commit fd3020ef96233c597adbbc2c08830539f41bf26f Author: ModelHub XC Date: Sun Aug 23 00:19:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: laion/exp-psu-stackoverflow-1K_glm_4_7_traces Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1ac4ac --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..a29a3f7 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen3-8B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: exp-psu-stackoverflow-1K_glm_4_7_traces + results: [] +--- + + + +# exp-psu-stackoverflow-1K_glm_4_7_traces + +This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/exp-psu-stackoverflow-1K_glm_4.7_traces dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 4e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 16 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 7.0 + +### Training results + + + +### Framework versions + +- Transformers 4.57.6 +- Pytorch 2.9.0+cu128 +- Datasets 4.4.1 +- Tokenizers 0.22.2 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..9b563d8 --- /dev/null +++ b/all_results.json @@ -0,0 +1,16 @@ +{ + "achieved_tflops_per_gpu": 4.246655504814489, + "achieved_tflops_per_gpu_theoretical": 711.4599581928652, + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.259745717048645, + "mfu_percent": 0.4293888275848826, + "mfu_percent_theoretical": 71.93730618734733, + "total_flos": 7.12082116746281e+16, + "train_loss": 0.38846772432732746, + "train_runtime": 2096.0086, + "train_samples_per_second": 3.336, + "train_steps_per_second": 0.21, + "valid_targets_mean": 3009.9, + "valid_targets_min": 873 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..59b4193 --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9adbb28 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.57.6" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..0628bc4 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2e8dd622356340989219c1c02d333d61b164b8157779a84fbd4337391e71cc +size 4902257696 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..8290210 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c059a0c4ec395f8f1568fb6d6a08ef787f1972d91a53820414d731d14262d71 +size 4915960368 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..fbb6f02 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:980c9bfbdbb8808c6338ade0e4cbd379e17c5cccb99a156d630a3d42b9bbc9a7 +size 4983068496 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..bd884a9 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deea426591e939fe269c5aa8915c1479093f16f447f0f3547b2b8eb0590892b5 +size 1580230264 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ba886c0 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,407 @@ +{ + "metadata": { + "total_parameters": 308224, + "total_size": 16381470720 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/run_summary.json b/run_summary.json new file mode 100644 index 0000000..54ada94 --- /dev/null +++ b/run_summary.json @@ -0,0 +1,12 @@ +{ + "agent_name": "exp-psu-stackoverflow-1K_glm_4.7_traces", + "training_start": null, + "training_end": null, + "created_by": "DCAgent", + "base_model_name": "Qwen/Qwen3-8B", + "dataset_name": "DCAgent/exp-psu-stackoverflow-1K_glm_4.7_traces", + "training_type": "SFT", + "training_parameters": "https://huggingface.co/laion/exp-psu-stackoverflow-1K_glm_4_7_traces/blob/main/config.json", + "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-psu-stackoverflow-1K_glm_4-7_traces_Qwen3-8B", + "traces_location_s3": null +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e9dc937 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 32768, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..9b563d8 --- /dev/null +++ b/train_results.json @@ -0,0 +1,16 @@ +{ + "achieved_tflops_per_gpu": 4.246655504814489, + "achieved_tflops_per_gpu_theoretical": 711.4599581928652, + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.259745717048645, + "mfu_percent": 0.4293888275848826, + "mfu_percent_theoretical": 71.93730618734733, + "total_flos": 7.12082116746281e+16, + "train_loss": 0.38846772432732746, + "train_runtime": 2096.0086, + "train_samples_per_second": 3.336, + "train_steps_per_second": 0.21, + "valid_targets_mean": 3009.9, + "valid_targets_min": 873 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..f76a578 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,89 @@ +{"current_steps": 5, "total_steps": 441, "loss": 0.8889, "lr": 3.555555555555556e-06, "epoch": 0.08, "percentage": 1.13, "elapsed_time": "0:00:32", "remaining_time": "0:47:25"} +{"current_steps": 10, "total_steps": 441, "loss": 0.8268, "lr": 8.000000000000001e-06, "epoch": 0.16, "percentage": 2.27, "elapsed_time": "0:00:59", "remaining_time": "0:42:43"} +{"current_steps": 15, "total_steps": 441, "loss": 0.7614, "lr": 1.2444444444444446e-05, "epoch": 0.24, "percentage": 3.4, "elapsed_time": "0:01:24", "remaining_time": "0:40:01"} +{"current_steps": 20, "total_steps": 441, "loss": 0.6515, "lr": 1.688888888888889e-05, "epoch": 0.32, "percentage": 4.54, "elapsed_time": "0:01:50", "remaining_time": "0:38:36"} +{"current_steps": 25, "total_steps": 441, "loss": 0.5973, "lr": 2.1333333333333335e-05, "epoch": 0.4, "percentage": 5.67, "elapsed_time": "0:02:24", "remaining_time": "0:40:01"} +{"current_steps": 30, "total_steps": 441, "loss": 0.6453, "lr": 2.577777777777778e-05, "epoch": 0.48, "percentage": 6.8, "elapsed_time": "0:02:47", "remaining_time": "0:38:17"} +{"current_steps": 35, "total_steps": 441, "loss": 0.5684, "lr": 3.0222222222222225e-05, "epoch": 0.56, "percentage": 7.94, "elapsed_time": "0:03:09", "remaining_time": "0:36:41"} +{"current_steps": 40, "total_steps": 441, "loss": 0.5656, "lr": 3.466666666666667e-05, "epoch": 0.64, "percentage": 9.07, "elapsed_time": "0:03:38", "remaining_time": "0:36:26"} +{"current_steps": 45, "total_steps": 441, "loss": 0.5234, "lr": 3.9111111111111115e-05, "epoch": 0.72, "percentage": 10.2, "elapsed_time": "0:04:01", "remaining_time": "0:35:24"} +{"current_steps": 50, "total_steps": 441, "loss": 0.53, "lr": 3.9989930847663706e-05, "epoch": 0.8, "percentage": 11.34, "elapsed_time": "0:04:27", "remaining_time": "0:34:48"} +{"current_steps": 55, "total_steps": 441, "loss": 0.5412, "lr": 3.994904229220507e-05, "epoch": 0.88, "percentage": 12.47, "elapsed_time": "0:04:48", "remaining_time": "0:33:47"} +{"current_steps": 60, "total_steps": 441, "loss": 0.4896, "lr": 3.9876769289225084e-05, "epoch": 0.96, "percentage": 13.61, "elapsed_time": "0:05:11", "remaining_time": "0:32:57"} +{"current_steps": 65, "total_steps": 441, "loss": 0.5374, "lr": 3.977322554083716e-05, "epoch": 1.032, "percentage": 14.74, "elapsed_time": "0:05:41", "remaining_time": "0:32:54"} +{"current_steps": 70, "total_steps": 441, "loss": 0.488, "lr": 3.963857394525413e-05, "epoch": 1.112, "percentage": 15.87, "elapsed_time": "0:06:02", "remaining_time": "0:32:03"} +{"current_steps": 75, "total_steps": 441, "loss": 0.4376, "lr": 3.947302634051182e-05, "epoch": 1.192, "percentage": 17.01, "elapsed_time": "0:06:26", "remaining_time": "0:31:25"} +{"current_steps": 80, "total_steps": 441, "loss": 0.4908, "lr": 3.9276843171198844e-05, "epoch": 1.272, "percentage": 18.14, "elapsed_time": "0:06:44", "remaining_time": "0:30:26"} +{"current_steps": 85, "total_steps": 441, "loss": 0.4667, "lr": 3.9050333078717216e-05, "epoch": 1.3519999999999999, "percentage": 19.27, "elapsed_time": "0:07:05", "remaining_time": "0:29:40"} +{"current_steps": 90, "total_steps": 441, "loss": 0.459, "lr": 3.879385241571817e-05, "epoch": 1.432, "percentage": 20.41, "elapsed_time": "0:07:36", "remaining_time": "0:29:41"} +{"current_steps": 95, "total_steps": 441, "loss": 0.446, "lr": 3.8507804685477223e-05, "epoch": 1.512, "percentage": 21.54, "elapsed_time": "0:07:58", "remaining_time": "0:29:03"} +{"current_steps": 100, "total_steps": 441, "loss": 0.443, "lr": 3.819263990709037e-05, "epoch": 1.592, "percentage": 22.68, "elapsed_time": "0:08:21", "remaining_time": "0:28:31"} +{"current_steps": 105, "total_steps": 441, "loss": 0.4578, "lr": 3.78488539074902e-05, "epoch": 1.6720000000000002, "percentage": 23.81, "elapsed_time": "0:08:41", "remaining_time": "0:27:48"} +{"current_steps": 110, "total_steps": 441, "loss": 0.4481, "lr": 3.74769875413957e-05, "epoch": 1.752, "percentage": 24.94, "elapsed_time": "0:09:05", "remaining_time": "0:27:21"} +{"current_steps": 115, "total_steps": 441, "loss": 0.4381, "lr": 3.707762584042297e-05, "epoch": 1.8319999999999999, "percentage": 26.08, "elapsed_time": "0:09:26", "remaining_time": "0:26:46"} +{"current_steps": 120, "total_steps": 441, "loss": 0.4437, "lr": 3.665139709269543e-05, "epoch": 1.912, "percentage": 27.21, "elapsed_time": "0:09:56", "remaining_time": "0:26:35"} +{"current_steps": 125, "total_steps": 441, "loss": 0.4438, "lr": 3.619897185440168e-05, "epoch": 1.992, "percentage": 28.34, "elapsed_time": "0:10:24", "remaining_time": "0:26:18"} +{"current_steps": 130, "total_steps": 441, "loss": 0.4077, "lr": 3.5721061894855756e-05, "epoch": 2.064, "percentage": 29.48, "elapsed_time": "0:10:47", "remaining_time": "0:25:48"} +{"current_steps": 135, "total_steps": 441, "loss": 0.4048, "lr": 3.521841907671983e-05, "epoch": 2.144, "percentage": 30.61, "elapsed_time": "0:11:09", "remaining_time": "0:25:17"} +{"current_steps": 140, "total_steps": 441, "loss": 0.4083, "lr": 3.469183417315066e-05, "epoch": 2.224, "percentage": 31.75, "elapsed_time": "0:11:32", "remaining_time": "0:24:48"} +{"current_steps": 145, "total_steps": 441, "loss": 0.4373, "lr": 3.4142135623730954e-05, "epoch": 2.304, "percentage": 32.88, "elapsed_time": "0:11:53", "remaining_time": "0:24:16"} +{"current_steps": 150, "total_steps": 441, "loss": 0.3945, "lr": 3.3570188231142647e-05, "epoch": 2.384, "percentage": 34.01, "elapsed_time": "0:12:15", "remaining_time": "0:23:47"} +{"current_steps": 155, "total_steps": 441, "loss": 0.4123, "lr": 3.2976891800632775e-05, "epoch": 2.464, "percentage": 35.15, "elapsed_time": "0:12:40", "remaining_time": "0:23:22"} +{"current_steps": 160, "total_steps": 441, "loss": 0.4185, "lr": 3.2363179724412105e-05, "epoch": 2.544, "percentage": 36.28, "elapsed_time": "0:12:55", "remaining_time": "0:22:42"} +{"current_steps": 165, "total_steps": 441, "loss": 0.3719, "lr": 3.173001751321381e-05, "epoch": 2.624, "percentage": 37.41, "elapsed_time": "0:13:17", "remaining_time": "0:22:14"} +{"current_steps": 170, "total_steps": 441, "loss": 0.3863, "lr": 3.107840127732221e-05, "epoch": 2.7039999999999997, "percentage": 38.55, "elapsed_time": "0:13:43", "remaining_time": "0:21:52"} +{"current_steps": 175, "total_steps": 441, "loss": 0.3715, "lr": 3.0409356159461447e-05, "epoch": 2.784, "percentage": 39.68, "elapsed_time": "0:14:10", "remaining_time": "0:21:32"} +{"current_steps": 180, "total_steps": 441, "loss": 0.3896, "lr": 2.9723934722009375e-05, "epoch": 2.864, "percentage": 40.82, "elapsed_time": "0:14:42", "remaining_time": "0:21:19"} +{"current_steps": 185, "total_steps": 441, "loss": 0.3836, "lr": 2.9023215291074017e-05, "epoch": 2.944, "percentage": 41.95, "elapsed_time": "0:15:03", "remaining_time": "0:20:49"} +{"current_steps": 190, "total_steps": 441, "loss": 0.3848, "lr": 2.8308300260037734e-05, "epoch": 3.016, "percentage": 43.08, "elapsed_time": "0:15:22", "remaining_time": "0:20:18"} +{"current_steps": 195, "total_steps": 441, "loss": 0.3376, "lr": 2.758031435523801e-05, "epoch": 3.096, "percentage": 44.22, "elapsed_time": "0:15:47", "remaining_time": "0:19:54"} +{"current_steps": 200, "total_steps": 441, "loss": 0.3525, "lr": 2.684040286651338e-05, "epoch": 3.176, "percentage": 45.35, "elapsed_time": "0:16:10", "remaining_time": "0:19:29"} +{"current_steps": 205, "total_steps": 441, "loss": 0.3631, "lr": 2.6089729845398144e-05, "epoch": 3.2560000000000002, "percentage": 46.49, "elapsed_time": "0:16:34", "remaining_time": "0:19:04"} +{"current_steps": 210, "total_steps": 441, "loss": 0.3683, "lr": 2.53294762738007e-05, "epoch": 3.336, "percentage": 47.62, "elapsed_time": "0:16:57", "remaining_time": "0:18:39"} +{"current_steps": 215, "total_steps": 441, "loss": 0.3376, "lr": 2.4560838206046437e-05, "epoch": 3.416, "percentage": 48.75, "elapsed_time": "0:17:20", "remaining_time": "0:18:13"} +{"current_steps": 220, "total_steps": 441, "loss": 0.3517, "lr": 2.3785024887208207e-05, "epoch": 3.496, "percentage": 49.89, "elapsed_time": "0:17:43", "remaining_time": "0:17:48"} +{"current_steps": 225, "total_steps": 441, "loss": 0.359, "lr": 2.3003256850684808e-05, "epoch": 3.576, "percentage": 51.02, "elapsed_time": "0:18:04", "remaining_time": "0:17:21"} +{"current_steps": 230, "total_steps": 441, "loss": 0.3463, "lr": 2.2216763998020222e-05, "epoch": 3.656, "percentage": 52.15, "elapsed_time": "0:18:25", "remaining_time": "0:16:54"} +{"current_steps": 235, "total_steps": 441, "loss": 0.3523, "lr": 2.1426783663984648e-05, "epoch": 3.7359999999999998, "percentage": 53.29, "elapsed_time": "0:18:50", "remaining_time": "0:16:31"} +{"current_steps": 240, "total_steps": 441, "loss": 0.3419, "lr": 2.063455866996136e-05, "epoch": 3.816, "percentage": 54.42, "elapsed_time": "0:19:12", "remaining_time": "0:16:04"} +{"current_steps": 245, "total_steps": 441, "loss": 0.3612, "lr": 1.9841335368701812e-05, "epoch": 3.896, "percentage": 55.56, "elapsed_time": "0:19:34", "remaining_time": "0:15:39"} +{"current_steps": 250, "total_steps": 441, "loss": 0.3398, "lr": 1.9048361683525155e-05, "epoch": 3.976, "percentage": 56.69, "elapsed_time": "0:19:53", "remaining_time": "0:15:11"} +{"current_steps": 255, "total_steps": 441, "loss": 0.3243, "lr": 1.8256885145046837e-05, "epoch": 4.048, "percentage": 57.82, "elapsed_time": "0:20:18", "remaining_time": "0:14:48"} +{"current_steps": 260, "total_steps": 441, "loss": 0.3167, "lr": 1.7468150928525014e-05, "epoch": 4.128, "percentage": 58.96, "elapsed_time": "0:20:40", "remaining_time": "0:14:23"} +{"current_steps": 265, "total_steps": 441, "loss": 0.3013, "lr": 1.6683399894912522e-05, "epoch": 4.208, "percentage": 60.09, "elapsed_time": "0:21:09", "remaining_time": "0:14:03"} +{"current_steps": 270, "total_steps": 441, "loss": 0.3216, "lr": 1.590386663869619e-05, "epoch": 4.288, "percentage": 61.22, "elapsed_time": "0:21:30", "remaining_time": "0:13:37"} +{"current_steps": 275, "total_steps": 441, "loss": 0.3127, "lr": 1.5130777545594824e-05, "epoch": 4.368, "percentage": 62.36, "elapsed_time": "0:21:56", "remaining_time": "0:13:14"} +{"current_steps": 280, "total_steps": 441, "loss": 0.3083, "lr": 1.4365348863171406e-05, "epoch": 4.448, "percentage": 63.49, "elapsed_time": "0:22:19", "remaining_time": "0:12:50"} +{"current_steps": 285, "total_steps": 441, "loss": 0.3294, "lr": 1.3608784787395005e-05, "epoch": 4.5280000000000005, "percentage": 64.63, "elapsed_time": "0:22:40", "remaining_time": "0:12:24"} +{"current_steps": 290, "total_steps": 441, "loss": 0.3251, "lr": 1.2862275568162566e-05, "epoch": 4.608, "percentage": 65.76, "elapsed_time": "0:23:04", "remaining_time": "0:12:00"} +{"current_steps": 295, "total_steps": 441, "loss": 0.3169, "lr": 1.2126995636761174e-05, "epoch": 4.688, "percentage": 66.89, "elapsed_time": "0:23:28", "remaining_time": "0:11:37"} +{"current_steps": 300, "total_steps": 441, "loss": 0.3043, "lr": 1.1404101758216568e-05, "epoch": 4.768, "percentage": 68.03, "elapsed_time": "0:23:46", "remaining_time": "0:11:10"} +{"current_steps": 305, "total_steps": 441, "loss": 0.3113, "lr": 1.0694731211434788e-05, "epoch": 4.848, "percentage": 69.16, "elapsed_time": "0:24:04", "remaining_time": "0:10:44"} +{"current_steps": 310, "total_steps": 441, "loss": 0.325, "lr": 1.0000000000000006e-05, "epoch": 4.928, "percentage": 70.29, "elapsed_time": "0:24:27", "remaining_time": "0:10:20"} +{"current_steps": 315, "total_steps": 441, "loss": 0.3011, "lr": 9.32100109644328e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "0:24:48", "remaining_time": "0:09:55"} +{"current_steps": 320, "total_steps": 441, "loss": 0.3003, "lr": 8.658802722744589e-06, "epoch": 5.08, "percentage": 72.56, "elapsed_time": "0:25:10", "remaining_time": "0:09:31"} +{"current_steps": 325, "total_steps": 441, "loss": 0.2765, "lr": 8.014446669773061e-06, "epoch": 5.16, "percentage": 73.7, "elapsed_time": "0:25:33", "remaining_time": "0:09:07"} +{"current_steps": 330, "total_steps": 441, "loss": 0.3104, "lr": 7.388946658309557e-06, "epoch": 5.24, "percentage": 74.83, "elapsed_time": "0:26:00", "remaining_time": "0:08:44"} +{"current_steps": 335, "total_steps": 441, "loss": 0.2844, "lr": 6.7832867442298645e-06, "epoch": 5.32, "percentage": 75.96, "elapsed_time": "0:26:22", "remaining_time": "0:08:20"} +{"current_steps": 340, "total_steps": 441, "loss": 0.2976, "lr": 6.198419770357764e-06, "epoch": 5.4, "percentage": 77.1, "elapsed_time": "0:26:44", "remaining_time": "0:07:56"} +{"current_steps": 345, "total_steps": 441, "loss": 0.2998, "lr": 5.635265867423321e-06, "epoch": 5.48, "percentage": 78.23, "elapsed_time": "0:27:03", "remaining_time": "0:07:31"} +{"current_steps": 350, "total_steps": 441, "loss": 0.2778, "lr": 5.094711006484907e-06, "epoch": 5.5600000000000005, "percentage": 79.37, "elapsed_time": "0:27:28", "remaining_time": "0:07:08"} +{"current_steps": 355, "total_steps": 441, "loss": 0.285, "lr": 4.577605605092248e-06, "epoch": 5.64, "percentage": 80.5, "elapsed_time": "0:27:59", "remaining_time": "0:06:46"} +{"current_steps": 360, "total_steps": 441, "loss": 0.2852, "lr": 4.0847631893833566e-06, "epoch": 5.72, "percentage": 81.63, "elapsed_time": "0:28:22", "remaining_time": "0:06:23"} +{"current_steps": 365, "total_steps": 441, "loss": 0.3002, "lr": 3.616959114220162e-06, "epoch": 5.8, "percentage": 82.77, "elapsed_time": "0:28:42", "remaining_time": "0:05:58"} +{"current_steps": 370, "total_steps": 441, "loss": 0.2841, "lr": 3.174929343376374e-06, "epoch": 5.88, "percentage": 83.9, "elapsed_time": "0:29:03", "remaining_time": "0:05:34"} +{"current_steps": 375, "total_steps": 441, "loss": 0.3004, "lr": 2.759369291696614e-06, "epoch": 5.96, "percentage": 85.03, "elapsed_time": "0:29:22", "remaining_time": "0:05:10"} +{"current_steps": 380, "total_steps": 441, "loss": 0.2684, "lr": 2.3709327310483608e-06, "epoch": 6.032, "percentage": 86.17, "elapsed_time": "0:29:41", "remaining_time": "0:04:45"} +{"current_steps": 385, "total_steps": 441, "loss": 0.2766, "lr": 2.0102307617879367e-06, "epoch": 6.112, "percentage": 87.3, "elapsed_time": "0:30:00", "remaining_time": "0:04:21"} +{"current_steps": 390, "total_steps": 441, "loss": 0.2962, "lr": 1.6778308513586084e-06, "epoch": 6.192, "percentage": 88.44, "elapsed_time": "0:30:26", "remaining_time": "0:03:58"} +{"current_steps": 395, "total_steps": 441, "loss": 0.2762, "lr": 1.3742559415333267e-06, "epoch": 6.272, "percentage": 89.57, "elapsed_time": "0:30:45", "remaining_time": "0:03:34"} +{"current_steps": 400, "total_steps": 441, "loss": 0.2655, "lr": 1.099983625706631e-06, "epoch": 6.352, "percentage": 90.7, "elapsed_time": "0:31:11", "remaining_time": "0:03:11"} +{"current_steps": 405, "total_steps": 441, "loss": 0.2789, "lr": 8.554453975300258e-07, "epoch": 6.432, "percentage": 91.84, "elapsed_time": "0:31:37", "remaining_time": "0:02:48"} +{"current_steps": 410, "total_steps": 441, "loss": 0.2992, "lr": 6.410259720728751e-07, "epoch": 6.5120000000000005, "percentage": 92.97, "elapsed_time": "0:32:00", "remaining_time": "0:02:25"} +{"current_steps": 415, "total_steps": 441, "loss": 0.273, "lr": 4.570626805768119e-07, "epoch": 6.592, "percentage": 94.1, "elapsed_time": "0:32:25", "remaining_time": "0:02:01"} +{"current_steps": 420, "total_steps": 441, "loss": 0.2942, "lr": 3.038449397558396e-07, "epoch": 6.672, "percentage": 95.24, "elapsed_time": "0:32:43", "remaining_time": "0:01:38"} +{"current_steps": 425, "total_steps": 441, "loss": 0.2789, "lr": 1.8161379647706034e-07, "epoch": 6.752, "percentage": 96.37, "elapsed_time": "0:33:04", "remaining_time": "0:01:14"} +{"current_steps": 430, "total_steps": 441, "loss": 0.2924, "lr": 9.056154853830823e-08, "epoch": 6.832, "percentage": 97.51, "elapsed_time": "0:33:26", "remaining_time": "0:00:51"} +{"current_steps": 435, "total_steps": 441, "loss": 0.2918, "lr": 3.083144213933853e-08, "epoch": 6.912, "percentage": 98.64, "elapsed_time": "0:33:53", "remaining_time": "0:00:28"} +{"current_steps": 440, "total_steps": 441, "loss": 0.2714, "lr": 2.5174465224986343e-09, "epoch": 6.992, "percentage": 99.77, "elapsed_time": "0:34:12", "remaining_time": "0:00:04"} +{"current_steps": 441, "total_steps": 441, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:34:52", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..12d9393 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1015 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.0, + "eval_steps": 500, + "global_step": 441, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.08, + "grad_norm": 7.505872381862423, + "learning_rate": 3.555555555555556e-06, + "loss": 0.8889, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3562159836292267, + "step": 5, + "valid_targets_mean": 2130.2, + "valid_targets_min": 1151 + }, + { + "epoch": 0.16, + "grad_norm": 4.299941064882982, + "learning_rate": 8.000000000000001e-06, + "loss": 0.8268, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.43203479051589966, + "step": 10, + "valid_targets_mean": 2883.6, + "valid_targets_min": 1121 + }, + { + "epoch": 0.24, + "grad_norm": 2.284058440682455, + "learning_rate": 1.2444444444444446e-05, + "loss": 0.7614, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3178209662437439, + "step": 15, + "valid_targets_mean": 2271.4, + "valid_targets_min": 779 + }, + { + "epoch": 0.32, + "grad_norm": 1.208566277480267, + "learning_rate": 1.688888888888889e-05, + "loss": 0.6515, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34249401092529297, + "step": 20, + "valid_targets_mean": 2947.9, + "valid_targets_min": 1111 + }, + { + "epoch": 0.4, + "grad_norm": 1.1034086292105623, + "learning_rate": 2.1333333333333335e-05, + "loss": 0.5973, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32616934180259705, + "step": 25, + "valid_targets_mean": 3281.1, + "valid_targets_min": 873 + }, + { + "epoch": 0.48, + "grad_norm": 1.0503267052677303, + "learning_rate": 2.577777777777778e-05, + "loss": 0.6453, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3611135482788086, + "step": 30, + "valid_targets_mean": 2335.5, + "valid_targets_min": 1311 + }, + { + "epoch": 0.56, + "grad_norm": 0.9194708186912789, + "learning_rate": 3.0222222222222225e-05, + "loss": 0.5684, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26414716243743896, + "step": 35, + "valid_targets_mean": 2443.0, + "valid_targets_min": 1337 + }, + { + "epoch": 0.64, + "grad_norm": 0.8752103356753728, + "learning_rate": 3.466666666666667e-05, + "loss": 0.5656, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3691626489162445, + "step": 40, + "valid_targets_mean": 3333.5, + "valid_targets_min": 989 + }, + { + "epoch": 0.72, + "grad_norm": 0.7978234001550478, + "learning_rate": 3.9111111111111115e-05, + "loss": 0.5234, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.28348302841186523, + "step": 45, + "valid_targets_mean": 2966.8, + "valid_targets_min": 886 + }, + { + "epoch": 0.8, + "grad_norm": 0.7861038745079318, + "learning_rate": 3.9989930847663706e-05, + "loss": 0.53, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.28643012046813965, + "step": 50, + "valid_targets_mean": 3180.1, + "valid_targets_min": 1358 + }, + { + "epoch": 0.88, + "grad_norm": 0.8055444173490995, + "learning_rate": 3.994904229220507e-05, + "loss": 0.5412, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.291437566280365, + "step": 55, + "valid_targets_mean": 2481.9, + "valid_targets_min": 1418 + }, + { + "epoch": 0.96, + "grad_norm": 0.8278524255463231, + "learning_rate": 3.9876769289225084e-05, + "loss": 0.4896, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22183263301849365, + "step": 60, + "valid_targets_mean": 1879.6, + "valid_targets_min": 981 + }, + { + "epoch": 1.032, + "grad_norm": 0.8696048731655817, + "learning_rate": 3.977322554083716e-05, + "loss": 0.5374, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.43486517667770386, + "step": 65, + "valid_targets_mean": 3426.5, + "valid_targets_min": 1408 + }, + { + "epoch": 1.112, + "grad_norm": 0.7781509716799682, + "learning_rate": 3.963857394525413e-05, + "loss": 0.488, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19639593362808228, + "step": 70, + "valid_targets_mean": 2309.4, + "valid_targets_min": 886 + }, + { + "epoch": 1.192, + "grad_norm": 0.8382160539678171, + "learning_rate": 3.947302634051182e-05, + "loss": 0.4376, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20422697067260742, + "step": 75, + "valid_targets_mean": 1743.0, + "valid_targets_min": 1050 + }, + { + "epoch": 1.272, + "grad_norm": 0.8476519934522162, + "learning_rate": 3.9276843171198844e-05, + "loss": 0.4908, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20554912090301514, + "step": 80, + "valid_targets_mean": 2396.1, + "valid_targets_min": 1201 + }, + { + "epoch": 1.3519999999999999, + "grad_norm": 0.9006870601615783, + "learning_rate": 3.9050333078717216e-05, + "loss": 0.4667, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1725320816040039, + "step": 85, + "valid_targets_mean": 1700.5, + "valid_targets_min": 1071 + }, + { + "epoch": 1.432, + "grad_norm": 0.791325198841491, + "learning_rate": 3.879385241571817e-05, + "loss": 0.459, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.21249258518218994, + "step": 90, + "valid_targets_mean": 2356.9, + "valid_targets_min": 1122 + }, + { + "epoch": 1.512, + "grad_norm": 1.0385117113315703, + "learning_rate": 3.8507804685477223e-05, + "loss": 0.446, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.21146586537361145, + "step": 95, + "valid_targets_mean": 1682.9, + "valid_targets_min": 873 + }, + { + "epoch": 1.592, + "grad_norm": 0.8011987888299815, + "learning_rate": 3.819263990709037e-05, + "loss": 0.443, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2212362438440323, + "step": 100, + "valid_targets_mean": 3187.1, + "valid_targets_min": 281 + }, + { + "epoch": 1.6720000000000002, + "grad_norm": 0.778909724911067, + "learning_rate": 3.78488539074902e-05, + "loss": 0.4578, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23308740556240082, + "step": 105, + "valid_targets_mean": 2398.9, + "valid_targets_min": 960 + }, + { + "epoch": 1.752, + "grad_norm": 0.7972257244582753, + "learning_rate": 3.74769875413957e-05, + "loss": 0.4481, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.16984760761260986, + "step": 110, + "valid_targets_mean": 1965.9, + "valid_targets_min": 670 + }, + { + "epoch": 1.8319999999999999, + "grad_norm": 0.8844948592143324, + "learning_rate": 3.707762584042297e-05, + "loss": 0.4381, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24562954902648926, + "step": 115, + "valid_targets_mean": 2081.1, + "valid_targets_min": 1412 + }, + { + "epoch": 1.912, + "grad_norm": 1.053576485355223, + "learning_rate": 3.665139709269543e-05, + "loss": 0.4437, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2656170129776001, + "step": 120, + "valid_targets_mean": 1548.0, + "valid_targets_min": 903 + }, + { + "epoch": 1.992, + "grad_norm": 0.7689058933714845, + "learning_rate": 3.619897185440168e-05, + "loss": 0.4438, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24418014287948608, + "step": 125, + "valid_targets_mean": 2581.8, + "valid_targets_min": 1259 + }, + { + "epoch": 2.064, + "grad_norm": 0.7326051302166501, + "learning_rate": 3.5721061894855756e-05, + "loss": 0.4077, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18473495543003082, + "step": 130, + "valid_targets_mean": 2903.2, + "valid_targets_min": 1410 + }, + { + "epoch": 2.144, + "grad_norm": 0.8708474099425602, + "learning_rate": 3.521841907671983e-05, + "loss": 0.4048, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2214871197938919, + "step": 135, + "valid_targets_mean": 2367.8, + "valid_targets_min": 1390 + }, + { + "epoch": 2.224, + "grad_norm": 0.7597533514662402, + "learning_rate": 3.469183417315066e-05, + "loss": 0.4083, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1592719554901123, + "step": 140, + "valid_targets_mean": 2209.9, + "valid_targets_min": 1123 + }, + { + "epoch": 2.304, + "grad_norm": 0.8308288880226818, + "learning_rate": 3.4142135623730954e-05, + "loss": 0.4373, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2935639023780823, + "step": 145, + "valid_targets_mean": 3067.8, + "valid_targets_min": 684 + }, + { + "epoch": 2.384, + "grad_norm": 0.7814988864434326, + "learning_rate": 3.3570188231142647e-05, + "loss": 0.3945, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2506471872329712, + "step": 150, + "valid_targets_mean": 3332.8, + "valid_targets_min": 1190 + }, + { + "epoch": 2.464, + "grad_norm": 0.9693558608483495, + "learning_rate": 3.2976891800632775e-05, + "loss": 0.4123, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18241941928863525, + "step": 155, + "valid_targets_mean": 1810.9, + "valid_targets_min": 508 + }, + { + "epoch": 2.544, + "grad_norm": 0.9188887892272475, + "learning_rate": 3.2363179724412105e-05, + "loss": 0.4185, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17377954721450806, + "step": 160, + "valid_targets_mean": 1971.0, + "valid_targets_min": 906 + }, + { + "epoch": 2.624, + "grad_norm": 0.8184684644144737, + "learning_rate": 3.173001751321381e-05, + "loss": 0.3719, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.21439319849014282, + "step": 165, + "valid_targets_mean": 2445.6, + "valid_targets_min": 1154 + }, + { + "epoch": 2.7039999999999997, + "grad_norm": 0.9397326224963451, + "learning_rate": 3.107840127732221e-05, + "loss": 0.3863, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17729023098945618, + "step": 170, + "valid_targets_mean": 1877.6, + "valid_targets_min": 990 + }, + { + "epoch": 2.784, + "grad_norm": 0.8420928524890345, + "learning_rate": 3.0409356159461447e-05, + "loss": 0.3715, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19148927927017212, + "step": 175, + "valid_targets_mean": 2280.6, + "valid_targets_min": 1077 + }, + { + "epoch": 2.864, + "grad_norm": 0.722070280229424, + "learning_rate": 2.9723934722009375e-05, + "loss": 0.3896, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11640667170286179, + "step": 180, + "valid_targets_mean": 2501.6, + "valid_targets_min": 1121 + }, + { + "epoch": 2.944, + "grad_norm": 0.7740124459994261, + "learning_rate": 2.9023215291074017e-05, + "loss": 0.3836, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.179210364818573, + "step": 185, + "valid_targets_mean": 2544.9, + "valid_targets_min": 1021 + }, + { + "epoch": 3.016, + "grad_norm": 0.8032029716283615, + "learning_rate": 2.8308300260037734e-05, + "loss": 0.3848, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1465587019920349, + "step": 190, + "valid_targets_mean": 2581.0, + "valid_targets_min": 1258 + }, + { + "epoch": 3.096, + "grad_norm": 1.0675192734720838, + "learning_rate": 2.758031435523801e-05, + "loss": 0.3376, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19570258259773254, + "step": 195, + "valid_targets_mean": 1776.4, + "valid_targets_min": 998 + }, + { + "epoch": 3.176, + "grad_norm": 0.7941943435641896, + "learning_rate": 2.684040286651338e-05, + "loss": 0.3525, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17122869193553925, + "step": 200, + "valid_targets_mean": 2871.4, + "valid_targets_min": 1062 + }, + { + "epoch": 3.2560000000000002, + "grad_norm": 0.8590713481269158, + "learning_rate": 2.6089729845398144e-05, + "loss": 0.3631, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20491699874401093, + "step": 205, + "valid_targets_mean": 2635.2, + "valid_targets_min": 1136 + }, + { + "epoch": 3.336, + "grad_norm": 0.8124117326779144, + "learning_rate": 2.53294762738007e-05, + "loss": 0.3683, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15610741078853607, + "step": 210, + "valid_targets_mean": 2695.1, + "valid_targets_min": 1041 + }, + { + "epoch": 3.416, + "grad_norm": 0.9190062289677365, + "learning_rate": 2.4560838206046437e-05, + "loss": 0.3376, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17463022470474243, + "step": 215, + "valid_targets_mean": 2569.9, + "valid_targets_min": 1514 + }, + { + "epoch": 3.496, + "grad_norm": 0.9065219155043758, + "learning_rate": 2.3785024887208207e-05, + "loss": 0.3517, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22582875192165375, + "step": 220, + "valid_targets_mean": 2724.9, + "valid_targets_min": 1220 + }, + { + "epoch": 3.576, + "grad_norm": 1.0837756986609808, + "learning_rate": 2.3003256850684808e-05, + "loss": 0.359, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18150931596755981, + "step": 225, + "valid_targets_mean": 2179.9, + "valid_targets_min": 1399 + }, + { + "epoch": 3.656, + "grad_norm": 1.2484982875648234, + "learning_rate": 2.2216763998020222e-05, + "loss": 0.3463, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18959809839725494, + "step": 230, + "valid_targets_mean": 1788.8, + "valid_targets_min": 903 + }, + { + "epoch": 3.7359999999999998, + "grad_norm": 1.3179674271154644, + "learning_rate": 2.1426783663984648e-05, + "loss": 0.3523, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15963847935199738, + "step": 235, + "valid_targets_mean": 1711.9, + "valid_targets_min": 886 + }, + { + "epoch": 3.816, + "grad_norm": 1.2429310941711111, + "learning_rate": 2.063455866996136e-05, + "loss": 0.3419, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1572306901216507, + "step": 240, + "valid_targets_mean": 2487.1, + "valid_targets_min": 1122 + }, + { + "epoch": 3.896, + "grad_norm": 1.015916750182016, + "learning_rate": 1.9841335368701812e-05, + "loss": 0.3612, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.14525054395198822, + "step": 245, + "valid_targets_mean": 1455.9, + "valid_targets_min": 1052 + }, + { + "epoch": 3.976, + "grad_norm": 0.7307166020752172, + "learning_rate": 1.9048361683525155e-05, + "loss": 0.3398, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1978192925453186, + "step": 250, + "valid_targets_mean": 4146.5, + "valid_targets_min": 1324 + }, + { + "epoch": 4.048, + "grad_norm": 0.7270768944589141, + "learning_rate": 1.8256885145046837e-05, + "loss": 0.3243, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1474921554327011, + "step": 255, + "valid_targets_mean": 3523.0, + "valid_targets_min": 1623 + }, + { + "epoch": 4.128, + "grad_norm": 0.8418803354786775, + "learning_rate": 1.7468150928525014e-05, + "loss": 0.3167, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13115155696868896, + "step": 260, + "valid_targets_mean": 2395.5, + "valid_targets_min": 1216 + }, + { + "epoch": 4.208, + "grad_norm": 0.8360752789280677, + "learning_rate": 1.6683399894912522e-05, + "loss": 0.3013, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.16828887164592743, + "step": 265, + "valid_targets_mean": 2699.0, + "valid_targets_min": 1050 + }, + { + "epoch": 4.288, + "grad_norm": 0.96113797783045, + "learning_rate": 1.590386663869619e-05, + "loss": 0.3216, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15936484932899475, + "step": 270, + "valid_targets_mean": 2447.2, + "valid_targets_min": 1046 + }, + { + "epoch": 4.368, + "grad_norm": 0.833095764473076, + "learning_rate": 1.5130777545594824e-05, + "loss": 0.3127, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.16047963500022888, + "step": 275, + "valid_targets_mean": 3236.5, + "valid_targets_min": 990 + }, + { + "epoch": 4.448, + "grad_norm": 0.947963665080153, + "learning_rate": 1.4365348863171406e-05, + "loss": 0.3083, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15773838758468628, + "step": 280, + "valid_targets_mean": 2548.2, + "valid_targets_min": 1062 + }, + { + "epoch": 4.5280000000000005, + "grad_norm": 1.0228687085990507, + "learning_rate": 1.3608784787395005e-05, + "loss": 0.3294, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2106139063835144, + "step": 285, + "valid_targets_mean": 2470.1, + "valid_targets_min": 1847 + }, + { + "epoch": 4.608, + "grad_norm": 0.80850799889799, + "learning_rate": 1.2862275568162566e-05, + "loss": 0.3251, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20072545111179352, + "step": 290, + "valid_targets_mean": 3350.9, + "valid_targets_min": 1369 + }, + { + "epoch": 4.688, + "grad_norm": 1.012254046643678, + "learning_rate": 1.2126995636761174e-05, + "loss": 0.3169, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15989793837070465, + "step": 295, + "valid_targets_mean": 2194.9, + "valid_targets_min": 1198 + }, + { + "epoch": 4.768, + "grad_norm": 1.0563967564745178, + "learning_rate": 1.1404101758216568e-05, + "loss": 0.3043, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1755823791027069, + "step": 300, + "valid_targets_mean": 1960.2, + "valid_targets_min": 1028 + }, + { + "epoch": 4.848, + "grad_norm": 0.9311730256722943, + "learning_rate": 1.0694731211434788e-05, + "loss": 0.3113, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12437054514884949, + "step": 305, + "valid_targets_mean": 1777.2, + "valid_targets_min": 1210 + }, + { + "epoch": 4.928, + "grad_norm": 0.9776791335105928, + "learning_rate": 1.0000000000000006e-05, + "loss": 0.325, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20600047707557678, + "step": 310, + "valid_targets_mean": 2911.2, + "valid_targets_min": 957 + }, + { + "epoch": 5.0, + "grad_norm": 1.4087833914171262, + "learning_rate": 9.32100109644328e-06, + "loss": 0.3011, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29628846049308777, + "step": 315, + "valid_targets_mean": 3412.9, + "valid_targets_min": 1927 + }, + { + "epoch": 5.08, + "grad_norm": 1.1237962021877523, + "learning_rate": 8.658802722744589e-06, + "loss": 0.3003, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1448991596698761, + "step": 320, + "valid_targets_mean": 1924.0, + "valid_targets_min": 1127 + }, + { + "epoch": 5.16, + "grad_norm": 0.9172596743702742, + "learning_rate": 8.014446669773061e-06, + "loss": 0.2765, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19501471519470215, + "step": 325, + "valid_targets_mean": 3372.5, + "valid_targets_min": 1486 + }, + { + "epoch": 5.24, + "grad_norm": 1.0573522542198426, + "learning_rate": 7.388946658309557e-06, + "loss": 0.3104, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13600924611091614, + "step": 330, + "valid_targets_mean": 1860.2, + "valid_targets_min": 626 + }, + { + "epoch": 5.32, + "grad_norm": 1.095408717419895, + "learning_rate": 6.7832867442298645e-06, + "loss": 0.2844, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.14203448593616486, + "step": 335, + "valid_targets_mean": 3012.0, + "valid_targets_min": 1445 + }, + { + "epoch": 5.4, + "grad_norm": 0.8946946595676237, + "learning_rate": 6.198419770357764e-06, + "loss": 0.2976, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.16260306537151337, + "step": 340, + "valid_targets_mean": 2969.6, + "valid_targets_min": 873 + }, + { + "epoch": 5.48, + "grad_norm": 0.8169352231394611, + "learning_rate": 5.635265867423321e-06, + "loss": 0.2998, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17487314343452454, + "step": 345, + "valid_targets_mean": 3076.6, + "valid_targets_min": 1050 + }, + { + "epoch": 5.5600000000000005, + "grad_norm": 0.8163208743049927, + "learning_rate": 5.094711006484907e-06, + "loss": 0.2778, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08679372817277908, + "step": 350, + "valid_targets_mean": 2021.5, + "valid_targets_min": 338 + }, + { + "epoch": 5.64, + "grad_norm": 0.9952519880856041, + "learning_rate": 4.577605605092248e-06, + "loss": 0.285, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.16831034421920776, + "step": 355, + "valid_targets_mean": 2338.1, + "valid_targets_min": 1084 + }, + { + "epoch": 5.72, + "grad_norm": 1.0756622420151967, + "learning_rate": 4.0847631893833566e-06, + "loss": 0.2852, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1444486677646637, + "step": 360, + "valid_targets_mean": 2133.6, + "valid_targets_min": 965 + }, + { + "epoch": 5.8, + "grad_norm": 0.9257674814633752, + "learning_rate": 3.616959114220162e-06, + "loss": 0.3002, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23777079582214355, + "step": 365, + "valid_targets_mean": 2538.9, + "valid_targets_min": 1373 + }, + { + "epoch": 5.88, + "grad_norm": 0.8690699429240454, + "learning_rate": 3.174929343376374e-06, + "loss": 0.2841, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11037126183509827, + "step": 370, + "valid_targets_mean": 2433.8, + "valid_targets_min": 1237 + }, + { + "epoch": 5.96, + "grad_norm": 0.9718357574467225, + "learning_rate": 2.759369291696614e-06, + "loss": 0.3004, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1343100368976593, + "step": 375, + "valid_targets_mean": 2798.5, + "valid_targets_min": 903 + }, + { + "epoch": 6.032, + "grad_norm": 0.9817652023621845, + "learning_rate": 2.3709327310483608e-06, + "loss": 0.2684, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12780410051345825, + "step": 380, + "valid_targets_mean": 2150.0, + "valid_targets_min": 998 + }, + { + "epoch": 6.112, + "grad_norm": 0.9014203224760045, + "learning_rate": 2.0102307617879367e-06, + "loss": 0.2766, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13069286942481995, + "step": 385, + "valid_targets_mean": 2268.4, + "valid_targets_min": 911 + }, + { + "epoch": 6.192, + "grad_norm": 1.0186765172032302, + "learning_rate": 1.6778308513586084e-06, + "loss": 0.2962, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11167597770690918, + "step": 390, + "valid_targets_mean": 1636.0, + "valid_targets_min": 693 + }, + { + "epoch": 6.272, + "grad_norm": 0.9007287293295244, + "learning_rate": 1.3742559415333267e-06, + "loss": 0.2762, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10594399273395538, + "step": 395, + "valid_targets_mean": 2016.9, + "valid_targets_min": 1210 + }, + { + "epoch": 6.352, + "grad_norm": 0.946964378636132, + "learning_rate": 1.099983625706631e-06, + "loss": 0.2655, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1707034707069397, + "step": 400, + "valid_targets_mean": 3195.9, + "valid_targets_min": 1289 + }, + { + "epoch": 6.432, + "grad_norm": 0.7899732764847707, + "learning_rate": 8.554453975300258e-07, + "loss": 0.2789, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08833309262990952, + "step": 405, + "valid_targets_mean": 2436.8, + "valid_targets_min": 888 + }, + { + "epoch": 6.5120000000000005, + "grad_norm": 0.8794195051438293, + "learning_rate": 6.410259720728751e-07, + "loss": 0.2992, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09639259427785873, + "step": 410, + "valid_targets_mean": 2271.0, + "valid_targets_min": 984 + }, + { + "epoch": 6.592, + "grad_norm": 1.0137858039965408, + "learning_rate": 4.570626805768119e-07, + "loss": 0.273, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15096719563007355, + "step": 415, + "valid_targets_mean": 2673.6, + "valid_targets_min": 1106 + }, + { + "epoch": 6.672, + "grad_norm": 0.9819001117157581, + "learning_rate": 3.038449397558396e-07, + "loss": 0.2942, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.15650422871112823, + "step": 420, + "valid_targets_mean": 2339.1, + "valid_targets_min": 718 + }, + { + "epoch": 6.752, + "grad_norm": 0.8517024842857888, + "learning_rate": 1.8161379647706034e-07, + "loss": 0.2789, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11373068392276764, + "step": 425, + "valid_targets_mean": 2288.1, + "valid_targets_min": 1061 + }, + { + "epoch": 6.832, + "grad_norm": 0.9942173325428866, + "learning_rate": 9.056154853830823e-08, + "loss": 0.2924, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1729286015033722, + "step": 430, + "valid_targets_mean": 2370.9, + "valid_targets_min": 436 + }, + { + "epoch": 6.912, + "grad_norm": 0.8761392834472287, + "learning_rate": 3.083144213933853e-08, + "loss": 0.2918, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0916639119386673, + "step": 435, + "valid_targets_mean": 2043.0, + "valid_targets_min": 1123 + }, + { + "epoch": 6.992, + "grad_norm": 1.0047486254280051, + "learning_rate": 2.5174465224986343e-09, + "loss": 0.2714, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1423904448747635, + "step": 440, + "valid_targets_mean": 1893.1, + "valid_targets_min": 626 + }, + { + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.259745717048645, + "step": 441, + "total_flos": 7.12082116746281e+16, + "train_loss": 0.38846772432732746, + "train_runtime": 2096.0086, + "train_samples_per_second": 3.336, + "train_steps_per_second": 0.21, + "valid_targets_mean": 3009.9, + "valid_targets_min": 873 + } + ], + "logging_steps": 5, + "max_steps": 441, + "num_input_tokens_seen": 0, + "num_train_epochs": 7, + "save_steps": 1500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 7.12082116746281e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..bddf2e7 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb753def72ae3578cb4459f4a537a0428480af48d3360e35fb787f22573db89c +size 8657 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..e2e8557 Binary files /dev/null and b/training_loss.png differ diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833