "grad_norm": 0.573357880115509, + "learning_rate": 5.227272727272727e-07, + "loss": 0.0965, + "step": 70 + }, + { + "epoch": 0.16173120728929385, + "grad_norm": 0.4898295998573303, + "learning_rate": 5.303030303030303e-07, + "loss": 0.0937, + "step": 71 + }, + { + "epoch": 0.16400911161731208, + "grad_norm": 0.5179144740104675, + "learning_rate": 5.378787878787878e-07, + "loss": 0.0931, + "step": 72 + }, + { + "epoch": 0.1662870159453303, + "grad_norm": 0.494838684797287, + "learning_rate": 5.454545454545454e-07, + "loss": 0.0931, + "step": 73 + }, + { + "epoch": 0.16856492027334852, + "grad_norm": 0.44552069902420044, + "learning_rate": 5.53030303030303e-07, + "loss": 0.0922, + "step": 74 + }, + { + "epoch": 0.17084282460136674, + "grad_norm": 0.5690138339996338, + "learning_rate": 5.606060606060605e-07, + "loss": 0.0951, + "step": 75 + }, + { + "epoch": 0.17312072892938496, + "grad_norm": 0.473254919052124, + "learning_rate": 5.681818181818182e-07, + "loss": 0.0918, + "step": 76 + }, + { + "epoch": 0.17539863325740318, + "grad_norm": 0.6595781445503235, + "learning_rate": 5.757575757575758e-07, + "loss": 0.0902, + "step": 77 + }, + { + "epoch": 0.1776765375854214, + "grad_norm": 0.43429794907569885, + "learning_rate": 5.833333333333334e-07, + "loss": 0.0884, + "step": 78 + }, + { + "epoch": 0.17995444191343962, + "grad_norm": 0.4575148820877075, + "learning_rate": 5.909090909090909e-07, + "loss": 0.0911, + "step": 79 + }, + { + "epoch": 0.18223234624145787, + "grad_norm": 0.5175042152404785, + "learning_rate": 5.984848484848485e-07, + "loss": 0.0934, + "step": 80 + }, + { + "epoch": 0.1845102505694761, + "grad_norm": 0.5621854662895203, + "learning_rate": 6.060606060606061e-07, + "loss": 0.0919, + "step": 81 + }, + { + "epoch": 0.1867881548974943, + "grad_norm": 0.6445803046226501, + "learning_rate": 6.136363636363636e-07, + "loss": 0.0898, + "step": 82 + }, + { + "epoch": 0.18906605922551253, + "grad_norm": 0.7300183773040771, + "learning_rate": 6.212121212121212e-07, + "loss": 0.0896, + "step": 83 + }, + { + "epoch": 0.19134396355353075, + "grad_norm": 0.6101515293121338, + "learning_rate": 6.287878787878788e-07, + "loss": 0.0896, + "step": 84 + }, + { + "epoch": 0.19362186788154898, + "grad_norm": 0.4891710579395294, + "learning_rate": 6.363636363636363e-07, + "loss": 0.0912, + "step": 85 + }, + { + "epoch": 0.1958997722095672, + "grad_norm": 0.524264931678772, + "learning_rate": 6.439393939393939e-07, + "loss": 0.0879, + "step": 86 + }, + { + "epoch": 0.19817767653758542, + "grad_norm": 0.4605697989463806, + "learning_rate": 6.515151515151515e-07, + "loss": 0.0874, + "step": 87 + }, + { + "epoch": 0.20045558086560364, + "grad_norm": 0.40725117921829224, + "learning_rate": 6.59090909090909e-07, + "loss": 0.0865, + "step": 88 + }, + { + "epoch": 0.20273348519362186, + "grad_norm": 0.41193538904190063, + "learning_rate": 6.666666666666666e-07, + "loss": 0.0927, + "step": 89 + }, + { + "epoch": 0.20501138952164008, + "grad_norm": 0.4224970042705536, + "learning_rate": 6.742424242424242e-07, + "loss": 0.0867, + "step": 90 + }, + { + "epoch": 0.2072892938496583, + "grad_norm": 0.5528525710105896, + "learning_rate": 6.818181818181817e-07, + "loss": 0.0869, + "step": 91 + }, + { + "epoch": 0.20956719817767655, + "grad_norm": 0.4862363040447235, + "learning_rate": 6.893939393939394e-07, + "loss": 0.0858, + "step": 92 + }, + { + "epoch": 0.21184510250569477, + "grad_norm": 0.38400912284851074, + "learning_rate": 6.96969696969697e-07, + "loss": 0.0885, + "step": 93 + }, + { + "epoch": 0.214123006833713, + "grad_norm": 0.4308898150920868, + "learning_rate": 7.045454545454545e-07, + "loss": 0.0879, + "step": 94 + }, + { + "epoch": 0.2164009111617312, + "grad_norm": 0.4687124192714691, + "learning_rate": 7.121212121212121e-07, + "loss": 0.0869, + "step": 95 + }, + { + "epoch": 0.21867881548974943, + "grad_norm": 0.43760785460472107, + "learning_rate": 7.196969696969697e-07, + "loss": 0.0845, + "step": 96 + }, + { + "epoch": 0.22095671981776766, + "grad_norm": 0.4250319004058838, + "learning_rate": 7.272727272727272e-07, + "loss": 0.0845, + "step": 97 + }, + { + "epoch": 0.22323462414578588, + "grad_norm": 0.42216047644615173, + "learning_rate": 7.348484848484848e-07, + "loss": 0.0853, + "step": 98 + }, + { + "epoch": 0.2255125284738041, + "grad_norm": 0.42051035165786743, + "learning_rate": 7.424242424242424e-07, + "loss": 0.0838, + "step": 99 + }, + { + "epoch": 0.22779043280182232, + "grad_norm": 0.5212217569351196, + "learning_rate": 7.5e-07, + "loss": 0.0849, + "step": 100 + }, + { + "epoch": 0.23006833712984054, + "grad_norm": 0.39043453335762024, + "learning_rate": 7.575757575757575e-07, + "loss": 0.0815, + "step": 101 + }, + { + "epoch": 0.23234624145785876, + "grad_norm": 0.4436104893684387, + "learning_rate": 7.651515151515151e-07, + "loss": 0.0821, + "step": 102 + }, + { + "epoch": 0.23462414578587698, + "grad_norm": 0.4133654236793518, + "learning_rate": 7.727272727272727e-07, + "loss": 0.0844, + "step": 103 + }, + { + "epoch": 0.23690205011389523, + "grad_norm": 0.42570510506629944, + "learning_rate": 7.803030303030302e-07, + "loss": 0.0878, + "step": 104 + }, + { + "epoch": 0.23917995444191345, + "grad_norm": 0.4208022654056549, + "learning_rate": 7.878787878787878e-07, + "loss": 0.0855, + "step": 105 + }, + { + "epoch": 0.24145785876993167, + "grad_norm": 0.36053919792175293, + "learning_rate": 7.954545454545454e-07, + "loss": 0.082, + "step": 106 + }, + { + "epoch": 0.2437357630979499, + "grad_norm": 0.4309670031070709, + "learning_rate": 8.030303030303029e-07, + "loss": 0.0838, + "step": 107 + }, + { + "epoch": 0.2460136674259681, + "grad_norm": 0.38219520449638367, + "learning_rate": 8.106060606060605e-07, + "loss": 0.0791, + "step": 108 + }, + { + "epoch": 0.24829157175398633, + "grad_norm": 1.8719490766525269, + "learning_rate": 8.181818181818182e-07, + "loss": 0.0826, + "step": 109 + }, + { + "epoch": 0.2505694760820046, + "grad_norm": 0.39609619975090027, + "learning_rate": 8.257575757575757e-07, + "loss": 0.081, + "step": 110 + }, + { + "epoch": 0.2528473804100228, + "grad_norm": 0.4301149845123291, + "learning_rate": 8.333333333333333e-07, + "loss": 0.0825, + "step": 111 + }, + { + "epoch": 0.255125284738041, + "grad_norm": 0.3767639100551605, + "learning_rate": 8.409090909090909e-07, + "loss": 0.0836, + "step": 112 + }, + { + "epoch": 0.25740318906605925, + "grad_norm": 0.3603886067867279, + "learning_rate": 8.484848484848484e-07, + "loss": 0.0804, + "step": 113 + }, + { + "epoch": 0.25968109339407747, + "grad_norm": 0.42016807198524475, + "learning_rate": 8.56060606060606e-07, + "loss": 0.0823, + "step": 114 + }, + { + "epoch": 0.2619589977220957, + "grad_norm": 0.37572023272514343, + "learning_rate": 8.636363636363636e-07, + "loss": 0.0819, + "step": 115 + }, + { + "epoch": 0.2642369020501139, + "grad_norm": 0.39218008518218994, + "learning_rate": 8.712121212121211e-07, + "loss": 0.0803, + "step": 116 + }, + { + "epoch": 0.26651480637813213, + "grad_norm": 0.4028224050998688, + "learning_rate": 8.787878787878787e-07, + "loss": 0.0809, + "step": 117 + }, + { + "epoch": 0.26879271070615035, + "grad_norm": 0.38201263546943665, + "learning_rate": 8.863636363636363e-07, + "loss": 0.0836, + "step": 118 + }, + { + "epoch": 0.27107061503416857, + "grad_norm": 0.40858525037765503, + "learning_rate": 8.939393939393938e-07, + "loss": 0.0793, + "step": 119 + }, + { + "epoch": 0.2733485193621868, + "grad_norm": 0.5176743268966675, + "learning_rate": 9.015151515151514e-07, + "loss": 0.0809, + "step": 120 + }, + { + "epoch": 0.275626423690205, + "grad_norm": 0.42799004912376404, + "learning_rate": 9.09090909090909e-07, + "loss": 0.0784, + "step": 121 + }, + { + "epoch": 0.27790432801822323, + "grad_norm": 0.41369882225990295, + "learning_rate": 9.166666666666665e-07, + "loss": 0.0763, + "step": 122 + }, + { + "epoch": 0.28018223234624146, + "grad_norm": 0.3963422179222107, + "learning_rate": 9.242424242424241e-07, + "loss": 0.0818, + "step": 123 + }, + { + "epoch": 0.2824601366742597, + "grad_norm": 0.5200080871582031, + "learning_rate": 9.318181818181817e-07, + "loss": 0.08, + "step": 124 + }, + { + "epoch": 0.2847380410022779, + "grad_norm": 0.4614328444004059, + "learning_rate": 9.393939393939395e-07, + "loss": 0.0753, + "step": 125 + }, + { + "epoch": 0.2870159453302961, + "grad_norm": 0.3704628348350525, + "learning_rate": 9.46969696969697e-07, + "loss": 0.0766, + "step": 126 + }, + { + "epoch": 0.28929384965831434, + "grad_norm": 0.5018488764762878, + "learning_rate": 9.545454545454546e-07, + "loss": 0.08, + "step": 127 + }, + { + "epoch": 0.29157175398633256, + "grad_norm": 0.3799089789390564, + "learning_rate": 9.62121212121212e-07, + "loss": 0.0785, + "step": 128 + }, + { + "epoch": 0.2938496583143508, + "grad_norm": 0.4421888291835785, + "learning_rate": 9.696969696969698e-07, + "loss": 0.0823, + "step": 129 + }, + { + "epoch": 0.296127562642369, + "grad_norm": 0.3620028495788574, + "learning_rate": 9.772727272727273e-07, + "loss": 0.0796, + "step": 130 + }, + { + "epoch": 0.2984054669703872, + "grad_norm": 0.5644951462745667, + "learning_rate": 9.848484848484847e-07, + "loss": 0.0722, + "step": 131 + }, + { + "epoch": 0.30068337129840544, + "grad_norm": 0.35744860768318176, + "learning_rate": 9.924242424242425e-07, + "loss": 0.0779, + "step": 132 + }, + { + "epoch": 0.30296127562642367, + "grad_norm": 0.49118587374687195, + "learning_rate": 1e-06, + "loss": 0.0795, + "step": 133 + }, + { + "epoch": 0.3052391799544419, + "grad_norm": 0.3668941259384155, + "learning_rate": 1e-06, + "loss": 0.0787, + "step": 134 + }, + { + "epoch": 0.30751708428246016, + "grad_norm": 0.4011993110179901, + "learning_rate": 1e-06, + "loss": 0.0795, + "step": 135 + }, + { + "epoch": 0.3097949886104784, + "grad_norm": 0.43992048501968384, + "learning_rate": 1e-06, + "loss": 0.0794, + "step": 136 + }, + { + "epoch": 0.3120728929384966, + "grad_norm": 0.5386244058609009, + "learning_rate": 1e-06, + "loss": 0.0771, + "step": 137 + }, + { + "epoch": 0.3143507972665148, + "grad_norm": 0.4377044439315796, + "learning_rate": 1e-06, + "loss": 0.0783, + "step": 138 + }, + { + "epoch": 0.31662870159453305, + "grad_norm": 0.34476202726364136, + "learning_rate": 1e-06, + "loss": 0.0793, + "step": 139 + }, + { + "epoch": 0.31890660592255127, + "grad_norm": 0.40727806091308594, + "learning_rate": 1e-06, + "loss": 0.0766, + "step": 140 + }, + { + "epoch": 0.3211845102505695, + "grad_norm": 0.6315299868583679, + "learning_rate": 1e-06, + "loss": 0.0807, + "step": 141 + }, + { + "epoch": 0.3234624145785877, + "grad_norm": 0.5480681657791138, + "learning_rate": 1e-06, + "loss": 0.0781, + "step": 142 + }, + { + "epoch": 0.32574031890660593, + "grad_norm": 0.40762820839881897, + "learning_rate": 1e-06, + "loss": 0.0745, + "step": 143 + }, + { + "epoch": 0.32801822323462415, + "grad_norm": 0.5186673402786255, + "learning_rate": 1e-06, + "loss": 0.0763, + "step": 144 + }, + { + "epoch": 0.33029612756264237, + "grad_norm": 0.3832704722881317, + "learning_rate": 1e-06, + "loss": 0.0772, + "step": 145 + }, + { + "epoch": 0.3325740318906606, + "grad_norm": 0.3368404805660248, + "learning_rate": 1e-06, + "loss": 0.075, + "step": 146 + }, + { + "epoch": 0.3348519362186788, + "grad_norm": 0.33721643686294556, + "learning_rate": 1e-06, + "loss": 0.075, + "step": 147 + }, + { + "epoch": 0.33712984054669703, + "grad_norm": 0.35688939690589905, + "learning_rate": 1e-06, + "loss": 0.078, + "step": 148 + }, + { + "epoch": 0.33940774487471526, + "grad_norm": 0.4005364179611206, + "learning_rate": 1e-06, + "loss": 0.0776, + "step": 149 + }, + { + "epoch": 0.3416856492027335, + "grad_norm": 0.36659881472587585, + "learning_rate": 1e-06, + "loss": 0.0769, + "step": 150 + }, + { + "epoch": 0.3439635535307517, + "grad_norm": 0.4420287013053894, + "learning_rate": 1e-06, + "loss": 0.0763, + "step": 151 + }, + { + "epoch": 0.3462414578587699, + "grad_norm": 0.44534027576446533, + "learning_rate": 1e-06, + "loss": 0.0761, + "step": 152 + }, + { + "epoch": 0.34851936218678814, + "grad_norm": 0.336983859539032, + "learning_rate": 1e-06, + "loss": 0.0747, + "step": 153 + }, + { + "epoch": 0.35079726651480636, + "grad_norm": 0.37923380732536316, + "learning_rate": 1e-06, + "loss": 0.0769, + "step": 154 + }, + { + "epoch": 0.3530751708428246, + "grad_norm": 0.3724338114261627, + "learning_rate": 1e-06, + "loss": 0.0765, + "step": 155 + }, + { + "epoch": 0.3553530751708428, + "grad_norm": 0.4099346697330475, + "learning_rate": 1e-06, + "loss": 0.0777, + "step": 156 + }, + { + "epoch": 0.357630979498861, + "grad_norm": 0.42383232712745667, + "learning_rate": 1e-06, + "loss": 0.0784, + "step": 157 + }, + { + "epoch": 0.35990888382687924, + "grad_norm": 0.4161367416381836, + "learning_rate": 1e-06, + "loss": 0.0781, + "step": 158 + }, + { + "epoch": 0.3621867881548975, + "grad_norm": 0.40564417839050293, + "learning_rate": 1e-06, + "loss": 0.0763, + "step": 159 + }, + { + "epoch": 0.36446469248291574, + "grad_norm": 0.3912067115306854, + "learning_rate": 1e-06, + "loss": 0.0741, + "step": 160 + }, + { + "epoch": 0.36674259681093396, + "grad_norm": 0.386160284280777, + "learning_rate": 1e-06, + "loss": 0.0753, + "step": 161 + }, + { + "epoch": 0.3690205011389522, + "grad_norm": 0.3776938021183014, + "learning_rate": 1e-06, + "loss": 0.0763, + "step": 162 + }, + { + "epoch": 0.3712984054669704, + "grad_norm": 0.37912315130233765, + "learning_rate": 1e-06, + "loss": 0.079, + "step": 163 + }, + { + "epoch": 0.3735763097949886, + "grad_norm": 0.33273792266845703, + "learning_rate": 1e-06, + "loss": 0.0765, + "step": 164 + }, + { + "epoch": 0.37585421412300685, + "grad_norm": 0.34678927063941956, + "learning_rate": 1e-06, + "loss": 0.0771, + "step": 165 + }, + { + "epoch": 0.37813211845102507, + "grad_norm": 0.35114893317222595, + "learning_rate": 1e-06, + "loss": 0.0765, + "step": 166 + }, + { + "epoch": 0.3804100227790433, + "grad_norm": 0.3405204117298126, + "learning_rate": 1e-06, + "loss": 0.0728, + "step": 167 + }, + { + "epoch": 0.3826879271070615, + "grad_norm": 0.34031590819358826, + "learning_rate": 1e-06, + "loss": 0.0768, + "step": 168 + }, + { + "epoch": 0.38496583143507973, + "grad_norm": 0.353154718875885, + "learning_rate": 1e-06, + "loss": 0.0736, + "step": 169 + }, + { + "epoch": 0.38724373576309795, + "grad_norm": 0.35976454615592957, + "learning_rate": 1e-06, + "loss": 0.0742, + "step": 170 + }, + { + "epoch": 0.3895216400911162, + "grad_norm": 0.37882116436958313, + "learning_rate": 1e-06, + "loss": 0.0736, + "step": 171 + }, + { + "epoch": 0.3917995444191344, + "grad_norm": 0.3837342858314514, + "learning_rate": 1e-06, + "loss": 0.0755, + "step": 172 + }, + { + "epoch": 0.3940774487471526, + "grad_norm": 0.34043431282043457, + "learning_rate": 1e-06, + "loss": 0.0764, + "step": 173 + }, + { + "epoch": 0.39635535307517084, + "grad_norm": 0.3652219772338867, + "learning_rate": 1e-06, + "loss": 0.0728, + "step": 174 + }, + { + "epoch": 0.39863325740318906, + "grad_norm": 0.3549719750881195, + "learning_rate": 1e-06, + "loss": 0.0733, + "step": 175 + }, + { + "epoch": 0.4009111617312073, + "grad_norm": 0.392108291387558, + "learning_rate": 1e-06, + "loss": 0.0737, + "step": 176 + }, + { + "epoch": 0.4031890660592255, + "grad_norm": 0.39466091990470886, + "learning_rate": 1e-06, + "loss": 0.0755, + "step": 177 + }, + { + "epoch": 0.4054669703872437, + "grad_norm": 0.42767536640167236, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 178 + }, + { + "epoch": 0.40774487471526194, + "grad_norm": 0.37782537937164307, + "learning_rate": 1e-06, + "loss": 0.0764, + "step": 179 + }, + { + "epoch": 0.41002277904328016, + "grad_norm": 0.393995076417923, + "learning_rate": 1e-06, + "loss": 0.0735, + "step": 180 + }, + { + "epoch": 0.4123006833712984, + "grad_norm": 0.3517935276031494, + "learning_rate": 1e-06, + "loss": 0.0753, + "step": 181 + }, + { + "epoch": 0.4145785876993166, + "grad_norm": 0.35618871450424194, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 182 + }, + { + "epoch": 0.4168564920273349, + "grad_norm": 0.38193410634994507, + "learning_rate": 1e-06, + "loss": 0.0725, + "step": 183 + }, + { + "epoch": 0.4191343963553531, + "grad_norm": 0.40648916363716125, + "learning_rate": 1e-06, + "loss": 0.077, + "step": 184 + }, + { + "epoch": 0.4214123006833713, + "grad_norm": 0.35797256231307983, + "learning_rate": 1e-06, + "loss": 0.0731, + "step": 185 + }, + { + "epoch": 0.42369020501138954, + "grad_norm": 0.35879969596862793, + "learning_rate": 1e-06, + "loss": 0.0745, + "step": 186 + }, + { + "epoch": 0.42596810933940776, + "grad_norm": 0.37205037474632263, + "learning_rate": 1e-06, + "loss": 0.0746, + "step": 187 + }, + { + "epoch": 0.428246013667426, + "grad_norm": 0.3497586250305176, + "learning_rate": 1e-06, + "loss": 0.0761, + "step": 188 + }, + { + "epoch": 0.4305239179954442, + "grad_norm": 0.36516034603118896, + "learning_rate": 1e-06, + "loss": 0.0767, + "step": 189 + }, + { + "epoch": 0.4328018223234624, + "grad_norm": 0.3595488667488098, + "learning_rate": 1e-06, + "loss": 0.0727, + "step": 190 + }, + { + "epoch": 0.43507972665148065, + "grad_norm": 0.3679116666316986, + "learning_rate": 1e-06, + "loss": 0.0748, + "step": 191 + }, + { + "epoch": 0.43735763097949887, + "grad_norm": 0.3438495099544525, + "learning_rate": 1e-06, + "loss": 0.0742, + "step": 192 + }, + { + "epoch": 0.4396355353075171, + "grad_norm": 0.3475053608417511, + "learning_rate": 1e-06, + "loss": 0.0733, + "step": 193 + }, + { + "epoch": 0.4419134396355353, + "grad_norm": 0.36513954401016235, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 194 + }, + { + "epoch": 0.44419134396355353, + "grad_norm": 0.325244665145874, + "learning_rate": 1e-06, + "loss": 0.0759, + "step": 195 + }, + { + "epoch": 0.44646924829157175, + "grad_norm": 0.34712353348731995, + "learning_rate": 1e-06, + "loss": 0.0771, + "step": 196 + }, + { + "epoch": 0.44874715261959, + "grad_norm": 0.33088621497154236, + "learning_rate": 1e-06, + "loss": 0.0748, + "step": 197 + }, + { + "epoch": 0.4510250569476082, + "grad_norm": 0.35378965735435486, + "learning_rate": 1e-06, + "loss": 0.0708, + "step": 198 + }, + { + "epoch": 0.4533029612756264, + "grad_norm": 0.35132139921188354, + "learning_rate": 1e-06, + "loss": 0.0767, + "step": 199 + }, + { + "epoch": 0.45558086560364464, + "grad_norm": 0.37184572219848633, + "learning_rate": 1e-06, + "loss": 0.0738, + "step": 200 + }, + { + "epoch": 0.45785876993166286, + "grad_norm": 0.3531855642795563, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 201 + }, + { + "epoch": 0.4601366742596811, + "grad_norm": 0.3488656282424927, + "learning_rate": 1e-06, + "loss": 0.0742, + "step": 202 + }, + { + "epoch": 0.4624145785876993, + "grad_norm": 0.3477659821510315, + "learning_rate": 1e-06, + "loss": 0.0727, + "step": 203 + }, + { + "epoch": 0.4646924829157175, + "grad_norm": 0.3662627637386322, + "learning_rate": 1e-06, + "loss": 0.0748, + "step": 204 + }, + { + "epoch": 0.46697038724373574, + "grad_norm": 0.3710251450538635, + "learning_rate": 1e-06, + "loss": 0.0752, + "step": 205 + }, + { + "epoch": 0.46924829157175396, + "grad_norm": 0.3326471745967865, + "learning_rate": 1e-06, + "loss": 0.0711, + "step": 206 + }, + { + "epoch": 0.4715261958997722, + "grad_norm": 0.35802939534187317, + "learning_rate": 1e-06, + "loss": 0.0778, + "step": 207 + }, + { + "epoch": 0.47380410022779046, + "grad_norm": 0.3655394911766052, + "learning_rate": 1e-06, + "loss": 0.0715, + "step": 208 + }, + { + "epoch": 0.4760820045558087, + "grad_norm": 0.31994614005088806, + "learning_rate": 1e-06, + "loss": 0.0732, + "step": 209 + }, + { + "epoch": 0.4783599088838269, + "grad_norm": 0.3492507040500641, + "learning_rate": 1e-06, + "loss": 0.0731, + "step": 210 + }, + { + "epoch": 0.4806378132118451, + "grad_norm": 0.3556287884712219, + "learning_rate": 1e-06, + "loss": 0.0716, + "step": 211 + }, + { + "epoch": 0.48291571753986334, + "grad_norm": 0.33689793944358826, + "learning_rate": 1e-06, + "loss": 0.0723, + "step": 212 + }, + { + "epoch": 0.48519362186788156, + "grad_norm": 0.35764843225479126, + "learning_rate": 1e-06, + "loss": 0.0724, + "step": 213 + }, + { + "epoch": 0.4874715261958998, + "grad_norm": 0.3588120639324188, + "learning_rate": 1e-06, + "loss": 0.0733, + "step": 214 + }, + { + "epoch": 0.489749430523918, + "grad_norm": 0.3354783356189728, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 215 + }, + { + "epoch": 0.4920273348519362, + "grad_norm": 0.33201050758361816, + "learning_rate": 1e-06, + "loss": 0.071, + "step": 216 + }, + { + "epoch": 0.49430523917995445, + "grad_norm": 0.3763951361179352, + "learning_rate": 1e-06, + "loss": 0.0742, + "step": 217 + }, + { + "epoch": 0.49658314350797267, + "grad_norm": 0.5205076932907104, + "learning_rate": 1e-06, + "loss": 0.0724, + "step": 218 + }, + { + "epoch": 0.4988610478359909, + "grad_norm": 0.4746200144290924, + "learning_rate": 1e-06, + "loss": 0.075, + "step": 219 + }, + { + "epoch": 0.5011389521640092, + "grad_norm": 0.4077713191509247, + "learning_rate": 1e-06, + "loss": 0.0752, + "step": 220 + }, + { + "epoch": 0.5034168564920274, + "grad_norm": 0.3273921310901642, + "learning_rate": 1e-06, + "loss": 0.0736, + "step": 221 + }, + { + "epoch": 0.5056947608200456, + "grad_norm": 0.4066220223903656, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 222 + }, + { + "epoch": 0.5079726651480638, + "grad_norm": 0.3608191907405853, + "learning_rate": 1e-06, + "loss": 0.0727, + "step": 223 + }, + { + "epoch": 0.510250569476082, + "grad_norm": 0.33274054527282715, + "learning_rate": 1e-06, + "loss": 0.0723, + "step": 224 + }, + { + "epoch": 0.5125284738041003, + "grad_norm": 0.35716891288757324, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 225 + }, + { + "epoch": 0.5148063781321185, + "grad_norm": 0.36759352684020996, + "learning_rate": 1e-06, + "loss": 0.0758, + "step": 226 + }, + { + "epoch": 0.5170842824601367, + "grad_norm": 0.3276847302913666, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 227 + }, + { + "epoch": 0.5193621867881549, + "grad_norm": 0.6134676337242126, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 228 + }, + { + "epoch": 0.5216400911161732, + "grad_norm": 0.3583739399909973, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 229 + }, + { + "epoch": 0.5239179954441914, + "grad_norm": 0.3452317416667938, + "learning_rate": 1e-06, + "loss": 0.0703, + "step": 230 + }, + { + "epoch": 0.5261958997722096, + "grad_norm": 0.3580189645290375, + "learning_rate": 1e-06, + "loss": 0.071, + "step": 231 + }, + { + "epoch": 0.5284738041002278, + "grad_norm": 0.3351745009422302, + "learning_rate": 1e-06, + "loss": 0.0724, + "step": 232 + }, + { + "epoch": 0.530751708428246, + "grad_norm": 1.9722075462341309, + "learning_rate": 1e-06, + "loss": 0.0751, + "step": 233 + }, + { + "epoch": 0.5330296127562643, + "grad_norm": 0.34854814410209656, + "learning_rate": 1e-06, + "loss": 0.0731, + "step": 234 + }, + { + "epoch": 0.5353075170842825, + "grad_norm": 0.3541731536388397, + "learning_rate": 1e-06, + "loss": 0.0699, + "step": 235 + }, + { + "epoch": 0.5375854214123007, + "grad_norm": 0.40238359570503235, + "learning_rate": 1e-06, + "loss": 0.0739, + "step": 236 + }, + { + "epoch": 0.5398633257403189, + "grad_norm": 0.3762642741203308, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 237 + }, + { + "epoch": 0.5421412300683371, + "grad_norm": 0.37260618805885315, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 238 + }, + { + "epoch": 0.5444191343963554, + "grad_norm": 0.37747710943222046, + "learning_rate": 1e-06, + "loss": 0.0753, + "step": 239 + }, + { + "epoch": 0.5466970387243736, + "grad_norm": 0.33547288179397583, + "learning_rate": 1e-06, + "loss": 0.0708, + "step": 240 + }, + { + "epoch": 0.5489749430523918, + "grad_norm": 0.33844342827796936, + "learning_rate": 1e-06, + "loss": 0.0723, + "step": 241 + }, + { + "epoch": 0.55125284738041, + "grad_norm": 0.4018166661262512, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 242 + }, + { + "epoch": 0.5535307517084282, + "grad_norm": 0.39423102140426636, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 243 + }, + { + "epoch": 0.5558086560364465, + "grad_norm": 0.3391086459159851, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 244 + }, + { + "epoch": 0.5580865603644647, + "grad_norm": 0.3549361228942871, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 245 + }, + { + "epoch": 0.5603644646924829, + "grad_norm": 0.3725798428058624, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 246 + }, + { + "epoch": 0.5626423690205011, + "grad_norm": 0.3683355152606964, + "learning_rate": 1e-06, + "loss": 0.0728, + "step": 247 + }, + { + "epoch": 0.5649202733485194, + "grad_norm": 0.3360946476459503, + "learning_rate": 1e-06, + "loss": 0.0715, + "step": 248 + }, + { + "epoch": 0.5671981776765376, + "grad_norm": 0.3819708526134491, + "learning_rate": 1e-06, + "loss": 0.0734, + "step": 249 + }, + { + "epoch": 0.5694760820045558, + "grad_norm": 0.36096087098121643, + "learning_rate": 1e-06, + "loss": 0.071, + "step": 250 + }, + { + "epoch": 0.571753986332574, + "grad_norm": 0.3853183686733246, + "learning_rate": 1e-06, + "loss": 0.071, + "step": 251 + }, + { + "epoch": 0.5740318906605922, + "grad_norm": 0.33971288800239563, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 252 + }, + { + "epoch": 0.5763097949886105, + "grad_norm": 0.38011038303375244, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 253 + }, + { + "epoch": 0.5785876993166287, + "grad_norm": 0.3617028295993805, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 254 + }, + { + "epoch": 0.5808656036446469, + "grad_norm": 0.341153085231781, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 255 + }, + { + "epoch": 0.5831435079726651, + "grad_norm": 0.3225387632846832, + "learning_rate": 1e-06, + "loss": 0.0719, + "step": 256 + }, + { + "epoch": 0.5854214123006833, + "grad_norm": 0.34903979301452637, + "learning_rate": 1e-06, + "loss": 0.0713, + "step": 257 + }, + { + "epoch": 0.5876993166287016, + "grad_norm": 0.37068599462509155, + "learning_rate": 1e-06, + "loss": 0.073, + "step": 258 + }, + { + "epoch": 0.5899772209567198, + "grad_norm": 0.3316898047924042, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 259 + }, + { + "epoch": 0.592255125284738, + "grad_norm": 0.41165006160736084, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 260 + }, + { + "epoch": 0.5945330296127562, + "grad_norm": 0.40296339988708496, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 261 + }, + { + "epoch": 0.5968109339407744, + "grad_norm": 0.35744959115982056, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 262 + }, + { + "epoch": 0.5990888382687927, + "grad_norm": 0.3516010046005249, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 263 + }, + { + "epoch": 0.6013667425968109, + "grad_norm": 0.3712936341762543, + "learning_rate": 1e-06, + "loss": 0.0714, + "step": 264 + }, + { + "epoch": 0.6036446469248291, + "grad_norm": 0.32422178983688354, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 265 + }, + { + "epoch": 0.6059225512528473, + "grad_norm": 0.34246915578842163, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 266 + }, + { + "epoch": 0.6082004555808656, + "grad_norm": 0.38620883226394653, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 267 + }, + { + "epoch": 0.6104783599088838, + "grad_norm": 0.35478872060775757, + "learning_rate": 1e-06, + "loss": 0.0716, + "step": 268 + }, + { + "epoch": 0.6127562642369021, + "grad_norm": 0.32179179787635803, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 269 + }, + { + "epoch": 0.6150341685649203, + "grad_norm": 0.34132757782936096, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 270 + }, + { + "epoch": 0.6173120728929385, + "grad_norm": 0.3638244867324829, + "learning_rate": 1e-06, + "loss": 0.0699, + "step": 271 + }, + { + "epoch": 0.6195899772209568, + "grad_norm": 0.3815762996673584, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 272 + }, + { + "epoch": 0.621867881548975, + "grad_norm": 0.3627689778804779, + "learning_rate": 1e-06, + "loss": 0.0713, + "step": 273 + }, + { + "epoch": 0.6241457858769932, + "grad_norm": 0.33969423174858093, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 274 + }, + { + "epoch": 0.6264236902050114, + "grad_norm": 0.34073522686958313, + "learning_rate": 1e-06, + "loss": 0.0709, + "step": 275 + }, + { + "epoch": 0.6287015945330297, + "grad_norm": 0.404371976852417, + "learning_rate": 1e-06, + "loss": 0.0709, + "step": 276 + }, + { + "epoch": 0.6309794988610479, + "grad_norm": 0.3594112992286682, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 277 + }, + { + "epoch": 0.6332574031890661, + "grad_norm": 0.3392229378223419, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 278 + }, + { + "epoch": 0.6355353075170843, + "grad_norm": 0.33321115374565125, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 279 + }, + { + "epoch": 0.6378132118451025, + "grad_norm": 0.34605705738067627, + "learning_rate": 1e-06, + "loss": 0.0723, + "step": 280 + }, + { + "epoch": 0.6400911161731208, + "grad_norm": 0.32384631037712097, + "learning_rate": 1e-06, + "loss": 0.0715, + "step": 281 + }, + { + "epoch": 0.642369020501139, + "grad_norm": 0.3199082612991333, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 282 + }, + { + "epoch": 0.6446469248291572, + "grad_norm": 0.3792301118373871, + "learning_rate": 1e-06, + "loss": 0.0733, + "step": 283 + }, + { + "epoch": 0.6469248291571754, + "grad_norm": 0.3747650980949402, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 284 + }, + { + "epoch": 0.6492027334851936, + "grad_norm": 0.3534970283508301, + "learning_rate": 1e-06, + "loss": 0.0705, + "step": 285 + }, + { + "epoch": 0.6514806378132119, + "grad_norm": 0.3473007380962372, + "learning_rate": 1e-06, + "loss": 0.0736, + "step": 286 + }, + { + "epoch": 0.6537585421412301, + "grad_norm": 0.33009853959083557, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 287 + }, + { + "epoch": 0.6560364464692483, + "grad_norm": 0.36439749598503113, + "learning_rate": 1e-06, + "loss": 0.07, + "step": 288 + }, + { + "epoch": 0.6583143507972665, + "grad_norm": 0.3407539129257202, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 289 + }, + { + "epoch": 0.6605922551252847, + "grad_norm": 0.3506968319416046, + "learning_rate": 1e-06, + "loss": 0.0726, + "step": 290 + }, + { + "epoch": 0.662870159453303, + "grad_norm": 0.33120062947273254, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 291 + }, + { + "epoch": 0.6651480637813212, + "grad_norm": 0.37392812967300415, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 292 + }, + { + "epoch": 0.6674259681093394, + "grad_norm": 0.37844860553741455, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 293 + }, + { + "epoch": 0.6697038724373576, + "grad_norm": 0.3126504421234131, + "learning_rate": 1e-06, + "loss": 0.0709, + "step": 294 + }, + { + "epoch": 0.6719817767653758, + "grad_norm": 0.31031060218811035, + "learning_rate": 1e-06, + "loss": 0.0702, + "step": 295 + }, + { + "epoch": 0.6742596810933941, + "grad_norm": 0.37186479568481445, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 296 + }, + { + "epoch": 0.6765375854214123, + "grad_norm": 0.4010624289512634, + "learning_rate": 1e-06, + "loss": 0.0722, + "step": 297 + }, + { + "epoch": 0.6788154897494305, + "grad_norm": 0.37667614221572876, + "learning_rate": 1e-06, + "loss": 0.0732, + "step": 298 + }, + { + "epoch": 0.6810933940774487, + "grad_norm": 0.35324499011039734, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 299 + }, + { + "epoch": 0.683371298405467, + "grad_norm": 0.3568263053894043, + "learning_rate": 1e-06, + "loss": 0.0735, + "step": 300 + }, + { + "epoch": 0.6856492027334852, + "grad_norm": 0.37012284994125366, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 301 + }, + { + "epoch": 0.6879271070615034, + "grad_norm": 0.36729714274406433, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 302 + }, + { + "epoch": 0.6902050113895216, + "grad_norm": 0.3658808469772339, + "learning_rate": 1e-06, + "loss": 0.071, + "step": 303 + }, + { + "epoch": 0.6924829157175398, + "grad_norm": 0.33323603868484497, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 304 + }, + { + "epoch": 0.6947608200455581, + "grad_norm": 0.3147551715373993, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 305 + }, + { + "epoch": 0.6970387243735763, + "grad_norm": 0.3457568287849426, + "learning_rate": 1e-06, + "loss": 0.0699, + "step": 306 + }, + { + "epoch": 0.6993166287015945, + "grad_norm": 0.40288424491882324, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 307 + }, + { + "epoch": 0.7015945330296127, + "grad_norm": 0.3422483801841736, + "learning_rate": 1e-06, + "loss": 0.0736, + "step": 308 + }, + { + "epoch": 0.7038724373576309, + "grad_norm": 0.3451822102069855, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 309 + }, + { + "epoch": 0.7061503416856492, + "grad_norm": 0.34883856773376465, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 310 + }, + { + "epoch": 0.7084282460136674, + "grad_norm": 0.40489402413368225, + "learning_rate": 1e-06, + "loss": 0.0712, + "step": 311 + }, + { + "epoch": 0.7107061503416856, + "grad_norm": 0.3783627152442932, + "learning_rate": 1e-06, + "loss": 0.0702, + "step": 312 + }, + { + "epoch": 0.7129840546697038, + "grad_norm": 0.36443835496902466, + "learning_rate": 1e-06, + "loss": 0.0725, + "step": 313 + }, + { + "epoch": 0.715261958997722, + "grad_norm": 0.3674992322921753, + "learning_rate": 1e-06, + "loss": 0.0747, + "step": 314 + }, + { + "epoch": 0.7175398633257403, + "grad_norm": 0.3334760069847107, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 315 + }, + { + "epoch": 0.7198177676537585, + "grad_norm": 0.3876517713069916, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 316 + }, + { + "epoch": 0.7220956719817767, + "grad_norm": 0.38126084208488464, + "learning_rate": 1e-06, + "loss": 0.0716, + "step": 317 + }, + { + "epoch": 0.724373576309795, + "grad_norm": 0.4029550552368164, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 318 + }, + { + "epoch": 0.7266514806378133, + "grad_norm": 0.36764946579933167, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 319 + }, + { + "epoch": 0.7289293849658315, + "grad_norm": 0.32915693521499634, + "learning_rate": 1e-06, + "loss": 0.0718, + "step": 320 + }, + { + "epoch": 0.7312072892938497, + "grad_norm": 0.34783512353897095, + "learning_rate": 1e-06, + "loss": 0.0713, + "step": 321 + }, + { + "epoch": 0.7334851936218679, + "grad_norm": 0.40711942315101624, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 322 + }, + { + "epoch": 0.7357630979498861, + "grad_norm": 0.49989888072013855, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 323 + }, + { + "epoch": 0.7380410022779044, + "grad_norm": 0.34234246611595154, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 324 + }, + { + "epoch": 0.7403189066059226, + "grad_norm": 0.3159977197647095, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 325 + }, + { + "epoch": 0.7425968109339408, + "grad_norm": 0.34032759070396423, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 326 + }, + { + "epoch": 0.744874715261959, + "grad_norm": 0.35689494013786316, + "learning_rate": 1e-06, + "loss": 0.0715, + "step": 327 + }, + { + "epoch": 0.7471526195899773, + "grad_norm": 0.3572857677936554, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 328 + }, + { + "epoch": 0.7494305239179955, + "grad_norm": 0.3455881178379059, + "learning_rate": 1e-06, + "loss": 0.073, + "step": 329 + }, + { + "epoch": 0.7517084282460137, + "grad_norm": 0.36338338255882263, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 330 + }, + { + "epoch": 0.7539863325740319, + "grad_norm": 0.32793566584587097, + "learning_rate": 1e-06, + "loss": 0.0705, + "step": 331 + }, + { + "epoch": 0.7562642369020501, + "grad_norm": 0.32589584589004517, + "learning_rate": 1e-06, + "loss": 0.0695, + "step": 332 + }, + { + "epoch": 0.7585421412300684, + "grad_norm": 0.32437798380851746, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 333 + }, + { + "epoch": 0.7608200455580866, + "grad_norm": 0.32902270555496216, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 334 + }, + { + "epoch": 0.7630979498861048, + "grad_norm": 0.3231542706489563, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 335 + }, + { + "epoch": 0.765375854214123, + "grad_norm": 0.348283052444458, + "learning_rate": 1e-06, + "loss": 0.0705, + "step": 336 + }, + { + "epoch": 0.7676537585421412, + "grad_norm": 0.3258485198020935, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 337 + }, + { + "epoch": 0.7699316628701595, + "grad_norm": 0.39988401532173157, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 338 + }, + { + "epoch": 0.7722095671981777, + "grad_norm": 0.3466617166996002, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 339 + }, + { + "epoch": 0.7744874715261959, + "grad_norm": 0.3262960910797119, + "learning_rate": 1e-06, + "loss": 0.069, + "step": 340 + }, + { + "epoch": 0.7767653758542141, + "grad_norm": 0.3613532483577728, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 341 + }, + { + "epoch": 0.7790432801822323, + "grad_norm": 0.3265013098716736, + "learning_rate": 1e-06, + "loss": 0.0705, + "step": 342 + }, + { + "epoch": 0.7813211845102506, + "grad_norm": 0.35323643684387207, + "learning_rate": 1e-06, + "loss": 0.072, + "step": 343 + }, + { + "epoch": 0.7835990888382688, + "grad_norm": 0.38076701760292053, + "learning_rate": 1e-06, + "loss": 0.0724, + "step": 344 + }, + { + "epoch": 0.785876993166287, + "grad_norm": 0.3264417052268982, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 345 + }, + { + "epoch": 0.7881548974943052, + "grad_norm": 0.3726365864276886, + "learning_rate": 1e-06, + "loss": 0.0678, + "step": 346 + }, + { + "epoch": 0.7904328018223234, + "grad_norm": 0.350151389837265, + "learning_rate": 1e-06, + "loss": 0.0688, + "step": 347 + }, + { + "epoch": 0.7927107061503417, + "grad_norm": 0.34270885586738586, + "learning_rate": 1e-06, + "loss": 0.07, + "step": 348 + }, + { + "epoch": 0.7949886104783599, + "grad_norm": 0.3403871953487396, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 349 + }, + { + "epoch": 0.7972665148063781, + "grad_norm": 1.3514533042907715, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 350 + }, + { + "epoch": 0.7995444191343963, + "grad_norm": 0.368386834859848, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 351 + }, + { + "epoch": 0.8018223234624146, + "grad_norm": 0.361936092376709, + "learning_rate": 1e-06, + "loss": 0.0702, + "step": 352 + }, + { + "epoch": 0.8041002277904328, + "grad_norm": 0.3473425507545471, + "learning_rate": 1e-06, + "loss": 0.0712, + "step": 353 + }, + { + "epoch": 0.806378132118451, + "grad_norm": 0.3462640345096588, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 354 + }, + { + "epoch": 0.8086560364464692, + "grad_norm": 0.3676953911781311, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 355 + }, + { + "epoch": 0.8109339407744874, + "grad_norm": 0.3505808115005493, + "learning_rate": 1e-06, + "loss": 0.0712, + "step": 356 + }, + { + "epoch": 0.8132118451025057, + "grad_norm": 0.3875659704208374, + "learning_rate": 1e-06, + "loss": 0.0688, + "step": 357 + }, + { + "epoch": 0.8154897494305239, + "grad_norm": 0.35812908411026, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 358 + }, + { + "epoch": 0.8177676537585421, + "grad_norm": 0.3472263514995575, + "learning_rate": 1e-06, + "loss": 0.0695, + "step": 359 + }, + { + "epoch": 0.8200455580865603, + "grad_norm": 0.31697091460227966, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 360 + }, + { + "epoch": 0.8223234624145785, + "grad_norm": 0.3516336679458618, + "learning_rate": 1e-06, + "loss": 0.0694, + "step": 361 + }, + { + "epoch": 0.8246013667425968, + "grad_norm": 0.3335164189338684, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 362 + }, + { + "epoch": 0.826879271070615, + "grad_norm": 0.35510173439979553, + "learning_rate": 1e-06, + "loss": 0.0713, + "step": 363 + }, + { + "epoch": 0.8291571753986332, + "grad_norm": 0.35068219900131226, + "learning_rate": 1e-06, + "loss": 0.07, + "step": 364 + }, + { + "epoch": 0.8314350797266514, + "grad_norm": 0.35298147797584534, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 365 + }, + { + "epoch": 0.8337129840546698, + "grad_norm": 0.31746482849121094, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 366 + }, + { + "epoch": 0.835990888382688, + "grad_norm": 0.3268543779850006, + "learning_rate": 1e-06, + "loss": 0.0717, + "step": 367 + }, + { + "epoch": 0.8382687927107062, + "grad_norm": 0.33943212032318115, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 368 + }, + { + "epoch": 0.8405466970387244, + "grad_norm": 0.40925899147987366, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 369 + }, + { + "epoch": 0.8428246013667426, + "grad_norm": 0.32886630296707153, + "learning_rate": 1e-06, + "loss": 0.0703, + "step": 370 + }, + { + "epoch": 0.8451025056947609, + "grad_norm": 0.4205392897129059, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 371 + }, + { + "epoch": 0.8473804100227791, + "grad_norm": 0.41933774948120117, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 372 + }, + { + "epoch": 0.8496583143507973, + "grad_norm": 0.401002436876297, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 373 + }, + { + "epoch": 0.8519362186788155, + "grad_norm": 0.3199481964111328, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 374 + }, + { + "epoch": 0.8542141230068337, + "grad_norm": 0.3749034106731415, + "learning_rate": 1e-06, + "loss": 0.0712, + "step": 375 + }, + { + "epoch": 0.856492027334852, + "grad_norm": 0.42667555809020996, + "learning_rate": 1e-06, + "loss": 0.0721, + "step": 376 + }, + { + "epoch": 0.8587699316628702, + "grad_norm": 0.36199232935905457, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 377 + }, + { + "epoch": 0.8610478359908884, + "grad_norm": 0.3168577551841736, + "learning_rate": 1e-06, + "loss": 0.0678, + "step": 378 + }, + { + "epoch": 0.8633257403189066, + "grad_norm": 0.3767094612121582, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 379 + }, + { + "epoch": 0.8656036446469249, + "grad_norm": 0.36170724034309387, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 380 + }, + { + "epoch": 0.8678815489749431, + "grad_norm": 0.41562336683273315, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 381 + }, + { + "epoch": 0.8701594533029613, + "grad_norm": 0.32717108726501465, + "learning_rate": 1e-06, + "loss": 0.0722, + "step": 382 + }, + { + "epoch": 0.8724373576309795, + "grad_norm": 0.4004034399986267, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 383 + }, + { + "epoch": 0.8747152619589977, + "grad_norm": 0.32923153042793274, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 384 + }, + { + "epoch": 0.876993166287016, + "grad_norm": 0.31748029589653015, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 385 + }, + { + "epoch": 0.8792710706150342, + "grad_norm": 0.3261202573776245, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 386 + }, + { + "epoch": 0.8815489749430524, + "grad_norm": 0.31908831000328064, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 387 + }, + { + "epoch": 0.8838268792710706, + "grad_norm": 0.3441467583179474, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 388 + }, + { + "epoch": 0.8861047835990888, + "grad_norm": 0.3102405071258545, + "learning_rate": 1e-06, + "loss": 0.07, + "step": 389 + }, + { + "epoch": 0.8883826879271071, + "grad_norm": 0.3471468389034271, + "learning_rate": 1e-06, + "loss": 0.0705, + "step": 390 + }, + { + "epoch": 0.8906605922551253, + "grad_norm": 0.31879404187202454, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 391 + }, + { + "epoch": 0.8929384965831435, + "grad_norm": 0.31299784779548645, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 392 + }, + { + "epoch": 0.8952164009111617, + "grad_norm": 0.3419700264930725, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 393 + }, + { + "epoch": 0.89749430523918, + "grad_norm": 0.3235711455345154, + "learning_rate": 1e-06, + "loss": 0.0694, + "step": 394 + }, + { + "epoch": 0.8997722095671982, + "grad_norm": 0.3626854419708252, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 395 + }, + { + "epoch": 0.9020501138952164, + "grad_norm": 0.36147570610046387, + "learning_rate": 1e-06, + "loss": 0.0715, + "step": 396 + }, + { + "epoch": 0.9043280182232346, + "grad_norm": 0.32112476229667664, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 397 + }, + { + "epoch": 0.9066059225512528, + "grad_norm": 0.33262965083122253, + "learning_rate": 1e-06, + "loss": 0.0708, + "step": 398 + }, + { + "epoch": 0.908883826879271, + "grad_norm": 0.34221151471138, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 399 + }, + { + "epoch": 0.9111617312072893, + "grad_norm": 0.3437449634075165, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 400 + }, + { + "epoch": 0.9134396355353075, + "grad_norm": 0.35348671674728394, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 401 + }, + { + "epoch": 0.9157175398633257, + "grad_norm": 0.3469555675983429, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 402 + }, + { + "epoch": 0.9179954441913439, + "grad_norm": 0.36037176847457886, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 403 + }, + { + "epoch": 0.9202733485193622, + "grad_norm": 0.35958054661750793, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 404 + }, + { + "epoch": 0.9225512528473804, + "grad_norm": 0.32297489047050476, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 405 + }, + { + "epoch": 0.9248291571753986, + "grad_norm": 0.33972153067588806, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 406 + }, + { + "epoch": 0.9271070615034168, + "grad_norm": 0.36468371748924255, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 407 + }, + { + "epoch": 0.929384965831435, + "grad_norm": 0.3498111665248871, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 408 + }, + { + "epoch": 0.9316628701594533, + "grad_norm": 0.33355921506881714, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 409 + }, + { + "epoch": 0.9339407744874715, + "grad_norm": 0.3066707253456116, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 410 + }, + { + "epoch": 0.9362186788154897, + "grad_norm": 0.4638671278953552, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 411 + }, + { + "epoch": 0.9384965831435079, + "grad_norm": 0.3198438286781311, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 412 + }, + { + "epoch": 0.9407744874715261, + "grad_norm": 0.3194102346897125, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 413 + }, + { + "epoch": 0.9430523917995444, + "grad_norm": 0.31611520051956177, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 414 + }, + { + "epoch": 0.9453302961275627, + "grad_norm": 0.36651939153671265, + "learning_rate": 1e-06, + "loss": 0.0699, + "step": 415 + }, + { + "epoch": 0.9476082004555809, + "grad_norm": 0.3427932858467102, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 416 + }, + { + "epoch": 0.9498861047835991, + "grad_norm": 0.3349170982837677, + "learning_rate": 1e-06, + "loss": 0.0712, + "step": 417 + }, + { + "epoch": 0.9521640091116174, + "grad_norm": 0.3443504571914673, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 418 + }, + { + "epoch": 0.9544419134396356, + "grad_norm": 0.3236871659755707, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 419 + }, + { + "epoch": 0.9567198177676538, + "grad_norm": 0.3143421411514282, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 420 + }, + { + "epoch": 0.958997722095672, + "grad_norm": 0.32714375853538513, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 421 + }, + { + "epoch": 0.9612756264236902, + "grad_norm": 0.31957992911338806, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 422 + }, + { + "epoch": 0.9635535307517085, + "grad_norm": 0.36437085270881653, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 423 + }, + { + "epoch": 0.9658314350797267, + "grad_norm": 0.32506945729255676, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 424 + }, + { + "epoch": 0.9681093394077449, + "grad_norm": 0.3341188132762909, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 425 + }, + { + "epoch": 0.9703872437357631, + "grad_norm": 0.36812299489974976, + "learning_rate": 1e-06, + "loss": 0.0695, + "step": 426 + }, + { + "epoch": 0.9726651480637813, + "grad_norm": 0.321887344121933, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 427 + }, + { + "epoch": 0.9749430523917996, + "grad_norm": 0.3227898180484772, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 428 + }, + { + "epoch": 0.9772209567198178, + "grad_norm": 0.3533880412578583, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 429 + }, + { + "epoch": 0.979498861047836, + "grad_norm": 0.3422560691833496, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 430 + }, + { + "epoch": 0.9817767653758542, + "grad_norm": 0.3354332149028778, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 431 + }, + { + "epoch": 0.9840546697038725, + "grad_norm": 0.34125322103500366, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 432 + }, + { + "epoch": 0.9863325740318907, + "grad_norm": 0.35332202911376953, + "learning_rate": 1e-06, + "loss": 0.0678, + "step": 433 + }, + { + "epoch": 0.9886104783599089, + "grad_norm": 0.36115190386772156, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 434 + }, + { + "epoch": 0.9908883826879271, + "grad_norm": 0.3293335437774658, + "learning_rate": 1e-06, + "loss": 0.0707, + "step": 435 + }, + { + "epoch": 0.9931662870159453, + "grad_norm": 0.3337555527687073, + "learning_rate": 1e-06, + "loss": 0.0678, + "step": 436 + }, + { + "epoch": 0.9954441913439636, + "grad_norm": 0.3095809519290924, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 437 + }, + { + "epoch": 0.9977220956719818, + "grad_norm": 0.33177903294563293, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 438 + }, + { + "epoch": 1.0, + "grad_norm": 0.3388390839099884, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 439 + }, + { + "epoch": 1.0022779043280183, + "grad_norm": 0.30988579988479614, + "learning_rate": 1e-06, + "loss": 0.0688, + "step": 440 + }, + { + "epoch": 1.0045558086560364, + "grad_norm": 0.3240199089050293, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 441 + }, + { + "epoch": 1.0068337129840548, + "grad_norm": 0.3264000117778778, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 442 + }, + { + "epoch": 1.0091116173120729, + "grad_norm": 0.3521413505077362, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 443 + }, + { + "epoch": 1.0113895216400912, + "grad_norm": 0.392244428396225, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 444 + }, + { + "epoch": 1.0136674259681093, + "grad_norm": 0.3147774636745453, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 445 + }, + { + "epoch": 1.0159453302961277, + "grad_norm": 0.29381468892097473, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 446 + }, + { + "epoch": 1.0182232346241458, + "grad_norm": 0.3181336522102356, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 447 + }, + { + "epoch": 1.020501138952164, + "grad_norm": 0.35800236463546753, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 448 + }, + { + "epoch": 1.0227790432801822, + "grad_norm": 0.35843002796173096, + "learning_rate": 1e-06, + "loss": 0.0699, + "step": 449 + }, + { + "epoch": 1.0250569476082005, + "grad_norm": 0.31250807642936707, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 450 + }, + { + "epoch": 1.0273348519362187, + "grad_norm": 0.3343101739883423, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 451 + }, + { + "epoch": 1.029612756264237, + "grad_norm": 0.35841140151023865, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 452 + }, + { + "epoch": 1.031890660592255, + "grad_norm": 0.3154529333114624, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 453 + }, + { + "epoch": 1.0341685649202734, + "grad_norm": 0.324746310710907, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 454 + }, + { + "epoch": 1.0364464692482915, + "grad_norm": 0.3360418677330017, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 455 + }, + { + "epoch": 1.0387243735763099, + "grad_norm": 0.33904778957366943, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 456 + }, + { + "epoch": 1.041002277904328, + "grad_norm": 0.35387182235717773, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 457 + }, + { + "epoch": 1.0432801822323463, + "grad_norm": 0.37013527750968933, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 458 + }, + { + "epoch": 1.0455580865603644, + "grad_norm": 0.3373245596885681, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 459 + }, + { + "epoch": 1.0478359908883828, + "grad_norm": 0.33496782183647156, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 460 + }, + { + "epoch": 1.0501138952164009, + "grad_norm": 0.423818439245224, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 461 + }, + { + "epoch": 1.0523917995444192, + "grad_norm": 0.34197914600372314, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 462 + }, + { + "epoch": 1.0546697038724373, + "grad_norm": 0.32195019721984863, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 463 + }, + { + "epoch": 1.0569476082004556, + "grad_norm": 0.31621792912483215, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 464 + }, + { + "epoch": 1.0592255125284737, + "grad_norm": 0.3677210807800293, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 465 + }, + { + "epoch": 1.061503416856492, + "grad_norm": 0.3999234437942505, + "learning_rate": 1e-06, + "loss": 0.069, + "step": 466 + }, + { + "epoch": 1.0637813211845102, + "grad_norm": 0.38259968161582947, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 467 + }, + { + "epoch": 1.0660592255125285, + "grad_norm": 0.3638353645801544, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 468 + }, + { + "epoch": 1.0683371298405466, + "grad_norm": 0.3442877233028412, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 469 + }, + { + "epoch": 1.070615034168565, + "grad_norm": 0.42925605177879333, + "learning_rate": 1e-06, + "loss": 0.0709, + "step": 470 + }, + { + "epoch": 1.072892938496583, + "grad_norm": 0.39095544815063477, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 471 + }, + { + "epoch": 1.0751708428246014, + "grad_norm": 0.35640642046928406, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 472 + }, + { + "epoch": 1.0774487471526195, + "grad_norm": 0.347804456949234, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 473 + }, + { + "epoch": 1.0797266514806378, + "grad_norm": 0.37211310863494873, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 474 + }, + { + "epoch": 1.082004555808656, + "grad_norm": 0.335788756608963, + "learning_rate": 1e-06, + "loss": 0.0695, + "step": 475 + }, + { + "epoch": 1.0842824601366743, + "grad_norm": 0.30532708764076233, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 476 + }, + { + "epoch": 1.0865603644646924, + "grad_norm": 0.3195244371891022, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 477 + }, + { + "epoch": 1.0888382687927107, + "grad_norm": 0.4001767635345459, + "learning_rate": 1e-06, + "loss": 0.069, + "step": 478 + }, + { + "epoch": 1.0911161731207288, + "grad_norm": 0.3229754865169525, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 479 + }, + { + "epoch": 1.0933940774487472, + "grad_norm": 0.3560506999492645, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 480 + }, + { + "epoch": 1.0956719817767653, + "grad_norm": 0.3412211239337921, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 481 + }, + { + "epoch": 1.0979498861047836, + "grad_norm": 0.3144529163837433, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 482 + }, + { + "epoch": 1.1002277904328017, + "grad_norm": 0.33026495575904846, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 483 + }, + { + "epoch": 1.10250569476082, + "grad_norm": 0.33904582262039185, + "learning_rate": 1e-06, + "loss": 0.0693, + "step": 484 + }, + { + "epoch": 1.1047835990888384, + "grad_norm": 0.31689393520355225, + "learning_rate": 1e-06, + "loss": 0.0696, + "step": 485 + }, + { + "epoch": 1.1070615034168565, + "grad_norm": 0.3543938994407654, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 486 + }, + { + "epoch": 1.1093394077448746, + "grad_norm": 0.3505360186100006, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 487 + }, + { + "epoch": 1.111617312072893, + "grad_norm": 0.3473118543624878, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 488 + }, + { + "epoch": 1.1138952164009113, + "grad_norm": 0.4074588418006897, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 489 + }, + { + "epoch": 1.1161731207289294, + "grad_norm": 0.3068782091140747, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 490 + }, + { + "epoch": 1.1184510250569477, + "grad_norm": 0.3224482536315918, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 491 + }, + { + "epoch": 1.1207289293849658, + "grad_norm": 0.33763933181762695, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 492 + }, + { + "epoch": 1.1230068337129842, + "grad_norm": 0.33450332283973694, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 493 + }, + { + "epoch": 1.1252847380410023, + "grad_norm": 0.3352438509464264, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 494 + }, + { + "epoch": 1.1275626423690206, + "grad_norm": 0.304317444562912, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 495 + }, + { + "epoch": 1.1298405466970387, + "grad_norm": 0.3272012770175934, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 496 + }, + { + "epoch": 1.132118451025057, + "grad_norm": 0.3104042410850525, + "learning_rate": 1e-06, + "loss": 0.069, + "step": 497 + }, + { + "epoch": 1.1343963553530751, + "grad_norm": 0.301382839679718, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 498 + }, + { + "epoch": 1.1366742596810935, + "grad_norm": 0.3357836604118347, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 499 + }, + { + "epoch": 1.1389521640091116, + "grad_norm": 0.36598333716392517, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 500 + }, + { + "epoch": 1.14123006833713, + "grad_norm": 0.3720233142375946, + "learning_rate": 1e-06, + "loss": 0.0706, + "step": 501 + }, + { + "epoch": 1.143507972665148, + "grad_norm": 0.3575650453567505, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 502 + }, + { + "epoch": 1.1457858769931664, + "grad_norm": 0.32442477345466614, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 503 + }, + { + "epoch": 1.1480637813211845, + "grad_norm": 0.30793291330337524, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 504 + }, + { + "epoch": 1.1503416856492028, + "grad_norm": 0.333222895860672, + "learning_rate": 1e-06, + "loss": 0.0704, + "step": 505 + }, + { + "epoch": 1.152619589977221, + "grad_norm": 0.3394605815410614, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 506 + }, + { + "epoch": 1.1548974943052392, + "grad_norm": 0.3398108184337616, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 507 + }, + { + "epoch": 1.1571753986332574, + "grad_norm": 0.3241231441497803, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 508 + }, + { + "epoch": 1.1594533029612757, + "grad_norm": 0.34561964869499207, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 509 + }, + { + "epoch": 1.1617312072892938, + "grad_norm": 0.362251877784729, + "learning_rate": 1e-06, + "loss": 0.0671, + "step": 510 + }, + { + "epoch": 1.1640091116173121, + "grad_norm": 0.33822059631347656, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 511 + }, + { + "epoch": 1.1662870159453302, + "grad_norm": 0.3024541735649109, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 512 + }, + { + "epoch": 1.1685649202733486, + "grad_norm": 0.3234706521034241, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 513 + }, + { + "epoch": 1.1708428246013667, + "grad_norm": 0.3673495352268219, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 514 + }, + { + "epoch": 1.173120728929385, + "grad_norm": 0.35112661123275757, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 515 + }, + { + "epoch": 1.1753986332574031, + "grad_norm": 0.3200247585773468, + "learning_rate": 1e-06, + "loss": 0.0697, + "step": 516 + }, + { + "epoch": 1.1776765375854215, + "grad_norm": 0.3429282009601593, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 517 + }, + { + "epoch": 1.1799544419134396, + "grad_norm": 0.38209104537963867, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 518 + }, + { + "epoch": 1.182232346241458, + "grad_norm": 0.33101147413253784, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 519 + }, + { + "epoch": 1.184510250569476, + "grad_norm": 0.31255191564559937, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 520 + }, + { + "epoch": 1.1867881548974943, + "grad_norm": 0.3177628219127655, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 521 + }, + { + "epoch": 1.1890660592255125, + "grad_norm": 0.3393605649471283, + "learning_rate": 1e-06, + "loss": 0.0689, + "step": 522 + }, + { + "epoch": 1.1913439635535308, + "grad_norm": 0.3224415183067322, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 523 + }, + { + "epoch": 1.193621867881549, + "grad_norm": 0.3364848494529724, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 524 + }, + { + "epoch": 1.1958997722095672, + "grad_norm": 0.3608461618423462, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 525 + }, + { + "epoch": 1.1981776765375853, + "grad_norm": 0.35563814640045166, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 526 + }, + { + "epoch": 1.2004555808656037, + "grad_norm": 0.33495691418647766, + "learning_rate": 1e-06, + "loss": 0.0688, + "step": 527 + }, + { + "epoch": 1.2027334851936218, + "grad_norm": 0.308938205242157, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 528 + }, + { + "epoch": 1.20501138952164, + "grad_norm": 0.314145028591156, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 529 + }, + { + "epoch": 1.2072892938496582, + "grad_norm": 0.3132685720920563, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 530 + }, + { + "epoch": 1.2095671981776766, + "grad_norm": 0.30664360523223877, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 531 + }, + { + "epoch": 1.2118451025056949, + "grad_norm": 0.3201133608818054, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 532 + }, + { + "epoch": 1.214123006833713, + "grad_norm": 0.34432342648506165, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 533 + }, + { + "epoch": 1.216400911161731, + "grad_norm": 0.344078004360199, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 534 + }, + { + "epoch": 1.2186788154897494, + "grad_norm": 0.3397848904132843, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 535 + }, + { + "epoch": 1.2209567198177678, + "grad_norm": 0.36217576265335083, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 536 + }, + { + "epoch": 1.2232346241457859, + "grad_norm": 0.3311270475387573, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 537 + }, + { + "epoch": 1.225512528473804, + "grad_norm": 0.32769450545310974, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 538 + }, + { + "epoch": 1.2277904328018223, + "grad_norm": 0.3352331221103668, + "learning_rate": 1e-06, + "loss": 0.07, + "step": 539 + }, + { + "epoch": 1.2300683371298406, + "grad_norm": 0.31901130080223083, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 540 + }, + { + "epoch": 1.2323462414578588, + "grad_norm": 0.3207155466079712, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 541 + }, + { + "epoch": 1.2346241457858769, + "grad_norm": 0.2960147261619568, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 542 + }, + { + "epoch": 1.2369020501138952, + "grad_norm": 0.29627591371536255, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 543 + }, + { + "epoch": 1.2391799544419135, + "grad_norm": 0.3241105377674103, + "learning_rate": 1e-06, + "loss": 0.0701, + "step": 544 + }, + { + "epoch": 1.2414578587699316, + "grad_norm": 0.326617956161499, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 545 + }, + { + "epoch": 1.24373576309795, + "grad_norm": 0.33163151144981384, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 546 + }, + { + "epoch": 1.246013667425968, + "grad_norm": 0.3241666555404663, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 547 + }, + { + "epoch": 1.2482915717539864, + "grad_norm": 0.31635862588882446, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 548 + }, + { + "epoch": 1.2505694760820045, + "grad_norm": 0.3181557357311249, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 549 + }, + { + "epoch": 1.2528473804100229, + "grad_norm": 0.31517043709754944, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 550 + }, + { + "epoch": 1.255125284738041, + "grad_norm": 0.34369298815727234, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 551 + }, + { + "epoch": 1.2574031890660593, + "grad_norm": 0.3312387764453888, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 552 + }, + { + "epoch": 1.2596810933940774, + "grad_norm": 0.36193200945854187, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 553 + }, + { + "epoch": 1.2619589977220957, + "grad_norm": 0.29782605171203613, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 554 + }, + { + "epoch": 1.2642369020501139, + "grad_norm": 0.3361304998397827, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 555 + }, + { + "epoch": 1.2665148063781322, + "grad_norm": 0.30416664481163025, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 556 + }, + { + "epoch": 1.2687927107061503, + "grad_norm": 0.3037481904029846, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 557 + }, + { + "epoch": 1.2710706150341686, + "grad_norm": 0.3138207197189331, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 558 + }, + { + "epoch": 1.2733485193621867, + "grad_norm": 0.3223991096019745, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 559 + }, + { + "epoch": 1.275626423690205, + "grad_norm": 0.317121684551239, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 560 + }, + { + "epoch": 1.2779043280182232, + "grad_norm": 0.3353293836116791, + "learning_rate": 1e-06, + "loss": 0.0686, + "step": 561 + }, + { + "epoch": 1.2801822323462415, + "grad_norm": 0.31532707810401917, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 562 + }, + { + "epoch": 1.2824601366742596, + "grad_norm": 0.350869745016098, + "learning_rate": 1e-06, + "loss": 0.0703, + "step": 563 + }, + { + "epoch": 1.284738041002278, + "grad_norm": 0.32417574524879456, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 564 + }, + { + "epoch": 1.287015945330296, + "grad_norm": 0.32570958137512207, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 565 + }, + { + "epoch": 1.2892938496583144, + "grad_norm": 0.33573219180107117, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 566 + }, + { + "epoch": 1.2915717539863325, + "grad_norm": 0.31365326046943665, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 567 + }, + { + "epoch": 1.2938496583143508, + "grad_norm": 0.312673956155777, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 568 + }, + { + "epoch": 1.296127562642369, + "grad_norm": 0.3033856153488159, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 569 + }, + { + "epoch": 1.2984054669703873, + "grad_norm": 0.3380340039730072, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 570 + }, + { + "epoch": 1.3006833712984054, + "grad_norm": 0.3312075734138489, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 571 + }, + { + "epoch": 1.3029612756264237, + "grad_norm": 0.29615795612335205, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 572 + }, + { + "epoch": 1.3052391799544418, + "grad_norm": 0.32707855105400085, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 573 + }, + { + "epoch": 1.3075170842824602, + "grad_norm": 0.35538920760154724, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 574 + }, + { + "epoch": 1.3097949886104785, + "grad_norm": 0.5136793255805969, + "learning_rate": 1e-06, + "loss": 0.0758, + "step": 575 + }, + { + "epoch": 1.3120728929384966, + "grad_norm": 0.32979828119277954, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 576 + }, + { + "epoch": 1.3143507972665147, + "grad_norm": 0.3334548771381378, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 577 + }, + { + "epoch": 1.316628701594533, + "grad_norm": 0.32665038108825684, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 578 + }, + { + "epoch": 1.3189066059225514, + "grad_norm": 0.31793147325515747, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 579 + }, + { + "epoch": 1.3211845102505695, + "grad_norm": 0.295227974653244, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 580 + }, + { + "epoch": 1.3234624145785876, + "grad_norm": 0.35839083790779114, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 581 + }, + { + "epoch": 1.325740318906606, + "grad_norm": 0.3305734395980835, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 582 + }, + { + "epoch": 1.3280182232346243, + "grad_norm": 0.3287615180015564, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 583 + }, + { + "epoch": 1.3302961275626424, + "grad_norm": 0.3139578104019165, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 584 + }, + { + "epoch": 1.3325740318906605, + "grad_norm": 0.35336899757385254, + "learning_rate": 1e-06, + "loss": 0.068, + "step": 585 + }, + { + "epoch": 1.3348519362186788, + "grad_norm": 0.3174915313720703, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 586 + }, + { + "epoch": 1.3371298405466971, + "grad_norm": 0.3224445879459381, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 587 + }, + { + "epoch": 1.3394077448747153, + "grad_norm": 0.33658137917518616, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 588 + }, + { + "epoch": 1.3416856492027334, + "grad_norm": 0.35723060369491577, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 589 + }, + { + "epoch": 1.3439635535307517, + "grad_norm": 0.3076712191104889, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 590 + }, + { + "epoch": 1.34624145785877, + "grad_norm": 0.3254822790622711, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 591 + }, + { + "epoch": 1.3485193621867881, + "grad_norm": 0.31978049874305725, + "learning_rate": 1e-06, + "loss": 0.0671, + "step": 592 + }, + { + "epoch": 1.3507972665148062, + "grad_norm": 0.36066919565200806, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 593 + }, + { + "epoch": 1.3530751708428246, + "grad_norm": 0.39579272270202637, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 594 + }, + { + "epoch": 1.355353075170843, + "grad_norm": 0.3199502229690552, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 595 + }, + { + "epoch": 1.357630979498861, + "grad_norm": 0.3178679049015045, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 596 + }, + { + "epoch": 1.3599088838268791, + "grad_norm": 0.31722742319107056, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 597 + }, + { + "epoch": 1.3621867881548975, + "grad_norm": 0.32186686992645264, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 598 + }, + { + "epoch": 1.3644646924829158, + "grad_norm": 0.3357408940792084, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 599 + }, + { + "epoch": 1.366742596810934, + "grad_norm": 0.33618712425231934, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 600 + }, + { + "epoch": 1.3690205011389522, + "grad_norm": 0.3645150065422058, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 601 + }, + { + "epoch": 1.3712984054669703, + "grad_norm": 0.33359652757644653, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 602 + }, + { + "epoch": 1.3735763097949887, + "grad_norm": 0.35728731751441956, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 603 + }, + { + "epoch": 1.3758542141230068, + "grad_norm": 0.30385470390319824, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 604 + }, + { + "epoch": 1.3781321184510251, + "grad_norm": 0.35180899500846863, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 605 + }, + { + "epoch": 1.3804100227790432, + "grad_norm": 0.37558212876319885, + "learning_rate": 1e-06, + "loss": 0.0681, + "step": 606 + }, + { + "epoch": 1.3826879271070616, + "grad_norm": 0.3561190664768219, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 607 + }, + { + "epoch": 1.3849658314350797, + "grad_norm": 0.3426625430583954, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 608 + }, + { + "epoch": 1.387243735763098, + "grad_norm": 0.38857758045196533, + "learning_rate": 1e-06, + "loss": 0.0702, + "step": 609 + }, + { + "epoch": 1.3895216400911161, + "grad_norm": 0.3672369122505188, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 610 + }, + { + "epoch": 1.3917995444191344, + "grad_norm": 0.3399842381477356, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 611 + }, + { + "epoch": 1.3940774487471526, + "grad_norm": 0.32340207695961, + "learning_rate": 1e-06, + "loss": 0.0663, + "step": 612 + }, + { + "epoch": 1.396355353075171, + "grad_norm": 0.33630892634391785, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 613 + }, + { + "epoch": 1.398633257403189, + "grad_norm": 0.31638872623443604, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 614 + }, + { + "epoch": 1.4009111617312073, + "grad_norm": 0.35047978162765503, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 615 + }, + { + "epoch": 1.4031890660592254, + "grad_norm": 0.3452295958995819, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 616 + }, + { + "epoch": 1.4054669703872438, + "grad_norm": 0.31333431601524353, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 617 + }, + { + "epoch": 1.4077448747152619, + "grad_norm": 0.3211308419704437, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 618 + }, + { + "epoch": 1.4100227790432802, + "grad_norm": 0.31560584902763367, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 619 + }, + { + "epoch": 1.4123006833712983, + "grad_norm": 0.3175780177116394, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 620 + }, + { + "epoch": 1.4145785876993167, + "grad_norm": 0.3598182797431946, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 621 + }, + { + "epoch": 1.416856492027335, + "grad_norm": 0.3456338942050934, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 622 + }, + { + "epoch": 1.419134396355353, + "grad_norm": 0.3167535364627838, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 623 + }, + { + "epoch": 1.4214123006833712, + "grad_norm": 0.34159666299819946, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 624 + }, + { + "epoch": 1.4236902050113895, + "grad_norm": 0.32574594020843506, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 625 + }, + { + "epoch": 1.4259681093394079, + "grad_norm": 0.3237164318561554, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 626 + }, + { + "epoch": 1.428246013667426, + "grad_norm": 0.3209851384162903, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 627 + }, + { + "epoch": 1.430523917995444, + "grad_norm": 0.3261626958847046, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 628 + }, + { + "epoch": 1.4328018223234624, + "grad_norm": 0.386074036359787, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 629 + }, + { + "epoch": 1.4350797266514808, + "grad_norm": 0.34562966227531433, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 630 + }, + { + "epoch": 1.4373576309794989, + "grad_norm": 0.33326995372772217, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 631 + }, + { + "epoch": 1.439635535307517, + "grad_norm": 0.34407275915145874, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 632 + }, + { + "epoch": 1.4419134396355353, + "grad_norm": 0.32634437084198, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 633 + }, + { + "epoch": 1.4441913439635536, + "grad_norm": 0.32662612199783325, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 634 + }, + { + "epoch": 1.4464692482915718, + "grad_norm": 0.3567451238632202, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 635 + }, + { + "epoch": 1.4487471526195899, + "grad_norm": 0.3363933563232422, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 636 + }, + { + "epoch": 1.4510250569476082, + "grad_norm": 0.3893454074859619, + "learning_rate": 1e-06, + "loss": 0.0663, + "step": 637 + }, + { + "epoch": 1.4533029612756265, + "grad_norm": 0.3028440475463867, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 638 + }, + { + "epoch": 1.4555808656036446, + "grad_norm": 0.33057036995887756, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 639 + }, + { + "epoch": 1.4578587699316627, + "grad_norm": 0.340852290391922, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 640 + }, + { + "epoch": 1.460136674259681, + "grad_norm": 0.31983551383018494, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 641 + }, + { + "epoch": 1.4624145785876994, + "grad_norm": 0.3343818485736847, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 642 + }, + { + "epoch": 1.4646924829157175, + "grad_norm": 0.28896236419677734, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 643 + }, + { + "epoch": 1.4669703872437356, + "grad_norm": 0.3149277865886688, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 644 + }, + { + "epoch": 1.469248291571754, + "grad_norm": 0.31318753957748413, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 645 + }, + { + "epoch": 1.4715261958997723, + "grad_norm": 0.29574984312057495, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 646 + }, + { + "epoch": 1.4738041002277904, + "grad_norm": 0.3432856798171997, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 647 + }, + { + "epoch": 1.4760820045558087, + "grad_norm": 0.30336350202560425, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 648 + }, + { + "epoch": 1.4783599088838268, + "grad_norm": 0.30616649985313416, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 649 + }, + { + "epoch": 1.4806378132118452, + "grad_norm": 0.32289063930511475, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 650 + }, + { + "epoch": 1.4829157175398633, + "grad_norm": 0.331571102142334, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 651 + }, + { + "epoch": 1.4851936218678816, + "grad_norm": 0.35566529631614685, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 652 + }, + { + "epoch": 1.4874715261958997, + "grad_norm": 0.3232436180114746, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 653 + }, + { + "epoch": 1.489749430523918, + "grad_norm": 0.32418763637542725, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 654 + }, + { + "epoch": 1.4920273348519362, + "grad_norm": 0.3313868045806885, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 655 + }, + { + "epoch": 1.4943052391799545, + "grad_norm": 0.33750343322753906, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 656 + }, + { + "epoch": 1.4965831435079726, + "grad_norm": 0.31327584385871887, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 657 + }, + { + "epoch": 1.498861047835991, + "grad_norm": 0.3157743215560913, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 658 + }, + { + "epoch": 1.501138952164009, + "grad_norm": 0.3371293842792511, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 659 + }, + { + "epoch": 1.5034168564920274, + "grad_norm": 0.3326658308506012, + "learning_rate": 1e-06, + "loss": 0.0671, + "step": 660 + }, + { + "epoch": 1.5056947608200457, + "grad_norm": 0.31945574283599854, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 661 + }, + { + "epoch": 1.5079726651480638, + "grad_norm": 0.34628620743751526, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 662 + }, + { + "epoch": 1.510250569476082, + "grad_norm": 0.34882378578186035, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 663 + }, + { + "epoch": 1.5125284738041003, + "grad_norm": 0.33263957500457764, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 664 + }, + { + "epoch": 1.5148063781321186, + "grad_norm": 0.3372634947299957, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 665 + }, + { + "epoch": 1.5170842824601367, + "grad_norm": 0.33056479692459106, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 666 + }, + { + "epoch": 1.5193621867881548, + "grad_norm": 0.32352063059806824, + "learning_rate": 1e-06, + "loss": 0.0663, + "step": 667 + }, + { + "epoch": 1.5216400911161732, + "grad_norm": 0.323993444442749, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 668 + }, + { + "epoch": 1.5239179954441915, + "grad_norm": 0.343328595161438, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 669 + }, + { + "epoch": 1.5261958997722096, + "grad_norm": 0.3183234632015228, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 670 + }, + { + "epoch": 1.5284738041002277, + "grad_norm": 0.3672555983066559, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 671 + }, + { + "epoch": 1.530751708428246, + "grad_norm": 0.3240128755569458, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 672 + }, + { + "epoch": 1.5330296127562644, + "grad_norm": 0.32380229234695435, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 673 + }, + { + "epoch": 1.5353075170842825, + "grad_norm": 0.30388766527175903, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 674 + }, + { + "epoch": 1.5375854214123006, + "grad_norm": 0.3284044861793518, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 675 + }, + { + "epoch": 1.539863325740319, + "grad_norm": 0.3362218141555786, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 676 + }, + { + "epoch": 1.5421412300683373, + "grad_norm": 0.33002832531929016, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 677 + }, + { + "epoch": 1.5444191343963554, + "grad_norm": 0.3419937193393707, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 678 + }, + { + "epoch": 1.5466970387243735, + "grad_norm": 0.3203066289424896, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 679 + }, + { + "epoch": 1.5489749430523918, + "grad_norm": 0.3255561590194702, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 680 + }, + { + "epoch": 1.5512528473804101, + "grad_norm": 0.330700159072876, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 681 + }, + { + "epoch": 1.5535307517084282, + "grad_norm": 0.3099619746208191, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 682 + }, + { + "epoch": 1.5558086560364464, + "grad_norm": 0.3167722225189209, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 683 + }, + { + "epoch": 1.5580865603644647, + "grad_norm": 0.3692430257797241, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 684 + }, + { + "epoch": 1.560364464692483, + "grad_norm": 0.35819220542907715, + "learning_rate": 1e-06, + "loss": 0.0663, + "step": 685 + }, + { + "epoch": 1.5626423690205011, + "grad_norm": 0.30240750312805176, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 686 + }, + { + "epoch": 1.5649202733485192, + "grad_norm": 0.3754892647266388, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 687 + }, + { + "epoch": 1.5671981776765376, + "grad_norm": 0.34892264008522034, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 688 + }, + { + "epoch": 1.569476082004556, + "grad_norm": 0.3233955502510071, + "learning_rate": 1e-06, + "loss": 0.0698, + "step": 689 + }, + { + "epoch": 1.571753986332574, + "grad_norm": 0.2941535413265228, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 690 + }, + { + "epoch": 1.5740318906605921, + "grad_norm": 0.321943461894989, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 691 + }, + { + "epoch": 1.5763097949886105, + "grad_norm": 0.30693188309669495, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 692 + }, + { + "epoch": 1.5785876993166288, + "grad_norm": 0.31709933280944824, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 693 + }, + { + "epoch": 1.580865603644647, + "grad_norm": 0.3240492343902588, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 694 + }, + { + "epoch": 1.583143507972665, + "grad_norm": 0.30294445157051086, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 695 + }, + { + "epoch": 1.5854214123006833, + "grad_norm": 0.374569833278656, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 696 + }, + { + "epoch": 1.5876993166287017, + "grad_norm": 0.3403237462043762, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 697 + }, + { + "epoch": 1.5899772209567198, + "grad_norm": 0.36598604917526245, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 698 + }, + { + "epoch": 1.592255125284738, + "grad_norm": 0.3391307592391968, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 699 + }, + { + "epoch": 1.5945330296127562, + "grad_norm": 0.3274058699607849, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 700 + }, + { + "epoch": 1.5968109339407746, + "grad_norm": 0.3924366533756256, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 701 + }, + { + "epoch": 1.5990888382687927, + "grad_norm": 0.3548175096511841, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 702 + }, + { + "epoch": 1.6013667425968108, + "grad_norm": 0.39162853360176086, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 703 + }, + { + "epoch": 1.603644646924829, + "grad_norm": 0.36531442403793335, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 704 + }, + { + "epoch": 1.6059225512528474, + "grad_norm": 0.3528921902179718, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 705 + }, + { + "epoch": 1.6082004555808656, + "grad_norm": 0.36990809440612793, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 706 + }, + { + "epoch": 1.6104783599088837, + "grad_norm": 0.372173547744751, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 707 + }, + { + "epoch": 1.6127562642369022, + "grad_norm": 0.3457825481891632, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 708 + }, + { + "epoch": 1.6150341685649203, + "grad_norm": 0.32944124937057495, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 709 + }, + { + "epoch": 1.6173120728929384, + "grad_norm": 0.3494454324245453, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 710 + }, + { + "epoch": 1.6195899772209568, + "grad_norm": 0.3718607425689697, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 711 + }, + { + "epoch": 1.621867881548975, + "grad_norm": 0.34790903329849243, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 712 + }, + { + "epoch": 1.6241457858769932, + "grad_norm": 0.37122929096221924, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 713 + }, + { + "epoch": 1.6264236902050113, + "grad_norm": 0.3455367982387543, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 714 + }, + { + "epoch": 1.6287015945330297, + "grad_norm": 0.36324557662010193, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 715 + }, + { + "epoch": 1.630979498861048, + "grad_norm": 0.39690402150154114, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 716 + }, + { + "epoch": 1.633257403189066, + "grad_norm": 0.312059223651886, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 717 + }, + { + "epoch": 1.6355353075170842, + "grad_norm": 0.29946544766426086, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 718 + }, + { + "epoch": 1.6378132118451025, + "grad_norm": 0.34980976581573486, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 719 + }, + { + "epoch": 1.6400911161731209, + "grad_norm": 0.3351825475692749, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 720 + }, + { + "epoch": 1.642369020501139, + "grad_norm": 0.33597150444984436, + "learning_rate": 1e-06, + "loss": 0.0685, + "step": 721 + }, + { + "epoch": 1.644646924829157, + "grad_norm": 0.34510233998298645, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 722 + }, + { + "epoch": 1.6469248291571754, + "grad_norm": 0.31456127762794495, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 723 + }, + { + "epoch": 1.6492027334851938, + "grad_norm": 0.3021286427974701, + "learning_rate": 1e-06, + "loss": 0.0617, + "step": 724 + }, + { + "epoch": 1.6514806378132119, + "grad_norm": 0.30333489179611206, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 725 + }, + { + "epoch": 1.65375854214123, + "grad_norm": 0.32748571038246155, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 726 + }, + { + "epoch": 1.6560364464692483, + "grad_norm": 0.36798450350761414, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 727 + }, + { + "epoch": 1.6583143507972666, + "grad_norm": 0.3090701103210449, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 728 + }, + { + "epoch": 1.6605922551252847, + "grad_norm": 0.3357798755168915, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 729 + }, + { + "epoch": 1.6628701594533029, + "grad_norm": 0.31389063596725464, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 730 + }, + { + "epoch": 1.6651480637813212, + "grad_norm": 0.3659593462944031, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 731 + }, + { + "epoch": 1.6674259681093395, + "grad_norm": 0.3131271004676819, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 732 + }, + { + "epoch": 1.6697038724373576, + "grad_norm": 0.3102443814277649, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 733 + }, + { + "epoch": 1.6719817767653757, + "grad_norm": 0.3327702581882477, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 734 + }, + { + "epoch": 1.674259681093394, + "grad_norm": 0.3621436655521393, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 735 + }, + { + "epoch": 1.6765375854214124, + "grad_norm": 0.32711032032966614, + "learning_rate": 1e-06, + "loss": 0.0678, + "step": 736 + }, + { + "epoch": 1.6788154897494305, + "grad_norm": 0.3139934837818146, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 737 + }, + { + "epoch": 1.6810933940774486, + "grad_norm": 0.3027886152267456, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 738 + }, + { + "epoch": 1.683371298405467, + "grad_norm": 0.30135729908943176, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 739 + }, + { + "epoch": 1.6856492027334853, + "grad_norm": 0.33525145053863525, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 740 + }, + { + "epoch": 1.6879271070615034, + "grad_norm": 0.3143167495727539, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 741 + }, + { + "epoch": 1.6902050113895215, + "grad_norm": 0.30170121788978577, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 742 + }, + { + "epoch": 1.6924829157175398, + "grad_norm": 0.3353256285190582, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 743 + }, + { + "epoch": 1.6947608200455582, + "grad_norm": 0.305199533700943, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 744 + }, + { + "epoch": 1.6970387243735763, + "grad_norm": 0.3161783814430237, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 745 + }, + { + "epoch": 1.6993166287015944, + "grad_norm": 0.3063722848892212, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 746 + }, + { + "epoch": 1.7015945330296127, + "grad_norm": 0.3572700619697571, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 747 + }, + { + "epoch": 1.703872437357631, + "grad_norm": 0.317890465259552, + "learning_rate": 1e-06, + "loss": 0.0694, + "step": 748 + }, + { + "epoch": 1.7061503416856492, + "grad_norm": 0.347693532705307, + "learning_rate": 1e-06, + "loss": 0.0674, + "step": 749 + }, + { + "epoch": 1.7084282460136673, + "grad_norm": 0.37009432911872864, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 750 + }, + { + "epoch": 1.7107061503416856, + "grad_norm": 0.34441858530044556, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 751 + }, + { + "epoch": 1.712984054669704, + "grad_norm": 0.34099671244621277, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 752 + }, + { + "epoch": 1.715261958997722, + "grad_norm": 0.3261203169822693, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 753 + }, + { + "epoch": 1.7175398633257402, + "grad_norm": 0.3501361906528473, + "learning_rate": 1e-06, + "loss": 0.0691, + "step": 754 + }, + { + "epoch": 1.7198177676537585, + "grad_norm": 0.3067166209220886, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 755 + }, + { + "epoch": 1.7220956719817768, + "grad_norm": 0.3171209394931793, + "learning_rate": 1e-06, + "loss": 0.0684, + "step": 756 + }, + { + "epoch": 1.724373576309795, + "grad_norm": 0.3320958614349365, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 757 + }, + { + "epoch": 1.7266514806378133, + "grad_norm": 0.33798831701278687, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 758 + }, + { + "epoch": 1.7289293849658316, + "grad_norm": 0.3628637194633484, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 759 + }, + { + "epoch": 1.7312072892938497, + "grad_norm": 0.30694565176963806, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 760 + }, + { + "epoch": 1.7334851936218678, + "grad_norm": 0.34436050057411194, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 761 + }, + { + "epoch": 1.7357630979498861, + "grad_norm": 0.31241530179977417, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 762 + }, + { + "epoch": 1.7380410022779045, + "grad_norm": 0.33010122179985046, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 763 + }, + { + "epoch": 1.7403189066059226, + "grad_norm": 0.35218313336372375, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 764 + }, + { + "epoch": 1.7425968109339407, + "grad_norm": 0.3310188949108124, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 765 + }, + { + "epoch": 1.744874715261959, + "grad_norm": 0.31889525055885315, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 766 + }, + { + "epoch": 1.7471526195899774, + "grad_norm": 0.353817880153656, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 767 + }, + { + "epoch": 1.7494305239179955, + "grad_norm": 0.3174983561038971, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 768 + }, + { + "epoch": 1.7517084282460136, + "grad_norm": 0.3145601153373718, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 769 + }, + { + "epoch": 1.753986332574032, + "grad_norm": 0.3266806900501251, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 770 + }, + { + "epoch": 1.7562642369020502, + "grad_norm": 0.32695260643959045, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 771 + }, + { + "epoch": 1.7585421412300684, + "grad_norm": 0.3176910877227783, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 772 + }, + { + "epoch": 1.7608200455580865, + "grad_norm": 0.30198749899864197, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 773 + }, + { + "epoch": 1.7630979498861048, + "grad_norm": 0.32037508487701416, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 774 + }, + { + "epoch": 1.7653758542141231, + "grad_norm": 0.32997143268585205, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 775 + }, + { + "epoch": 1.7676537585421412, + "grad_norm": 0.3138270378112793, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 776 + }, + { + "epoch": 1.7699316628701594, + "grad_norm": 0.3312433063983917, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 777 + }, + { + "epoch": 1.7722095671981777, + "grad_norm": 0.30379700660705566, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 778 + }, + { + "epoch": 1.774487471526196, + "grad_norm": 0.38104745745658875, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 779 + }, + { + "epoch": 1.7767653758542141, + "grad_norm": 0.3453124463558197, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 780 + }, + { + "epoch": 1.7790432801822322, + "grad_norm": 0.31360694766044617, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 781 + }, + { + "epoch": 1.7813211845102506, + "grad_norm": 0.37559816241264343, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 782 + }, + { + "epoch": 1.783599088838269, + "grad_norm": 0.32602521777153015, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 783 + }, + { + "epoch": 1.785876993166287, + "grad_norm": 0.327021986246109, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 784 + }, + { + "epoch": 1.7881548974943051, + "grad_norm": 0.33992865681648254, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 785 + }, + { + "epoch": 1.7904328018223234, + "grad_norm": 0.34317806363105774, + "learning_rate": 1e-06, + "loss": 0.0687, + "step": 786 + }, + { + "epoch": 1.7927107061503418, + "grad_norm": 0.3103628158569336, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 787 + }, + { + "epoch": 1.79498861047836, + "grad_norm": 0.3204653561115265, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 788 + }, + { + "epoch": 1.797266514806378, + "grad_norm": 0.3239515423774719, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 789 + }, + { + "epoch": 1.7995444191343963, + "grad_norm": 0.3199343979358673, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 790 + }, + { + "epoch": 1.8018223234624147, + "grad_norm": 0.365479439496994, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 791 + }, + { + "epoch": 1.8041002277904328, + "grad_norm": 0.3533048927783966, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 792 + }, + { + "epoch": 1.8063781321184509, + "grad_norm": 0.3177263140678406, + "learning_rate": 1e-06, + "loss": 0.0676, + "step": 793 + }, + { + "epoch": 1.8086560364464692, + "grad_norm": 0.3009091317653656, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 794 + }, + { + "epoch": 1.8109339407744875, + "grad_norm": 0.310372531414032, + "learning_rate": 1e-06, + "loss": 0.0619, + "step": 795 + }, + { + "epoch": 1.8132118451025057, + "grad_norm": 0.2957143783569336, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 796 + }, + { + "epoch": 1.8154897494305238, + "grad_norm": 0.31243398785591125, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 797 + }, + { + "epoch": 1.817767653758542, + "grad_norm": 0.3182040750980377, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 798 + }, + { + "epoch": 1.8200455580865604, + "grad_norm": 0.34190985560417175, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 799 + }, + { + "epoch": 1.8223234624145785, + "grad_norm": 0.2959096431732178, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 800 + }, + { + "epoch": 1.8246013667425967, + "grad_norm": 0.3374524414539337, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 801 + }, + { + "epoch": 1.826879271070615, + "grad_norm": 0.32855015993118286, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 802 + }, + { + "epoch": 1.8291571753986333, + "grad_norm": 0.3250168561935425, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 803 + }, + { + "epoch": 1.8314350797266514, + "grad_norm": 0.33588096499443054, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 804 + }, + { + "epoch": 1.8337129840546698, + "grad_norm": 0.34796997904777527, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 805 + }, + { + "epoch": 1.835990888382688, + "grad_norm": 0.3319361209869385, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 806 + }, + { + "epoch": 1.8382687927107062, + "grad_norm": 0.3266584277153015, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 807 + }, + { + "epoch": 1.8405466970387243, + "grad_norm": 0.35344088077545166, + "learning_rate": 1e-06, + "loss": 0.067, + "step": 808 + }, + { + "epoch": 1.8428246013667426, + "grad_norm": 0.29383906722068787, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 809 + }, + { + "epoch": 1.845102505694761, + "grad_norm": 0.3131392300128937, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 810 + }, + { + "epoch": 1.847380410022779, + "grad_norm": 0.33933424949645996, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 811 + }, + { + "epoch": 1.8496583143507972, + "grad_norm": 0.3552645444869995, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 812 + }, + { + "epoch": 1.8519362186788155, + "grad_norm": 0.4089110493659973, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 813 + }, + { + "epoch": 1.8542141230068339, + "grad_norm": 0.30431970953941345, + "learning_rate": 1e-06, + "loss": 0.0683, + "step": 814 + }, + { + "epoch": 1.856492027334852, + "grad_norm": 0.3229494094848633, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 815 + }, + { + "epoch": 1.85876993166287, + "grad_norm": 0.30082717537879944, + "learning_rate": 1e-06, + "loss": 0.0667, + "step": 816 + }, + { + "epoch": 1.8610478359908884, + "grad_norm": 0.34094908833503723, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 817 + }, + { + "epoch": 1.8633257403189067, + "grad_norm": 0.3411218225955963, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 818 + }, + { + "epoch": 1.8656036446469249, + "grad_norm": 0.32742491364479065, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 819 + }, + { + "epoch": 1.867881548974943, + "grad_norm": 0.3249320983886719, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 820 + }, + { + "epoch": 1.8701594533029613, + "grad_norm": 0.31099623441696167, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 821 + }, + { + "epoch": 1.8724373576309796, + "grad_norm": 0.46357813477516174, + "learning_rate": 1e-06, + "loss": 0.0658, + "step": 822 + }, + { + "epoch": 1.8747152619589977, + "grad_norm": 0.3178175091743469, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 823 + }, + { + "epoch": 1.8769931662870158, + "grad_norm": 0.31006255745887756, + "learning_rate": 1e-06, + "loss": 0.0688, + "step": 824 + }, + { + "epoch": 1.8792710706150342, + "grad_norm": 0.3245089650154114, + "learning_rate": 1e-06, + "loss": 0.0672, + "step": 825 + }, + { + "epoch": 1.8815489749430525, + "grad_norm": 0.29895344376564026, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 826 + }, + { + "epoch": 1.8838268792710706, + "grad_norm": 0.32286185026168823, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 827 + }, + { + "epoch": 1.8861047835990887, + "grad_norm": 0.3141544461250305, + "learning_rate": 1e-06, + "loss": 0.0671, + "step": 828 + }, + { + "epoch": 1.888382687927107, + "grad_norm": 0.31435057520866394, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 829 + }, + { + "epoch": 1.8906605922551254, + "grad_norm": 0.3043149709701538, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 830 + }, + { + "epoch": 1.8929384965831435, + "grad_norm": 0.30732980370521545, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 831 + }, + { + "epoch": 1.8952164009111616, + "grad_norm": 0.3207799196243286, + "learning_rate": 1e-06, + "loss": 0.0614, + "step": 832 + }, + { + "epoch": 1.89749430523918, + "grad_norm": 0.3308825194835663, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 833 + }, + { + "epoch": 1.8997722095671983, + "grad_norm": 0.34850481152534485, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 834 + }, + { + "epoch": 1.9020501138952164, + "grad_norm": 0.3378564417362213, + "learning_rate": 1e-06, + "loss": 0.0617, + "step": 835 + }, + { + "epoch": 1.9043280182232345, + "grad_norm": 0.3291390836238861, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 836 + }, + { + "epoch": 1.9066059225512528, + "grad_norm": 0.33691149950027466, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 837 + }, + { + "epoch": 1.9088838268792712, + "grad_norm": 0.3159260153770447, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 838 + }, + { + "epoch": 1.9111617312072893, + "grad_norm": 0.35957998037338257, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 839 + }, + { + "epoch": 1.9134396355353074, + "grad_norm": 0.29190635681152344, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 840 + }, + { + "epoch": 1.9157175398633257, + "grad_norm": 0.317518025636673, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 841 + }, + { + "epoch": 1.917995444191344, + "grad_norm": 0.33885568380355835, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 842 + }, + { + "epoch": 1.9202733485193622, + "grad_norm": 0.34959676861763, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 843 + }, + { + "epoch": 1.9225512528473803, + "grad_norm": 0.4898427724838257, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 844 + }, + { + "epoch": 1.9248291571753986, + "grad_norm": 0.5298956632614136, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 845 + }, + { + "epoch": 1.927107061503417, + "grad_norm": 1.8848764896392822, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 846 + }, + { + "epoch": 1.929384965831435, + "grad_norm": 0.5137393474578857, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 847 + }, + { + "epoch": 1.9316628701594531, + "grad_norm": 0.3969299793243408, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 848 + }, + { + "epoch": 1.9339407744874715, + "grad_norm": 0.4130834937095642, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 849 + }, + { + "epoch": 1.9362186788154898, + "grad_norm": 0.3259606957435608, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 850 + }, + { + "epoch": 1.938496583143508, + "grad_norm": 0.358647882938385, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 851 + }, + { + "epoch": 1.940774487471526, + "grad_norm": 0.31734347343444824, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 852 + }, + { + "epoch": 1.9430523917995444, + "grad_norm": 0.3081108331680298, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 853 + }, + { + "epoch": 1.9453302961275627, + "grad_norm": 0.3544929027557373, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 854 + }, + { + "epoch": 1.9476082004555808, + "grad_norm": 0.3169618248939514, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 855 + }, + { + "epoch": 1.9498861047835991, + "grad_norm": 0.36319029331207275, + "learning_rate": 1e-06, + "loss": 0.0677, + "step": 856 + }, + { + "epoch": 1.9521640091116175, + "grad_norm": 0.34755897521972656, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 857 + }, + { + "epoch": 1.9544419134396356, + "grad_norm": 0.33121469616889954, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 858 + }, + { + "epoch": 1.9567198177676537, + "grad_norm": 0.3531659245491028, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 859 + }, + { + "epoch": 1.958997722095672, + "grad_norm": 0.3290151357650757, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 860 + }, + { + "epoch": 1.9612756264236904, + "grad_norm": 0.32417309284210205, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 861 + }, + { + "epoch": 1.9635535307517085, + "grad_norm": 0.30841973423957825, + "learning_rate": 1e-06, + "loss": 0.0682, + "step": 862 + }, + { + "epoch": 1.9658314350797266, + "grad_norm": 0.30138304829597473, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 863 + }, + { + "epoch": 1.968109339407745, + "grad_norm": 0.34160947799682617, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 864 + }, + { + "epoch": 1.9703872437357632, + "grad_norm": 0.31649959087371826, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 865 + }, + { + "epoch": 1.9726651480637813, + "grad_norm": 0.31511417031288147, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 866 + }, + { + "epoch": 1.9749430523917995, + "grad_norm": 0.28958871960639954, + "learning_rate": 1e-06, + "loss": 0.0619, + "step": 867 + }, + { + "epoch": 1.9772209567198178, + "grad_norm": 0.31726354360580444, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 868 + }, + { + "epoch": 1.9794988610478361, + "grad_norm": 0.33189961314201355, + "learning_rate": 1e-06, + "loss": 0.0614, + "step": 869 + }, + { + "epoch": 1.9817767653758542, + "grad_norm": 0.3234447240829468, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 870 + }, + { + "epoch": 1.9840546697038723, + "grad_norm": 0.3311309814453125, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 871 + }, + { + "epoch": 1.9863325740318907, + "grad_norm": 0.3180658221244812, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 872 + }, + { + "epoch": 1.988610478359909, + "grad_norm": 0.34991568326950073, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 873 + }, + { + "epoch": 1.9908883826879271, + "grad_norm": 0.41331782937049866, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 874 + }, + { + "epoch": 1.9931662870159452, + "grad_norm": 0.355467826128006, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 875 + }, + { + "epoch": 1.9954441913439636, + "grad_norm": 0.35229191184043884, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 876 + }, + { + "epoch": 1.997722095671982, + "grad_norm": 0.3391554653644562, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 877 + }, + { + "epoch": 2.0, + "grad_norm": 0.3079349100589752, + "learning_rate": 1e-06, + "loss": 0.0616, + "step": 878 + }, + { + "epoch": 2.002277904328018, + "grad_norm": 0.3298395276069641, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 879 + }, + { + "epoch": 2.0045558086560367, + "grad_norm": 0.3107350766658783, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 880 + }, + { + "epoch": 2.0068337129840548, + "grad_norm": 0.29757434129714966, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 881 + }, + { + "epoch": 2.009111617312073, + "grad_norm": 0.3028092086315155, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 882 + }, + { + "epoch": 2.011389521640091, + "grad_norm": 0.3350479006767273, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 883 + }, + { + "epoch": 2.0136674259681095, + "grad_norm": 0.3410264551639557, + "learning_rate": 1e-06, + "loss": 0.0591, + "step": 884 + }, + { + "epoch": 2.0159453302961277, + "grad_norm": 0.30534204840660095, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 885 + }, + { + "epoch": 2.0182232346241458, + "grad_norm": 0.30282455682754517, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 886 + }, + { + "epoch": 2.020501138952164, + "grad_norm": 0.340212881565094, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 887 + }, + { + "epoch": 2.0227790432801824, + "grad_norm": 0.35072022676467896, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 888 + }, + { + "epoch": 2.0250569476082005, + "grad_norm": 0.34727659821510315, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 889 + }, + { + "epoch": 2.0273348519362187, + "grad_norm": 0.31438976526260376, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 890 + }, + { + "epoch": 2.0296127562642368, + "grad_norm": 0.34864282608032227, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 891 + }, + { + "epoch": 2.0318906605922553, + "grad_norm": 0.31428372859954834, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 892 + }, + { + "epoch": 2.0341685649202734, + "grad_norm": 0.3400989770889282, + "learning_rate": 1e-06, + "loss": 0.0661, + "step": 893 + }, + { + "epoch": 2.0364464692482915, + "grad_norm": 0.3399061858654022, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 894 + }, + { + "epoch": 2.0387243735763096, + "grad_norm": 0.322358638048172, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 895 + }, + { + "epoch": 2.041002277904328, + "grad_norm": 0.3160433769226074, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 896 + }, + { + "epoch": 2.0432801822323463, + "grad_norm": 0.29157277941703796, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 897 + }, + { + "epoch": 2.0455580865603644, + "grad_norm": 0.31765398383140564, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 898 + }, + { + "epoch": 2.0478359908883825, + "grad_norm": 0.31541430950164795, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 899 + }, + { + "epoch": 2.050113895216401, + "grad_norm": 0.34013354778289795, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 900 + }, + { + "epoch": 2.052391799544419, + "grad_norm": 0.30183082818984985, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 901 + }, + { + "epoch": 2.0546697038724373, + "grad_norm": 0.322486937046051, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 902 + }, + { + "epoch": 2.0569476082004554, + "grad_norm": 0.28377974033355713, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 903 + }, + { + "epoch": 2.059225512528474, + "grad_norm": 0.3314119577407837, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 904 + }, + { + "epoch": 2.061503416856492, + "grad_norm": 0.42795753479003906, + "learning_rate": 1e-06, + "loss": 0.0679, + "step": 905 + }, + { + "epoch": 2.06378132118451, + "grad_norm": 0.3579128086566925, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 906 + }, + { + "epoch": 2.0660592255125283, + "grad_norm": 0.3247331380844116, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 907 + }, + { + "epoch": 2.068337129840547, + "grad_norm": 0.373795747756958, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 908 + }, + { + "epoch": 2.070615034168565, + "grad_norm": 0.3675771653652191, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 909 + }, + { + "epoch": 2.072892938496583, + "grad_norm": 0.3396068513393402, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 910 + }, + { + "epoch": 2.075170842824601, + "grad_norm": 0.36947745084762573, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 911 + }, + { + "epoch": 2.0774487471526197, + "grad_norm": 0.347051739692688, + "learning_rate": 1e-06, + "loss": 0.0662, + "step": 912 + }, + { + "epoch": 2.079726651480638, + "grad_norm": 0.37528035044670105, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 913 + }, + { + "epoch": 2.082004555808656, + "grad_norm": 0.34556132555007935, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 914 + }, + { + "epoch": 2.084282460136674, + "grad_norm": 0.32326239347457886, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 915 + }, + { + "epoch": 2.0865603644646926, + "grad_norm": 0.33874595165252686, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 916 + }, + { + "epoch": 2.0888382687927107, + "grad_norm": 0.3369845151901245, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 917 + }, + { + "epoch": 2.091116173120729, + "grad_norm": 0.3170710802078247, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 918 + }, + { + "epoch": 2.093394077448747, + "grad_norm": 0.3326922655105591, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 919 + }, + { + "epoch": 2.0956719817767655, + "grad_norm": 0.32724231481552124, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 920 + }, + { + "epoch": 2.0979498861047836, + "grad_norm": 0.30799350142478943, + "learning_rate": 1e-06, + "loss": 0.0604, + "step": 921 + }, + { + "epoch": 2.1002277904328017, + "grad_norm": 0.31784242391586304, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 922 + }, + { + "epoch": 2.10250569476082, + "grad_norm": 0.36320555210113525, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 923 + }, + { + "epoch": 2.1047835990888384, + "grad_norm": 0.3562675416469574, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 924 + }, + { + "epoch": 2.1070615034168565, + "grad_norm": 0.32459166646003723, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 925 + }, + { + "epoch": 2.1093394077448746, + "grad_norm": 0.30547642707824707, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 926 + }, + { + "epoch": 2.1116173120728927, + "grad_norm": 0.35435694456100464, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 927 + }, + { + "epoch": 2.1138952164009113, + "grad_norm": 0.3270133137702942, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 928 + }, + { + "epoch": 2.1161731207289294, + "grad_norm": 0.32915616035461426, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 929 + }, + { + "epoch": 2.1184510250569475, + "grad_norm": 0.33874085545539856, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 930 + }, + { + "epoch": 2.120728929384966, + "grad_norm": 0.3053398132324219, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 931 + }, + { + "epoch": 2.123006833712984, + "grad_norm": 0.3030601739883423, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 932 + }, + { + "epoch": 2.1252847380410023, + "grad_norm": 0.36700138449668884, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 933 + }, + { + "epoch": 2.1275626423690204, + "grad_norm": 0.3098386824131012, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 934 + }, + { + "epoch": 2.129840546697039, + "grad_norm": 0.3141404390335083, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 935 + }, + { + "epoch": 2.132118451025057, + "grad_norm": 0.2975289523601532, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 936 + }, + { + "epoch": 2.134396355353075, + "grad_norm": 0.31993308663368225, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 937 + }, + { + "epoch": 2.1366742596810933, + "grad_norm": 0.305317759513855, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 938 + }, + { + "epoch": 2.138952164009112, + "grad_norm": 0.285225510597229, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 939 + }, + { + "epoch": 2.14123006833713, + "grad_norm": 0.2939205467700958, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 940 + }, + { + "epoch": 2.143507972665148, + "grad_norm": 0.3053128719329834, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 941 + }, + { + "epoch": 2.145785876993166, + "grad_norm": 0.28846943378448486, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 942 + }, + { + "epoch": 2.1480637813211847, + "grad_norm": 0.31324896216392517, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 943 + }, + { + "epoch": 2.150341685649203, + "grad_norm": 0.3111551105976105, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 944 + }, + { + "epoch": 2.152619589977221, + "grad_norm": 0.319558322429657, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 945 + }, + { + "epoch": 2.154897494305239, + "grad_norm": 0.3317141532897949, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 946 + }, + { + "epoch": 2.1571753986332576, + "grad_norm": 0.3146052956581116, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 947 + }, + { + "epoch": 2.1594533029612757, + "grad_norm": 0.2950224280357361, + "learning_rate": 1e-06, + "loss": 0.0598, + "step": 948 + }, + { + "epoch": 2.161731207289294, + "grad_norm": 0.3068746030330658, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 949 + }, + { + "epoch": 2.164009111617312, + "grad_norm": 0.3253471553325653, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 950 + }, + { + "epoch": 2.1662870159453305, + "grad_norm": 0.29616138339042664, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 951 + }, + { + "epoch": 2.1685649202733486, + "grad_norm": 0.2936265766620636, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 952 + }, + { + "epoch": 2.1708428246013667, + "grad_norm": 0.3426027297973633, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 953 + }, + { + "epoch": 2.173120728929385, + "grad_norm": 0.33823007345199585, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 954 + }, + { + "epoch": 2.1753986332574033, + "grad_norm": 0.2923634648323059, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 955 + }, + { + "epoch": 2.1776765375854215, + "grad_norm": 0.324340283870697, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 956 + }, + { + "epoch": 2.1799544419134396, + "grad_norm": 0.38607659935951233, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 957 + }, + { + "epoch": 2.1822323462414577, + "grad_norm": 0.34259331226348877, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 958 + }, + { + "epoch": 2.1845102505694762, + "grad_norm": 0.2994532585144043, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 959 + }, + { + "epoch": 2.1867881548974943, + "grad_norm": 0.3358297646045685, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 960 + }, + { + "epoch": 2.1890660592255125, + "grad_norm": 0.3114963173866272, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 961 + }, + { + "epoch": 2.1913439635535306, + "grad_norm": 0.3565235137939453, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 962 + }, + { + "epoch": 2.193621867881549, + "grad_norm": 0.30073282122612, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 963 + }, + { + "epoch": 2.1958997722095672, + "grad_norm": 0.32632434368133545, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 964 + }, + { + "epoch": 2.1981776765375853, + "grad_norm": 0.30063581466674805, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 965 + }, + { + "epoch": 2.2004555808656034, + "grad_norm": 0.2940434217453003, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 966 + }, + { + "epoch": 2.202733485193622, + "grad_norm": 0.38594627380371094, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 967 + }, + { + "epoch": 2.20501138952164, + "grad_norm": 0.3209696114063263, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 968 + }, + { + "epoch": 2.207289293849658, + "grad_norm": 0.3685375452041626, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 969 + }, + { + "epoch": 2.2095671981776768, + "grad_norm": 0.35377630591392517, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 970 + }, + { + "epoch": 2.211845102505695, + "grad_norm": 0.3365820646286011, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 971 + }, + { + "epoch": 2.214123006833713, + "grad_norm": 0.34001877903938293, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 972 + }, + { + "epoch": 2.216400911161731, + "grad_norm": 0.33722350001335144, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 973 + }, + { + "epoch": 2.218678815489749, + "grad_norm": 0.4820878803730011, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 974 + }, + { + "epoch": 2.2209567198177678, + "grad_norm": 0.35107719898223877, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 975 + }, + { + "epoch": 2.223234624145786, + "grad_norm": 0.3394877016544342, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 976 + }, + { + "epoch": 2.225512528473804, + "grad_norm": 0.4072915017604828, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 977 + }, + { + "epoch": 2.2277904328018225, + "grad_norm": 0.3848952353000641, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 978 + }, + { + "epoch": 2.2300683371298406, + "grad_norm": 0.3877342939376831, + "learning_rate": 1e-06, + "loss": 0.0673, + "step": 979 + }, + { + "epoch": 2.2323462414578588, + "grad_norm": 0.33901846408843994, + "learning_rate": 1e-06, + "loss": 0.0666, + "step": 980 + }, + { + "epoch": 2.234624145785877, + "grad_norm": 0.4054679274559021, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 981 + }, + { + "epoch": 2.2369020501138954, + "grad_norm": 0.3689222037792206, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 982 + }, + { + "epoch": 2.2391799544419135, + "grad_norm": 0.33417072892189026, + "learning_rate": 1e-06, + "loss": 0.066, + "step": 983 + }, + { + "epoch": 2.2414578587699316, + "grad_norm": 0.3429153561592102, + "learning_rate": 1e-06, + "loss": 0.0606, + "step": 984 + }, + { + "epoch": 2.2437357630979498, + "grad_norm": 0.33090659976005554, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 985 + }, + { + "epoch": 2.2460136674259683, + "grad_norm": 0.3319113254547119, + "learning_rate": 1e-06, + "loss": 0.0607, + "step": 986 + }, + { + "epoch": 2.2482915717539864, + "grad_norm": 0.3743402063846588, + "learning_rate": 1e-06, + "loss": 0.0617, + "step": 987 + }, + { + "epoch": 2.2505694760820045, + "grad_norm": 0.29698455333709717, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 988 + }, + { + "epoch": 2.2528473804100226, + "grad_norm": 0.29791760444641113, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 989 + }, + { + "epoch": 2.255125284738041, + "grad_norm": 0.3675908148288727, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 990 + }, + { + "epoch": 2.2574031890660593, + "grad_norm": 0.3660987615585327, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 991 + }, + { + "epoch": 2.2596810933940774, + "grad_norm": 0.3584524691104889, + "learning_rate": 1e-06, + "loss": 0.0653, + "step": 992 + }, + { + "epoch": 2.2619589977220955, + "grad_norm": 0.31528687477111816, + "learning_rate": 1e-06, + "loss": 0.0607, + "step": 993 + }, + { + "epoch": 2.264236902050114, + "grad_norm": 0.38335245847702026, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 994 + }, + { + "epoch": 2.266514806378132, + "grad_norm": 0.35109302401542664, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 995 + }, + { + "epoch": 2.2687927107061503, + "grad_norm": 0.31480076909065247, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 996 + }, + { + "epoch": 2.2710706150341684, + "grad_norm": 0.3158552348613739, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 997 + }, + { + "epoch": 2.273348519362187, + "grad_norm": 0.37096795439720154, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 998 + }, + { + "epoch": 2.275626423690205, + "grad_norm": 0.34207212924957275, + "learning_rate": 1e-06, + "loss": 0.0614, + "step": 999 + }, + { + "epoch": 2.277904328018223, + "grad_norm": 0.31389740109443665, + "learning_rate": 1e-06, + "loss": 0.061, + "step": 1000 + }, + { + "epoch": 2.2801822323462413, + "grad_norm": 0.3090605139732361, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1001 + }, + { + "epoch": 2.28246013667426, + "grad_norm": 0.3092558681964874, + "learning_rate": 1e-06, + "loss": 0.0692, + "step": 1002 + }, + { + "epoch": 2.284738041002278, + "grad_norm": 0.3177545964717865, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1003 + }, + { + "epoch": 2.287015945330296, + "grad_norm": 0.29728224873542786, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1004 + }, + { + "epoch": 2.289293849658314, + "grad_norm": 0.29910656809806824, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1005 + }, + { + "epoch": 2.2915717539863327, + "grad_norm": 0.317891001701355, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 1006 + }, + { + "epoch": 2.293849658314351, + "grad_norm": 0.3119383156299591, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1007 + }, + { + "epoch": 2.296127562642369, + "grad_norm": 0.3160797357559204, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1008 + }, + { + "epoch": 2.298405466970387, + "grad_norm": 0.3228830397129059, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 1009 + }, + { + "epoch": 2.3006833712984056, + "grad_norm": 0.31505975127220154, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1010 + }, + { + "epoch": 2.3029612756264237, + "grad_norm": 0.3386927843093872, + "learning_rate": 1e-06, + "loss": 0.0617, + "step": 1011 + }, + { + "epoch": 2.305239179954442, + "grad_norm": 0.31644317507743835, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1012 + }, + { + "epoch": 2.30751708428246, + "grad_norm": 0.3250298798084259, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1013 + }, + { + "epoch": 2.3097949886104785, + "grad_norm": 0.34258517622947693, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1014 + }, + { + "epoch": 2.3120728929384966, + "grad_norm": 0.3133108615875244, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 1015 + }, + { + "epoch": 2.3143507972665147, + "grad_norm": 0.34875139594078064, + "learning_rate": 1e-06, + "loss": 0.0607, + "step": 1016 + }, + { + "epoch": 2.3166287015945333, + "grad_norm": 0.34328892827033997, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 1017 + }, + { + "epoch": 2.3189066059225514, + "grad_norm": 0.3494330048561096, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1018 + }, + { + "epoch": 2.3211845102505695, + "grad_norm": 0.32389935851097107, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1019 + }, + { + "epoch": 2.3234624145785876, + "grad_norm": 0.30033954977989197, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1020 + }, + { + "epoch": 2.3257403189066057, + "grad_norm": 0.2934894561767578, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1021 + }, + { + "epoch": 2.3280182232346243, + "grad_norm": 0.32762518525123596, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 1022 + }, + { + "epoch": 2.3302961275626424, + "grad_norm": 0.312628835439682, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1023 + }, + { + "epoch": 2.3325740318906605, + "grad_norm": 0.378641277551651, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 1024 + }, + { + "epoch": 2.334851936218679, + "grad_norm": 0.3300485610961914, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 1025 + }, + { + "epoch": 2.337129840546697, + "grad_norm": 0.33844852447509766, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 1026 + }, + { + "epoch": 2.3394077448747153, + "grad_norm": 0.3224867284297943, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1027 + }, + { + "epoch": 2.3416856492027334, + "grad_norm": 0.3092311918735504, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1028 + }, + { + "epoch": 2.3439635535307515, + "grad_norm": 0.3083791136741638, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 1029 + }, + { + "epoch": 2.34624145785877, + "grad_norm": 0.3352966010570526, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 1030 + }, + { + "epoch": 2.348519362186788, + "grad_norm": 0.3157583773136139, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1031 + }, + { + "epoch": 2.3507972665148062, + "grad_norm": 0.3214615285396576, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 1032 + }, + { + "epoch": 2.353075170842825, + "grad_norm": 0.2926361858844757, + "learning_rate": 1e-06, + "loss": 0.0616, + "step": 1033 + }, + { + "epoch": 2.355353075170843, + "grad_norm": 0.30561769008636475, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1034 + }, + { + "epoch": 2.357630979498861, + "grad_norm": 0.3239099085330963, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1035 + }, + { + "epoch": 2.359908883826879, + "grad_norm": 0.3393976092338562, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1036 + }, + { + "epoch": 2.3621867881548977, + "grad_norm": 0.29840222001075745, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 1037 + }, + { + "epoch": 2.364464692482916, + "grad_norm": 0.3359712064266205, + "learning_rate": 1e-06, + "loss": 0.0665, + "step": 1038 + }, + { + "epoch": 2.366742596810934, + "grad_norm": 0.3008364737033844, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1039 + }, + { + "epoch": 2.369020501138952, + "grad_norm": 0.29434284567832947, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 1040 + }, + { + "epoch": 2.3712984054669706, + "grad_norm": 0.3117225468158722, + "learning_rate": 1e-06, + "loss": 0.0606, + "step": 1041 + }, + { + "epoch": 2.3735763097949887, + "grad_norm": 0.3177486062049866, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1042 + }, + { + "epoch": 2.375854214123007, + "grad_norm": 0.31976795196533203, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1043 + }, + { + "epoch": 2.378132118451025, + "grad_norm": 0.30389031767845154, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 1044 + }, + { + "epoch": 2.3804100227790435, + "grad_norm": 0.30087682604789734, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1045 + }, + { + "epoch": 2.3826879271070616, + "grad_norm": 0.3025425970554352, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1046 + }, + { + "epoch": 2.3849658314350797, + "grad_norm": 0.32383060455322266, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1047 + }, + { + "epoch": 2.387243735763098, + "grad_norm": 0.345550000667572, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1048 + }, + { + "epoch": 2.3895216400911163, + "grad_norm": 0.3448682129383087, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1049 + }, + { + "epoch": 2.3917995444191344, + "grad_norm": 0.32550114393234253, + "learning_rate": 1e-06, + "loss": 0.0605, + "step": 1050 + }, + { + "epoch": 2.3940774487471526, + "grad_norm": 0.3083193302154541, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1051 + }, + { + "epoch": 2.3963553530751707, + "grad_norm": 0.3057478368282318, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1052 + }, + { + "epoch": 2.3986332574031892, + "grad_norm": 0.32537388801574707, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1053 + }, + { + "epoch": 2.4009111617312073, + "grad_norm": 0.3248838484287262, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1054 + }, + { + "epoch": 2.4031890660592254, + "grad_norm": 0.30495864152908325, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1055 + }, + { + "epoch": 2.4054669703872436, + "grad_norm": 0.290139764547348, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1056 + }, + { + "epoch": 2.407744874715262, + "grad_norm": 0.3083683252334595, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1057 + }, + { + "epoch": 2.41002277904328, + "grad_norm": 0.3095282018184662, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1058 + }, + { + "epoch": 2.4123006833712983, + "grad_norm": 0.28504014015197754, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1059 + }, + { + "epoch": 2.4145785876993164, + "grad_norm": 0.2969081401824951, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1060 + }, + { + "epoch": 2.416856492027335, + "grad_norm": 0.30184394121170044, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1061 + }, + { + "epoch": 2.419134396355353, + "grad_norm": 0.359831839799881, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 1062 + }, + { + "epoch": 2.421412300683371, + "grad_norm": 0.31837114691734314, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1063 + }, + { + "epoch": 2.4236902050113898, + "grad_norm": 0.34367606043815613, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1064 + }, + { + "epoch": 2.425968109339408, + "grad_norm": 0.310528963804245, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1065 + }, + { + "epoch": 2.428246013667426, + "grad_norm": 0.2981131076812744, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1066 + }, + { + "epoch": 2.430523917995444, + "grad_norm": 0.28755995631217957, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1067 + }, + { + "epoch": 2.432801822323462, + "grad_norm": 0.30812400579452515, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1068 + }, + { + "epoch": 2.4350797266514808, + "grad_norm": 0.30188748240470886, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1069 + }, + { + "epoch": 2.437357630979499, + "grad_norm": 0.3097800612449646, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 1070 + }, + { + "epoch": 2.439635535307517, + "grad_norm": 0.2936986982822418, + "learning_rate": 1e-06, + "loss": 0.0671, + "step": 1071 + }, + { + "epoch": 2.4419134396355355, + "grad_norm": 0.3198126256465912, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1072 + }, + { + "epoch": 2.4441913439635536, + "grad_norm": 0.32505905628204346, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1073 + }, + { + "epoch": 2.4464692482915718, + "grad_norm": 0.3216456174850464, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1074 + }, + { + "epoch": 2.44874715261959, + "grad_norm": 0.3079557716846466, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1075 + }, + { + "epoch": 2.451025056947608, + "grad_norm": 0.33667927980422974, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1076 + }, + { + "epoch": 2.4533029612756265, + "grad_norm": 0.35140907764434814, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1077 + }, + { + "epoch": 2.4555808656036446, + "grad_norm": 0.32909226417541504, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1078 + }, + { + "epoch": 2.4578587699316627, + "grad_norm": 0.3274776041507721, + "learning_rate": 1e-06, + "loss": 0.0664, + "step": 1079 + }, + { + "epoch": 2.4601366742596813, + "grad_norm": 0.3429358899593353, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1080 + }, + { + "epoch": 2.4624145785876994, + "grad_norm": 0.3202768862247467, + "learning_rate": 1e-06, + "loss": 0.0655, + "step": 1081 + }, + { + "epoch": 2.4646924829157175, + "grad_norm": 0.3264595866203308, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1082 + }, + { + "epoch": 2.4669703872437356, + "grad_norm": 0.29129666090011597, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1083 + }, + { + "epoch": 2.4692482915717537, + "grad_norm": 0.30288031697273254, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 1084 + }, + { + "epoch": 2.4715261958997723, + "grad_norm": 0.32726582884788513, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1085 + }, + { + "epoch": 2.4738041002277904, + "grad_norm": 0.3253808319568634, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1086 + }, + { + "epoch": 2.4760820045558085, + "grad_norm": 0.32200029492378235, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 1087 + }, + { + "epoch": 2.478359908883827, + "grad_norm": 0.28810763359069824, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1088 + }, + { + "epoch": 2.480637813211845, + "grad_norm": 0.3284909725189209, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 1089 + }, + { + "epoch": 2.4829157175398633, + "grad_norm": 0.31362593173980713, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1090 + }, + { + "epoch": 2.4851936218678814, + "grad_norm": 0.3110062777996063, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1091 + }, + { + "epoch": 2.4874715261959, + "grad_norm": 0.34175312519073486, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1092 + }, + { + "epoch": 2.489749430523918, + "grad_norm": 0.3296828269958496, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 1093 + }, + { + "epoch": 2.492027334851936, + "grad_norm": 0.34978562593460083, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1094 + }, + { + "epoch": 2.4943052391799543, + "grad_norm": 0.3244493901729584, + "learning_rate": 1e-06, + "loss": 0.0652, + "step": 1095 + }, + { + "epoch": 2.496583143507973, + "grad_norm": 0.35493922233581543, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1096 + }, + { + "epoch": 2.498861047835991, + "grad_norm": 0.3524758219718933, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1097 + }, + { + "epoch": 2.501138952164009, + "grad_norm": 0.3213484585285187, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1098 + }, + { + "epoch": 2.503416856492027, + "grad_norm": 0.33105844259262085, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1099 + }, + { + "epoch": 2.5056947608200457, + "grad_norm": 0.32136300206184387, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1100 + }, + { + "epoch": 2.507972665148064, + "grad_norm": 0.3017794191837311, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 1101 + }, + { + "epoch": 2.510250569476082, + "grad_norm": 0.31190139055252075, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1102 + }, + { + "epoch": 2.5125284738041005, + "grad_norm": 0.3272608816623688, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1103 + }, + { + "epoch": 2.5148063781321186, + "grad_norm": 0.3389891982078552, + "learning_rate": 1e-06, + "loss": 0.0605, + "step": 1104 + }, + { + "epoch": 2.5170842824601367, + "grad_norm": 0.3586137592792511, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1105 + }, + { + "epoch": 2.519362186788155, + "grad_norm": 0.3160545229911804, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1106 + }, + { + "epoch": 2.521640091116173, + "grad_norm": 0.30957674980163574, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1107 + }, + { + "epoch": 2.5239179954441915, + "grad_norm": 0.36720675230026245, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 1108 + }, + { + "epoch": 2.5261958997722096, + "grad_norm": 0.3376382291316986, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1109 + }, + { + "epoch": 2.5284738041002277, + "grad_norm": 0.2924495041370392, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1110 + }, + { + "epoch": 2.5307517084282463, + "grad_norm": 0.3009905517101288, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 1111 + }, + { + "epoch": 2.5330296127562644, + "grad_norm": 0.3150876462459564, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1112 + }, + { + "epoch": 2.5353075170842825, + "grad_norm": 0.3668336868286133, + "learning_rate": 1e-06, + "loss": 0.0675, + "step": 1113 + }, + { + "epoch": 2.5375854214123006, + "grad_norm": 0.3260135054588318, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1114 + }, + { + "epoch": 2.5398633257403187, + "grad_norm": 0.30943727493286133, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 1115 + }, + { + "epoch": 2.5421412300683373, + "grad_norm": 0.3114602863788605, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1116 + }, + { + "epoch": 2.5444191343963554, + "grad_norm": 0.3168443739414215, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 1117 + }, + { + "epoch": 2.5466970387243735, + "grad_norm": 0.3130890429019928, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1118 + }, + { + "epoch": 2.548974943052392, + "grad_norm": 0.33613255620002747, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 1119 + }, + { + "epoch": 2.55125284738041, + "grad_norm": 0.31414246559143066, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1120 + }, + { + "epoch": 2.5535307517084282, + "grad_norm": 0.3417739272117615, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 1121 + }, + { + "epoch": 2.5558086560364464, + "grad_norm": 0.31404909491539, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1122 + }, + { + "epoch": 2.5580865603644645, + "grad_norm": 0.3080407381057739, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1123 + }, + { + "epoch": 2.560364464692483, + "grad_norm": 0.33803316950798035, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1124 + }, + { + "epoch": 2.562642369020501, + "grad_norm": 0.3130744397640228, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1125 + }, + { + "epoch": 2.5649202733485192, + "grad_norm": 0.2957046329975128, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1126 + }, + { + "epoch": 2.567198177676538, + "grad_norm": 0.32519596815109253, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1127 + }, + { + "epoch": 2.569476082004556, + "grad_norm": 0.29689908027648926, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1128 + }, + { + "epoch": 2.571753986332574, + "grad_norm": 0.28607016801834106, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1129 + }, + { + "epoch": 2.574031890660592, + "grad_norm": 0.31669101119041443, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1130 + }, + { + "epoch": 2.5763097949886102, + "grad_norm": 0.3078513741493225, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1131 + }, + { + "epoch": 2.578587699316629, + "grad_norm": 0.32021909952163696, + "learning_rate": 1e-06, + "loss": 0.0656, + "step": 1132 + }, + { + "epoch": 2.580865603644647, + "grad_norm": 0.2952992618083954, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1133 + }, + { + "epoch": 2.583143507972665, + "grad_norm": 0.29613935947418213, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1134 + }, + { + "epoch": 2.5854214123006836, + "grad_norm": 0.2994500994682312, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 1135 + }, + { + "epoch": 2.5876993166287017, + "grad_norm": 0.35281914472579956, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1136 + }, + { + "epoch": 2.58997722095672, + "grad_norm": 0.3151220381259918, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1137 + }, + { + "epoch": 2.592255125284738, + "grad_norm": 0.3167590796947479, + "learning_rate": 1e-06, + "loss": 0.0597, + "step": 1138 + }, + { + "epoch": 2.594533029612756, + "grad_norm": 0.32674601674079895, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1139 + }, + { + "epoch": 2.5968109339407746, + "grad_norm": 0.3486584722995758, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1140 + }, + { + "epoch": 2.5990888382687927, + "grad_norm": 0.3223385512828827, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1141 + }, + { + "epoch": 2.6013667425968108, + "grad_norm": 0.35205402970314026, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1142 + }, + { + "epoch": 2.6036446469248293, + "grad_norm": 0.3090757727622986, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1143 + }, + { + "epoch": 2.6059225512528474, + "grad_norm": 0.29854586720466614, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1144 + }, + { + "epoch": 2.6082004555808656, + "grad_norm": 0.31086039543151855, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1145 + }, + { + "epoch": 2.6104783599088837, + "grad_norm": 0.33719751238822937, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 1146 + }, + { + "epoch": 2.612756264236902, + "grad_norm": 0.31607624888420105, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1147 + }, + { + "epoch": 2.6150341685649203, + "grad_norm": 0.32685747742652893, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1148 + }, + { + "epoch": 2.6173120728929384, + "grad_norm": 0.3138400614261627, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1149 + }, + { + "epoch": 2.619589977220957, + "grad_norm": 0.2995753586292267, + "learning_rate": 1e-06, + "loss": 0.0606, + "step": 1150 + }, + { + "epoch": 2.621867881548975, + "grad_norm": 0.32046765089035034, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 1151 + }, + { + "epoch": 2.624145785876993, + "grad_norm": 0.3098139464855194, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 1152 + }, + { + "epoch": 2.6264236902050113, + "grad_norm": 0.3240780234336853, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1153 + }, + { + "epoch": 2.6287015945330294, + "grad_norm": 0.30977919697761536, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1154 + }, + { + "epoch": 2.630979498861048, + "grad_norm": 0.3068590462207794, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 1155 + }, + { + "epoch": 2.633257403189066, + "grad_norm": 0.30591702461242676, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1156 + }, + { + "epoch": 2.635535307517084, + "grad_norm": 0.3209840953350067, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 1157 + }, + { + "epoch": 2.6378132118451028, + "grad_norm": 0.3293345272541046, + "learning_rate": 1e-06, + "loss": 0.0654, + "step": 1158 + }, + { + "epoch": 2.640091116173121, + "grad_norm": 0.3091947138309479, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1159 + }, + { + "epoch": 2.642369020501139, + "grad_norm": 0.31698569655418396, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1160 + }, + { + "epoch": 2.644646924829157, + "grad_norm": 0.30938753485679626, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1161 + }, + { + "epoch": 2.646924829157175, + "grad_norm": 0.33399319648742676, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1162 + }, + { + "epoch": 2.6492027334851938, + "grad_norm": 0.31355342268943787, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1163 + }, + { + "epoch": 2.651480637813212, + "grad_norm": 0.316654771566391, + "learning_rate": 1e-06, + "loss": 0.0649, + "step": 1164 + }, + { + "epoch": 2.65375854214123, + "grad_norm": 0.29832085967063904, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1165 + }, + { + "epoch": 2.6560364464692485, + "grad_norm": 0.3212261497974396, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1166 + }, + { + "epoch": 2.6583143507972666, + "grad_norm": 0.33575674891471863, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1167 + }, + { + "epoch": 2.6605922551252847, + "grad_norm": 0.3022531270980835, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 1168 + }, + { + "epoch": 2.662870159453303, + "grad_norm": 0.3286031186580658, + "learning_rate": 1e-06, + "loss": 0.0668, + "step": 1169 + }, + { + "epoch": 2.665148063781321, + "grad_norm": 0.29720622301101685, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 1170 + }, + { + "epoch": 2.6674259681093395, + "grad_norm": 0.3407134711742401, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1171 + }, + { + "epoch": 2.6697038724373576, + "grad_norm": 0.33104053139686584, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1172 + }, + { + "epoch": 2.6719817767653757, + "grad_norm": 0.3048887252807617, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1173 + }, + { + "epoch": 2.6742596810933943, + "grad_norm": 0.3189552426338196, + "learning_rate": 1e-06, + "loss": 0.0605, + "step": 1174 + }, + { + "epoch": 2.6765375854214124, + "grad_norm": 0.33991917967796326, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1175 + }, + { + "epoch": 2.6788154897494305, + "grad_norm": 0.33319586515426636, + "learning_rate": 1e-06, + "loss": 0.0607, + "step": 1176 + }, + { + "epoch": 2.6810933940774486, + "grad_norm": 0.30225613713264465, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1177 + }, + { + "epoch": 2.6833712984054667, + "grad_norm": 0.33196207880973816, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1178 + }, + { + "epoch": 2.6856492027334853, + "grad_norm": 0.3292437195777893, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1179 + }, + { + "epoch": 2.6879271070615034, + "grad_norm": 0.296673446893692, + "learning_rate": 1e-06, + "loss": 0.0608, + "step": 1180 + }, + { + "epoch": 2.6902050113895215, + "grad_norm": 0.31759268045425415, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 1181 + }, + { + "epoch": 2.69248291571754, + "grad_norm": 0.3035334348678589, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1182 + }, + { + "epoch": 2.694760820045558, + "grad_norm": 0.28981852531433105, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1183 + }, + { + "epoch": 2.6970387243735763, + "grad_norm": 0.3319694995880127, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1184 + }, + { + "epoch": 2.6993166287015944, + "grad_norm": 0.31823375821113586, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 1185 + }, + { + "epoch": 2.7015945330296125, + "grad_norm": 0.3065875470638275, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1186 + }, + { + "epoch": 2.703872437357631, + "grad_norm": 0.3361159563064575, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1187 + }, + { + "epoch": 2.706150341685649, + "grad_norm": 0.3099355399608612, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1188 + }, + { + "epoch": 2.7084282460136673, + "grad_norm": 0.30267569422721863, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1189 + }, + { + "epoch": 2.710706150341686, + "grad_norm": 0.31148144602775574, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1190 + }, + { + "epoch": 2.712984054669704, + "grad_norm": 0.3119550347328186, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 1191 + }, + { + "epoch": 2.715261958997722, + "grad_norm": 0.31687048077583313, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1192 + }, + { + "epoch": 2.71753986332574, + "grad_norm": 0.3108922839164734, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 1193 + }, + { + "epoch": 2.7198177676537583, + "grad_norm": 0.3001142144203186, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1194 + }, + { + "epoch": 2.722095671981777, + "grad_norm": 0.3873944878578186, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1195 + }, + { + "epoch": 2.724373576309795, + "grad_norm": 0.34534773230552673, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1196 + }, + { + "epoch": 2.7266514806378135, + "grad_norm": 0.3606201708316803, + "learning_rate": 1e-06, + "loss": 0.0669, + "step": 1197 + }, + { + "epoch": 2.7289293849658316, + "grad_norm": 0.3477628529071808, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1198 + }, + { + "epoch": 2.7312072892938497, + "grad_norm": 0.282744437456131, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1199 + }, + { + "epoch": 2.733485193621868, + "grad_norm": 0.371529221534729, + "learning_rate": 1e-06, + "loss": 0.0645, + "step": 1200 + }, + { + "epoch": 2.735763097949886, + "grad_norm": 0.32477474212646484, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1201 + }, + { + "epoch": 2.7380410022779045, + "grad_norm": 0.317609041929245, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1202 + }, + { + "epoch": 2.7403189066059226, + "grad_norm": 0.37395036220550537, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 1203 + }, + { + "epoch": 2.7425968109339407, + "grad_norm": 0.335528165102005, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1204 + }, + { + "epoch": 2.7448747152619593, + "grad_norm": 0.33896511793136597, + "learning_rate": 1e-06, + "loss": 0.0659, + "step": 1205 + }, + { + "epoch": 2.7471526195899774, + "grad_norm": 0.32078099250793457, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1206 + }, + { + "epoch": 2.7494305239179955, + "grad_norm": 0.32208141684532166, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 1207 + }, + { + "epoch": 2.7517084282460136, + "grad_norm": 0.4123600423336029, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1208 + }, + { + "epoch": 2.7539863325740317, + "grad_norm": 0.32614096999168396, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1209 + }, + { + "epoch": 2.7562642369020502, + "grad_norm": 0.3150961399078369, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1210 + }, + { + "epoch": 2.7585421412300684, + "grad_norm": 0.3025928735733032, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1211 + }, + { + "epoch": 2.7608200455580865, + "grad_norm": 0.3232964873313904, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1212 + }, + { + "epoch": 2.763097949886105, + "grad_norm": 0.33953917026519775, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1213 + }, + { + "epoch": 2.765375854214123, + "grad_norm": 0.32320111989974976, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1214 + }, + { + "epoch": 2.7676537585421412, + "grad_norm": 0.31046774983406067, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1215 + }, + { + "epoch": 2.7699316628701594, + "grad_norm": 0.31355375051498413, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1216 + }, + { + "epoch": 2.7722095671981775, + "grad_norm": 0.3095831274986267, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1217 + }, + { + "epoch": 2.774487471526196, + "grad_norm": 0.3160685896873474, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1218 + }, + { + "epoch": 2.776765375854214, + "grad_norm": 0.3148292601108551, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1219 + }, + { + "epoch": 2.7790432801822322, + "grad_norm": 0.3714725971221924, + "learning_rate": 1e-06, + "loss": 0.0648, + "step": 1220 + }, + { + "epoch": 2.781321184510251, + "grad_norm": 0.319255530834198, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1221 + }, + { + "epoch": 2.783599088838269, + "grad_norm": 0.34812065958976746, + "learning_rate": 1e-06, + "loss": 0.0651, + "step": 1222 + }, + { + "epoch": 2.785876993166287, + "grad_norm": 0.32483720779418945, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1223 + }, + { + "epoch": 2.788154897494305, + "grad_norm": 0.32725390791893005, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1224 + }, + { + "epoch": 2.7904328018223232, + "grad_norm": 0.32553112506866455, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1225 + }, + { + "epoch": 2.792710706150342, + "grad_norm": 0.3020703196525574, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1226 + }, + { + "epoch": 2.79498861047836, + "grad_norm": 0.28815552592277527, + "learning_rate": 1e-06, + "loss": 0.0608, + "step": 1227 + }, + { + "epoch": 2.797266514806378, + "grad_norm": 0.30407530069351196, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1228 + }, + { + "epoch": 2.7995444191343966, + "grad_norm": 0.325113445520401, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1229 + }, + { + "epoch": 2.8018223234624147, + "grad_norm": 0.33632412552833557, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 1230 + }, + { + "epoch": 2.8041002277904328, + "grad_norm": 0.30699655413627625, + "learning_rate": 1e-06, + "loss": 0.0596, + "step": 1231 + }, + { + "epoch": 2.806378132118451, + "grad_norm": 0.3185036778450012, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1232 + }, + { + "epoch": 2.808656036446469, + "grad_norm": 0.3325420916080475, + "learning_rate": 1e-06, + "loss": 0.0596, + "step": 1233 + }, + { + "epoch": 2.8109339407744875, + "grad_norm": 0.320686012506485, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1234 + }, + { + "epoch": 2.8132118451025057, + "grad_norm": 0.32656344771385193, + "learning_rate": 1e-06, + "loss": 0.0606, + "step": 1235 + }, + { + "epoch": 2.8154897494305238, + "grad_norm": 0.3348785936832428, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1236 + }, + { + "epoch": 2.8177676537585423, + "grad_norm": 0.3099953532218933, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1237 + }, + { + "epoch": 2.8200455580865604, + "grad_norm": 0.35770779848098755, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1238 + }, + { + "epoch": 2.8223234624145785, + "grad_norm": 0.3863605260848999, + "learning_rate": 1e-06, + "loss": 0.0625, + "step": 1239 + }, + { + "epoch": 2.8246013667425967, + "grad_norm": 0.3190959095954895, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 1240 + }, + { + "epoch": 2.8268792710706148, + "grad_norm": 0.29154112935066223, + "learning_rate": 1e-06, + "loss": 0.0644, + "step": 1241 + }, + { + "epoch": 2.8291571753986333, + "grad_norm": 0.35592120885849, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1242 + }, + { + "epoch": 2.8314350797266514, + "grad_norm": 0.39352738857269287, + "learning_rate": 1e-06, + "loss": 0.064, + "step": 1243 + }, + { + "epoch": 2.83371298405467, + "grad_norm": 0.3047989308834076, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1244 + }, + { + "epoch": 2.835990888382688, + "grad_norm": 0.30240598320961, + "learning_rate": 1e-06, + "loss": 0.0602, + "step": 1245 + }, + { + "epoch": 2.838268792710706, + "grad_norm": 0.3366698622703552, + "learning_rate": 1e-06, + "loss": 0.0608, + "step": 1246 + }, + { + "epoch": 2.8405466970387243, + "grad_norm": 0.334710031747818, + "learning_rate": 1e-06, + "loss": 0.061, + "step": 1247 + }, + { + "epoch": 2.8428246013667424, + "grad_norm": 0.3057287037372589, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1248 + }, + { + "epoch": 2.845102505694761, + "grad_norm": 0.2892928123474121, + "learning_rate": 1e-06, + "loss": 0.0616, + "step": 1249 + }, + { + "epoch": 2.847380410022779, + "grad_norm": 0.3434309661388397, + "learning_rate": 1e-06, + "loss": 0.0657, + "step": 1250 + }, + { + "epoch": 2.849658314350797, + "grad_norm": 0.3227265179157257, + "learning_rate": 1e-06, + "loss": 0.0615, + "step": 1251 + }, + { + "epoch": 2.8519362186788157, + "grad_norm": 0.3329966068267822, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1252 + }, + { + "epoch": 2.854214123006834, + "grad_norm": 0.3313438594341278, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 1253 + }, + { + "epoch": 2.856492027334852, + "grad_norm": 0.33178552985191345, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1254 + }, + { + "epoch": 2.85876993166287, + "grad_norm": 0.3342040181159973, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 1255 + }, + { + "epoch": 2.861047835990888, + "grad_norm": 0.33365437388420105, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1256 + }, + { + "epoch": 2.8633257403189067, + "grad_norm": 0.3274896442890167, + "learning_rate": 1e-06, + "loss": 0.0614, + "step": 1257 + }, + { + "epoch": 2.865603644646925, + "grad_norm": 0.3632802367210388, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1258 + }, + { + "epoch": 2.867881548974943, + "grad_norm": 0.3183388113975525, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1259 + }, + { + "epoch": 2.8701594533029615, + "grad_norm": 0.3145568370819092, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1260 + }, + { + "epoch": 2.8724373576309796, + "grad_norm": 0.3258124589920044, + "learning_rate": 1e-06, + "loss": 0.0623, + "step": 1261 + }, + { + "epoch": 2.8747152619589977, + "grad_norm": 0.31933653354644775, + "learning_rate": 1e-06, + "loss": 0.0627, + "step": 1262 + }, + { + "epoch": 2.876993166287016, + "grad_norm": 0.312185138463974, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1263 + }, + { + "epoch": 2.879271070615034, + "grad_norm": 0.32056960463523865, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1264 + }, + { + "epoch": 2.8815489749430525, + "grad_norm": 0.32241058349609375, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1265 + }, + { + "epoch": 2.8838268792710706, + "grad_norm": 0.31692224740982056, + "learning_rate": 1e-06, + "loss": 0.0609, + "step": 1266 + }, + { + "epoch": 2.8861047835990887, + "grad_norm": 0.29960310459136963, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1267 + }, + { + "epoch": 2.8883826879271073, + "grad_norm": 0.3611791431903839, + "learning_rate": 1e-06, + "loss": 0.0602, + "step": 1268 + }, + { + "epoch": 2.8906605922551254, + "grad_norm": 0.32895493507385254, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1269 + }, + { + "epoch": 2.8929384965831435, + "grad_norm": 0.32370278239250183, + "learning_rate": 1e-06, + "loss": 0.0629, + "step": 1270 + }, + { + "epoch": 2.8952164009111616, + "grad_norm": 0.34192004799842834, + "learning_rate": 1e-06, + "loss": 0.0602, + "step": 1271 + }, + { + "epoch": 2.8974943052391797, + "grad_norm": 0.3065672516822815, + "learning_rate": 1e-06, + "loss": 0.0617, + "step": 1272 + }, + { + "epoch": 2.8997722095671983, + "grad_norm": 0.34392425417900085, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1273 + }, + { + "epoch": 2.9020501138952164, + "grad_norm": 0.3067595958709717, + "learning_rate": 1e-06, + "loss": 0.0639, + "step": 1274 + }, + { + "epoch": 2.9043280182232345, + "grad_norm": 0.34329450130462646, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1275 + }, + { + "epoch": 2.906605922551253, + "grad_norm": 0.31491053104400635, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1276 + }, + { + "epoch": 2.908883826879271, + "grad_norm": 0.29325541853904724, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1277 + }, + { + "epoch": 2.9111617312072893, + "grad_norm": 0.3152156174182892, + "learning_rate": 1e-06, + "loss": 0.0642, + "step": 1278 + }, + { + "epoch": 2.9134396355353074, + "grad_norm": 0.3079128563404083, + "learning_rate": 1e-06, + "loss": 0.0618, + "step": 1279 + }, + { + "epoch": 2.9157175398633255, + "grad_norm": 0.3399355411529541, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1280 + }, + { + "epoch": 2.917995444191344, + "grad_norm": 0.30263328552246094, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1281 + }, + { + "epoch": 2.920273348519362, + "grad_norm": 0.29829227924346924, + "learning_rate": 1e-06, + "loss": 0.0619, + "step": 1282 + }, + { + "epoch": 2.9225512528473803, + "grad_norm": 0.3105120360851288, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1283 + }, + { + "epoch": 2.924829157175399, + "grad_norm": 0.31891483068466187, + "learning_rate": 1e-06, + "loss": 0.0634, + "step": 1284 + }, + { + "epoch": 2.927107061503417, + "grad_norm": 0.31023547053337097, + "learning_rate": 1e-06, + "loss": 0.0624, + "step": 1285 + }, + { + "epoch": 2.929384965831435, + "grad_norm": 0.30297133326530457, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1286 + }, + { + "epoch": 2.931662870159453, + "grad_norm": 0.29199153184890747, + "learning_rate": 1e-06, + "loss": 0.0632, + "step": 1287 + }, + { + "epoch": 2.9339407744874713, + "grad_norm": 0.3189626634120941, + "learning_rate": 1e-06, + "loss": 0.0635, + "step": 1288 + }, + { + "epoch": 2.93621867881549, + "grad_norm": 0.30239737033843994, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1289 + }, + { + "epoch": 2.938496583143508, + "grad_norm": 0.3491579294204712, + "learning_rate": 1e-06, + "loss": 0.065, + "step": 1290 + }, + { + "epoch": 2.940774487471526, + "grad_norm": 0.33288323879241943, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1291 + }, + { + "epoch": 2.9430523917995446, + "grad_norm": 0.2876352071762085, + "learning_rate": 1e-06, + "loss": 0.0621, + "step": 1292 + }, + { + "epoch": 2.9453302961275627, + "grad_norm": 0.3352383077144623, + "learning_rate": 1e-06, + "loss": 0.0631, + "step": 1293 + }, + { + "epoch": 2.947608200455581, + "grad_norm": 0.3068503439426422, + "learning_rate": 1e-06, + "loss": 0.0626, + "step": 1294 + }, + { + "epoch": 2.949886104783599, + "grad_norm": 0.2919013202190399, + "learning_rate": 1e-06, + "loss": 0.0628, + "step": 1295 + }, + { + "epoch": 2.9521640091116175, + "grad_norm": 0.28330349922180176, + "learning_rate": 1e-06, + "loss": 0.0633, + "step": 1296 + }, + { + "epoch": 2.9544419134396356, + "grad_norm": 0.3266514837741852, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1297 + }, + { + "epoch": 2.9567198177676537, + "grad_norm": 0.34017476439476013, + "learning_rate": 1e-06, + "loss": 0.0595, + "step": 1298 + }, + { + "epoch": 2.9589977220956722, + "grad_norm": 0.29811179637908936, + "learning_rate": 1e-06, + "loss": 0.063, + "step": 1299 + }, + { + "epoch": 2.9612756264236904, + "grad_norm": 0.2969530522823334, + "learning_rate": 1e-06, + "loss": 0.0598, + "step": 1300 + }, + { + "epoch": 2.9635535307517085, + "grad_norm": 0.30584046244621277, + "learning_rate": 1e-06, + "loss": 0.0616, + "step": 1301 + }, + { + "epoch": 2.9658314350797266, + "grad_norm": 0.2911823093891144, + "learning_rate": 1e-06, + "loss": 0.0638, + "step": 1302 + }, + { + "epoch": 2.9681093394077447, + "grad_norm": 0.341012179851532, + "learning_rate": 1e-06, + "loss": 0.0603, + "step": 1303 + }, + { + "epoch": 2.9703872437357632, + "grad_norm": 0.3077567517757416, + "learning_rate": 1e-06, + "loss": 0.0643, + "step": 1304 + }, + { + "epoch": 2.9726651480637813, + "grad_norm": 0.29344695806503296, + "learning_rate": 1e-06, + "loss": 0.062, + "step": 1305 + }, + { + "epoch": 2.9749430523917995, + "grad_norm": 0.3135875165462494, + "learning_rate": 1e-06, + "loss": 0.0612, + "step": 1306 + }, + { + "epoch": 2.977220956719818, + "grad_norm": 0.3218052089214325, + "learning_rate": 1e-06, + "loss": 0.0641, + "step": 1307 + }, + { + "epoch": 2.979498861047836, + "grad_norm": 0.3129740357398987, + "learning_rate": 1e-06, + "loss": 0.0637, + "step": 1308 + }, + { + "epoch": 2.9817767653758542, + "grad_norm": 0.31531840562820435, + "learning_rate": 1e-06, + "loss": 0.0647, + "step": 1309 + }, + { + "epoch": 2.9840546697038723, + "grad_norm": 0.3099454939365387, + "learning_rate": 1e-06, + "loss": 0.0636, + "step": 1310 + }, + { + "epoch": 2.9863325740318905, + "grad_norm": 0.3111046552658081, + "learning_rate": 1e-06, + "loss": 0.0622, + "step": 1311 + }, + { + "epoch": 2.988610478359909, + "grad_norm": 0.29768481850624084, + "learning_rate": 1e-06, + "loss": 0.0593, + "step": 1312 + }, + { + "epoch": 2.990888382687927, + "grad_norm": 0.2913056015968323, + "learning_rate": 1e-06, + "loss": 0.06, + "step": 1313 + }, + { + "epoch": 2.9931662870159452, + "grad_norm": 0.3387179672718048, + "learning_rate": 1e-06, + "loss": 0.0611, + "step": 1314 + }, + { + "epoch": 2.995444191343964, + "grad_norm": 0.3035430908203125, + "learning_rate": 1e-06, + "loss": 0.0613, + "step": 1315 + }, + { + "epoch": 2.997722095671982, + "grad_norm": 1.5779786109924316, + "learning_rate": 1e-06, + "loss": 0.0646, + "step": 1316 + }, + { + "epoch": 3.0, + "grad_norm": 0.30352920293807983, + "learning_rate": 1e-06, + "loss": 0.0603, + "step": 1317 + }, + { + "epoch": 3.0, + "step": 1317, + "total_flos": 0.0, + "train_loss": 0.07083441573637131, + "train_runtime": 38065.4229, + "train_samples_per_second": 17.743, + "train_steps_per_second": 0.035 + } + ], + "logging_steps": 1, + "max_steps": 1317, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 132, + "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": 64, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..5ee3753 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e51cc926c4a4805c591cfe92aa952d0006d63049b02852340d3d63b6ac2d9e0 +size 9425