commit 203ebe4a1aca52342a9cfb9aebeff6b030c76d09 Author: ModelHub XC Date: Fri Oct 2 23:51:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: renaudb1999/le-harnais-ft-medium-jepa-drop75 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b73d348 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +ft-medium-jepa-drop75.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..29c0843 --- /dev/null +++ b/README.md @@ -0,0 +1,32 @@ +--- +license: llama3.2 +base_model: meta-llama/Llama-3.2-1B-Instruct +library_name: transformers +tags: [le-harnais, ablation, retrain-only] +--- + +# le-harnais / ft-medium-jepa-drop75 + +> ⚠️ **retrain-only** — this is an ablation checkpoint, **not useful for inference**. It ships only to reproduce / continue the training study. For real use see the hero models: `le-harnais-ft-agentworld-{1b,3b,8b}`, `le-harnais-ft-counsel`. + +Spider NL→SQL JEPA ablation — shows JEPA does NOT help on loose view-alignment. + +- **Base model:** [`meta-llama/Llama-3.2-1B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) — **Built with Llama**; Llama Community License applies. +- **Class:** `ablation` +- **Training data:** spider (NL→SQL) +- **Headline:** JEPA ≤0 on NL→SQL (the negative result; exec-match ~0.287) + +## Reproduce + +```sh +cd refs/llm-jepa && .venv/bin/python ../../tools/run_jepa_sweep.py --seeds 82 --eval-cap 300 +``` + +Full recipe, datasets, and eval commands: see `docs/REPRODUCE.md` in the +[le-harnais distribution]. Provenance & license: `docs/PROVENANCE.md`. + +## Formats in this repo +- `*.safetensors` — bf16 inference weights (serve with `transformers` or le-harnais `lh-serve`/candle). +- `*.Q4_K_M.gguf` — portable 4-bit quant (run via `ollama` / `llama.cpp`; Mac-friendly). + +> Orchestration amplifies a capable generator; it does not create competence. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1bad6a0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,93 @@ +{{- 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 %} + {%- if strftime_now is defined %} + {%- set date_string = strftime_now("%d %b %Y") %} + {%- else %} + {%- set date_string = "26 Jul 2024" %} + {%- endif %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {{- "<|eot_id|>" }} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..bf0e53e --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 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, + "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, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.2", + "use_cache": false, + "vocab_size": 128267 +} diff --git a/ft-medium-jepa-drop75.Q4_K_M.gguf b/ft-medium-jepa-drop75.Q4_K_M.gguf new file mode 100644 index 0000000..27613c3 --- /dev/null +++ b/ft-medium-jepa-drop75.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59eff11512315d24d8e639c8cc7cc7d8c256a332718540459ded0f3aa5981ac1 +size 807712864 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b513e54 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.55.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..538faee --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30766e5ffee5b3dfd6871b93622c2492c68089c3e9f766ae9ea600315a9a6cc6 +size 2471690664 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..88d121d --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,96 @@ +{ + "additional_special_tokens": [ + { + "content": "<|predictor_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|predictor_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + { + "content": "<|perception|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } + ], + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e319b34 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f692c83c9abf03141aa73f056d2d200a33d01f2b482b70b98c5438a48736a6 +size 17212032 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5dc98bf --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2164 @@ +{ + "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 + }, + "128256": { + "content": "<|predictor_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128257": { + "content": "<|predictor_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128258": { + "content": "<|predictor_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128259": { + "content": "<|predictor_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128260": { + "content": "<|predictor_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128261": { + "content": "<|predictor_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128262": { + "content": "<|predictor_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128263": { + "content": "<|predictor_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128264": { + "content": "<|predictor_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128265": { + "content": "<|predictor_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128266": { + "content": "<|perception|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|predictor_1|>", + "<|predictor_2|>", + "<|predictor_3|>", + "<|predictor_4|>", + "<|predictor_5|>", + "<|predictor_6|>", + "<|predictor_7|>", + "<|predictor_8|>", + "<|predictor_9|>", + "<|predictor_10|>", + "<|perception|>" + ], + "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/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..fb9acf3 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1191 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.0, + "eval_steps": 500, + "global_step": 1648, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.024301336573511544, + "grad_norm": 20.125, + "learning_rate": 9.945388349514565e-06, + "loss": 4.4175, + "step": 10 + }, + { + "epoch": 0.04860267314702309, + "grad_norm": 15.0, + "learning_rate": 9.884708737864079e-06, + "loss": 2.33, + "step": 20 + }, + { + "epoch": 0.07290400972053462, + "grad_norm": 14.5, + "learning_rate": 9.824029126213593e-06, + "loss": 2.239, + "step": 30 + }, + { + "epoch": 0.09720534629404617, + "grad_norm": 14.625, + "learning_rate": 9.763349514563108e-06, + "loss": 2.1425, + "step": 40 + }, + { + "epoch": 0.12150668286755771, + "grad_norm": 16.5, + "learning_rate": 9.702669902912622e-06, + "loss": 2.0576, + "step": 50 + }, + { + "epoch": 0.14580801944106925, + "grad_norm": 16.5, + "learning_rate": 9.641990291262136e-06, + "loss": 1.9621, + "step": 60 + }, + { + "epoch": 0.1701093560145808, + "grad_norm": 22.625, + "learning_rate": 9.581310679611652e-06, + "loss": 1.8598, + "step": 70 + }, + { + "epoch": 0.19441069258809235, + "grad_norm": 26.375, + "learning_rate": 9.520631067961167e-06, + "loss": 1.8001, + "step": 80 + }, + { + "epoch": 0.2187120291616039, + "grad_norm": 22.375, + "learning_rate": 9.45995145631068e-06, + "loss": 1.671, + "step": 90 + }, + { + "epoch": 0.24301336573511542, + "grad_norm": 19.875, + "learning_rate": 9.399271844660195e-06, + "loss": 1.607, + "step": 100 + }, + { + "epoch": 0.267314702308627, + "grad_norm": 13.3125, + "learning_rate": 9.33859223300971e-06, + "loss": 1.4746, + "step": 110 + }, + { + "epoch": 0.2916160388821385, + "grad_norm": 14.4375, + "learning_rate": 9.277912621359224e-06, + "loss": 1.4323, + "step": 120 + }, + { + "epoch": 0.3159173754556501, + "grad_norm": 12.5625, + "learning_rate": 9.217233009708738e-06, + "loss": 1.3916, + "step": 130 + }, + { + "epoch": 0.3402187120291616, + "grad_norm": 13.6875, + "learning_rate": 9.156553398058252e-06, + "loss": 1.3317, + "step": 140 + }, + { + "epoch": 0.3645200486026732, + "grad_norm": 12.5625, + "learning_rate": 9.095873786407767e-06, + "loss": 1.3815, + "step": 150 + }, + { + "epoch": 0.3888213851761847, + "grad_norm": 12.5625, + "learning_rate": 9.035194174757283e-06, + "loss": 1.3461, + "step": 160 + }, + { + "epoch": 0.4131227217496962, + "grad_norm": 13.125, + "learning_rate": 8.974514563106797e-06, + "loss": 1.3367, + "step": 170 + }, + { + "epoch": 0.4374240583232078, + "grad_norm": 14.0625, + "learning_rate": 8.913834951456311e-06, + "loss": 1.3163, + "step": 180 + }, + { + "epoch": 0.4617253948967193, + "grad_norm": 14.25, + "learning_rate": 8.853155339805826e-06, + "loss": 1.2797, + "step": 190 + }, + { + "epoch": 0.48602673147023084, + "grad_norm": 11.9375, + "learning_rate": 8.79247572815534e-06, + "loss": 1.2701, + "step": 200 + }, + { + "epoch": 0.5103280680437424, + "grad_norm": 14.0, + "learning_rate": 8.731796116504854e-06, + "loss": 1.2656, + "step": 210 + }, + { + "epoch": 0.534629404617254, + "grad_norm": 12.25, + "learning_rate": 8.67111650485437e-06, + "loss": 1.2368, + "step": 220 + }, + { + "epoch": 0.5589307411907655, + "grad_norm": 12.25, + "learning_rate": 8.610436893203885e-06, + "loss": 1.2554, + "step": 230 + }, + { + "epoch": 0.583232077764277, + "grad_norm": 13.4375, + "learning_rate": 8.549757281553399e-06, + "loss": 1.2104, + "step": 240 + }, + { + "epoch": 0.6075334143377886, + "grad_norm": 11.0, + "learning_rate": 8.489077669902913e-06, + "loss": 1.2462, + "step": 250 + }, + { + "epoch": 0.6318347509113001, + "grad_norm": 12.625, + "learning_rate": 8.428398058252428e-06, + "loss": 1.2527, + "step": 260 + }, + { + "epoch": 0.6561360874848117, + "grad_norm": 12.25, + "learning_rate": 8.367718446601942e-06, + "loss": 1.1658, + "step": 270 + }, + { + "epoch": 0.6804374240583232, + "grad_norm": 11.0, + "learning_rate": 8.307038834951458e-06, + "loss": 1.1742, + "step": 280 + }, + { + "epoch": 0.7047387606318347, + "grad_norm": 12.3125, + "learning_rate": 8.246359223300972e-06, + "loss": 1.1899, + "step": 290 + }, + { + "epoch": 0.7290400972053463, + "grad_norm": 12.9375, + "learning_rate": 8.185679611650487e-06, + "loss": 1.2163, + "step": 300 + }, + { + "epoch": 0.7533414337788579, + "grad_norm": 13.125, + "learning_rate": 8.125000000000001e-06, + "loss": 1.1369, + "step": 310 + }, + { + "epoch": 0.7776427703523694, + "grad_norm": 11.25, + "learning_rate": 8.064320388349515e-06, + "loss": 1.2361, + "step": 320 + }, + { + "epoch": 0.8019441069258809, + "grad_norm": 12.5, + "learning_rate": 8.00364077669903e-06, + "loss": 1.1655, + "step": 330 + }, + { + "epoch": 0.8262454434993924, + "grad_norm": 11.625, + "learning_rate": 7.942961165048544e-06, + "loss": 1.1279, + "step": 340 + }, + { + "epoch": 0.850546780072904, + "grad_norm": 12.6875, + "learning_rate": 7.882281553398058e-06, + "loss": 1.2015, + "step": 350 + }, + { + "epoch": 0.8748481166464156, + "grad_norm": 11.5, + "learning_rate": 7.821601941747573e-06, + "loss": 1.1246, + "step": 360 + }, + { + "epoch": 0.8991494532199271, + "grad_norm": 10.625, + "learning_rate": 7.760922330097089e-06, + "loss": 1.1186, + "step": 370 + }, + { + "epoch": 0.9234507897934386, + "grad_norm": 14.0625, + "learning_rate": 7.700242718446603e-06, + "loss": 1.1466, + "step": 380 + }, + { + "epoch": 0.9477521263669502, + "grad_norm": 13.4375, + "learning_rate": 7.639563106796117e-06, + "loss": 1.1755, + "step": 390 + }, + { + "epoch": 0.9720534629404617, + "grad_norm": 13.6875, + "learning_rate": 7.5788834951456316e-06, + "loss": 1.078, + "step": 400 + }, + { + "epoch": 0.9963547995139733, + "grad_norm": 13.3125, + "learning_rate": 7.518203883495147e-06, + "loss": 1.1136, + "step": 410 + }, + { + "epoch": 1.0194410692588092, + "grad_norm": 12.3125, + "learning_rate": 7.45752427184466e-06, + "loss": 1.0297, + "step": 420 + }, + { + "epoch": 1.0437424058323208, + "grad_norm": 12.75, + "learning_rate": 7.396844660194175e-06, + "loss": 1.0281, + "step": 430 + }, + { + "epoch": 1.0680437424058322, + "grad_norm": 15.0625, + "learning_rate": 7.33616504854369e-06, + "loss": 1.0903, + "step": 440 + }, + { + "epoch": 1.0923450789793439, + "grad_norm": 13.125, + "learning_rate": 7.275485436893205e-06, + "loss": 1.0475, + "step": 450 + }, + { + "epoch": 1.1166464155528555, + "grad_norm": 12.875, + "learning_rate": 7.214805825242719e-06, + "loss": 1.0828, + "step": 460 + }, + { + "epoch": 1.140947752126367, + "grad_norm": 12.8125, + "learning_rate": 7.154126213592234e-06, + "loss": 1.0635, + "step": 470 + }, + { + "epoch": 1.1652490886998785, + "grad_norm": 13.0, + "learning_rate": 7.093446601941748e-06, + "loss": 1.0717, + "step": 480 + }, + { + "epoch": 1.18955042527339, + "grad_norm": 13.4375, + "learning_rate": 7.032766990291263e-06, + "loss": 1.0588, + "step": 490 + }, + { + "epoch": 1.2138517618469016, + "grad_norm": 13.5625, + "learning_rate": 6.972087378640777e-06, + "loss": 1.0225, + "step": 500 + }, + { + "epoch": 1.2381530984204132, + "grad_norm": 14.625, + "learning_rate": 6.9114077669902925e-06, + "loss": 0.9822, + "step": 510 + }, + { + "epoch": 1.2624544349939246, + "grad_norm": 14.1875, + "learning_rate": 6.850728155339806e-06, + "loss": 1.0506, + "step": 520 + }, + { + "epoch": 1.2867557715674363, + "grad_norm": 15.5, + "learning_rate": 6.79004854368932e-06, + "loss": 1.0428, + "step": 530 + }, + { + "epoch": 1.3110571081409477, + "grad_norm": 13.6875, + "learning_rate": 6.7293689320388355e-06, + "loss": 1.0507, + "step": 540 + }, + { + "epoch": 1.3353584447144593, + "grad_norm": 12.8125, + "learning_rate": 6.66868932038835e-06, + "loss": 1.0246, + "step": 550 + }, + { + "epoch": 1.359659781287971, + "grad_norm": 14.8125, + "learning_rate": 6.608009708737865e-06, + "loss": 1.0581, + "step": 560 + }, + { + "epoch": 1.3839611178614823, + "grad_norm": 13.625, + "learning_rate": 6.5473300970873784e-06, + "loss": 1.0488, + "step": 570 + }, + { + "epoch": 1.408262454434994, + "grad_norm": 11.9375, + "learning_rate": 6.486650485436894e-06, + "loss": 1.0205, + "step": 580 + }, + { + "epoch": 1.4325637910085054, + "grad_norm": 14.0625, + "learning_rate": 6.425970873786408e-06, + "loss": 1.0181, + "step": 590 + }, + { + "epoch": 1.456865127582017, + "grad_norm": 13.25, + "learning_rate": 6.365291262135923e-06, + "loss": 1.0212, + "step": 600 + }, + { + "epoch": 1.4811664641555287, + "grad_norm": 13.4375, + "learning_rate": 6.304611650485437e-06, + "loss": 1.0581, + "step": 610 + }, + { + "epoch": 1.50546780072904, + "grad_norm": 12.625, + "learning_rate": 6.243932038834953e-06, + "loss": 1.0311, + "step": 620 + }, + { + "epoch": 1.5297691373025515, + "grad_norm": 12.0, + "learning_rate": 6.183252427184466e-06, + "loss": 0.9874, + "step": 630 + }, + { + "epoch": 1.5540704738760631, + "grad_norm": 13.125, + "learning_rate": 6.122572815533981e-06, + "loss": 1.0407, + "step": 640 + }, + { + "epoch": 1.5783718104495748, + "grad_norm": 12.875, + "learning_rate": 6.0618932038834955e-06, + "loss": 1.0107, + "step": 650 + }, + { + "epoch": 1.6026731470230864, + "grad_norm": 12.0625, + "learning_rate": 6.001213592233011e-06, + "loss": 1.0165, + "step": 660 + }, + { + "epoch": 1.6269744835965978, + "grad_norm": 15.375, + "learning_rate": 5.940533980582525e-06, + "loss": 1.0136, + "step": 670 + }, + { + "epoch": 1.6512758201701092, + "grad_norm": 13.6875, + "learning_rate": 5.879854368932039e-06, + "loss": 1.0103, + "step": 680 + }, + { + "epoch": 1.6755771567436208, + "grad_norm": 13.5625, + "learning_rate": 5.819174757281554e-06, + "loss": 0.9989, + "step": 690 + }, + { + "epoch": 1.6998784933171325, + "grad_norm": 14.1875, + "learning_rate": 5.758495145631069e-06, + "loss": 1.0195, + "step": 700 + }, + { + "epoch": 1.7241798298906441, + "grad_norm": 13.375, + "learning_rate": 5.697815533980583e-06, + "loss": 0.9705, + "step": 710 + }, + { + "epoch": 1.7484811664641555, + "grad_norm": 13.0625, + "learning_rate": 5.637135922330098e-06, + "loss": 1.0208, + "step": 720 + }, + { + "epoch": 1.772782503037667, + "grad_norm": 12.5625, + "learning_rate": 5.576456310679612e-06, + "loss": 0.9949, + "step": 730 + }, + { + "epoch": 1.7970838396111786, + "grad_norm": 14.0625, + "learning_rate": 5.515776699029126e-06, + "loss": 1.0189, + "step": 740 + }, + { + "epoch": 1.8213851761846902, + "grad_norm": 13.4375, + "learning_rate": 5.455097087378641e-06, + "loss": 1.0553, + "step": 750 + }, + { + "epoch": 1.8456865127582018, + "grad_norm": 15.375, + "learning_rate": 5.394417475728156e-06, + "loss": 1.0128, + "step": 760 + }, + { + "epoch": 1.8699878493317132, + "grad_norm": 13.125, + "learning_rate": 5.333737864077671e-06, + "loss": 1.0254, + "step": 770 + }, + { + "epoch": 1.8942891859052247, + "grad_norm": 13.125, + "learning_rate": 5.273058252427184e-06, + "loss": 1.0202, + "step": 780 + }, + { + "epoch": 1.9185905224787363, + "grad_norm": 13.9375, + "learning_rate": 5.2123786407766994e-06, + "loss": 0.9873, + "step": 790 + }, + { + "epoch": 1.942891859052248, + "grad_norm": 13.5, + "learning_rate": 5.151699029126214e-06, + "loss": 1.0542, + "step": 800 + }, + { + "epoch": 1.9671931956257596, + "grad_norm": 13.1875, + "learning_rate": 5.091019417475729e-06, + "loss": 1.0108, + "step": 810 + }, + { + "epoch": 1.991494532199271, + "grad_norm": 12.4375, + "learning_rate": 5.030339805825243e-06, + "loss": 0.9592, + "step": 820 + }, + { + "epoch": 2.0145808019441067, + "grad_norm": 13.375, + "learning_rate": 4.9696601941747576e-06, + "loss": 0.9372, + "step": 830 + }, + { + "epoch": 2.0388821385176183, + "grad_norm": 14.5625, + "learning_rate": 4.908980582524272e-06, + "loss": 0.941, + "step": 840 + }, + { + "epoch": 2.06318347509113, + "grad_norm": 14.25, + "learning_rate": 4.848300970873786e-06, + "loss": 0.9501, + "step": 850 + }, + { + "epoch": 2.0874848116646416, + "grad_norm": 14.5625, + "learning_rate": 4.787621359223301e-06, + "loss": 0.9443, + "step": 860 + }, + { + "epoch": 2.1117861482381532, + "grad_norm": 15.125, + "learning_rate": 4.726941747572816e-06, + "loss": 0.987, + "step": 870 + }, + { + "epoch": 2.1360874848116644, + "grad_norm": 13.8125, + "learning_rate": 4.66626213592233e-06, + "loss": 0.9643, + "step": 880 + }, + { + "epoch": 2.160388821385176, + "grad_norm": 12.3125, + "learning_rate": 4.605582524271845e-06, + "loss": 0.945, + "step": 890 + }, + { + "epoch": 2.1846901579586877, + "grad_norm": 15.5, + "learning_rate": 4.5449029126213595e-06, + "loss": 0.9956, + "step": 900 + }, + { + "epoch": 2.2089914945321993, + "grad_norm": 13.3125, + "learning_rate": 4.484223300970874e-06, + "loss": 0.9668, + "step": 910 + }, + { + "epoch": 2.233292831105711, + "grad_norm": 13.8125, + "learning_rate": 4.423543689320389e-06, + "loss": 0.9339, + "step": 920 + }, + { + "epoch": 2.257594167679222, + "grad_norm": 13.3125, + "learning_rate": 4.362864077669903e-06, + "loss": 0.9511, + "step": 930 + }, + { + "epoch": 2.281895504252734, + "grad_norm": 12.6875, + "learning_rate": 4.302184466019418e-06, + "loss": 0.9292, + "step": 940 + }, + { + "epoch": 2.3061968408262454, + "grad_norm": 16.25, + "learning_rate": 4.241504854368933e-06, + "loss": 0.9498, + "step": 950 + }, + { + "epoch": 2.330498177399757, + "grad_norm": 16.375, + "learning_rate": 4.180825242718447e-06, + "loss": 0.9948, + "step": 960 + }, + { + "epoch": 2.3547995139732687, + "grad_norm": 14.75, + "learning_rate": 4.1201456310679615e-06, + "loss": 0.9611, + "step": 970 + }, + { + "epoch": 2.37910085054678, + "grad_norm": 14.6875, + "learning_rate": 4.059466019417476e-06, + "loss": 0.9515, + "step": 980 + }, + { + "epoch": 2.4034021871202915, + "grad_norm": 12.8125, + "learning_rate": 3.998786407766991e-06, + "loss": 0.9555, + "step": 990 + }, + { + "epoch": 2.427703523693803, + "grad_norm": 14.0625, + "learning_rate": 3.938106796116505e-06, + "loss": 0.9762, + "step": 1000 + }, + { + "epoch": 2.452004860267315, + "grad_norm": 12.6875, + "learning_rate": 3.87742718446602e-06, + "loss": 0.9621, + "step": 1010 + }, + { + "epoch": 2.4763061968408264, + "grad_norm": 12.9375, + "learning_rate": 3.816747572815535e-06, + "loss": 0.8967, + "step": 1020 + }, + { + "epoch": 2.500607533414338, + "grad_norm": 14.6875, + "learning_rate": 3.756067961165049e-06, + "loss": 0.9938, + "step": 1030 + }, + { + "epoch": 2.5249088699878492, + "grad_norm": 15.1875, + "learning_rate": 3.695388349514563e-06, + "loss": 0.9379, + "step": 1040 + }, + { + "epoch": 2.549210206561361, + "grad_norm": 13.625, + "learning_rate": 3.6347087378640777e-06, + "loss": 0.9745, + "step": 1050 + }, + { + "epoch": 2.5735115431348725, + "grad_norm": 16.125, + "learning_rate": 3.5740291262135925e-06, + "loss": 0.9806, + "step": 1060 + }, + { + "epoch": 2.5978128797083837, + "grad_norm": 18.0, + "learning_rate": 3.513349514563107e-06, + "loss": 0.9586, + "step": 1070 + }, + { + "epoch": 2.6221142162818953, + "grad_norm": 15.125, + "learning_rate": 3.4526699029126215e-06, + "loss": 0.9413, + "step": 1080 + }, + { + "epoch": 2.646415552855407, + "grad_norm": 14.0, + "learning_rate": 3.3919902912621363e-06, + "loss": 0.9522, + "step": 1090 + }, + { + "epoch": 2.6707168894289186, + "grad_norm": 15.125, + "learning_rate": 3.3313106796116506e-06, + "loss": 0.9426, + "step": 1100 + }, + { + "epoch": 2.6950182260024302, + "grad_norm": 14.5, + "learning_rate": 3.2706310679611654e-06, + "loss": 0.9692, + "step": 1110 + }, + { + "epoch": 2.719319562575942, + "grad_norm": 13.4375, + "learning_rate": 3.2099514563106797e-06, + "loss": 0.9897, + "step": 1120 + }, + { + "epoch": 2.743620899149453, + "grad_norm": 16.0, + "learning_rate": 3.1492718446601944e-06, + "loss": 0.9801, + "step": 1130 + }, + { + "epoch": 2.7679222357229647, + "grad_norm": 14.8125, + "learning_rate": 3.088592233009709e-06, + "loss": 0.9611, + "step": 1140 + }, + { + "epoch": 2.7922235722964763, + "grad_norm": 16.625, + "learning_rate": 3.0279126213592235e-06, + "loss": 0.9653, + "step": 1150 + }, + { + "epoch": 2.816524908869988, + "grad_norm": 14.1875, + "learning_rate": 2.9672330097087382e-06, + "loss": 0.9504, + "step": 1160 + }, + { + "epoch": 2.840826245443499, + "grad_norm": 14.5625, + "learning_rate": 2.9065533980582526e-06, + "loss": 0.9645, + "step": 1170 + }, + { + "epoch": 2.865127582017011, + "grad_norm": 12.3125, + "learning_rate": 2.8458737864077673e-06, + "loss": 0.9574, + "step": 1180 + }, + { + "epoch": 2.8894289185905224, + "grad_norm": 12.875, + "learning_rate": 2.785194174757282e-06, + "loss": 0.9169, + "step": 1190 + }, + { + "epoch": 2.913730255164034, + "grad_norm": 15.125, + "learning_rate": 2.7245145631067964e-06, + "loss": 0.9618, + "step": 1200 + }, + { + "epoch": 2.9380315917375457, + "grad_norm": 13.625, + "learning_rate": 2.663834951456311e-06, + "loss": 0.9003, + "step": 1210 + }, + { + "epoch": 2.9623329283110573, + "grad_norm": 16.5, + "learning_rate": 2.603155339805826e-06, + "loss": 0.9579, + "step": 1220 + }, + { + "epoch": 2.9866342648845685, + "grad_norm": 12.25, + "learning_rate": 2.54247572815534e-06, + "loss": 0.9406, + "step": 1230 + }, + { + "epoch": 3.0097205346294045, + "grad_norm": 15.0, + "learning_rate": 2.4817961165048545e-06, + "loss": 0.9015, + "step": 1240 + }, + { + "epoch": 3.034021871202916, + "grad_norm": 13.8125, + "learning_rate": 2.4211165048543692e-06, + "loss": 0.9243, + "step": 1250 + }, + { + "epoch": 3.0583232077764277, + "grad_norm": 15.25, + "learning_rate": 2.3604368932038836e-06, + "loss": 0.9119, + "step": 1260 + }, + { + "epoch": 3.0826245443499394, + "grad_norm": 14.25, + "learning_rate": 2.2997572815533983e-06, + "loss": 0.9555, + "step": 1270 + }, + { + "epoch": 3.106925880923451, + "grad_norm": 13.5625, + "learning_rate": 2.239077669902913e-06, + "loss": 0.9045, + "step": 1280 + }, + { + "epoch": 3.131227217496962, + "grad_norm": 13.75, + "learning_rate": 2.1783980582524274e-06, + "loss": 0.9157, + "step": 1290 + }, + { + "epoch": 3.155528554070474, + "grad_norm": 13.75, + "learning_rate": 2.1177184466019417e-06, + "loss": 0.9171, + "step": 1300 + }, + { + "epoch": 3.1798298906439855, + "grad_norm": 13.6875, + "learning_rate": 2.0570388349514564e-06, + "loss": 0.928, + "step": 1310 + }, + { + "epoch": 3.204131227217497, + "grad_norm": 16.125, + "learning_rate": 1.996359223300971e-06, + "loss": 0.9414, + "step": 1320 + }, + { + "epoch": 3.2284325637910083, + "grad_norm": 13.9375, + "learning_rate": 1.9356796116504855e-06, + "loss": 0.9325, + "step": 1330 + }, + { + "epoch": 3.25273390036452, + "grad_norm": 15.0, + "learning_rate": 1.8750000000000003e-06, + "loss": 0.9446, + "step": 1340 + }, + { + "epoch": 3.2770352369380316, + "grad_norm": 13.75, + "learning_rate": 1.8143203883495148e-06, + "loss": 0.9222, + "step": 1350 + }, + { + "epoch": 3.301336573511543, + "grad_norm": 12.6875, + "learning_rate": 1.7536407766990293e-06, + "loss": 0.9383, + "step": 1360 + }, + { + "epoch": 3.325637910085055, + "grad_norm": 13.375, + "learning_rate": 1.6929611650485439e-06, + "loss": 0.9589, + "step": 1370 + }, + { + "epoch": 3.3499392466585665, + "grad_norm": 14.6875, + "learning_rate": 1.6322815533980584e-06, + "loss": 0.888, + "step": 1380 + }, + { + "epoch": 3.3742405832320777, + "grad_norm": 13.5, + "learning_rate": 1.5716019417475731e-06, + "loss": 0.9585, + "step": 1390 + }, + { + "epoch": 3.3985419198055893, + "grad_norm": 15.0, + "learning_rate": 1.5109223300970875e-06, + "loss": 0.9338, + "step": 1400 + }, + { + "epoch": 3.422843256379101, + "grad_norm": 14.125, + "learning_rate": 1.450242718446602e-06, + "loss": 0.9273, + "step": 1410 + }, + { + "epoch": 3.4471445929526126, + "grad_norm": 15.625, + "learning_rate": 1.3895631067961165e-06, + "loss": 0.9426, + "step": 1420 + }, + { + "epoch": 3.4714459295261237, + "grad_norm": 13.9375, + "learning_rate": 1.328883495145631e-06, + "loss": 0.9026, + "step": 1430 + }, + { + "epoch": 3.4957472660996354, + "grad_norm": 16.125, + "learning_rate": 1.2682038834951458e-06, + "loss": 0.9404, + "step": 1440 + }, + { + "epoch": 3.520048602673147, + "grad_norm": 14.125, + "learning_rate": 1.2075242718446603e-06, + "loss": 0.9534, + "step": 1450 + }, + { + "epoch": 3.5443499392466586, + "grad_norm": 16.625, + "learning_rate": 1.1468446601941749e-06, + "loss": 0.96, + "step": 1460 + }, + { + "epoch": 3.5686512758201703, + "grad_norm": 16.125, + "learning_rate": 1.0861650485436894e-06, + "loss": 0.9319, + "step": 1470 + }, + { + "epoch": 3.592952612393682, + "grad_norm": 15.125, + "learning_rate": 1.025485436893204e-06, + "loss": 0.9883, + "step": 1480 + }, + { + "epoch": 3.617253948967193, + "grad_norm": 13.0625, + "learning_rate": 9.648058252427185e-07, + "loss": 0.9267, + "step": 1490 + }, + { + "epoch": 3.6415552855407047, + "grad_norm": 13.4375, + "learning_rate": 9.041262135922331e-07, + "loss": 0.9326, + "step": 1500 + }, + { + "epoch": 3.6658566221142164, + "grad_norm": 13.3125, + "learning_rate": 8.434466019417476e-07, + "loss": 0.8841, + "step": 1510 + }, + { + "epoch": 3.6901579586877276, + "grad_norm": 14.3125, + "learning_rate": 7.827669902912623e-07, + "loss": 0.9653, + "step": 1520 + }, + { + "epoch": 3.714459295261239, + "grad_norm": 14.4375, + "learning_rate": 7.220873786407767e-07, + "loss": 0.9535, + "step": 1530 + }, + { + "epoch": 3.738760631834751, + "grad_norm": 13.625, + "learning_rate": 6.614077669902914e-07, + "loss": 0.9511, + "step": 1540 + }, + { + "epoch": 3.7630619684082625, + "grad_norm": 14.875, + "learning_rate": 6.007281553398059e-07, + "loss": 0.9389, + "step": 1550 + }, + { + "epoch": 3.787363304981774, + "grad_norm": 14.3125, + "learning_rate": 5.400485436893204e-07, + "loss": 0.9104, + "step": 1560 + }, + { + "epoch": 3.8116646415552857, + "grad_norm": 15.25, + "learning_rate": 4.79368932038835e-07, + "loss": 0.9152, + "step": 1570 + }, + { + "epoch": 3.8359659781287974, + "grad_norm": 14.125, + "learning_rate": 4.186893203883496e-07, + "loss": 0.9231, + "step": 1580 + }, + { + "epoch": 3.8602673147023085, + "grad_norm": 15.375, + "learning_rate": 3.5800970873786407e-07, + "loss": 0.9483, + "step": 1590 + }, + { + "epoch": 3.88456865127582, + "grad_norm": 14.9375, + "learning_rate": 2.9733009708737866e-07, + "loss": 0.9744, + "step": 1600 + }, + { + "epoch": 3.908869987849332, + "grad_norm": 13.375, + "learning_rate": 2.3665048543689322e-07, + "loss": 0.9, + "step": 1610 + }, + { + "epoch": 3.933171324422843, + "grad_norm": 13.125, + "learning_rate": 1.7597087378640778e-07, + "loss": 0.9097, + "step": 1620 + }, + { + "epoch": 3.9574726609963546, + "grad_norm": 12.5625, + "learning_rate": 1.1529126213592234e-07, + "loss": 0.9358, + "step": 1630 + }, + { + "epoch": 3.9817739975698663, + "grad_norm": 15.25, + "learning_rate": 5.46116504854369e-08, + "loss": 0.9268, + "step": 1640 + }, + { + "epoch": 4.0, + "step": 1648, + "total_flos": 7.87315998893015e+16, + "train_loss": 1.0966709982422949, + "train_runtime": 2934.2964, + "train_samples_per_second": 8.979, + "train_steps_per_second": 0.562 + } + ], + "logging_steps": 10, + "max_steps": 1648, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 411, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 7.87315998893015e+16, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +}