commit 7a510433131272143053ab742b081fd9f142abcc Author: ModelHub XC Date: Sat Jul 11 01:02:11 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: Neelectric/Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06 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..de8478a --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +base_model: meta-llama/Llama-3.2-1B-Instruct +datasets: Neelectric/MoT_science_Llama3_2048toks +library_name: transformers +model_name: Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06 +tags: +- generated_from_trainer +- trl +- open-r1 +- sft +licence: license +--- + +# Model Card for Llama-3.2-1B-Instruct_SFT_sciencefisher_v00.06 + +This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [Neelectric/MoT_science_Llama3_2048toks](https://huggingface.co/datasets/Neelectric/MoT_science_Llama3_2048toks) 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-3.2-1B-Instruct_SFT_sciencefisher_v00.06", 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_science/runs/ywtvmrqy) + + + +This model was trained with SFT. + +### Framework versions + +- TRL: 1.0.0.dev0 +- Transformers: 4.57.6 +- Pytorch: 2.9.0 +- Datasets: 4.8.3 +- Tokenizers: 0.22.2 + +## Citations + + + +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..f2f11f1 --- /dev/null +++ b/all_results.json @@ -0,0 +1,9 @@ +{ + "ewc_loss": 0.0003185272216796875, + "total_flos": 2.1853937174671524e+18, + "train_loss": 1.1745690016519457, + "train_runtime": 2017.134, + "train_samples": 107517, + "train_samples_per_second": 159.906, + "train_steps_per_second": 0.312 +} \ 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..da3c141 --- /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": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "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": true, + "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.safetensors b/model.safetensors new file mode 100644 index 0000000..29c1d28 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc2bb8cd471f7faa622ba445e5277fbad29594a2463e925412ad7a579e38d52 +size 2996982344 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9d4773c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,11 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": "<|eot_id|>", + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 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..f2f11f1 --- /dev/null +++ b/train_results.json @@ -0,0 +1,9 @@ +{ + "ewc_loss": 0.0003185272216796875, + "total_flos": 2.1853937174671524e+18, + "train_loss": 1.1745690016519457, + "train_runtime": 2017.134, + "train_samples": 107517, + "train_samples_per_second": 159.906, + "train_steps_per_second": 0.312 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..b8549e6 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,6344 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 630, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.004761904761904762, + "ewc_loss": 0.0, + "grad_norm": 8.288021087646484, + "learning_rate": 0.0, + "loss": 1.7656, + "mean_token_accuracy": 0.5768666863441467, + "num_tokens": 582781.0, + "step": 1 + }, + { + "epoch": 0.009523809523809525, + "ewc_loss": 0.0, + "grad_norm": 8.259840965270996, + "learning_rate": 1.5873015873015874e-07, + "loss": 1.7728, + "mean_token_accuracy": 0.5752322673797607, + "num_tokens": 1163696.0, + "step": 2 + }, + { + "epoch": 0.014285714285714285, + "ewc_loss": 2.1941559680271894e-11, + "grad_norm": 8.164591789245605, + "learning_rate": 3.174603174603175e-07, + "loss": 1.7761, + "mean_token_accuracy": 0.5746868848800659, + "num_tokens": 1762000.0, + "step": 3 + }, + { + "epoch": 0.01904761904761905, + "ewc_loss": 3.8744474295526743e-10, + "grad_norm": 8.081689834594727, + "learning_rate": 4.7619047619047623e-07, + "loss": 1.7764, + "mean_token_accuracy": 0.5741555690765381, + "num_tokens": 2363228.0, + "step": 4 + }, + { + "epoch": 0.023809523809523808, + "ewc_loss": 2.7066562324762344e-09, + "grad_norm": 7.886556625366211, + "learning_rate": 6.34920634920635e-07, + "loss": 1.7922, + "mean_token_accuracy": 0.5724079608917236, + "num_tokens": 2968748.0, + "step": 5 + }, + { + "epoch": 0.02857142857142857, + "ewc_loss": 1.2398231774568558e-08, + "grad_norm": 7.912679195404053, + "learning_rate": 7.936507936507937e-07, + "loss": 1.7647, + "mean_token_accuracy": 0.5755211114883423, + "num_tokens": 3564062.0, + "step": 6 + }, + { + "epoch": 0.03333333333333333, + "ewc_loss": 3.236345946788788e-08, + "grad_norm": 7.614343643188477, + "learning_rate": 9.523809523809525e-07, + "loss": 1.7771, + "mean_token_accuracy": 0.571951150894165, + "num_tokens": 4140352.0, + "step": 7 + }, + { + "epoch": 0.0380952380952381, + "ewc_loss": 5.960464477539063e-08, + "grad_norm": 7.1151442527771, + "learning_rate": 1.111111111111111e-06, + "loss": 1.7748, + "mean_token_accuracy": 0.5719363689422607, + "num_tokens": 4748067.0, + "step": 8 + }, + { + "epoch": 0.04285714285714286, + "ewc_loss": 1.3597309589385986e-07, + "grad_norm": 6.122899055480957, + "learning_rate": 1.26984126984127e-06, + "loss": 1.7288, + "mean_token_accuracy": 0.5777610540390015, + "num_tokens": 5333791.0, + "step": 9 + }, + { + "epoch": 0.047619047619047616, + "ewc_loss": 2.0489096641540527e-07, + "grad_norm": 6.0077056884765625, + "learning_rate": 1.4285714285714286e-06, + "loss": 1.7399, + "mean_token_accuracy": 0.5752891302108765, + "num_tokens": 5923564.0, + "step": 10 + }, + { + "epoch": 0.05238095238095238, + "ewc_loss": 2.849847078323364e-07, + "grad_norm": 5.588916778564453, + "learning_rate": 1.5873015873015873e-06, + "loss": 1.7097, + "mean_token_accuracy": 0.5800076723098755, + "num_tokens": 6528559.0, + "step": 11 + }, + { + "epoch": 0.05714285714285714, + "ewc_loss": 6.07222318649292e-07, + "grad_norm": 4.213420391082764, + "learning_rate": 1.746031746031746e-06, + "loss": 1.6597, + "mean_token_accuracy": 0.5851666927337646, + "num_tokens": 7118765.0, + "step": 12 + }, + { + "epoch": 0.06190476190476191, + "ewc_loss": 7.711350917816162e-07, + "grad_norm": 4.142368793487549, + "learning_rate": 1.904761904761905e-06, + "loss": 1.6598, + "mean_token_accuracy": 0.584291398525238, + "num_tokens": 7709226.0, + "step": 13 + }, + { + "epoch": 0.06666666666666667, + "ewc_loss": 9.685754776000977e-07, + "grad_norm": 3.8679122924804688, + "learning_rate": 2.0634920634920634e-06, + "loss": 1.6302, + "mean_token_accuracy": 0.5907664895057678, + "num_tokens": 8298984.0, + "step": 14 + }, + { + "epoch": 0.07142857142857142, + "ewc_loss": 1.1920928955078125e-06, + "grad_norm": 3.7752058506011963, + "learning_rate": 2.222222222222222e-06, + "loss": 1.628, + "mean_token_accuracy": 0.5898678302764893, + "num_tokens": 8875624.0, + "step": 15 + }, + { + "epoch": 0.0761904761904762, + "ewc_loss": 2.115964889526367e-06, + "grad_norm": 3.0702943801879883, + "learning_rate": 2.380952380952381e-06, + "loss": 1.5688, + "mean_token_accuracy": 0.5990877151489258, + "num_tokens": 9448671.0, + "step": 16 + }, + { + "epoch": 0.08095238095238096, + "ewc_loss": 2.6226043701171875e-06, + "grad_norm": 2.727433919906616, + "learning_rate": 2.53968253968254e-06, + "loss": 1.5548, + "mean_token_accuracy": 0.6022457480430603, + "num_tokens": 10049546.0, + "step": 17 + }, + { + "epoch": 0.08571428571428572, + "ewc_loss": 3.0249357223510742e-06, + "grad_norm": 2.559558391571045, + "learning_rate": 2.6984126984126986e-06, + "loss": 1.5608, + "mean_token_accuracy": 0.5994151830673218, + "num_tokens": 10644905.0, + "step": 18 + }, + { + "epoch": 0.09047619047619047, + "ewc_loss": 3.5017728805541992e-06, + "grad_norm": 2.1854259967803955, + "learning_rate": 2.8571428571428573e-06, + "loss": 1.554, + "mean_token_accuracy": 0.601824164390564, + "num_tokens": 11239583.0, + "step": 19 + }, + { + "epoch": 0.09523809523809523, + "ewc_loss": 3.933906555175781e-06, + "grad_norm": 1.942903757095337, + "learning_rate": 3.015873015873016e-06, + "loss": 1.5295, + "mean_token_accuracy": 0.6070558428764343, + "num_tokens": 11827320.0, + "step": 20 + }, + { + "epoch": 0.1, + "ewc_loss": 4.827976226806641e-06, + "grad_norm": 1.885478138923645, + "learning_rate": 3.1746031746031746e-06, + "loss": 1.4813, + "mean_token_accuracy": 0.615217924118042, + "num_tokens": 12425511.0, + "step": 21 + }, + { + "epoch": 0.10476190476190476, + "ewc_loss": 6.0498714447021484e-06, + "grad_norm": 2.386911630630493, + "learning_rate": 3.3333333333333333e-06, + "loss": 1.4867, + "mean_token_accuracy": 0.6138845086097717, + "num_tokens": 13015708.0, + "step": 22 + }, + { + "epoch": 0.10952380952380952, + "ewc_loss": 6.973743438720703e-06, + "grad_norm": 2.189323663711548, + "learning_rate": 3.492063492063492e-06, + "loss": 1.4694, + "mean_token_accuracy": 0.6165228486061096, + "num_tokens": 13608875.0, + "step": 23 + }, + { + "epoch": 0.11428571428571428, + "ewc_loss": 7.867813110351562e-06, + "grad_norm": 2.005537748336792, + "learning_rate": 3.6507936507936507e-06, + "loss": 1.4766, + "mean_token_accuracy": 0.6140103340148926, + "num_tokens": 14204297.0, + "step": 24 + }, + { + "epoch": 0.11904761904761904, + "ewc_loss": 8.58306884765625e-06, + "grad_norm": 1.7334803342819214, + "learning_rate": 3.80952380952381e-06, + "loss": 1.4617, + "mean_token_accuracy": 0.6164035797119141, + "num_tokens": 14782206.0, + "step": 25 + }, + { + "epoch": 0.12380952380952381, + "ewc_loss": 9.357929229736328e-06, + "grad_norm": 1.4836677312850952, + "learning_rate": 3.968253968253968e-06, + "loss": 1.4392, + "mean_token_accuracy": 0.6210890412330627, + "num_tokens": 15377829.0, + "step": 26 + }, + { + "epoch": 0.12857142857142856, + "ewc_loss": 1.0073184967041016e-05, + "grad_norm": 1.2513998746871948, + "learning_rate": 4.126984126984127e-06, + "loss": 1.4329, + "mean_token_accuracy": 0.6221857070922852, + "num_tokens": 15975819.0, + "step": 27 + }, + { + "epoch": 0.13333333333333333, + "ewc_loss": 1.0669231414794922e-05, + "grad_norm": 1.1351968050003052, + "learning_rate": 4.2857142857142855e-06, + "loss": 1.4195, + "mean_token_accuracy": 0.62498539686203, + "num_tokens": 16577839.0, + "step": 28 + }, + { + "epoch": 0.1380952380952381, + "ewc_loss": 1.1205673217773438e-05, + "grad_norm": 1.1534360647201538, + "learning_rate": 4.444444444444444e-06, + "loss": 1.413, + "mean_token_accuracy": 0.625639796257019, + "num_tokens": 17164831.0, + "step": 29 + }, + { + "epoch": 0.14285714285714285, + "ewc_loss": 1.1920928955078125e-05, + "grad_norm": 1.211313009262085, + "learning_rate": 4.603174603174604e-06, + "loss": 1.3991, + "mean_token_accuracy": 0.6288596391677856, + "num_tokens": 17770476.0, + "step": 30 + }, + { + "epoch": 0.14761904761904762, + "ewc_loss": 1.2636184692382812e-05, + "grad_norm": 1.175661563873291, + "learning_rate": 4.761904761904762e-06, + "loss": 1.3849, + "mean_token_accuracy": 0.6300349831581116, + "num_tokens": 18360862.0, + "step": 31 + }, + { + "epoch": 0.1523809523809524, + "ewc_loss": 1.3470649719238281e-05, + "grad_norm": 1.0536342859268188, + "learning_rate": 4.920634920634921e-06, + "loss": 1.4001, + "mean_token_accuracy": 0.6267796754837036, + "num_tokens": 18944338.0, + "step": 32 + }, + { + "epoch": 0.15714285714285714, + "ewc_loss": 1.4007091522216797e-05, + "grad_norm": 0.923198401927948, + "learning_rate": 5.07936507936508e-06, + "loss": 1.374, + "mean_token_accuracy": 0.6326636672019958, + "num_tokens": 19540189.0, + "step": 33 + }, + { + "epoch": 0.1619047619047619, + "ewc_loss": 1.4841556549072266e-05, + "grad_norm": 0.9605510234832764, + "learning_rate": 5.2380952380952384e-06, + "loss": 1.3707, + "mean_token_accuracy": 0.6338174939155579, + "num_tokens": 20138131.0, + "step": 34 + }, + { + "epoch": 0.16666666666666666, + "ewc_loss": 1.537799835205078e-05, + "grad_norm": 0.9490035772323608, + "learning_rate": 5.396825396825397e-06, + "loss": 1.3872, + "mean_token_accuracy": 0.6293957233428955, + "num_tokens": 20735187.0, + "step": 35 + }, + { + "epoch": 0.17142857142857143, + "ewc_loss": 1.5735626220703125e-05, + "grad_norm": 0.9345461130142212, + "learning_rate": 5.555555555555557e-06, + "loss": 1.3633, + "mean_token_accuracy": 0.633197546005249, + "num_tokens": 21316383.0, + "step": 36 + }, + { + "epoch": 0.1761904761904762, + "ewc_loss": 1.6450881958007812e-05, + "grad_norm": 0.8252076506614685, + "learning_rate": 5.7142857142857145e-06, + "loss": 1.3398, + "mean_token_accuracy": 0.6397838592529297, + "num_tokens": 21910626.0, + "step": 37 + }, + { + "epoch": 0.18095238095238095, + "ewc_loss": 1.6927719116210938e-05, + "grad_norm": 0.7578451633453369, + "learning_rate": 5.873015873015874e-06, + "loss": 1.3614, + "mean_token_accuracy": 0.6338489055633545, + "num_tokens": 22503955.0, + "step": 38 + }, + { + "epoch": 0.18571428571428572, + "ewc_loss": 1.728534698486328e-05, + "grad_norm": 0.7257813215255737, + "learning_rate": 6.031746031746032e-06, + "loss": 1.3563, + "mean_token_accuracy": 0.6351788640022278, + "num_tokens": 23093310.0, + "step": 39 + }, + { + "epoch": 0.19047619047619047, + "ewc_loss": 1.823902130126953e-05, + "grad_norm": 0.7297197580337524, + "learning_rate": 6.1904761904761914e-06, + "loss": 1.327, + "mean_token_accuracy": 0.6416804194450378, + "num_tokens": 23681028.0, + "step": 40 + }, + { + "epoch": 0.19523809523809524, + "ewc_loss": 1.8715858459472656e-05, + "grad_norm": 0.678717851638794, + "learning_rate": 6.349206349206349e-06, + "loss": 1.3292, + "mean_token_accuracy": 0.6411443948745728, + "num_tokens": 24275532.0, + "step": 41 + }, + { + "epoch": 0.2, + "ewc_loss": 1.9073486328125e-05, + "grad_norm": 0.6785043478012085, + "learning_rate": 6.507936507936509e-06, + "loss": 1.3331, + "mean_token_accuracy": 0.6407352685928345, + "num_tokens": 24868054.0, + "step": 42 + }, + { + "epoch": 0.20476190476190476, + "ewc_loss": 1.9431114196777344e-05, + "grad_norm": 0.6338180899620056, + "learning_rate": 6.666666666666667e-06, + "loss": 1.3346, + "mean_token_accuracy": 0.6393934488296509, + "num_tokens": 25459842.0, + "step": 43 + }, + { + "epoch": 0.20952380952380953, + "ewc_loss": 1.990795135498047e-05, + "grad_norm": 0.6361852884292603, + "learning_rate": 6.825396825396826e-06, + "loss": 1.3412, + "mean_token_accuracy": 0.6371585130691528, + "num_tokens": 26051340.0, + "step": 44 + }, + { + "epoch": 0.21428571428571427, + "ewc_loss": 2.0503997802734375e-05, + "grad_norm": 0.6392099261283875, + "learning_rate": 6.984126984126984e-06, + "loss": 1.3209, + "mean_token_accuracy": 0.6427756547927856, + "num_tokens": 26635240.0, + "step": 45 + }, + { + "epoch": 0.21904761904761905, + "ewc_loss": 2.110004425048828e-05, + "grad_norm": 0.6442952156066895, + "learning_rate": 7.1428571428571436e-06, + "loss": 1.322, + "mean_token_accuracy": 0.6418497562408447, + "num_tokens": 27228570.0, + "step": 46 + }, + { + "epoch": 0.22380952380952382, + "ewc_loss": 2.193450927734375e-05, + "grad_norm": 0.6580334901809692, + "learning_rate": 7.301587301587301e-06, + "loss": 1.3162, + "mean_token_accuracy": 0.6436214447021484, + "num_tokens": 27825958.0, + "step": 47 + }, + { + "epoch": 0.22857142857142856, + "ewc_loss": 2.2411346435546875e-05, + "grad_norm": 0.6492692828178406, + "learning_rate": 7.460317460317461e-06, + "loss": 1.3098, + "mean_token_accuracy": 0.643293023109436, + "num_tokens": 28418470.0, + "step": 48 + }, + { + "epoch": 0.23333333333333334, + "ewc_loss": 2.3245811462402344e-05, + "grad_norm": 0.6469078660011292, + "learning_rate": 7.61904761904762e-06, + "loss": 1.3066, + "mean_token_accuracy": 0.6446727514266968, + "num_tokens": 29013060.0, + "step": 49 + }, + { + "epoch": 0.23809523809523808, + "ewc_loss": 2.384185791015625e-05, + "grad_norm": 0.6333920955657959, + "learning_rate": 7.77777777777778e-06, + "loss": 1.3155, + "mean_token_accuracy": 0.6416593790054321, + "num_tokens": 29624709.0, + "step": 50 + }, + { + "epoch": 0.24285714285714285, + "ewc_loss": 2.4437904357910156e-05, + "grad_norm": 0.630892276763916, + "learning_rate": 7.936507936507936e-06, + "loss": 1.3079, + "mean_token_accuracy": 0.6437000036239624, + "num_tokens": 30227928.0, + "step": 51 + }, + { + "epoch": 0.24761904761904763, + "ewc_loss": 2.47955322265625e-05, + "grad_norm": 0.5994595885276794, + "learning_rate": 8.095238095238097e-06, + "loss": 1.3095, + "mean_token_accuracy": 0.6425583362579346, + "num_tokens": 30823383.0, + "step": 52 + }, + { + "epoch": 0.2523809523809524, + "ewc_loss": 2.574920654296875e-05, + "grad_norm": 0.5976656079292297, + "learning_rate": 8.253968253968254e-06, + "loss": 1.291, + "mean_token_accuracy": 0.6478736400604248, + "num_tokens": 31418593.0, + "step": 53 + }, + { + "epoch": 0.2571428571428571, + "ewc_loss": 2.6464462280273438e-05, + "grad_norm": 0.6434232592582703, + "learning_rate": 8.412698412698414e-06, + "loss": 1.2836, + "mean_token_accuracy": 0.6491208672523499, + "num_tokens": 32008377.0, + "step": 54 + }, + { + "epoch": 0.2619047619047619, + "ewc_loss": 2.682209014892578e-05, + "grad_norm": 0.633117139339447, + "learning_rate": 8.571428571428571e-06, + "loss": 1.2905, + "mean_token_accuracy": 0.6463996171951294, + "num_tokens": 32600302.0, + "step": 55 + }, + { + "epoch": 0.26666666666666666, + "ewc_loss": 2.777576446533203e-05, + "grad_norm": 0.6181126832962036, + "learning_rate": 8.730158730158731e-06, + "loss": 1.2918, + "mean_token_accuracy": 0.6465189456939697, + "num_tokens": 33201147.0, + "step": 56 + }, + { + "epoch": 0.2714285714285714, + "ewc_loss": 2.872943878173828e-05, + "grad_norm": 0.5806352496147156, + "learning_rate": 8.888888888888888e-06, + "loss": 1.2714, + "mean_token_accuracy": 0.6510688066482544, + "num_tokens": 33790565.0, + "step": 57 + }, + { + "epoch": 0.2761904761904762, + "ewc_loss": 2.9921531677246094e-05, + "grad_norm": 0.6705154776573181, + "learning_rate": 9.047619047619049e-06, + "loss": 1.2771, + "mean_token_accuracy": 0.6506456136703491, + "num_tokens": 34387187.0, + "step": 58 + }, + { + "epoch": 0.28095238095238095, + "ewc_loss": 3.0517578125e-05, + "grad_norm": 0.6201812028884888, + "learning_rate": 9.206349206349207e-06, + "loss": 1.2857, + "mean_token_accuracy": 0.6484991908073425, + "num_tokens": 35000480.0, + "step": 59 + }, + { + "epoch": 0.2857142857142857, + "ewc_loss": 3.123283386230469e-05, + "grad_norm": 0.6412603855133057, + "learning_rate": 9.365079365079366e-06, + "loss": 1.2683, + "mean_token_accuracy": 0.6524419784545898, + "num_tokens": 35588577.0, + "step": 60 + }, + { + "epoch": 0.2904761904761905, + "ewc_loss": 3.1948089599609375e-05, + "grad_norm": 0.644237756729126, + "learning_rate": 9.523809523809525e-06, + "loss": 1.272, + "mean_token_accuracy": 0.6506987810134888, + "num_tokens": 36179186.0, + "step": 61 + }, + { + "epoch": 0.29523809523809524, + "ewc_loss": 3.266334533691406e-05, + "grad_norm": 0.5917180180549622, + "learning_rate": 9.682539682539683e-06, + "loss": 1.2793, + "mean_token_accuracy": 0.6496506929397583, + "num_tokens": 36787338.0, + "step": 62 + }, + { + "epoch": 0.3, + "ewc_loss": 3.337860107421875e-05, + "grad_norm": 0.6421388983726501, + "learning_rate": 9.841269841269842e-06, + "loss": 1.2683, + "mean_token_accuracy": 0.6511802673339844, + "num_tokens": 37376232.0, + "step": 63 + }, + { + "epoch": 0.3047619047619048, + "ewc_loss": 3.4332275390625e-05, + "grad_norm": 0.5740679502487183, + "learning_rate": 1e-05, + "loss": 1.26, + "mean_token_accuracy": 0.65364670753479, + "num_tokens": 37965066.0, + "step": 64 + }, + { + "epoch": 0.30952380952380953, + "ewc_loss": 3.528594970703125e-05, + "grad_norm": 0.6459997892379761, + "learning_rate": 1e-05, + "loss": 1.2733, + "mean_token_accuracy": 0.6502293944358826, + "num_tokens": 38556474.0, + "step": 65 + }, + { + "epoch": 0.3142857142857143, + "ewc_loss": 3.600120544433594e-05, + "grad_norm": 0.5708662271499634, + "learning_rate": 1e-05, + "loss": 1.2843, + "mean_token_accuracy": 0.6482360363006592, + "num_tokens": 39153957.0, + "step": 66 + }, + { + "epoch": 0.319047619047619, + "ewc_loss": 3.6716461181640625e-05, + "grad_norm": 0.6389670968055725, + "learning_rate": 1e-05, + "loss": 1.2717, + "mean_token_accuracy": 0.6506360173225403, + "num_tokens": 39743079.0, + "step": 67 + }, + { + "epoch": 0.3238095238095238, + "ewc_loss": 3.7670135498046875e-05, + "grad_norm": 0.6586436033248901, + "learning_rate": 1e-05, + "loss": 1.2564, + "mean_token_accuracy": 0.654888391494751, + "num_tokens": 40341422.0, + "step": 68 + }, + { + "epoch": 0.32857142857142857, + "ewc_loss": 3.8623809814453125e-05, + "grad_norm": 0.6264131665229797, + "learning_rate": 1e-05, + "loss": 1.2548, + "mean_token_accuracy": 0.6545756459236145, + "num_tokens": 40930579.0, + "step": 69 + }, + { + "epoch": 0.3333333333333333, + "ewc_loss": 3.9577484130859375e-05, + "grad_norm": 0.6541554927825928, + "learning_rate": 1e-05, + "loss": 1.2502, + "mean_token_accuracy": 0.6559510231018066, + "num_tokens": 41521392.0, + "step": 70 + }, + { + "epoch": 0.3380952380952381, + "ewc_loss": 4.0531158447265625e-05, + "grad_norm": 0.6627256274223328, + "learning_rate": 1e-05, + "loss": 1.2679, + "mean_token_accuracy": 0.651904821395874, + "num_tokens": 42126117.0, + "step": 71 + }, + { + "epoch": 0.34285714285714286, + "ewc_loss": 4.100799560546875e-05, + "grad_norm": 0.635160505771637, + "learning_rate": 1e-05, + "loss": 1.2463, + "mean_token_accuracy": 0.6567121744155884, + "num_tokens": 42717085.0, + "step": 72 + }, + { + "epoch": 0.3476190476190476, + "ewc_loss": 4.220008850097656e-05, + "grad_norm": 0.7168654203414917, + "learning_rate": 1e-05, + "loss": 1.2504, + "mean_token_accuracy": 0.6550968885421753, + "num_tokens": 43300932.0, + "step": 73 + }, + { + "epoch": 0.3523809523809524, + "ewc_loss": 4.291534423828125e-05, + "grad_norm": 0.712209165096283, + "learning_rate": 1e-05, + "loss": 1.2642, + "mean_token_accuracy": 0.6511810421943665, + "num_tokens": 43885512.0, + "step": 74 + }, + { + "epoch": 0.35714285714285715, + "ewc_loss": 4.3392181396484375e-05, + "grad_norm": 0.6051343083381653, + "learning_rate": 1e-05, + "loss": 1.249, + "mean_token_accuracy": 0.6552016139030457, + "num_tokens": 44482626.0, + "step": 75 + }, + { + "epoch": 0.3619047619047619, + "ewc_loss": 4.410743713378906e-05, + "grad_norm": 0.6990807056427002, + "learning_rate": 1e-05, + "loss": 1.2584, + "mean_token_accuracy": 0.6525766253471375, + "num_tokens": 45073331.0, + "step": 76 + }, + { + "epoch": 0.36666666666666664, + "ewc_loss": 4.506111145019531e-05, + "grad_norm": 0.6724445819854736, + "learning_rate": 1e-05, + "loss": 1.2566, + "mean_token_accuracy": 0.6541537046432495, + "num_tokens": 45683001.0, + "step": 77 + }, + { + "epoch": 0.37142857142857144, + "ewc_loss": 4.553794860839844e-05, + "grad_norm": 0.6027698516845703, + "learning_rate": 1e-05, + "loss": 1.26, + "mean_token_accuracy": 0.6538848280906677, + "num_tokens": 46280871.0, + "step": 78 + }, + { + "epoch": 0.3761904761904762, + "ewc_loss": 4.6253204345703125e-05, + "grad_norm": 0.6557961106300354, + "learning_rate": 1e-05, + "loss": 1.2402, + "mean_token_accuracy": 0.6560071110725403, + "num_tokens": 46860927.0, + "step": 79 + }, + { + "epoch": 0.38095238095238093, + "ewc_loss": 4.673004150390625e-05, + "grad_norm": 0.672111451625824, + "learning_rate": 1e-05, + "loss": 1.2557, + "mean_token_accuracy": 0.6535240411758423, + "num_tokens": 47450747.0, + "step": 80 + }, + { + "epoch": 0.38571428571428573, + "ewc_loss": 4.7206878662109375e-05, + "grad_norm": 0.6007350087165833, + "learning_rate": 1e-05, + "loss": 1.2531, + "mean_token_accuracy": 0.6552194356918335, + "num_tokens": 48053355.0, + "step": 81 + }, + { + "epoch": 0.3904761904761905, + "ewc_loss": 4.8160552978515625e-05, + "grad_norm": 0.7301807999610901, + "learning_rate": 1e-05, + "loss": 1.224, + "mean_token_accuracy": 0.6597331762313843, + "num_tokens": 48654406.0, + "step": 82 + }, + { + "epoch": 0.3952380952380952, + "ewc_loss": 4.863739013671875e-05, + "grad_norm": 0.6621304154396057, + "learning_rate": 1e-05, + "loss": 1.2314, + "mean_token_accuracy": 0.6582869291305542, + "num_tokens": 49253902.0, + "step": 83 + }, + { + "epoch": 0.4, + "ewc_loss": 4.9114227294921875e-05, + "grad_norm": 0.6037917733192444, + "learning_rate": 1e-05, + "loss": 1.2484, + "mean_token_accuracy": 0.6550902724266052, + "num_tokens": 49851728.0, + "step": 84 + }, + { + "epoch": 0.40476190476190477, + "ewc_loss": 4.9591064453125e-05, + "grad_norm": 0.6156448721885681, + "learning_rate": 1e-05, + "loss": 1.2544, + "mean_token_accuracy": 0.6535503268241882, + "num_tokens": 50456288.0, + "step": 85 + }, + { + "epoch": 0.4095238095238095, + "ewc_loss": 5.0067901611328125e-05, + "grad_norm": 0.6396542191505432, + "learning_rate": 1e-05, + "loss": 1.2609, + "mean_token_accuracy": 0.6525429487228394, + "num_tokens": 51058176.0, + "step": 86 + }, + { + "epoch": 0.4142857142857143, + "ewc_loss": 5.078315734863281e-05, + "grad_norm": 0.6346539258956909, + "learning_rate": 1e-05, + "loss": 1.2458, + "mean_token_accuracy": 0.6555163860321045, + "num_tokens": 51665178.0, + "step": 87 + }, + { + "epoch": 0.41904761904761906, + "ewc_loss": 5.14984130859375e-05, + "grad_norm": 0.734662652015686, + "learning_rate": 1e-05, + "loss": 1.2307, + "mean_token_accuracy": 0.6585971117019653, + "num_tokens": 52237427.0, + "step": 88 + }, + { + "epoch": 0.4238095238095238, + "ewc_loss": 5.245208740234375e-05, + "grad_norm": 0.6333789825439453, + "learning_rate": 1e-05, + "loss": 1.2526, + "mean_token_accuracy": 0.6529765725135803, + "num_tokens": 52850605.0, + "step": 89 + }, + { + "epoch": 0.42857142857142855, + "ewc_loss": 5.269050598144531e-05, + "grad_norm": 0.637751042842865, + "learning_rate": 1e-05, + "loss": 1.214, + "mean_token_accuracy": 0.6617136597633362, + "num_tokens": 53435907.0, + "step": 90 + }, + { + "epoch": 0.43333333333333335, + "ewc_loss": 5.316734313964844e-05, + "grad_norm": 0.6406871676445007, + "learning_rate": 1e-05, + "loss": 1.2513, + "mean_token_accuracy": 0.6529551148414612, + "num_tokens": 54032690.0, + "step": 91 + }, + { + "epoch": 0.4380952380952381, + "ewc_loss": 5.364418029785156e-05, + "grad_norm": 0.5955501794815063, + "learning_rate": 1e-05, + "loss": 1.2372, + "mean_token_accuracy": 0.6577882170677185, + "num_tokens": 54631908.0, + "step": 92 + }, + { + "epoch": 0.44285714285714284, + "ewc_loss": 5.412101745605469e-05, + "grad_norm": 0.6889634728431702, + "learning_rate": 1e-05, + "loss": 1.2309, + "mean_token_accuracy": 0.6583378911018372, + "num_tokens": 55218598.0, + "step": 93 + }, + { + "epoch": 0.44761904761904764, + "ewc_loss": 5.555152893066406e-05, + "grad_norm": 0.7095226049423218, + "learning_rate": 1e-05, + "loss": 1.2547, + "mean_token_accuracy": 0.6527206897735596, + "num_tokens": 55814642.0, + "step": 94 + }, + { + "epoch": 0.4523809523809524, + "ewc_loss": 5.626678466796875e-05, + "grad_norm": 0.6113548278808594, + "learning_rate": 1e-05, + "loss": 1.2266, + "mean_token_accuracy": 0.660247802734375, + "num_tokens": 56410000.0, + "step": 95 + }, + { + "epoch": 0.45714285714285713, + "ewc_loss": 5.698204040527344e-05, + "grad_norm": 0.7079361081123352, + "learning_rate": 1e-05, + "loss": 1.236, + "mean_token_accuracy": 0.6573811769485474, + "num_tokens": 57001902.0, + "step": 96 + }, + { + "epoch": 0.46190476190476193, + "ewc_loss": 5.745887756347656e-05, + "grad_norm": 0.6543773412704468, + "learning_rate": 1e-05, + "loss": 1.2449, + "mean_token_accuracy": 0.6550565958023071, + "num_tokens": 57612227.0, + "step": 97 + }, + { + "epoch": 0.4666666666666667, + "ewc_loss": 5.745887756347656e-05, + "grad_norm": 0.686723530292511, + "learning_rate": 1e-05, + "loss": 1.2307, + "mean_token_accuracy": 0.6572390794754028, + "num_tokens": 58198983.0, + "step": 98 + }, + { + "epoch": 0.4714285714285714, + "ewc_loss": 5.793571472167969e-05, + "grad_norm": 0.794451117515564, + "learning_rate": 1e-05, + "loss": 1.2526, + "mean_token_accuracy": 0.6535791158676147, + "num_tokens": 58805739.0, + "step": 99 + }, + { + "epoch": 0.47619047619047616, + "ewc_loss": 5.8650970458984375e-05, + "grad_norm": 0.6614603400230408, + "learning_rate": 1e-05, + "loss": 1.2196, + "mean_token_accuracy": 0.6609863042831421, + "num_tokens": 59386596.0, + "step": 100 + }, + { + "epoch": 0.48095238095238096, + "ewc_loss": 5.9604644775390625e-05, + "grad_norm": 0.8497462868690491, + "learning_rate": 1e-05, + "loss": 1.2279, + "mean_token_accuracy": 0.6586320400238037, + "num_tokens": 59976677.0, + "step": 101 + }, + { + "epoch": 0.4857142857142857, + "ewc_loss": 6.008148193359375e-05, + "grad_norm": 0.6434870362281799, + "learning_rate": 1e-05, + "loss": 1.2406, + "mean_token_accuracy": 0.6560160517692566, + "num_tokens": 60581023.0, + "step": 102 + }, + { + "epoch": 0.49047619047619045, + "ewc_loss": 6.079673767089844e-05, + "grad_norm": 0.81642746925354, + "learning_rate": 1e-05, + "loss": 1.231, + "mean_token_accuracy": 0.6587409973144531, + "num_tokens": 61177587.0, + "step": 103 + }, + { + "epoch": 0.49523809523809526, + "ewc_loss": 6.103515625e-05, + "grad_norm": 0.6543331742286682, + "learning_rate": 1e-05, + "loss": 1.2246, + "mean_token_accuracy": 0.6584880352020264, + "num_tokens": 61759739.0, + "step": 104 + }, + { + "epoch": 0.5, + "ewc_loss": 6.151199340820312e-05, + "grad_norm": 0.7787368297576904, + "learning_rate": 1e-05, + "loss": 1.2324, + "mean_token_accuracy": 0.6578609943389893, + "num_tokens": 62343623.0, + "step": 105 + }, + { + "epoch": 0.5047619047619047, + "ewc_loss": 6.246566772460938e-05, + "grad_norm": 0.681171178817749, + "learning_rate": 1e-05, + "loss": 1.2265, + "mean_token_accuracy": 0.6585533022880554, + "num_tokens": 62936609.0, + "step": 106 + }, + { + "epoch": 0.5095238095238095, + "ewc_loss": 6.29425048828125e-05, + "grad_norm": 0.7038831114768982, + "learning_rate": 1e-05, + "loss": 1.2232, + "mean_token_accuracy": 0.6601380109786987, + "num_tokens": 63540035.0, + "step": 107 + }, + { + "epoch": 0.5142857142857142, + "ewc_loss": 6.389617919921875e-05, + "grad_norm": 0.6259385943412781, + "learning_rate": 1e-05, + "loss": 1.2293, + "mean_token_accuracy": 0.6583002209663391, + "num_tokens": 64137406.0, + "step": 108 + }, + { + "epoch": 0.5190476190476191, + "ewc_loss": 6.437301635742188e-05, + "grad_norm": 0.6318548917770386, + "learning_rate": 1e-05, + "loss": 1.2146, + "mean_token_accuracy": 0.6620792150497437, + "num_tokens": 64747343.0, + "step": 109 + }, + { + "epoch": 0.5238095238095238, + "ewc_loss": 6.437301635742188e-05, + "grad_norm": 0.5972775220870972, + "learning_rate": 1e-05, + "loss": 1.2141, + "mean_token_accuracy": 0.6610211133956909, + "num_tokens": 65340433.0, + "step": 110 + }, + { + "epoch": 0.5285714285714286, + "ewc_loss": 6.4849853515625e-05, + "grad_norm": 0.555220365524292, + "learning_rate": 1e-05, + "loss": 1.207, + "mean_token_accuracy": 0.6629165410995483, + "num_tokens": 65928375.0, + "step": 111 + }, + { + "epoch": 0.5333333333333333, + "ewc_loss": 6.4849853515625e-05, + "grad_norm": 0.5961295962333679, + "learning_rate": 1e-05, + "loss": 1.2327, + "mean_token_accuracy": 0.6570777297019958, + "num_tokens": 66527455.0, + "step": 112 + }, + { + "epoch": 0.5380952380952381, + "ewc_loss": 6.532669067382812e-05, + "grad_norm": 0.5626892447471619, + "learning_rate": 1e-05, + "loss": 1.2042, + "mean_token_accuracy": 0.6643252372741699, + "num_tokens": 67120147.0, + "step": 113 + }, + { + "epoch": 0.5428571428571428, + "ewc_loss": 6.580352783203125e-05, + "grad_norm": 0.5593003630638123, + "learning_rate": 1e-05, + "loss": 1.2224, + "mean_token_accuracy": 0.6598198413848877, + "num_tokens": 67726850.0, + "step": 114 + }, + { + "epoch": 0.5476190476190477, + "ewc_loss": 6.628036499023438e-05, + "grad_norm": 0.5357206463813782, + "learning_rate": 1e-05, + "loss": 1.2168, + "mean_token_accuracy": 0.6608775854110718, + "num_tokens": 68316713.0, + "step": 115 + }, + { + "epoch": 0.5523809523809524, + "ewc_loss": 6.723403930664062e-05, + "grad_norm": 0.60752272605896, + "learning_rate": 1e-05, + "loss": 1.2198, + "mean_token_accuracy": 0.6601148247718811, + "num_tokens": 68892365.0, + "step": 116 + }, + { + "epoch": 0.5571428571428572, + "ewc_loss": 6.818771362304688e-05, + "grad_norm": 0.613874614238739, + "learning_rate": 1e-05, + "loss": 1.2255, + "mean_token_accuracy": 0.6590179800987244, + "num_tokens": 69505524.0, + "step": 117 + }, + { + "epoch": 0.5619047619047619, + "ewc_loss": 6.866455078125e-05, + "grad_norm": 0.6986200213432312, + "learning_rate": 1e-05, + "loss": 1.208, + "mean_token_accuracy": 0.662236213684082, + "num_tokens": 70095302.0, + "step": 118 + }, + { + "epoch": 0.5666666666666667, + "ewc_loss": 6.914138793945312e-05, + "grad_norm": 0.5868731737136841, + "learning_rate": 1e-05, + "loss": 1.2204, + "mean_token_accuracy": 0.6595965623855591, + "num_tokens": 70694971.0, + "step": 119 + }, + { + "epoch": 0.5714285714285714, + "ewc_loss": 6.961822509765625e-05, + "grad_norm": 0.6726260185241699, + "learning_rate": 1e-05, + "loss": 1.219, + "mean_token_accuracy": 0.6606526374816895, + "num_tokens": 71279415.0, + "step": 120 + }, + { + "epoch": 0.5761904761904761, + "ewc_loss": 7.05718994140625e-05, + "grad_norm": 0.6847469806671143, + "learning_rate": 1e-05, + "loss": 1.2136, + "mean_token_accuracy": 0.6616922616958618, + "num_tokens": 71869014.0, + "step": 121 + }, + { + "epoch": 0.580952380952381, + "ewc_loss": 7.104873657226562e-05, + "grad_norm": 0.5946815609931946, + "learning_rate": 1e-05, + "loss": 1.2216, + "mean_token_accuracy": 0.6589410305023193, + "num_tokens": 72472715.0, + "step": 122 + }, + { + "epoch": 0.5857142857142857, + "ewc_loss": 7.104873657226562e-05, + "grad_norm": 0.7214268445968628, + "learning_rate": 1e-05, + "loss": 1.2136, + "mean_token_accuracy": 0.6611043810844421, + "num_tokens": 73055740.0, + "step": 123 + }, + { + "epoch": 0.5904761904761905, + "ewc_loss": 7.104873657226562e-05, + "grad_norm": 0.5754434466362, + "learning_rate": 1e-05, + "loss": 1.197, + "mean_token_accuracy": 0.6657254695892334, + "num_tokens": 73639151.0, + "step": 124 + }, + { + "epoch": 0.5952380952380952, + "ewc_loss": 7.152557373046875e-05, + "grad_norm": 0.7243437767028809, + "learning_rate": 1e-05, + "loss": 1.2159, + "mean_token_accuracy": 0.6623419523239136, + "num_tokens": 74216756.0, + "step": 125 + }, + { + "epoch": 0.6, + "ewc_loss": 7.200241088867188e-05, + "grad_norm": 0.6202445030212402, + "learning_rate": 1e-05, + "loss": 1.2109, + "mean_token_accuracy": 0.6620380878448486, + "num_tokens": 74813953.0, + "step": 126 + }, + { + "epoch": 0.6047619047619047, + "ewc_loss": 7.343292236328125e-05, + "grad_norm": 0.6378516554832458, + "learning_rate": 1e-05, + "loss": 1.2112, + "mean_token_accuracy": 0.6623302698135376, + "num_tokens": 75410691.0, + "step": 127 + }, + { + "epoch": 0.6095238095238096, + "ewc_loss": 7.390975952148438e-05, + "grad_norm": 0.6438445448875427, + "learning_rate": 1e-05, + "loss": 1.2283, + "mean_token_accuracy": 0.6572309732437134, + "num_tokens": 75996496.0, + "step": 128 + }, + { + "epoch": 0.6142857142857143, + "ewc_loss": 7.534027099609375e-05, + "grad_norm": 0.613435685634613, + "learning_rate": 1e-05, + "loss": 1.2035, + "mean_token_accuracy": 0.6648565530776978, + "num_tokens": 76585198.0, + "step": 129 + }, + { + "epoch": 0.6190476190476191, + "ewc_loss": 7.534027099609375e-05, + "grad_norm": 0.6530207991600037, + "learning_rate": 1e-05, + "loss": 1.192, + "mean_token_accuracy": 0.6663568019866943, + "num_tokens": 77191596.0, + "step": 130 + }, + { + "epoch": 0.6238095238095238, + "ewc_loss": 7.62939453125e-05, + "grad_norm": 0.6292564868927002, + "learning_rate": 1e-05, + "loss": 1.2093, + "mean_token_accuracy": 0.662111222743988, + "num_tokens": 77796998.0, + "step": 131 + }, + { + "epoch": 0.6285714285714286, + "ewc_loss": 7.677078247070312e-05, + "grad_norm": 0.7430987358093262, + "learning_rate": 1e-05, + "loss": 1.2221, + "mean_token_accuracy": 0.6589036583900452, + "num_tokens": 78395104.0, + "step": 132 + }, + { + "epoch": 0.6333333333333333, + "ewc_loss": 7.724761962890625e-05, + "grad_norm": 0.7552570104598999, + "learning_rate": 1e-05, + "loss": 1.2085, + "mean_token_accuracy": 0.6627721786499023, + "num_tokens": 78988563.0, + "step": 133 + }, + { + "epoch": 0.638095238095238, + "ewc_loss": 7.867813110351562e-05, + "grad_norm": 0.5875095129013062, + "learning_rate": 1e-05, + "loss": 1.2284, + "mean_token_accuracy": 0.6573638319969177, + "num_tokens": 79599633.0, + "step": 134 + }, + { + "epoch": 0.6428571428571429, + "ewc_loss": 7.915496826171875e-05, + "grad_norm": 0.6983376145362854, + "learning_rate": 1e-05, + "loss": 1.2196, + "mean_token_accuracy": 0.6600324511528015, + "num_tokens": 80196954.0, + "step": 135 + }, + { + "epoch": 0.6476190476190476, + "ewc_loss": 7.915496826171875e-05, + "grad_norm": 0.647911787033081, + "learning_rate": 1e-05, + "loss": 1.2189, + "mean_token_accuracy": 0.6596968770027161, + "num_tokens": 80790959.0, + "step": 136 + }, + { + "epoch": 0.6523809523809524, + "ewc_loss": 7.963180541992188e-05, + "grad_norm": 0.6033630967140198, + "learning_rate": 1e-05, + "loss": 1.2049, + "mean_token_accuracy": 0.6640007495880127, + "num_tokens": 81363350.0, + "step": 137 + }, + { + "epoch": 0.6571428571428571, + "ewc_loss": 8.058547973632812e-05, + "grad_norm": 0.7302987575531006, + "learning_rate": 1e-05, + "loss": 1.2068, + "mean_token_accuracy": 0.6629554033279419, + "num_tokens": 81960356.0, + "step": 138 + }, + { + "epoch": 0.6619047619047619, + "ewc_loss": 8.106231689453125e-05, + "grad_norm": 0.6291311383247375, + "learning_rate": 1e-05, + "loss": 1.2165, + "mean_token_accuracy": 0.6605432033538818, + "num_tokens": 82573967.0, + "step": 139 + }, + { + "epoch": 0.6666666666666666, + "ewc_loss": 8.106231689453125e-05, + "grad_norm": 0.77925705909729, + "learning_rate": 1e-05, + "loss": 1.2047, + "mean_token_accuracy": 0.6634047627449036, + "num_tokens": 83170751.0, + "step": 140 + }, + { + "epoch": 0.6714285714285714, + "ewc_loss": 8.153915405273438e-05, + "grad_norm": 0.5943464040756226, + "learning_rate": 1e-05, + "loss": 1.1863, + "mean_token_accuracy": 0.6674145460128784, + "num_tokens": 83744022.0, + "step": 141 + }, + { + "epoch": 0.6761904761904762, + "ewc_loss": 8.20159912109375e-05, + "grad_norm": 0.7075134515762329, + "learning_rate": 1e-05, + "loss": 1.2224, + "mean_token_accuracy": 0.6587080359458923, + "num_tokens": 84336667.0, + "step": 142 + }, + { + "epoch": 0.680952380952381, + "ewc_loss": 8.296966552734375e-05, + "grad_norm": 0.6221350431442261, + "learning_rate": 1e-05, + "loss": 1.2038, + "mean_token_accuracy": 0.6635011434555054, + "num_tokens": 84927599.0, + "step": 143 + }, + { + "epoch": 0.6857142857142857, + "ewc_loss": 8.344650268554688e-05, + "grad_norm": 0.6779686808586121, + "learning_rate": 1e-05, + "loss": 1.2028, + "mean_token_accuracy": 0.6638973951339722, + "num_tokens": 85516121.0, + "step": 144 + }, + { + "epoch": 0.6904761904761905, + "ewc_loss": 8.392333984375e-05, + "grad_norm": 0.6363284587860107, + "learning_rate": 1e-05, + "loss": 1.1977, + "mean_token_accuracy": 0.6649864315986633, + "num_tokens": 86106161.0, + "step": 145 + }, + { + "epoch": 0.6952380952380952, + "ewc_loss": 8.440017700195312e-05, + "grad_norm": 0.6659577488899231, + "learning_rate": 1e-05, + "loss": 1.2138, + "mean_token_accuracy": 0.6618106365203857, + "num_tokens": 86723880.0, + "step": 146 + }, + { + "epoch": 0.7, + "ewc_loss": 8.487701416015625e-05, + "grad_norm": 0.7540108561515808, + "learning_rate": 1e-05, + "loss": 1.2086, + "mean_token_accuracy": 0.6632779240608215, + "num_tokens": 87327542.0, + "step": 147 + }, + { + "epoch": 0.7047619047619048, + "ewc_loss": 8.58306884765625e-05, + "grad_norm": 0.5985829830169678, + "learning_rate": 1e-05, + "loss": 1.203, + "mean_token_accuracy": 0.6631919145584106, + "num_tokens": 87912557.0, + "step": 148 + }, + { + "epoch": 0.7095238095238096, + "ewc_loss": 8.630752563476562e-05, + "grad_norm": 0.7489357590675354, + "learning_rate": 1e-05, + "loss": 1.2142, + "mean_token_accuracy": 0.6614629626274109, + "num_tokens": 88514499.0, + "step": 149 + }, + { + "epoch": 0.7142857142857143, + "ewc_loss": 8.630752563476562e-05, + "grad_norm": 0.5868208408355713, + "learning_rate": 1e-05, + "loss": 1.1933, + "mean_token_accuracy": 0.6661566495895386, + "num_tokens": 89090412.0, + "step": 150 + }, + { + "epoch": 0.719047619047619, + "ewc_loss": 8.678436279296875e-05, + "grad_norm": 0.6479862928390503, + "learning_rate": 1e-05, + "loss": 1.2032, + "mean_token_accuracy": 0.66373610496521, + "num_tokens": 89689944.0, + "step": 151 + }, + { + "epoch": 0.7238095238095238, + "ewc_loss": 8.678436279296875e-05, + "grad_norm": 0.6591699123382568, + "learning_rate": 1e-05, + "loss": 1.2144, + "mean_token_accuracy": 0.6610070466995239, + "num_tokens": 90281605.0, + "step": 152 + }, + { + "epoch": 0.7285714285714285, + "ewc_loss": 8.726119995117188e-05, + "grad_norm": 0.6273887157440186, + "learning_rate": 1e-05, + "loss": 1.2151, + "mean_token_accuracy": 0.6615536212921143, + "num_tokens": 90877169.0, + "step": 153 + }, + { + "epoch": 0.7333333333333333, + "ewc_loss": 8.7738037109375e-05, + "grad_norm": 0.6174249053001404, + "learning_rate": 1e-05, + "loss": 1.2196, + "mean_token_accuracy": 0.6595685482025146, + "num_tokens": 91473587.0, + "step": 154 + }, + { + "epoch": 0.7380952380952381, + "ewc_loss": 8.821487426757812e-05, + "grad_norm": 0.6399466395378113, + "learning_rate": 1e-05, + "loss": 1.2124, + "mean_token_accuracy": 0.6614258289337158, + "num_tokens": 92066142.0, + "step": 155 + }, + { + "epoch": 0.7428571428571429, + "ewc_loss": 8.916854858398438e-05, + "grad_norm": 0.6208449602127075, + "learning_rate": 1e-05, + "loss": 1.1943, + "mean_token_accuracy": 0.6653621196746826, + "num_tokens": 92671294.0, + "step": 156 + }, + { + "epoch": 0.7476190476190476, + "ewc_loss": 8.916854858398438e-05, + "grad_norm": 0.6701812148094177, + "learning_rate": 1e-05, + "loss": 1.1971, + "mean_token_accuracy": 0.664833128452301, + "num_tokens": 93267004.0, + "step": 157 + }, + { + "epoch": 0.7523809523809524, + "ewc_loss": 8.96453857421875e-05, + "grad_norm": 0.5950197577476501, + "learning_rate": 1e-05, + "loss": 1.2151, + "mean_token_accuracy": 0.6610333323478699, + "num_tokens": 93865099.0, + "step": 158 + }, + { + "epoch": 0.7571428571428571, + "ewc_loss": 9.012222290039062e-05, + "grad_norm": 0.6761289238929749, + "learning_rate": 1e-05, + "loss": 1.1882, + "mean_token_accuracy": 0.6674374341964722, + "num_tokens": 94449283.0, + "step": 159 + }, + { + "epoch": 0.7619047619047619, + "ewc_loss": 9.059906005859375e-05, + "grad_norm": 0.6658070087432861, + "learning_rate": 1e-05, + "loss": 1.1986, + "mean_token_accuracy": 0.664233386516571, + "num_tokens": 95037160.0, + "step": 160 + }, + { + "epoch": 0.7666666666666667, + "ewc_loss": 9.059906005859375e-05, + "grad_norm": 0.6344804167747498, + "learning_rate": 1e-05, + "loss": 1.1817, + "mean_token_accuracy": 0.6688761711120605, + "num_tokens": 95620329.0, + "step": 161 + }, + { + "epoch": 0.7714285714285715, + "ewc_loss": 9.250640869140625e-05, + "grad_norm": 0.6172727346420288, + "learning_rate": 1e-05, + "loss": 1.2036, + "mean_token_accuracy": 0.6623877286911011, + "num_tokens": 96202979.0, + "step": 162 + }, + { + "epoch": 0.7761904761904762, + "ewc_loss": 9.250640869140625e-05, + "grad_norm": 0.576758086681366, + "learning_rate": 1e-05, + "loss": 1.1976, + "mean_token_accuracy": 0.664994478225708, + "num_tokens": 96794135.0, + "step": 163 + }, + { + "epoch": 0.780952380952381, + "ewc_loss": 9.250640869140625e-05, + "grad_norm": 0.5772844552993774, + "learning_rate": 1e-05, + "loss": 1.1877, + "mean_token_accuracy": 0.6661553382873535, + "num_tokens": 97380180.0, + "step": 164 + }, + { + "epoch": 0.7857142857142857, + "ewc_loss": 9.34600830078125e-05, + "grad_norm": 0.5949466228485107, + "learning_rate": 1e-05, + "loss": 1.206, + "mean_token_accuracy": 0.6634715795516968, + "num_tokens": 97979583.0, + "step": 165 + }, + { + "epoch": 0.7904761904761904, + "ewc_loss": 9.34600830078125e-05, + "grad_norm": 0.7309633493423462, + "learning_rate": 1e-05, + "loss": 1.1876, + "mean_token_accuracy": 0.6680320501327515, + "num_tokens": 98573453.0, + "step": 166 + }, + { + "epoch": 0.7952380952380952, + "ewc_loss": 9.393692016601562e-05, + "grad_norm": 0.5999202728271484, + "learning_rate": 1e-05, + "loss": 1.1948, + "mean_token_accuracy": 0.665028989315033, + "num_tokens": 99162518.0, + "step": 167 + }, + { + "epoch": 0.8, + "ewc_loss": 9.489059448242188e-05, + "grad_norm": 0.6260110139846802, + "learning_rate": 1e-05, + "loss": 1.1918, + "mean_token_accuracy": 0.6654178500175476, + "num_tokens": 99755688.0, + "step": 168 + }, + { + "epoch": 0.8047619047619048, + "ewc_loss": 9.489059448242188e-05, + "grad_norm": 0.5720483064651489, + "learning_rate": 1e-05, + "loss": 1.1982, + "mean_token_accuracy": 0.6642268896102905, + "num_tokens": 100367122.0, + "step": 169 + }, + { + "epoch": 0.8095238095238095, + "ewc_loss": 9.5367431640625e-05, + "grad_norm": 0.5899868011474609, + "learning_rate": 1e-05, + "loss": 1.1924, + "mean_token_accuracy": 0.6649571061134338, + "num_tokens": 100966663.0, + "step": 170 + }, + { + "epoch": 0.8142857142857143, + "ewc_loss": 9.5367431640625e-05, + "grad_norm": 0.6257776618003845, + "learning_rate": 1e-05, + "loss": 1.2054, + "mean_token_accuracy": 0.6636680364608765, + "num_tokens": 101561561.0, + "step": 171 + }, + { + "epoch": 0.819047619047619, + "ewc_loss": 9.632110595703125e-05, + "grad_norm": 0.5902847051620483, + "learning_rate": 1e-05, + "loss": 1.2118, + "mean_token_accuracy": 0.6617633104324341, + "num_tokens": 102150367.0, + "step": 172 + }, + { + "epoch": 0.8238095238095238, + "ewc_loss": 9.72747802734375e-05, + "grad_norm": 0.6149330139160156, + "learning_rate": 1e-05, + "loss": 1.2016, + "mean_token_accuracy": 0.6645001173019409, + "num_tokens": 102744438.0, + "step": 173 + }, + { + "epoch": 0.8285714285714286, + "ewc_loss": 9.822845458984375e-05, + "grad_norm": 0.6235402226448059, + "learning_rate": 1e-05, + "loss": 1.2003, + "mean_token_accuracy": 0.6640701293945312, + "num_tokens": 103336159.0, + "step": 174 + }, + { + "epoch": 0.8333333333333334, + "ewc_loss": 9.870529174804688e-05, + "grad_norm": 0.7237935066223145, + "learning_rate": 1e-05, + "loss": 1.2054, + "mean_token_accuracy": 0.6627719402313232, + "num_tokens": 103933457.0, + "step": 175 + }, + { + "epoch": 0.8380952380952381, + "ewc_loss": 9.870529174804688e-05, + "grad_norm": 0.6574564576148987, + "learning_rate": 1e-05, + "loss": 1.1914, + "mean_token_accuracy": 0.6652967929840088, + "num_tokens": 104528020.0, + "step": 176 + }, + { + "epoch": 0.8428571428571429, + "ewc_loss": 9.918212890625e-05, + "grad_norm": 0.6675592660903931, + "learning_rate": 1e-05, + "loss": 1.2203, + "mean_token_accuracy": 0.6594563722610474, + "num_tokens": 105126562.0, + "step": 177 + }, + { + "epoch": 0.8476190476190476, + "ewc_loss": 9.918212890625e-05, + "grad_norm": 0.6076056957244873, + "learning_rate": 1e-05, + "loss": 1.1857, + "mean_token_accuracy": 0.6670438647270203, + "num_tokens": 105730229.0, + "step": 178 + }, + { + "epoch": 0.8523809523809524, + "ewc_loss": 0.00010013580322265625, + "grad_norm": 0.6883161664009094, + "learning_rate": 1e-05, + "loss": 1.207, + "mean_token_accuracy": 0.6618679761886597, + "num_tokens": 106338239.0, + "step": 179 + }, + { + "epoch": 0.8571428571428571, + "ewc_loss": 0.00010061264038085938, + "grad_norm": 0.6851189136505127, + "learning_rate": 1e-05, + "loss": 1.2045, + "mean_token_accuracy": 0.6627447605133057, + "num_tokens": 106929782.0, + "step": 180 + }, + { + "epoch": 0.861904761904762, + "ewc_loss": 0.00010156631469726562, + "grad_norm": 0.6659080982208252, + "learning_rate": 1e-05, + "loss": 1.1995, + "mean_token_accuracy": 0.6644128561019897, + "num_tokens": 107516950.0, + "step": 181 + }, + { + "epoch": 0.8666666666666667, + "ewc_loss": 0.00010156631469726562, + "grad_norm": 0.6930555105209351, + "learning_rate": 1e-05, + "loss": 1.189, + "mean_token_accuracy": 0.6657518744468689, + "num_tokens": 108104046.0, + "step": 182 + }, + { + "epoch": 0.8714285714285714, + "ewc_loss": 0.00010204315185546875, + "grad_norm": 0.5535694360733032, + "learning_rate": 1e-05, + "loss": 1.2055, + "mean_token_accuracy": 0.6628379225730896, + "num_tokens": 108711068.0, + "step": 183 + }, + { + "epoch": 0.8761904761904762, + "ewc_loss": 0.00010204315185546875, + "grad_norm": 0.6049023270606995, + "learning_rate": 1e-05, + "loss": 1.1751, + "mean_token_accuracy": 0.6691579222679138, + "num_tokens": 109294847.0, + "step": 184 + }, + { + "epoch": 0.8809523809523809, + "ewc_loss": 0.00010204315185546875, + "grad_norm": 0.5582939982414246, + "learning_rate": 1e-05, + "loss": 1.1948, + "mean_token_accuracy": 0.6648955345153809, + "num_tokens": 109903424.0, + "step": 185 + }, + { + "epoch": 0.8857142857142857, + "ewc_loss": 0.00010251998901367188, + "grad_norm": 0.6902385354042053, + "learning_rate": 1e-05, + "loss": 1.1959, + "mean_token_accuracy": 0.6643984317779541, + "num_tokens": 110515082.0, + "step": 186 + }, + { + "epoch": 0.8904761904761904, + "ewc_loss": 0.00010347366333007812, + "grad_norm": 0.598051130771637, + "learning_rate": 1e-05, + "loss": 1.1951, + "mean_token_accuracy": 0.6649090647697449, + "num_tokens": 111105456.0, + "step": 187 + }, + { + "epoch": 0.8952380952380953, + "ewc_loss": 0.00010395050048828125, + "grad_norm": 0.6643283367156982, + "learning_rate": 1e-05, + "loss": 1.1957, + "mean_token_accuracy": 0.6654419302940369, + "num_tokens": 111699029.0, + "step": 188 + }, + { + "epoch": 0.9, + "ewc_loss": 0.00010538101196289062, + "grad_norm": 0.6105185747146606, + "learning_rate": 1e-05, + "loss": 1.1725, + "mean_token_accuracy": 0.6694669723510742, + "num_tokens": 112280321.0, + "step": 189 + }, + { + "epoch": 0.9047619047619048, + "ewc_loss": 0.00010585784912109375, + "grad_norm": 0.6771377325057983, + "learning_rate": 1e-05, + "loss": 1.1743, + "mean_token_accuracy": 0.6691171526908875, + "num_tokens": 112860009.0, + "step": 190 + }, + { + "epoch": 0.9095238095238095, + "ewc_loss": 0.00010633468627929688, + "grad_norm": 0.6756452918052673, + "learning_rate": 1e-05, + "loss": 1.1939, + "mean_token_accuracy": 0.6648098230361938, + "num_tokens": 113457303.0, + "step": 191 + }, + { + "epoch": 0.9142857142857143, + "ewc_loss": 0.00010776519775390625, + "grad_norm": 0.5745353698730469, + "learning_rate": 1e-05, + "loss": 1.1876, + "mean_token_accuracy": 0.6669417023658752, + "num_tokens": 114054977.0, + "step": 192 + }, + { + "epoch": 0.919047619047619, + "ewc_loss": 0.00010824203491210938, + "grad_norm": 0.5740221738815308, + "learning_rate": 1e-05, + "loss": 1.1845, + "mean_token_accuracy": 0.6670070886611938, + "num_tokens": 114641555.0, + "step": 193 + }, + { + "epoch": 0.9238095238095239, + "ewc_loss": 0.00010919570922851562, + "grad_norm": 0.6284497380256653, + "learning_rate": 1e-05, + "loss": 1.2007, + "mean_token_accuracy": 0.6643847823143005, + "num_tokens": 115241437.0, + "step": 194 + }, + { + "epoch": 0.9285714285714286, + "ewc_loss": 0.00010919570922851562, + "grad_norm": 0.5833153128623962, + "learning_rate": 1e-05, + "loss": 1.1782, + "mean_token_accuracy": 0.6683659553527832, + "num_tokens": 115845775.0, + "step": 195 + }, + { + "epoch": 0.9333333333333333, + "ewc_loss": 0.00010967254638671875, + "grad_norm": 0.6330277323722839, + "learning_rate": 1e-05, + "loss": 1.1851, + "mean_token_accuracy": 0.6675300598144531, + "num_tokens": 116452623.0, + "step": 196 + }, + { + "epoch": 0.9380952380952381, + "ewc_loss": 0.00011014938354492188, + "grad_norm": 0.5661508440971375, + "learning_rate": 1e-05, + "loss": 1.1929, + "mean_token_accuracy": 0.6653560400009155, + "num_tokens": 117045570.0, + "step": 197 + }, + { + "epoch": 0.9428571428571428, + "ewc_loss": 0.00011014938354492188, + "grad_norm": 0.6743243336677551, + "learning_rate": 1e-05, + "loss": 1.1706, + "mean_token_accuracy": 0.6707065105438232, + "num_tokens": 117654535.0, + "step": 198 + }, + { + "epoch": 0.9476190476190476, + "ewc_loss": 0.00011014938354492188, + "grad_norm": 0.5636059641838074, + "learning_rate": 1e-05, + "loss": 1.184, + "mean_token_accuracy": 0.6679331064224243, + "num_tokens": 118247244.0, + "step": 199 + }, + { + "epoch": 0.9523809523809523, + "ewc_loss": 0.00011110305786132812, + "grad_norm": 0.6201364398002625, + "learning_rate": 1e-05, + "loss": 1.1781, + "mean_token_accuracy": 0.6689824461936951, + "num_tokens": 118843074.0, + "step": 200 + }, + { + "epoch": 0.9571428571428572, + "ewc_loss": 0.00011110305786132812, + "grad_norm": 0.5889277458190918, + "learning_rate": 1e-05, + "loss": 1.1782, + "mean_token_accuracy": 0.6685971021652222, + "num_tokens": 119445023.0, + "step": 201 + }, + { + "epoch": 0.9619047619047619, + "ewc_loss": 0.00011157989501953125, + "grad_norm": 0.599198043346405, + "learning_rate": 1e-05, + "loss": 1.1933, + "mean_token_accuracy": 0.6657448410987854, + "num_tokens": 120045748.0, + "step": 202 + }, + { + "epoch": 0.9666666666666667, + "ewc_loss": 0.00011205673217773438, + "grad_norm": 0.6123493909835815, + "learning_rate": 1e-05, + "loss": 1.1854, + "mean_token_accuracy": 0.6666924953460693, + "num_tokens": 120635079.0, + "step": 203 + }, + { + "epoch": 0.9714285714285714, + "ewc_loss": 0.00011205673217773438, + "grad_norm": 0.5863441228866577, + "learning_rate": 1e-05, + "loss": 1.1861, + "mean_token_accuracy": 0.665822446346283, + "num_tokens": 121220486.0, + "step": 204 + }, + { + "epoch": 0.9761904761904762, + "ewc_loss": 0.00011301040649414062, + "grad_norm": 0.5958433151245117, + "learning_rate": 1e-05, + "loss": 1.1874, + "mean_token_accuracy": 0.666378915309906, + "num_tokens": 121800676.0, + "step": 205 + }, + { + "epoch": 0.9809523809523809, + "ewc_loss": 0.00011301040649414062, + "grad_norm": 0.594279944896698, + "learning_rate": 1e-05, + "loss": 1.1913, + "mean_token_accuracy": 0.6657083034515381, + "num_tokens": 122409399.0, + "step": 206 + }, + { + "epoch": 0.9857142857142858, + "ewc_loss": 0.00011348724365234375, + "grad_norm": 0.7570769786834717, + "learning_rate": 1e-05, + "loss": 1.1722, + "mean_token_accuracy": 0.6697901487350464, + "num_tokens": 123003502.0, + "step": 207 + }, + { + "epoch": 0.9904761904761905, + "ewc_loss": 0.00011396408081054688, + "grad_norm": 0.583046555519104, + "learning_rate": 1e-05, + "loss": 1.1891, + "mean_token_accuracy": 0.6667864322662354, + "num_tokens": 123595838.0, + "step": 208 + }, + { + "epoch": 0.9952380952380953, + "ewc_loss": 0.00011539459228515625, + "grad_norm": 0.6892156004905701, + "learning_rate": 1e-05, + "loss": 1.1868, + "mean_token_accuracy": 0.666805624961853, + "num_tokens": 124166476.0, + "step": 209 + }, + { + "epoch": 1.0, + "ewc_loss": 0.00011587142944335938, + "grad_norm": 0.60233473777771, + "learning_rate": 1e-05, + "loss": 1.1758, + "mean_token_accuracy": 0.6685359477996826, + "num_tokens": 124761423.0, + "step": 210 + }, + { + "epoch": 1.0047619047619047, + "ewc_loss": 0.00011682510375976562, + "grad_norm": 0.6940872669219971, + "learning_rate": 1e-05, + "loss": 1.1836, + "mean_token_accuracy": 0.6664184927940369, + "num_tokens": 125364371.0, + "step": 211 + }, + { + "epoch": 1.0095238095238095, + "ewc_loss": 0.00011777877807617188, + "grad_norm": 0.6687514781951904, + "learning_rate": 1e-05, + "loss": 1.1425, + "mean_token_accuracy": 0.6756107807159424, + "num_tokens": 125954118.0, + "step": 212 + }, + { + "epoch": 1.0142857142857142, + "ewc_loss": 0.00011777877807617188, + "grad_norm": 0.6151235699653625, + "learning_rate": 1e-05, + "loss": 1.1478, + "mean_token_accuracy": 0.6743132472038269, + "num_tokens": 126544991.0, + "step": 213 + }, + { + "epoch": 1.019047619047619, + "ewc_loss": 0.000118255615234375, + "grad_norm": 0.6397988200187683, + "learning_rate": 1e-05, + "loss": 1.1507, + "mean_token_accuracy": 0.6746599674224854, + "num_tokens": 127151772.0, + "step": 214 + }, + { + "epoch": 1.0238095238095237, + "ewc_loss": 0.00011873245239257812, + "grad_norm": 0.6342989802360535, + "learning_rate": 1e-05, + "loss": 1.155, + "mean_token_accuracy": 0.6730877757072449, + "num_tokens": 127762517.0, + "step": 215 + }, + { + "epoch": 1.0285714285714285, + "ewc_loss": 0.00011968612670898438, + "grad_norm": 0.6400744318962097, + "learning_rate": 1e-05, + "loss": 1.1597, + "mean_token_accuracy": 0.6719417572021484, + "num_tokens": 128358892.0, + "step": 216 + }, + { + "epoch": 1.0333333333333334, + "ewc_loss": 0.0001201629638671875, + "grad_norm": 0.6657331585884094, + "learning_rate": 1e-05, + "loss": 1.1566, + "mean_token_accuracy": 0.6724061965942383, + "num_tokens": 128930309.0, + "step": 217 + }, + { + "epoch": 1.0380952380952382, + "ewc_loss": 0.00012063980102539062, + "grad_norm": 0.6766237616539001, + "learning_rate": 1e-05, + "loss": 1.142, + "mean_token_accuracy": 0.6765217185020447, + "num_tokens": 129537678.0, + "step": 218 + }, + { + "epoch": 1.042857142857143, + "ewc_loss": 0.00012111663818359375, + "grad_norm": 0.6086320281028748, + "learning_rate": 1e-05, + "loss": 1.1567, + "mean_token_accuracy": 0.6731134653091431, + "num_tokens": 130113717.0, + "step": 219 + }, + { + "epoch": 1.0476190476190477, + "ewc_loss": 0.0001220703125, + "grad_norm": 0.7390220761299133, + "learning_rate": 1e-05, + "loss": 1.1639, + "mean_token_accuracy": 0.6712628602981567, + "num_tokens": 130724521.0, + "step": 220 + }, + { + "epoch": 1.0523809523809524, + "ewc_loss": 0.00012302398681640625, + "grad_norm": 0.6970507502555847, + "learning_rate": 1e-05, + "loss": 1.1493, + "mean_token_accuracy": 0.6746741533279419, + "num_tokens": 131298037.0, + "step": 221 + }, + { + "epoch": 1.0571428571428572, + "ewc_loss": 0.00012302398681640625, + "grad_norm": 0.6448761224746704, + "learning_rate": 1e-05, + "loss": 1.1567, + "mean_token_accuracy": 0.6726914644241333, + "num_tokens": 131909779.0, + "step": 222 + }, + { + "epoch": 1.061904761904762, + "ewc_loss": 0.00012302398681640625, + "grad_norm": 0.7612317800521851, + "learning_rate": 1e-05, + "loss": 1.1546, + "mean_token_accuracy": 0.6728156805038452, + "num_tokens": 132506621.0, + "step": 223 + }, + { + "epoch": 1.0666666666666667, + "ewc_loss": 0.00012302398681640625, + "grad_norm": 0.6246641278266907, + "learning_rate": 1e-05, + "loss": 1.1585, + "mean_token_accuracy": 0.6720011234283447, + "num_tokens": 133124443.0, + "step": 224 + }, + { + "epoch": 1.0714285714285714, + "ewc_loss": 0.00012302398681640625, + "grad_norm": 0.7723531723022461, + "learning_rate": 1e-05, + "loss": 1.1694, + "mean_token_accuracy": 0.6692392826080322, + "num_tokens": 133719672.0, + "step": 225 + }, + { + "epoch": 1.0761904761904761, + "ewc_loss": 0.0001239776611328125, + "grad_norm": 0.626321017742157, + "learning_rate": 1e-05, + "loss": 1.1442, + "mean_token_accuracy": 0.6742342710494995, + "num_tokens": 134309852.0, + "step": 226 + }, + { + "epoch": 1.0809523809523809, + "ewc_loss": 0.00012493133544921875, + "grad_norm": 0.7580941319465637, + "learning_rate": 1e-05, + "loss": 1.1564, + "mean_token_accuracy": 0.6717894673347473, + "num_tokens": 134890952.0, + "step": 227 + }, + { + "epoch": 1.0857142857142856, + "ewc_loss": 0.00012493133544921875, + "grad_norm": 0.6416178941726685, + "learning_rate": 1e-05, + "loss": 1.1228, + "mean_token_accuracy": 0.6809052228927612, + "num_tokens": 135479588.0, + "step": 228 + }, + { + "epoch": 1.0904761904761904, + "ewc_loss": 0.00012493133544921875, + "grad_norm": 0.7048900127410889, + "learning_rate": 1e-05, + "loss": 1.1487, + "mean_token_accuracy": 0.6742109656333923, + "num_tokens": 136065836.0, + "step": 229 + }, + { + "epoch": 1.0952380952380953, + "ewc_loss": 0.00012493133544921875, + "grad_norm": 0.7079852223396301, + "learning_rate": 1e-05, + "loss": 1.1468, + "mean_token_accuracy": 0.6756322979927063, + "num_tokens": 136668062.0, + "step": 230 + }, + { + "epoch": 1.1, + "ewc_loss": 0.000125885009765625, + "grad_norm": 0.6603137850761414, + "learning_rate": 1e-05, + "loss": 1.149, + "mean_token_accuracy": 0.6736916303634644, + "num_tokens": 137256533.0, + "step": 231 + }, + { + "epoch": 1.1047619047619048, + "ewc_loss": 0.00012683868408203125, + "grad_norm": 0.6657995581626892, + "learning_rate": 1e-05, + "loss": 1.1551, + "mean_token_accuracy": 0.6728039979934692, + "num_tokens": 137848246.0, + "step": 232 + }, + { + "epoch": 1.1095238095238096, + "ewc_loss": 0.0001277923583984375, + "grad_norm": 0.7172450423240662, + "learning_rate": 1e-05, + "loss": 1.1585, + "mean_token_accuracy": 0.672776997089386, + "num_tokens": 138450870.0, + "step": 233 + }, + { + "epoch": 1.1142857142857143, + "ewc_loss": 0.0001277923583984375, + "grad_norm": 0.6164809465408325, + "learning_rate": 1e-05, + "loss": 1.1588, + "mean_token_accuracy": 0.671145498752594, + "num_tokens": 139048178.0, + "step": 234 + }, + { + "epoch": 1.119047619047619, + "ewc_loss": 0.0001277923583984375, + "grad_norm": 0.7396353483200073, + "learning_rate": 1e-05, + "loss": 1.149, + "mean_token_accuracy": 0.6741979718208313, + "num_tokens": 139647536.0, + "step": 235 + }, + { + "epoch": 1.1238095238095238, + "ewc_loss": 0.0001277923583984375, + "grad_norm": 0.6293736100196838, + "learning_rate": 1e-05, + "loss": 1.1521, + "mean_token_accuracy": 0.6737790703773499, + "num_tokens": 140237569.0, + "step": 236 + }, + { + "epoch": 1.1285714285714286, + "ewc_loss": 0.00012874603271484375, + "grad_norm": 0.722634494304657, + "learning_rate": 1e-05, + "loss": 1.1553, + "mean_token_accuracy": 0.6723701357841492, + "num_tokens": 140808948.0, + "step": 237 + }, + { + "epoch": 1.1333333333333333, + "ewc_loss": 0.00012969970703125, + "grad_norm": 0.6444483399391174, + "learning_rate": 1e-05, + "loss": 1.1512, + "mean_token_accuracy": 0.6727620959281921, + "num_tokens": 141387906.0, + "step": 238 + }, + { + "epoch": 1.138095238095238, + "ewc_loss": 0.00013065338134765625, + "grad_norm": 0.6716317534446716, + "learning_rate": 1e-05, + "loss": 1.1513, + "mean_token_accuracy": 0.6741545796394348, + "num_tokens": 141991024.0, + "step": 239 + }, + { + "epoch": 1.1428571428571428, + "ewc_loss": 0.00013065338134765625, + "grad_norm": 0.6552713513374329, + "learning_rate": 1e-05, + "loss": 1.1311, + "mean_token_accuracy": 0.6786593198776245, + "num_tokens": 142585170.0, + "step": 240 + }, + { + "epoch": 1.1476190476190475, + "ewc_loss": 0.00013065338134765625, + "grad_norm": 0.6885207891464233, + "learning_rate": 1e-05, + "loss": 1.1602, + "mean_token_accuracy": 0.671287477016449, + "num_tokens": 143178473.0, + "step": 241 + }, + { + "epoch": 1.1523809523809523, + "ewc_loss": 0.0001316070556640625, + "grad_norm": 0.6194717288017273, + "learning_rate": 1e-05, + "loss": 1.16, + "mean_token_accuracy": 0.6703994274139404, + "num_tokens": 143782184.0, + "step": 242 + }, + { + "epoch": 1.157142857142857, + "ewc_loss": 0.000133514404296875, + "grad_norm": 0.6374044418334961, + "learning_rate": 1e-05, + "loss": 1.1425, + "mean_token_accuracy": 0.6752372980117798, + "num_tokens": 144383051.0, + "step": 243 + }, + { + "epoch": 1.161904761904762, + "ewc_loss": 0.00013446807861328125, + "grad_norm": 0.6159126162528992, + "learning_rate": 1e-05, + "loss": 1.1527, + "mean_token_accuracy": 0.6738500595092773, + "num_tokens": 144977872.0, + "step": 244 + }, + { + "epoch": 1.1666666666666667, + "ewc_loss": 0.00013446807861328125, + "grad_norm": 0.6623093485832214, + "learning_rate": 1e-05, + "loss": 1.155, + "mean_token_accuracy": 0.6730083227157593, + "num_tokens": 145573077.0, + "step": 245 + }, + { + "epoch": 1.1714285714285715, + "ewc_loss": 0.0001354217529296875, + "grad_norm": 0.7325803637504578, + "learning_rate": 1e-05, + "loss": 1.1557, + "mean_token_accuracy": 0.6735334396362305, + "num_tokens": 146165107.0, + "step": 246 + }, + { + "epoch": 1.1761904761904762, + "ewc_loss": 0.0001354217529296875, + "grad_norm": 0.5923898220062256, + "learning_rate": 1e-05, + "loss": 1.1486, + "mean_token_accuracy": 0.6737574934959412, + "num_tokens": 146763356.0, + "step": 247 + }, + { + "epoch": 1.180952380952381, + "ewc_loss": 0.0001354217529296875, + "grad_norm": 0.7248337268829346, + "learning_rate": 1e-05, + "loss": 1.1453, + "mean_token_accuracy": 0.6756094694137573, + "num_tokens": 147358035.0, + "step": 248 + }, + { + "epoch": 1.1857142857142857, + "ewc_loss": 0.00013637542724609375, + "grad_norm": 0.6490603089332581, + "learning_rate": 1e-05, + "loss": 1.1616, + "mean_token_accuracy": 0.6706793308258057, + "num_tokens": 147955530.0, + "step": 249 + }, + { + "epoch": 1.1904761904761905, + "ewc_loss": 0.00013637542724609375, + "grad_norm": 0.6352701187133789, + "learning_rate": 1e-05, + "loss": 1.1563, + "mean_token_accuracy": 0.6722099781036377, + "num_tokens": 148547950.0, + "step": 250 + }, + { + "epoch": 1.1952380952380952, + "ewc_loss": 0.00013637542724609375, + "grad_norm": 0.6453648805618286, + "learning_rate": 1e-05, + "loss": 1.1403, + "mean_token_accuracy": 0.6759542226791382, + "num_tokens": 149127280.0, + "step": 251 + }, + { + "epoch": 1.2, + "ewc_loss": 0.00013637542724609375, + "grad_norm": 0.6950802803039551, + "learning_rate": 1e-05, + "loss": 1.1488, + "mean_token_accuracy": 0.6745351552963257, + "num_tokens": 149735096.0, + "step": 252 + }, + { + "epoch": 1.2047619047619047, + "ewc_loss": 0.0001373291015625, + "grad_norm": 0.6548479199409485, + "learning_rate": 1e-05, + "loss": 1.1522, + "mean_token_accuracy": 0.6739116907119751, + "num_tokens": 150338864.0, + "step": 253 + }, + { + "epoch": 1.2095238095238094, + "ewc_loss": 0.00013828277587890625, + "grad_norm": 0.6387858986854553, + "learning_rate": 1e-05, + "loss": 1.1329, + "mean_token_accuracy": 0.6780798435211182, + "num_tokens": 150940365.0, + "step": 254 + }, + { + "epoch": 1.2142857142857142, + "ewc_loss": 0.00013828277587890625, + "grad_norm": 0.714256763458252, + "learning_rate": 1e-05, + "loss": 1.155, + "mean_token_accuracy": 0.6730684041976929, + "num_tokens": 151517902.0, + "step": 255 + }, + { + "epoch": 1.2190476190476192, + "ewc_loss": 0.0001392364501953125, + "grad_norm": 0.6362060308456421, + "learning_rate": 1e-05, + "loss": 1.132, + "mean_token_accuracy": 0.6782940030097961, + "num_tokens": 152093932.0, + "step": 256 + }, + { + "epoch": 1.223809523809524, + "ewc_loss": 0.0001392364501953125, + "grad_norm": 0.7105438709259033, + "learning_rate": 1e-05, + "loss": 1.1379, + "mean_token_accuracy": 0.6773548722267151, + "num_tokens": 152690003.0, + "step": 257 + }, + { + "epoch": 1.2285714285714286, + "ewc_loss": 0.000141143798828125, + "grad_norm": 0.6334164142608643, + "learning_rate": 1e-05, + "loss": 1.14, + "mean_token_accuracy": 0.6767330169677734, + "num_tokens": 153278014.0, + "step": 258 + }, + { + "epoch": 1.2333333333333334, + "ewc_loss": 0.000141143798828125, + "grad_norm": 0.758152425289154, + "learning_rate": 1e-05, + "loss": 1.1475, + "mean_token_accuracy": 0.6749956607818604, + "num_tokens": 153871781.0, + "step": 259 + }, + { + "epoch": 1.2380952380952381, + "ewc_loss": 0.000141143798828125, + "grad_norm": 0.6939448118209839, + "learning_rate": 1e-05, + "loss": 1.1497, + "mean_token_accuracy": 0.6739530563354492, + "num_tokens": 154466124.0, + "step": 260 + }, + { + "epoch": 1.2428571428571429, + "ewc_loss": 0.00014209747314453125, + "grad_norm": 0.603489100933075, + "learning_rate": 1e-05, + "loss": 1.1439, + "mean_token_accuracy": 0.6745976805686951, + "num_tokens": 155073053.0, + "step": 261 + }, + { + "epoch": 1.2476190476190476, + "ewc_loss": 0.00014209747314453125, + "grad_norm": 0.711421012878418, + "learning_rate": 1e-05, + "loss": 1.171, + "mean_token_accuracy": 0.669694185256958, + "num_tokens": 155680694.0, + "step": 262 + }, + { + "epoch": 1.2523809523809524, + "ewc_loss": 0.0001430511474609375, + "grad_norm": 0.610242486000061, + "learning_rate": 1e-05, + "loss": 1.1591, + "mean_token_accuracy": 0.6712985038757324, + "num_tokens": 156279612.0, + "step": 263 + }, + { + "epoch": 1.2571428571428571, + "ewc_loss": 0.0001430511474609375, + "grad_norm": 0.7285740971565247, + "learning_rate": 1e-05, + "loss": 1.1482, + "mean_token_accuracy": 0.6754512786865234, + "num_tokens": 156898086.0, + "step": 264 + }, + { + "epoch": 1.2619047619047619, + "ewc_loss": 0.00014400482177734375, + "grad_norm": 0.5847838521003723, + "learning_rate": 1e-05, + "loss": 1.1628, + "mean_token_accuracy": 0.6710183620452881, + "num_tokens": 157502996.0, + "step": 265 + }, + { + "epoch": 1.2666666666666666, + "ewc_loss": 0.00014495849609375, + "grad_norm": 0.6710178256034851, + "learning_rate": 1e-05, + "loss": 1.1646, + "mean_token_accuracy": 0.6704910397529602, + "num_tokens": 158107778.0, + "step": 266 + }, + { + "epoch": 1.2714285714285714, + "ewc_loss": 0.00014591217041015625, + "grad_norm": 0.6027423143386841, + "learning_rate": 1e-05, + "loss": 1.1279, + "mean_token_accuracy": 0.6791141629219055, + "num_tokens": 158713147.0, + "step": 267 + }, + { + "epoch": 1.276190476190476, + "ewc_loss": 0.00014591217041015625, + "grad_norm": 0.5769360065460205, + "learning_rate": 1e-05, + "loss": 1.1357, + "mean_token_accuracy": 0.6770607233047485, + "num_tokens": 159292006.0, + "step": 268 + }, + { + "epoch": 1.2809523809523808, + "ewc_loss": 0.0001468658447265625, + "grad_norm": 0.6142705082893372, + "learning_rate": 1e-05, + "loss": 1.1336, + "mean_token_accuracy": 0.6771590709686279, + "num_tokens": 159889197.0, + "step": 269 + }, + { + "epoch": 1.2857142857142856, + "ewc_loss": 0.00014781951904296875, + "grad_norm": 0.6947009563446045, + "learning_rate": 1e-05, + "loss": 1.1479, + "mean_token_accuracy": 0.6745225191116333, + "num_tokens": 160485304.0, + "step": 270 + }, + { + "epoch": 1.2904761904761906, + "ewc_loss": 0.00014781951904296875, + "grad_norm": 0.6055759787559509, + "learning_rate": 1e-05, + "loss": 1.1506, + "mean_token_accuracy": 0.674088180065155, + "num_tokens": 161092433.0, + "step": 271 + }, + { + "epoch": 1.2952380952380953, + "ewc_loss": 0.00014781951904296875, + "grad_norm": 0.6188156604766846, + "learning_rate": 1e-05, + "loss": 1.15, + "mean_token_accuracy": 0.6741783618927002, + "num_tokens": 161683555.0, + "step": 272 + }, + { + "epoch": 1.3, + "ewc_loss": 0.00014781951904296875, + "grad_norm": 0.6326225996017456, + "learning_rate": 1e-05, + "loss": 1.1395, + "mean_token_accuracy": 0.6768181324005127, + "num_tokens": 162278973.0, + "step": 273 + }, + { + "epoch": 1.3047619047619048, + "ewc_loss": 0.00014781951904296875, + "grad_norm": 0.5972573161125183, + "learning_rate": 1e-05, + "loss": 1.147, + "mean_token_accuracy": 0.6756206750869751, + "num_tokens": 162885270.0, + "step": 274 + }, + { + "epoch": 1.3095238095238095, + "ewc_loss": 0.00014972686767578125, + "grad_norm": 0.6515802145004272, + "learning_rate": 1e-05, + "loss": 1.1421, + "mean_token_accuracy": 0.6755932569503784, + "num_tokens": 163476311.0, + "step": 275 + }, + { + "epoch": 1.3142857142857143, + "ewc_loss": 0.00014972686767578125, + "grad_norm": 0.6344941854476929, + "learning_rate": 1e-05, + "loss": 1.156, + "mean_token_accuracy": 0.6727930307388306, + "num_tokens": 164071314.0, + "step": 276 + }, + { + "epoch": 1.319047619047619, + "ewc_loss": 0.00015163421630859375, + "grad_norm": 0.6195539236068726, + "learning_rate": 1e-05, + "loss": 1.1426, + "mean_token_accuracy": 0.675897479057312, + "num_tokens": 164663415.0, + "step": 277 + }, + { + "epoch": 1.3238095238095238, + "ewc_loss": 0.00015354156494140625, + "grad_norm": 0.5894035696983337, + "learning_rate": 1e-05, + "loss": 1.1376, + "mean_token_accuracy": 0.6770185232162476, + "num_tokens": 165256997.0, + "step": 278 + }, + { + "epoch": 1.3285714285714285, + "ewc_loss": 0.0001544952392578125, + "grad_norm": 0.6396046280860901, + "learning_rate": 1e-05, + "loss": 1.1426, + "mean_token_accuracy": 0.6757199764251709, + "num_tokens": 165847922.0, + "step": 279 + }, + { + "epoch": 1.3333333333333333, + "ewc_loss": 0.0001544952392578125, + "grad_norm": 0.6168200373649597, + "learning_rate": 1e-05, + "loss": 1.1444, + "mean_token_accuracy": 0.6751879453659058, + "num_tokens": 166444541.0, + "step": 280 + }, + { + "epoch": 1.3380952380952382, + "ewc_loss": 0.00015544891357421875, + "grad_norm": 0.6780683398246765, + "learning_rate": 1e-05, + "loss": 1.1356, + "mean_token_accuracy": 0.6775497198104858, + "num_tokens": 167028591.0, + "step": 281 + }, + { + "epoch": 1.342857142857143, + "ewc_loss": 0.00015544891357421875, + "grad_norm": 0.651656448841095, + "learning_rate": 1e-05, + "loss": 1.158, + "mean_token_accuracy": 0.6717301607131958, + "num_tokens": 167627132.0, + "step": 282 + }, + { + "epoch": 1.3476190476190477, + "ewc_loss": 0.000156402587890625, + "grad_norm": 0.6992460489273071, + "learning_rate": 1e-05, + "loss": 1.1305, + "mean_token_accuracy": 0.6792446374893188, + "num_tokens": 168226854.0, + "step": 283 + }, + { + "epoch": 1.3523809523809525, + "ewc_loss": 0.00015735626220703125, + "grad_norm": 0.6887460947036743, + "learning_rate": 1e-05, + "loss": 1.1619, + "mean_token_accuracy": 0.6714077591896057, + "num_tokens": 168833732.0, + "step": 284 + }, + { + "epoch": 1.3571428571428572, + "ewc_loss": 0.0001583099365234375, + "grad_norm": 0.6171844601631165, + "learning_rate": 1e-05, + "loss": 1.1373, + "mean_token_accuracy": 0.6776933670043945, + "num_tokens": 169426970.0, + "step": 285 + }, + { + "epoch": 1.361904761904762, + "ewc_loss": 0.0001583099365234375, + "grad_norm": 0.6948171854019165, + "learning_rate": 1e-05, + "loss": 1.1615, + "mean_token_accuracy": 0.6726795434951782, + "num_tokens": 170025787.0, + "step": 286 + }, + { + "epoch": 1.3666666666666667, + "ewc_loss": 0.00015926361083984375, + "grad_norm": 0.639401376247406, + "learning_rate": 1e-05, + "loss": 1.1569, + "mean_token_accuracy": 0.6718345880508423, + "num_tokens": 170621857.0, + "step": 287 + }, + { + "epoch": 1.3714285714285714, + "ewc_loss": 0.00016021728515625, + "grad_norm": 0.6140373945236206, + "learning_rate": 1e-05, + "loss": 1.1542, + "mean_token_accuracy": 0.6728547811508179, + "num_tokens": 171220708.0, + "step": 288 + }, + { + "epoch": 1.3761904761904762, + "ewc_loss": 0.00016117095947265625, + "grad_norm": 0.622337818145752, + "learning_rate": 1e-05, + "loss": 1.1639, + "mean_token_accuracy": 0.6701761484146118, + "num_tokens": 171812508.0, + "step": 289 + }, + { + "epoch": 1.380952380952381, + "ewc_loss": 0.00016117095947265625, + "grad_norm": 0.6259892582893372, + "learning_rate": 1e-05, + "loss": 1.1351, + "mean_token_accuracy": 0.6765514612197876, + "num_tokens": 172401090.0, + "step": 290 + }, + { + "epoch": 1.3857142857142857, + "ewc_loss": 0.000164031982421875, + "grad_norm": 0.6238521337509155, + "learning_rate": 1e-05, + "loss": 1.1415, + "mean_token_accuracy": 0.6761304140090942, + "num_tokens": 172989201.0, + "step": 291 + }, + { + "epoch": 1.3904761904761904, + "ewc_loss": 0.000164031982421875, + "grad_norm": 0.6326766610145569, + "learning_rate": 1e-05, + "loss": 1.1432, + "mean_token_accuracy": 0.674975574016571, + "num_tokens": 173563807.0, + "step": 292 + }, + { + "epoch": 1.3952380952380952, + "ewc_loss": 0.000164031982421875, + "grad_norm": 0.5691280364990234, + "learning_rate": 1e-05, + "loss": 1.1417, + "mean_token_accuracy": 0.6763608455657959, + "num_tokens": 174159574.0, + "step": 293 + }, + { + "epoch": 1.4, + "ewc_loss": 0.00016498565673828125, + "grad_norm": 0.6361227631568909, + "learning_rate": 1e-05, + "loss": 1.1603, + "mean_token_accuracy": 0.6713976263999939, + "num_tokens": 174744244.0, + "step": 294 + }, + { + "epoch": 1.4047619047619047, + "ewc_loss": 0.00016498565673828125, + "grad_norm": 0.6221501231193542, + "learning_rate": 1e-05, + "loss": 1.1432, + "mean_token_accuracy": 0.6749350428581238, + "num_tokens": 175341946.0, + "step": 295 + }, + { + "epoch": 1.4095238095238094, + "ewc_loss": 0.00016498565673828125, + "grad_norm": 0.6367595791816711, + "learning_rate": 1e-05, + "loss": 1.1136, + "mean_token_accuracy": 0.6822153329849243, + "num_tokens": 175904117.0, + "step": 296 + }, + { + "epoch": 1.4142857142857144, + "ewc_loss": 0.00016498565673828125, + "grad_norm": 0.6647323966026306, + "learning_rate": 1e-05, + "loss": 1.1425, + "mean_token_accuracy": 0.6758924722671509, + "num_tokens": 176493621.0, + "step": 297 + }, + { + "epoch": 1.4190476190476191, + "ewc_loss": 0.0001659393310546875, + "grad_norm": 0.5820210576057434, + "learning_rate": 1e-05, + "loss": 1.1434, + "mean_token_accuracy": 0.6752427816390991, + "num_tokens": 177082157.0, + "step": 298 + }, + { + "epoch": 1.4238095238095239, + "ewc_loss": 0.0001659393310546875, + "grad_norm": 0.6057286262512207, + "learning_rate": 1e-05, + "loss": 1.1443, + "mean_token_accuracy": 0.6744421124458313, + "num_tokens": 177668681.0, + "step": 299 + }, + { + "epoch": 1.4285714285714286, + "ewc_loss": 0.0001659393310546875, + "grad_norm": 0.6335484385490417, + "learning_rate": 1e-05, + "loss": 1.147, + "mean_token_accuracy": 0.6743271946907043, + "num_tokens": 178256283.0, + "step": 300 + }, + { + "epoch": 1.4333333333333333, + "ewc_loss": 0.0001678466796875, + "grad_norm": 0.6306686997413635, + "learning_rate": 1e-05, + "loss": 1.1586, + "mean_token_accuracy": 0.6716290712356567, + "num_tokens": 178850673.0, + "step": 301 + }, + { + "epoch": 1.438095238095238, + "ewc_loss": 0.0001678466796875, + "grad_norm": 0.6037660837173462, + "learning_rate": 1e-05, + "loss": 1.1365, + "mean_token_accuracy": 0.6781344413757324, + "num_tokens": 179457871.0, + "step": 302 + }, + { + "epoch": 1.4428571428571428, + "ewc_loss": 0.00016880035400390625, + "grad_norm": 0.6161314249038696, + "learning_rate": 1e-05, + "loss": 1.167, + "mean_token_accuracy": 0.6697080731391907, + "num_tokens": 180064071.0, + "step": 303 + }, + { + "epoch": 1.4476190476190476, + "ewc_loss": 0.0001697540283203125, + "grad_norm": 0.6294899582862854, + "learning_rate": 1e-05, + "loss": 1.1226, + "mean_token_accuracy": 0.6799255609512329, + "num_tokens": 180650796.0, + "step": 304 + }, + { + "epoch": 1.4523809523809523, + "ewc_loss": 0.0001697540283203125, + "grad_norm": 0.6562028527259827, + "learning_rate": 1e-05, + "loss": 1.1531, + "mean_token_accuracy": 0.6746268272399902, + "num_tokens": 181246825.0, + "step": 305 + }, + { + "epoch": 1.457142857142857, + "ewc_loss": 0.0001697540283203125, + "grad_norm": 0.5896769762039185, + "learning_rate": 1e-05, + "loss": 1.1552, + "mean_token_accuracy": 0.6729496717453003, + "num_tokens": 181855567.0, + "step": 306 + }, + { + "epoch": 1.461904761904762, + "ewc_loss": 0.00017070770263671875, + "grad_norm": 0.6085930466651917, + "learning_rate": 1e-05, + "loss": 1.1217, + "mean_token_accuracy": 0.6797447204589844, + "num_tokens": 182433911.0, + "step": 307 + }, + { + "epoch": 1.4666666666666668, + "ewc_loss": 0.00017070770263671875, + "grad_norm": 0.6299704313278198, + "learning_rate": 1e-05, + "loss": 1.1429, + "mean_token_accuracy": 0.6757924556732178, + "num_tokens": 183023144.0, + "step": 308 + }, + { + "epoch": 1.4714285714285715, + "ewc_loss": 0.000171661376953125, + "grad_norm": 0.604974627494812, + "learning_rate": 1e-05, + "loss": 1.1348, + "mean_token_accuracy": 0.6769924759864807, + "num_tokens": 183626514.0, + "step": 309 + }, + { + "epoch": 1.4761904761904763, + "ewc_loss": 0.000171661376953125, + "grad_norm": 0.6737529039382935, + "learning_rate": 1e-05, + "loss": 1.1406, + "mean_token_accuracy": 0.6758840680122375, + "num_tokens": 184221439.0, + "step": 310 + }, + { + "epoch": 1.480952380952381, + "ewc_loss": 0.000171661376953125, + "grad_norm": 0.6270067691802979, + "learning_rate": 1e-05, + "loss": 1.1462, + "mean_token_accuracy": 0.6749770641326904, + "num_tokens": 184819506.0, + "step": 311 + }, + { + "epoch": 1.4857142857142858, + "ewc_loss": 0.00017261505126953125, + "grad_norm": 0.6235854029655457, + "learning_rate": 1e-05, + "loss": 1.1463, + "mean_token_accuracy": 0.6750996112823486, + "num_tokens": 185419019.0, + "step": 312 + }, + { + "epoch": 1.4904761904761905, + "ewc_loss": 0.00017261505126953125, + "grad_norm": 0.5771413445472717, + "learning_rate": 1e-05, + "loss": 1.1335, + "mean_token_accuracy": 0.6793861389160156, + "num_tokens": 186010772.0, + "step": 313 + }, + { + "epoch": 1.4952380952380953, + "ewc_loss": 0.0001735687255859375, + "grad_norm": 0.6319766044616699, + "learning_rate": 1e-05, + "loss": 1.1305, + "mean_token_accuracy": 0.678336501121521, + "num_tokens": 186589243.0, + "step": 314 + }, + { + "epoch": 1.5, + "ewc_loss": 0.0001735687255859375, + "grad_norm": 0.6413438320159912, + "learning_rate": 1e-05, + "loss": 1.1291, + "mean_token_accuracy": 0.6791257262229919, + "num_tokens": 187182368.0, + "step": 315 + }, + { + "epoch": 1.5047619047619047, + "ewc_loss": 0.0001735687255859375, + "grad_norm": 0.6370982527732849, + "learning_rate": 1e-05, + "loss": 1.1303, + "mean_token_accuracy": 0.6782152056694031, + "num_tokens": 187763428.0, + "step": 316 + }, + { + "epoch": 1.5095238095238095, + "ewc_loss": 0.00017452239990234375, + "grad_norm": 0.5750306248664856, + "learning_rate": 1e-05, + "loss": 1.1253, + "mean_token_accuracy": 0.6799981594085693, + "num_tokens": 188359395.0, + "step": 317 + }, + { + "epoch": 1.5142857142857142, + "ewc_loss": 0.00017452239990234375, + "grad_norm": 0.6567773222923279, + "learning_rate": 1e-05, + "loss": 1.1456, + "mean_token_accuracy": 0.6748775243759155, + "num_tokens": 188952450.0, + "step": 318 + }, + { + "epoch": 1.519047619047619, + "ewc_loss": 0.00017547607421875, + "grad_norm": 0.6511772274971008, + "learning_rate": 1e-05, + "loss": 1.1411, + "mean_token_accuracy": 0.6756794452667236, + "num_tokens": 189535853.0, + "step": 319 + }, + { + "epoch": 1.5238095238095237, + "ewc_loss": 0.00017642974853515625, + "grad_norm": 0.6242381930351257, + "learning_rate": 1e-05, + "loss": 1.1239, + "mean_token_accuracy": 0.6801682710647583, + "num_tokens": 190127386.0, + "step": 320 + }, + { + "epoch": 1.5285714285714285, + "ewc_loss": 0.0001773834228515625, + "grad_norm": 0.6234132647514343, + "learning_rate": 1e-05, + "loss": 1.1409, + "mean_token_accuracy": 0.6756604909896851, + "num_tokens": 190718877.0, + "step": 321 + }, + { + "epoch": 1.5333333333333332, + "ewc_loss": 0.0001773834228515625, + "grad_norm": 0.6304793357849121, + "learning_rate": 1e-05, + "loss": 1.163, + "mean_token_accuracy": 0.670893132686615, + "num_tokens": 191320553.0, + "step": 322 + }, + { + "epoch": 1.538095238095238, + "ewc_loss": 0.000179290771484375, + "grad_norm": 0.6538220643997192, + "learning_rate": 1e-05, + "loss": 1.1347, + "mean_token_accuracy": 0.6782395839691162, + "num_tokens": 191911786.0, + "step": 323 + }, + { + "epoch": 1.5428571428571427, + "ewc_loss": 0.000179290771484375, + "grad_norm": 0.5803797841072083, + "learning_rate": 1e-05, + "loss": 1.1612, + "mean_token_accuracy": 0.672095000743866, + "num_tokens": 192517254.0, + "step": 324 + }, + { + "epoch": 1.5476190476190477, + "ewc_loss": 0.000179290771484375, + "grad_norm": 0.6748237609863281, + "learning_rate": 1e-05, + "loss": 1.1568, + "mean_token_accuracy": 0.6723283529281616, + "num_tokens": 193113713.0, + "step": 325 + }, + { + "epoch": 1.5523809523809524, + "ewc_loss": 0.000179290771484375, + "grad_norm": 0.6310884356498718, + "learning_rate": 1e-05, + "loss": 1.1381, + "mean_token_accuracy": 0.6770954132080078, + "num_tokens": 193718335.0, + "step": 326 + }, + { + "epoch": 1.5571428571428572, + "ewc_loss": 0.00018024444580078125, + "grad_norm": 0.7079461216926575, + "learning_rate": 1e-05, + "loss": 1.14, + "mean_token_accuracy": 0.6757882833480835, + "num_tokens": 194303328.0, + "step": 327 + }, + { + "epoch": 1.561904761904762, + "ewc_loss": 0.00018024444580078125, + "grad_norm": 0.6592386364936829, + "learning_rate": 1e-05, + "loss": 1.1335, + "mean_token_accuracy": 0.6780304312705994, + "num_tokens": 194886509.0, + "step": 328 + }, + { + "epoch": 1.5666666666666667, + "ewc_loss": 0.00018024444580078125, + "grad_norm": 0.7015005946159363, + "learning_rate": 1e-05, + "loss": 1.1399, + "mean_token_accuracy": 0.6771315336227417, + "num_tokens": 195456896.0, + "step": 329 + }, + { + "epoch": 1.5714285714285714, + "ewc_loss": 0.0001811981201171875, + "grad_norm": 0.6742457151412964, + "learning_rate": 1e-05, + "loss": 1.1371, + "mean_token_accuracy": 0.676336944103241, + "num_tokens": 196053871.0, + "step": 330 + }, + { + "epoch": 1.5761904761904761, + "ewc_loss": 0.00018215179443359375, + "grad_norm": 0.7495582699775696, + "learning_rate": 1e-05, + "loss": 1.137, + "mean_token_accuracy": 0.6765727996826172, + "num_tokens": 196654732.0, + "step": 331 + }, + { + "epoch": 1.580952380952381, + "ewc_loss": 0.00018215179443359375, + "grad_norm": 0.6955667734146118, + "learning_rate": 1e-05, + "loss": 1.1256, + "mean_token_accuracy": 0.6800401210784912, + "num_tokens": 197242864.0, + "step": 332 + }, + { + "epoch": 1.5857142857142859, + "ewc_loss": 0.00018215179443359375, + "grad_norm": 0.7974697351455688, + "learning_rate": 1e-05, + "loss": 1.1285, + "mean_token_accuracy": 0.6790241003036499, + "num_tokens": 197840214.0, + "step": 333 + }, + { + "epoch": 1.5904761904761906, + "ewc_loss": 0.00018215179443359375, + "grad_norm": 0.6629257202148438, + "learning_rate": 1e-05, + "loss": 1.1308, + "mean_token_accuracy": 0.6786867380142212, + "num_tokens": 198440572.0, + "step": 334 + }, + { + "epoch": 1.5952380952380953, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.6797847151756287, + "learning_rate": 1e-05, + "loss": 1.1265, + "mean_token_accuracy": 0.6796398162841797, + "num_tokens": 199039184.0, + "step": 335 + }, + { + "epoch": 1.6, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.7100812196731567, + "learning_rate": 1e-05, + "loss": 1.1272, + "mean_token_accuracy": 0.6783736348152161, + "num_tokens": 199626548.0, + "step": 336 + }, + { + "epoch": 1.6047619047619048, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.705389142036438, + "learning_rate": 1e-05, + "loss": 1.1412, + "mean_token_accuracy": 0.6764625906944275, + "num_tokens": 200222258.0, + "step": 337 + }, + { + "epoch": 1.6095238095238096, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.6956824064254761, + "learning_rate": 1e-05, + "loss": 1.1339, + "mean_token_accuracy": 0.678327202796936, + "num_tokens": 200819172.0, + "step": 338 + }, + { + "epoch": 1.6142857142857143, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.6533691883087158, + "learning_rate": 1e-05, + "loss": 1.1447, + "mean_token_accuracy": 0.6752112507820129, + "num_tokens": 201413549.0, + "step": 339 + }, + { + "epoch": 1.619047619047619, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.6796064376831055, + "learning_rate": 1e-05, + "loss": 1.1295, + "mean_token_accuracy": 0.6788633465766907, + "num_tokens": 202014069.0, + "step": 340 + }, + { + "epoch": 1.6238095238095238, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.660502552986145, + "learning_rate": 1e-05, + "loss": 1.1612, + "mean_token_accuracy": 0.671108067035675, + "num_tokens": 202600379.0, + "step": 341 + }, + { + "epoch": 1.6285714285714286, + "ewc_loss": 0.00018405914306640625, + "grad_norm": 0.6652624011039734, + "learning_rate": 1e-05, + "loss": 1.1357, + "mean_token_accuracy": 0.6770787239074707, + "num_tokens": 203203233.0, + "step": 342 + }, + { + "epoch": 1.6333333333333333, + "ewc_loss": 0.0001850128173828125, + "grad_norm": 0.6191333532333374, + "learning_rate": 1e-05, + "loss": 1.1291, + "mean_token_accuracy": 0.678756594657898, + "num_tokens": 203802554.0, + "step": 343 + }, + { + "epoch": 1.638095238095238, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.6783542037010193, + "learning_rate": 1e-05, + "loss": 1.1429, + "mean_token_accuracy": 0.6766753792762756, + "num_tokens": 204395560.0, + "step": 344 + }, + { + "epoch": 1.6428571428571428, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.6509584784507751, + "learning_rate": 1e-05, + "loss": 1.1264, + "mean_token_accuracy": 0.679986834526062, + "num_tokens": 205001404.0, + "step": 345 + }, + { + "epoch": 1.6476190476190475, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.5738518834114075, + "learning_rate": 1e-05, + "loss": 1.1199, + "mean_token_accuracy": 0.6812908053398132, + "num_tokens": 205599855.0, + "step": 346 + }, + { + "epoch": 1.6523809523809523, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.6862993836402893, + "learning_rate": 1e-05, + "loss": 1.1258, + "mean_token_accuracy": 0.6794612407684326, + "num_tokens": 206163338.0, + "step": 347 + }, + { + "epoch": 1.657142857142857, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.6373027563095093, + "learning_rate": 1e-05, + "loss": 1.1505, + "mean_token_accuracy": 0.6739401817321777, + "num_tokens": 206741397.0, + "step": 348 + }, + { + "epoch": 1.6619047619047618, + "ewc_loss": 0.00018596649169921875, + "grad_norm": 0.6026475429534912, + "learning_rate": 1e-05, + "loss": 1.1435, + "mean_token_accuracy": 0.6751222610473633, + "num_tokens": 207323297.0, + "step": 349 + }, + { + "epoch": 1.6666666666666665, + "ewc_loss": 0.00018787384033203125, + "grad_norm": 0.63143390417099, + "learning_rate": 1e-05, + "loss": 1.1428, + "mean_token_accuracy": 0.6754919290542603, + "num_tokens": 207908589.0, + "step": 350 + }, + { + "epoch": 1.6714285714285713, + "ewc_loss": 0.0001888275146484375, + "grad_norm": 0.646081805229187, + "learning_rate": 1e-05, + "loss": 1.1539, + "mean_token_accuracy": 0.6725949048995972, + "num_tokens": 208500281.0, + "step": 351 + }, + { + "epoch": 1.6761904761904762, + "ewc_loss": 0.00018978118896484375, + "grad_norm": 0.6226057410240173, + "learning_rate": 1e-05, + "loss": 1.1337, + "mean_token_accuracy": 0.6781013011932373, + "num_tokens": 209097427.0, + "step": 352 + }, + { + "epoch": 1.680952380952381, + "ewc_loss": 0.00018978118896484375, + "grad_norm": 0.6119362115859985, + "learning_rate": 1e-05, + "loss": 1.1354, + "mean_token_accuracy": 0.676925003528595, + "num_tokens": 209704225.0, + "step": 353 + }, + { + "epoch": 1.6857142857142857, + "ewc_loss": 0.00018978118896484375, + "grad_norm": 0.6145895719528198, + "learning_rate": 1e-05, + "loss": 1.1314, + "mean_token_accuracy": 0.6787194013595581, + "num_tokens": 210313267.0, + "step": 354 + }, + { + "epoch": 1.6904761904761905, + "ewc_loss": 0.00019073486328125, + "grad_norm": 0.5921496152877808, + "learning_rate": 1e-05, + "loss": 1.1408, + "mean_token_accuracy": 0.6759685277938843, + "num_tokens": 210918588.0, + "step": 355 + }, + { + "epoch": 1.6952380952380952, + "ewc_loss": 0.00019073486328125, + "grad_norm": 0.6301826238632202, + "learning_rate": 1e-05, + "loss": 1.1405, + "mean_token_accuracy": 0.6764883399009705, + "num_tokens": 211508221.0, + "step": 356 + }, + { + "epoch": 1.7, + "ewc_loss": 0.0001926422119140625, + "grad_norm": 0.6039449572563171, + "learning_rate": 1e-05, + "loss": 1.1499, + "mean_token_accuracy": 0.6741034388542175, + "num_tokens": 212108728.0, + "step": 357 + }, + { + "epoch": 1.704761904761905, + "ewc_loss": 0.0001926422119140625, + "grad_norm": 0.585624098777771, + "learning_rate": 1e-05, + "loss": 1.1364, + "mean_token_accuracy": 0.6767901182174683, + "num_tokens": 212705437.0, + "step": 358 + }, + { + "epoch": 1.7095238095238097, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.6170507073402405, + "learning_rate": 1e-05, + "loss": 1.1467, + "mean_token_accuracy": 0.673753559589386, + "num_tokens": 213300176.0, + "step": 359 + }, + { + "epoch": 1.7142857142857144, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.6424557566642761, + "learning_rate": 1e-05, + "loss": 1.146, + "mean_token_accuracy": 0.6745511889457703, + "num_tokens": 213890731.0, + "step": 360 + }, + { + "epoch": 1.7190476190476192, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.6581194400787354, + "learning_rate": 1e-05, + "loss": 1.1288, + "mean_token_accuracy": 0.6774623394012451, + "num_tokens": 214471137.0, + "step": 361 + }, + { + "epoch": 1.723809523809524, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.6715754270553589, + "learning_rate": 1e-05, + "loss": 1.1311, + "mean_token_accuracy": 0.6783310174942017, + "num_tokens": 215062165.0, + "step": 362 + }, + { + "epoch": 1.7285714285714286, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.6053357124328613, + "learning_rate": 1e-05, + "loss": 1.1406, + "mean_token_accuracy": 0.6758085489273071, + "num_tokens": 215662977.0, + "step": 363 + }, + { + "epoch": 1.7333333333333334, + "ewc_loss": 0.00019359588623046875, + "grad_norm": 0.68400639295578, + "learning_rate": 1e-05, + "loss": 1.147, + "mean_token_accuracy": 0.6744489669799805, + "num_tokens": 216253942.0, + "step": 364 + }, + { + "epoch": 1.7380952380952381, + "ewc_loss": 0.00019550323486328125, + "grad_norm": 0.616698682308197, + "learning_rate": 1e-05, + "loss": 1.1378, + "mean_token_accuracy": 0.6757856607437134, + "num_tokens": 216847247.0, + "step": 365 + }, + { + "epoch": 1.7428571428571429, + "ewc_loss": 0.00019550323486328125, + "grad_norm": 0.6318507790565491, + "learning_rate": 1e-05, + "loss": 1.1255, + "mean_token_accuracy": 0.6798416376113892, + "num_tokens": 217427979.0, + "step": 366 + }, + { + "epoch": 1.7476190476190476, + "ewc_loss": 0.00019550323486328125, + "grad_norm": 0.6107721328735352, + "learning_rate": 1e-05, + "loss": 1.129, + "mean_token_accuracy": 0.678071916103363, + "num_tokens": 218020622.0, + "step": 367 + }, + { + "epoch": 1.7523809523809524, + "ewc_loss": 0.0001964569091796875, + "grad_norm": 0.652899980545044, + "learning_rate": 1e-05, + "loss": 1.1383, + "mean_token_accuracy": 0.6769452095031738, + "num_tokens": 218613768.0, + "step": 368 + }, + { + "epoch": 1.7571428571428571, + "ewc_loss": 0.00019741058349609375, + "grad_norm": 0.669549822807312, + "learning_rate": 1e-05, + "loss": 1.1499, + "mean_token_accuracy": 0.6737456917762756, + "num_tokens": 219217863.0, + "step": 369 + }, + { + "epoch": 1.7619047619047619, + "ewc_loss": 0.00019741058349609375, + "grad_norm": 0.619970977306366, + "learning_rate": 1e-05, + "loss": 1.1391, + "mean_token_accuracy": 0.6763114929199219, + "num_tokens": 219826128.0, + "step": 370 + }, + { + "epoch": 1.7666666666666666, + "ewc_loss": 0.0001983642578125, + "grad_norm": 0.5451305508613586, + "learning_rate": 1e-05, + "loss": 1.1339, + "mean_token_accuracy": 0.678363561630249, + "num_tokens": 220424737.0, + "step": 371 + }, + { + "epoch": 1.7714285714285714, + "ewc_loss": 0.00019931793212890625, + "grad_norm": 0.6214661598205566, + "learning_rate": 1e-05, + "loss": 1.1388, + "mean_token_accuracy": 0.6761868000030518, + "num_tokens": 221010073.0, + "step": 372 + }, + { + "epoch": 1.776190476190476, + "ewc_loss": 0.00019931793212890625, + "grad_norm": 0.6402221322059631, + "learning_rate": 1e-05, + "loss": 1.1351, + "mean_token_accuracy": 0.677847146987915, + "num_tokens": 221614799.0, + "step": 373 + }, + { + "epoch": 1.7809523809523808, + "ewc_loss": 0.0002002716064453125, + "grad_norm": 0.5561360716819763, + "learning_rate": 1e-05, + "loss": 1.1331, + "mean_token_accuracy": 0.6774996519088745, + "num_tokens": 222215943.0, + "step": 374 + }, + { + "epoch": 1.7857142857142856, + "ewc_loss": 0.0002002716064453125, + "grad_norm": 0.5576399564743042, + "learning_rate": 1e-05, + "loss": 1.1288, + "mean_token_accuracy": 0.6792528629302979, + "num_tokens": 222803822.0, + "step": 375 + }, + { + "epoch": 1.7904761904761903, + "ewc_loss": 0.00020122528076171875, + "grad_norm": 0.5990220308303833, + "learning_rate": 1e-05, + "loss": 1.1462, + "mean_token_accuracy": 0.6745100021362305, + "num_tokens": 223409541.0, + "step": 376 + }, + { + "epoch": 1.795238095238095, + "ewc_loss": 0.00020122528076171875, + "grad_norm": 0.5610822439193726, + "learning_rate": 1e-05, + "loss": 1.1332, + "mean_token_accuracy": 0.6772064566612244, + "num_tokens": 223996446.0, + "step": 377 + }, + { + "epoch": 1.8, + "ewc_loss": 0.00020122528076171875, + "grad_norm": 0.6272426247596741, + "learning_rate": 1e-05, + "loss": 1.1352, + "mean_token_accuracy": 0.6773086786270142, + "num_tokens": 224599074.0, + "step": 378 + }, + { + "epoch": 1.8047619047619048, + "ewc_loss": 0.000202178955078125, + "grad_norm": 0.6106992959976196, + "learning_rate": 1e-05, + "loss": 1.1272, + "mean_token_accuracy": 0.6791713833808899, + "num_tokens": 225184557.0, + "step": 379 + }, + { + "epoch": 1.8095238095238095, + "ewc_loss": 0.000202178955078125, + "grad_norm": 0.614132285118103, + "learning_rate": 1e-05, + "loss": 1.1334, + "mean_token_accuracy": 0.678817629814148, + "num_tokens": 225774197.0, + "step": 380 + }, + { + "epoch": 1.8142857142857143, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.6004734039306641, + "learning_rate": 1e-05, + "loss": 1.1223, + "mean_token_accuracy": 0.6798949241638184, + "num_tokens": 226359063.0, + "step": 381 + }, + { + "epoch": 1.819047619047619, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.6243444681167603, + "learning_rate": 1e-05, + "loss": 1.1389, + "mean_token_accuracy": 0.6760082244873047, + "num_tokens": 226962202.0, + "step": 382 + }, + { + "epoch": 1.8238095238095238, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.6604143977165222, + "learning_rate": 1e-05, + "loss": 1.1369, + "mean_token_accuracy": 0.6767272353172302, + "num_tokens": 227541002.0, + "step": 383 + }, + { + "epoch": 1.8285714285714287, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.6482001543045044, + "learning_rate": 1e-05, + "loss": 1.137, + "mean_token_accuracy": 0.6770564317703247, + "num_tokens": 228134124.0, + "step": 384 + }, + { + "epoch": 1.8333333333333335, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.6695340871810913, + "learning_rate": 1e-05, + "loss": 1.1274, + "mean_token_accuracy": 0.6787882447242737, + "num_tokens": 228729717.0, + "step": 385 + }, + { + "epoch": 1.8380952380952382, + "ewc_loss": 0.0002040863037109375, + "grad_norm": 0.7216992974281311, + "learning_rate": 1e-05, + "loss": 1.1334, + "mean_token_accuracy": 0.6771396398544312, + "num_tokens": 229318931.0, + "step": 386 + }, + { + "epoch": 1.842857142857143, + "ewc_loss": 0.00020503997802734375, + "grad_norm": 0.6791576743125916, + "learning_rate": 1e-05, + "loss": 1.1401, + "mean_token_accuracy": 0.6765166521072388, + "num_tokens": 229923675.0, + "step": 387 + }, + { + "epoch": 1.8476190476190477, + "ewc_loss": 0.00020503997802734375, + "grad_norm": 0.6774105429649353, + "learning_rate": 1e-05, + "loss": 1.1303, + "mean_token_accuracy": 0.678852915763855, + "num_tokens": 230514254.0, + "step": 388 + }, + { + "epoch": 1.8523809523809525, + "ewc_loss": 0.00020503997802734375, + "grad_norm": 0.5919401049613953, + "learning_rate": 1e-05, + "loss": 1.1382, + "mean_token_accuracy": 0.6770588159561157, + "num_tokens": 231113801.0, + "step": 389 + }, + { + "epoch": 1.8571428571428572, + "ewc_loss": 0.00020503997802734375, + "grad_norm": 0.6320315599441528, + "learning_rate": 1e-05, + "loss": 1.1271, + "mean_token_accuracy": 0.6778794527053833, + "num_tokens": 231709098.0, + "step": 390 + }, + { + "epoch": 1.861904761904762, + "ewc_loss": 0.00020694732666015625, + "grad_norm": 0.5665856599807739, + "learning_rate": 1e-05, + "loss": 1.1401, + "mean_token_accuracy": 0.675905704498291, + "num_tokens": 232311276.0, + "step": 391 + }, + { + "epoch": 1.8666666666666667, + "ewc_loss": 0.00020694732666015625, + "grad_norm": 0.6316301822662354, + "learning_rate": 1e-05, + "loss": 1.1285, + "mean_token_accuracy": 0.6785460710525513, + "num_tokens": 232904607.0, + "step": 392 + }, + { + "epoch": 1.8714285714285714, + "ewc_loss": 0.0002079010009765625, + "grad_norm": 0.5852479338645935, + "learning_rate": 1e-05, + "loss": 1.1211, + "mean_token_accuracy": 0.681178629398346, + "num_tokens": 233493254.0, + "step": 393 + }, + { + "epoch": 1.8761904761904762, + "ewc_loss": 0.0002079010009765625, + "grad_norm": 0.6655333638191223, + "learning_rate": 1e-05, + "loss": 1.1306, + "mean_token_accuracy": 0.6790977120399475, + "num_tokens": 234085431.0, + "step": 394 + }, + { + "epoch": 1.880952380952381, + "ewc_loss": 0.0002079010009765625, + "grad_norm": 0.6633432507514954, + "learning_rate": 1e-05, + "loss": 1.1399, + "mean_token_accuracy": 0.6759408712387085, + "num_tokens": 234685396.0, + "step": 395 + }, + { + "epoch": 1.8857142857142857, + "ewc_loss": 0.000209808349609375, + "grad_norm": 0.709540605545044, + "learning_rate": 1e-05, + "loss": 1.1411, + "mean_token_accuracy": 0.6760150194168091, + "num_tokens": 235280049.0, + "step": 396 + }, + { + "epoch": 1.8904761904761904, + "ewc_loss": 0.000209808349609375, + "grad_norm": 0.6758368015289307, + "learning_rate": 1e-05, + "loss": 1.1419, + "mean_token_accuracy": 0.6759270429611206, + "num_tokens": 235867276.0, + "step": 397 + }, + { + "epoch": 1.8952380952380952, + "ewc_loss": 0.000209808349609375, + "grad_norm": 0.6794525980949402, + "learning_rate": 1e-05, + "loss": 1.1284, + "mean_token_accuracy": 0.6793118119239807, + "num_tokens": 236448647.0, + "step": 398 + }, + { + "epoch": 1.9, + "ewc_loss": 0.00021076202392578125, + "grad_norm": 0.6180399060249329, + "learning_rate": 1e-05, + "loss": 1.1414, + "mean_token_accuracy": 0.6747409105300903, + "num_tokens": 237054180.0, + "step": 399 + }, + { + "epoch": 1.9047619047619047, + "ewc_loss": 0.00021266937255859375, + "grad_norm": 0.610095739364624, + "learning_rate": 1e-05, + "loss": 1.1553, + "mean_token_accuracy": 0.6724796891212463, + "num_tokens": 237658218.0, + "step": 400 + }, + { + "epoch": 1.9095238095238094, + "ewc_loss": 0.00021266937255859375, + "grad_norm": 0.6335026621818542, + "learning_rate": 1e-05, + "loss": 1.1381, + "mean_token_accuracy": 0.6772992610931396, + "num_tokens": 238248393.0, + "step": 401 + }, + { + "epoch": 1.9142857142857141, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6482390761375427, + "learning_rate": 1e-05, + "loss": 1.1255, + "mean_token_accuracy": 0.6805286407470703, + "num_tokens": 238838548.0, + "step": 402 + }, + { + "epoch": 1.919047619047619, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6335037350654602, + "learning_rate": 1e-05, + "loss": 1.1312, + "mean_token_accuracy": 0.6789015531539917, + "num_tokens": 239442502.0, + "step": 403 + }, + { + "epoch": 1.9238095238095239, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6646998524665833, + "learning_rate": 1e-05, + "loss": 1.1432, + "mean_token_accuracy": 0.6749930381774902, + "num_tokens": 240029019.0, + "step": 404 + }, + { + "epoch": 1.9285714285714286, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.592803955078125, + "learning_rate": 1e-05, + "loss": 1.1293, + "mean_token_accuracy": 0.6791863441467285, + "num_tokens": 240623504.0, + "step": 405 + }, + { + "epoch": 1.9333333333333333, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6436818838119507, + "learning_rate": 1e-05, + "loss": 1.1182, + "mean_token_accuracy": 0.6806778907775879, + "num_tokens": 241217102.0, + "step": 406 + }, + { + "epoch": 1.938095238095238, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6258701682090759, + "learning_rate": 1e-05, + "loss": 1.1301, + "mean_token_accuracy": 0.6794149875640869, + "num_tokens": 241812222.0, + "step": 407 + }, + { + "epoch": 1.9428571428571428, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6515687704086304, + "learning_rate": 1e-05, + "loss": 1.1247, + "mean_token_accuracy": 0.6796150207519531, + "num_tokens": 242388669.0, + "step": 408 + }, + { + "epoch": 1.9476190476190476, + "ewc_loss": 0.000213623046875, + "grad_norm": 0.6868777871131897, + "learning_rate": 1e-05, + "loss": 1.1272, + "mean_token_accuracy": 0.6793463826179504, + "num_tokens": 242965686.0, + "step": 409 + }, + { + "epoch": 1.9523809523809523, + "ewc_loss": 0.0002155303955078125, + "grad_norm": 0.5799442529678345, + "learning_rate": 1e-05, + "loss": 1.1343, + "mean_token_accuracy": 0.6781398057937622, + "num_tokens": 243553853.0, + "step": 410 + }, + { + "epoch": 1.9571428571428573, + "ewc_loss": 0.0002155303955078125, + "grad_norm": 0.7715296745300293, + "learning_rate": 1e-05, + "loss": 1.1298, + "mean_token_accuracy": 0.6777502298355103, + "num_tokens": 244139754.0, + "step": 411 + }, + { + "epoch": 1.961904761904762, + "ewc_loss": 0.000217437744140625, + "grad_norm": 0.6108430624008179, + "learning_rate": 1e-05, + "loss": 1.1338, + "mean_token_accuracy": 0.6766902208328247, + "num_tokens": 244736423.0, + "step": 412 + }, + { + "epoch": 1.9666666666666668, + "ewc_loss": 0.000217437744140625, + "grad_norm": 0.8047634363174438, + "learning_rate": 1e-05, + "loss": 1.1353, + "mean_token_accuracy": 0.678554892539978, + "num_tokens": 245337682.0, + "step": 413 + }, + { + "epoch": 1.9714285714285715, + "ewc_loss": 0.00021839141845703125, + "grad_norm": 0.6595780849456787, + "learning_rate": 1e-05, + "loss": 1.1337, + "mean_token_accuracy": 0.6777966022491455, + "num_tokens": 245952105.0, + "step": 414 + }, + { + "epoch": 1.9761904761904763, + "ewc_loss": 0.00021839141845703125, + "grad_norm": 0.8265883922576904, + "learning_rate": 1e-05, + "loss": 1.1206, + "mean_token_accuracy": 0.6808149218559265, + "num_tokens": 246540999.0, + "step": 415 + }, + { + "epoch": 1.980952380952381, + "ewc_loss": 0.00021839141845703125, + "grad_norm": 0.7714787125587463, + "learning_rate": 1e-05, + "loss": 1.127, + "mean_token_accuracy": 0.6805012226104736, + "num_tokens": 247142303.0, + "step": 416 + }, + { + "epoch": 1.9857142857142858, + "ewc_loss": 0.00021839141845703125, + "grad_norm": 0.8024966716766357, + "learning_rate": 1e-05, + "loss": 1.1249, + "mean_token_accuracy": 0.6798273324966431, + "num_tokens": 247732988.0, + "step": 417 + }, + { + "epoch": 1.9904761904761905, + "ewc_loss": 0.00022029876708984375, + "grad_norm": 0.7162186503410339, + "learning_rate": 1e-05, + "loss": 1.1193, + "mean_token_accuracy": 0.6806788444519043, + "num_tokens": 248334744.0, + "step": 418 + }, + { + "epoch": 1.9952380952380953, + "ewc_loss": 0.00022029876708984375, + "grad_norm": 0.7226163744926453, + "learning_rate": 1e-05, + "loss": 1.1302, + "mean_token_accuracy": 0.6784956455230713, + "num_tokens": 248930347.0, + "step": 419 + }, + { + "epoch": 2.0, + "ewc_loss": 0.00022029876708984375, + "grad_norm": 0.7311334013938904, + "learning_rate": 1e-05, + "loss": 1.1458, + "mean_token_accuracy": 0.6754096150398254, + "num_tokens": 249522093.0, + "step": 420 + }, + { + "epoch": 2.0047619047619047, + "ewc_loss": 0.00022029876708984375, + "grad_norm": 0.8578425049781799, + "learning_rate": 1e-05, + "loss": 1.0953, + "mean_token_accuracy": 0.6862645149230957, + "num_tokens": 250112163.0, + "step": 421 + }, + { + "epoch": 2.0095238095238095, + "ewc_loss": 0.00022125244140625, + "grad_norm": 0.7634640336036682, + "learning_rate": 1e-05, + "loss": 1.0832, + "mean_token_accuracy": 0.689671516418457, + "num_tokens": 250690466.0, + "step": 422 + }, + { + "epoch": 2.0142857142857142, + "ewc_loss": 0.00022125244140625, + "grad_norm": 0.6766038537025452, + "learning_rate": 1e-05, + "loss": 1.086, + "mean_token_accuracy": 0.6878221035003662, + "num_tokens": 251279220.0, + "step": 423 + }, + { + "epoch": 2.019047619047619, + "ewc_loss": 0.00022125244140625, + "grad_norm": 0.7540344595909119, + "learning_rate": 1e-05, + "loss": 1.0892, + "mean_token_accuracy": 0.6877608299255371, + "num_tokens": 251871717.0, + "step": 424 + }, + { + "epoch": 2.0238095238095237, + "ewc_loss": 0.0002231597900390625, + "grad_norm": 0.6913050413131714, + "learning_rate": 1e-05, + "loss": 1.1088, + "mean_token_accuracy": 0.6827316880226135, + "num_tokens": 252474129.0, + "step": 425 + }, + { + "epoch": 2.0285714285714285, + "ewc_loss": 0.000225067138671875, + "grad_norm": 0.6734918355941772, + "learning_rate": 1e-05, + "loss": 1.07, + "mean_token_accuracy": 0.6919132471084595, + "num_tokens": 253069065.0, + "step": 426 + }, + { + "epoch": 2.033333333333333, + "ewc_loss": 0.00022411346435546875, + "grad_norm": 0.6644809246063232, + "learning_rate": 1e-05, + "loss": 1.0972, + "mean_token_accuracy": 0.6849592924118042, + "num_tokens": 253654392.0, + "step": 427 + }, + { + "epoch": 2.038095238095238, + "ewc_loss": 0.000225067138671875, + "grad_norm": 0.624981701374054, + "learning_rate": 1e-05, + "loss": 1.0867, + "mean_token_accuracy": 0.6875358819961548, + "num_tokens": 254245168.0, + "step": 428 + }, + { + "epoch": 2.0428571428571427, + "ewc_loss": 0.000225067138671875, + "grad_norm": 0.6262357234954834, + "learning_rate": 1e-05, + "loss": 1.1004, + "mean_token_accuracy": 0.6838569641113281, + "num_tokens": 254841132.0, + "step": 429 + }, + { + "epoch": 2.0476190476190474, + "ewc_loss": 0.000225067138671875, + "grad_norm": 0.6207374334335327, + "learning_rate": 1e-05, + "loss": 1.0859, + "mean_token_accuracy": 0.6880031824111938, + "num_tokens": 255433793.0, + "step": 430 + }, + { + "epoch": 2.052380952380952, + "ewc_loss": 0.000225067138671875, + "grad_norm": 0.7145369052886963, + "learning_rate": 1e-05, + "loss": 1.084, + "mean_token_accuracy": 0.6888326406478882, + "num_tokens": 256015225.0, + "step": 431 + }, + { + "epoch": 2.057142857142857, + "ewc_loss": 0.0002269744873046875, + "grad_norm": 0.6520535349845886, + "learning_rate": 1e-05, + "loss": 1.0822, + "mean_token_accuracy": 0.688860297203064, + "num_tokens": 256617333.0, + "step": 432 + }, + { + "epoch": 2.0619047619047617, + "ewc_loss": 0.0002269744873046875, + "grad_norm": 0.6045935750007629, + "learning_rate": 1e-05, + "loss": 1.1099, + "mean_token_accuracy": 0.6832070350646973, + "num_tokens": 257214120.0, + "step": 433 + }, + { + "epoch": 2.066666666666667, + "ewc_loss": 0.0002269744873046875, + "grad_norm": 0.6979225277900696, + "learning_rate": 1e-05, + "loss": 1.0893, + "mean_token_accuracy": 0.6868165731430054, + "num_tokens": 257807506.0, + "step": 434 + }, + { + "epoch": 2.0714285714285716, + "ewc_loss": 0.0002288818359375, + "grad_norm": 0.6106749773025513, + "learning_rate": 1e-05, + "loss": 1.1059, + "mean_token_accuracy": 0.6829272508621216, + "num_tokens": 258414225.0, + "step": 435 + }, + { + "epoch": 2.0761904761904764, + "ewc_loss": 0.0002288818359375, + "grad_norm": 0.6551795601844788, + "learning_rate": 1e-05, + "loss": 1.0871, + "mean_token_accuracy": 0.6866270303726196, + "num_tokens": 259009305.0, + "step": 436 + }, + { + "epoch": 2.080952380952381, + "ewc_loss": 0.0002288818359375, + "grad_norm": 0.6068414449691772, + "learning_rate": 1e-05, + "loss": 1.0812, + "mean_token_accuracy": 0.6889495849609375, + "num_tokens": 259600283.0, + "step": 437 + }, + { + "epoch": 2.085714285714286, + "ewc_loss": 0.0002288818359375, + "grad_norm": 0.6038678884506226, + "learning_rate": 1e-05, + "loss": 1.1068, + "mean_token_accuracy": 0.6829336881637573, + "num_tokens": 260203907.0, + "step": 438 + }, + { + "epoch": 2.0904761904761906, + "ewc_loss": 0.00022983551025390625, + "grad_norm": 0.642615795135498, + "learning_rate": 1e-05, + "loss": 1.1015, + "mean_token_accuracy": 0.6835439801216125, + "num_tokens": 260795356.0, + "step": 439 + }, + { + "epoch": 2.0952380952380953, + "ewc_loss": 0.0002307891845703125, + "grad_norm": 0.634620189666748, + "learning_rate": 1e-05, + "loss": 1.0788, + "mean_token_accuracy": 0.690065860748291, + "num_tokens": 261376414.0, + "step": 440 + }, + { + "epoch": 2.1, + "ewc_loss": 0.0002307891845703125, + "grad_norm": 0.6749728918075562, + "learning_rate": 1e-05, + "loss": 1.1047, + "mean_token_accuracy": 0.683939516544342, + "num_tokens": 261965206.0, + "step": 441 + }, + { + "epoch": 2.104761904761905, + "ewc_loss": 0.0002307891845703125, + "grad_norm": 0.5971515774726868, + "learning_rate": 1e-05, + "loss": 1.0979, + "mean_token_accuracy": 0.6850525140762329, + "num_tokens": 262561371.0, + "step": 442 + }, + { + "epoch": 2.1095238095238096, + "ewc_loss": 0.0002307891845703125, + "grad_norm": 0.6850727796554565, + "learning_rate": 1e-05, + "loss": 1.0873, + "mean_token_accuracy": 0.6881117820739746, + "num_tokens": 263159935.0, + "step": 443 + }, + { + "epoch": 2.1142857142857143, + "ewc_loss": 0.00023174285888671875, + "grad_norm": 0.6744555830955505, + "learning_rate": 1e-05, + "loss": 1.0995, + "mean_token_accuracy": 0.6837301850318909, + "num_tokens": 263754299.0, + "step": 444 + }, + { + "epoch": 2.119047619047619, + "ewc_loss": 0.00023365020751953125, + "grad_norm": 0.6423435807228088, + "learning_rate": 1e-05, + "loss": 1.0987, + "mean_token_accuracy": 0.6849546432495117, + "num_tokens": 264354630.0, + "step": 445 + }, + { + "epoch": 2.123809523809524, + "ewc_loss": 0.0002346038818359375, + "grad_norm": 0.6921698451042175, + "learning_rate": 1e-05, + "loss": 1.1192, + "mean_token_accuracy": 0.6797018051147461, + "num_tokens": 264964353.0, + "step": 446 + }, + { + "epoch": 2.1285714285714286, + "ewc_loss": 0.0002346038818359375, + "grad_norm": 0.6895200610160828, + "learning_rate": 1e-05, + "loss": 1.1009, + "mean_token_accuracy": 0.6842555999755859, + "num_tokens": 265561411.0, + "step": 447 + }, + { + "epoch": 2.1333333333333333, + "ewc_loss": 0.00023651123046875, + "grad_norm": 0.682570219039917, + "learning_rate": 1e-05, + "loss": 1.0924, + "mean_token_accuracy": 0.6860439777374268, + "num_tokens": 266155790.0, + "step": 448 + }, + { + "epoch": 2.138095238095238, + "ewc_loss": 0.00023651123046875, + "grad_norm": 0.6175945401191711, + "learning_rate": 1e-05, + "loss": 1.0986, + "mean_token_accuracy": 0.6853482723236084, + "num_tokens": 266757269.0, + "step": 449 + }, + { + "epoch": 2.142857142857143, + "ewc_loss": 0.00023651123046875, + "grad_norm": 0.6771435141563416, + "learning_rate": 1e-05, + "loss": 1.114, + "mean_token_accuracy": 0.6814285516738892, + "num_tokens": 267369143.0, + "step": 450 + }, + { + "epoch": 2.1476190476190475, + "ewc_loss": 0.00023746490478515625, + "grad_norm": 0.6228008270263672, + "learning_rate": 1e-05, + "loss": 1.0817, + "mean_token_accuracy": 0.6898776292800903, + "num_tokens": 267965437.0, + "step": 451 + }, + { + "epoch": 2.1523809523809523, + "ewc_loss": 0.00023746490478515625, + "grad_norm": 0.6344319581985474, + "learning_rate": 1e-05, + "loss": 1.0911, + "mean_token_accuracy": 0.6870379447937012, + "num_tokens": 268571463.0, + "step": 452 + }, + { + "epoch": 2.157142857142857, + "ewc_loss": 0.00023937225341796875, + "grad_norm": 0.6430404186248779, + "learning_rate": 1e-05, + "loss": 1.0898, + "mean_token_accuracy": 0.6871657371520996, + "num_tokens": 269157041.0, + "step": 453 + }, + { + "epoch": 2.1619047619047618, + "ewc_loss": 0.000240325927734375, + "grad_norm": 0.6411321759223938, + "learning_rate": 1e-05, + "loss": 1.0882, + "mean_token_accuracy": 0.6875712871551514, + "num_tokens": 269758195.0, + "step": 454 + }, + { + "epoch": 2.1666666666666665, + "ewc_loss": 0.000240325927734375, + "grad_norm": 0.6321033239364624, + "learning_rate": 1e-05, + "loss": 1.117, + "mean_token_accuracy": 0.6806339025497437, + "num_tokens": 270349613.0, + "step": 455 + }, + { + "epoch": 2.1714285714285713, + "ewc_loss": 0.000240325927734375, + "grad_norm": 0.634148120880127, + "learning_rate": 1e-05, + "loss": 1.1035, + "mean_token_accuracy": 0.6824407577514648, + "num_tokens": 270947174.0, + "step": 456 + }, + { + "epoch": 2.176190476190476, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.6483026146888733, + "learning_rate": 1e-05, + "loss": 1.1126, + "mean_token_accuracy": 0.6817720532417297, + "num_tokens": 271549889.0, + "step": 457 + }, + { + "epoch": 2.1809523809523808, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.6000745892524719, + "learning_rate": 1e-05, + "loss": 1.0842, + "mean_token_accuracy": 0.6890138387680054, + "num_tokens": 272139782.0, + "step": 458 + }, + { + "epoch": 2.185714285714286, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.6325382590293884, + "learning_rate": 1e-05, + "loss": 1.0965, + "mean_token_accuracy": 0.6854788064956665, + "num_tokens": 272746279.0, + "step": 459 + }, + { + "epoch": 2.1904761904761907, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.684240460395813, + "learning_rate": 1e-05, + "loss": 1.0829, + "mean_token_accuracy": 0.6891235113143921, + "num_tokens": 273348449.0, + "step": 460 + }, + { + "epoch": 2.1952380952380954, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.6116349101066589, + "learning_rate": 1e-05, + "loss": 1.1058, + "mean_token_accuracy": 0.6841614842414856, + "num_tokens": 273949928.0, + "step": 461 + }, + { + "epoch": 2.2, + "ewc_loss": 0.00024127960205078125, + "grad_norm": 0.6647228598594666, + "learning_rate": 1e-05, + "loss": 1.0936, + "mean_token_accuracy": 0.6860436201095581, + "num_tokens": 274548070.0, + "step": 462 + }, + { + "epoch": 2.204761904761905, + "ewc_loss": 0.0002422332763671875, + "grad_norm": 0.6649495363235474, + "learning_rate": 1e-05, + "loss": 1.096, + "mean_token_accuracy": 0.6850506663322449, + "num_tokens": 275135656.0, + "step": 463 + }, + { + "epoch": 2.2095238095238097, + "ewc_loss": 0.0002422332763671875, + "grad_norm": 0.6741588115692139, + "learning_rate": 1e-05, + "loss": 1.0967, + "mean_token_accuracy": 0.6854337453842163, + "num_tokens": 275740663.0, + "step": 464 + }, + { + "epoch": 2.2142857142857144, + "ewc_loss": 0.0002422332763671875, + "grad_norm": 0.6212270855903625, + "learning_rate": 1e-05, + "loss": 1.0957, + "mean_token_accuracy": 0.6866968870162964, + "num_tokens": 276346207.0, + "step": 465 + }, + { + "epoch": 2.219047619047619, + "ewc_loss": 0.00024318695068359375, + "grad_norm": 0.6458845734596252, + "learning_rate": 1e-05, + "loss": 1.0957, + "mean_token_accuracy": 0.6854987144470215, + "num_tokens": 276940208.0, + "step": 466 + }, + { + "epoch": 2.223809523809524, + "ewc_loss": 0.00024318695068359375, + "grad_norm": 0.6392099261283875, + "learning_rate": 1e-05, + "loss": 1.1113, + "mean_token_accuracy": 0.6819874048233032, + "num_tokens": 277539762.0, + "step": 467 + }, + { + "epoch": 2.2285714285714286, + "ewc_loss": 0.00024318695068359375, + "grad_norm": 0.7088193893432617, + "learning_rate": 1e-05, + "loss": 1.1073, + "mean_token_accuracy": 0.6821719408035278, + "num_tokens": 278136526.0, + "step": 468 + }, + { + "epoch": 2.2333333333333334, + "ewc_loss": 0.000244140625, + "grad_norm": 0.6352142095565796, + "learning_rate": 1e-05, + "loss": 1.0975, + "mean_token_accuracy": 0.6854268312454224, + "num_tokens": 278723575.0, + "step": 469 + }, + { + "epoch": 2.238095238095238, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6939430236816406, + "learning_rate": 1e-05, + "loss": 1.0752, + "mean_token_accuracy": 0.6909745931625366, + "num_tokens": 279313692.0, + "step": 470 + }, + { + "epoch": 2.242857142857143, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6521109342575073, + "learning_rate": 1e-05, + "loss": 1.1077, + "mean_token_accuracy": 0.6827565431594849, + "num_tokens": 279911596.0, + "step": 471 + }, + { + "epoch": 2.2476190476190476, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6479250192642212, + "learning_rate": 1e-05, + "loss": 1.091, + "mean_token_accuracy": 0.6876091361045837, + "num_tokens": 280516626.0, + "step": 472 + }, + { + "epoch": 2.2523809523809524, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6596609950065613, + "learning_rate": 1e-05, + "loss": 1.093, + "mean_token_accuracy": 0.6872715950012207, + "num_tokens": 281109826.0, + "step": 473 + }, + { + "epoch": 2.257142857142857, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6441872119903564, + "learning_rate": 1e-05, + "loss": 1.099, + "mean_token_accuracy": 0.6854004263877869, + "num_tokens": 281705908.0, + "step": 474 + }, + { + "epoch": 2.261904761904762, + "ewc_loss": 0.0002460479736328125, + "grad_norm": 0.6421202421188354, + "learning_rate": 1e-05, + "loss": 1.0943, + "mean_token_accuracy": 0.6859012842178345, + "num_tokens": 282295646.0, + "step": 475 + }, + { + "epoch": 2.2666666666666666, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6606177091598511, + "learning_rate": 1e-05, + "loss": 1.0851, + "mean_token_accuracy": 0.6878588199615479, + "num_tokens": 282882984.0, + "step": 476 + }, + { + "epoch": 2.2714285714285714, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6211093068122864, + "learning_rate": 1e-05, + "loss": 1.0916, + "mean_token_accuracy": 0.6873608827590942, + "num_tokens": 283470314.0, + "step": 477 + }, + { + "epoch": 2.276190476190476, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6513420939445496, + "learning_rate": 1e-05, + "loss": 1.094, + "mean_token_accuracy": 0.6858557462692261, + "num_tokens": 284064822.0, + "step": 478 + }, + { + "epoch": 2.280952380952381, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6506226062774658, + "learning_rate": 1e-05, + "loss": 1.0878, + "mean_token_accuracy": 0.688177227973938, + "num_tokens": 284659143.0, + "step": 479 + }, + { + "epoch": 2.2857142857142856, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6157212853431702, + "learning_rate": 1e-05, + "loss": 1.0998, + "mean_token_accuracy": 0.6856635808944702, + "num_tokens": 285260603.0, + "step": 480 + }, + { + "epoch": 2.2904761904761903, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6622475981712341, + "learning_rate": 1e-05, + "loss": 1.0874, + "mean_token_accuracy": 0.6871859431266785, + "num_tokens": 285858617.0, + "step": 481 + }, + { + "epoch": 2.295238095238095, + "ewc_loss": 0.0002498626708984375, + "grad_norm": 0.6582114100456238, + "learning_rate": 1e-05, + "loss": 1.0945, + "mean_token_accuracy": 0.6868870258331299, + "num_tokens": 286462909.0, + "step": 482 + }, + { + "epoch": 2.3, + "ewc_loss": 0.00025177001953125, + "grad_norm": 0.7757292985916138, + "learning_rate": 1e-05, + "loss": 1.0896, + "mean_token_accuracy": 0.6877955198287964, + "num_tokens": 287057508.0, + "step": 483 + }, + { + "epoch": 2.3047619047619046, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.6204884052276611, + "learning_rate": 1e-05, + "loss": 1.0995, + "mean_token_accuracy": 0.6847972273826599, + "num_tokens": 287647864.0, + "step": 484 + }, + { + "epoch": 2.3095238095238093, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.7772699594497681, + "learning_rate": 1e-05, + "loss": 1.1017, + "mean_token_accuracy": 0.6844268441200256, + "num_tokens": 288244654.0, + "step": 485 + }, + { + "epoch": 2.314285714285714, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.6531155705451965, + "learning_rate": 1e-05, + "loss": 1.1108, + "mean_token_accuracy": 0.68239426612854, + "num_tokens": 288833805.0, + "step": 486 + }, + { + "epoch": 2.319047619047619, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.6397417783737183, + "learning_rate": 1e-05, + "loss": 1.0938, + "mean_token_accuracy": 0.6862900257110596, + "num_tokens": 289430249.0, + "step": 487 + }, + { + "epoch": 2.323809523809524, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.7201059460639954, + "learning_rate": 1e-05, + "loss": 1.0948, + "mean_token_accuracy": 0.6874886751174927, + "num_tokens": 290017640.0, + "step": 488 + }, + { + "epoch": 2.3285714285714287, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.634040355682373, + "learning_rate": 1e-05, + "loss": 1.0906, + "mean_token_accuracy": 0.6867818832397461, + "num_tokens": 290598414.0, + "step": 489 + }, + { + "epoch": 2.3333333333333335, + "ewc_loss": 0.0002536773681640625, + "grad_norm": 0.7719990611076355, + "learning_rate": 1e-05, + "loss": 1.0821, + "mean_token_accuracy": 0.6888085603713989, + "num_tokens": 291181812.0, + "step": 490 + }, + { + "epoch": 2.3380952380952382, + "ewc_loss": 0.000255584716796875, + "grad_norm": 0.6298912167549133, + "learning_rate": 1e-05, + "loss": 1.0958, + "mean_token_accuracy": 0.6860299706459045, + "num_tokens": 291764317.0, + "step": 491 + }, + { + "epoch": 2.342857142857143, + "ewc_loss": 0.000255584716796875, + "grad_norm": 0.6416546702384949, + "learning_rate": 1e-05, + "loss": 1.1023, + "mean_token_accuracy": 0.683631420135498, + "num_tokens": 292350504.0, + "step": 492 + }, + { + "epoch": 2.3476190476190477, + "ewc_loss": 0.000255584716796875, + "grad_norm": 0.641428530216217, + "learning_rate": 1e-05, + "loss": 1.0988, + "mean_token_accuracy": 0.684672474861145, + "num_tokens": 292951776.0, + "step": 493 + }, + { + "epoch": 2.3523809523809525, + "ewc_loss": 0.000255584716796875, + "grad_norm": 0.6588485240936279, + "learning_rate": 1e-05, + "loss": 1.0906, + "mean_token_accuracy": 0.6867492198944092, + "num_tokens": 293532488.0, + "step": 494 + }, + { + "epoch": 2.357142857142857, + "ewc_loss": 0.0002574920654296875, + "grad_norm": 0.6672496795654297, + "learning_rate": 1e-05, + "loss": 1.0786, + "mean_token_accuracy": 0.6902459859848022, + "num_tokens": 294121146.0, + "step": 495 + }, + { + "epoch": 2.361904761904762, + "ewc_loss": 0.0002574920654296875, + "grad_norm": 0.6488090753555298, + "learning_rate": 1e-05, + "loss": 1.0985, + "mean_token_accuracy": 0.6855859160423279, + "num_tokens": 294726732.0, + "step": 496 + }, + { + "epoch": 2.3666666666666667, + "ewc_loss": 0.0002593994140625, + "grad_norm": 0.740645170211792, + "learning_rate": 1e-05, + "loss": 1.0897, + "mean_token_accuracy": 0.6874679923057556, + "num_tokens": 295306697.0, + "step": 497 + }, + { + "epoch": 2.3714285714285714, + "ewc_loss": 0.0002593994140625, + "grad_norm": 0.7239862680435181, + "learning_rate": 1e-05, + "loss": 1.1106, + "mean_token_accuracy": 0.6815863847732544, + "num_tokens": 295894972.0, + "step": 498 + }, + { + "epoch": 2.376190476190476, + "ewc_loss": 0.0002593994140625, + "grad_norm": 0.7529853582382202, + "learning_rate": 1e-05, + "loss": 1.105, + "mean_token_accuracy": 0.6833587884902954, + "num_tokens": 296505345.0, + "step": 499 + }, + { + "epoch": 2.380952380952381, + "ewc_loss": 0.0002593994140625, + "grad_norm": 0.7494781017303467, + "learning_rate": 1e-05, + "loss": 1.088, + "mean_token_accuracy": 0.687516450881958, + "num_tokens": 297100909.0, + "step": 500 + }, + { + "epoch": 2.3857142857142857, + "ewc_loss": 0.0002613067626953125, + "grad_norm": 0.7255764007568359, + "learning_rate": 1e-05, + "loss": 1.0963, + "mean_token_accuracy": 0.6865135431289673, + "num_tokens": 297690267.0, + "step": 501 + }, + { + "epoch": 2.3904761904761904, + "ewc_loss": 0.0002613067626953125, + "grad_norm": 0.6610298156738281, + "learning_rate": 1e-05, + "loss": 1.0868, + "mean_token_accuracy": 0.6878113150596619, + "num_tokens": 298283484.0, + "step": 502 + }, + { + "epoch": 2.395238095238095, + "ewc_loss": 0.0002613067626953125, + "grad_norm": 0.6402058005332947, + "learning_rate": 1e-05, + "loss": 1.1029, + "mean_token_accuracy": 0.6836656332015991, + "num_tokens": 298880193.0, + "step": 503 + }, + { + "epoch": 2.4, + "ewc_loss": 0.0002613067626953125, + "grad_norm": 0.6304318904876709, + "learning_rate": 1e-05, + "loss": 1.08, + "mean_token_accuracy": 0.689216136932373, + "num_tokens": 299479995.0, + "step": 504 + }, + { + "epoch": 2.4047619047619047, + "ewc_loss": 0.0002613067626953125, + "grad_norm": 0.6863888502120972, + "learning_rate": 1e-05, + "loss": 1.095, + "mean_token_accuracy": 0.6860719919204712, + "num_tokens": 300068384.0, + "step": 505 + }, + { + "epoch": 2.4095238095238094, + "ewc_loss": 0.0002651214599609375, + "grad_norm": 0.6324161291122437, + "learning_rate": 1e-05, + "loss": 1.1051, + "mean_token_accuracy": 0.6829588413238525, + "num_tokens": 300687274.0, + "step": 506 + }, + { + "epoch": 2.414285714285714, + "ewc_loss": 0.0002651214599609375, + "grad_norm": 0.6402003765106201, + "learning_rate": 1e-05, + "loss": 1.0972, + "mean_token_accuracy": 0.6850780248641968, + "num_tokens": 301288728.0, + "step": 507 + }, + { + "epoch": 2.419047619047619, + "ewc_loss": 0.0002651214599609375, + "grad_norm": 0.6511923670768738, + "learning_rate": 1e-05, + "loss": 1.0918, + "mean_token_accuracy": 0.6871336698532104, + "num_tokens": 301868926.0, + "step": 508 + }, + { + "epoch": 2.4238095238095236, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.5909934043884277, + "learning_rate": 1e-05, + "loss": 1.0867, + "mean_token_accuracy": 0.6885550022125244, + "num_tokens": 302467630.0, + "step": 509 + }, + { + "epoch": 2.4285714285714284, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.6420947909355164, + "learning_rate": 1e-05, + "loss": 1.1124, + "mean_token_accuracy": 0.6827173233032227, + "num_tokens": 303058965.0, + "step": 510 + }, + { + "epoch": 2.4333333333333336, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.7422255873680115, + "learning_rate": 1e-05, + "loss": 1.1132, + "mean_token_accuracy": 0.6811249852180481, + "num_tokens": 303639694.0, + "step": 511 + }, + { + "epoch": 2.4380952380952383, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.5849118232727051, + "learning_rate": 1e-05, + "loss": 1.0872, + "mean_token_accuracy": 0.688429594039917, + "num_tokens": 304234504.0, + "step": 512 + }, + { + "epoch": 2.442857142857143, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.6605814695358276, + "learning_rate": 1e-05, + "loss": 1.1072, + "mean_token_accuracy": 0.6834832429885864, + "num_tokens": 304822484.0, + "step": 513 + }, + { + "epoch": 2.447619047619048, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.6439646482467651, + "learning_rate": 1e-05, + "loss": 1.0914, + "mean_token_accuracy": 0.6877273321151733, + "num_tokens": 305405226.0, + "step": 514 + }, + { + "epoch": 2.4523809523809526, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.6148564219474792, + "learning_rate": 1e-05, + "loss": 1.0926, + "mean_token_accuracy": 0.6872304677963257, + "num_tokens": 306007153.0, + "step": 515 + }, + { + "epoch": 2.4571428571428573, + "ewc_loss": 0.00026702880859375, + "grad_norm": 0.7719348669052124, + "learning_rate": 1e-05, + "loss": 1.0925, + "mean_token_accuracy": 0.687697172164917, + "num_tokens": 306588836.0, + "step": 516 + }, + { + "epoch": 2.461904761904762, + "ewc_loss": 0.0002689361572265625, + "grad_norm": 0.6450639963150024, + "learning_rate": 1e-05, + "loss": 1.1026, + "mean_token_accuracy": 0.6843742728233337, + "num_tokens": 307200955.0, + "step": 517 + }, + { + "epoch": 2.466666666666667, + "ewc_loss": 0.0002689361572265625, + "grad_norm": 0.6376486420631409, + "learning_rate": 1e-05, + "loss": 1.0897, + "mean_token_accuracy": 0.6869982481002808, + "num_tokens": 307799028.0, + "step": 518 + }, + { + "epoch": 2.4714285714285715, + "ewc_loss": 0.000270843505859375, + "grad_norm": 0.6870455145835876, + "learning_rate": 1e-05, + "loss": 1.1194, + "mean_token_accuracy": 0.6805319786071777, + "num_tokens": 308389748.0, + "step": 519 + }, + { + "epoch": 2.4761904761904763, + "ewc_loss": 0.000270843505859375, + "grad_norm": 0.7288525700569153, + "learning_rate": 1e-05, + "loss": 1.1, + "mean_token_accuracy": 0.6850531101226807, + "num_tokens": 308978715.0, + "step": 520 + }, + { + "epoch": 2.480952380952381, + "ewc_loss": 0.000270843505859375, + "grad_norm": 0.6307763457298279, + "learning_rate": 1e-05, + "loss": 1.0982, + "mean_token_accuracy": 0.6853634119033813, + "num_tokens": 309587298.0, + "step": 521 + }, + { + "epoch": 2.4857142857142858, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6117209792137146, + "learning_rate": 1e-05, + "loss": 1.0872, + "mean_token_accuracy": 0.6878750920295715, + "num_tokens": 310173585.0, + "step": 522 + }, + { + "epoch": 2.4904761904761905, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.705482006072998, + "learning_rate": 1e-05, + "loss": 1.0964, + "mean_token_accuracy": 0.6861386299133301, + "num_tokens": 310760313.0, + "step": 523 + }, + { + "epoch": 2.4952380952380953, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6580640077590942, + "learning_rate": 1e-05, + "loss": 1.0993, + "mean_token_accuracy": 0.6852800250053406, + "num_tokens": 311374002.0, + "step": 524 + }, + { + "epoch": 2.5, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6252064108848572, + "learning_rate": 1e-05, + "loss": 1.093, + "mean_token_accuracy": 0.6863818764686584, + "num_tokens": 311952533.0, + "step": 525 + }, + { + "epoch": 2.5047619047619047, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6290083527565002, + "learning_rate": 1e-05, + "loss": 1.0884, + "mean_token_accuracy": 0.6875872611999512, + "num_tokens": 312542383.0, + "step": 526 + }, + { + "epoch": 2.5095238095238095, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6927263736724854, + "learning_rate": 1e-05, + "loss": 1.0975, + "mean_token_accuracy": 0.6845716238021851, + "num_tokens": 313136427.0, + "step": 527 + }, + { + "epoch": 2.5142857142857142, + "ewc_loss": 0.0002727508544921875, + "grad_norm": 0.6051463484764099, + "learning_rate": 1e-05, + "loss": 1.0791, + "mean_token_accuracy": 0.6904033422470093, + "num_tokens": 313731115.0, + "step": 528 + }, + { + "epoch": 2.519047619047619, + "ewc_loss": 0.000274658203125, + "grad_norm": 0.596738338470459, + "learning_rate": 1e-05, + "loss": 1.0876, + "mean_token_accuracy": 0.6877933740615845, + "num_tokens": 314316253.0, + "step": 529 + }, + { + "epoch": 2.5238095238095237, + "ewc_loss": 0.000274658203125, + "grad_norm": 0.6629331707954407, + "learning_rate": 1e-05, + "loss": 1.0863, + "mean_token_accuracy": 0.6883895397186279, + "num_tokens": 314906539.0, + "step": 530 + }, + { + "epoch": 2.5285714285714285, + "ewc_loss": 0.000274658203125, + "grad_norm": 0.6418980956077576, + "learning_rate": 1e-05, + "loss": 1.0841, + "mean_token_accuracy": 0.6888552904129028, + "num_tokens": 315491005.0, + "step": 531 + }, + { + "epoch": 2.533333333333333, + "ewc_loss": 0.000274658203125, + "grad_norm": 0.7186934351921082, + "learning_rate": 1e-05, + "loss": 1.0994, + "mean_token_accuracy": 0.684372067451477, + "num_tokens": 316086156.0, + "step": 532 + }, + { + "epoch": 2.538095238095238, + "ewc_loss": 0.000274658203125, + "grad_norm": 0.6993562579154968, + "learning_rate": 1e-05, + "loss": 1.1043, + "mean_token_accuracy": 0.6843150854110718, + "num_tokens": 316687284.0, + "step": 533 + }, + { + "epoch": 2.5428571428571427, + "ewc_loss": 0.000278472900390625, + "grad_norm": 0.6663571000099182, + "learning_rate": 1e-05, + "loss": 1.0885, + "mean_token_accuracy": 0.6884730458259583, + "num_tokens": 317280976.0, + "step": 534 + }, + { + "epoch": 2.5476190476190474, + "ewc_loss": 0.000278472900390625, + "grad_norm": 0.7372015118598938, + "learning_rate": 1e-05, + "loss": 1.0956, + "mean_token_accuracy": 0.6859520077705383, + "num_tokens": 317869704.0, + "step": 535 + }, + { + "epoch": 2.552380952380952, + "ewc_loss": 0.000278472900390625, + "grad_norm": 0.6314377784729004, + "learning_rate": 1e-05, + "loss": 1.0989, + "mean_token_accuracy": 0.6853036880493164, + "num_tokens": 318453830.0, + "step": 536 + }, + { + "epoch": 2.557142857142857, + "ewc_loss": 0.000278472900390625, + "grad_norm": 0.7449570894241333, + "learning_rate": 1e-05, + "loss": 1.1053, + "mean_token_accuracy": 0.6832983493804932, + "num_tokens": 319036628.0, + "step": 537 + }, + { + "epoch": 2.5619047619047617, + "ewc_loss": 0.0002803802490234375, + "grad_norm": 0.6725446581840515, + "learning_rate": 1e-05, + "loss": 1.0906, + "mean_token_accuracy": 0.687649130821228, + "num_tokens": 319641680.0, + "step": 538 + }, + { + "epoch": 2.5666666666666664, + "ewc_loss": 0.0002803802490234375, + "grad_norm": 0.676888108253479, + "learning_rate": 1e-05, + "loss": 1.0969, + "mean_token_accuracy": 0.6854783296585083, + "num_tokens": 320235018.0, + "step": 539 + }, + { + "epoch": 2.571428571428571, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.6857782006263733, + "learning_rate": 1e-05, + "loss": 1.1019, + "mean_token_accuracy": 0.6843587160110474, + "num_tokens": 320839523.0, + "step": 540 + }, + { + "epoch": 2.576190476190476, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.6418814659118652, + "learning_rate": 1e-05, + "loss": 1.0929, + "mean_token_accuracy": 0.6861611604690552, + "num_tokens": 321445469.0, + "step": 541 + }, + { + "epoch": 2.580952380952381, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.6760387420654297, + "learning_rate": 1e-05, + "loss": 1.1004, + "mean_token_accuracy": 0.6836677193641663, + "num_tokens": 322040382.0, + "step": 542 + }, + { + "epoch": 2.585714285714286, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.7056438326835632, + "learning_rate": 1e-05, + "loss": 1.0974, + "mean_token_accuracy": 0.6857728362083435, + "num_tokens": 322631980.0, + "step": 543 + }, + { + "epoch": 2.5904761904761906, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.5993045568466187, + "learning_rate": 1e-05, + "loss": 1.0953, + "mean_token_accuracy": 0.6852395534515381, + "num_tokens": 323217003.0, + "step": 544 + }, + { + "epoch": 2.5952380952380953, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.7542611360549927, + "learning_rate": 1e-05, + "loss": 1.099, + "mean_token_accuracy": 0.6849566698074341, + "num_tokens": 323797882.0, + "step": 545 + }, + { + "epoch": 2.6, + "ewc_loss": 0.00028228759765625, + "grad_norm": 0.7374502420425415, + "learning_rate": 1e-05, + "loss": 1.1028, + "mean_token_accuracy": 0.68355792760849, + "num_tokens": 324381508.0, + "step": 546 + }, + { + "epoch": 2.604761904761905, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.6817171573638916, + "learning_rate": 1e-05, + "loss": 1.1195, + "mean_token_accuracy": 0.6800934076309204, + "num_tokens": 324979976.0, + "step": 547 + }, + { + "epoch": 2.6095238095238096, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.8233842253684998, + "learning_rate": 1e-05, + "loss": 1.0921, + "mean_token_accuracy": 0.6865252256393433, + "num_tokens": 325579147.0, + "step": 548 + }, + { + "epoch": 2.6142857142857143, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.5994913578033447, + "learning_rate": 1e-05, + "loss": 1.0943, + "mean_token_accuracy": 0.6869341731071472, + "num_tokens": 326189724.0, + "step": 549 + }, + { + "epoch": 2.619047619047619, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.7653443217277527, + "learning_rate": 1e-05, + "loss": 1.0966, + "mean_token_accuracy": 0.685234785079956, + "num_tokens": 326781040.0, + "step": 550 + }, + { + "epoch": 2.623809523809524, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.6217694282531738, + "learning_rate": 1e-05, + "loss": 1.0901, + "mean_token_accuracy": 0.6882113814353943, + "num_tokens": 327384993.0, + "step": 551 + }, + { + "epoch": 2.6285714285714286, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.718234121799469, + "learning_rate": 1e-05, + "loss": 1.0784, + "mean_token_accuracy": 0.6902750730514526, + "num_tokens": 327967527.0, + "step": 552 + }, + { + "epoch": 2.6333333333333333, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.6313990950584412, + "learning_rate": 1e-05, + "loss": 1.0843, + "mean_token_accuracy": 0.6890004277229309, + "num_tokens": 328556111.0, + "step": 553 + }, + { + "epoch": 2.638095238095238, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.6425944566726685, + "learning_rate": 1e-05, + "loss": 1.0911, + "mean_token_accuracy": 0.6867983341217041, + "num_tokens": 329156419.0, + "step": 554 + }, + { + "epoch": 2.642857142857143, + "ewc_loss": 0.0002841949462890625, + "grad_norm": 0.6443769335746765, + "learning_rate": 1e-05, + "loss": 1.1149, + "mean_token_accuracy": 0.6811692714691162, + "num_tokens": 329765795.0, + "step": 555 + }, + { + "epoch": 2.6476190476190475, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.5741829872131348, + "learning_rate": 1e-05, + "loss": 1.0955, + "mean_token_accuracy": 0.6868147850036621, + "num_tokens": 330366805.0, + "step": 556 + }, + { + "epoch": 2.6523809523809523, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.6206058859825134, + "learning_rate": 1e-05, + "loss": 1.0839, + "mean_token_accuracy": 0.6878576278686523, + "num_tokens": 330960683.0, + "step": 557 + }, + { + "epoch": 2.657142857142857, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.6149351000785828, + "learning_rate": 1e-05, + "loss": 1.1007, + "mean_token_accuracy": 0.6851035356521606, + "num_tokens": 331566617.0, + "step": 558 + }, + { + "epoch": 2.6619047619047618, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.7190388441085815, + "learning_rate": 1e-05, + "loss": 1.0847, + "mean_token_accuracy": 0.6887768507003784, + "num_tokens": 332146780.0, + "step": 559 + }, + { + "epoch": 2.6666666666666665, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.6560397744178772, + "learning_rate": 1e-05, + "loss": 1.0969, + "mean_token_accuracy": 0.6865469217300415, + "num_tokens": 332744565.0, + "step": 560 + }, + { + "epoch": 2.6714285714285713, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.622414767742157, + "learning_rate": 1e-05, + "loss": 1.096, + "mean_token_accuracy": 0.6858752965927124, + "num_tokens": 333327246.0, + "step": 561 + }, + { + "epoch": 2.6761904761904765, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.6037507057189941, + "learning_rate": 1e-05, + "loss": 1.0843, + "mean_token_accuracy": 0.6884275674819946, + "num_tokens": 333924279.0, + "step": 562 + }, + { + "epoch": 2.680952380952381, + "ewc_loss": 0.000286102294921875, + "grad_norm": 0.6246011853218079, + "learning_rate": 1e-05, + "loss": 1.0867, + "mean_token_accuracy": 0.6876472234725952, + "num_tokens": 334526451.0, + "step": 563 + }, + { + "epoch": 2.685714285714286, + "ewc_loss": 0.0002918243408203125, + "grad_norm": 0.5896040797233582, + "learning_rate": 1e-05, + "loss": 1.097, + "mean_token_accuracy": 0.6860911250114441, + "num_tokens": 335121296.0, + "step": 564 + }, + { + "epoch": 2.6904761904761907, + "ewc_loss": 0.0002918243408203125, + "grad_norm": 0.6939911246299744, + "learning_rate": 1e-05, + "loss": 1.0936, + "mean_token_accuracy": 0.685463547706604, + "num_tokens": 335705229.0, + "step": 565 + }, + { + "epoch": 2.6952380952380954, + "ewc_loss": 0.0002918243408203125, + "grad_norm": 0.6435744166374207, + "learning_rate": 1e-05, + "loss": 1.0993, + "mean_token_accuracy": 0.6851183772087097, + "num_tokens": 336296515.0, + "step": 566 + }, + { + "epoch": 2.7, + "ewc_loss": 0.0002918243408203125, + "grad_norm": 0.611495316028595, + "learning_rate": 1e-05, + "loss": 1.1016, + "mean_token_accuracy": 0.6851454377174377, + "num_tokens": 336898581.0, + "step": 567 + }, + { + "epoch": 2.704761904761905, + "ewc_loss": 0.0002956390380859375, + "grad_norm": 0.6619069576263428, + "learning_rate": 1e-05, + "loss": 1.1099, + "mean_token_accuracy": 0.6834651231765747, + "num_tokens": 337492720.0, + "step": 568 + }, + { + "epoch": 2.7095238095238097, + "ewc_loss": 0.0002956390380859375, + "grad_norm": 0.6501826047897339, + "learning_rate": 1e-05, + "loss": 1.0934, + "mean_token_accuracy": 0.6870158314704895, + "num_tokens": 338088080.0, + "step": 569 + }, + { + "epoch": 2.7142857142857144, + "ewc_loss": 0.0002956390380859375, + "grad_norm": 0.6129790544509888, + "learning_rate": 1e-05, + "loss": 1.0926, + "mean_token_accuracy": 0.6872150301933289, + "num_tokens": 338682863.0, + "step": 570 + }, + { + "epoch": 2.719047619047619, + "ewc_loss": 0.0002956390380859375, + "grad_norm": 0.6841142773628235, + "learning_rate": 1e-05, + "loss": 1.0989, + "mean_token_accuracy": 0.686607301235199, + "num_tokens": 339274595.0, + "step": 571 + }, + { + "epoch": 2.723809523809524, + "ewc_loss": 0.0002956390380859375, + "grad_norm": 0.6318419575691223, + "learning_rate": 1e-05, + "loss": 1.0984, + "mean_token_accuracy": 0.6854850649833679, + "num_tokens": 339857633.0, + "step": 572 + }, + { + "epoch": 2.7285714285714286, + "ewc_loss": 0.00029754638671875, + "grad_norm": 0.7148617506027222, + "learning_rate": 1e-05, + "loss": 1.0816, + "mean_token_accuracy": 0.6896705031394958, + "num_tokens": 340451043.0, + "step": 573 + }, + { + "epoch": 2.7333333333333334, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.6437733173370361, + "learning_rate": 1e-05, + "loss": 1.1057, + "mean_token_accuracy": 0.6841121912002563, + "num_tokens": 341042238.0, + "step": 574 + }, + { + "epoch": 2.738095238095238, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.6289849877357483, + "learning_rate": 1e-05, + "loss": 1.1016, + "mean_token_accuracy": 0.6848798990249634, + "num_tokens": 341644006.0, + "step": 575 + }, + { + "epoch": 2.742857142857143, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.6226376295089722, + "learning_rate": 1e-05, + "loss": 1.092, + "mean_token_accuracy": 0.6862528324127197, + "num_tokens": 342238235.0, + "step": 576 + }, + { + "epoch": 2.7476190476190476, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.5970023274421692, + "learning_rate": 1e-05, + "loss": 1.0862, + "mean_token_accuracy": 0.6886621713638306, + "num_tokens": 342831260.0, + "step": 577 + }, + { + "epoch": 2.7523809523809524, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.660430371761322, + "learning_rate": 1e-05, + "loss": 1.1018, + "mean_token_accuracy": 0.6849748492240906, + "num_tokens": 343427629.0, + "step": 578 + }, + { + "epoch": 2.757142857142857, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.667527973651886, + "learning_rate": 1e-05, + "loss": 1.1015, + "mean_token_accuracy": 0.6853987574577332, + "num_tokens": 344021401.0, + "step": 579 + }, + { + "epoch": 2.761904761904762, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.6155567169189453, + "learning_rate": 1e-05, + "loss": 1.0872, + "mean_token_accuracy": 0.6892693042755127, + "num_tokens": 344610108.0, + "step": 580 + }, + { + "epoch": 2.7666666666666666, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.7035388350486755, + "learning_rate": 1e-05, + "loss": 1.0982, + "mean_token_accuracy": 0.6849664449691772, + "num_tokens": 345217241.0, + "step": 581 + }, + { + "epoch": 2.7714285714285714, + "ewc_loss": 0.0002994537353515625, + "grad_norm": 0.7222366333007812, + "learning_rate": 1e-05, + "loss": 1.0914, + "mean_token_accuracy": 0.6867033243179321, + "num_tokens": 345804258.0, + "step": 582 + }, + { + "epoch": 2.776190476190476, + "ewc_loss": 0.000301361083984375, + "grad_norm": 0.6310369968414307, + "learning_rate": 1e-05, + "loss": 1.0946, + "mean_token_accuracy": 0.6864722967147827, + "num_tokens": 346399481.0, + "step": 583 + }, + { + "epoch": 2.780952380952381, + "ewc_loss": 0.0003032684326171875, + "grad_norm": 0.7673488259315491, + "learning_rate": 1e-05, + "loss": 1.082, + "mean_token_accuracy": 0.6891627907752991, + "num_tokens": 346997922.0, + "step": 584 + }, + { + "epoch": 2.7857142857142856, + "ewc_loss": 0.0003032684326171875, + "grad_norm": 0.6260553002357483, + "learning_rate": 1e-05, + "loss": 1.0958, + "mean_token_accuracy": 0.6864192485809326, + "num_tokens": 347597863.0, + "step": 585 + }, + { + "epoch": 2.7904761904761903, + "ewc_loss": 0.0003032684326171875, + "grad_norm": 0.6710972785949707, + "learning_rate": 1e-05, + "loss": 1.0895, + "mean_token_accuracy": 0.6866884827613831, + "num_tokens": 348201046.0, + "step": 586 + }, + { + "epoch": 2.795238095238095, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6588578820228577, + "learning_rate": 1e-05, + "loss": 1.0849, + "mean_token_accuracy": 0.6883187294006348, + "num_tokens": 348787326.0, + "step": 587 + }, + { + "epoch": 2.8, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6305686831474304, + "learning_rate": 1e-05, + "loss": 1.0949, + "mean_token_accuracy": 0.6861594319343567, + "num_tokens": 349380645.0, + "step": 588 + }, + { + "epoch": 2.8047619047619046, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6676114201545715, + "learning_rate": 1e-05, + "loss": 1.0915, + "mean_token_accuracy": 0.687538743019104, + "num_tokens": 349983092.0, + "step": 589 + }, + { + "epoch": 2.8095238095238093, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.646616518497467, + "learning_rate": 1e-05, + "loss": 1.0875, + "mean_token_accuracy": 0.6879235506057739, + "num_tokens": 350576836.0, + "step": 590 + }, + { + "epoch": 2.814285714285714, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.7164124250411987, + "learning_rate": 1e-05, + "loss": 1.0884, + "mean_token_accuracy": 0.6889692544937134, + "num_tokens": 351172725.0, + "step": 591 + }, + { + "epoch": 2.819047619047619, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6886141300201416, + "learning_rate": 1e-05, + "loss": 1.0825, + "mean_token_accuracy": 0.6895938515663147, + "num_tokens": 351777142.0, + "step": 592 + }, + { + "epoch": 2.8238095238095235, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.7644420266151428, + "learning_rate": 1e-05, + "loss": 1.0837, + "mean_token_accuracy": 0.6887251138687134, + "num_tokens": 352361834.0, + "step": 593 + }, + { + "epoch": 2.8285714285714287, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6970800161361694, + "learning_rate": 1e-05, + "loss": 1.0917, + "mean_token_accuracy": 0.6871269941329956, + "num_tokens": 352964892.0, + "step": 594 + }, + { + "epoch": 2.8333333333333335, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.7470777630805969, + "learning_rate": 1e-05, + "loss": 1.0916, + "mean_token_accuracy": 0.6862577199935913, + "num_tokens": 353563696.0, + "step": 595 + }, + { + "epoch": 2.8380952380952382, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6488667130470276, + "learning_rate": 1e-05, + "loss": 1.0922, + "mean_token_accuracy": 0.6870537996292114, + "num_tokens": 354162323.0, + "step": 596 + }, + { + "epoch": 2.842857142857143, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6846103668212891, + "learning_rate": 1e-05, + "loss": 1.1232, + "mean_token_accuracy": 0.6794463992118835, + "num_tokens": 354763224.0, + "step": 597 + }, + { + "epoch": 2.8476190476190477, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6310172080993652, + "learning_rate": 1e-05, + "loss": 1.086, + "mean_token_accuracy": 0.688154399394989, + "num_tokens": 355360011.0, + "step": 598 + }, + { + "epoch": 2.8523809523809525, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6696777939796448, + "learning_rate": 1e-05, + "loss": 1.0923, + "mean_token_accuracy": 0.687064528465271, + "num_tokens": 355948770.0, + "step": 599 + }, + { + "epoch": 2.857142857142857, + "ewc_loss": 0.0003070831298828125, + "grad_norm": 0.6052023768424988, + "learning_rate": 1e-05, + "loss": 1.1009, + "mean_token_accuracy": 0.684508204460144, + "num_tokens": 356555915.0, + "step": 600 + }, + { + "epoch": 2.861904761904762, + "ewc_loss": 0.000308990478515625, + "grad_norm": 0.6420809030532837, + "learning_rate": 1e-05, + "loss": 1.1023, + "mean_token_accuracy": 0.6843985915184021, + "num_tokens": 357168089.0, + "step": 601 + }, + { + "epoch": 2.8666666666666667, + "ewc_loss": 0.000308990478515625, + "grad_norm": 0.5903171896934509, + "learning_rate": 1e-05, + "loss": 1.085, + "mean_token_accuracy": 0.6882248520851135, + "num_tokens": 357762209.0, + "step": 602 + }, + { + "epoch": 2.8714285714285714, + "ewc_loss": 0.000308990478515625, + "grad_norm": 0.5908778309822083, + "learning_rate": 1e-05, + "loss": 1.0915, + "mean_token_accuracy": 0.6876108646392822, + "num_tokens": 358365632.0, + "step": 603 + }, + { + "epoch": 2.876190476190476, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.596641480922699, + "learning_rate": 1e-05, + "loss": 1.1057, + "mean_token_accuracy": 0.6840469837188721, + "num_tokens": 358969038.0, + "step": 604 + }, + { + "epoch": 2.880952380952381, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6038164496421814, + "learning_rate": 1e-05, + "loss": 1.0878, + "mean_token_accuracy": 0.6891322135925293, + "num_tokens": 359560638.0, + "step": 605 + }, + { + "epoch": 2.8857142857142857, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6134818196296692, + "learning_rate": 1e-05, + "loss": 1.099, + "mean_token_accuracy": 0.6851480007171631, + "num_tokens": 360159047.0, + "step": 606 + }, + { + "epoch": 2.8904761904761904, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6219021677970886, + "learning_rate": 1e-05, + "loss": 1.0962, + "mean_token_accuracy": 0.6873064637184143, + "num_tokens": 360752550.0, + "step": 607 + }, + { + "epoch": 2.895238095238095, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6381514072418213, + "learning_rate": 1e-05, + "loss": 1.0976, + "mean_token_accuracy": 0.6855471134185791, + "num_tokens": 361348966.0, + "step": 608 + }, + { + "epoch": 2.9, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6458147764205933, + "learning_rate": 1e-05, + "loss": 1.0893, + "mean_token_accuracy": 0.6883772015571594, + "num_tokens": 361933541.0, + "step": 609 + }, + { + "epoch": 2.9047619047619047, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.5930789709091187, + "learning_rate": 1e-05, + "loss": 1.0945, + "mean_token_accuracy": 0.6869880557060242, + "num_tokens": 362522689.0, + "step": 610 + }, + { + "epoch": 2.9095238095238094, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.7089120745658875, + "learning_rate": 1e-05, + "loss": 1.0749, + "mean_token_accuracy": 0.6913515329360962, + "num_tokens": 363107779.0, + "step": 611 + }, + { + "epoch": 2.914285714285714, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6399405002593994, + "learning_rate": 1e-05, + "loss": 1.0891, + "mean_token_accuracy": 0.6878145933151245, + "num_tokens": 363690809.0, + "step": 612 + }, + { + "epoch": 2.919047619047619, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6499505639076233, + "learning_rate": 1e-05, + "loss": 1.0899, + "mean_token_accuracy": 0.6871790885925293, + "num_tokens": 364279923.0, + "step": 613 + }, + { + "epoch": 2.923809523809524, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6635950803756714, + "learning_rate": 1e-05, + "loss": 1.0806, + "mean_token_accuracy": 0.6896902918815613, + "num_tokens": 364846929.0, + "step": 614 + }, + { + "epoch": 2.928571428571429, + "ewc_loss": 0.00031280517578125, + "grad_norm": 0.6600082516670227, + "learning_rate": 1e-05, + "loss": 1.1066, + "mean_token_accuracy": 0.684548020362854, + "num_tokens": 365427755.0, + "step": 615 + }, + { + "epoch": 2.9333333333333336, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6414427757263184, + "learning_rate": 1e-05, + "loss": 1.0884, + "mean_token_accuracy": 0.6878275871276855, + "num_tokens": 366022879.0, + "step": 616 + }, + { + "epoch": 2.9380952380952383, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6265722513198853, + "learning_rate": 1e-05, + "loss": 1.0911, + "mean_token_accuracy": 0.6866036653518677, + "num_tokens": 366608198.0, + "step": 617 + }, + { + "epoch": 2.942857142857143, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6315493583679199, + "learning_rate": 1e-05, + "loss": 1.0959, + "mean_token_accuracy": 0.685697615146637, + "num_tokens": 367187170.0, + "step": 618 + }, + { + "epoch": 2.947619047619048, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6812767386436462, + "learning_rate": 1e-05, + "loss": 1.089, + "mean_token_accuracy": 0.6873213052749634, + "num_tokens": 367778542.0, + "step": 619 + }, + { + "epoch": 2.9523809523809526, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6282839775085449, + "learning_rate": 1e-05, + "loss": 1.0955, + "mean_token_accuracy": 0.6853768229484558, + "num_tokens": 368374361.0, + "step": 620 + }, + { + "epoch": 2.9571428571428573, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6914244890213013, + "learning_rate": 1e-05, + "loss": 1.0963, + "mean_token_accuracy": 0.6863818764686584, + "num_tokens": 368975961.0, + "step": 621 + }, + { + "epoch": 2.961904761904762, + "ewc_loss": 0.0003147125244140625, + "grad_norm": 0.6497926712036133, + "learning_rate": 1e-05, + "loss": 1.0717, + "mean_token_accuracy": 0.6926910877227783, + "num_tokens": 369565801.0, + "step": 622 + }, + { + "epoch": 2.966666666666667, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6825300455093384, + "learning_rate": 1e-05, + "loss": 1.0962, + "mean_token_accuracy": 0.685806930065155, + "num_tokens": 370147963.0, + "step": 623 + }, + { + "epoch": 2.9714285714285715, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.7046704292297363, + "learning_rate": 1e-05, + "loss": 1.0937, + "mean_token_accuracy": 0.6864057183265686, + "num_tokens": 370730337.0, + "step": 624 + }, + { + "epoch": 2.9761904761904763, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6102251410484314, + "learning_rate": 1e-05, + "loss": 1.0868, + "mean_token_accuracy": 0.6879177689552307, + "num_tokens": 371313464.0, + "step": 625 + }, + { + "epoch": 2.980952380952381, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6395936608314514, + "learning_rate": 1e-05, + "loss": 1.0906, + "mean_token_accuracy": 0.6877844929695129, + "num_tokens": 371903211.0, + "step": 626 + }, + { + "epoch": 2.9857142857142858, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.671822190284729, + "learning_rate": 1e-05, + "loss": 1.0807, + "mean_token_accuracy": 0.6911332607269287, + "num_tokens": 372496314.0, + "step": 627 + }, + { + "epoch": 2.9904761904761905, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6819448471069336, + "learning_rate": 1e-05, + "loss": 1.0948, + "mean_token_accuracy": 0.6863044500350952, + "num_tokens": 373096610.0, + "step": 628 + }, + { + "epoch": 2.9952380952380953, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6858343482017517, + "learning_rate": 1e-05, + "loss": 1.0969, + "mean_token_accuracy": 0.6852229833602905, + "num_tokens": 373694165.0, + "step": 629 + }, + { + "epoch": 3.0, + "ewc_loss": 0.0003185272216796875, + "grad_norm": 0.6127511262893677, + "learning_rate": 1e-05, + "loss": 1.0855, + "mean_token_accuracy": 0.6899734735488892, + "num_tokens": 374283247.0, + "step": 630 + }, + { + "epoch": 3.0, + "ewc_loss": 0.0003185272216796875, + "step": 630, + "total_flos": 2.1853937174671524e+18, + "train_loss": 1.1745690016519457, + "train_runtime": 2017.134, + "train_samples_per_second": 159.906, + "train_steps_per_second": 0.312 + } + ], + "logging_steps": 1, + "max_steps": 630, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 315, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.1853937174671524e+18, + "train_batch_size": 128, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..384fbd0 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf59eeab83acacf653c93bdc0889d4c49e51283a6eca00df105f5fbb2b41758 +size 13393