commit 5efc4852de8c7b621c59c037dffee340acecce95 Author: ModelHub XC Date: Thu Apr 23 11:31:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: laion/GLM-4_6-stackexchange-superuser-32ep-32k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40275e7 --- /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 + +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json 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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt 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..861d938 --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen3-8B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: GLM-4_6-stackexchange-superuser-32ep-32k + results: [] +--- + + + +# GLM-4_6-stackexchange-superuser-32ep-32k + +This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/GLM-4.6-stackexchange-superuser-32ep-32k 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: 16 +- total_train_batch_size: 16 +- total_eval_batch_size: 128 +- 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 4.56.0 +- Pytorch 2.9.0+cu128 +- Datasets 4.4.1 +- Tokenizers 0.22.1 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..f0aa701 --- /dev/null +++ b/all_results.json @@ -0,0 +1,16 @@ +{ + "achieved_tflops_per_gpu": 0.002928386808870264, + "achieved_tflops_per_gpu_theoretical": 494.6340661721825, + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24434766173362732, + "mfu_percent": 0.00020695313136892326, + "mfu_percent_theoretical": 34.956471107574735, + "total_flos": 459870247321600.0, + "train_loss": 0.3203928537069713, + "train_runtime": 9814.9228, + "train_samples_per_second": 2.332, + "train_steps_per_second": 0.146, + "valid_targets_mean": 2891.9, + "valid_targets_min": 658 +} \ 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..d04042c --- /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": "4.56.0", + "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..eff07c5 --- /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": "4.56.0" +} 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..c79ae44 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3119a7a7bd62d0ebd4c2db4e1eccf56b9c2801b3b10e2c0cf98d62a01b9b403 +size 4902257696 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..d9b79f7 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77466c92df220e31419b978068bc1a54db9d99908ac4542d9da9b6d9777f7a01 +size 4915960368 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..3e6eead --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33dc2b169d7672e16a58c82c5f48a214dd0a8eeb79853e488cd2a6925394247a +size 4983068496 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..e3423e6 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df684dd16922838e02ccd761eae30e648c99e293fbeed12fbe728b2bc77f0865 +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..bc7da6f --- /dev/null +++ b/run_summary.json @@ -0,0 +1,12 @@ +{ + "agent_name": null, + "training_start": null, + "training_end": null, + "created_by": "DCAgent", + "base_model_name": "Qwen/Qwen3-8B", + "dataset_name": "penfever/GLM-4.6-stackexchange-superuser-32ep-32k", + "training_type": "SFT", + "training_parameters": "https://huggingface.co/laion/GLM-4_6-stackexchange-superuser-32ep-32k/blob/main/config.json", + "wandb_link": "https://wandb.ai/dogml/dc-agent/runs/GLM-4.6-stackexchange-superuser-32ep-32k_hub-model-id_GLM-4.6-stackexchange-superuser-32ep-32k_Q", + "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..f0aa701 --- /dev/null +++ b/train_results.json @@ -0,0 +1,16 @@ +{ + "achieved_tflops_per_gpu": 0.002928386808870264, + "achieved_tflops_per_gpu_theoretical": 494.6340661721825, + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24434766173362732, + "mfu_percent": 0.00020695313136892326, + "mfu_percent_theoretical": 34.956471107574735, + "total_flos": 459870247321600.0, + "train_loss": 0.3203928537069713, + "train_runtime": 9814.9228, + "train_samples_per_second": 2.332, + "train_steps_per_second": 0.146, + "valid_targets_mean": 2891.9, + "valid_targets_min": 658 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..d362af7 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,288 @@ +{"current_steps": 5, "total_steps": 1435, "loss": 0.8361, "lr": 1.111111111111111e-06, "epoch": 0.024390243902439025, "percentage": 0.35, "elapsed_time": "0:00:47", "remaining_time": "3:46:53"} +{"current_steps": 10, "total_steps": 1435, "loss": 0.8084, "lr": 2.5e-06, "epoch": 0.04878048780487805, "percentage": 0.7, "elapsed_time": "0:01:22", "remaining_time": "3:15:42"} +{"current_steps": 15, "total_steps": 1435, "loss": 0.8018, "lr": 3.88888888888889e-06, "epoch": 0.07317073170731707, "percentage": 1.05, "elapsed_time": "0:01:52", "remaining_time": "2:57:01"} +{"current_steps": 20, "total_steps": 1435, "loss": 0.7365, "lr": 5.2777777777777785e-06, "epoch": 0.0975609756097561, "percentage": 1.39, "elapsed_time": "0:02:24", "remaining_time": "2:50:49"} +{"current_steps": 25, "total_steps": 1435, "loss": 0.6356, "lr": 6.666666666666667e-06, "epoch": 0.12195121951219512, "percentage": 1.74, "elapsed_time": "0:02:52", "remaining_time": "2:42:21"} +{"current_steps": 30, "total_steps": 1435, "loss": 0.5786, "lr": 8.055555555555557e-06, "epoch": 0.14634146341463414, "percentage": 2.09, "elapsed_time": "0:03:22", "remaining_time": "2:38:02"} +{"current_steps": 35, "total_steps": 1435, "loss": 0.5669, "lr": 9.444444444444445e-06, "epoch": 0.17073170731707318, "percentage": 2.44, "elapsed_time": "0:03:50", "remaining_time": "2:33:52"} +{"current_steps": 40, "total_steps": 1435, "loss": 0.5178, "lr": 1.0833333333333334e-05, "epoch": 0.1951219512195122, "percentage": 2.79, "elapsed_time": "0:04:29", "remaining_time": "2:36:32"} +{"current_steps": 45, "total_steps": 1435, "loss": 0.5122, "lr": 1.2222222222222224e-05, "epoch": 0.21951219512195122, "percentage": 3.14, "elapsed_time": "0:05:04", "remaining_time": "2:36:54"} +{"current_steps": 50, "total_steps": 1435, "loss": 0.5046, "lr": 1.3611111111111113e-05, "epoch": 0.24390243902439024, "percentage": 3.48, "elapsed_time": "0:05:40", "remaining_time": "2:37:09"} +{"current_steps": 55, "total_steps": 1435, "loss": 0.5042, "lr": 1.5000000000000002e-05, "epoch": 0.2682926829268293, "percentage": 3.83, "elapsed_time": "0:06:14", "remaining_time": "2:36:31"} +{"current_steps": 60, "total_steps": 1435, "loss": 0.4964, "lr": 1.638888888888889e-05, "epoch": 0.2926829268292683, "percentage": 4.18, "elapsed_time": "0:06:49", "remaining_time": "2:36:28"} +{"current_steps": 65, "total_steps": 1435, "loss": 0.4878, "lr": 1.7777777777777777e-05, "epoch": 0.3170731707317073, "percentage": 4.53, "elapsed_time": "0:07:22", "remaining_time": "2:35:26"} +{"current_steps": 70, "total_steps": 1435, "loss": 0.4473, "lr": 1.916666666666667e-05, "epoch": 0.34146341463414637, "percentage": 4.88, "elapsed_time": "0:07:56", "remaining_time": "2:34:53"} +{"current_steps": 75, "total_steps": 1435, "loss": 0.4557, "lr": 2.0555555555555555e-05, "epoch": 0.36585365853658536, "percentage": 5.23, "elapsed_time": "0:08:25", "remaining_time": "2:32:51"} +{"current_steps": 80, "total_steps": 1435, "loss": 0.46, "lr": 2.194444444444445e-05, "epoch": 0.3902439024390244, "percentage": 5.57, "elapsed_time": "0:08:57", "remaining_time": "2:31:36"} +{"current_steps": 85, "total_steps": 1435, "loss": 0.4682, "lr": 2.3333333333333336e-05, "epoch": 0.4146341463414634, "percentage": 5.92, "elapsed_time": "0:09:34", "remaining_time": "2:32:01"} +{"current_steps": 90, "total_steps": 1435, "loss": 0.4455, "lr": 2.4722222222222226e-05, "epoch": 0.43902439024390244, "percentage": 6.27, "elapsed_time": "0:10:07", "remaining_time": "2:31:23"} +{"current_steps": 95, "total_steps": 1435, "loss": 0.4531, "lr": 2.6111111111111114e-05, "epoch": 0.4634146341463415, "percentage": 6.62, "elapsed_time": "0:10:42", "remaining_time": "2:31:01"} +{"current_steps": 100, "total_steps": 1435, "loss": 0.4494, "lr": 2.75e-05, "epoch": 0.4878048780487805, "percentage": 6.97, "elapsed_time": "0:11:11", "remaining_time": "2:29:28"} +{"current_steps": 105, "total_steps": 1435, "loss": 0.418, "lr": 2.888888888888889e-05, "epoch": 0.5121951219512195, "percentage": 7.32, "elapsed_time": "0:11:44", "remaining_time": "2:28:43"} +{"current_steps": 110, "total_steps": 1435, "loss": 0.4421, "lr": 3.027777777777778e-05, "epoch": 0.5365853658536586, "percentage": 7.67, "elapsed_time": "0:12:16", "remaining_time": "2:27:57"} +{"current_steps": 115, "total_steps": 1435, "loss": 0.4504, "lr": 3.1666666666666666e-05, "epoch": 0.5609756097560976, "percentage": 8.01, "elapsed_time": "0:12:49", "remaining_time": "2:27:10"} +{"current_steps": 120, "total_steps": 1435, "loss": 0.4249, "lr": 3.3055555555555553e-05, "epoch": 0.5853658536585366, "percentage": 8.36, "elapsed_time": "0:13:26", "remaining_time": "2:27:19"} +{"current_steps": 125, "total_steps": 1435, "loss": 0.4417, "lr": 3.444444444444445e-05, "epoch": 0.6097560975609756, "percentage": 8.71, "elapsed_time": "0:13:51", "remaining_time": "2:25:17"} +{"current_steps": 130, "total_steps": 1435, "loss": 0.4383, "lr": 3.5833333333333335e-05, "epoch": 0.6341463414634146, "percentage": 9.06, "elapsed_time": "0:14:23", "remaining_time": "2:24:24"} +{"current_steps": 135, "total_steps": 1435, "loss": 0.4266, "lr": 3.722222222222223e-05, "epoch": 0.6585365853658537, "percentage": 9.41, "elapsed_time": "0:14:56", "remaining_time": "2:23:49"} +{"current_steps": 140, "total_steps": 1435, "loss": 0.4089, "lr": 3.8611111111111116e-05, "epoch": 0.6829268292682927, "percentage": 9.76, "elapsed_time": "0:15:27", "remaining_time": "2:23:02"} +{"current_steps": 145, "total_steps": 1435, "loss": 0.4009, "lr": 4e-05, "epoch": 0.7073170731707317, "percentage": 10.1, "elapsed_time": "0:15:59", "remaining_time": "2:22:16"} +{"current_steps": 150, "total_steps": 1435, "loss": 0.4064, "lr": 3.999851959033532e-05, "epoch": 0.7317073170731707, "percentage": 10.45, "elapsed_time": "0:16:34", "remaining_time": "2:22:00"} +{"current_steps": 155, "total_steps": 1435, "loss": 0.4104, "lr": 3.999407858050255e-05, "epoch": 0.7560975609756098, "percentage": 10.8, "elapsed_time": "0:17:04", "remaining_time": "2:21:01"} +{"current_steps": 160, "total_steps": 1435, "loss": 0.4061, "lr": 3.998667762795307e-05, "epoch": 0.7804878048780488, "percentage": 11.15, "elapsed_time": "0:17:41", "remaining_time": "2:20:58"} +{"current_steps": 165, "total_steps": 1435, "loss": 0.4108, "lr": 3.9976317828331075e-05, "epoch": 0.8048780487804879, "percentage": 11.5, "elapsed_time": "0:18:13", "remaining_time": "2:20:14"} +{"current_steps": 170, "total_steps": 1435, "loss": 0.4148, "lr": 3.9963000715311284e-05, "epoch": 0.8292682926829268, "percentage": 11.85, "elapsed_time": "0:18:47", "remaining_time": "2:19:46"} +{"current_steps": 175, "total_steps": 1435, "loss": 0.4097, "lr": 3.9946728260372e-05, "epoch": 0.8536585365853658, "percentage": 12.2, "elapsed_time": "0:19:22", "remaining_time": "2:19:27"} +{"current_steps": 180, "total_steps": 1435, "loss": 0.4262, "lr": 3.992750287250316e-05, "epoch": 0.8780487804878049, "percentage": 12.54, "elapsed_time": "0:19:51", "remaining_time": "2:18:27"} +{"current_steps": 185, "total_steps": 1435, "loss": 0.4143, "lr": 3.9905327397849776e-05, "epoch": 0.9024390243902439, "percentage": 12.89, "elapsed_time": "0:20:22", "remaining_time": "2:17:43"} +{"current_steps": 190, "total_steps": 1435, "loss": 0.4068, "lr": 3.988020511929055e-05, "epoch": 0.926829268292683, "percentage": 13.24, "elapsed_time": "0:20:55", "remaining_time": "2:17:05"} +{"current_steps": 195, "total_steps": 1435, "loss": 0.4169, "lr": 3.985213975595188e-05, "epoch": 0.9512195121951219, "percentage": 13.59, "elapsed_time": "0:21:26", "remaining_time": "2:16:19"} +{"current_steps": 200, "total_steps": 1435, "loss": 0.4196, "lr": 3.982113546265727e-05, "epoch": 0.975609756097561, "percentage": 13.94, "elapsed_time": "0:22:03", "remaining_time": "2:16:15"} +{"current_steps": 205, "total_steps": 1435, "loss": 0.3994, "lr": 3.978719682931227e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:23:35", "remaining_time": "2:21:33"} +{"current_steps": 210, "total_steps": 1435, "loss": 0.3843, "lr": 3.9750328880224964e-05, "epoch": 1.024390243902439, "percentage": 14.63, "elapsed_time": "0:24:05", "remaining_time": "2:20:29"} +{"current_steps": 215, "total_steps": 1435, "loss": 0.3676, "lr": 3.9710537073362154e-05, "epoch": 1.048780487804878, "percentage": 14.98, "elapsed_time": "0:24:40", "remaining_time": "2:20:02"} +{"current_steps": 220, "total_steps": 1435, "loss": 0.376, "lr": 3.9667827299541405e-05, "epoch": 1.0731707317073171, "percentage": 15.33, "elapsed_time": "0:25:13", "remaining_time": "2:19:20"} +{"current_steps": 225, "total_steps": 1435, "loss": 0.3914, "lr": 3.962220588155889e-05, "epoch": 1.0975609756097562, "percentage": 15.68, "elapsed_time": "0:25:50", "remaining_time": "2:18:55"} +{"current_steps": 230, "total_steps": 1435, "loss": 0.3891, "lr": 3.957367957325344e-05, "epoch": 1.1219512195121952, "percentage": 16.03, "elapsed_time": "0:26:16", "remaining_time": "2:17:38"} +{"current_steps": 235, "total_steps": 1435, "loss": 0.3805, "lr": 3.952225555850662e-05, "epoch": 1.146341463414634, "percentage": 16.38, "elapsed_time": "0:26:54", "remaining_time": "2:17:23"} +{"current_steps": 240, "total_steps": 1435, "loss": 0.4021, "lr": 3.9467941450179276e-05, "epoch": 1.170731707317073, "percentage": 16.72, "elapsed_time": "0:27:22", "remaining_time": "2:16:18"} +{"current_steps": 245, "total_steps": 1435, "loss": 0.3768, "lr": 3.94107452889845e-05, "epoch": 1.1951219512195121, "percentage": 17.07, "elapsed_time": "0:27:55", "remaining_time": "2:15:37"} +{"current_steps": 250, "total_steps": 1435, "loss": 0.3985, "lr": 3.9350675542297273e-05, "epoch": 1.2195121951219512, "percentage": 17.42, "elapsed_time": "0:28:25", "remaining_time": "2:14:45"} +{"current_steps": 255, "total_steps": 1435, "loss": 0.3822, "lr": 3.9287741102900956e-05, "epoch": 1.2439024390243902, "percentage": 17.77, "elapsed_time": "0:29:02", "remaining_time": "2:14:24"} +{"current_steps": 260, "total_steps": 1435, "loss": 0.3531, "lr": 3.922195128767077e-05, "epoch": 1.2682926829268293, "percentage": 18.12, "elapsed_time": "0:29:36", "remaining_time": "2:13:50"} +{"current_steps": 265, "total_steps": 1435, "loss": 0.3768, "lr": 3.915331583619455e-05, "epoch": 1.2926829268292683, "percentage": 18.47, "elapsed_time": "0:30:13", "remaining_time": "2:13:25"} +{"current_steps": 270, "total_steps": 1435, "loss": 0.3667, "lr": 3.908184490933087e-05, "epoch": 1.3170731707317074, "percentage": 18.82, "elapsed_time": "0:30:45", "remaining_time": "2:12:42"} +{"current_steps": 275, "total_steps": 1435, "loss": 0.3852, "lr": 3.90075490877048e-05, "epoch": 1.3414634146341464, "percentage": 19.16, "elapsed_time": "0:31:16", "remaining_time": "2:11:54"} +{"current_steps": 280, "total_steps": 1435, "loss": 0.3607, "lr": 3.893043937014161e-05, "epoch": 1.3658536585365852, "percentage": 19.51, "elapsed_time": "0:31:45", "remaining_time": "2:11:01"} +{"current_steps": 285, "total_steps": 1435, "loss": 0.3789, "lr": 3.885052717203839e-05, "epoch": 1.3902439024390243, "percentage": 19.86, "elapsed_time": "0:32:16", "remaining_time": "2:10:14"} +{"current_steps": 290, "total_steps": 1435, "loss": 0.3593, "lr": 3.876782432367419e-05, "epoch": 1.4146341463414633, "percentage": 20.21, "elapsed_time": "0:32:45", "remaining_time": "2:09:20"} +{"current_steps": 295, "total_steps": 1435, "loss": 0.3787, "lr": 3.86823430684586e-05, "epoch": 1.4390243902439024, "percentage": 20.56, "elapsed_time": "0:33:23", "remaining_time": "2:09:00"} +{"current_steps": 300, "total_steps": 1435, "loss": 0.3935, "lr": 3.859409606111927e-05, "epoch": 1.4634146341463414, "percentage": 20.91, "elapsed_time": "0:33:56", "remaining_time": "2:08:25"} +{"current_steps": 305, "total_steps": 1435, "loss": 0.3699, "lr": 3.850309636582844e-05, "epoch": 1.4878048780487805, "percentage": 21.25, "elapsed_time": "0:34:30", "remaining_time": "2:07:52"} +{"current_steps": 310, "total_steps": 1435, "loss": 0.3777, "lr": 3.8409357454268954e-05, "epoch": 1.5121951219512195, "percentage": 21.6, "elapsed_time": "0:35:03", "remaining_time": "2:07:12"} +{"current_steps": 315, "total_steps": 1435, "loss": 0.3883, "lr": 3.831289320363988e-05, "epoch": 1.5365853658536586, "percentage": 21.95, "elapsed_time": "0:35:33", "remaining_time": "2:06:24"} +{"current_steps": 320, "total_steps": 1435, "loss": 0.3614, "lr": 3.821371789460211e-05, "epoch": 1.5609756097560976, "percentage": 22.3, "elapsed_time": "0:36:05", "remaining_time": "2:05:45"} +{"current_steps": 325, "total_steps": 1435, "loss": 0.3748, "lr": 3.8111846209164245e-05, "epoch": 1.5853658536585367, "percentage": 22.65, "elapsed_time": "0:36:42", "remaining_time": "2:05:21"} +{"current_steps": 330, "total_steps": 1435, "loss": 0.3763, "lr": 3.800729322850905e-05, "epoch": 1.6097560975609757, "percentage": 23.0, "elapsed_time": "0:37:13", "remaining_time": "2:04:40"} +{"current_steps": 335, "total_steps": 1435, "loss": 0.3838, "lr": 3.790007443076083e-05, "epoch": 1.6341463414634148, "percentage": 23.34, "elapsed_time": "0:37:46", "remaining_time": "2:04:02"} +{"current_steps": 340, "total_steps": 1435, "loss": 0.3559, "lr": 3.779020568869402e-05, "epoch": 1.6585365853658538, "percentage": 23.69, "elapsed_time": "0:38:19", "remaining_time": "2:03:27"} +{"current_steps": 345, "total_steps": 1435, "loss": 0.3816, "lr": 3.767770326738339e-05, "epoch": 1.6829268292682928, "percentage": 24.04, "elapsed_time": "0:38:55", "remaining_time": "2:03:00"} +{"current_steps": 350, "total_steps": 1435, "loss": 0.3735, "lr": 3.7562583821796114e-05, "epoch": 1.7073170731707317, "percentage": 24.39, "elapsed_time": "0:39:31", "remaining_time": "2:02:30"} +{"current_steps": 355, "total_steps": 1435, "loss": 0.3607, "lr": 3.7444864394326186e-05, "epoch": 1.7317073170731707, "percentage": 24.74, "elapsed_time": "0:40:04", "remaining_time": "2:01:54"} +{"current_steps": 360, "total_steps": 1435, "loss": 0.3591, "lr": 3.732456241227141e-05, "epoch": 1.7560975609756098, "percentage": 25.09, "elapsed_time": "0:40:39", "remaining_time": "2:01:24"} +{"current_steps": 365, "total_steps": 1435, "loss": 0.3896, "lr": 3.7201695685253476e-05, "epoch": 1.7804878048780488, "percentage": 25.44, "elapsed_time": "0:41:09", "remaining_time": "2:00:39"} +{"current_steps": 370, "total_steps": 1435, "loss": 0.3927, "lr": 3.7076282402581404e-05, "epoch": 1.8048780487804879, "percentage": 25.78, "elapsed_time": "0:41:41", "remaining_time": "1:59:58"} +{"current_steps": 375, "total_steps": 1435, "loss": 0.3652, "lr": 3.694834113055877e-05, "epoch": 1.8292682926829267, "percentage": 26.13, "elapsed_time": "0:42:14", "remaining_time": "1:59:23"} +{"current_steps": 380, "total_steps": 1435, "loss": 0.3603, "lr": 3.681789080973514e-05, "epoch": 1.8536585365853657, "percentage": 26.48, "elapsed_time": "0:42:42", "remaining_time": "1:58:33"} +{"current_steps": 385, "total_steps": 1435, "loss": 0.3593, "lr": 3.668495075210207e-05, "epoch": 1.8780487804878048, "percentage": 26.83, "elapsed_time": "0:43:19", "remaining_time": "1:58:09"} +{"current_steps": 390, "total_steps": 1435, "loss": 0.3631, "lr": 3.654954063823419e-05, "epoch": 1.9024390243902438, "percentage": 27.18, "elapsed_time": "0:43:53", "remaining_time": "1:57:36"} +{"current_steps": 395, "total_steps": 1435, "loss": 0.3838, "lr": 3.641168051437562e-05, "epoch": 1.9268292682926829, "percentage": 27.53, "elapsed_time": "0:44:21", "remaining_time": "1:56:47"} +{"current_steps": 400, "total_steps": 1435, "loss": 0.3785, "lr": 3.627139078947233e-05, "epoch": 1.951219512195122, "percentage": 27.87, "elapsed_time": "0:44:51", "remaining_time": "1:56:05"} +{"current_steps": 405, "total_steps": 1435, "loss": 0.3547, "lr": 3.6128692232150775e-05, "epoch": 1.975609756097561, "percentage": 28.22, "elapsed_time": "0:46:25", "remaining_time": "1:58:04"} +{"current_steps": 410, "total_steps": 1435, "loss": 0.3574, "lr": 3.598360596764331e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:47:00", "remaining_time": "1:57:30"} +{"current_steps": 415, "total_steps": 1435, "loss": 0.346, "lr": 3.583615347466075e-05, "epoch": 2.024390243902439, "percentage": 28.92, "elapsed_time": "0:47:34", "remaining_time": "1:56:55"} +{"current_steps": 420, "total_steps": 1435, "loss": 0.3131, "lr": 3.568635658221266e-05, "epoch": 2.048780487804878, "percentage": 29.27, "elapsed_time": "0:48:02", "remaining_time": "1:56:06"} +{"current_steps": 425, "total_steps": 1435, "loss": 0.3289, "lr": 3.553423746637577e-05, "epoch": 2.073170731707317, "percentage": 29.62, "elapsed_time": "0:48:35", "remaining_time": "1:55:28"} +{"current_steps": 430, "total_steps": 1435, "loss": 0.3556, "lr": 3.537981864701101e-05, "epoch": 2.097560975609756, "percentage": 29.97, "elapsed_time": "0:49:03", "remaining_time": "1:54:39"} +{"current_steps": 435, "total_steps": 1435, "loss": 0.3533, "lr": 3.5223122984429645e-05, "epoch": 2.1219512195121952, "percentage": 30.31, "elapsed_time": "0:49:36", "remaining_time": "1:54:03"} +{"current_steps": 440, "total_steps": 1435, "loss": 0.3302, "lr": 3.5064173676008994e-05, "epoch": 2.1463414634146343, "percentage": 30.66, "elapsed_time": "0:50:10", "remaining_time": "1:53:28"} +{"current_steps": 445, "total_steps": 1435, "loss": 0.3471, "lr": 3.4902994252758295e-05, "epoch": 2.1707317073170733, "percentage": 31.01, "elapsed_time": "0:50:39", "remaining_time": "1:52:42"} +{"current_steps": 450, "total_steps": 1435, "loss": 0.3171, "lr": 3.473960857583515e-05, "epoch": 2.1951219512195124, "percentage": 31.36, "elapsed_time": "0:51:11", "remaining_time": "1:52:02"} +{"current_steps": 455, "total_steps": 1435, "loss": 0.347, "lr": 3.457404083301308e-05, "epoch": 2.2195121951219514, "percentage": 31.71, "elapsed_time": "0:51:44", "remaining_time": "1:51:26"} +{"current_steps": 460, "total_steps": 1435, "loss": 0.3289, "lr": 3.440631553510074e-05, "epoch": 2.2439024390243905, "percentage": 32.06, "elapsed_time": "0:52:17", "remaining_time": "1:50:51"} +{"current_steps": 465, "total_steps": 1435, "loss": 0.3214, "lr": 3.423645751231334e-05, "epoch": 2.2682926829268295, "percentage": 32.4, "elapsed_time": "0:52:52", "remaining_time": "1:50:17"} +{"current_steps": 470, "total_steps": 1435, "loss": 0.3219, "lr": 3.4064491910596726e-05, "epoch": 2.292682926829268, "percentage": 32.75, "elapsed_time": "0:53:24", "remaining_time": "1:49:38"} +{"current_steps": 475, "total_steps": 1435, "loss": 0.3375, "lr": 3.389044418790478e-05, "epoch": 2.317073170731707, "percentage": 33.1, "elapsed_time": "0:53:54", "remaining_time": "1:48:56"} +{"current_steps": 480, "total_steps": 1435, "loss": 0.337, "lr": 3.371434011043059e-05, "epoch": 2.341463414634146, "percentage": 33.45, "elapsed_time": "0:54:21", "remaining_time": "1:48:08"} +{"current_steps": 485, "total_steps": 1435, "loss": 0.3149, "lr": 3.353620574879197e-05, "epoch": 2.3658536585365852, "percentage": 33.8, "elapsed_time": "0:54:55", "remaining_time": "1:47:34"} +{"current_steps": 490, "total_steps": 1435, "loss": 0.3216, "lr": 3.335606747417199e-05, "epoch": 2.3902439024390243, "percentage": 34.15, "elapsed_time": "0:55:29", "remaining_time": "1:47:01"} +{"current_steps": 495, "total_steps": 1435, "loss": 0.3528, "lr": 3.317395195441492e-05, "epoch": 2.4146341463414633, "percentage": 34.49, "elapsed_time": "0:56:06", "remaining_time": "1:46:33"} +{"current_steps": 500, "total_steps": 1435, "loss": 0.3328, "lr": 3.29898861500783e-05, "epoch": 2.4390243902439024, "percentage": 34.84, "elapsed_time": "0:56:42", "remaining_time": "1:46:02"} +{"current_steps": 505, "total_steps": 1435, "loss": 0.3202, "lr": 3.280389731044172e-05, "epoch": 2.4634146341463414, "percentage": 35.19, "elapsed_time": "0:57:19", "remaining_time": "1:45:34"} +{"current_steps": 510, "total_steps": 1435, "loss": 0.3201, "lr": 3.261601296947274e-05, "epoch": 2.4878048780487805, "percentage": 35.54, "elapsed_time": "0:57:48", "remaining_time": "1:44:50"} +{"current_steps": 515, "total_steps": 1435, "loss": 0.3346, "lr": 3.242626094175078e-05, "epoch": 2.5121951219512195, "percentage": 35.89, "elapsed_time": "0:58:18", "remaining_time": "1:44:09"} +{"current_steps": 520, "total_steps": 1435, "loss": 0.318, "lr": 3.223466931834942e-05, "epoch": 2.5365853658536586, "percentage": 36.24, "elapsed_time": "0:58:54", "remaining_time": "1:43:40"} +{"current_steps": 525, "total_steps": 1435, "loss": 0.336, "lr": 3.204126646267775e-05, "epoch": 2.5609756097560976, "percentage": 36.59, "elapsed_time": "0:59:28", "remaining_time": "1:43:06"} +{"current_steps": 530, "total_steps": 1435, "loss": 0.3356, "lr": 3.184608100628144e-05, "epoch": 2.5853658536585367, "percentage": 36.93, "elapsed_time": "1:00:02", "remaining_time": "1:42:31"} +{"current_steps": 535, "total_steps": 1435, "loss": 0.3355, "lr": 3.1649141844604104e-05, "epoch": 2.6097560975609757, "percentage": 37.28, "elapsed_time": "1:00:34", "remaining_time": "1:41:54"} +{"current_steps": 540, "total_steps": 1435, "loss": 0.3285, "lr": 3.1450478132709564e-05, "epoch": 2.6341463414634148, "percentage": 37.63, "elapsed_time": "1:01:01", "remaining_time": "1:41:09"} +{"current_steps": 545, "total_steps": 1435, "loss": 0.3151, "lr": 3.125011928096573e-05, "epoch": 2.658536585365854, "percentage": 37.98, "elapsed_time": "1:01:34", "remaining_time": "1:40:32"} +{"current_steps": 550, "total_steps": 1435, "loss": 0.3253, "lr": 3.1048094950690666e-05, "epoch": 2.682926829268293, "percentage": 38.33, "elapsed_time": "1:02:10", "remaining_time": "1:40:02"} +{"current_steps": 555, "total_steps": 1435, "loss": 0.3211, "lr": 3.084443504976146e-05, "epoch": 2.7073170731707314, "percentage": 38.68, "elapsed_time": "1:02:46", "remaining_time": "1:39:31"} +{"current_steps": 560, "total_steps": 1435, "loss": 0.3079, "lr": 3.063916972818668e-05, "epoch": 2.7317073170731705, "percentage": 39.02, "elapsed_time": "1:03:13", "remaining_time": "1:38:47"} +{"current_steps": 565, "total_steps": 1435, "loss": 0.3296, "lr": 3.0432329373642932e-05, "epoch": 2.7560975609756095, "percentage": 39.37, "elapsed_time": "1:03:48", "remaining_time": "1:38:15"} +{"current_steps": 570, "total_steps": 1435, "loss": 0.3424, "lr": 3.022394460697619e-05, "epoch": 2.7804878048780486, "percentage": 39.72, "elapsed_time": "1:04:23", "remaining_time": "1:37:42"} +{"current_steps": 575, "total_steps": 1435, "loss": 0.34, "lr": 3.0014046277668717e-05, "epoch": 2.8048780487804876, "percentage": 40.07, "elapsed_time": "1:04:54", "remaining_time": "1:37:04"} +{"current_steps": 580, "total_steps": 1435, "loss": 0.3348, "lr": 2.980266545927203e-05, "epoch": 2.8292682926829267, "percentage": 40.42, "elapsed_time": "1:05:28", "remaining_time": "1:36:30"} +{"current_steps": 585, "total_steps": 1435, "loss": 0.3144, "lr": 2.9589833444806792e-05, "epoch": 2.8536585365853657, "percentage": 40.77, "elapsed_time": "1:05:59", "remaining_time": "1:35:53"} +{"current_steps": 590, "total_steps": 1435, "loss": 0.3305, "lr": 2.9375581742130114e-05, "epoch": 2.8780487804878048, "percentage": 41.11, "elapsed_time": "1:06:35", "remaining_time": "1:35:22"} +{"current_steps": 595, "total_steps": 1435, "loss": 0.3246, "lr": 2.9159942069271134e-05, "epoch": 2.902439024390244, "percentage": 41.46, "elapsed_time": "1:07:10", "remaining_time": "1:34:50"} +{"current_steps": 600, "total_steps": 1435, "loss": 0.3389, "lr": 2.8942946349735418e-05, "epoch": 2.926829268292683, "percentage": 41.81, "elapsed_time": "1:07:35", "remaining_time": "1:34:04"} +{"current_steps": 605, "total_steps": 1435, "loss": 0.3444, "lr": 2.872462670777902e-05, "epoch": 2.951219512195122, "percentage": 42.16, "elapsed_time": "1:09:04", "remaining_time": "1:34:46"} +{"current_steps": 610, "total_steps": 1435, "loss": 0.3298, "lr": 2.850501546365272e-05, "epoch": 2.975609756097561, "percentage": 42.51, "elapsed_time": "1:09:37", "remaining_time": "1:34:09"} +{"current_steps": 615, "total_steps": 1435, "loss": 0.3203, "lr": 2.8284145128817356e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "1:10:07", "remaining_time": "1:33:30"} +{"current_steps": 620, "total_steps": 1435, "loss": 0.2882, "lr": 2.8062048401130756e-05, "epoch": 3.024390243902439, "percentage": 43.21, "elapsed_time": "1:10:43", "remaining_time": "1:32:58"} +{"current_steps": 625, "total_steps": 1435, "loss": 0.2966, "lr": 2.7838758160007143e-05, "epoch": 3.048780487804878, "percentage": 43.55, "elapsed_time": "1:11:24", "remaining_time": "1:32:32"} +{"current_steps": 630, "total_steps": 1435, "loss": 0.2901, "lr": 2.7614307461549608e-05, "epoch": 3.073170731707317, "percentage": 43.9, "elapsed_time": "1:11:56", "remaining_time": "1:31:55"} +{"current_steps": 635, "total_steps": 1435, "loss": 0.3045, "lr": 2.7388729533656486e-05, "epoch": 3.097560975609756, "percentage": 44.25, "elapsed_time": "1:12:25", "remaining_time": "1:31:14"} +{"current_steps": 640, "total_steps": 1435, "loss": 0.2904, "lr": 2.716205777110222e-05, "epoch": 3.1219512195121952, "percentage": 44.6, "elapsed_time": "1:13:02", "remaining_time": "1:30:44"} +{"current_steps": 645, "total_steps": 1435, "loss": 0.3019, "lr": 2.693432573059362e-05, "epoch": 3.1463414634146343, "percentage": 44.95, "elapsed_time": "1:13:26", "remaining_time": "1:29:57"} +{"current_steps": 650, "total_steps": 1435, "loss": 0.3081, "lr": 2.6705567125802062e-05, "epoch": 3.1707317073170733, "percentage": 45.3, "elapsed_time": "1:13:54", "remaining_time": "1:29:15"} +{"current_steps": 655, "total_steps": 1435, "loss": 0.2962, "lr": 2.6475815822372477e-05, "epoch": 3.1951219512195124, "percentage": 45.64, "elapsed_time": "1:14:26", "remaining_time": "1:28:39"} +{"current_steps": 660, "total_steps": 1435, "loss": 0.3042, "lr": 2.624510583290988e-05, "epoch": 3.2195121951219514, "percentage": 45.99, "elapsed_time": "1:15:03", "remaining_time": "1:28:08"} +{"current_steps": 665, "total_steps": 1435, "loss": 0.2824, "lr": 2.601347131194408e-05, "epoch": 3.2439024390243905, "percentage": 46.34, "elapsed_time": "1:15:40", "remaining_time": "1:27:37"} +{"current_steps": 670, "total_steps": 1435, "loss": 0.2887, "lr": 2.578094655087343e-05, "epoch": 3.2682926829268295, "percentage": 46.69, "elapsed_time": "1:16:16", "remaining_time": "1:27:05"} +{"current_steps": 675, "total_steps": 1435, "loss": 0.2758, "lr": 2.5547565972888287e-05, "epoch": 3.292682926829268, "percentage": 47.04, "elapsed_time": "1:16:52", "remaining_time": "1:26:33"} +{"current_steps": 680, "total_steps": 1435, "loss": 0.2936, "lr": 2.5313364127874974e-05, "epoch": 3.317073170731707, "percentage": 47.39, "elapsed_time": "1:17:25", "remaining_time": "1:25:58"} +{"current_steps": 685, "total_steps": 1435, "loss": 0.289, "lr": 2.507837568730097e-05, "epoch": 3.341463414634146, "percentage": 47.74, "elapsed_time": "1:17:59", "remaining_time": "1:25:23"} +{"current_steps": 690, "total_steps": 1435, "loss": 0.3008, "lr": 2.484263543908213e-05, "epoch": 3.3658536585365852, "percentage": 48.08, "elapsed_time": "1:18:26", "remaining_time": "1:24:41"} +{"current_steps": 695, "total_steps": 1435, "loss": 0.2919, "lr": 2.460617828243263e-05, "epoch": 3.3902439024390243, "percentage": 48.43, "elapsed_time": "1:18:56", "remaining_time": "1:24:03"} +{"current_steps": 700, "total_steps": 1435, "loss": 0.2898, "lr": 2.4369039222698484e-05, "epoch": 3.4146341463414633, "percentage": 48.78, "elapsed_time": "1:19:26", "remaining_time": "1:23:24"} +{"current_steps": 705, "total_steps": 1435, "loss": 0.3052, "lr": 2.413125336617526e-05, "epoch": 3.4390243902439024, "percentage": 49.13, "elapsed_time": "1:19:59", "remaining_time": "1:22:49"} +{"current_steps": 710, "total_steps": 1435, "loss": 0.2925, "lr": 2.3892855914910996e-05, "epoch": 3.4634146341463414, "percentage": 49.48, "elapsed_time": "1:20:31", "remaining_time": "1:22:13"} +{"current_steps": 715, "total_steps": 1435, "loss": 0.2896, "lr": 2.3653882161494758e-05, "epoch": 3.4878048780487805, "percentage": 49.83, "elapsed_time": "1:21:04", "remaining_time": "1:21:38"} +{"current_steps": 720, "total_steps": 1435, "loss": 0.2972, "lr": 2.3414367483831972e-05, "epoch": 3.5121951219512195, "percentage": 50.17, "elapsed_time": "1:21:39", "remaining_time": "1:21:05"} +{"current_steps": 725, "total_steps": 1435, "loss": 0.2909, "lr": 2.3174347339906994e-05, "epoch": 3.5365853658536586, "percentage": 50.52, "elapsed_time": "1:22:09", "remaining_time": "1:20:27"} +{"current_steps": 730, "total_steps": 1435, "loss": 0.2953, "lr": 2.293385726253392e-05, "epoch": 3.5609756097560976, "percentage": 50.87, "elapsed_time": "1:22:37", "remaining_time": "1:19:47"} +{"current_steps": 735, "total_steps": 1435, "loss": 0.2895, "lr": 2.2692932854096218e-05, "epoch": 3.5853658536585367, "percentage": 51.22, "elapsed_time": "1:23:06", "remaining_time": "1:19:09"} +{"current_steps": 740, "total_steps": 1435, "loss": 0.2971, "lr": 2.245160978127616e-05, "epoch": 3.6097560975609757, "percentage": 51.57, "elapsed_time": "1:23:40", "remaining_time": "1:18:35"} +{"current_steps": 745, "total_steps": 1435, "loss": 0.2993, "lr": 2.220992376977468e-05, "epoch": 3.6341463414634148, "percentage": 51.92, "elapsed_time": "1:24:13", "remaining_time": "1:18:00"} +{"current_steps": 750, "total_steps": 1435, "loss": 0.2898, "lr": 2.1967910599022508e-05, "epoch": 3.658536585365854, "percentage": 52.26, "elapsed_time": "1:24:45", "remaining_time": "1:17:24"} +{"current_steps": 755, "total_steps": 1435, "loss": 0.2915, "lr": 2.1725606096883324e-05, "epoch": 3.682926829268293, "percentage": 52.61, "elapsed_time": "1:25:13", "remaining_time": "1:16:45"} +{"current_steps": 760, "total_steps": 1435, "loss": 0.2876, "lr": 2.1483046134349813e-05, "epoch": 3.7073170731707314, "percentage": 52.96, "elapsed_time": "1:25:47", "remaining_time": "1:16:12"} +{"current_steps": 765, "total_steps": 1435, "loss": 0.3112, "lr": 2.1240266620233263e-05, "epoch": 3.7317073170731705, "percentage": 53.31, "elapsed_time": "1:26:16", "remaining_time": "1:15:33"} +{"current_steps": 770, "total_steps": 1435, "loss": 0.2832, "lr": 2.099730349584757e-05, "epoch": 3.7560975609756095, "percentage": 53.66, "elapsed_time": "1:26:49", "remaining_time": "1:14:59"} +{"current_steps": 775, "total_steps": 1435, "loss": 0.2996, "lr": 2.0754192729688496e-05, "epoch": 3.7804878048780486, "percentage": 54.01, "elapsed_time": "1:27:14", "remaining_time": "1:14:18"} +{"current_steps": 780, "total_steps": 1435, "loss": 0.2893, "lr": 2.0510970312108804e-05, "epoch": 3.8048780487804876, "percentage": 54.36, "elapsed_time": "1:27:51", "remaining_time": "1:13:46"} +{"current_steps": 785, "total_steps": 1435, "loss": 0.3032, "lr": 2.026767224999028e-05, "epoch": 3.8292682926829267, "percentage": 54.7, "elapsed_time": "1:28:28", "remaining_time": "1:13:15"} +{"current_steps": 790, "total_steps": 1435, "loss": 0.2907, "lr": 2.0024334561413167e-05, "epoch": 3.8536585365853657, "percentage": 55.05, "elapsed_time": "1:29:01", "remaining_time": "1:12:40"} +{"current_steps": 795, "total_steps": 1435, "loss": 0.2978, "lr": 1.9780993270324063e-05, "epoch": 3.8780487804878048, "percentage": 55.4, "elapsed_time": "1:29:34", "remaining_time": "1:12:06"} +{"current_steps": 800, "total_steps": 1435, "loss": 0.3073, "lr": 1.953768440120289e-05, "epoch": 3.902439024390244, "percentage": 55.75, "elapsed_time": "1:30:08", "remaining_time": "1:11:32"} +{"current_steps": 805, "total_steps": 1435, "loss": 0.296, "lr": 1.9294443973729768e-05, "epoch": 3.926829268292683, "percentage": 56.1, "elapsed_time": "1:31:40", "remaining_time": "1:11:44"} +{"current_steps": 810, "total_steps": 1435, "loss": 0.2969, "lr": 1.905130799745268e-05, "epoch": 3.951219512195122, "percentage": 56.45, "elapsed_time": "1:32:10", "remaining_time": "1:11:07"} +{"current_steps": 815, "total_steps": 1435, "loss": 0.2856, "lr": 1.8808312466456525e-05, "epoch": 3.975609756097561, "percentage": 56.79, "elapsed_time": "1:32:39", "remaining_time": "1:10:29"} +{"current_steps": 820, "total_steps": 1435, "loss": 0.2977, "lr": 1.856549335403457e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:33:15", "remaining_time": "1:09:56"} +{"current_steps": 825, "total_steps": 1435, "loss": 0.2709, "lr": 1.832288660736288e-05, "epoch": 4.024390243902439, "percentage": 57.49, "elapsed_time": "1:33:48", "remaining_time": "1:09:21"} +{"current_steps": 830, "total_steps": 1435, "loss": 0.2656, "lr": 1.808052814217871e-05, "epoch": 4.048780487804878, "percentage": 57.84, "elapsed_time": "1:34:17", "remaining_time": "1:08:44"} +{"current_steps": 835, "total_steps": 1435, "loss": 0.2833, "lr": 1.7838453837463498e-05, "epoch": 4.073170731707317, "percentage": 58.19, "elapsed_time": "1:34:49", "remaining_time": "1:08:08"} +{"current_steps": 840, "total_steps": 1435, "loss": 0.2617, "lr": 1.7596699530131234e-05, "epoch": 4.097560975609756, "percentage": 58.54, "elapsed_time": "1:35:25", "remaining_time": "1:07:35"} +{"current_steps": 845, "total_steps": 1435, "loss": 0.2681, "lr": 1.735530100972326e-05, "epoch": 4.121951219512195, "percentage": 58.89, "elapsed_time": "1:36:01", "remaining_time": "1:07:02"} +{"current_steps": 850, "total_steps": 1435, "loss": 0.2808, "lr": 1.711429401310981e-05, "epoch": 4.146341463414634, "percentage": 59.23, "elapsed_time": "1:36:29", "remaining_time": "1:06:24"} +{"current_steps": 855, "total_steps": 1435, "loss": 0.2702, "lr": 1.687371421919961e-05, "epoch": 4.170731707317073, "percentage": 59.58, "elapsed_time": "1:36:59", "remaining_time": "1:05:47"} +{"current_steps": 860, "total_steps": 1435, "loss": 0.283, "lr": 1.6633597243657855e-05, "epoch": 4.195121951219512, "percentage": 59.93, "elapsed_time": "1:37:29", "remaining_time": "1:05:11"} +{"current_steps": 865, "total_steps": 1435, "loss": 0.2692, "lr": 1.6393978633633668e-05, "epoch": 4.219512195121951, "percentage": 60.28, "elapsed_time": "1:38:01", "remaining_time": "1:04:35"} +{"current_steps": 870, "total_steps": 1435, "loss": 0.2949, "lr": 1.6154893862497673e-05, "epoch": 4.2439024390243905, "percentage": 60.63, "elapsed_time": "1:38:31", "remaining_time": "1:03:58"} +{"current_steps": 875, "total_steps": 1435, "loss": 0.2598, "lr": 1.5916378324590437e-05, "epoch": 4.2682926829268295, "percentage": 60.98, "elapsed_time": "1:39:04", "remaining_time": "1:03:24"} +{"current_steps": 880, "total_steps": 1435, "loss": 0.267, "lr": 1.5678467329982717e-05, "epoch": 4.2926829268292686, "percentage": 61.32, "elapsed_time": "1:39:43", "remaining_time": "1:02:53"} +{"current_steps": 885, "total_steps": 1435, "loss": 0.2786, "lr": 1.54411960992481e-05, "epoch": 4.317073170731708, "percentage": 61.67, "elapsed_time": "1:40:11", "remaining_time": "1:02:15"} +{"current_steps": 890, "total_steps": 1435, "loss": 0.2797, "lr": 1.5204599758248884e-05, "epoch": 4.341463414634147, "percentage": 62.02, "elapsed_time": "1:40:35", "remaining_time": "1:01:36"} +{"current_steps": 895, "total_steps": 1435, "loss": 0.2648, "lr": 1.4968713332936063e-05, "epoch": 4.365853658536586, "percentage": 62.37, "elapsed_time": "1:41:06", "remaining_time": "1:01:00"} +{"current_steps": 900, "total_steps": 1435, "loss": 0.2589, "lr": 1.473357174416401e-05, "epoch": 4.390243902439025, "percentage": 62.72, "elapsed_time": "1:41:38", "remaining_time": "1:00:24"} +{"current_steps": 905, "total_steps": 1435, "loss": 0.2616, "lr": 1.4499209802520791e-05, "epoch": 4.414634146341464, "percentage": 63.07, "elapsed_time": "1:42:12", "remaining_time": "0:59:51"} +{"current_steps": 910, "total_steps": 1435, "loss": 0.2664, "lr": 1.426566220317474e-05, "epoch": 4.439024390243903, "percentage": 63.41, "elapsed_time": "1:42:45", "remaining_time": "0:59:16"} +{"current_steps": 915, "total_steps": 1435, "loss": 0.2661, "lr": 1.4032963520738183e-05, "epoch": 4.463414634146342, "percentage": 63.76, "elapsed_time": "1:43:17", "remaining_time": "0:58:42"} +{"current_steps": 920, "total_steps": 1435, "loss": 0.2625, "lr": 1.3801148204148983e-05, "epoch": 4.487804878048781, "percentage": 64.11, "elapsed_time": "1:43:47", "remaining_time": "0:58:05"} +{"current_steps": 925, "total_steps": 1435, "loss": 0.2732, "lr": 1.357025057157062e-05, "epoch": 4.512195121951219, "percentage": 64.46, "elapsed_time": "1:44:16", "remaining_time": "0:57:29"} +{"current_steps": 930, "total_steps": 1435, "loss": 0.2593, "lr": 1.3340304805311802e-05, "epoch": 4.536585365853659, "percentage": 64.81, "elapsed_time": "1:44:41", "remaining_time": "0:56:50"} +{"current_steps": 935, "total_steps": 1435, "loss": 0.2576, "lr": 1.3111344946765977e-05, "epoch": 4.560975609756097, "percentage": 65.16, "elapsed_time": "1:45:14", "remaining_time": "0:56:16"} +{"current_steps": 940, "total_steps": 1435, "loss": 0.276, "lr": 1.2883404891371907e-05, "epoch": 4.585365853658536, "percentage": 65.51, "elapsed_time": "1:45:42", "remaining_time": "0:55:39"} +{"current_steps": 945, "total_steps": 1435, "loss": 0.2621, "lr": 1.2656518383595681e-05, "epoch": 4.609756097560975, "percentage": 65.85, "elapsed_time": "1:46:21", "remaining_time": "0:55:08"} +{"current_steps": 950, "total_steps": 1435, "loss": 0.2676, "lr": 1.243071901193519e-05, "epoch": 4.634146341463414, "percentage": 66.2, "elapsed_time": "1:46:55", "remaining_time": "0:54:35"} +{"current_steps": 955, "total_steps": 1435, "loss": 0.2661, "lr": 1.2206040203947645e-05, "epoch": 4.658536585365853, "percentage": 66.55, "elapsed_time": "1:47:28", "remaining_time": "0:54:00"} +{"current_steps": 960, "total_steps": 1435, "loss": 0.2624, "lr": 1.1982515221300917e-05, "epoch": 4.682926829268292, "percentage": 66.9, "elapsed_time": "1:48:05", "remaining_time": "0:53:28"} +{"current_steps": 965, "total_steps": 1435, "loss": 0.2558, "lr": 1.1760177154849473e-05, "epoch": 4.7073170731707314, "percentage": 67.25, "elapsed_time": "1:48:32", "remaining_time": "0:52:51"} +{"current_steps": 970, "total_steps": 1435, "loss": 0.2636, "lr": 1.1539058919735557e-05, "epoch": 4.7317073170731705, "percentage": 67.6, "elapsed_time": "1:49:00", "remaining_time": "0:52:15"} +{"current_steps": 975, "total_steps": 1435, "loss": 0.2684, "lr": 1.1319193250516387e-05, "epoch": 4.7560975609756095, "percentage": 67.94, "elapsed_time": "1:49:31", "remaining_time": "0:51:40"} +{"current_steps": 980, "total_steps": 1435, "loss": 0.2707, "lr": 1.1100612696318143e-05, "epoch": 4.780487804878049, "percentage": 68.29, "elapsed_time": "1:50:02", "remaining_time": "0:51:05"} +{"current_steps": 985, "total_steps": 1435, "loss": 0.2746, "lr": 1.0883349616017312e-05, "epoch": 4.804878048780488, "percentage": 68.64, "elapsed_time": "1:50:40", "remaining_time": "0:50:33"} +{"current_steps": 990, "total_steps": 1435, "loss": 0.2476, "lr": 1.0667436173450278e-05, "epoch": 4.829268292682927, "percentage": 68.99, "elapsed_time": "1:51:12", "remaining_time": "0:49:59"} +{"current_steps": 995, "total_steps": 1435, "loss": 0.2621, "lr": 1.0452904332651745e-05, "epoch": 4.853658536585366, "percentage": 69.34, "elapsed_time": "1:51:47", "remaining_time": "0:49:26"} +{"current_steps": 1000, "total_steps": 1435, "loss": 0.265, "lr": 1.0239785853122784e-05, "epoch": 4.878048780487805, "percentage": 69.69, "elapsed_time": "1:52:26", "remaining_time": "0:48:54"} +{"current_steps": 1005, "total_steps": 1435, "loss": 0.2654, "lr": 1.0028112285129058e-05, "epoch": 4.902439024390244, "percentage": 70.03, "elapsed_time": "1:54:15", "remaining_time": "0:48:53"} +{"current_steps": 1010, "total_steps": 1435, "loss": 0.2616, "lr": 9.81791496503015e-06, "epoch": 4.926829268292683, "percentage": 70.38, "elapsed_time": "1:54:46", "remaining_time": "0:48:17"} +{"current_steps": 1015, "total_steps": 1435, "loss": 0.2582, "lr": 9.60922501064049e-06, "epoch": 4.951219512195122, "percentage": 70.73, "elapsed_time": "1:55:17", "remaining_time": "0:47:42"} +{"current_steps": 1020, "total_steps": 1435, "loss": 0.2536, "lr": 9.402073316622609e-06, "epoch": 4.975609756097561, "percentage": 71.08, "elapsed_time": "1:55:52", "remaining_time": "0:47:08"} +{"current_steps": 1025, "total_steps": 1435, "loss": 0.2622, "lr": 9.196490549913486e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:56:22", "remaining_time": "0:46:33"} +{"current_steps": 1030, "total_steps": 1435, "loss": 0.2405, "lr": 8.992507145184613e-06, "epoch": 5.024390243902439, "percentage": 71.78, "elapsed_time": "1:56:56", "remaining_time": "0:45:59"} +{"current_steps": 1035, "total_steps": 1435, "loss": 0.2438, "lr": 8.79015330033635e-06, "epoch": 5.048780487804878, "percentage": 72.13, "elapsed_time": "1:57:27", "remaining_time": "0:45:23"} +{"current_steps": 1040, "total_steps": 1435, "loss": 0.2436, "lr": 8.589458972027483e-06, "epoch": 5.073170731707317, "percentage": 72.47, "elapsed_time": "1:58:01", "remaining_time": "0:44:49"} +{"current_steps": 1045, "total_steps": 1435, "loss": 0.2453, "lr": 8.390453871240307e-06, "epoch": 5.097560975609756, "percentage": 72.82, "elapsed_time": "1:58:26", "remaining_time": "0:44:12"} +{"current_steps": 1050, "total_steps": 1435, "loss": 0.2446, "lr": 8.193167458882292e-06, "epoch": 5.121951219512195, "percentage": 73.17, "elapsed_time": "1:58:59", "remaining_time": "0:43:37"} +{"current_steps": 1055, "total_steps": 1435, "loss": 0.2452, "lr": 7.9976289414246e-06, "epoch": 5.146341463414634, "percentage": 73.52, "elapsed_time": "1:59:31", "remaining_time": "0:43:02"} +{"current_steps": 1060, "total_steps": 1435, "loss": 0.2373, "lr": 7.803867266578329e-06, "epoch": 5.170731707317073, "percentage": 73.87, "elapsed_time": "2:00:03", "remaining_time": "0:42:28"} +{"current_steps": 1065, "total_steps": 1435, "loss": 0.2536, "lr": 7.611911119009092e-06, "epoch": 5.195121951219512, "percentage": 74.22, "elapsed_time": "2:00:38", "remaining_time": "0:41:54"} +{"current_steps": 1070, "total_steps": 1435, "loss": 0.2544, "lr": 7.4217889160904824e-06, "epoch": 5.219512195121951, "percentage": 74.56, "elapsed_time": "2:01:09", "remaining_time": "0:41:19"} +{"current_steps": 1075, "total_steps": 1435, "loss": 0.2452, "lr": 7.233528803697185e-06, "epoch": 5.2439024390243905, "percentage": 74.91, "elapsed_time": "2:01:40", "remaining_time": "0:40:44"} +{"current_steps": 1080, "total_steps": 1435, "loss": 0.2497, "lr": 7.0471586520381796e-06, "epoch": 5.2682926829268295, "percentage": 75.26, "elapsed_time": "2:02:13", "remaining_time": "0:40:10"} +{"current_steps": 1085, "total_steps": 1435, "loss": 0.2494, "lr": 6.8627060515308275e-06, "epoch": 5.2926829268292686, "percentage": 75.61, "elapsed_time": "2:02:45", "remaining_time": "0:39:35"} +{"current_steps": 1090, "total_steps": 1435, "loss": 0.2514, "lr": 6.6801983087163944e-06, "epoch": 5.317073170731708, "percentage": 75.96, "elapsed_time": "2:03:17", "remaining_time": "0:39:01"} +{"current_steps": 1095, "total_steps": 1435, "loss": 0.2406, "lr": 6.499662442217496e-06, "epoch": 5.341463414634147, "percentage": 76.31, "elapsed_time": "2:03:52", "remaining_time": "0:38:27"} +{"current_steps": 1100, "total_steps": 1435, "loss": 0.2506, "lr": 6.3211251787383146e-06, "epoch": 5.365853658536586, "percentage": 76.66, "elapsed_time": "2:04:25", "remaining_time": "0:37:53"} +{"current_steps": 1105, "total_steps": 1435, "loss": 0.2786, "lr": 6.144612949107858e-06, "epoch": 5.390243902439025, "percentage": 77.0, "elapsed_time": "2:04:57", "remaining_time": "0:37:18"} +{"current_steps": 1110, "total_steps": 1435, "loss": 0.2648, "lr": 5.970151884367206e-06, "epoch": 5.414634146341464, "percentage": 77.35, "elapsed_time": "2:05:23", "remaining_time": "0:36:42"} +{"current_steps": 1115, "total_steps": 1435, "loss": 0.2537, "lr": 5.7977678119010025e-06, "epoch": 5.439024390243903, "percentage": 77.7, "elapsed_time": "2:05:59", "remaining_time": "0:36:09"} +{"current_steps": 1120, "total_steps": 1435, "loss": 0.2409, "lr": 5.627486251613934e-06, "epoch": 5.463414634146342, "percentage": 78.05, "elapsed_time": "2:06:27", "remaining_time": "0:35:33"} +{"current_steps": 1125, "total_steps": 1435, "loss": 0.2649, "lr": 5.4593324121527554e-06, "epoch": 5.487804878048781, "percentage": 78.4, "elapsed_time": "2:06:59", "remaining_time": "0:34:59"} +{"current_steps": 1130, "total_steps": 1435, "loss": 0.252, "lr": 5.293331187174369e-06, "epoch": 5.512195121951219, "percentage": 78.75, "elapsed_time": "2:07:26", "remaining_time": "0:34:23"} +{"current_steps": 1135, "total_steps": 1435, "loss": 0.2579, "lr": 5.129507151660566e-06, "epoch": 5.536585365853659, "percentage": 79.09, "elapsed_time": "2:07:57", "remaining_time": "0:33:49"} +{"current_steps": 1140, "total_steps": 1435, "loss": 0.2434, "lr": 4.967884558279894e-06, "epoch": 5.560975609756097, "percentage": 79.44, "elapsed_time": "2:08:36", "remaining_time": "0:33:16"} +{"current_steps": 1145, "total_steps": 1435, "loss": 0.2543, "lr": 4.808487333797272e-06, "epoch": 5.585365853658536, "percentage": 79.79, "elapsed_time": "2:09:02", "remaining_time": "0:32:40"} +{"current_steps": 1150, "total_steps": 1435, "loss": 0.2622, "lr": 4.651339075531873e-06, "epoch": 5.609756097560975, "percentage": 80.14, "elapsed_time": "2:09:38", "remaining_time": "0:32:07"} +{"current_steps": 1155, "total_steps": 1435, "loss": 0.248, "lr": 4.496463047863728e-06, "epoch": 5.634146341463414, "percentage": 80.49, "elapsed_time": "2:10:11", "remaining_time": "0:31:33"} +{"current_steps": 1160, "total_steps": 1435, "loss": 0.2457, "lr": 4.343882178789649e-06, "epoch": 5.658536585365853, "percentage": 80.84, "elapsed_time": "2:10:43", "remaining_time": "0:30:59"} +{"current_steps": 1165, "total_steps": 1435, "loss": 0.2536, "lr": 4.193619056528968e-06, "epoch": 5.682926829268292, "percentage": 81.18, "elapsed_time": "2:11:15", "remaining_time": "0:30:25"} +{"current_steps": 1170, "total_steps": 1435, "loss": 0.2331, "lr": 4.045695926179518e-06, "epoch": 5.7073170731707314, "percentage": 81.53, "elapsed_time": "2:11:45", "remaining_time": "0:29:50"} +{"current_steps": 1175, "total_steps": 1435, "loss": 0.2461, "lr": 3.900134686424497e-06, "epoch": 5.7317073170731705, "percentage": 81.88, "elapsed_time": "2:12:18", "remaining_time": "0:29:16"} +{"current_steps": 1180, "total_steps": 1435, "loss": 0.2532, "lr": 3.756956886290497e-06, "epoch": 5.7560975609756095, "percentage": 82.23, "elapsed_time": "2:12:52", "remaining_time": "0:28:42"} +{"current_steps": 1185, "total_steps": 1435, "loss": 0.244, "lr": 3.6161837219574423e-06, "epoch": 5.780487804878049, "percentage": 82.58, "elapsed_time": "2:13:28", "remaining_time": "0:28:09"} +{"current_steps": 1190, "total_steps": 1435, "loss": 0.2452, "lr": 3.477836033620623e-06, "epoch": 5.804878048780488, "percentage": 82.93, "elapsed_time": "2:14:01", "remaining_time": "0:27:35"} +{"current_steps": 1195, "total_steps": 1435, "loss": 0.2456, "lr": 3.3419343024055385e-06, "epoch": 5.829268292682927, "percentage": 83.28, "elapsed_time": "2:14:36", "remaining_time": "0:27:02"} +{"current_steps": 1200, "total_steps": 1435, "loss": 0.2436, "lr": 3.208498647335818e-06, "epoch": 5.853658536585366, "percentage": 83.62, "elapsed_time": "2:15:10", "remaining_time": "0:26:28"} +{"current_steps": 1205, "total_steps": 1435, "loss": 0.2497, "lr": 3.0775488223547946e-06, "epoch": 5.878048780487805, "percentage": 83.97, "elapsed_time": "2:16:41", "remaining_time": "0:26:05"} +{"current_steps": 1210, "total_steps": 1435, "loss": 0.2358, "lr": 2.949104213401126e-06, "epoch": 5.902439024390244, "percentage": 84.32, "elapsed_time": "2:17:18", "remaining_time": "0:25:31"} +{"current_steps": 1215, "total_steps": 1435, "loss": 0.2607, "lr": 2.8231838355388564e-06, "epoch": 5.926829268292683, "percentage": 84.67, "elapsed_time": "2:17:47", "remaining_time": "0:24:56"} +{"current_steps": 1220, "total_steps": 1435, "loss": 0.2592, "lr": 2.6998063301424183e-06, "epoch": 5.951219512195122, "percentage": 85.02, "elapsed_time": "2:18:15", "remaining_time": "0:24:21"} +{"current_steps": 1225, "total_steps": 1435, "loss": 0.2397, "lr": 2.5789899621369576e-06, "epoch": 5.975609756097561, "percentage": 85.37, "elapsed_time": "2:18:47", "remaining_time": "0:23:47"} +{"current_steps": 1230, "total_steps": 1435, "loss": 0.2363, "lr": 2.4607526172943573e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:19:24", "remaining_time": "0:23:14"} +{"current_steps": 1235, "total_steps": 1435, "loss": 0.231, "lr": 2.345111799585418e-06, "epoch": 6.024390243902439, "percentage": 86.06, "elapsed_time": "2:20:00", "remaining_time": "0:22:40"} +{"current_steps": 1240, "total_steps": 1435, "loss": 0.2403, "lr": 2.2320846285885536e-06, "epoch": 6.048780487804878, "percentage": 86.41, "elapsed_time": "2:20:30", "remaining_time": "0:22:05"} +{"current_steps": 1245, "total_steps": 1435, "loss": 0.2407, "lr": 2.1216878369554018e-06, "epoch": 6.073170731707317, "percentage": 86.76, "elapsed_time": "2:21:06", "remaining_time": "0:21:32"} +{"current_steps": 1250, "total_steps": 1435, "loss": 0.2312, "lr": 2.0139377679336914e-06, "epoch": 6.097560975609756, "percentage": 87.11, "elapsed_time": "2:21:37", "remaining_time": "0:20:57"} +{"current_steps": 1255, "total_steps": 1435, "loss": 0.2404, "lr": 1.908850372947775e-06, "epoch": 6.121951219512195, "percentage": 87.46, "elapsed_time": "2:22:14", "remaining_time": "0:20:24"} +{"current_steps": 1260, "total_steps": 1435, "loss": 0.2417, "lr": 1.8064412092371687e-06, "epoch": 6.146341463414634, "percentage": 87.8, "elapsed_time": "2:22:45", "remaining_time": "0:19:49"} +{"current_steps": 1265, "total_steps": 1435, "loss": 0.2408, "lr": 1.7067254375534426e-06, "epoch": 6.170731707317073, "percentage": 88.15, "elapsed_time": "2:23:15", "remaining_time": "0:19:15"} +{"current_steps": 1270, "total_steps": 1435, "loss": 0.2446, "lr": 1.6097178199158147e-06, "epoch": 6.195121951219512, "percentage": 88.5, "elapsed_time": "2:23:50", "remaining_time": "0:18:41"} +{"current_steps": 1275, "total_steps": 1435, "loss": 0.2331, "lr": 1.5154327174257487e-06, "epoch": 6.219512195121951, "percentage": 88.85, "elapsed_time": "2:24:18", "remaining_time": "0:18:06"} +{"current_steps": 1280, "total_steps": 1435, "loss": 0.2454, "lr": 1.4238840881409411e-06, "epoch": 6.2439024390243905, "percentage": 89.2, "elapsed_time": "2:24:56", "remaining_time": "0:17:33"} +{"current_steps": 1285, "total_steps": 1435, "loss": 0.2436, "lr": 1.3350854850089556e-06, "epoch": 6.2682926829268295, "percentage": 89.55, "elapsed_time": "2:25:27", "remaining_time": "0:16:58"} +{"current_steps": 1290, "total_steps": 1435, "loss": 0.2494, "lr": 1.2490500538608186e-06, "epoch": 6.2926829268292686, "percentage": 89.9, "elapsed_time": "2:25:55", "remaining_time": "0:16:24"} +{"current_steps": 1295, "total_steps": 1435, "loss": 0.2477, "lr": 1.1657905314649054e-06, "epoch": 6.317073170731708, "percentage": 90.24, "elapsed_time": "2:26:27", "remaining_time": "0:15:50"} +{"current_steps": 1300, "total_steps": 1435, "loss": 0.2414, "lr": 1.0853192436413761e-06, "epoch": 6.341463414634147, "percentage": 90.59, "elapsed_time": "2:26:57", "remaining_time": "0:15:15"} +{"current_steps": 1305, "total_steps": 1435, "loss": 0.2386, "lr": 1.0076481034374597e-06, "epoch": 6.365853658536586, "percentage": 90.94, "elapsed_time": "2:27:36", "remaining_time": "0:14:42"} +{"current_steps": 1310, "total_steps": 1435, "loss": 0.2396, "lr": 9.327886093638217e-07, "epoch": 6.390243902439025, "percentage": 91.29, "elapsed_time": "2:28:12", "remaining_time": "0:14:08"} +{"current_steps": 1315, "total_steps": 1435, "loss": 0.2352, "lr": 8.607518436923024e-07, "epoch": 6.414634146341464, "percentage": 91.64, "elapsed_time": "2:28:43", "remaining_time": "0:13:34"} +{"current_steps": 1320, "total_steps": 1435, "loss": 0.2365, "lr": 7.915484708153221e-07, "epoch": 6.439024390243903, "percentage": 91.99, "elapsed_time": "2:29:14", "remaining_time": "0:13:00"} +{"current_steps": 1325, "total_steps": 1435, "loss": 0.2262, "lr": 7.251887356670795e-07, "epoch": 6.463414634146342, "percentage": 92.33, "elapsed_time": "2:29:48", "remaining_time": "0:12:26"} +{"current_steps": 1330, "total_steps": 1435, "loss": 0.2411, "lr": 6.616824622069029e-07, "epoch": 6.487804878048781, "percentage": 92.68, "elapsed_time": "2:30:21", "remaining_time": "0:11:52"} +{"current_steps": 1335, "total_steps": 1435, "loss": 0.2348, "lr": 6.010390519648956e-07, "epoch": 6.512195121951219, "percentage": 93.03, "elapsed_time": "2:30:56", "remaining_time": "0:11:18"} +{"current_steps": 1340, "total_steps": 1435, "loss": 0.2437, "lr": 5.432674826501116e-07, "epoch": 6.536585365853659, "percentage": 93.38, "elapsed_time": "2:31:28", "remaining_time": "0:10:44"} +{"current_steps": 1345, "total_steps": 1435, "loss": 0.2404, "lr": 4.883763068215142e-07, "epoch": 6.560975609756097, "percentage": 93.73, "elapsed_time": "2:31:58", "remaining_time": "0:10:10"} +{"current_steps": 1350, "total_steps": 1435, "loss": 0.244, "lr": 4.363736506218197e-07, "epoch": 6.585365853658536, "percentage": 94.08, "elapsed_time": "2:32:28", "remaining_time": "0:09:36"} +{"current_steps": 1355, "total_steps": 1435, "loss": 0.2422, "lr": 3.8726721257451137e-07, "epoch": 6.609756097560975, "percentage": 94.43, "elapsed_time": "2:32:59", "remaining_time": "0:09:01"} +{"current_steps": 1360, "total_steps": 1435, "loss": 0.2375, "lr": 3.410642624441352e-07, "epoch": 6.634146341463414, "percentage": 94.77, "elapsed_time": "2:33:29", "remaining_time": "0:08:27"} +{"current_steps": 1365, "total_steps": 1435, "loss": 0.2312, "lr": 2.977716401600894e-07, "epoch": 6.658536585365853, "percentage": 95.12, "elapsed_time": "2:33:56", "remaining_time": "0:07:53"} +{"current_steps": 1370, "total_steps": 1435, "loss": 0.2184, "lr": 2.573957548040107e-07, "epoch": 6.682926829268292, "percentage": 95.47, "elapsed_time": "2:34:28", "remaining_time": "0:07:19"} +{"current_steps": 1375, "total_steps": 1435, "loss": 0.2417, "lr": 2.1994258366099253e-07, "epoch": 6.7073170731707314, "percentage": 95.82, "elapsed_time": "2:34:59", "remaining_time": "0:06:45"} +{"current_steps": 1380, "total_steps": 1435, "loss": 0.2674, "lr": 1.854176713346867e-07, "epoch": 6.7317073170731705, "percentage": 96.17, "elapsed_time": "2:35:28", "remaining_time": "0:06:11"} +{"current_steps": 1385, "total_steps": 1435, "loss": 0.2371, "lr": 1.538261289264842e-07, "epoch": 6.7560975609756095, "percentage": 96.52, "elapsed_time": "2:36:01", "remaining_time": "0:05:37"} +{"current_steps": 1390, "total_steps": 1435, "loss": 0.2609, "lr": 1.2517263327884944e-07, "epoch": 6.780487804878049, "percentage": 96.86, "elapsed_time": "2:36:38", "remaining_time": "0:05:04"} +{"current_steps": 1395, "total_steps": 1435, "loss": 0.2384, "lr": 9.94614262829785e-08, "epoch": 6.804878048780488, "percentage": 97.21, "elapsed_time": "2:37:11", "remaining_time": "0:04:30"} +{"current_steps": 1400, "total_steps": 1435, "loss": 0.2448, "lr": 7.669631425079705e-08, "epoch": 6.829268292682927, "percentage": 97.56, "elapsed_time": "2:37:42", "remaining_time": "0:03:56"} +{"current_steps": 1405, "total_steps": 1435, "loss": 0.235, "lr": 5.6880667351497664e-08, "epoch": 6.853658536585366, "percentage": 97.91, "elapsed_time": "2:39:18", "remaining_time": "0:03:24"} +{"current_steps": 1410, "total_steps": 1435, "loss": 0.2342, "lr": 4.00174191125946e-08, "epoch": 6.878048780487805, "percentage": 98.26, "elapsed_time": "2:39:54", "remaining_time": "0:02:50"} +{"current_steps": 1415, "total_steps": 1435, "loss": 0.2368, "lr": 2.6109065985655547e-08, "epoch": 6.902439024390244, "percentage": 98.61, "elapsed_time": "2:40:26", "remaining_time": "0:02:16"} +{"current_steps": 1420, "total_steps": 1435, "loss": 0.2396, "lr": 1.515766697672172e-08, "epoch": 6.926829268292683, "percentage": 98.95, "elapsed_time": "2:40:54", "remaining_time": "0:01:41"} +{"current_steps": 1425, "total_steps": 1435, "loss": 0.2342, "lr": 7.16484334148504e-09, "epoch": 6.951219512195122, "percentage": 99.3, "elapsed_time": "2:41:26", "remaining_time": "0:01:07"} +{"current_steps": 1430, "total_steps": 1435, "loss": 0.2378, "lr": 2.1317783452823315e-09, "epoch": 6.975609756097561, "percentage": 99.65, "elapsed_time": "2:41:58", "remaining_time": "0:00:33"} +{"current_steps": 1435, "total_steps": 1435, "loss": 0.2521, "lr": 5.921708791767344e-11, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:42:30", "remaining_time": "0:00:00"} +{"current_steps": 1435, "total_steps": 1435, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:43:33", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..61d85a9 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3204 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.0, + "eval_steps": 500, + "global_step": 1435, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.024390243902439025, + "grad_norm": 11.487528759401481, + "learning_rate": 1.111111111111111e-06, + "loss": 0.8361, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.7365100383758545, + "step": 5, + "valid_targets_mean": 3762.9, + "valid_targets_min": 1347 + }, + { + "epoch": 0.04878048780487805, + "grad_norm": 9.475522028864606, + "learning_rate": 2.5e-06, + "loss": 0.8084, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.780247688293457, + "step": 10, + "valid_targets_mean": 4102.0, + "valid_targets_min": 1132 + }, + { + "epoch": 0.07317073170731707, + "grad_norm": 7.04279574223532, + "learning_rate": 3.88888888888889e-06, + "loss": 0.8018, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.8029437065124512, + "step": 15, + "valid_targets_mean": 2743.9, + "valid_targets_min": 1037 + }, + { + "epoch": 0.0975609756097561, + "grad_norm": 3.837408273985971, + "learning_rate": 5.2777777777777785e-06, + "loss": 0.7365, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.7130635380744934, + "step": 20, + "valid_targets_mean": 3803.7, + "valid_targets_min": 1728 + }, + { + "epoch": 0.12195121951219512, + "grad_norm": 2.623752522634304, + "learning_rate": 6.666666666666667e-06, + "loss": 0.6356, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.5704323053359985, + "step": 25, + "valid_targets_mean": 3090.2, + "valid_targets_min": 15 + }, + { + "epoch": 0.14634146341463414, + "grad_norm": 1.5000325065486164, + "learning_rate": 8.055555555555557e-06, + "loss": 0.5786, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.5754331946372986, + "step": 30, + "valid_targets_mean": 2901.2, + "valid_targets_min": 444 + }, + { + "epoch": 0.17073170731707318, + "grad_norm": 1.0195672514305119, + "learning_rate": 9.444444444444445e-06, + "loss": 0.5669, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.5453179478645325, + "step": 35, + "valid_targets_mean": 3570.7, + "valid_targets_min": 1386 + }, + { + "epoch": 0.1951219512195122, + "grad_norm": 0.7667691926950433, + "learning_rate": 1.0833333333333334e-05, + "loss": 0.5178, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4652627110481262, + "step": 40, + "valid_targets_mean": 4426.4, + "valid_targets_min": 1435 + }, + { + "epoch": 0.21951219512195122, + "grad_norm": 0.8476292747424702, + "learning_rate": 1.2222222222222224e-05, + "loss": 0.5122, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4817873239517212, + "step": 45, + "valid_targets_mean": 3324.3, + "valid_targets_min": 973 + }, + { + "epoch": 0.24390243902439024, + "grad_norm": 0.769487975286158, + "learning_rate": 1.3611111111111113e-05, + "loss": 0.5046, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4777624309062958, + "step": 50, + "valid_targets_mean": 3475.6, + "valid_targets_min": 946 + }, + { + "epoch": 0.2682926829268293, + "grad_norm": 0.8003810670887064, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.5042, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4954460859298706, + "step": 55, + "valid_targets_mean": 3635.2, + "valid_targets_min": 1205 + }, + { + "epoch": 0.2926829268292683, + "grad_norm": 0.771135490268948, + "learning_rate": 1.638888888888889e-05, + "loss": 0.4964, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4748877286911011, + "step": 60, + "valid_targets_mean": 3454.8, + "valid_targets_min": 841 + }, + { + "epoch": 0.3170731707317073, + "grad_norm": 0.8492751703287535, + "learning_rate": 1.7777777777777777e-05, + "loss": 0.4878, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.5011531114578247, + "step": 65, + "valid_targets_mean": 2957.6, + "valid_targets_min": 582 + }, + { + "epoch": 0.34146341463414637, + "grad_norm": 0.7716257577706961, + "learning_rate": 1.916666666666667e-05, + "loss": 0.4473, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.47079670429229736, + "step": 70, + "valid_targets_mean": 3449.3, + "valid_targets_min": 853 + }, + { + "epoch": 0.36585365853658536, + "grad_norm": 0.8434747864822957, + "learning_rate": 2.0555555555555555e-05, + "loss": 0.4557, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.43814384937286377, + "step": 75, + "valid_targets_mean": 3228.6, + "valid_targets_min": 414 + }, + { + "epoch": 0.3902439024390244, + "grad_norm": 0.7458155064497034, + "learning_rate": 2.194444444444445e-05, + "loss": 0.46, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.44705730676651, + "step": 80, + "valid_targets_mean": 3524.7, + "valid_targets_min": 875 + }, + { + "epoch": 0.4146341463414634, + "grad_norm": 0.8049876326023591, + "learning_rate": 2.3333333333333336e-05, + "loss": 0.4682, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.5294123888015747, + "step": 85, + "valid_targets_mean": 3489.1, + "valid_targets_min": 899 + }, + { + "epoch": 0.43902439024390244, + "grad_norm": 0.6716168920810122, + "learning_rate": 2.4722222222222226e-05, + "loss": 0.4455, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4092828929424286, + "step": 90, + "valid_targets_mean": 3573.4, + "valid_targets_min": 979 + }, + { + "epoch": 0.4634146341463415, + "grad_norm": 0.7612668390820156, + "learning_rate": 2.6111111111111114e-05, + "loss": 0.4531, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.478001207113266, + "step": 95, + "valid_targets_mean": 3585.0, + "valid_targets_min": 878 + }, + { + "epoch": 0.4878048780487805, + "grad_norm": 0.8720193134806395, + "learning_rate": 2.75e-05, + "loss": 0.4494, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4325084090232849, + "step": 100, + "valid_targets_mean": 2660.9, + "valid_targets_min": 15 + }, + { + "epoch": 0.5121951219512195, + "grad_norm": 0.9243802248475099, + "learning_rate": 2.888888888888889e-05, + "loss": 0.418, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4396073818206787, + "step": 105, + "valid_targets_mean": 2434.6, + "valid_targets_min": 772 + }, + { + "epoch": 0.5365853658536586, + "grad_norm": 0.7410305143235792, + "learning_rate": 3.027777777777778e-05, + "loss": 0.4421, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.39146214723587036, + "step": 110, + "valid_targets_mean": 3399.3, + "valid_targets_min": 265 + }, + { + "epoch": 0.5609756097560976, + "grad_norm": 0.9932166784633583, + "learning_rate": 3.1666666666666666e-05, + "loss": 0.4504, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.44398099184036255, + "step": 115, + "valid_targets_mean": 3370.4, + "valid_targets_min": 993 + }, + { + "epoch": 0.5853658536585366, + "grad_norm": 0.7226380775954716, + "learning_rate": 3.3055555555555553e-05, + "loss": 0.4249, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3628934323787689, + "step": 120, + "valid_targets_mean": 3499.3, + "valid_targets_min": 477 + }, + { + "epoch": 0.6097560975609756, + "grad_norm": 0.8823777151936405, + "learning_rate": 3.444444444444445e-05, + "loss": 0.4417, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.41109269857406616, + "step": 125, + "valid_targets_mean": 2774.8, + "valid_targets_min": 15 + }, + { + "epoch": 0.6341463414634146, + "grad_norm": 0.7500022204056533, + "learning_rate": 3.5833333333333335e-05, + "loss": 0.4383, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4249718189239502, + "step": 130, + "valid_targets_mean": 3250.6, + "valid_targets_min": 1490 + }, + { + "epoch": 0.6585365853658537, + "grad_norm": 0.7608537033688073, + "learning_rate": 3.722222222222223e-05, + "loss": 0.4266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.41326218843460083, + "step": 135, + "valid_targets_mean": 3088.5, + "valid_targets_min": 539 + }, + { + "epoch": 0.6829268292682927, + "grad_norm": 0.8309125080829076, + "learning_rate": 3.8611111111111116e-05, + "loss": 0.4089, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4202869236469269, + "step": 140, + "valid_targets_mean": 3053.9, + "valid_targets_min": 15 + }, + { + "epoch": 0.7073170731707317, + "grad_norm": 0.7091166521276581, + "learning_rate": 4e-05, + "loss": 0.4009, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3712766766548157, + "step": 145, + "valid_targets_mean": 4122.2, + "valid_targets_min": 1176 + }, + { + "epoch": 0.7317073170731707, + "grad_norm": 0.7272991052058403, + "learning_rate": 3.999851959033532e-05, + "loss": 0.4064, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4357445240020752, + "step": 150, + "valid_targets_mean": 3601.1, + "valid_targets_min": 886 + }, + { + "epoch": 0.7560975609756098, + "grad_norm": 0.7530784025869104, + "learning_rate": 3.999407858050255e-05, + "loss": 0.4104, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4047582745552063, + "step": 155, + "valid_targets_mean": 2777.0, + "valid_targets_min": 976 + }, + { + "epoch": 0.7804878048780488, + "grad_norm": 0.5809719279424417, + "learning_rate": 3.998667762795307e-05, + "loss": 0.4061, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3885638117790222, + "step": 160, + "valid_targets_mean": 5063.3, + "valid_targets_min": 1079 + }, + { + "epoch": 0.8048780487804879, + "grad_norm": 0.7354864856165856, + "learning_rate": 3.9976317828331075e-05, + "loss": 0.4108, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4471714496612549, + "step": 165, + "valid_targets_mean": 3957.6, + "valid_targets_min": 470 + }, + { + "epoch": 0.8292682926829268, + "grad_norm": 0.8186760526901421, + "learning_rate": 3.9963000715311284e-05, + "loss": 0.4148, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.47168421745300293, + "step": 170, + "valid_targets_mean": 2868.2, + "valid_targets_min": 916 + }, + { + "epoch": 0.8536585365853658, + "grad_norm": 0.8249337383629396, + "learning_rate": 3.9946728260372e-05, + "loss": 0.4097, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4015315771102905, + "step": 175, + "valid_targets_mean": 3402.2, + "valid_targets_min": 475 + }, + { + "epoch": 0.8780487804878049, + "grad_norm": 0.802745972860082, + "learning_rate": 3.992750287250316e-05, + "loss": 0.4262, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.46255892515182495, + "step": 180, + "valid_targets_mean": 3201.5, + "valid_targets_min": 467 + }, + { + "epoch": 0.9024390243902439, + "grad_norm": 0.8369027610414674, + "learning_rate": 3.9905327397849776e-05, + "loss": 0.4143, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.438213050365448, + "step": 185, + "valid_targets_mean": 2837.9, + "valid_targets_min": 1004 + }, + { + "epoch": 0.926829268292683, + "grad_norm": 0.7620682825729357, + "learning_rate": 3.988020511929055e-05, + "loss": 0.4068, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3820480406284332, + "step": 190, + "valid_targets_mean": 3607.6, + "valid_targets_min": 15 + }, + { + "epoch": 0.9512195121951219, + "grad_norm": 0.8231019760594912, + "learning_rate": 3.985213975595188e-05, + "loss": 0.4169, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4414719045162201, + "step": 195, + "valid_targets_mean": 2511.9, + "valid_targets_min": 363 + }, + { + "epoch": 0.975609756097561, + "grad_norm": 0.7380667621345177, + "learning_rate": 3.982113546265727e-05, + "loss": 0.4196, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.4193473160266876, + "step": 200, + "valid_targets_mean": 3748.1, + "valid_targets_min": 692 + }, + { + "epoch": 1.0, + "grad_norm": 0.7458650521840304, + "learning_rate": 3.978719682931227e-05, + "loss": 0.3994, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3914061188697815, + "step": 205, + "valid_targets_mean": 3714.5, + "valid_targets_min": 1568 + }, + { + "epoch": 1.024390243902439, + "grad_norm": 0.8139396617003434, + "learning_rate": 3.9750328880224964e-05, + "loss": 0.3843, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3921425938606262, + "step": 210, + "valid_targets_mean": 2894.5, + "valid_targets_min": 1142 + }, + { + "epoch": 1.048780487804878, + "grad_norm": 0.920561844317153, + "learning_rate": 3.9710537073362154e-05, + "loss": 0.3676, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.37253957986831665, + "step": 215, + "valid_targets_mean": 2493.4, + "valid_targets_min": 1141 + }, + { + "epoch": 1.0731707317073171, + "grad_norm": 0.8730069289304332, + "learning_rate": 3.9667827299541405e-05, + "loss": 0.376, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3857506215572357, + "step": 220, + "valid_targets_mean": 2558.9, + "valid_targets_min": 848 + }, + { + "epoch": 1.0975609756097562, + "grad_norm": 0.6229292309392103, + "learning_rate": 3.962220588155889e-05, + "loss": 0.3914, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3528486490249634, + "step": 225, + "valid_targets_mean": 4876.5, + "valid_targets_min": 15 + }, + { + "epoch": 1.1219512195121952, + "grad_norm": 1.0416514376225245, + "learning_rate": 3.957367957325344e-05, + "loss": 0.3891, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.40384507179260254, + "step": 230, + "valid_targets_mean": 2797.6, + "valid_targets_min": 654 + }, + { + "epoch": 1.146341463414634, + "grad_norm": 0.8974767692382145, + "learning_rate": 3.952225555850662e-05, + "loss": 0.3805, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.41643357276916504, + "step": 235, + "valid_targets_mean": 3033.7, + "valid_targets_min": 1141 + }, + { + "epoch": 1.170731707317073, + "grad_norm": 0.6882577926862582, + "learning_rate": 3.9467941450179276e-05, + "loss": 0.4021, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34199321269989014, + "step": 240, + "valid_targets_mean": 3899.6, + "valid_targets_min": 947 + }, + { + "epoch": 1.1951219512195121, + "grad_norm": 0.7598060326395756, + "learning_rate": 3.94107452889845e-05, + "loss": 0.3768, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3925563097000122, + "step": 245, + "valid_targets_mean": 3416.5, + "valid_targets_min": 976 + }, + { + "epoch": 1.2195121951219512, + "grad_norm": 0.7953917356483156, + "learning_rate": 3.9350675542297273e-05, + "loss": 0.3985, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3889926075935364, + "step": 250, + "valid_targets_mean": 3197.0, + "valid_targets_min": 960 + }, + { + "epoch": 1.2439024390243902, + "grad_norm": 0.8560153490249861, + "learning_rate": 3.9287741102900956e-05, + "loss": 0.3822, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3994605541229248, + "step": 255, + "valid_targets_mean": 2937.1, + "valid_targets_min": 576 + }, + { + "epoch": 1.2682926829268293, + "grad_norm": 0.7105463458999842, + "learning_rate": 3.922195128767077e-05, + "loss": 0.3531, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32579752802848816, + "step": 260, + "valid_targets_mean": 3560.3, + "valid_targets_min": 363 + }, + { + "epoch": 1.2926829268292683, + "grad_norm": 0.7542653042504447, + "learning_rate": 3.915331583619455e-05, + "loss": 0.3768, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3614310324192047, + "step": 265, + "valid_targets_mean": 3289.0, + "valid_targets_min": 849 + }, + { + "epoch": 1.3170731707317074, + "grad_norm": 0.8497951456582137, + "learning_rate": 3.908184490933087e-05, + "loss": 0.3667, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3782227337360382, + "step": 270, + "valid_targets_mean": 2581.6, + "valid_targets_min": 696 + }, + { + "epoch": 1.3414634146341464, + "grad_norm": 0.7719791862885925, + "learning_rate": 3.90075490877048e-05, + "loss": 0.3852, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.37844318151474, + "step": 275, + "valid_targets_mean": 3066.4, + "valid_targets_min": 15 + }, + { + "epoch": 1.3658536585365852, + "grad_norm": 0.7223338146517535, + "learning_rate": 3.893043937014161e-05, + "loss": 0.3607, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.36418038606643677, + "step": 280, + "valid_targets_mean": 3117.9, + "valid_targets_min": 940 + }, + { + "epoch": 1.3902439024390243, + "grad_norm": 0.7019756644424542, + "learning_rate": 3.885052717203839e-05, + "loss": 0.3789, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.39389437437057495, + "step": 285, + "valid_targets_mean": 3810.8, + "valid_targets_min": 989 + }, + { + "epoch": 1.4146341463414633, + "grad_norm": 0.7126900107048149, + "learning_rate": 3.876782432367419e-05, + "loss": 0.3593, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3678337335586548, + "step": 290, + "valid_targets_mean": 3401.9, + "valid_targets_min": 417 + }, + { + "epoch": 1.4390243902439024, + "grad_norm": 0.6043008862137972, + "learning_rate": 3.86823430684586e-05, + "loss": 0.3787, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3658294081687927, + "step": 295, + "valid_targets_mean": 4910.9, + "valid_targets_min": 1152 + }, + { + "epoch": 1.4634146341463414, + "grad_norm": 0.9549115770574411, + "learning_rate": 3.859409606111927e-05, + "loss": 0.3935, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.41088318824768066, + "step": 300, + "valid_targets_mean": 3028.8, + "valid_targets_min": 288 + }, + { + "epoch": 1.4878048780487805, + "grad_norm": 0.8424403005867168, + "learning_rate": 3.850309636582844e-05, + "loss": 0.3699, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34833067655563354, + "step": 305, + "valid_targets_mean": 4002.8, + "valid_targets_min": 1645 + }, + { + "epoch": 1.5121951219512195, + "grad_norm": 0.6306861230305417, + "learning_rate": 3.8409357454268954e-05, + "loss": 0.3777, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.37073996663093567, + "step": 310, + "valid_targets_mean": 5012.4, + "valid_targets_min": 1119 + }, + { + "epoch": 1.5365853658536586, + "grad_norm": 0.7155539048246429, + "learning_rate": 3.831289320363988e-05, + "loss": 0.3883, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.37950462102890015, + "step": 315, + "valid_targets_mean": 4102.6, + "valid_targets_min": 265 + }, + { + "epoch": 1.5609756097560976, + "grad_norm": 0.7974667376832275, + "learning_rate": 3.821371789460211e-05, + "loss": 0.3614, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.36880871653556824, + "step": 320, + "valid_targets_mean": 3079.6, + "valid_targets_min": 959 + }, + { + "epoch": 1.5853658536585367, + "grad_norm": 0.8043178482245835, + "learning_rate": 3.8111846209164245e-05, + "loss": 0.3748, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.40152832865715027, + "step": 325, + "valid_targets_mean": 2942.4, + "valid_targets_min": 1052 + }, + { + "epoch": 1.6097560975609757, + "grad_norm": 0.7724860293036107, + "learning_rate": 3.800729322850905e-05, + "loss": 0.3763, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.39380210638046265, + "step": 330, + "valid_targets_mean": 3036.5, + "valid_targets_min": 886 + }, + { + "epoch": 1.6341463414634148, + "grad_norm": 0.8482463253190202, + "learning_rate": 3.790007443076083e-05, + "loss": 0.3838, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3798723816871643, + "step": 335, + "valid_targets_mean": 3018.6, + "valid_targets_min": 15 + }, + { + "epoch": 1.6585365853658538, + "grad_norm": 0.8833799570209917, + "learning_rate": 3.779020568869402e-05, + "loss": 0.3559, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.36824825406074524, + "step": 340, + "valid_targets_mean": 2802.5, + "valid_targets_min": 711 + }, + { + "epoch": 1.6829268292682928, + "grad_norm": 0.6829517524240788, + "learning_rate": 3.767770326738339e-05, + "loss": 0.3816, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3737407326698303, + "step": 345, + "valid_targets_mean": 4252.8, + "valid_targets_min": 876 + }, + { + "epoch": 1.7073170731707317, + "grad_norm": 0.6903358415372074, + "learning_rate": 3.7562583821796114e-05, + "loss": 0.3735, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.36414116621017456, + "step": 350, + "valid_targets_mean": 3665.8, + "valid_targets_min": 660 + }, + { + "epoch": 1.7317073170731707, + "grad_norm": 0.6233603443152537, + "learning_rate": 3.7444864394326186e-05, + "loss": 0.3607, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3237985670566559, + "step": 355, + "valid_targets_mean": 4911.9, + "valid_targets_min": 711 + }, + { + "epoch": 1.7560975609756098, + "grad_norm": 0.9214069599336896, + "learning_rate": 3.732456241227141e-05, + "loss": 0.3591, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3726973533630371, + "step": 360, + "valid_targets_mean": 3513.8, + "valid_targets_min": 1456 + }, + { + "epoch": 1.7804878048780488, + "grad_norm": 0.7500860882422733, + "learning_rate": 3.7201695685253476e-05, + "loss": 0.3896, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3697166442871094, + "step": 365, + "valid_targets_mean": 3385.0, + "valid_targets_min": 825 + }, + { + "epoch": 1.8048780487804879, + "grad_norm": 0.8780041171925682, + "learning_rate": 3.7076282402581404e-05, + "loss": 0.3927, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.41772669553756714, + "step": 370, + "valid_targets_mean": 2651.1, + "valid_targets_min": 1157 + }, + { + "epoch": 1.8292682926829267, + "grad_norm": 0.7547594930022417, + "learning_rate": 3.694834113055877e-05, + "loss": 0.3652, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3808954358100891, + "step": 375, + "valid_targets_mean": 3378.3, + "valid_targets_min": 865 + }, + { + "epoch": 1.8536585365853657, + "grad_norm": 1.062524119548778, + "learning_rate": 3.681789080973514e-05, + "loss": 0.3603, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.37782055139541626, + "step": 380, + "valid_targets_mean": 2781.2, + "valid_targets_min": 448 + }, + { + "epoch": 1.8780487804878048, + "grad_norm": 0.7747602704814769, + "learning_rate": 3.668495075210207e-05, + "loss": 0.3593, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3768714666366577, + "step": 385, + "valid_targets_mean": 3837.8, + "valid_targets_min": 1132 + }, + { + "epoch": 1.9024390243902438, + "grad_norm": 0.6379661220392324, + "learning_rate": 3.654954063823419e-05, + "loss": 0.3631, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3241764307022095, + "step": 390, + "valid_targets_mean": 3892.8, + "valid_targets_min": 1626 + }, + { + "epoch": 1.9268292682926829, + "grad_norm": 0.8306626736395537, + "learning_rate": 3.641168051437562e-05, + "loss": 0.3838, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3675532937049866, + "step": 395, + "valid_targets_mean": 3192.4, + "valid_targets_min": 916 + }, + { + "epoch": 1.951219512195122, + "grad_norm": 0.6795328481586967, + "learning_rate": 3.627139078947233e-05, + "loss": 0.3785, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3840370774269104, + "step": 400, + "valid_targets_mean": 4188.1, + "valid_targets_min": 1483 + }, + { + "epoch": 1.975609756097561, + "grad_norm": 0.6384377969297063, + "learning_rate": 3.6128692232150775e-05, + "loss": 0.3547, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3258434534072876, + "step": 405, + "valid_targets_mean": 3781.2, + "valid_targets_min": 492 + }, + { + "epoch": 2.0, + "grad_norm": 0.6449462111499721, + "learning_rate": 3.598360596764331e-05, + "loss": 0.3574, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3393850326538086, + "step": 410, + "valid_targets_mean": 4006.3, + "valid_targets_min": 719 + }, + { + "epoch": 2.024390243902439, + "grad_norm": 0.8321218841560414, + "learning_rate": 3.583615347466075e-05, + "loss": 0.346, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3338969945907593, + "step": 415, + "valid_targets_mean": 2771.9, + "valid_targets_min": 928 + }, + { + "epoch": 2.048780487804878, + "grad_norm": 0.7320573520455086, + "learning_rate": 3.568635658221266e-05, + "loss": 0.3131, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31023988127708435, + "step": 420, + "valid_targets_mean": 3438.1, + "valid_targets_min": 1040 + }, + { + "epoch": 2.073170731707317, + "grad_norm": 0.8445720664474741, + "learning_rate": 3.553423746637577e-05, + "loss": 0.3289, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3350527584552765, + "step": 425, + "valid_targets_mean": 2859.0, + "valid_targets_min": 15 + }, + { + "epoch": 2.097560975609756, + "grad_norm": 0.9479920623957632, + "learning_rate": 3.537981864701101e-05, + "loss": 0.3556, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.39427098631858826, + "step": 430, + "valid_targets_mean": 2811.9, + "valid_targets_min": 760 + }, + { + "epoch": 2.1219512195121952, + "grad_norm": 0.740296255448551, + "learning_rate": 3.5223122984429645e-05, + "loss": 0.3533, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3620370626449585, + "step": 435, + "valid_targets_mean": 3927.2, + "valid_targets_min": 1332 + }, + { + "epoch": 2.1463414634146343, + "grad_norm": 0.8475846605532067, + "learning_rate": 3.5064173676008994e-05, + "loss": 0.3302, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3536580502986908, + "step": 440, + "valid_targets_mean": 3192.6, + "valid_targets_min": 15 + }, + { + "epoch": 2.1707317073170733, + "grad_norm": 0.7927213460960987, + "learning_rate": 3.4902994252758295e-05, + "loss": 0.3471, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.35433822870254517, + "step": 445, + "valid_targets_mean": 3070.1, + "valid_targets_min": 1186 + }, + { + "epoch": 2.1951219512195124, + "grad_norm": 0.7610761241152856, + "learning_rate": 3.473960857583515e-05, + "loss": 0.3171, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32693955302238464, + "step": 450, + "valid_targets_mean": 3352.6, + "valid_targets_min": 470 + }, + { + "epoch": 2.2195121951219514, + "grad_norm": 0.7661120709390085, + "learning_rate": 3.457404083301308e-05, + "loss": 0.347, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.39784368872642517, + "step": 455, + "valid_targets_mean": 2986.9, + "valid_targets_min": 659 + }, + { + "epoch": 2.2439024390243905, + "grad_norm": 0.7246543900328846, + "learning_rate": 3.440631553510074e-05, + "loss": 0.3289, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34927499294281006, + "step": 460, + "valid_targets_mean": 4064.9, + "valid_targets_min": 895 + }, + { + "epoch": 2.2682926829268295, + "grad_norm": 0.8008639860765635, + "learning_rate": 3.423645751231334e-05, + "loss": 0.3214, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31427597999572754, + "step": 465, + "valid_targets_mean": 3223.2, + "valid_targets_min": 948 + }, + { + "epoch": 2.292682926829268, + "grad_norm": 0.8738414902443441, + "learning_rate": 3.4064491910596726e-05, + "loss": 0.3219, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34688445925712585, + "step": 470, + "valid_targets_mean": 2696.8, + "valid_targets_min": 414 + }, + { + "epoch": 2.317073170731707, + "grad_norm": 0.8678786719122115, + "learning_rate": 3.389044418790478e-05, + "loss": 0.3375, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.36265698075294495, + "step": 475, + "valid_targets_mean": 3027.2, + "valid_targets_min": 827 + }, + { + "epoch": 2.341463414634146, + "grad_norm": 0.8786827707032558, + "learning_rate": 3.371434011043059e-05, + "loss": 0.337, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3238053321838379, + "step": 480, + "valid_targets_mean": 3018.0, + "valid_targets_min": 879 + }, + { + "epoch": 2.3658536585365852, + "grad_norm": 0.7675111501407975, + "learning_rate": 3.353620574879197e-05, + "loss": 0.3149, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.33381664752960205, + "step": 485, + "valid_targets_mean": 3482.8, + "valid_targets_min": 822 + }, + { + "epoch": 2.3902439024390243, + "grad_norm": 0.6390042122755262, + "learning_rate": 3.335606747417199e-05, + "loss": 0.3216, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2951709032058716, + "step": 490, + "valid_targets_mean": 4398.2, + "valid_targets_min": 778 + }, + { + "epoch": 2.4146341463414633, + "grad_norm": 0.8212805538188749, + "learning_rate": 3.317395195441492e-05, + "loss": 0.3528, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3706200122833252, + "step": 495, + "valid_targets_mean": 2767.0, + "valid_targets_min": 15 + }, + { + "epoch": 2.4390243902439024, + "grad_norm": 0.8090900974135942, + "learning_rate": 3.29898861500783e-05, + "loss": 0.3328, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3654935956001282, + "step": 500, + "valid_targets_mean": 3085.2, + "valid_targets_min": 242 + }, + { + "epoch": 2.4634146341463414, + "grad_norm": 0.7178716047967076, + "learning_rate": 3.280389731044172e-05, + "loss": 0.3202, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32301709055900574, + "step": 505, + "valid_targets_mean": 3715.7, + "valid_targets_min": 716 + }, + { + "epoch": 2.4878048780487805, + "grad_norm": 0.7793422281432595, + "learning_rate": 3.261601296947274e-05, + "loss": 0.3201, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.335943341255188, + "step": 510, + "valid_targets_mean": 3158.2, + "valid_targets_min": 734 + }, + { + "epoch": 2.5121951219512195, + "grad_norm": 0.7681138811218, + "learning_rate": 3.242626094175078e-05, + "loss": 0.3346, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.35204848647117615, + "step": 515, + "valid_targets_mean": 3170.2, + "valid_targets_min": 1079 + }, + { + "epoch": 2.5365853658536586, + "grad_norm": 0.6712571944834722, + "learning_rate": 3.223466931834942e-05, + "loss": 0.318, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29909318685531616, + "step": 520, + "valid_targets_mean": 4161.2, + "valid_targets_min": 766 + }, + { + "epoch": 2.5609756097560976, + "grad_norm": 0.8147312751968008, + "learning_rate": 3.204126646267775e-05, + "loss": 0.336, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3322216272354126, + "step": 525, + "valid_targets_mean": 3378.3, + "valid_targets_min": 443 + }, + { + "epoch": 2.5853658536585367, + "grad_norm": 0.9657053285042281, + "learning_rate": 3.184608100628144e-05, + "loss": 0.3356, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3430883288383484, + "step": 530, + "valid_targets_mean": 3151.1, + "valid_targets_min": 1443 + }, + { + "epoch": 2.6097560975609757, + "grad_norm": 0.8322031702520009, + "learning_rate": 3.1649141844604104e-05, + "loss": 0.3355, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.338076114654541, + "step": 535, + "valid_targets_mean": 3503.4, + "valid_targets_min": 1613 + }, + { + "epoch": 2.6341463414634148, + "grad_norm": 0.6205044905999079, + "learning_rate": 3.1450478132709564e-05, + "loss": 0.3285, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27576902508735657, + "step": 540, + "valid_targets_mean": 3844.5, + "valid_targets_min": 1855 + }, + { + "epoch": 2.658536585365854, + "grad_norm": 0.6286837078803078, + "learning_rate": 3.125011928096573e-05, + "loss": 0.3151, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3034632205963135, + "step": 545, + "valid_targets_mean": 4288.0, + "valid_targets_min": 719 + }, + { + "epoch": 2.682926829268293, + "grad_norm": 0.6004872520430579, + "learning_rate": 3.1048094950690666e-05, + "loss": 0.3253, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31010162830352783, + "step": 550, + "valid_targets_mean": 4788.6, + "valid_targets_min": 1098 + }, + { + "epoch": 2.7073170731707314, + "grad_norm": 0.7437431500245776, + "learning_rate": 3.084443504976146e-05, + "loss": 0.3211, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3372463881969452, + "step": 555, + "valid_targets_mean": 3434.3, + "valid_targets_min": 706 + }, + { + "epoch": 2.7317073170731705, + "grad_norm": 0.7853234418992919, + "learning_rate": 3.063916972818668e-05, + "loss": 0.3079, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32306212186813354, + "step": 560, + "valid_targets_mean": 3142.7, + "valid_targets_min": 509 + }, + { + "epoch": 2.7560975609756095, + "grad_norm": 0.7334837795099509, + "learning_rate": 3.0432329373642932e-05, + "loss": 0.3296, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.35558754205703735, + "step": 565, + "valid_targets_mean": 3550.8, + "valid_targets_min": 951 + }, + { + "epoch": 2.7804878048780486, + "grad_norm": 0.7080533587312593, + "learning_rate": 3.022394460697619e-05, + "loss": 0.3424, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.33535170555114746, + "step": 570, + "valid_targets_mean": 3713.6, + "valid_targets_min": 947 + }, + { + "epoch": 2.8048780487804876, + "grad_norm": 0.73150297718836, + "learning_rate": 3.0014046277668717e-05, + "loss": 0.34, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3074615001678467, + "step": 575, + "valid_targets_mean": 3663.5, + "valid_targets_min": 215 + }, + { + "epoch": 2.8292682926829267, + "grad_norm": 0.6590534931503084, + "learning_rate": 2.980266545927203e-05, + "loss": 0.3348, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32705825567245483, + "step": 580, + "valid_targets_mean": 4970.6, + "valid_targets_min": 1788 + }, + { + "epoch": 2.8536585365853657, + "grad_norm": 0.6817244060162384, + "learning_rate": 2.9589833444806792e-05, + "loss": 0.3144, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.30664777755737305, + "step": 585, + "valid_targets_mean": 3579.2, + "valid_targets_min": 917 + }, + { + "epoch": 2.8780487804878048, + "grad_norm": 0.7336497853782242, + "learning_rate": 2.9375581742130114e-05, + "loss": 0.3305, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3490193486213684, + "step": 590, + "valid_targets_mean": 3624.7, + "valid_targets_min": 876 + }, + { + "epoch": 2.902439024390244, + "grad_norm": 0.7790909299976445, + "learning_rate": 2.9159942069271134e-05, + "loss": 0.3246, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3473791778087616, + "step": 595, + "valid_targets_mean": 3575.1, + "valid_targets_min": 532 + }, + { + "epoch": 2.926829268292683, + "grad_norm": 0.8701084213390046, + "learning_rate": 2.8942946349735418e-05, + "loss": 0.3389, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3636641800403595, + "step": 600, + "valid_targets_mean": 3125.3, + "valid_targets_min": 1655 + }, + { + "epoch": 2.951219512195122, + "grad_norm": 0.6582306859910523, + "learning_rate": 2.872462670777902e-05, + "loss": 0.3444, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.34115156531333923, + "step": 605, + "valid_targets_mean": 4006.7, + "valid_targets_min": 856 + }, + { + "epoch": 2.975609756097561, + "grad_norm": 0.6682235966360865, + "learning_rate": 2.850501546365272e-05, + "loss": 0.3298, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2904140055179596, + "step": 610, + "valid_targets_mean": 4037.1, + "valid_targets_min": 1157 + }, + { + "epoch": 3.0, + "grad_norm": 0.7895951757040935, + "learning_rate": 2.8284145128817356e-05, + "loss": 0.3203, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.354103684425354, + "step": 615, + "valid_targets_mean": 3262.8, + "valid_targets_min": 841 + }, + { + "epoch": 3.024390243902439, + "grad_norm": 0.6974883146545042, + "learning_rate": 2.8062048401130756e-05, + "loss": 0.2882, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24095089733600616, + "step": 620, + "valid_targets_mean": 3347.9, + "valid_targets_min": 883 + }, + { + "epoch": 3.048780487804878, + "grad_norm": 0.7109250659036205, + "learning_rate": 2.7838758160007143e-05, + "loss": 0.2966, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2862807512283325, + "step": 625, + "valid_targets_mean": 4033.4, + "valid_targets_min": 1140 + }, + { + "epoch": 3.073170731707317, + "grad_norm": 0.7946160604885082, + "learning_rate": 2.7614307461549608e-05, + "loss": 0.2901, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29598280787467957, + "step": 630, + "valid_targets_mean": 3057.0, + "valid_targets_min": 1115 + }, + { + "epoch": 3.097560975609756, + "grad_norm": 0.7097254573358867, + "learning_rate": 2.7388729533656486e-05, + "loss": 0.3045, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3431246876716614, + "step": 635, + "valid_targets_mean": 4266.8, + "valid_targets_min": 1238 + }, + { + "epoch": 3.1219512195121952, + "grad_norm": 0.6657050549479481, + "learning_rate": 2.716205777110222e-05, + "loss": 0.2904, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2793746590614319, + "step": 640, + "valid_targets_mean": 4308.1, + "valid_targets_min": 1604 + }, + { + "epoch": 3.1463414634146343, + "grad_norm": 0.8163459205438388, + "learning_rate": 2.693432573059362e-05, + "loss": 0.3019, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3036867678165436, + "step": 645, + "valid_targets_mean": 3326.4, + "valid_targets_min": 1119 + }, + { + "epoch": 3.1707317073170733, + "grad_norm": 0.7669109525500525, + "learning_rate": 2.6705567125802062e-05, + "loss": 0.3081, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3797120451927185, + "step": 650, + "valid_targets_mean": 3517.2, + "valid_targets_min": 1445 + }, + { + "epoch": 3.1951219512195124, + "grad_norm": 0.7809371072538767, + "learning_rate": 2.6475815822372477e-05, + "loss": 0.2962, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2904462516307831, + "step": 655, + "valid_targets_mean": 3374.4, + "valid_targets_min": 752 + }, + { + "epoch": 3.2195121951219514, + "grad_norm": 0.8873754094152563, + "learning_rate": 2.624510583290988e-05, + "loss": 0.3042, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2988511919975281, + "step": 660, + "valid_targets_mean": 2854.0, + "valid_targets_min": 283 + }, + { + "epoch": 3.2439024390243905, + "grad_norm": 0.6937976107448536, + "learning_rate": 2.601347131194408e-05, + "loss": 0.2824, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2786598205566406, + "step": 665, + "valid_targets_mean": 3895.2, + "valid_targets_min": 848 + }, + { + "epoch": 3.2682926829268295, + "grad_norm": 0.6938504187586086, + "learning_rate": 2.578094655087343e-05, + "loss": 0.2887, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.284922331571579, + "step": 670, + "valid_targets_mean": 3660.7, + "valid_targets_min": 376 + }, + { + "epoch": 3.292682926829268, + "grad_norm": 0.6657085168651424, + "learning_rate": 2.5547565972888287e-05, + "loss": 0.2758, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2657183110713959, + "step": 675, + "valid_targets_mean": 4128.4, + "valid_targets_min": 1404 + }, + { + "epoch": 3.317073170731707, + "grad_norm": 0.7187359550353202, + "learning_rate": 2.5313364127874974e-05, + "loss": 0.2936, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27557191252708435, + "step": 680, + "valid_targets_mean": 3624.4, + "valid_targets_min": 796 + }, + { + "epoch": 3.341463414634146, + "grad_norm": 0.7875009925701425, + "learning_rate": 2.507837568730097e-05, + "loss": 0.289, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3072514533996582, + "step": 685, + "valid_targets_mean": 3990.4, + "valid_targets_min": 15 + }, + { + "epoch": 3.3658536585365852, + "grad_norm": 0.842619447531655, + "learning_rate": 2.484263543908213e-05, + "loss": 0.3008, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3235273063182831, + "step": 690, + "valid_targets_mean": 2521.5, + "valid_targets_min": 1158 + }, + { + "epoch": 3.3902439024390243, + "grad_norm": 0.7753973868751888, + "learning_rate": 2.460617828243263e-05, + "loss": 0.2919, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27399516105651855, + "step": 695, + "valid_targets_mean": 3223.4, + "valid_targets_min": 899 + }, + { + "epoch": 3.4146341463414633, + "grad_norm": 0.7336548815168598, + "learning_rate": 2.4369039222698484e-05, + "loss": 0.2898, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2887844443321228, + "step": 700, + "valid_targets_mean": 3239.1, + "valid_targets_min": 979 + }, + { + "epoch": 3.4390243902439024, + "grad_norm": 0.7641087596057364, + "learning_rate": 2.413125336617526e-05, + "loss": 0.3052, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.30372944474220276, + "step": 705, + "valid_targets_mean": 3645.4, + "valid_targets_min": 1803 + }, + { + "epoch": 3.4634146341463414, + "grad_norm": 0.7436323943905782, + "learning_rate": 2.3892855914910996e-05, + "loss": 0.2925, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2785486578941345, + "step": 710, + "valid_targets_mean": 3915.2, + "valid_targets_min": 1063 + }, + { + "epoch": 3.4878048780487805, + "grad_norm": 0.7111257893891988, + "learning_rate": 2.3653882161494758e-05, + "loss": 0.2896, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2819863557815552, + "step": 715, + "valid_targets_mean": 3914.8, + "valid_targets_min": 1277 + }, + { + "epoch": 3.5121951219512195, + "grad_norm": 0.7237969701861009, + "learning_rate": 2.3414367483831972e-05, + "loss": 0.2972, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2876496911048889, + "step": 720, + "valid_targets_mean": 3642.9, + "valid_targets_min": 575 + }, + { + "epoch": 3.5365853658536586, + "grad_norm": 0.750501060308758, + "learning_rate": 2.3174347339906994e-05, + "loss": 0.2909, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31642240285873413, + "step": 725, + "valid_targets_mean": 3697.5, + "valid_targets_min": 917 + }, + { + "epoch": 3.5609756097560976, + "grad_norm": 0.7241041312746126, + "learning_rate": 2.293385726253392e-05, + "loss": 0.2953, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2714157700538635, + "step": 730, + "valid_targets_mean": 3771.2, + "valid_targets_min": 723 + }, + { + "epoch": 3.5853658536585367, + "grad_norm": 0.6954133761615647, + "learning_rate": 2.2692932854096218e-05, + "loss": 0.2895, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25798699259757996, + "step": 735, + "valid_targets_mean": 3402.4, + "valid_targets_min": 1080 + }, + { + "epoch": 3.6097560975609757, + "grad_norm": 0.7417839254349834, + "learning_rate": 2.245160978127616e-05, + "loss": 0.2971, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.28403568267822266, + "step": 740, + "valid_targets_mean": 3251.5, + "valid_targets_min": 841 + }, + { + "epoch": 3.6341463414634148, + "grad_norm": 0.7403025968890654, + "learning_rate": 2.220992376977468e-05, + "loss": 0.2993, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.32009467482566833, + "step": 745, + "valid_targets_mean": 3620.8, + "valid_targets_min": 1178 + }, + { + "epoch": 3.658536585365854, + "grad_norm": 0.9161578181958758, + "learning_rate": 2.1967910599022508e-05, + "loss": 0.2898, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.331581711769104, + "step": 750, + "valid_targets_mean": 2408.2, + "valid_targets_min": 507 + }, + { + "epoch": 3.682926829268293, + "grad_norm": 0.881155980649594, + "learning_rate": 2.1725606096883324e-05, + "loss": 0.2915, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29733753204345703, + "step": 755, + "valid_targets_mean": 2705.3, + "valid_targets_min": 257 + }, + { + "epoch": 3.7073170731707314, + "grad_norm": 0.7297940343575094, + "learning_rate": 2.1483046134349813e-05, + "loss": 0.2876, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.28595206141471863, + "step": 760, + "valid_targets_mean": 4102.2, + "valid_targets_min": 318 + }, + { + "epoch": 3.7317073170731705, + "grad_norm": 0.8649348588673672, + "learning_rate": 2.1240266620233263e-05, + "loss": 0.3112, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31264781951904297, + "step": 765, + "valid_targets_mean": 2636.3, + "valid_targets_min": 772 + }, + { + "epoch": 3.7560975609756095, + "grad_norm": 0.7040450574601868, + "learning_rate": 2.099730349584757e-05, + "loss": 0.2832, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3125355541706085, + "step": 770, + "valid_targets_mean": 3862.3, + "valid_targets_min": 867 + }, + { + "epoch": 3.7804878048780486, + "grad_norm": 0.6737989713489716, + "learning_rate": 2.0754192729688496e-05, + "loss": 0.2996, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2767524719238281, + "step": 775, + "valid_targets_mean": 3927.2, + "valid_targets_min": 1667 + }, + { + "epoch": 3.8048780487804876, + "grad_norm": 0.745892500316203, + "learning_rate": 2.0510970312108804e-05, + "loss": 0.2893, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.30204904079437256, + "step": 780, + "valid_targets_mean": 3651.2, + "valid_targets_min": 1125 + }, + { + "epoch": 3.8292682926829267, + "grad_norm": 0.9046132327931361, + "learning_rate": 2.026767224999028e-05, + "loss": 0.3032, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3154948353767395, + "step": 785, + "valid_targets_mean": 2786.5, + "valid_targets_min": 15 + }, + { + "epoch": 3.8536585365853657, + "grad_norm": 0.7325036224094065, + "learning_rate": 2.0024334561413167e-05, + "loss": 0.2907, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29411929845809937, + "step": 790, + "valid_targets_mean": 3472.8, + "valid_targets_min": 827 + }, + { + "epoch": 3.8780487804878048, + "grad_norm": 0.6498743836905022, + "learning_rate": 1.9780993270324063e-05, + "loss": 0.2978, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29405295848846436, + "step": 795, + "valid_targets_mean": 3882.9, + "valid_targets_min": 803 + }, + { + "epoch": 3.902439024390244, + "grad_norm": 0.7094727814399049, + "learning_rate": 1.953768440120289e-05, + "loss": 0.3073, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.3063426613807678, + "step": 800, + "valid_targets_mean": 3734.4, + "valid_targets_min": 1149 + }, + { + "epoch": 3.926829268292683, + "grad_norm": 0.6952694500011949, + "learning_rate": 1.9294443973729768e-05, + "loss": 0.296, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27972686290740967, + "step": 805, + "valid_targets_mean": 4442.4, + "valid_targets_min": 916 + }, + { + "epoch": 3.951219512195122, + "grad_norm": 0.7839669200280891, + "learning_rate": 1.905130799745268e-05, + "loss": 0.2969, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31134629249572754, + "step": 810, + "valid_targets_mean": 3801.6, + "valid_targets_min": 1288 + }, + { + "epoch": 3.975609756097561, + "grad_norm": 0.9512260820024343, + "learning_rate": 1.8808312466456525e-05, + "loss": 0.2856, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2893509864807129, + "step": 815, + "valid_targets_mean": 2878.5, + "valid_targets_min": 719 + }, + { + "epoch": 4.0, + "grad_norm": 0.9409702055658681, + "learning_rate": 1.856549335403457e-05, + "loss": 0.2977, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.252194344997406, + "step": 820, + "valid_targets_mean": 2933.2, + "valid_targets_min": 15 + }, + { + "epoch": 4.024390243902439, + "grad_norm": 0.776260250287857, + "learning_rate": 1.832288660736288e-05, + "loss": 0.2709, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2807005047798157, + "step": 825, + "valid_targets_mean": 3608.9, + "valid_targets_min": 576 + }, + { + "epoch": 4.048780487804878, + "grad_norm": 0.9103236999012465, + "learning_rate": 1.808052814217871e-05, + "loss": 0.2656, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25947239995002747, + "step": 830, + "valid_targets_mean": 2974.0, + "valid_targets_min": 795 + }, + { + "epoch": 4.073170731707317, + "grad_norm": 0.8207458807710281, + "learning_rate": 1.7838453837463498e-05, + "loss": 0.2833, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27700158953666687, + "step": 835, + "valid_targets_mean": 3059.9, + "valid_targets_min": 257 + }, + { + "epoch": 4.097560975609756, + "grad_norm": 0.8039571548469557, + "learning_rate": 1.7596699530131234e-05, + "loss": 0.2617, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27044573426246643, + "step": 840, + "valid_targets_mean": 3390.8, + "valid_targets_min": 1003 + }, + { + "epoch": 4.121951219512195, + "grad_norm": 0.9264411779501436, + "learning_rate": 1.735530100972326e-05, + "loss": 0.2681, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26993459463119507, + "step": 845, + "valid_targets_mean": 3243.6, + "valid_targets_min": 899 + }, + { + "epoch": 4.146341463414634, + "grad_norm": 0.7529964631351728, + "learning_rate": 1.711429401310981e-05, + "loss": 0.2808, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27355536818504333, + "step": 850, + "valid_targets_mean": 4023.1, + "valid_targets_min": 737 + }, + { + "epoch": 4.170731707317073, + "grad_norm": 0.731074690052081, + "learning_rate": 1.687371421919961e-05, + "loss": 0.2702, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.28618645668029785, + "step": 855, + "valid_targets_mean": 3938.9, + "valid_targets_min": 1832 + }, + { + "epoch": 4.195121951219512, + "grad_norm": 0.800079732721868, + "learning_rate": 1.6633597243657855e-05, + "loss": 0.283, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27056562900543213, + "step": 860, + "valid_targets_mean": 3650.1, + "valid_targets_min": 1942 + }, + { + "epoch": 4.219512195121951, + "grad_norm": 0.7533482927823113, + "learning_rate": 1.6393978633633668e-05, + "loss": 0.2692, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2656148076057434, + "step": 865, + "valid_targets_mean": 3817.5, + "valid_targets_min": 1813 + }, + { + "epoch": 4.2439024390243905, + "grad_norm": 0.827289388678526, + "learning_rate": 1.6154893862497673e-05, + "loss": 0.2949, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.31596875190734863, + "step": 870, + "valid_targets_mean": 3127.2, + "valid_targets_min": 15 + }, + { + "epoch": 4.2682926829268295, + "grad_norm": 0.7369615846193128, + "learning_rate": 1.5916378324590437e-05, + "loss": 0.2598, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2373199164867401, + "step": 875, + "valid_targets_mean": 4179.9, + "valid_targets_min": 1584 + }, + { + "epoch": 4.2926829268292686, + "grad_norm": 1.187298637557265, + "learning_rate": 1.5678467329982717e-05, + "loss": 0.267, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2759140729904175, + "step": 880, + "valid_targets_mean": 2973.3, + "valid_targets_min": 228 + }, + { + "epoch": 4.317073170731708, + "grad_norm": 0.8246031829017411, + "learning_rate": 1.54411960992481e-05, + "loss": 0.2786, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2655995190143585, + "step": 885, + "valid_targets_mean": 3138.6, + "valid_targets_min": 474 + }, + { + "epoch": 4.341463414634147, + "grad_norm": 0.8451062461907763, + "learning_rate": 1.5204599758248884e-05, + "loss": 0.2797, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.30422964692115784, + "step": 890, + "valid_targets_mean": 3195.1, + "valid_targets_min": 612 + }, + { + "epoch": 4.365853658536586, + "grad_norm": 0.9965472168956042, + "learning_rate": 1.4968713332936063e-05, + "loss": 0.2648, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2871067523956299, + "step": 895, + "valid_targets_mean": 3281.6, + "valid_targets_min": 1371 + }, + { + "epoch": 4.390243902439025, + "grad_norm": 0.826560392213051, + "learning_rate": 1.473357174416401e-05, + "loss": 0.2589, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2745562493801117, + "step": 900, + "valid_targets_mean": 3754.0, + "valid_targets_min": 1695 + }, + { + "epoch": 4.414634146341464, + "grad_norm": 0.773956566336489, + "learning_rate": 1.4499209802520791e-05, + "loss": 0.2616, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2717684209346771, + "step": 905, + "valid_targets_mean": 3665.7, + "valid_targets_min": 15 + }, + { + "epoch": 4.439024390243903, + "grad_norm": 0.8542711399057813, + "learning_rate": 1.426566220317474e-05, + "loss": 0.2664, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2737499475479126, + "step": 910, + "valid_targets_mean": 3421.7, + "valid_targets_min": 830 + }, + { + "epoch": 4.463414634146342, + "grad_norm": 0.7962556850092083, + "learning_rate": 1.4032963520738183e-05, + "loss": 0.2661, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2802625596523285, + "step": 915, + "valid_targets_mean": 3547.3, + "valid_targets_min": 1008 + }, + { + "epoch": 4.487804878048781, + "grad_norm": 0.7955484777521536, + "learning_rate": 1.3801148204148983e-05, + "loss": 0.2625, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2767943739891052, + "step": 920, + "valid_targets_mean": 3616.8, + "valid_targets_min": 773 + }, + { + "epoch": 4.512195121951219, + "grad_norm": 0.8832279494046948, + "learning_rate": 1.357025057157062e-05, + "loss": 0.2732, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2521354854106903, + "step": 925, + "valid_targets_mean": 3143.2, + "valid_targets_min": 359 + }, + { + "epoch": 4.536585365853659, + "grad_norm": 0.8306588428706537, + "learning_rate": 1.3340304805311802e-05, + "loss": 0.2593, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2435213327407837, + "step": 930, + "valid_targets_mean": 2687.6, + "valid_targets_min": 15 + }, + { + "epoch": 4.560975609756097, + "grad_norm": 0.9185238023912488, + "learning_rate": 1.3111344946765977e-05, + "loss": 0.2576, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2888595461845398, + "step": 935, + "valid_targets_mean": 2984.8, + "valid_targets_min": 1098 + }, + { + "epoch": 4.585365853658536, + "grad_norm": 0.7784668165576322, + "learning_rate": 1.2883404891371907e-05, + "loss": 0.276, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26759079098701477, + "step": 940, + "valid_targets_mean": 3324.6, + "valid_targets_min": 283 + }, + { + "epoch": 4.609756097560975, + "grad_norm": 0.7198225881137529, + "learning_rate": 1.2656518383595681e-05, + "loss": 0.2621, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26038920879364014, + "step": 945, + "valid_targets_mean": 3841.4, + "valid_targets_min": 1226 + }, + { + "epoch": 4.634146341463414, + "grad_norm": 0.8067268967379502, + "learning_rate": 1.243071901193519e-05, + "loss": 0.2676, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2618296444416046, + "step": 950, + "valid_targets_mean": 3059.1, + "valid_targets_min": 1288 + }, + { + "epoch": 4.658536585365853, + "grad_norm": 0.7371365951689539, + "learning_rate": 1.2206040203947645e-05, + "loss": 0.2661, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25615987181663513, + "step": 955, + "valid_targets_mean": 4461.9, + "valid_targets_min": 448 + }, + { + "epoch": 4.682926829268292, + "grad_norm": 0.7267519757978881, + "learning_rate": 1.1982515221300917e-05, + "loss": 0.2624, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24453848600387573, + "step": 960, + "valid_targets_mean": 3733.6, + "valid_targets_min": 1445 + }, + { + "epoch": 4.7073170731707314, + "grad_norm": 0.7178491229060002, + "learning_rate": 1.1760177154849473e-05, + "loss": 0.2558, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23430632054805756, + "step": 965, + "valid_targets_mean": 3454.4, + "valid_targets_min": 647 + }, + { + "epoch": 4.7317073170731705, + "grad_norm": 0.8635688252339446, + "learning_rate": 1.1539058919735557e-05, + "loss": 0.2636, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2552710175514221, + "step": 970, + "valid_targets_mean": 3115.4, + "valid_targets_min": 260 + }, + { + "epoch": 4.7560975609756095, + "grad_norm": 0.8178807633478934, + "learning_rate": 1.1319193250516387e-05, + "loss": 0.2684, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26949605345726013, + "step": 975, + "valid_targets_mean": 3029.0, + "valid_targets_min": 1160 + }, + { + "epoch": 4.780487804878049, + "grad_norm": 0.8606877647771227, + "learning_rate": 1.1100612696318143e-05, + "loss": 0.2707, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2672426998615265, + "step": 980, + "valid_targets_mean": 2994.4, + "valid_targets_min": 597 + }, + { + "epoch": 4.804878048780488, + "grad_norm": 0.8363734717967222, + "learning_rate": 1.0883349616017312e-05, + "loss": 0.2746, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2739032506942749, + "step": 985, + "valid_targets_mean": 2968.4, + "valid_targets_min": 426 + }, + { + "epoch": 4.829268292682927, + "grad_norm": 0.7709748619894506, + "learning_rate": 1.0667436173450278e-05, + "loss": 0.2476, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26799261569976807, + "step": 990, + "valid_targets_mean": 3660.3, + "valid_targets_min": 1059 + }, + { + "epoch": 4.853658536585366, + "grad_norm": 0.8172048769220687, + "learning_rate": 1.0452904332651745e-05, + "loss": 0.2621, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25125956535339355, + "step": 995, + "valid_targets_mean": 2627.2, + "valid_targets_min": 15 + }, + { + "epoch": 4.878048780487805, + "grad_norm": 0.7823743455001714, + "learning_rate": 1.0239785853122784e-05, + "loss": 0.265, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.265064537525177, + "step": 1000, + "valid_targets_mean": 3875.0, + "valid_targets_min": 15 + }, + { + "epoch": 4.902439024390244, + "grad_norm": 0.7650125864589816, + "learning_rate": 1.0028112285129058e-05, + "loss": 0.2654, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.29131659865379333, + "step": 1005, + "valid_targets_mean": 3470.4, + "valid_targets_min": 786 + }, + { + "epoch": 4.926829268292683, + "grad_norm": 0.668827826218542, + "learning_rate": 9.81791496503015e-06, + "loss": 0.2616, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2571777105331421, + "step": 1010, + "valid_targets_mean": 4372.1, + "valid_targets_min": 1355 + }, + { + "epoch": 4.951219512195122, + "grad_norm": 0.6873823999708377, + "learning_rate": 9.60922501064049e-06, + "loss": 0.2582, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2555577754974365, + "step": 1015, + "valid_targets_mean": 4297.0, + "valid_targets_min": 1361 + }, + { + "epoch": 4.975609756097561, + "grad_norm": 0.7801780285443586, + "learning_rate": 9.402073316622609e-06, + "loss": 0.2536, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24865934252738953, + "step": 1020, + "valid_targets_mean": 3150.4, + "valid_targets_min": 875 + }, + { + "epoch": 5.0, + "grad_norm": 0.7967802474346398, + "learning_rate": 9.196490549913486e-06, + "loss": 0.2622, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2609595060348511, + "step": 1025, + "valid_targets_mean": 3708.4, + "valid_targets_min": 1052 + }, + { + "epoch": 5.024390243902439, + "grad_norm": 0.6513129597791458, + "learning_rate": 8.992507145184613e-06, + "loss": 0.2405, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2445092499256134, + "step": 1030, + "valid_targets_mean": 4137.7, + "valid_targets_min": 448 + }, + { + "epoch": 5.048780487804878, + "grad_norm": 0.9278929525940717, + "learning_rate": 8.79015330033635e-06, + "loss": 0.2438, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24177995324134827, + "step": 1035, + "valid_targets_mean": 3097.0, + "valid_targets_min": 1277 + }, + { + "epoch": 5.073170731707317, + "grad_norm": 1.552193652315139, + "learning_rate": 8.589458972027483e-06, + "loss": 0.2436, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24827489256858826, + "step": 1040, + "valid_targets_mean": 3416.3, + "valid_targets_min": 1001 + }, + { + "epoch": 5.097560975609756, + "grad_norm": 0.7093858199198262, + "learning_rate": 8.390453871240307e-06, + "loss": 0.2453, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23724865913391113, + "step": 1045, + "valid_targets_mean": 4210.4, + "valid_targets_min": 1619 + }, + { + "epoch": 5.121951219512195, + "grad_norm": 1.0012021920667462, + "learning_rate": 8.193167458882292e-06, + "loss": 0.2446, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.27012312412261963, + "step": 1050, + "valid_targets_mean": 2548.9, + "valid_targets_min": 641 + }, + { + "epoch": 5.146341463414634, + "grad_norm": 0.8690910331604649, + "learning_rate": 7.9976289414246e-06, + "loss": 0.2452, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2542031705379486, + "step": 1055, + "valid_targets_mean": 2743.4, + "valid_targets_min": 744 + }, + { + "epoch": 5.170731707317073, + "grad_norm": 1.044901979443724, + "learning_rate": 7.803867266578329e-06, + "loss": 0.2373, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25191807746887207, + "step": 1060, + "valid_targets_mean": 3127.7, + "valid_targets_min": 906 + }, + { + "epoch": 5.195121951219512, + "grad_norm": 0.9050120681858465, + "learning_rate": 7.611911119009092e-06, + "loss": 0.2536, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2629399001598358, + "step": 1065, + "valid_targets_mean": 3758.2, + "valid_targets_min": 376 + }, + { + "epoch": 5.219512195121951, + "grad_norm": 0.9283099215477023, + "learning_rate": 7.4217889160904824e-06, + "loss": 0.2544, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2586513161659241, + "step": 1070, + "valid_targets_mean": 2433.7, + "valid_targets_min": 228 + }, + { + "epoch": 5.2439024390243905, + "grad_norm": 0.8259428205883735, + "learning_rate": 7.233528803697185e-06, + "loss": 0.2452, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24752004444599152, + "step": 1075, + "valid_targets_mean": 3368.4, + "valid_targets_min": 741 + }, + { + "epoch": 5.2682926829268295, + "grad_norm": 0.7209136325847043, + "learning_rate": 7.0471586520381796e-06, + "loss": 0.2497, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23628446459770203, + "step": 1080, + "valid_targets_mean": 4003.1, + "valid_targets_min": 730 + }, + { + "epoch": 5.2926829268292686, + "grad_norm": 0.7406882461573, + "learning_rate": 6.8627060515308275e-06, + "loss": 0.2494, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23052799701690674, + "step": 1085, + "valid_targets_mean": 3915.6, + "valid_targets_min": 895 + }, + { + "epoch": 5.317073170731708, + "grad_norm": 0.9022661536003552, + "learning_rate": 6.6801983087163944e-06, + "loss": 0.2514, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2609993815422058, + "step": 1090, + "valid_targets_mean": 3229.1, + "valid_targets_min": 1347 + }, + { + "epoch": 5.341463414634147, + "grad_norm": 0.6825772427499014, + "learning_rate": 6.499662442217496e-06, + "loss": 0.2406, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22986085712909698, + "step": 1095, + "valid_targets_mean": 4128.3, + "valid_targets_min": 808 + }, + { + "epoch": 5.365853658536586, + "grad_norm": 0.9787201186348055, + "learning_rate": 6.3211251787383146e-06, + "loss": 0.2506, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26659125089645386, + "step": 1100, + "valid_targets_mean": 2601.8, + "valid_targets_min": 778 + }, + { + "epoch": 5.390243902439025, + "grad_norm": 0.7673661220615522, + "learning_rate": 6.144612949107858e-06, + "loss": 0.2786, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24559593200683594, + "step": 1105, + "valid_targets_mean": 4265.2, + "valid_targets_min": 1373 + }, + { + "epoch": 5.414634146341464, + "grad_norm": 0.9843589364752354, + "learning_rate": 5.970151884367206e-06, + "loss": 0.2648, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2827834486961365, + "step": 1110, + "valid_targets_mean": 2506.9, + "valid_targets_min": 15 + }, + { + "epoch": 5.439024390243903, + "grad_norm": 0.7949717862044275, + "learning_rate": 5.7977678119010025e-06, + "loss": 0.2537, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24906060099601746, + "step": 1115, + "valid_targets_mean": 3294.9, + "valid_targets_min": 444 + }, + { + "epoch": 5.463414634146342, + "grad_norm": 0.9750761574373105, + "learning_rate": 5.627486251613934e-06, + "loss": 0.2409, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24433453381061554, + "step": 1120, + "valid_targets_mean": 2488.4, + "valid_targets_min": 215 + }, + { + "epoch": 5.487804878048781, + "grad_norm": 0.8567488259221477, + "learning_rate": 5.4593324121527554e-06, + "loss": 0.2649, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26337265968322754, + "step": 1125, + "valid_targets_mean": 3024.3, + "valid_targets_min": 959 + }, + { + "epoch": 5.512195121951219, + "grad_norm": 0.812251328892105, + "learning_rate": 5.293331187174369e-06, + "loss": 0.252, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23273511230945587, + "step": 1130, + "valid_targets_mean": 2921.6, + "valid_targets_min": 347 + }, + { + "epoch": 5.536585365853659, + "grad_norm": 1.075912086276383, + "learning_rate": 5.129507151660566e-06, + "loss": 0.2579, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26345235109329224, + "step": 1135, + "valid_targets_mean": 2968.8, + "valid_targets_min": 645 + }, + { + "epoch": 5.560975609756097, + "grad_norm": 0.7590504022526489, + "learning_rate": 4.967884558279894e-06, + "loss": 0.2434, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22883421182632446, + "step": 1140, + "valid_targets_mean": 3830.3, + "valid_targets_min": 477 + }, + { + "epoch": 5.585365853658536, + "grad_norm": 0.9309391468937491, + "learning_rate": 4.808487333797272e-06, + "loss": 0.2543, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26027998328208923, + "step": 1145, + "valid_targets_mean": 2935.4, + "valid_targets_min": 1080 + }, + { + "epoch": 5.609756097560975, + "grad_norm": 0.9093755260374964, + "learning_rate": 4.651339075531873e-06, + "loss": 0.2622, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2955099642276764, + "step": 1150, + "valid_targets_mean": 2912.1, + "valid_targets_min": 1208 + }, + { + "epoch": 5.634146341463414, + "grad_norm": 0.7573696056760568, + "learning_rate": 4.496463047863728e-06, + "loss": 0.248, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24394544959068298, + "step": 1155, + "valid_targets_mean": 3498.8, + "valid_targets_min": 1321 + }, + { + "epoch": 5.658536585365853, + "grad_norm": 0.766437897262525, + "learning_rate": 4.343882178789649e-06, + "loss": 0.2457, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25831907987594604, + "step": 1160, + "valid_targets_mean": 3925.3, + "valid_targets_min": 1203 + }, + { + "epoch": 5.682926829268292, + "grad_norm": 0.685642357911014, + "learning_rate": 4.193619056528968e-06, + "loss": 0.2536, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23799964785575867, + "step": 1165, + "valid_targets_mean": 4780.6, + "valid_targets_min": 1015 + }, + { + "epoch": 5.7073170731707314, + "grad_norm": 0.8782575976505613, + "learning_rate": 4.045695926179518e-06, + "loss": 0.2331, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25392627716064453, + "step": 1170, + "valid_targets_mean": 3876.3, + "valid_targets_min": 15 + }, + { + "epoch": 5.7317073170731705, + "grad_norm": 0.6746053110171998, + "learning_rate": 3.900134686424497e-06, + "loss": 0.2461, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22202837467193604, + "step": 1175, + "valid_targets_mean": 4104.9, + "valid_targets_min": 1062 + }, + { + "epoch": 5.7560975609756095, + "grad_norm": 0.808869320274757, + "learning_rate": 3.756956886290497e-06, + "loss": 0.2532, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26272523403167725, + "step": 1180, + "valid_targets_mean": 3688.8, + "valid_targets_min": 1201 + }, + { + "epoch": 5.780487804878049, + "grad_norm": 0.8464273251163792, + "learning_rate": 3.6161837219574423e-06, + "loss": 0.244, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26603326201438904, + "step": 1185, + "valid_targets_mean": 2798.3, + "valid_targets_min": 1006 + }, + { + "epoch": 5.804878048780488, + "grad_norm": 0.9647474178559449, + "learning_rate": 3.477836033620623e-06, + "loss": 0.2452, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26358962059020996, + "step": 1190, + "valid_targets_mean": 2401.4, + "valid_targets_min": 383 + }, + { + "epoch": 5.829268292682927, + "grad_norm": 0.9304341033869954, + "learning_rate": 3.3419343024055385e-06, + "loss": 0.2456, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2455274760723114, + "step": 1195, + "valid_targets_mean": 2808.2, + "valid_targets_min": 940 + }, + { + "epoch": 5.853658536585366, + "grad_norm": 0.890111073772623, + "learning_rate": 3.208498647335818e-06, + "loss": 0.2436, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2638408839702606, + "step": 1200, + "valid_targets_mean": 3505.1, + "valid_targets_min": 284 + }, + { + "epoch": 5.878048780487805, + "grad_norm": 0.7108698871221218, + "learning_rate": 3.0775488223547946e-06, + "loss": 0.2497, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25884100794792175, + "step": 1205, + "valid_targets_mean": 4374.9, + "valid_targets_min": 859 + }, + { + "epoch": 5.902439024390244, + "grad_norm": 0.7134129262752172, + "learning_rate": 2.949104213401126e-06, + "loss": 0.2358, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23458099365234375, + "step": 1210, + "valid_targets_mean": 4402.4, + "valid_targets_min": 960 + }, + { + "epoch": 5.926829268292683, + "grad_norm": 0.766327851314873, + "learning_rate": 2.8231838355388564e-06, + "loss": 0.2607, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26184824109077454, + "step": 1215, + "valid_targets_mean": 3815.8, + "valid_targets_min": 893 + }, + { + "epoch": 5.951219512195122, + "grad_norm": 1.1353404399035876, + "learning_rate": 2.6998063301424183e-06, + "loss": 0.2592, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25338470935821533, + "step": 1220, + "valid_targets_mean": 2824.6, + "valid_targets_min": 15 + }, + { + "epoch": 5.975609756097561, + "grad_norm": 0.8927504722814279, + "learning_rate": 2.5789899621369576e-06, + "loss": 0.2397, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24313412606716156, + "step": 1225, + "valid_targets_mean": 3381.8, + "valid_targets_min": 317 + }, + { + "epoch": 6.0, + "grad_norm": 0.5993805237959021, + "learning_rate": 2.4607526172943573e-06, + "loss": 0.2363, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22973109781742096, + "step": 1230, + "valid_targets_mean": 5376.5, + "valid_targets_min": 1426 + }, + { + "epoch": 6.024390243902439, + "grad_norm": 0.8354731757428007, + "learning_rate": 2.345111799585418e-06, + "loss": 0.231, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2252325713634491, + "step": 1235, + "valid_targets_mean": 3432.8, + "valid_targets_min": 15 + }, + { + "epoch": 6.048780487804878, + "grad_norm": 0.6750361987361632, + "learning_rate": 2.2320846285885536e-06, + "loss": 0.2403, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18881835043430328, + "step": 1240, + "valid_targets_mean": 4703.5, + "valid_targets_min": 909 + }, + { + "epoch": 6.073170731707317, + "grad_norm": 0.8147913212830856, + "learning_rate": 2.1216878369554018e-06, + "loss": 0.2407, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23672699928283691, + "step": 1245, + "valid_targets_mean": 3134.4, + "valid_targets_min": 730 + }, + { + "epoch": 6.097560975609756, + "grad_norm": 0.7466076107590293, + "learning_rate": 2.0139377679336914e-06, + "loss": 0.2312, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22420379519462585, + "step": 1250, + "valid_targets_mean": 3622.1, + "valid_targets_min": 424 + }, + { + "epoch": 6.121951219512195, + "grad_norm": 0.7651624761198161, + "learning_rate": 1.908850372947775e-06, + "loss": 0.2404, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2247518002986908, + "step": 1255, + "valid_targets_mean": 4336.2, + "valid_targets_min": 641 + }, + { + "epoch": 6.146341463414634, + "grad_norm": 1.0311971502086403, + "learning_rate": 1.8064412092371687e-06, + "loss": 0.2417, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23574134707450867, + "step": 1260, + "valid_targets_mean": 2097.2, + "valid_targets_min": 15 + }, + { + "epoch": 6.170731707317073, + "grad_norm": 0.8187942030961283, + "learning_rate": 1.7067254375534426e-06, + "loss": 0.2408, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22960010170936584, + "step": 1265, + "valid_targets_mean": 3018.4, + "valid_targets_min": 1903 + }, + { + "epoch": 6.195121951219512, + "grad_norm": 1.029146328727017, + "learning_rate": 1.6097178199158147e-06, + "loss": 0.2446, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23877152800559998, + "step": 1270, + "valid_targets_mean": 3062.9, + "valid_targets_min": 15 + }, + { + "epoch": 6.219512195121951, + "grad_norm": 0.8154855502925126, + "learning_rate": 1.5154327174257487e-06, + "loss": 0.2331, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2658793330192566, + "step": 1275, + "valid_targets_mean": 3184.2, + "valid_targets_min": 879 + }, + { + "epoch": 6.2439024390243905, + "grad_norm": 0.8092122258788375, + "learning_rate": 1.4238840881409411e-06, + "loss": 0.2454, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.25030407309532166, + "step": 1280, + "valid_targets_mean": 3467.3, + "valid_targets_min": 979 + }, + { + "epoch": 6.2682926829268295, + "grad_norm": 0.7990164724748857, + "learning_rate": 1.3350854850089556e-06, + "loss": 0.2436, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24833282828330994, + "step": 1285, + "valid_targets_mean": 3502.2, + "valid_targets_min": 947 + }, + { + "epoch": 6.2926829268292686, + "grad_norm": 0.9741101055525349, + "learning_rate": 1.2490500538608186e-06, + "loss": 0.2494, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23695826530456543, + "step": 1290, + "valid_targets_mean": 3103.2, + "valid_targets_min": 734 + }, + { + "epoch": 6.317073170731708, + "grad_norm": 0.7866383371157202, + "learning_rate": 1.1657905314649054e-06, + "loss": 0.2477, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23404628038406372, + "step": 1295, + "valid_targets_mean": 3434.3, + "valid_targets_min": 518 + }, + { + "epoch": 6.341463414634147, + "grad_norm": 1.052443778688222, + "learning_rate": 1.0853192436413761e-06, + "loss": 0.2414, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26550811529159546, + "step": 1300, + "valid_targets_mean": 2595.0, + "valid_targets_min": 15 + }, + { + "epoch": 6.365853658536586, + "grad_norm": 0.7368539211291545, + "learning_rate": 1.0076481034374597e-06, + "loss": 0.2386, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22750580310821533, + "step": 1305, + "valid_targets_mean": 4232.3, + "valid_targets_min": 1352 + }, + { + "epoch": 6.390243902439025, + "grad_norm": 0.8172404431791918, + "learning_rate": 9.327886093638217e-07, + "loss": 0.2396, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.228601336479187, + "step": 1310, + "valid_targets_mean": 3308.4, + "valid_targets_min": 745 + }, + { + "epoch": 6.414634146341464, + "grad_norm": 0.9556714377855368, + "learning_rate": 8.607518436923024e-07, + "loss": 0.2352, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22058895230293274, + "step": 1315, + "valid_targets_mean": 3972.5, + "valid_targets_min": 1721 + }, + { + "epoch": 6.439024390243903, + "grad_norm": 0.8574584113032061, + "learning_rate": 7.915484708153221e-07, + "loss": 0.2365, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23830386996269226, + "step": 1320, + "valid_targets_mean": 3130.8, + "valid_targets_min": 244 + }, + { + "epoch": 6.463414634146342, + "grad_norm": 0.7867469974906987, + "learning_rate": 7.251887356670795e-07, + "loss": 0.2262, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2254469245672226, + "step": 1325, + "valid_targets_mean": 3359.5, + "valid_targets_min": 880 + }, + { + "epoch": 6.487804878048781, + "grad_norm": 0.7986596207181103, + "learning_rate": 6.616824622069029e-07, + "loss": 0.2411, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22942882776260376, + "step": 1330, + "valid_targets_mean": 3246.1, + "valid_targets_min": 15 + }, + { + "epoch": 6.512195121951219, + "grad_norm": 0.8394244430546116, + "learning_rate": 6.010390519648956e-07, + "loss": 0.2348, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23827606439590454, + "step": 1335, + "valid_targets_mean": 3922.2, + "valid_targets_min": 748 + }, + { + "epoch": 6.536585365853659, + "grad_norm": 1.0223514496941088, + "learning_rate": 5.432674826501116e-07, + "loss": 0.2437, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2501652240753174, + "step": 1340, + "valid_targets_mean": 2854.8, + "valid_targets_min": 730 + }, + { + "epoch": 6.560975609756097, + "grad_norm": 0.8493598124019298, + "learning_rate": 4.883763068215142e-07, + "loss": 0.2404, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2515867352485657, + "step": 1345, + "valid_targets_mean": 3138.7, + "valid_targets_min": 638 + }, + { + "epoch": 6.585365853658536, + "grad_norm": 0.9193382117725917, + "learning_rate": 4.363736506218197e-07, + "loss": 0.244, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26839739084243774, + "step": 1350, + "valid_targets_mean": 2877.6, + "valid_targets_min": 15 + }, + { + "epoch": 6.609756097560975, + "grad_norm": 0.8621845943305007, + "learning_rate": 3.8726721257451137e-07, + "loss": 0.2422, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23818087577819824, + "step": 1355, + "valid_targets_mean": 3133.2, + "valid_targets_min": 699 + }, + { + "epoch": 6.634146341463414, + "grad_norm": 0.9578375613810739, + "learning_rate": 3.410642624441352e-07, + "loss": 0.2375, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24605871737003326, + "step": 1360, + "valid_targets_mean": 2749.3, + "valid_targets_min": 383 + }, + { + "epoch": 6.658536585365853, + "grad_norm": 0.8904495992448669, + "learning_rate": 2.977716401600894e-07, + "loss": 0.2312, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24474391341209412, + "step": 1365, + "valid_targets_mean": 2796.8, + "valid_targets_min": 954 + }, + { + "epoch": 6.682926829268292, + "grad_norm": 0.8518441087464355, + "learning_rate": 2.573957548040107e-07, + "loss": 0.2184, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19270995259284973, + "step": 1370, + "valid_targets_mean": 3499.1, + "valid_targets_min": 893 + }, + { + "epoch": 6.7073170731707314, + "grad_norm": 0.7685128175135679, + "learning_rate": 2.1994258366099253e-07, + "loss": 0.2417, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24854759871959686, + "step": 1375, + "valid_targets_mean": 3583.8, + "valid_targets_min": 744 + }, + { + "epoch": 6.7317073170731705, + "grad_norm": 0.8337143588524125, + "learning_rate": 1.854176713346867e-07, + "loss": 0.2674, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2495569884777069, + "step": 1380, + "valid_targets_mean": 3424.1, + "valid_targets_min": 755 + }, + { + "epoch": 6.7560975609756095, + "grad_norm": 0.8172528668416672, + "learning_rate": 1.538261289264842e-07, + "loss": 0.2371, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2521843910217285, + "step": 1385, + "valid_targets_mean": 3401.9, + "valid_targets_min": 1633 + }, + { + "epoch": 6.780487804878049, + "grad_norm": 0.7445112746003925, + "learning_rate": 1.2517263327884944e-07, + "loss": 0.2609, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2370169758796692, + "step": 1390, + "valid_targets_mean": 3845.2, + "valid_targets_min": 474 + }, + { + "epoch": 6.804878048780488, + "grad_norm": 0.7797928451134836, + "learning_rate": 9.94614262829785e-08, + "loss": 0.2384, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23094391822814941, + "step": 1395, + "valid_targets_mean": 3594.2, + "valid_targets_min": 1001 + }, + { + "epoch": 6.829268292682927, + "grad_norm": 0.8197547024772956, + "learning_rate": 7.669631425079705e-08, + "loss": 0.2448, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.23373377323150635, + "step": 1400, + "valid_targets_mean": 3304.5, + "valid_targets_min": 959 + }, + { + "epoch": 6.853658536585366, + "grad_norm": 0.819098164874208, + "learning_rate": 5.6880667351497664e-08, + "loss": 0.235, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2553420662879944, + "step": 1405, + "valid_targets_mean": 3185.7, + "valid_targets_min": 1009 + }, + { + "epoch": 6.878048780487805, + "grad_norm": 0.7376496931499309, + "learning_rate": 4.00174191125946e-08, + "loss": 0.2342, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24166685342788696, + "step": 1410, + "valid_targets_mean": 4154.6, + "valid_targets_min": 1356 + }, + { + "epoch": 6.902439024390244, + "grad_norm": 0.7007641583033006, + "learning_rate": 2.6109065985655547e-08, + "loss": 0.2368, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.22494983673095703, + "step": 1415, + "valid_targets_mean": 4674.7, + "valid_targets_min": 1114 + }, + { + "epoch": 6.926829268292683, + "grad_norm": 0.9573315937952928, + "learning_rate": 1.515766697672172e-08, + "loss": 0.2396, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2521101236343384, + "step": 1420, + "valid_targets_mean": 3319.0, + "valid_targets_min": 1386 + }, + { + "epoch": 6.951219512195122, + "grad_norm": 0.7016789049970602, + "learning_rate": 7.16484334148504e-09, + "loss": 0.2342, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2223004400730133, + "step": 1425, + "valid_targets_mean": 4016.6, + "valid_targets_min": 928 + }, + { + "epoch": 6.975609756097561, + "grad_norm": 0.8796275429117553, + "learning_rate": 2.1317783452823315e-09, + "loss": 0.2378, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2460535764694214, + "step": 1430, + "valid_targets_mean": 2961.6, + "valid_targets_min": 1039 + }, + { + "epoch": 7.0, + "grad_norm": 0.8974037466412109, + "learning_rate": 5.921708791767344e-11, + "loss": 0.2521, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24434766173362732, + "step": 1435, + "valid_targets_mean": 2891.9, + "valid_targets_min": 658 + }, + { + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.24434766173362732, + "step": 1435, + "total_flos": 459870247321600.0, + "train_loss": 0.3203928537069713, + "train_runtime": 9814.9228, + "train_samples_per_second": 2.332, + "train_steps_per_second": 0.146, + "valid_targets_mean": 2891.9, + "valid_targets_min": 658 + } + ], + "logging_steps": 5, + "max_steps": 1435, + "num_input_tokens_seen": 0, + "num_train_epochs": 7, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 459870247321600.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..17cd03c --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e2f04ef077bc3f818f1df077fcf3f981bd7ad3e1921a112ea0a18268201990 +size 8785 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..65710ab 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