commit 4e220f32fac27bca9d60a7373bc6d6cc96096fc6 Author: ModelHub XC Date: Sun Aug 9 11:49:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: laion/exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5e69b43 --- /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 + +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +training_args.bin 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..1ef6e9f --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: Qwen/Qwen3-8B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: sft__exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi + results: [] +--- + + + +# sft__exp-syh-r2egym-askllm-constrained_glm_4-7_traces_jupiter_cleaned-exp-gfi-swesmith-random-fi + +This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-syh-r2egym-askllm-constrained_glm_4.7_traces_jupiter_cleaned/snapshots/d13cd4ded646d8380dc70005a25fadeae9836514_thinking_preprocessed and the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-gfi-swesmith-random-filtered-10K_glm_4.7_traces_jupiter/snapshots/cb971aef68078d7bd025e0d8c33040bba180d914_thinking_preprocessed datasets. + +## 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: 32 +- gradient_accumulation_steps: 3 +- total_train_batch_size: 96 +- total_eval_batch_size: 256 +- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 7.0 + +### Training results + + + +### Framework versions + +- Transformers 4.57.6 +- Pytorch 2.9.1+cu130 +- Datasets 4.7.0 +- Tokenizers 0.22.2 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..9a34fd7 --- /dev/null +++ b/all_results.json @@ -0,0 +1,16 @@ +{ + "achieved_tflops_per_gpu": 243953.4620453116, + "achieved_tflops_per_gpu_theoretical": 5579919.469824511, + "epoch": 7.0, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07613854110240936, + "mfu_percent": 17240.527353025554, + "mfu_percent_theoretical": 394340.5985741704, + "total_flos": 6.436468142603502e+18, + "train_loss": 0.0, + "train_runtime": 0.8245, + "train_samples_per_second": 157900.906, + "train_steps_per_second": 1647.012, + "valid_targets_mean": 5572.4, + "valid_targets_min": 657 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..59b4193 --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9adbb28 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.57.6" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..10adb49 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1ab0ae3bf99889426fc1d409cc970f1aaeee20ca5264a26ed937b4d587c2c7 +size 4902257696 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..cfecc3d --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa7dc79fee34fef77aee71b1b3f4b23f55e41b77476f0b348746f587065e282 +size 4915960368 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..adf2d37 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22a77c65c7fcca5251650eb9551321909edba34e1cf5380a64bb9c728542f56 +size 4983068496 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..21f1c8a --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ca38a9b7d8219700ffd3edc1c4468d0e3c50397a4560309ab0886b40ba6eb4 +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..c504197 --- /dev/null +++ b/run_summary.json @@ -0,0 +1,12 @@ +{ + "agent_name": "cb971aef68078d7bd025e0d8c33040bba180d914_thinking_preprocessed", + "training_start": null, + "training_end": null, + "created_by": "DCAgent", + "base_model_name": "Qwen/Qwen3-8B", + "dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-syh-r2egym-askllm-constrained_glm_4.7_traces_jupiter_cleaned/snapshots/d13cd4ded646d8380dc70005a25fadeae9836514_thinking_preprocessed,/e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp-gfi-swesmith-random-filtered-10K_glm_4.7_traces_jupiter/snapshots/cb971aef68078d7bd025e0d8c33040bba180d914_thinking_preprocessed", + "training_type": "SFT", + "training_parameters": "https://huggingface.co/laion/r2egym-askllm-constrained-swesmith-random-filtered/blob/main/config.json", + "wandb_link": null, + "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..999ac8f --- /dev/null +++ b/train_results.json @@ -0,0 +1,12 @@ +{ + "achieved_tflops_per_gpu": 243953.4620453116, + "achieved_tflops_per_gpu_theoretical": 5579919.469824511, + "epoch": 7.0, + "mfu_percent": 17240.527353025554, + "mfu_percent_theoretical": 394340.5985741704, + "total_flos": 6.436468142603502e+18, + "train_loss": 0.0, + "train_runtime": 0.8245, + "train_samples_per_second": 157900.906, + "train_steps_per_second": 1647.012 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..fb93162 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,276 @@ +{"current_steps": 5, "total_steps": 1358, "loss": 0.7739, "lr": 1.1764705882352942e-06, "epoch": 0.02577319587628866, "percentage": 0.37, "elapsed_time": "0:02:35", "remaining_time": "11:43:33"} +{"current_steps": 10, "total_steps": 1358, "loss": 0.747, "lr": 2.647058823529412e-06, "epoch": 0.05154639175257732, "percentage": 0.74, "elapsed_time": "0:05:03", "remaining_time": "11:21:22"} +{"current_steps": 15, "total_steps": 1358, "loss": 0.6522, "lr": 4.11764705882353e-06, "epoch": 0.07731958762886598, "percentage": 1.1, "elapsed_time": "0:07:30", "remaining_time": "11:11:35"} +{"current_steps": 20, "total_steps": 1358, "loss": 0.5807, "lr": 5.588235294117647e-06, "epoch": 0.10309278350515463, "percentage": 1.47, "elapsed_time": "0:09:55", "remaining_time": "11:03:53"} +{"current_steps": 25, "total_steps": 1358, "loss": 0.5389, "lr": 7.058823529411766e-06, "epoch": 0.12886597938144329, "percentage": 1.84, "elapsed_time": "0:12:21", "remaining_time": "10:59:12"} +{"current_steps": 30, "total_steps": 1358, "loss": 0.5272, "lr": 8.529411764705883e-06, "epoch": 0.15463917525773196, "percentage": 2.21, "elapsed_time": "0:14:47", "remaining_time": "10:54:35"} +{"current_steps": 35, "total_steps": 1358, "loss": 0.496, "lr": 1e-05, "epoch": 0.18041237113402062, "percentage": 2.58, "elapsed_time": "0:17:14", "remaining_time": "10:51:31"} +{"current_steps": 40, "total_steps": 1358, "loss": 0.487, "lr": 1.1470588235294118e-05, "epoch": 0.20618556701030927, "percentage": 2.95, "elapsed_time": "0:19:39", "remaining_time": "10:47:48"} +{"current_steps": 45, "total_steps": 1358, "loss": 0.4661, "lr": 1.2941176470588238e-05, "epoch": 0.23195876288659795, "percentage": 3.31, "elapsed_time": "0:22:07", "remaining_time": "10:45:44"} +{"current_steps": 50, "total_steps": 1358, "loss": 0.4478, "lr": 1.4411764705882353e-05, "epoch": 0.25773195876288657, "percentage": 3.68, "elapsed_time": "0:24:29", "remaining_time": "10:40:50"} +{"current_steps": 55, "total_steps": 1358, "loss": 0.4307, "lr": 1.5882352941176473e-05, "epoch": 0.28350515463917525, "percentage": 4.05, "elapsed_time": "0:26:53", "remaining_time": "10:37:08"} +{"current_steps": 60, "total_steps": 1358, "loss": 0.4226, "lr": 1.735294117647059e-05, "epoch": 0.30927835051546393, "percentage": 4.42, "elapsed_time": "0:29:17", "remaining_time": "10:33:47"} +{"current_steps": 65, "total_steps": 1358, "loss": 0.4034, "lr": 1.8823529411764708e-05, "epoch": 0.33505154639175255, "percentage": 4.79, "elapsed_time": "0:31:47", "remaining_time": "10:32:23"} +{"current_steps": 70, "total_steps": 1358, "loss": 0.4074, "lr": 2.0294117647058825e-05, "epoch": 0.36082474226804123, "percentage": 5.15, "elapsed_time": "0:34:14", "remaining_time": "10:29:54"} +{"current_steps": 75, "total_steps": 1358, "loss": 0.3876, "lr": 2.1764705882352943e-05, "epoch": 0.3865979381443299, "percentage": 5.52, "elapsed_time": "0:36:37", "remaining_time": "10:26:25"} +{"current_steps": 80, "total_steps": 1358, "loss": 0.376, "lr": 2.3235294117647064e-05, "epoch": 0.41237113402061853, "percentage": 5.89, "elapsed_time": "0:39:02", "remaining_time": "10:23:36"} +{"current_steps": 85, "total_steps": 1358, "loss": 0.3845, "lr": 2.470588235294118e-05, "epoch": 0.4381443298969072, "percentage": 6.26, "elapsed_time": "0:41:25", "remaining_time": "10:20:22"} +{"current_steps": 90, "total_steps": 1358, "loss": 0.3754, "lr": 2.6176470588235295e-05, "epoch": 0.4639175257731959, "percentage": 6.63, "elapsed_time": "0:43:52", "remaining_time": "10:18:04"} +{"current_steps": 95, "total_steps": 1358, "loss": 0.3617, "lr": 2.7647058823529413e-05, "epoch": 0.4896907216494845, "percentage": 7.0, "elapsed_time": "0:46:15", "remaining_time": "10:14:55"} +{"current_steps": 100, "total_steps": 1358, "loss": 0.3555, "lr": 2.911764705882353e-05, "epoch": 0.5154639175257731, "percentage": 7.36, "elapsed_time": "0:48:40", "remaining_time": "10:12:22"} +{"current_steps": 105, "total_steps": 1358, "loss": 0.3549, "lr": 3.0588235294117644e-05, "epoch": 0.5412371134020618, "percentage": 7.73, "elapsed_time": "0:51:02", "remaining_time": "10:09:09"} +{"current_steps": 110, "total_steps": 1358, "loss": 0.344, "lr": 3.205882352941177e-05, "epoch": 0.5670103092783505, "percentage": 8.1, "elapsed_time": "0:53:25", "remaining_time": "10:06:12"} +{"current_steps": 115, "total_steps": 1358, "loss": 0.3511, "lr": 3.3529411764705886e-05, "epoch": 0.5927835051546392, "percentage": 8.47, "elapsed_time": "0:55:53", "remaining_time": "10:04:02"} +{"current_steps": 120, "total_steps": 1358, "loss": 0.341, "lr": 3.5000000000000004e-05, "epoch": 0.6185567010309279, "percentage": 8.84, "elapsed_time": "0:58:20", "remaining_time": "10:01:56"} +{"current_steps": 125, "total_steps": 1358, "loss": 0.3343, "lr": 3.647058823529412e-05, "epoch": 0.6443298969072165, "percentage": 9.2, "elapsed_time": "1:00:45", "remaining_time": "9:59:16"} +{"current_steps": 130, "total_steps": 1358, "loss": 0.3471, "lr": 3.794117647058824e-05, "epoch": 0.6701030927835051, "percentage": 9.57, "elapsed_time": "1:03:09", "remaining_time": "9:56:36"} +{"current_steps": 135, "total_steps": 1358, "loss": 0.3413, "lr": 3.9411764705882356e-05, "epoch": 0.6958762886597938, "percentage": 9.94, "elapsed_time": "1:05:35", "remaining_time": "9:54:09"} +{"current_steps": 140, "total_steps": 1358, "loss": 0.3306, "lr": 3.999940516338956e-05, "epoch": 0.7216494845360825, "percentage": 10.31, "elapsed_time": "1:08:02", "remaining_time": "9:52:01"} +{"current_steps": 145, "total_steps": 1358, "loss": 0.3175, "lr": 3.99957701789056e-05, "epoch": 0.7474226804123711, "percentage": 10.68, "elapsed_time": "1:10:29", "remaining_time": "9:49:44"} +{"current_steps": 150, "total_steps": 1358, "loss": 0.3232, "lr": 3.998883127460509e-05, "epoch": 0.7731958762886598, "percentage": 11.05, "elapsed_time": "1:12:50", "remaining_time": "9:46:39"} +{"current_steps": 155, "total_steps": 1358, "loss": 0.3359, "lr": 3.997858959700969e-05, "epoch": 0.7989690721649485, "percentage": 11.41, "elapsed_time": "1:15:15", "remaining_time": "9:44:06"} +{"current_steps": 160, "total_steps": 1358, "loss": 0.324, "lr": 3.996504683836136e-05, "epoch": 0.8247422680412371, "percentage": 11.78, "elapsed_time": "1:17:37", "remaining_time": "9:41:10"} +{"current_steps": 165, "total_steps": 1358, "loss": 0.3245, "lr": 3.994820523634279e-05, "epoch": 0.8505154639175257, "percentage": 12.15, "elapsed_time": "1:20:03", "remaining_time": "9:38:49"} +{"current_steps": 170, "total_steps": 1358, "loss": 0.3248, "lr": 3.992806757370764e-05, "epoch": 0.8762886597938144, "percentage": 12.52, "elapsed_time": "1:22:28", "remaining_time": "9:36:19"} +{"current_steps": 175, "total_steps": 1358, "loss": 0.3137, "lr": 3.990463717782074e-05, "epoch": 0.9020618556701031, "percentage": 12.89, "elapsed_time": "1:24:52", "remaining_time": "9:33:42"} +{"current_steps": 180, "total_steps": 1358, "loss": 0.323, "lr": 3.987791792010834e-05, "epoch": 0.9278350515463918, "percentage": 13.25, "elapsed_time": "1:27:19", "remaining_time": "9:31:32"} +{"current_steps": 185, "total_steps": 1358, "loss": 0.323, "lr": 3.984791421541839e-05, "epoch": 0.9536082474226805, "percentage": 13.62, "elapsed_time": "1:29:43", "remaining_time": "9:28:57"} +{"current_steps": 190, "total_steps": 1358, "loss": 0.3266, "lr": 3.981463102129109e-05, "epoch": 0.979381443298969, "percentage": 13.99, "elapsed_time": "1:32:07", "remaining_time": "9:26:19"} +{"current_steps": 195, "total_steps": 1358, "loss": 0.3167, "lr": 3.9778073837139735e-05, "epoch": 1.0051546391752577, "percentage": 14.36, "elapsed_time": "1:34:33", "remaining_time": "9:23:58"} +{"current_steps": 200, "total_steps": 1358, "loss": 0.3124, "lr": 3.9738248703342085e-05, "epoch": 1.0309278350515463, "percentage": 14.73, "elapsed_time": "1:36:59", "remaining_time": "9:21:35"} +{"current_steps": 205, "total_steps": 1358, "loss": 0.3132, "lr": 3.9695162200242256e-05, "epoch": 1.056701030927835, "percentage": 15.1, "elapsed_time": "1:39:26", "remaining_time": "9:19:15"} +{"current_steps": 210, "total_steps": 1358, "loss": 0.3077, "lr": 3.964882144706347e-05, "epoch": 1.0824742268041236, "percentage": 15.46, "elapsed_time": "1:41:48", "remaining_time": "9:16:32"} +{"current_steps": 215, "total_steps": 1358, "loss": 0.3141, "lr": 3.959923410073174e-05, "epoch": 1.1082474226804124, "percentage": 15.83, "elapsed_time": "1:44:13", "remaining_time": "9:14:06"} +{"current_steps": 220, "total_steps": 1358, "loss": 0.3158, "lr": 3.954640835461069e-05, "epoch": 1.134020618556701, "percentage": 16.2, "elapsed_time": "1:46:39", "remaining_time": "9:11:45"} +{"current_steps": 225, "total_steps": 1358, "loss": 0.3133, "lr": 3.9490352937147786e-05, "epoch": 1.1597938144329896, "percentage": 16.57, "elapsed_time": "1:49:01", "remaining_time": "9:08:59"} +{"current_steps": 230, "total_steps": 1358, "loss": 0.3031, "lr": 3.943107711043211e-05, "epoch": 1.1855670103092784, "percentage": 16.94, "elapsed_time": "1:51:25", "remaining_time": "9:06:27"} +{"current_steps": 235, "total_steps": 1358, "loss": 0.3109, "lr": 3.936859066866397e-05, "epoch": 1.211340206185567, "percentage": 17.3, "elapsed_time": "1:53:48", "remaining_time": "9:03:53"} +{"current_steps": 240, "total_steps": 1358, "loss": 0.3147, "lr": 3.93029039365366e-05, "epoch": 1.2371134020618557, "percentage": 17.67, "elapsed_time": "1:56:13", "remaining_time": "9:01:22"} +{"current_steps": 245, "total_steps": 1358, "loss": 0.3011, "lr": 3.923402776753022e-05, "epoch": 1.2628865979381443, "percentage": 18.04, "elapsed_time": "1:58:35", "remaining_time": "8:58:46"} +{"current_steps": 250, "total_steps": 1358, "loss": 0.3044, "lr": 3.9161973542118686e-05, "epoch": 1.2886597938144329, "percentage": 18.41, "elapsed_time": "2:00:58", "remaining_time": "8:56:07"} +{"current_steps": 255, "total_steps": 1358, "loss": 0.2985, "lr": 3.9086753165889076e-05, "epoch": 1.3144329896907216, "percentage": 18.78, "elapsed_time": "2:03:18", "remaining_time": "8:53:23"} +{"current_steps": 260, "total_steps": 1358, "loss": 0.3096, "lr": 3.900837906757454e-05, "epoch": 1.3402061855670104, "percentage": 19.15, "elapsed_time": "2:05:41", "remaining_time": "8:50:50"} +{"current_steps": 265, "total_steps": 1358, "loss": 0.3124, "lr": 3.8926864197000676e-05, "epoch": 1.365979381443299, "percentage": 19.51, "elapsed_time": "2:08:05", "remaining_time": "8:48:18"} +{"current_steps": 270, "total_steps": 1358, "loss": 0.3049, "lr": 3.8842222022945823e-05, "epoch": 1.3917525773195876, "percentage": 19.88, "elapsed_time": "2:10:29", "remaining_time": "8:45:48"} +{"current_steps": 275, "total_steps": 1358, "loss": 0.2924, "lr": 3.875446653091559e-05, "epoch": 1.4175257731958764, "percentage": 20.25, "elapsed_time": "2:12:53", "remaining_time": "8:43:22"} +{"current_steps": 280, "total_steps": 1358, "loss": 0.3095, "lr": 3.866361222083205e-05, "epoch": 1.443298969072165, "percentage": 20.62, "elapsed_time": "2:15:18", "remaining_time": "8:40:55"} +{"current_steps": 285, "total_steps": 1358, "loss": 0.2981, "lr": 3.856967410463787e-05, "epoch": 1.4690721649484537, "percentage": 20.99, "elapsed_time": "2:17:42", "remaining_time": "8:38:27"} +{"current_steps": 290, "total_steps": 1358, "loss": 0.3017, "lr": 3.8472667703815876e-05, "epoch": 1.4948453608247423, "percentage": 21.35, "elapsed_time": "2:20:02", "remaining_time": "8:35:45"} +{"current_steps": 295, "total_steps": 1358, "loss": 0.2977, "lr": 3.837260904682445e-05, "epoch": 1.5206185567010309, "percentage": 21.72, "elapsed_time": "2:22:26", "remaining_time": "8:33:17"} +{"current_steps": 300, "total_steps": 1358, "loss": 0.3025, "lr": 3.8269514666449116e-05, "epoch": 1.5463917525773194, "percentage": 22.09, "elapsed_time": "2:24:51", "remaining_time": "8:30:52"} +{"current_steps": 305, "total_steps": 1358, "loss": 0.298, "lr": 3.816340159707079e-05, "epoch": 1.5721649484536082, "percentage": 22.46, "elapsed_time": "2:27:24", "remaining_time": "8:28:54"} +{"current_steps": 310, "total_steps": 1358, "loss": 0.2903, "lr": 3.805428737185124e-05, "epoch": 1.597938144329897, "percentage": 22.83, "elapsed_time": "2:29:45", "remaining_time": "8:26:15"} +{"current_steps": 315, "total_steps": 1358, "loss": 0.2854, "lr": 3.794219001983597e-05, "epoch": 1.6237113402061856, "percentage": 23.2, "elapsed_time": "2:32:05", "remaining_time": "8:23:36"} +{"current_steps": 320, "total_steps": 1358, "loss": 0.298, "lr": 3.782712806297536e-05, "epoch": 1.6494845360824741, "percentage": 23.56, "elapsed_time": "2:34:30", "remaining_time": "8:21:09"} +{"current_steps": 325, "total_steps": 1358, "loss": 0.2957, "lr": 3.7709120513064196e-05, "epoch": 1.675257731958763, "percentage": 23.93, "elapsed_time": "2:36:52", "remaining_time": "8:18:37"} +{"current_steps": 330, "total_steps": 1358, "loss": 0.2941, "lr": 3.758818686860038e-05, "epoch": 1.7010309278350515, "percentage": 24.3, "elapsed_time": "2:39:16", "remaining_time": "8:16:09"} +{"current_steps": 335, "total_steps": 1358, "loss": 0.2939, "lr": 3.746434711156314e-05, "epoch": 1.7268041237113403, "percentage": 24.67, "elapsed_time": "2:41:39", "remaining_time": "8:13:38"} +{"current_steps": 340, "total_steps": 1358, "loss": 0.3005, "lr": 3.733762170411138e-05, "epoch": 1.7525773195876289, "percentage": 25.04, "elapsed_time": "2:44:02", "remaining_time": "8:11:09"} +{"current_steps": 345, "total_steps": 1358, "loss": 0.2991, "lr": 3.720803158520279e-05, "epoch": 1.7783505154639174, "percentage": 25.41, "elapsed_time": "2:46:25", "remaining_time": "8:08:41"} +{"current_steps": 350, "total_steps": 1358, "loss": 0.2936, "lr": 3.707559816713395e-05, "epoch": 1.8041237113402062, "percentage": 25.77, "elapsed_time": "2:48:51", "remaining_time": "8:06:18"} +{"current_steps": 355, "total_steps": 1358, "loss": 0.301, "lr": 3.694034333200245e-05, "epoch": 1.829896907216495, "percentage": 26.14, "elapsed_time": "2:51:14", "remaining_time": "8:03:49"} +{"current_steps": 360, "total_steps": 1358, "loss": 0.292, "lr": 3.680228942809126e-05, "epoch": 1.8556701030927836, "percentage": 26.51, "elapsed_time": "2:53:34", "remaining_time": "8:01:12"} +{"current_steps": 365, "total_steps": 1358, "loss": 0.2888, "lr": 3.666145926617609e-05, "epoch": 1.8814432989690721, "percentage": 26.88, "elapsed_time": "2:55:55", "remaining_time": "7:58:37"} +{"current_steps": 370, "total_steps": 1358, "loss": 0.2922, "lr": 3.6517876115756376e-05, "epoch": 1.9072164948453607, "percentage": 27.25, "elapsed_time": "2:58:17", "remaining_time": "7:56:04"} +{"current_steps": 375, "total_steps": 1358, "loss": 0.3038, "lr": 3.6371563701210406e-05, "epoch": 1.9329896907216495, "percentage": 27.61, "elapsed_time": "3:00:40", "remaining_time": "7:53:37"} +{"current_steps": 380, "total_steps": 1358, "loss": 0.2941, "lr": 3.622254619787533e-05, "epoch": 1.9587628865979383, "percentage": 27.98, "elapsed_time": "3:03:05", "remaining_time": "7:51:12"} +{"current_steps": 385, "total_steps": 1358, "loss": 0.2951, "lr": 3.607084822805268e-05, "epoch": 1.9845360824742269, "percentage": 28.35, "elapsed_time": "3:05:29", "remaining_time": "7:48:48"} +{"current_steps": 390, "total_steps": 1358, "loss": 0.2949, "lr": 3.5916494856939944e-05, "epoch": 2.0103092783505154, "percentage": 28.72, "elapsed_time": "3:07:54", "remaining_time": "7:46:24"} +{"current_steps": 395, "total_steps": 1358, "loss": 0.2882, "lr": 3.575951158848905e-05, "epoch": 2.036082474226804, "percentage": 29.09, "elapsed_time": "3:10:15", "remaining_time": "7:43:50"} +{"current_steps": 400, "total_steps": 1358, "loss": 0.2835, "lr": 3.5599924361192335e-05, "epoch": 2.0618556701030926, "percentage": 29.46, "elapsed_time": "3:12:38", "remaining_time": "7:41:22"} +{"current_steps": 405, "total_steps": 1358, "loss": 0.2872, "lr": 3.54377595437967e-05, "epoch": 2.0876288659793816, "percentage": 29.82, "elapsed_time": "3:15:01", "remaining_time": "7:38:54"} +{"current_steps": 410, "total_steps": 1358, "loss": 0.2822, "lr": 3.527304393094665e-05, "epoch": 2.11340206185567, "percentage": 30.19, "elapsed_time": "3:17:25", "remaining_time": "7:36:29"} +{"current_steps": 415, "total_steps": 1358, "loss": 0.2917, "lr": 3.510580473875701e-05, "epoch": 2.1391752577319587, "percentage": 30.56, "elapsed_time": "3:19:51", "remaining_time": "7:34:08"} +{"current_steps": 420, "total_steps": 1358, "loss": 0.2757, "lr": 3.493606960031601e-05, "epoch": 2.1649484536082473, "percentage": 30.93, "elapsed_time": "3:22:15", "remaining_time": "7:31:42"} +{"current_steps": 425, "total_steps": 1358, "loss": 0.2851, "lr": 3.476386656111938e-05, "epoch": 2.1907216494845363, "percentage": 31.3, "elapsed_time": "3:24:37", "remaining_time": "7:29:12"} +{"current_steps": 430, "total_steps": 1358, "loss": 0.2844, "lr": 3.458922407443643e-05, "epoch": 2.216494845360825, "percentage": 31.66, "elapsed_time": "3:27:01", "remaining_time": "7:26:46"} +{"current_steps": 435, "total_steps": 1358, "loss": 0.2853, "lr": 3.441217099660864e-05, "epoch": 2.2422680412371134, "percentage": 32.03, "elapsed_time": "3:29:23", "remaining_time": "7:24:17"} +{"current_steps": 440, "total_steps": 1358, "loss": 0.2887, "lr": 3.423273658228171e-05, "epoch": 2.268041237113402, "percentage": 32.4, "elapsed_time": "3:31:48", "remaining_time": "7:21:53"} +{"current_steps": 445, "total_steps": 1358, "loss": 0.2923, "lr": 3.405095047957183e-05, "epoch": 2.2938144329896906, "percentage": 32.77, "elapsed_time": "3:34:09", "remaining_time": "7:19:22"} +{"current_steps": 450, "total_steps": 1358, "loss": 0.2828, "lr": 3.3866842725166855e-05, "epoch": 2.319587628865979, "percentage": 33.14, "elapsed_time": "3:36:31", "remaining_time": "7:16:53"} +{"current_steps": 455, "total_steps": 1358, "loss": 0.2829, "lr": 3.3680443739363304e-05, "epoch": 2.345360824742268, "percentage": 33.51, "elapsed_time": "3:38:53", "remaining_time": "7:14:25"} +{"current_steps": 460, "total_steps": 1358, "loss": 0.2866, "lr": 3.349178432104001e-05, "epoch": 2.3711340206185567, "percentage": 33.87, "elapsed_time": "3:41:17", "remaining_time": "7:11:59"} +{"current_steps": 465, "total_steps": 1358, "loss": 0.2875, "lr": 3.330089564256919e-05, "epoch": 2.3969072164948453, "percentage": 34.24, "elapsed_time": "3:43:38", "remaining_time": "7:09:30"} +{"current_steps": 470, "total_steps": 1358, "loss": 0.2908, "lr": 3.3107809244665805e-05, "epoch": 2.422680412371134, "percentage": 34.61, "elapsed_time": "3:46:00", "remaining_time": "7:07:01"} +{"current_steps": 475, "total_steps": 1358, "loss": 0.2847, "lr": 3.291255703117605e-05, "epoch": 2.448453608247423, "percentage": 34.98, "elapsed_time": "3:48:24", "remaining_time": "7:04:35"} +{"current_steps": 480, "total_steps": 1358, "loss": 0.2827, "lr": 3.271517126380586e-05, "epoch": 2.4742268041237114, "percentage": 35.35, "elapsed_time": "3:50:46", "remaining_time": "7:02:08"} +{"current_steps": 485, "total_steps": 1358, "loss": 0.2891, "lr": 3.251568455679025e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "3:53:10", "remaining_time": "6:59:42"} +{"current_steps": 490, "total_steps": 1358, "loss": 0.2853, "lr": 3.2314129871504504e-05, "epoch": 2.5257731958762886, "percentage": 36.08, "elapsed_time": "3:55:32", "remaining_time": "6:57:14"} +{"current_steps": 495, "total_steps": 1358, "loss": 0.2766, "lr": 3.211054051101785e-05, "epoch": 2.551546391752577, "percentage": 36.45, "elapsed_time": "3:57:55", "remaining_time": "6:54:48"} +{"current_steps": 500, "total_steps": 1358, "loss": 0.2869, "lr": 3.190495011459082e-05, "epoch": 2.5773195876288657, "percentage": 36.82, "elapsed_time": "4:00:17", "remaining_time": "6:52:21"} +{"current_steps": 505, "total_steps": 1358, "loss": 0.2766, "lr": 3.1697392652116996e-05, "epoch": 2.6030927835051547, "percentage": 37.19, "elapsed_time": "4:02:41", "remaining_time": "6:49:56"} +{"current_steps": 510, "total_steps": 1358, "loss": 0.2857, "lr": 3.1487902418510095e-05, "epoch": 2.6288659793814433, "percentage": 37.56, "elapsed_time": "4:05:04", "remaining_time": "6:47:30"} +{"current_steps": 515, "total_steps": 1358, "loss": 0.2809, "lr": 3.1276514028037444e-05, "epoch": 2.654639175257732, "percentage": 37.92, "elapsed_time": "4:07:26", "remaining_time": "6:45:01"} +{"current_steps": 520, "total_steps": 1358, "loss": 0.2746, "lr": 3.10632624086006e-05, "epoch": 2.680412371134021, "percentage": 38.29, "elapsed_time": "4:09:49", "remaining_time": "6:42:35"} +{"current_steps": 525, "total_steps": 1358, "loss": 0.2819, "lr": 3.084818279596417e-05, "epoch": 2.7061855670103094, "percentage": 38.66, "elapsed_time": "4:12:14", "remaining_time": "6:40:13"} +{"current_steps": 530, "total_steps": 1358, "loss": 0.283, "lr": 3.063131072793379e-05, "epoch": 2.731958762886598, "percentage": 39.03, "elapsed_time": "4:14:31", "remaining_time": "6:37:37"} +{"current_steps": 535, "total_steps": 1358, "loss": 0.2741, "lr": 3.0412682038484215e-05, "epoch": 2.7577319587628866, "percentage": 39.4, "elapsed_time": "4:16:55", "remaining_time": "6:35:14"} +{"current_steps": 540, "total_steps": 1358, "loss": 0.2753, "lr": 3.019233285183835e-05, "epoch": 2.783505154639175, "percentage": 39.76, "elapsed_time": "4:19:18", "remaining_time": "6:32:48"} +{"current_steps": 545, "total_steps": 1358, "loss": 0.2858, "lr": 2.9970299576498495e-05, "epoch": 2.8092783505154637, "percentage": 40.13, "elapsed_time": "4:21:39", "remaining_time": "6:30:20"} +{"current_steps": 550, "total_steps": 1358, "loss": 0.2906, "lr": 2.974661889923048e-05, "epoch": 2.8350515463917527, "percentage": 40.5, "elapsed_time": "4:24:01", "remaining_time": "6:27:52"} +{"current_steps": 555, "total_steps": 1358, "loss": 0.2789, "lr": 2.9521327779001906e-05, "epoch": 2.8608247422680413, "percentage": 40.87, "elapsed_time": "4:26:23", "remaining_time": "6:25:24"} +{"current_steps": 560, "total_steps": 1358, "loss": 0.2846, "lr": 2.9294463440875375e-05, "epoch": 2.88659793814433, "percentage": 41.24, "elapsed_time": "4:28:45", "remaining_time": "6:22:58"} +{"current_steps": 565, "total_steps": 1358, "loss": 0.2779, "lr": 2.906606336985775e-05, "epoch": 2.9123711340206184, "percentage": 41.61, "elapsed_time": "4:31:04", "remaining_time": "6:20:28"} +{"current_steps": 570, "total_steps": 1358, "loss": 0.2772, "lr": 2.883616530470648e-05, "epoch": 2.9381443298969074, "percentage": 41.97, "elapsed_time": "4:33:27", "remaining_time": "6:18:03"} +{"current_steps": 575, "total_steps": 1358, "loss": 0.2854, "lr": 2.8604807231693987e-05, "epoch": 2.963917525773196, "percentage": 42.34, "elapsed_time": "4:35:51", "remaining_time": "6:15:39"} +{"current_steps": 580, "total_steps": 1358, "loss": 0.2783, "lr": 2.8372027378331148e-05, "epoch": 2.9896907216494846, "percentage": 42.71, "elapsed_time": "4:38:14", "remaining_time": "6:13:14"} +{"current_steps": 585, "total_steps": 1358, "loss": 0.2746, "lr": 2.8137864207050945e-05, "epoch": 3.015463917525773, "percentage": 43.08, "elapsed_time": "4:40:40", "remaining_time": "6:10:52"} +{"current_steps": 590, "total_steps": 1358, "loss": 0.2675, "lr": 2.790235640885327e-05, "epoch": 3.0412371134020617, "percentage": 43.45, "elapsed_time": "4:43:01", "remaining_time": "6:08:24"} +{"current_steps": 595, "total_steps": 1358, "loss": 0.2764, "lr": 2.7665542896911993e-05, "epoch": 3.0670103092783507, "percentage": 43.81, "elapsed_time": "4:45:22", "remaining_time": "6:05:57"} +{"current_steps": 600, "total_steps": 1358, "loss": 0.2661, "lr": 2.742746280014527e-05, "epoch": 3.0927835051546393, "percentage": 44.18, "elapsed_time": "4:47:46", "remaining_time": "6:03:32"} +{"current_steps": 605, "total_steps": 1358, "loss": 0.2814, "lr": 2.7188155456750257e-05, "epoch": 3.118556701030928, "percentage": 44.55, "elapsed_time": "4:50:18", "remaining_time": "6:01:19"} +{"current_steps": 610, "total_steps": 1358, "loss": 0.2728, "lr": 2.694766040770323e-05, "epoch": 3.1443298969072164, "percentage": 44.92, "elapsed_time": "4:52:42", "remaining_time": "5:58:55"} +{"current_steps": 615, "total_steps": 1358, "loss": 0.2754, "lr": 2.6706017390226162e-05, "epoch": 3.170103092783505, "percentage": 45.29, "elapsed_time": "4:55:05", "remaining_time": "5:56:30"} +{"current_steps": 620, "total_steps": 1358, "loss": 0.2702, "lr": 2.646326633122094e-05, "epoch": 3.195876288659794, "percentage": 45.66, "elapsed_time": "4:57:27", "remaining_time": "5:54:04"} +{"current_steps": 625, "total_steps": 1358, "loss": 0.28, "lr": 2.621944734067218e-05, "epoch": 3.2216494845360826, "percentage": 46.02, "elapsed_time": "4:59:50", "remaining_time": "5:51:39"} +{"current_steps": 630, "total_steps": 1358, "loss": 0.2775, "lr": 2.597460070501983e-05, "epoch": 3.247422680412371, "percentage": 46.39, "elapsed_time": "5:02:09", "remaining_time": "5:49:09"} +{"current_steps": 635, "total_steps": 1358, "loss": 0.2752, "lr": 2.5728766880502604e-05, "epoch": 3.2731958762886597, "percentage": 46.76, "elapsed_time": "5:04:32", "remaining_time": "5:46:44"} +{"current_steps": 640, "total_steps": 1358, "loss": 0.2757, "lr": 2.5481986486473352e-05, "epoch": 3.2989690721649483, "percentage": 47.13, "elapsed_time": "5:06:54", "remaining_time": "5:44:18"} +{"current_steps": 645, "total_steps": 1358, "loss": 0.27, "lr": 2.523430029868749e-05, "epoch": 3.3247422680412373, "percentage": 47.5, "elapsed_time": "5:09:17", "remaining_time": "5:41:53"} +{"current_steps": 650, "total_steps": 1358, "loss": 0.268, "lr": 2.498574924256558e-05, "epoch": 3.350515463917526, "percentage": 47.86, "elapsed_time": "5:11:41", "remaining_time": "5:39:29"} +{"current_steps": 655, "total_steps": 1358, "loss": 0.2701, "lr": 2.4736374386431194e-05, "epoch": 3.3762886597938144, "percentage": 48.23, "elapsed_time": "5:14:02", "remaining_time": "5:37:03"} +{"current_steps": 660, "total_steps": 1358, "loss": 0.2815, "lr": 2.4486216934725143e-05, "epoch": 3.402061855670103, "percentage": 48.6, "elapsed_time": "5:16:23", "remaining_time": "5:34:36"} +{"current_steps": 665, "total_steps": 1358, "loss": 0.2749, "lr": 2.4235318221197258e-05, "epoch": 3.4278350515463916, "percentage": 48.97, "elapsed_time": "5:18:47", "remaining_time": "5:32:12"} +{"current_steps": 670, "total_steps": 1358, "loss": 0.2785, "lr": 2.3983719702076724e-05, "epoch": 3.4536082474226806, "percentage": 49.34, "elapsed_time": "5:21:08", "remaining_time": "5:29:45"} +{"current_steps": 675, "total_steps": 1358, "loss": 0.2685, "lr": 2.3731462949222282e-05, "epoch": 3.479381443298969, "percentage": 49.71, "elapsed_time": "5:23:32", "remaining_time": "5:27:22"} +{"current_steps": 680, "total_steps": 1358, "loss": 0.2697, "lr": 2.347858964325324e-05, "epoch": 3.5051546391752577, "percentage": 50.07, "elapsed_time": "5:25:55", "remaining_time": "5:24:57"} +{"current_steps": 685, "total_steps": 1358, "loss": 0.2817, "lr": 2.3225141566662556e-05, "epoch": 3.5309278350515463, "percentage": 50.44, "elapsed_time": "5:28:16", "remaining_time": "5:22:31"} +{"current_steps": 690, "total_steps": 1358, "loss": 0.2717, "lr": 2.297116059691307e-05, "epoch": 3.556701030927835, "percentage": 50.81, "elapsed_time": "5:30:39", "remaining_time": "5:20:06"} +{"current_steps": 695, "total_steps": 1358, "loss": 0.2703, "lr": 2.2716688699518063e-05, "epoch": 3.582474226804124, "percentage": 51.18, "elapsed_time": "5:33:00", "remaining_time": "5:17:40"} +{"current_steps": 700, "total_steps": 1358, "loss": 0.2741, "lr": 2.2461767921107255e-05, "epoch": 3.6082474226804124, "percentage": 51.55, "elapsed_time": "5:35:18", "remaining_time": "5:15:11"} +{"current_steps": 705, "total_steps": 1358, "loss": 0.2709, "lr": 2.2206440382479378e-05, "epoch": 3.634020618556701, "percentage": 51.91, "elapsed_time": "5:37:41", "remaining_time": "5:12:47"} +{"current_steps": 710, "total_steps": 1358, "loss": 0.2674, "lr": 2.195074827164256e-05, "epoch": 3.6597938144329896, "percentage": 52.28, "elapsed_time": "5:40:05", "remaining_time": "5:10:23"} +{"current_steps": 715, "total_steps": 1358, "loss": 0.2679, "lr": 2.169473383684352e-05, "epoch": 3.6855670103092786, "percentage": 52.65, "elapsed_time": "5:42:27", "remaining_time": "5:07:58"} +{"current_steps": 720, "total_steps": 1358, "loss": 0.2736, "lr": 2.143843937958687e-05, "epoch": 3.711340206185567, "percentage": 53.02, "elapsed_time": "5:44:51", "remaining_time": "5:05:34"} +{"current_steps": 725, "total_steps": 1358, "loss": 0.2741, "lr": 2.118190724764559e-05, "epoch": 3.7371134020618557, "percentage": 53.39, "elapsed_time": "5:47:14", "remaining_time": "5:03:10"} +{"current_steps": 730, "total_steps": 1358, "loss": 0.2812, "lr": 2.0925179828063875e-05, "epoch": 3.7628865979381443, "percentage": 53.76, "elapsed_time": "5:49:35", "remaining_time": "5:00:44"} +{"current_steps": 735, "total_steps": 1358, "loss": 0.2803, "lr": 2.0668299540153494e-05, "epoch": 3.788659793814433, "percentage": 54.12, "elapsed_time": "5:51:56", "remaining_time": "4:58:18"} +{"current_steps": 740, "total_steps": 1358, "loss": 0.2728, "lr": 2.0411308828484766e-05, "epoch": 3.8144329896907214, "percentage": 54.49, "elapsed_time": "5:54:17", "remaining_time": "4:55:52"} +{"current_steps": 745, "total_steps": 1358, "loss": 0.2708, "lr": 2.0154250155873454e-05, "epoch": 3.8402061855670104, "percentage": 54.86, "elapsed_time": "5:56:40", "remaining_time": "4:53:28"} +{"current_steps": 750, "total_steps": 1358, "loss": 0.2733, "lr": 1.989716599636456e-05, "epoch": 3.865979381443299, "percentage": 55.23, "elapsed_time": "5:59:01", "remaining_time": "4:51:02"} +{"current_steps": 755, "total_steps": 1358, "loss": 0.2699, "lr": 1.964009882821429e-05, "epoch": 3.8917525773195876, "percentage": 55.6, "elapsed_time": "6:01:24", "remaining_time": "4:48:39"} +{"current_steps": 760, "total_steps": 1358, "loss": 0.2695, "lr": 1.9383091126871406e-05, "epoch": 3.917525773195876, "percentage": 55.96, "elapsed_time": "6:03:46", "remaining_time": "4:46:14"} +{"current_steps": 765, "total_steps": 1358, "loss": 0.2678, "lr": 1.9126185357958863e-05, "epoch": 3.943298969072165, "percentage": 56.33, "elapsed_time": "6:06:08", "remaining_time": "4:43:48"} +{"current_steps": 770, "total_steps": 1358, "loss": 0.2687, "lr": 1.8869423970257243e-05, "epoch": 3.9690721649484537, "percentage": 56.7, "elapsed_time": "6:08:28", "remaining_time": "4:41:22"} +{"current_steps": 775, "total_steps": 1358, "loss": 0.2704, "lr": 1.8612849388690893e-05, "epoch": 3.9948453608247423, "percentage": 57.07, "elapsed_time": "6:10:50", "remaining_time": "4:38:58"} +{"current_steps": 780, "total_steps": 1358, "loss": 0.2642, "lr": 1.835650400731799e-05, "epoch": 4.020618556701031, "percentage": 57.44, "elapsed_time": "6:13:06", "remaining_time": "4:36:28"} +{"current_steps": 785, "total_steps": 1358, "loss": 0.2687, "lr": 1.810043018232577e-05, "epoch": 4.046391752577319, "percentage": 57.81, "elapsed_time": "6:15:31", "remaining_time": "4:34:06"} +{"current_steps": 790, "total_steps": 1358, "loss": 0.269, "lr": 1.7844670225031934e-05, "epoch": 4.072164948453608, "percentage": 58.17, "elapsed_time": "6:17:53", "remaining_time": "4:31:41"} +{"current_steps": 795, "total_steps": 1358, "loss": 0.265, "lr": 1.758926639489354e-05, "epoch": 4.097938144329897, "percentage": 58.54, "elapsed_time": "6:20:17", "remaining_time": "4:29:19"} +{"current_steps": 800, "total_steps": 1358, "loss": 0.2697, "lr": 1.733426089252443e-05, "epoch": 4.123711340206185, "percentage": 58.91, "elapsed_time": "6:22:38", "remaining_time": "4:26:53"} +{"current_steps": 805, "total_steps": 1358, "loss": 0.2635, "lr": 1.7079695852722347e-05, "epoch": 4.149484536082475, "percentage": 59.28, "elapsed_time": "6:25:01", "remaining_time": "4:24:29"} +{"current_steps": 810, "total_steps": 1358, "loss": 0.2581, "lr": 1.682561333750703e-05, "epoch": 4.175257731958763, "percentage": 59.65, "elapsed_time": "6:27:24", "remaining_time": "4:22:05"} +{"current_steps": 815, "total_steps": 1358, "loss": 0.2652, "lr": 1.6572055329170214e-05, "epoch": 4.201030927835052, "percentage": 60.01, "elapsed_time": "6:29:44", "remaining_time": "4:19:40"} +{"current_steps": 820, "total_steps": 1358, "loss": 0.2688, "lr": 1.6319063723338855e-05, "epoch": 4.22680412371134, "percentage": 60.38, "elapsed_time": "6:32:06", "remaining_time": "4:17:15"} +{"current_steps": 825, "total_steps": 1358, "loss": 0.26, "lr": 1.6066680322052703e-05, "epoch": 4.252577319587629, "percentage": 60.75, "elapsed_time": "6:34:29", "remaining_time": "4:14:52"} +{"current_steps": 830, "total_steps": 1358, "loss": 0.2669, "lr": 1.5814946826857323e-05, "epoch": 4.278350515463917, "percentage": 61.12, "elapsed_time": "6:36:53", "remaining_time": "4:12:28"} +{"current_steps": 835, "total_steps": 1358, "loss": 0.2722, "lr": 1.5563904831913663e-05, "epoch": 4.304123711340206, "percentage": 61.49, "elapsed_time": "6:39:11", "remaining_time": "4:10:01"} +{"current_steps": 840, "total_steps": 1358, "loss": 0.2647, "lr": 1.5313595817125445e-05, "epoch": 4.329896907216495, "percentage": 61.86, "elapsed_time": "6:41:36", "remaining_time": "4:07:39"} +{"current_steps": 845, "total_steps": 1358, "loss": 0.2711, "lr": 1.5064061141285397e-05, "epoch": 4.355670103092783, "percentage": 62.22, "elapsed_time": "6:43:59", "remaining_time": "4:05:16"} +{"current_steps": 850, "total_steps": 1358, "loss": 0.2645, "lr": 1.481534203524149e-05, "epoch": 4.381443298969073, "percentage": 62.59, "elapsed_time": "6:46:22", "remaining_time": "4:02:52"} +{"current_steps": 855, "total_steps": 1358, "loss": 0.2629, "lr": 1.4567479595084349e-05, "epoch": 4.407216494845361, "percentage": 62.96, "elapsed_time": "6:48:47", "remaining_time": "4:00:29"} +{"current_steps": 860, "total_steps": 1358, "loss": 0.2661, "lr": 1.4320514775356878e-05, "epoch": 4.43298969072165, "percentage": 63.33, "elapsed_time": "6:51:10", "remaining_time": "3:58:05"} +{"current_steps": 865, "total_steps": 1358, "loss": 0.267, "lr": 1.4074488382287324e-05, "epoch": 4.458762886597938, "percentage": 63.7, "elapsed_time": "6:53:32", "remaining_time": "3:55:41"} +{"current_steps": 870, "total_steps": 1358, "loss": 0.2708, "lr": 1.3829441067046822e-05, "epoch": 4.484536082474227, "percentage": 64.06, "elapsed_time": "6:55:55", "remaining_time": "3:53:17"} +{"current_steps": 875, "total_steps": 1358, "loss": 0.2626, "lr": 1.358541331903255e-05, "epoch": 4.510309278350515, "percentage": 64.43, "elapsed_time": "6:58:19", "remaining_time": "3:50:54"} +{"current_steps": 880, "total_steps": 1358, "loss": 0.2674, "lr": 1.3342445459177658e-05, "epoch": 4.536082474226804, "percentage": 64.8, "elapsed_time": "7:00:39", "remaining_time": "3:48:29"} +{"current_steps": 885, "total_steps": 1358, "loss": 0.262, "lr": 1.3100577633288967e-05, "epoch": 4.561855670103093, "percentage": 65.17, "elapsed_time": "7:03:02", "remaining_time": "3:46:05"} +{"current_steps": 890, "total_steps": 1358, "loss": 0.271, "lr": 1.2859849805413664e-05, "epoch": 4.587628865979381, "percentage": 65.54, "elapsed_time": "7:05:24", "remaining_time": "3:43:41"} +{"current_steps": 895, "total_steps": 1358, "loss": 0.2638, "lr": 1.262030175123599e-05, "epoch": 4.61340206185567, "percentage": 65.91, "elapsed_time": "7:07:47", "remaining_time": "3:41:18"} +{"current_steps": 900, "total_steps": 1358, "loss": 0.2613, "lr": 1.2381973051505089e-05, "epoch": 4.639175257731958, "percentage": 66.27, "elapsed_time": "7:10:06", "remaining_time": "3:38:52"} +{"current_steps": 905, "total_steps": 1358, "loss": 0.266, "lr": 1.2144903085495021e-05, "epoch": 4.664948453608248, "percentage": 66.64, "elapsed_time": "7:12:34", "remaining_time": "3:36:31"} +{"current_steps": 910, "total_steps": 1358, "loss": 0.2693, "lr": 1.190913102449809e-05, "epoch": 4.690721649484536, "percentage": 67.01, "elapsed_time": "7:14:55", "remaining_time": "3:34:06"} +{"current_steps": 915, "total_steps": 1358, "loss": 0.267, "lr": 1.1674695825352544e-05, "epoch": 4.716494845360825, "percentage": 67.38, "elapsed_time": "7:17:19", "remaining_time": "3:31:43"} +{"current_steps": 920, "total_steps": 1358, "loss": 0.2692, "lr": 1.1441636224005684e-05, "epoch": 4.742268041237113, "percentage": 67.75, "elapsed_time": "7:19:39", "remaining_time": "3:29:19"} +{"current_steps": 925, "total_steps": 1358, "loss": 0.2632, "lr": 1.120999072911354e-05, "epoch": 4.768041237113402, "percentage": 68.11, "elapsed_time": "7:22:04", "remaining_time": "3:26:56"} +{"current_steps": 930, "total_steps": 1358, "loss": 0.2624, "lr": 1.097979761567796e-05, "epoch": 4.793814432989691, "percentage": 68.48, "elapsed_time": "7:24:28", "remaining_time": "3:24:33"} +{"current_steps": 935, "total_steps": 1358, "loss": 0.2714, "lr": 1.0751094918722487e-05, "epoch": 4.819587628865979, "percentage": 68.85, "elapsed_time": "7:26:51", "remaining_time": "3:22:09"} +{"current_steps": 940, "total_steps": 1358, "loss": 0.2641, "lr": 1.0523920427007717e-05, "epoch": 4.845360824742268, "percentage": 69.22, "elapsed_time": "7:29:14", "remaining_time": "3:19:46"} +{"current_steps": 945, "total_steps": 1358, "loss": 0.2715, "lr": 1.0298311676787474e-05, "epoch": 4.871134020618557, "percentage": 69.59, "elapsed_time": "7:31:37", "remaining_time": "3:17:22"} +{"current_steps": 950, "total_steps": 1358, "loss": 0.2656, "lr": 1.0074305945606684e-05, "epoch": 4.896907216494846, "percentage": 69.96, "elapsed_time": "7:34:01", "remaining_time": "3:14:59"} +{"current_steps": 955, "total_steps": 1358, "loss": 0.2653, "lr": 9.851940246141888e-06, "epoch": 4.922680412371134, "percentage": 70.32, "elapsed_time": "7:36:23", "remaining_time": "3:12:35"} +{"current_steps": 960, "total_steps": 1358, "loss": 0.2655, "lr": 9.63125132008569e-06, "epoch": 4.948453608247423, "percentage": 70.69, "elapsed_time": "7:38:45", "remaining_time": "3:10:11"} +{"current_steps": 965, "total_steps": 1358, "loss": 0.2633, "lr": 9.412275632075827e-06, "epoch": 4.974226804123711, "percentage": 71.06, "elapsed_time": "7:41:05", "remaining_time": "3:07:46"} +{"current_steps": 970, "total_steps": 1358, "loss": 0.266, "lr": 9.195049363670125e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "7:43:23", "remaining_time": "3:05:21"} +{"current_steps": 975, "total_steps": 1358, "loss": 0.2674, "lr": 8.979608407368182e-06, "epoch": 5.025773195876289, "percentage": 71.8, "elapsed_time": "7:45:47", "remaining_time": "3:02:58"} +{"current_steps": 980, "total_steps": 1358, "loss": 0.2621, "lr": 8.765988360680772e-06, "epoch": 5.051546391752577, "percentage": 72.16, "elapsed_time": "7:48:10", "remaining_time": "3:00:34"} +{"current_steps": 985, "total_steps": 1358, "loss": 0.2641, "lr": 8.554224520248115e-06, "epoch": 5.077319587628866, "percentage": 72.53, "elapsed_time": "7:50:29", "remaining_time": "2:58:09"} +{"current_steps": 990, "total_steps": 1358, "loss": 0.2644, "lr": 8.344351876007686e-06, "epoch": 5.103092783505154, "percentage": 72.9, "elapsed_time": "7:52:51", "remaining_time": "2:55:46"} +{"current_steps": 995, "total_steps": 1358, "loss": 0.266, "lr": 8.136405105412897e-06, "epoch": 5.128865979381443, "percentage": 73.27, "elapsed_time": "7:55:16", "remaining_time": "2:53:23"} +{"current_steps": 1000, "total_steps": 1358, "loss": 0.2541, "lr": 7.930418567703215e-06, "epoch": 5.154639175257732, "percentage": 73.64, "elapsed_time": "7:57:40", "remaining_time": "2:51:00"} +{"current_steps": 1005, "total_steps": 1358, "loss": 0.2656, "lr": 7.726426298226996e-06, "epoch": 5.180412371134021, "percentage": 74.01, "elapsed_time": "8:00:00", "remaining_time": "2:48:36"} +{"current_steps": 1010, "total_steps": 1358, "loss": 0.2592, "lr": 7.524462002817809e-06, "epoch": 5.206185567010309, "percentage": 74.37, "elapsed_time": "8:02:21", "remaining_time": "2:46:12"} +{"current_steps": 1015, "total_steps": 1358, "loss": 0.2559, "lr": 7.324559052225162e-06, "epoch": 5.231958762886598, "percentage": 74.74, "elapsed_time": "8:04:45", "remaining_time": "2:43:48"} +{"current_steps": 1020, "total_steps": 1358, "loss": 0.2595, "lr": 7.126750476600635e-06, "epoch": 5.257731958762887, "percentage": 75.11, "elapsed_time": "8:07:08", "remaining_time": "2:41:25"} +{"current_steps": 1025, "total_steps": 1358, "loss": 0.2688, "lr": 6.931068960040248e-06, "epoch": 5.283505154639175, "percentage": 75.48, "elapsed_time": "8:09:32", "remaining_time": "2:39:02"} +{"current_steps": 1030, "total_steps": 1358, "loss": 0.2632, "lr": 6.737546835184101e-06, "epoch": 5.309278350515464, "percentage": 75.85, "elapsed_time": "8:11:54", "remaining_time": "2:36:38"} +{"current_steps": 1035, "total_steps": 1358, "loss": 0.2673, "lr": 6.546216077873941e-06, "epoch": 5.335051546391752, "percentage": 76.22, "elapsed_time": "8:14:19", "remaining_time": "2:34:15"} +{"current_steps": 1040, "total_steps": 1358, "loss": 0.2631, "lr": 6.3571083018698385e-06, "epoch": 5.360824742268041, "percentage": 76.58, "elapsed_time": "8:16:43", "remaining_time": "2:31:53"} +{"current_steps": 1045, "total_steps": 1358, "loss": 0.2594, "lr": 6.17025475362657e-06, "epoch": 5.38659793814433, "percentage": 76.95, "elapsed_time": "8:19:08", "remaining_time": "2:29:30"} +{"current_steps": 1050, "total_steps": 1358, "loss": 0.2646, "lr": 5.985686307130738e-06, "epoch": 5.412371134020619, "percentage": 77.32, "elapsed_time": "8:21:29", "remaining_time": "2:27:06"} +{"current_steps": 1055, "total_steps": 1358, "loss": 0.2628, "lr": 5.80343345879947e-06, "epoch": 5.438144329896907, "percentage": 77.69, "elapsed_time": "8:23:52", "remaining_time": "2:24:42"} +{"current_steps": 1060, "total_steps": 1358, "loss": 0.2652, "lr": 5.623526322441417e-06, "epoch": 5.463917525773196, "percentage": 78.06, "elapsed_time": "8:26:14", "remaining_time": "2:22:19"} +{"current_steps": 1065, "total_steps": 1358, "loss": 0.255, "lr": 5.445994624281059e-06, "epoch": 5.489690721649485, "percentage": 78.42, "elapsed_time": "8:28:36", "remaining_time": "2:19:55"} +{"current_steps": 1070, "total_steps": 1358, "loss": 0.2588, "lr": 5.270867698047009e-06, "epoch": 5.515463917525773, "percentage": 78.79, "elapsed_time": "8:31:02", "remaining_time": "2:17:32"} +{"current_steps": 1075, "total_steps": 1358, "loss": 0.266, "lr": 5.098174480125138e-06, "epoch": 5.541237113402062, "percentage": 79.16, "elapsed_time": "8:33:21", "remaining_time": "2:15:08"} +{"current_steps": 1080, "total_steps": 1358, "loss": 0.2625, "lr": 4.927943504777439e-06, "epoch": 5.56701030927835, "percentage": 79.53, "elapsed_time": "8:35:45", "remaining_time": "2:12:45"} +{"current_steps": 1085, "total_steps": 1358, "loss": 0.2662, "lr": 4.760202899427251e-06, "epoch": 5.592783505154639, "percentage": 79.9, "elapsed_time": "8:38:06", "remaining_time": "2:10:21"} +{"current_steps": 1090, "total_steps": 1358, "loss": 0.2648, "lr": 4.594980380011756e-06, "epoch": 5.618556701030927, "percentage": 80.27, "elapsed_time": "8:40:30", "remaining_time": "2:07:58"} +{"current_steps": 1095, "total_steps": 1358, "loss": 0.2609, "lr": 4.432303246402423e-06, "epoch": 5.644329896907217, "percentage": 80.63, "elapsed_time": "8:42:54", "remaining_time": "2:05:35"} +{"current_steps": 1100, "total_steps": 1358, "loss": 0.2682, "lr": 4.272198377894266e-06, "epoch": 5.670103092783505, "percentage": 81.0, "elapsed_time": "8:45:17", "remaining_time": "2:03:12"} +{"current_steps": 1105, "total_steps": 1358, "loss": 0.2615, "lr": 4.114692228764506e-06, "epoch": 5.695876288659794, "percentage": 81.37, "elapsed_time": "8:47:39", "remaining_time": "2:00:48"} +{"current_steps": 1110, "total_steps": 1358, "loss": 0.2613, "lr": 3.959810823901544e-06, "epoch": 5.721649484536083, "percentage": 81.74, "elapsed_time": "8:49:58", "remaining_time": "1:58:24"} +{"current_steps": 1115, "total_steps": 1358, "loss": 0.2606, "lr": 3.8075797545048352e-06, "epoch": 5.747422680412371, "percentage": 82.11, "elapsed_time": "8:52:21", "remaining_time": "1:56:01"} +{"current_steps": 1120, "total_steps": 1358, "loss": 0.2607, "lr": 3.658024173856407e-06, "epoch": 5.77319587628866, "percentage": 82.47, "elapsed_time": "8:54:42", "remaining_time": "1:53:37"} +{"current_steps": 1125, "total_steps": 1358, "loss": 0.2605, "lr": 3.5111687931647984e-06, "epoch": 5.798969072164948, "percentage": 82.84, "elapsed_time": "8:57:07", "remaining_time": "1:51:14"} +{"current_steps": 1130, "total_steps": 1358, "loss": 0.2577, "lr": 3.3670378774819602e-06, "epoch": 5.824742268041237, "percentage": 83.21, "elapsed_time": "8:59:28", "remaining_time": "1:48:51"} +{"current_steps": 1135, "total_steps": 1358, "loss": 0.2595, "lr": 3.225655241693959e-06, "epoch": 5.850515463917525, "percentage": 83.58, "elapsed_time": "9:01:49", "remaining_time": "1:46:27"} +{"current_steps": 1140, "total_steps": 1358, "loss": 0.2667, "lr": 3.0870442465859995e-06, "epoch": 5.876288659793815, "percentage": 83.95, "elapsed_time": "9:04:09", "remaining_time": "1:44:03"} +{"current_steps": 1145, "total_steps": 1358, "loss": 0.2575, "lr": 2.9512277949824964e-06, "epoch": 5.902061855670103, "percentage": 84.32, "elapsed_time": "9:06:31", "remaining_time": "1:41:40"} +{"current_steps": 1150, "total_steps": 1358, "loss": 0.2589, "lr": 2.8182283279628286e-06, "epoch": 5.927835051546392, "percentage": 84.68, "elapsed_time": "9:08:51", "remaining_time": "1:39:16"} +{"current_steps": 1155, "total_steps": 1358, "loss": 0.2542, "lr": 2.688067821153384e-06, "epoch": 5.953608247422681, "percentage": 85.05, "elapsed_time": "9:11:15", "remaining_time": "1:36:53"} +{"current_steps": 1160, "total_steps": 1358, "loss": 0.2565, "lr": 2.5607677810964936e-06, "epoch": 5.979381443298969, "percentage": 85.42, "elapsed_time": "9:13:36", "remaining_time": "1:34:29"} +{"current_steps": 1165, "total_steps": 1358, "loss": 0.2605, "lr": 2.436349241696885e-06, "epoch": 6.005154639175258, "percentage": 85.79, "elapsed_time": "9:15:52", "remaining_time": "1:32:05"} +{"current_steps": 1170, "total_steps": 1358, "loss": 0.2577, "lr": 2.314832760746244e-06, "epoch": 6.030927835051546, "percentage": 86.16, "elapsed_time": "9:18:12", "remaining_time": "1:29:41"} +{"current_steps": 1175, "total_steps": 1358, "loss": 0.2567, "lr": 2.196238416526415e-06, "epoch": 6.056701030927835, "percentage": 86.52, "elapsed_time": "9:20:32", "remaining_time": "1:27:18"} +{"current_steps": 1180, "total_steps": 1358, "loss": 0.2603, "lr": 2.0805858044918638e-06, "epoch": 6.082474226804123, "percentage": 86.89, "elapsed_time": "9:22:54", "remaining_time": "1:24:54"} +{"current_steps": 1185, "total_steps": 1358, "loss": 0.2543, "lr": 1.9678940340318984e-06, "epoch": 6.108247422680412, "percentage": 87.26, "elapsed_time": "9:25:18", "remaining_time": "1:22:31"} +{"current_steps": 1190, "total_steps": 1358, "loss": 0.2585, "lr": 1.8581817253131861e-06, "epoch": 6.134020618556701, "percentage": 87.63, "elapsed_time": "9:27:43", "remaining_time": "1:20:08"} +{"current_steps": 1195, "total_steps": 1358, "loss": 0.2571, "lr": 1.751467006203158e-06, "epoch": 6.15979381443299, "percentage": 88.0, "elapsed_time": "9:30:04", "remaining_time": "1:17:45"} +{"current_steps": 1200, "total_steps": 1358, "loss": 0.256, "lr": 1.6477675092747113e-06, "epoch": 6.185567010309279, "percentage": 88.37, "elapsed_time": "9:32:26", "remaining_time": "1:15:22"} +{"current_steps": 1205, "total_steps": 1358, "loss": 0.2606, "lr": 1.5471003688927423e-06, "epoch": 6.211340206185567, "percentage": 88.73, "elapsed_time": "9:34:54", "remaining_time": "1:12:59"} +{"current_steps": 1210, "total_steps": 1358, "loss": 0.2615, "lr": 1.4494822183830604e-06, "epoch": 6.237113402061856, "percentage": 89.1, "elapsed_time": "9:37:17", "remaining_time": "1:10:36"} +{"current_steps": 1215, "total_steps": 1358, "loss": 0.2617, "lr": 1.3549291872840087e-06, "epoch": 6.262886597938144, "percentage": 89.47, "elapsed_time": "9:39:38", "remaining_time": "1:08:13"} +{"current_steps": 1220, "total_steps": 1358, "loss": 0.2652, "lr": 1.2634568986813878e-06, "epoch": 6.288659793814433, "percentage": 89.84, "elapsed_time": "9:41:59", "remaining_time": "1:05:49"} +{"current_steps": 1225, "total_steps": 1358, "loss": 0.2576, "lr": 1.1750804666270365e-06, "epoch": 6.314432989690721, "percentage": 90.21, "elapsed_time": "9:44:21", "remaining_time": "1:03:26"} +{"current_steps": 1230, "total_steps": 1358, "loss": 0.2672, "lr": 1.0898144936415168e-06, "epoch": 6.34020618556701, "percentage": 90.57, "elapsed_time": "9:46:45", "remaining_time": "1:01:03"} +{"current_steps": 1235, "total_steps": 1358, "loss": 0.2564, "lr": 1.007673068301327e-06, "epoch": 6.365979381443299, "percentage": 90.94, "elapsed_time": "9:49:07", "remaining_time": "0:58:40"} +{"current_steps": 1240, "total_steps": 1358, "loss": 0.2603, "lr": 9.286697629110319e-07, "epoch": 6.391752577319588, "percentage": 91.31, "elapsed_time": "9:51:29", "remaining_time": "0:56:17"} +{"current_steps": 1245, "total_steps": 1358, "loss": 0.2599, "lr": 8.528176312607072e-07, "epoch": 6.417525773195877, "percentage": 91.68, "elapsed_time": "9:53:50", "remaining_time": "0:53:53"} +{"current_steps": 1250, "total_steps": 1358, "loss": 0.2599, "lr": 7.80129206469038e-07, "epoch": 6.443298969072165, "percentage": 92.05, "elapsed_time": "9:56:14", "remaining_time": "0:51:30"} +{"current_steps": 1255, "total_steps": 1358, "loss": 0.2577, "lr": 7.106164989124708e-07, "epoch": 6.469072164948454, "percentage": 92.42, "elapsed_time": "9:58:37", "remaining_time": "0:49:07"} +{"current_steps": 1260, "total_steps": 1358, "loss": 0.2589, "lr": 6.442909942407105e-07, "epoch": 6.494845360824742, "percentage": 92.78, "elapsed_time": "10:01:03", "remaining_time": "0:46:44"} +{"current_steps": 1265, "total_steps": 1358, "loss": 0.275, "lr": 5.811636514789598e-07, "epoch": 6.520618556701031, "percentage": 93.15, "elapsed_time": "10:03:25", "remaining_time": "0:44:21"} +{"current_steps": 1270, "total_steps": 1358, "loss": 0.2588, "lr": 5.212449012171306e-07, "epoch": 6.546391752577319, "percentage": 93.52, "elapsed_time": "10:05:46", "remaining_time": "0:41:58"} +{"current_steps": 1275, "total_steps": 1358, "loss": 0.2622, "lr": 4.64544643886391e-07, "epoch": 6.572164948453608, "percentage": 93.89, "elapsed_time": "10:08:07", "remaining_time": "0:39:35"} +{"current_steps": 1280, "total_steps": 1358, "loss": 0.2633, "lr": 4.1107224812331867e-07, "epoch": 6.597938144329897, "percentage": 94.26, "elapsed_time": "10:10:31", "remaining_time": "0:37:12"} +{"current_steps": 1285, "total_steps": 1358, "loss": 0.2535, "lr": 3.6083654922189237e-07, "epoch": 6.623711340206185, "percentage": 94.62, "elapsed_time": "10:12:54", "remaining_time": "0:34:49"} +{"current_steps": 1290, "total_steps": 1358, "loss": 0.2625, "lr": 3.1384584767365276e-07, "epoch": 6.649484536082475, "percentage": 94.99, "elapsed_time": "10:15:16", "remaining_time": "0:32:25"} +{"current_steps": 1295, "total_steps": 1358, "loss": 0.2582, "lr": 2.701079077961821e-07, "epoch": 6.675257731958763, "percentage": 95.36, "elapsed_time": "10:17:38", "remaining_time": "0:30:02"} +{"current_steps": 1300, "total_steps": 1358, "loss": 0.263, "lr": 2.2962995645021469e-07, "epoch": 6.701030927835052, "percentage": 95.73, "elapsed_time": "10:19:59", "remaining_time": "0:27:39"} +{"current_steps": 1305, "total_steps": 1358, "loss": 0.2718, "lr": 1.9241868184552537e-07, "epoch": 6.72680412371134, "percentage": 96.1, "elapsed_time": "10:22:22", "remaining_time": "0:25:16"} +{"current_steps": 1310, "total_steps": 1358, "loss": 0.261, "lr": 1.5848023243583143e-07, "epoch": 6.752577319587629, "percentage": 96.47, "elapsed_time": "10:24:46", "remaining_time": "0:22:53"} +{"current_steps": 1315, "total_steps": 1358, "loss": 0.2663, "lr": 1.278202159028896e-07, "epoch": 6.778350515463917, "percentage": 96.83, "elapsed_time": "10:27:09", "remaining_time": "0:20:30"} +{"current_steps": 1320, "total_steps": 1358, "loss": 0.2565, "lr": 1.0044369822991729e-07, "epoch": 6.804123711340206, "percentage": 97.2, "elapsed_time": "10:29:29", "remaining_time": "0:18:07"} +{"current_steps": 1325, "total_steps": 1358, "loss": 0.2505, "lr": 7.635520286454868e-08, "epoch": 6.829896907216495, "percentage": 97.57, "elapsed_time": "10:31:48", "remaining_time": "0:15:44"} +{"current_steps": 1330, "total_steps": 1358, "loss": 0.2571, "lr": 5.555870997140833e-08, "epoch": 6.855670103092783, "percentage": 97.94, "elapsed_time": "10:34:07", "remaining_time": "0:13:21"} +{"current_steps": 1335, "total_steps": 1358, "loss": 0.2577, "lr": 3.8057655774479395e-08, "epoch": 6.881443298969073, "percentage": 98.31, "elapsed_time": "10:36:30", "remaining_time": "0:10:57"} +{"current_steps": 1340, "total_steps": 1358, "loss": 0.2604, "lr": 2.3854931989319986e-08, "epoch": 6.907216494845361, "percentage": 98.67, "elapsed_time": "10:38:52", "remaining_time": "0:08:34"} +{"current_steps": 1345, "total_steps": 1358, "loss": 0.26, "lr": 1.295288534527206e-08, "epoch": 6.93298969072165, "percentage": 99.04, "elapsed_time": "10:41:14", "remaining_time": "0:06:11"} +{"current_steps": 1350, "total_steps": 1358, "loss": 0.2617, "lr": 5.353317197702712e-09, "epoch": 6.958762886597938, "percentage": 99.41, "elapsed_time": "10:43:38", "remaining_time": "0:03:48"} +{"current_steps": 1355, "total_steps": 1358, "loss": 0.2569, "lr": 1.0574832303689164e-09, "epoch": 6.984536082474227, "percentage": 99.78, "elapsed_time": "10:45:59", "remaining_time": "0:01:25"} +{"current_steps": 1358, "total_steps": 1358, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "10:47:32", "remaining_time": "0:00:00"} +{"current_steps": 1358, "total_steps": 1358, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"} +{"current_steps": 1358, "total_steps": 1358, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"} +{"current_steps": 1358, "total_steps": 1358, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"} +{"current_steps": 1358, "total_steps": 1358, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..9d2eba3 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3024 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.0, + "eval_steps": 500, + "global_step": 1358, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.02577319587628866, + "grad_norm": 19.361754624645346, + "learning_rate": 1.1764705882352942e-06, + "loss": 0.7739, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.2674316167831421, + "step": 5, + "valid_targets_mean": 6342.4, + "valid_targets_min": 796 + }, + { + "epoch": 0.05154639175257732, + "grad_norm": 14.776293018924607, + "learning_rate": 2.647058823529412e-06, + "loss": 0.747, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.26964008808135986, + "step": 10, + "valid_targets_mean": 6470.9, + "valid_targets_min": 589 + }, + { + "epoch": 0.07731958762886598, + "grad_norm": 6.299200585171311, + "learning_rate": 4.11764705882353e-06, + "loss": 0.6522, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.19556403160095215, + "step": 15, + "valid_targets_mean": 5640.0, + "valid_targets_min": 568 + }, + { + "epoch": 0.10309278350515463, + "grad_norm": 2.1706585789929167, + "learning_rate": 5.588235294117647e-06, + "loss": 0.5807, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.20123359560966492, + "step": 20, + "valid_targets_mean": 5792.0, + "valid_targets_min": 421 + }, + { + "epoch": 0.12886597938144329, + "grad_norm": 1.281667358551557, + "learning_rate": 7.058823529411766e-06, + "loss": 0.5389, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.18983393907546997, + "step": 25, + "valid_targets_mean": 6190.2, + "valid_targets_min": 637 + }, + { + "epoch": 0.15463917525773196, + "grad_norm": 0.9543622306940317, + "learning_rate": 8.529411764705883e-06, + "loss": 0.5272, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1809738576412201, + "step": 30, + "valid_targets_mean": 5972.4, + "valid_targets_min": 657 + }, + { + "epoch": 0.18041237113402062, + "grad_norm": 0.6809974107949935, + "learning_rate": 1e-05, + "loss": 0.496, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.17243939638137817, + "step": 35, + "valid_targets_mean": 6295.2, + "valid_targets_min": 687 + }, + { + "epoch": 0.20618556701030927, + "grad_norm": 0.5174417340859547, + "learning_rate": 1.1470588235294118e-05, + "loss": 0.487, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12923963367938995, + "step": 40, + "valid_targets_mean": 5336.0, + "valid_targets_min": 587 + }, + { + "epoch": 0.23195876288659795, + "grad_norm": 0.4256636161095827, + "learning_rate": 1.2941176470588238e-05, + "loss": 0.4661, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1391327828168869, + "step": 45, + "valid_targets_mean": 6423.3, + "valid_targets_min": 567 + }, + { + "epoch": 0.25773195876288657, + "grad_norm": 0.3673686393591969, + "learning_rate": 1.4411764705882353e-05, + "loss": 0.4478, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13855600357055664, + "step": 50, + "valid_targets_mean": 5495.0, + "valid_targets_min": 540 + }, + { + "epoch": 0.28350515463917525, + "grad_norm": 0.28758629083178733, + "learning_rate": 1.5882352941176473e-05, + "loss": 0.4307, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12716147303581238, + "step": 55, + "valid_targets_mean": 5351.4, + "valid_targets_min": 455 + }, + { + "epoch": 0.30927835051546393, + "grad_norm": 0.2803915310544906, + "learning_rate": 1.735294117647059e-05, + "loss": 0.4226, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13830243051052094, + "step": 60, + "valid_targets_mean": 5775.8, + "valid_targets_min": 526 + }, + { + "epoch": 0.33505154639175255, + "grad_norm": 0.2975359105410568, + "learning_rate": 1.8823529411764708e-05, + "loss": 0.4034, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13560298085212708, + "step": 65, + "valid_targets_mean": 6934.9, + "valid_targets_min": 619 + }, + { + "epoch": 0.36082474226804123, + "grad_norm": 0.25312341649003284, + "learning_rate": 2.0294117647058825e-05, + "loss": 0.4074, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13240735232830048, + "step": 70, + "valid_targets_mean": 6072.6, + "valid_targets_min": 575 + }, + { + "epoch": 0.3865979381443299, + "grad_norm": 0.2327782906957274, + "learning_rate": 2.1764705882352943e-05, + "loss": 0.3876, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12153078615665436, + "step": 75, + "valid_targets_mean": 5931.8, + "valid_targets_min": 770 + }, + { + "epoch": 0.41237113402061853, + "grad_norm": 0.23209410691794588, + "learning_rate": 2.3235294117647064e-05, + "loss": 0.376, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12323503196239471, + "step": 80, + "valid_targets_mean": 5867.5, + "valid_targets_min": 627 + }, + { + "epoch": 0.4381443298969072, + "grad_norm": 0.22608571307773745, + "learning_rate": 2.470588235294118e-05, + "loss": 0.3845, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1206689402461052, + "step": 85, + "valid_targets_mean": 5408.6, + "valid_targets_min": 674 + }, + { + "epoch": 0.4639175257731959, + "grad_norm": 0.6310853681606622, + "learning_rate": 2.6176470588235295e-05, + "loss": 0.3754, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11591410636901855, + "step": 90, + "valid_targets_mean": 5860.6, + "valid_targets_min": 629 + }, + { + "epoch": 0.4896907216494845, + "grad_norm": 0.2303573287176781, + "learning_rate": 2.7647058823529413e-05, + "loss": 0.3617, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10666414350271225, + "step": 95, + "valid_targets_mean": 5568.6, + "valid_targets_min": 484 + }, + { + "epoch": 0.5154639175257731, + "grad_norm": 0.2302775696607361, + "learning_rate": 2.911764705882353e-05, + "loss": 0.3555, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.13573025166988373, + "step": 100, + "valid_targets_mean": 6281.9, + "valid_targets_min": 614 + }, + { + "epoch": 0.5412371134020618, + "grad_norm": 0.21637067325838502, + "learning_rate": 3.0588235294117644e-05, + "loss": 0.3549, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0937468409538269, + "step": 105, + "valid_targets_mean": 5264.0, + "valid_targets_min": 542 + }, + { + "epoch": 0.5670103092783505, + "grad_norm": 0.23809642219447041, + "learning_rate": 3.205882352941177e-05, + "loss": 0.344, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10166369378566742, + "step": 110, + "valid_targets_mean": 6304.4, + "valid_targets_min": 524 + }, + { + "epoch": 0.5927835051546392, + "grad_norm": 0.23288667622755851, + "learning_rate": 3.3529411764705886e-05, + "loss": 0.3511, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10661657154560089, + "step": 115, + "valid_targets_mean": 5671.1, + "valid_targets_min": 632 + }, + { + "epoch": 0.6185567010309279, + "grad_norm": 0.2484689669811016, + "learning_rate": 3.5000000000000004e-05, + "loss": 0.341, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11113717406988144, + "step": 120, + "valid_targets_mean": 5165.4, + "valid_targets_min": 647 + }, + { + "epoch": 0.6443298969072165, + "grad_norm": 0.2482938299277476, + "learning_rate": 3.647058823529412e-05, + "loss": 0.3343, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10907314717769623, + "step": 125, + "valid_targets_mean": 5740.9, + "valid_targets_min": 541 + }, + { + "epoch": 0.6701030927835051, + "grad_norm": 0.25658063294793965, + "learning_rate": 3.794117647058824e-05, + "loss": 0.3471, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1199379414319992, + "step": 130, + "valid_targets_mean": 5379.9, + "valid_targets_min": 538 + }, + { + "epoch": 0.6958762886597938, + "grad_norm": 0.280087729238946, + "learning_rate": 3.9411764705882356e-05, + "loss": 0.3413, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11225313693284988, + "step": 135, + "valid_targets_mean": 5651.6, + "valid_targets_min": 607 + }, + { + "epoch": 0.7216494845360825, + "grad_norm": 0.24721279712124644, + "learning_rate": 3.999940516338956e-05, + "loss": 0.3306, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1001933217048645, + "step": 140, + "valid_targets_mean": 5565.4, + "valid_targets_min": 624 + }, + { + "epoch": 0.7474226804123711, + "grad_norm": 0.23337875442078515, + "learning_rate": 3.99957701789056e-05, + "loss": 0.3175, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10798051208257675, + "step": 145, + "valid_targets_mean": 5987.2, + "valid_targets_min": 506 + }, + { + "epoch": 0.7731958762886598, + "grad_norm": 0.2493552441513084, + "learning_rate": 3.998883127460509e-05, + "loss": 0.3232, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.101970374584198, + "step": 150, + "valid_targets_mean": 5937.7, + "valid_targets_min": 605 + }, + { + "epoch": 0.7989690721649485, + "grad_norm": 0.24775631537939216, + "learning_rate": 3.997858959700969e-05, + "loss": 0.3359, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10961902141571045, + "step": 155, + "valid_targets_mean": 6309.8, + "valid_targets_min": 594 + }, + { + "epoch": 0.8247422680412371, + "grad_norm": 0.25978597983421364, + "learning_rate": 3.996504683836136e-05, + "loss": 0.324, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11169438064098358, + "step": 160, + "valid_targets_mean": 5201.8, + "valid_targets_min": 420 + }, + { + "epoch": 0.8505154639175257, + "grad_norm": 0.23898990849913665, + "learning_rate": 3.994820523634279e-05, + "loss": 0.3245, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09977433830499649, + "step": 165, + "valid_targets_mean": 5932.4, + "valid_targets_min": 290 + }, + { + "epoch": 0.8762886597938144, + "grad_norm": 0.24238386639193504, + "learning_rate": 3.992806757370764e-05, + "loss": 0.3248, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1041790246963501, + "step": 170, + "valid_targets_mean": 5472.7, + "valid_targets_min": 603 + }, + { + "epoch": 0.9020618556701031, + "grad_norm": 0.25746086870152124, + "learning_rate": 3.990463717782074e-05, + "loss": 0.3137, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1092878133058548, + "step": 175, + "valid_targets_mean": 5549.4, + "valid_targets_min": 470 + }, + { + "epoch": 0.9278350515463918, + "grad_norm": 0.2592996660818364, + "learning_rate": 3.987791792010834e-05, + "loss": 0.323, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10904739797115326, + "step": 180, + "valid_targets_mean": 6642.5, + "valid_targets_min": 678 + }, + { + "epoch": 0.9536082474226805, + "grad_norm": 0.2550877179756528, + "learning_rate": 3.984791421541839e-05, + "loss": 0.323, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11759485304355621, + "step": 185, + "valid_targets_mean": 5979.9, + "valid_targets_min": 678 + }, + { + "epoch": 0.979381443298969, + "grad_norm": 0.23574276810911696, + "learning_rate": 3.981463102129109e-05, + "loss": 0.3266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0982227697968483, + "step": 190, + "valid_targets_mean": 5994.5, + "valid_targets_min": 583 + }, + { + "epoch": 1.0051546391752577, + "grad_norm": 0.2409637458488068, + "learning_rate": 3.9778073837139735e-05, + "loss": 0.3167, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09220079332590103, + "step": 195, + "valid_targets_mean": 5070.1, + "valid_targets_min": 620 + }, + { + "epoch": 1.0309278350515463, + "grad_norm": 0.2380204035855985, + "learning_rate": 3.9738248703342085e-05, + "loss": 0.3124, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09644968062639236, + "step": 200, + "valid_targets_mean": 6010.5, + "valid_targets_min": 604 + }, + { + "epoch": 1.056701030927835, + "grad_norm": 0.2549648587514221, + "learning_rate": 3.9695162200242256e-05, + "loss": 0.3132, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11107391119003296, + "step": 205, + "valid_targets_mean": 6042.8, + "valid_targets_min": 777 + }, + { + "epoch": 1.0824742268041236, + "grad_norm": 0.2534182080407131, + "learning_rate": 3.964882144706347e-05, + "loss": 0.3077, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10496579855680466, + "step": 210, + "valid_targets_mean": 5895.7, + "valid_targets_min": 574 + }, + { + "epoch": 1.1082474226804124, + "grad_norm": 0.25768862239255363, + "learning_rate": 3.959923410073174e-05, + "loss": 0.3141, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10322555154561996, + "step": 215, + "valid_targets_mean": 5244.7, + "valid_targets_min": 593 + }, + { + "epoch": 1.134020618556701, + "grad_norm": 0.2426564982364801, + "learning_rate": 3.954640835461069e-05, + "loss": 0.3158, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10308908671140671, + "step": 220, + "valid_targets_mean": 6443.2, + "valid_targets_min": 590 + }, + { + "epoch": 1.1597938144329896, + "grad_norm": 0.23655770946779622, + "learning_rate": 3.9490352937147786e-05, + "loss": 0.3133, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11381332576274872, + "step": 225, + "valid_targets_mean": 6552.3, + "valid_targets_min": 575 + }, + { + "epoch": 1.1855670103092784, + "grad_norm": 0.24301765299422307, + "learning_rate": 3.943107711043211e-05, + "loss": 0.3031, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10668733716011047, + "step": 230, + "valid_targets_mean": 5882.4, + "valid_targets_min": 601 + }, + { + "epoch": 1.211340206185567, + "grad_norm": 0.2514857854558027, + "learning_rate": 3.936859066866397e-05, + "loss": 0.3109, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08552701771259308, + "step": 235, + "valid_targets_mean": 5791.9, + "valid_targets_min": 618 + }, + { + "epoch": 1.2371134020618557, + "grad_norm": 0.2877896952104453, + "learning_rate": 3.93029039365366e-05, + "loss": 0.3147, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09683221578598022, + "step": 240, + "valid_targets_mean": 5507.1, + "valid_targets_min": 635 + }, + { + "epoch": 1.2628865979381443, + "grad_norm": 0.23920924217001596, + "learning_rate": 3.923402776753022e-05, + "loss": 0.3011, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11555798351764679, + "step": 245, + "valid_targets_mean": 6155.2, + "valid_targets_min": 806 + }, + { + "epoch": 1.2886597938144329, + "grad_norm": 0.25899916480361196, + "learning_rate": 3.9161973542118686e-05, + "loss": 0.3044, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10108867287635803, + "step": 250, + "valid_targets_mean": 6389.3, + "valid_targets_min": 689 + }, + { + "epoch": 1.3144329896907216, + "grad_norm": 0.23959656238848795, + "learning_rate": 3.9086753165889076e-05, + "loss": 0.2985, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0946207121014595, + "step": 255, + "valid_targets_mean": 5665.8, + "valid_targets_min": 596 + }, + { + "epoch": 1.3402061855670104, + "grad_norm": 0.23205059436417375, + "learning_rate": 3.900837906757454e-05, + "loss": 0.3096, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1049540713429451, + "step": 260, + "valid_targets_mean": 6088.0, + "valid_targets_min": 549 + }, + { + "epoch": 1.365979381443299, + "grad_norm": 0.23826424065683088, + "learning_rate": 3.8926864197000676e-05, + "loss": 0.3124, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10210095345973969, + "step": 265, + "valid_targets_mean": 5778.2, + "valid_targets_min": 455 + }, + { + "epoch": 1.3917525773195876, + "grad_norm": 0.23824515889271916, + "learning_rate": 3.8842222022945823e-05, + "loss": 0.3049, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10111156105995178, + "step": 270, + "valid_targets_mean": 6070.1, + "valid_targets_min": 605 + }, + { + "epoch": 1.4175257731958764, + "grad_norm": 0.23845633943933653, + "learning_rate": 3.875446653091559e-05, + "loss": 0.2924, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11315014958381653, + "step": 275, + "valid_targets_mean": 6917.2, + "valid_targets_min": 983 + }, + { + "epoch": 1.443298969072165, + "grad_norm": 0.2310439199773325, + "learning_rate": 3.866361222083205e-05, + "loss": 0.3095, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08991458266973495, + "step": 280, + "valid_targets_mean": 5686.5, + "valid_targets_min": 627 + }, + { + "epoch": 1.4690721649484537, + "grad_norm": 0.22655104228409462, + "learning_rate": 3.856967410463787e-05, + "loss": 0.2981, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09699489921331406, + "step": 285, + "valid_targets_mean": 5802.7, + "valid_targets_min": 458 + }, + { + "epoch": 1.4948453608247423, + "grad_norm": 0.22292542695729753, + "learning_rate": 3.8472667703815876e-05, + "loss": 0.3017, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09988431632518768, + "step": 290, + "valid_targets_mean": 6589.3, + "valid_targets_min": 559 + }, + { + "epoch": 1.5206185567010309, + "grad_norm": 0.2408453057328623, + "learning_rate": 3.837260904682445e-05, + "loss": 0.2977, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09748954325914383, + "step": 295, + "valid_targets_mean": 6321.9, + "valid_targets_min": 586 + }, + { + "epoch": 1.5463917525773194, + "grad_norm": 0.23558386336961148, + "learning_rate": 3.8269514666449116e-05, + "loss": 0.3025, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10613813996315002, + "step": 300, + "valid_targets_mean": 6418.5, + "valid_targets_min": 806 + }, + { + "epoch": 1.5721649484536082, + "grad_norm": 0.24812086882951945, + "learning_rate": 3.816340159707079e-05, + "loss": 0.298, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10738293081521988, + "step": 305, + "valid_targets_mean": 5983.7, + "valid_targets_min": 601 + }, + { + "epoch": 1.597938144329897, + "grad_norm": 0.21029547243360874, + "learning_rate": 3.805428737185124e-05, + "loss": 0.2903, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08348864316940308, + "step": 310, + "valid_targets_mean": 5838.5, + "valid_targets_min": 657 + }, + { + "epoch": 1.6237113402061856, + "grad_norm": 0.23325282068417247, + "learning_rate": 3.794219001983597e-05, + "loss": 0.2854, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08546201884746552, + "step": 315, + "valid_targets_mean": 5487.7, + "valid_targets_min": 503 + }, + { + "epoch": 1.6494845360824741, + "grad_norm": 0.23941733339783547, + "learning_rate": 3.782712806297536e-05, + "loss": 0.298, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09802323579788208, + "step": 320, + "valid_targets_mean": 5105.8, + "valid_targets_min": 687 + }, + { + "epoch": 1.675257731958763, + "grad_norm": 0.2429264263419137, + "learning_rate": 3.7709120513064196e-05, + "loss": 0.2957, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10877049714326859, + "step": 325, + "valid_targets_mean": 6018.4, + "valid_targets_min": 524 + }, + { + "epoch": 1.7010309278350515, + "grad_norm": 0.2286086286790759, + "learning_rate": 3.758818686860038e-05, + "loss": 0.2941, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09833472967147827, + "step": 330, + "valid_targets_mean": 6012.3, + "valid_targets_min": 683 + }, + { + "epoch": 1.7268041237113403, + "grad_norm": 0.23910119281288197, + "learning_rate": 3.746434711156314e-05, + "loss": 0.2939, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11784946173429489, + "step": 335, + "valid_targets_mean": 6342.0, + "valid_targets_min": 659 + }, + { + "epoch": 1.7525773195876289, + "grad_norm": 0.24850545007143537, + "learning_rate": 3.733762170411138e-05, + "loss": 0.3005, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09112188220024109, + "step": 340, + "valid_targets_mean": 5050.5, + "valid_targets_min": 506 + }, + { + "epoch": 1.7783505154639174, + "grad_norm": 0.24896810002197928, + "learning_rate": 3.720803158520279e-05, + "loss": 0.2991, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11645789444446564, + "step": 345, + "valid_targets_mean": 6646.2, + "valid_targets_min": 992 + }, + { + "epoch": 1.8041237113402062, + "grad_norm": 0.24171025750101124, + "learning_rate": 3.707559816713395e-05, + "loss": 0.2936, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08031776547431946, + "step": 350, + "valid_targets_mean": 5258.9, + "valid_targets_min": 503 + }, + { + "epoch": 1.829896907216495, + "grad_norm": 0.22904770581010406, + "learning_rate": 3.694034333200245e-05, + "loss": 0.301, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0882028341293335, + "step": 355, + "valid_targets_mean": 5434.7, + "valid_targets_min": 676 + }, + { + "epoch": 1.8556701030927836, + "grad_norm": 0.2582656548833247, + "learning_rate": 3.680228942809126e-05, + "loss": 0.292, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09634621441364288, + "step": 360, + "valid_targets_mean": 5531.5, + "valid_targets_min": 612 + }, + { + "epoch": 1.8814432989690721, + "grad_norm": 0.21524059520826663, + "learning_rate": 3.666145926617609e-05, + "loss": 0.2888, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.096525639295578, + "step": 365, + "valid_targets_mean": 5507.4, + "valid_targets_min": 682 + }, + { + "epoch": 1.9072164948453607, + "grad_norm": 0.24255084476459574, + "learning_rate": 3.6517876115756376e-05, + "loss": 0.2922, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09641002118587494, + "step": 370, + "valid_targets_mean": 5803.1, + "valid_targets_min": 811 + }, + { + "epoch": 1.9329896907216495, + "grad_norm": 0.23858816600196303, + "learning_rate": 3.6371563701210406e-05, + "loss": 0.3038, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10171850025653839, + "step": 375, + "valid_targets_mean": 6099.8, + "valid_targets_min": 801 + }, + { + "epoch": 1.9587628865979383, + "grad_norm": 0.23332041195703118, + "learning_rate": 3.622254619787533e-05, + "loss": 0.2941, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10116893798112869, + "step": 380, + "valid_targets_mean": 6078.7, + "valid_targets_min": 733 + }, + { + "epoch": 1.9845360824742269, + "grad_norm": 0.2420312100632208, + "learning_rate": 3.607084822805268e-05, + "loss": 0.2951, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08722677826881409, + "step": 385, + "valid_targets_mean": 5265.4, + "valid_targets_min": 591 + }, + { + "epoch": 2.0103092783505154, + "grad_norm": 0.2343248517342809, + "learning_rate": 3.5916494856939944e-05, + "loss": 0.2949, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08683840185403824, + "step": 390, + "valid_targets_mean": 5935.9, + "valid_targets_min": 645 + }, + { + "epoch": 2.036082474226804, + "grad_norm": 0.24099732747355063, + "learning_rate": 3.575951158848905e-05, + "loss": 0.2882, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10633479058742523, + "step": 395, + "valid_targets_mean": 6427.1, + "valid_targets_min": 576 + }, + { + "epoch": 2.0618556701030926, + "grad_norm": 0.2658298537622557, + "learning_rate": 3.5599924361192335e-05, + "loss": 0.2835, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09219761192798615, + "step": 400, + "valid_targets_mean": 6387.1, + "valid_targets_min": 674 + }, + { + "epoch": 2.0876288659793816, + "grad_norm": 0.24887435726906582, + "learning_rate": 3.54377595437967e-05, + "loss": 0.2872, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09384647756814957, + "step": 405, + "valid_targets_mean": 5790.4, + "valid_targets_min": 618 + }, + { + "epoch": 2.11340206185567, + "grad_norm": 0.2342275822421684, + "learning_rate": 3.527304393094665e-05, + "loss": 0.2822, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09381407499313354, + "step": 410, + "valid_targets_mean": 5896.6, + "valid_targets_min": 618 + }, + { + "epoch": 2.1391752577319587, + "grad_norm": 0.2534942268345584, + "learning_rate": 3.510580473875701e-05, + "loss": 0.2917, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1218668520450592, + "step": 415, + "valid_targets_mean": 6681.8, + "valid_targets_min": 518 + }, + { + "epoch": 2.1649484536082473, + "grad_norm": 0.23284944470966143, + "learning_rate": 3.493606960031601e-05, + "loss": 0.2757, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09857223927974701, + "step": 420, + "valid_targets_mean": 6568.3, + "valid_targets_min": 527 + }, + { + "epoch": 2.1907216494845363, + "grad_norm": 0.2421756941998698, + "learning_rate": 3.476386656111938e-05, + "loss": 0.2851, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09131501615047455, + "step": 425, + "valid_targets_mean": 5952.6, + "valid_targets_min": 750 + }, + { + "epoch": 2.216494845360825, + "grad_norm": 0.25771606949400594, + "learning_rate": 3.458922407443643e-05, + "loss": 0.2844, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09061141312122345, + "step": 430, + "valid_targets_mean": 5639.3, + "valid_targets_min": 734 + }, + { + "epoch": 2.2422680412371134, + "grad_norm": 0.24545909429015159, + "learning_rate": 3.441217099660864e-05, + "loss": 0.2853, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11367497593164444, + "step": 435, + "valid_targets_mean": 6035.3, + "valid_targets_min": 689 + }, + { + "epoch": 2.268041237113402, + "grad_norm": 0.28375620819640673, + "learning_rate": 3.423273658228171e-05, + "loss": 0.2887, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09130064398050308, + "step": 440, + "valid_targets_mean": 5681.8, + "valid_targets_min": 594 + }, + { + "epoch": 2.2938144329896906, + "grad_norm": 0.251365825220021, + "learning_rate": 3.405095047957183e-05, + "loss": 0.2923, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09749715775251389, + "step": 445, + "valid_targets_mean": 5888.2, + "valid_targets_min": 960 + }, + { + "epoch": 2.319587628865979, + "grad_norm": 0.2402309094467951, + "learning_rate": 3.3866842725166855e-05, + "loss": 0.2828, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0872880220413208, + "step": 450, + "valid_targets_mean": 5899.3, + "valid_targets_min": 769 + }, + { + "epoch": 2.345360824742268, + "grad_norm": 0.25176884070476524, + "learning_rate": 3.3680443739363304e-05, + "loss": 0.2829, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1044222041964531, + "step": 455, + "valid_targets_mean": 5661.7, + "valid_targets_min": 503 + }, + { + "epoch": 2.3711340206185567, + "grad_norm": 0.23866003231483893, + "learning_rate": 3.349178432104001e-05, + "loss": 0.2866, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09630560874938965, + "step": 460, + "valid_targets_mean": 6392.2, + "valid_targets_min": 612 + }, + { + "epoch": 2.3969072164948453, + "grad_norm": 0.23396899390869666, + "learning_rate": 3.330089564256919e-05, + "loss": 0.2875, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10524716228246689, + "step": 465, + "valid_targets_mean": 6265.0, + "valid_targets_min": 524 + }, + { + "epoch": 2.422680412371134, + "grad_norm": 0.25436406743642886, + "learning_rate": 3.3107809244665805e-05, + "loss": 0.2908, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09861588478088379, + "step": 470, + "valid_targets_mean": 5925.4, + "valid_targets_min": 548 + }, + { + "epoch": 2.448453608247423, + "grad_norm": 0.2315961680878081, + "learning_rate": 3.291255703117605e-05, + "loss": 0.2847, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07914268970489502, + "step": 475, + "valid_targets_mean": 5032.7, + "valid_targets_min": 549 + }, + { + "epoch": 2.4742268041237114, + "grad_norm": 0.24059524256760667, + "learning_rate": 3.271517126380586e-05, + "loss": 0.2827, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09832991659641266, + "step": 480, + "valid_targets_mean": 5955.6, + "valid_targets_min": 877 + }, + { + "epoch": 2.5, + "grad_norm": 0.23560310629184877, + "learning_rate": 3.251568455679025e-05, + "loss": 0.2891, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.11293981969356537, + "step": 485, + "valid_targets_mean": 7011.7, + "valid_targets_min": 761 + }, + { + "epoch": 2.5257731958762886, + "grad_norm": 0.24957734753553512, + "learning_rate": 3.2314129871504504e-05, + "loss": 0.2853, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1026647537946701, + "step": 490, + "valid_targets_mean": 5802.8, + "valid_targets_min": 582 + }, + { + "epoch": 2.551546391752577, + "grad_norm": 0.22947364439758133, + "learning_rate": 3.211054051101785e-05, + "loss": 0.2766, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0943123921751976, + "step": 495, + "valid_targets_mean": 5864.0, + "valid_targets_min": 610 + }, + { + "epoch": 2.5773195876288657, + "grad_norm": 0.23770497464938728, + "learning_rate": 3.190495011459082e-05, + "loss": 0.2869, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08464314043521881, + "step": 500, + "valid_targets_mean": 5466.0, + "valid_targets_min": 659 + }, + { + "epoch": 2.6030927835051547, + "grad_norm": 0.2529741357172592, + "learning_rate": 3.1697392652116996e-05, + "loss": 0.2766, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.107028529047966, + "step": 505, + "valid_targets_mean": 6372.2, + "valid_targets_min": 661 + }, + { + "epoch": 2.6288659793814433, + "grad_norm": 0.21932740574304702, + "learning_rate": 3.1487902418510095e-05, + "loss": 0.2857, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09716858714818954, + "step": 510, + "valid_targets_mean": 6433.1, + "valid_targets_min": 681 + }, + { + "epoch": 2.654639175257732, + "grad_norm": 0.21132373673187144, + "learning_rate": 3.1276514028037444e-05, + "loss": 0.2809, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09688623994588852, + "step": 515, + "valid_targets_mean": 6873.9, + "valid_targets_min": 655 + }, + { + "epoch": 2.680412371134021, + "grad_norm": 0.22391906122745997, + "learning_rate": 3.10632624086006e-05, + "loss": 0.2746, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09009232372045517, + "step": 520, + "valid_targets_mean": 5922.0, + "valid_targets_min": 626 + }, + { + "epoch": 2.7061855670103094, + "grad_norm": 0.2416840076675489, + "learning_rate": 3.084818279596417e-05, + "loss": 0.2819, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09669722616672516, + "step": 525, + "valid_targets_mean": 5536.5, + "valid_targets_min": 463 + }, + { + "epoch": 2.731958762886598, + "grad_norm": 0.24005876397100998, + "learning_rate": 3.063131072793379e-05, + "loss": 0.283, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09082949161529541, + "step": 530, + "valid_targets_mean": 5989.2, + "valid_targets_min": 581 + }, + { + "epoch": 2.7577319587628866, + "grad_norm": 0.22663868595846726, + "learning_rate": 3.0412682038484215e-05, + "loss": 0.2741, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09188930690288544, + "step": 535, + "valid_targets_mean": 6203.5, + "valid_targets_min": 707 + }, + { + "epoch": 2.783505154639175, + "grad_norm": 0.21908930480458605, + "learning_rate": 3.019233285183835e-05, + "loss": 0.2753, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10089852660894394, + "step": 540, + "valid_targets_mean": 6096.4, + "valid_targets_min": 749 + }, + { + "epoch": 2.8092783505154637, + "grad_norm": 0.2515063915320478, + "learning_rate": 2.9970299576498495e-05, + "loss": 0.2858, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09591610729694366, + "step": 545, + "valid_targets_mean": 5674.9, + "valid_targets_min": 592 + }, + { + "epoch": 2.8350515463917527, + "grad_norm": 0.2328364488943388, + "learning_rate": 2.974661889923048e-05, + "loss": 0.2906, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.12141162902116776, + "step": 550, + "valid_targets_mean": 6436.8, + "valid_targets_min": 651 + }, + { + "epoch": 2.8608247422680413, + "grad_norm": 0.244877435814816, + "learning_rate": 2.9521327779001906e-05, + "loss": 0.2789, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10483044385910034, + "step": 555, + "valid_targets_mean": 6250.4, + "valid_targets_min": 795 + }, + { + "epoch": 2.88659793814433, + "grad_norm": 0.24326293126897247, + "learning_rate": 2.9294463440875375e-05, + "loss": 0.2846, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08272717893123627, + "step": 560, + "valid_targets_mean": 5923.4, + "valid_targets_min": 503 + }, + { + "epoch": 2.9123711340206184, + "grad_norm": 0.24352900559746452, + "learning_rate": 2.906606336985775e-05, + "loss": 0.2779, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08788428455591202, + "step": 565, + "valid_targets_mean": 4883.2, + "valid_targets_min": 627 + }, + { + "epoch": 2.9381443298969074, + "grad_norm": 0.24432741772867364, + "learning_rate": 2.883616530470648e-05, + "loss": 0.2772, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10530249029397964, + "step": 570, + "valid_targets_mean": 5787.4, + "valid_targets_min": 599 + }, + { + "epoch": 2.963917525773196, + "grad_norm": 0.2652726308860743, + "learning_rate": 2.8604807231693987e-05, + "loss": 0.2854, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08077148348093033, + "step": 575, + "valid_targets_mean": 5646.8, + "valid_targets_min": 603 + }, + { + "epoch": 2.9896907216494846, + "grad_norm": 0.23411552434676475, + "learning_rate": 2.8372027378331148e-05, + "loss": 0.2783, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08464553207159042, + "step": 580, + "valid_targets_mean": 5979.0, + "valid_targets_min": 613 + }, + { + "epoch": 3.015463917525773, + "grad_norm": 0.20260770993636365, + "learning_rate": 2.8137864207050945e-05, + "loss": 0.2746, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09096153825521469, + "step": 585, + "valid_targets_mean": 6076.0, + "valid_targets_min": 682 + }, + { + "epoch": 3.0412371134020617, + "grad_norm": 0.28486265482999723, + "learning_rate": 2.790235640885327e-05, + "loss": 0.2675, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10470966249704361, + "step": 590, + "valid_targets_mean": 6595.6, + "valid_targets_min": 546 + }, + { + "epoch": 3.0670103092783507, + "grad_norm": 0.24942742541858107, + "learning_rate": 2.7665542896911993e-05, + "loss": 0.2764, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09387102723121643, + "step": 595, + "valid_targets_mean": 6898.8, + "valid_targets_min": 2944 + }, + { + "epoch": 3.0927835051546393, + "grad_norm": 0.22996526245052193, + "learning_rate": 2.742746280014527e-05, + "loss": 0.2661, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08765529841184616, + "step": 600, + "valid_targets_mean": 5356.6, + "valid_targets_min": 683 + }, + { + "epoch": 3.118556701030928, + "grad_norm": 0.26407748188095326, + "learning_rate": 2.7188155456750257e-05, + "loss": 0.2814, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0783463567495346, + "step": 605, + "valid_targets_mean": 4844.9, + "valid_targets_min": 733 + }, + { + "epoch": 3.1443298969072164, + "grad_norm": 0.22348367760182972, + "learning_rate": 2.694766040770323e-05, + "loss": 0.2728, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09305690228939056, + "step": 610, + "valid_targets_mean": 6214.3, + "valid_targets_min": 558 + }, + { + "epoch": 3.170103092783505, + "grad_norm": 0.2361655369361659, + "learning_rate": 2.6706017390226162e-05, + "loss": 0.2754, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09483394771814346, + "step": 615, + "valid_targets_mean": 6181.8, + "valid_targets_min": 817 + }, + { + "epoch": 3.195876288659794, + "grad_norm": 0.22483897147525417, + "learning_rate": 2.646326633122094e-05, + "loss": 0.2702, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08822141587734222, + "step": 620, + "valid_targets_mean": 5600.7, + "valid_targets_min": 568 + }, + { + "epoch": 3.2216494845360826, + "grad_norm": 0.23594366918535295, + "learning_rate": 2.621944734067218e-05, + "loss": 0.28, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10289697349071503, + "step": 625, + "valid_targets_mean": 6439.7, + "valid_targets_min": 829 + }, + { + "epoch": 3.247422680412371, + "grad_norm": 0.23205688764514465, + "learning_rate": 2.597460070501983e-05, + "loss": 0.2775, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08696689456701279, + "step": 630, + "valid_targets_mean": 5283.2, + "valid_targets_min": 634 + }, + { + "epoch": 3.2731958762886597, + "grad_norm": 0.22585622138198921, + "learning_rate": 2.5728766880502604e-05, + "loss": 0.2752, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08871736377477646, + "step": 635, + "valid_targets_mean": 5726.8, + "valid_targets_min": 610 + }, + { + "epoch": 3.2989690721649483, + "grad_norm": 0.22220502134440065, + "learning_rate": 2.5481986486473352e-05, + "loss": 0.2757, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07732512056827545, + "step": 640, + "valid_targets_mean": 5585.0, + "valid_targets_min": 701 + }, + { + "epoch": 3.3247422680412373, + "grad_norm": 0.23991535815705303, + "learning_rate": 2.523430029868749e-05, + "loss": 0.27, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08161801099777222, + "step": 645, + "valid_targets_mean": 5979.8, + "valid_targets_min": 524 + }, + { + "epoch": 3.350515463917526, + "grad_norm": 0.2200888804921485, + "learning_rate": 2.498574924256558e-05, + "loss": 0.268, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08938449621200562, + "step": 650, + "valid_targets_mean": 5659.7, + "valid_targets_min": 581 + }, + { + "epoch": 3.3762886597938144, + "grad_norm": 0.22680091617135775, + "learning_rate": 2.4736374386431194e-05, + "loss": 0.2701, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08103431016206741, + "step": 655, + "valid_targets_mean": 6188.1, + "valid_targets_min": 509 + }, + { + "epoch": 3.402061855670103, + "grad_norm": 0.2304373114730706, + "learning_rate": 2.4486216934725143e-05, + "loss": 0.2815, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10041002184152603, + "step": 660, + "valid_targets_mean": 6363.6, + "valid_targets_min": 996 + }, + { + "epoch": 3.4278350515463916, + "grad_norm": 0.23661270764251344, + "learning_rate": 2.4235318221197258e-05, + "loss": 0.2749, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0988386869430542, + "step": 665, + "valid_targets_mean": 6608.8, + "valid_targets_min": 958 + }, + { + "epoch": 3.4536082474226806, + "grad_norm": 0.2515269393218624, + "learning_rate": 2.3983719702076724e-05, + "loss": 0.2785, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09459570050239563, + "step": 670, + "valid_targets_mean": 5628.4, + "valid_targets_min": 492 + }, + { + "epoch": 3.479381443298969, + "grad_norm": 0.22183184343635845, + "learning_rate": 2.3731462949222282e-05, + "loss": 0.2685, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10383935272693634, + "step": 675, + "valid_targets_mean": 6286.9, + "valid_targets_min": 610 + }, + { + "epoch": 3.5051546391752577, + "grad_norm": 0.218173519793643, + "learning_rate": 2.347858964325324e-05, + "loss": 0.2697, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08168500661849976, + "step": 680, + "valid_targets_mean": 5534.5, + "valid_targets_min": 569 + }, + { + "epoch": 3.5309278350515463, + "grad_norm": 0.24391334613816987, + "learning_rate": 2.3225141566662556e-05, + "loss": 0.2817, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1026201918721199, + "step": 685, + "valid_targets_mean": 5892.1, + "valid_targets_min": 587 + }, + { + "epoch": 3.556701030927835, + "grad_norm": 0.22283037278700582, + "learning_rate": 2.297116059691307e-05, + "loss": 0.2717, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09592479467391968, + "step": 690, + "valid_targets_mean": 5870.2, + "valid_targets_min": 692 + }, + { + "epoch": 3.582474226804124, + "grad_norm": 0.2327362706557194, + "learning_rate": 2.2716688699518063e-05, + "loss": 0.2703, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08582796156406403, + "step": 695, + "valid_targets_mean": 5697.4, + "valid_targets_min": 617 + }, + { + "epoch": 3.6082474226804124, + "grad_norm": 0.22590384878782008, + "learning_rate": 2.2461767921107255e-05, + "loss": 0.2741, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0797477662563324, + "step": 700, + "valid_targets_mean": 5632.4, + "valid_targets_min": 574 + }, + { + "epoch": 3.634020618556701, + "grad_norm": 0.29798031320705237, + "learning_rate": 2.2206440382479378e-05, + "loss": 0.2709, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08003167808055878, + "step": 705, + "valid_targets_mean": 5537.1, + "valid_targets_min": 515 + }, + { + "epoch": 3.6597938144329896, + "grad_norm": 0.21131751862752976, + "learning_rate": 2.195074827164256e-05, + "loss": 0.2674, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1092803105711937, + "step": 710, + "valid_targets_mean": 6254.5, + "valid_targets_min": 710 + }, + { + "epoch": 3.6855670103092786, + "grad_norm": 0.2154469780366876, + "learning_rate": 2.169473383684352e-05, + "loss": 0.2679, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08612493425607681, + "step": 715, + "valid_targets_mean": 6330.3, + "valid_targets_min": 466 + }, + { + "epoch": 3.711340206185567, + "grad_norm": 0.23087260590653957, + "learning_rate": 2.143843937958687e-05, + "loss": 0.2736, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08392924070358276, + "step": 720, + "valid_targets_mean": 5510.4, + "valid_targets_min": 806 + }, + { + "epoch": 3.7371134020618557, + "grad_norm": 0.23084663151007864, + "learning_rate": 2.118190724764559e-05, + "loss": 0.2741, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08487777411937714, + "step": 725, + "valid_targets_mean": 5964.2, + "valid_targets_min": 618 + }, + { + "epoch": 3.7628865979381443, + "grad_norm": 0.22025011833513305, + "learning_rate": 2.0925179828063875e-05, + "loss": 0.2812, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10198937356472015, + "step": 730, + "valid_targets_mean": 5891.6, + "valid_targets_min": 709 + }, + { + "epoch": 3.788659793814433, + "grad_norm": 0.22121842128951696, + "learning_rate": 2.0668299540153494e-05, + "loss": 0.2803, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09764805436134338, + "step": 735, + "valid_targets_mean": 6472.3, + "valid_targets_min": 807 + }, + { + "epoch": 3.8144329896907214, + "grad_norm": 0.22565018419259, + "learning_rate": 2.0411308828484766e-05, + "loss": 0.2728, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09720548987388611, + "step": 740, + "valid_targets_mean": 6513.4, + "valid_targets_min": 796 + }, + { + "epoch": 3.8402061855670104, + "grad_norm": 0.21971367853705612, + "learning_rate": 2.0154250155873454e-05, + "loss": 0.2708, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08757640421390533, + "step": 745, + "valid_targets_mean": 5806.6, + "valid_targets_min": 531 + }, + { + "epoch": 3.865979381443299, + "grad_norm": 0.23684124646299223, + "learning_rate": 1.989716599636456e-05, + "loss": 0.2733, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09203958511352539, + "step": 750, + "valid_targets_mean": 6173.7, + "valid_targets_min": 635 + }, + { + "epoch": 3.8917525773195876, + "grad_norm": 0.2208836110906776, + "learning_rate": 1.964009882821429e-05, + "loss": 0.2699, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08275872468948364, + "step": 755, + "valid_targets_mean": 5502.0, + "valid_targets_min": 527 + }, + { + "epoch": 3.917525773195876, + "grad_norm": 0.21857410574502745, + "learning_rate": 1.9383091126871406e-05, + "loss": 0.2695, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09316932410001755, + "step": 760, + "valid_targets_mean": 5920.6, + "valid_targets_min": 585 + }, + { + "epoch": 3.943298969072165, + "grad_norm": 0.21398463578295063, + "learning_rate": 1.9126185357958863e-05, + "loss": 0.2678, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09043984115123749, + "step": 765, + "valid_targets_mean": 6321.4, + "valid_targets_min": 887 + }, + { + "epoch": 3.9690721649484537, + "grad_norm": 0.21415830494203367, + "learning_rate": 1.8869423970257243e-05, + "loss": 0.2687, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09687180817127228, + "step": 770, + "valid_targets_mean": 6493.0, + "valid_targets_min": 593 + }, + { + "epoch": 3.9948453608247423, + "grad_norm": 0.23164224876228207, + "learning_rate": 1.8612849388690893e-05, + "loss": 0.2704, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0891723483800888, + "step": 775, + "valid_targets_mean": 5776.0, + "valid_targets_min": 907 + }, + { + "epoch": 4.020618556701031, + "grad_norm": 0.21756533495233116, + "learning_rate": 1.835650400731799e-05, + "loss": 0.2642, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08937852084636688, + "step": 780, + "valid_targets_mean": 6833.9, + "valid_targets_min": 675 + }, + { + "epoch": 4.046391752577319, + "grad_norm": 0.21433750105865554, + "learning_rate": 1.810043018232577e-05, + "loss": 0.2687, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08626782894134521, + "step": 785, + "valid_targets_mean": 6847.7, + "valid_targets_min": 1132 + }, + { + "epoch": 4.072164948453608, + "grad_norm": 0.2288990231618256, + "learning_rate": 1.7844670225031934e-05, + "loss": 0.269, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07571521401405334, + "step": 790, + "valid_targets_mean": 5339.3, + "valid_targets_min": 524 + }, + { + "epoch": 4.097938144329897, + "grad_norm": 0.23192269065818466, + "learning_rate": 1.758926639489354e-05, + "loss": 0.265, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07901392877101898, + "step": 795, + "valid_targets_mean": 4847.0, + "valid_targets_min": 503 + }, + { + "epoch": 4.123711340206185, + "grad_norm": 0.23478575143774874, + "learning_rate": 1.733426089252443e-05, + "loss": 0.2697, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09161382913589478, + "step": 800, + "valid_targets_mean": 5251.7, + "valid_targets_min": 548 + }, + { + "epoch": 4.149484536082475, + "grad_norm": 0.22000507442418243, + "learning_rate": 1.7079695852722347e-05, + "loss": 0.2635, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09962445497512817, + "step": 805, + "valid_targets_mean": 5863.6, + "valid_targets_min": 685 + }, + { + "epoch": 4.175257731958763, + "grad_norm": 0.22765250973668155, + "learning_rate": 1.682561333750703e-05, + "loss": 0.2581, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0884147435426712, + "step": 810, + "valid_targets_mean": 5735.3, + "valid_targets_min": 653 + }, + { + "epoch": 4.201030927835052, + "grad_norm": 0.2095776550984572, + "learning_rate": 1.6572055329170214e-05, + "loss": 0.2652, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07988305389881134, + "step": 815, + "valid_targets_mean": 6059.3, + "valid_targets_min": 421 + }, + { + "epoch": 4.22680412371134, + "grad_norm": 0.20422248570855148, + "learning_rate": 1.6319063723338855e-05, + "loss": 0.2688, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0876869261264801, + "step": 820, + "valid_targets_mean": 6198.9, + "valid_targets_min": 726 + }, + { + "epoch": 4.252577319587629, + "grad_norm": 0.2270878274423797, + "learning_rate": 1.6066680322052703e-05, + "loss": 0.26, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08421394973993301, + "step": 825, + "valid_targets_mean": 6588.2, + "valid_targets_min": 563 + }, + { + "epoch": 4.278350515463917, + "grad_norm": 0.2178736819595442, + "learning_rate": 1.5814946826857323e-05, + "loss": 0.2669, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0885683000087738, + "step": 830, + "valid_targets_mean": 5630.2, + "valid_targets_min": 475 + }, + { + "epoch": 4.304123711340206, + "grad_norm": 0.21081740441324276, + "learning_rate": 1.5563904831913663e-05, + "loss": 0.2722, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09665192663669586, + "step": 835, + "valid_targets_mean": 6812.8, + "valid_targets_min": 665 + }, + { + "epoch": 4.329896907216495, + "grad_norm": 0.22526468296223778, + "learning_rate": 1.5313595817125445e-05, + "loss": 0.2647, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08404377102851868, + "step": 840, + "valid_targets_mean": 6131.6, + "valid_targets_min": 528 + }, + { + "epoch": 4.355670103092783, + "grad_norm": 0.2146685650480542, + "learning_rate": 1.5064061141285397e-05, + "loss": 0.2711, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08425067365169525, + "step": 845, + "valid_targets_mean": 6123.2, + "valid_targets_min": 587 + }, + { + "epoch": 4.381443298969073, + "grad_norm": 0.2127817486043924, + "learning_rate": 1.481534203524149e-05, + "loss": 0.2645, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07339270412921906, + "step": 850, + "valid_targets_mean": 5728.7, + "valid_targets_min": 580 + }, + { + "epoch": 4.407216494845361, + "grad_norm": 0.22478007486889792, + "learning_rate": 1.4567479595084349e-05, + "loss": 0.2629, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07707114517688751, + "step": 855, + "valid_targets_mean": 5482.8, + "valid_targets_min": 760 + }, + { + "epoch": 4.43298969072165, + "grad_norm": 0.24636487762866363, + "learning_rate": 1.4320514775356878e-05, + "loss": 0.2661, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10012729465961456, + "step": 860, + "valid_targets_mean": 6463.2, + "valid_targets_min": 665 + }, + { + "epoch": 4.458762886597938, + "grad_norm": 0.20615408947011518, + "learning_rate": 1.4074488382287324e-05, + "loss": 0.267, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08085936307907104, + "step": 865, + "valid_targets_mean": 5675.8, + "valid_targets_min": 705 + }, + { + "epoch": 4.484536082474227, + "grad_norm": 0.22354565382405714, + "learning_rate": 1.3829441067046822e-05, + "loss": 0.2708, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0899420902132988, + "step": 870, + "valid_targets_mean": 5963.5, + "valid_targets_min": 579 + }, + { + "epoch": 4.510309278350515, + "grad_norm": 0.2136805096947886, + "learning_rate": 1.358541331903255e-05, + "loss": 0.2626, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09212556481361389, + "step": 875, + "valid_targets_mean": 5723.1, + "valid_targets_min": 630 + }, + { + "epoch": 4.536082474226804, + "grad_norm": 0.21156293091841508, + "learning_rate": 1.3342445459177658e-05, + "loss": 0.2674, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09288851916790009, + "step": 880, + "valid_targets_mean": 6316.2, + "valid_targets_min": 761 + }, + { + "epoch": 4.561855670103093, + "grad_norm": 0.21227368812862335, + "learning_rate": 1.3100577633288967e-05, + "loss": 0.262, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08863004297018051, + "step": 885, + "valid_targets_mean": 6136.3, + "valid_targets_min": 700 + }, + { + "epoch": 4.587628865979381, + "grad_norm": 0.21992367316398848, + "learning_rate": 1.2859849805413664e-05, + "loss": 0.271, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09031090140342712, + "step": 890, + "valid_targets_mean": 5882.1, + "valid_targets_min": 624 + }, + { + "epoch": 4.61340206185567, + "grad_norm": 0.22712167753510576, + "learning_rate": 1.262030175123599e-05, + "loss": 0.2638, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09249001741409302, + "step": 895, + "valid_targets_mean": 6656.8, + "valid_targets_min": 877 + }, + { + "epoch": 4.639175257731958, + "grad_norm": 0.2181886728130532, + "learning_rate": 1.2381973051505089e-05, + "loss": 0.2613, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09235621988773346, + "step": 900, + "valid_targets_mean": 6152.6, + "valid_targets_min": 519 + }, + { + "epoch": 4.664948453608248, + "grad_norm": 0.21173138896730861, + "learning_rate": 1.2144903085495021e-05, + "loss": 0.266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09007187932729721, + "step": 905, + "valid_targets_mean": 6109.0, + "valid_targets_min": 571 + }, + { + "epoch": 4.690721649484536, + "grad_norm": 0.21384173047360272, + "learning_rate": 1.190913102449809e-05, + "loss": 0.2693, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09088248014450073, + "step": 910, + "valid_targets_mean": 6272.6, + "valid_targets_min": 516 + }, + { + "epoch": 4.716494845360825, + "grad_norm": 0.2471444990761087, + "learning_rate": 1.1674695825352544e-05, + "loss": 0.267, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08068041503429413, + "step": 915, + "valid_targets_mean": 5634.2, + "valid_targets_min": 537 + }, + { + "epoch": 4.742268041237113, + "grad_norm": 0.20417738889614037, + "learning_rate": 1.1441636224005684e-05, + "loss": 0.2692, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09102384746074677, + "step": 920, + "valid_targets_mean": 5985.6, + "valid_targets_min": 549 + }, + { + "epoch": 4.768041237113402, + "grad_norm": 0.20933575423306253, + "learning_rate": 1.120999072911354e-05, + "loss": 0.2632, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09504446387290955, + "step": 925, + "valid_targets_mean": 6498.6, + "valid_targets_min": 826 + }, + { + "epoch": 4.793814432989691, + "grad_norm": 0.21495610205009033, + "learning_rate": 1.097979761567796e-05, + "loss": 0.2624, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08593370765447617, + "step": 930, + "valid_targets_mean": 6293.3, + "valid_targets_min": 836 + }, + { + "epoch": 4.819587628865979, + "grad_norm": 0.21628152707138062, + "learning_rate": 1.0751094918722487e-05, + "loss": 0.2714, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09788992255926132, + "step": 935, + "valid_targets_mean": 5808.1, + "valid_targets_min": 543 + }, + { + "epoch": 4.845360824742268, + "grad_norm": 0.20876818864253993, + "learning_rate": 1.0523920427007717e-05, + "loss": 0.2641, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10079794377088547, + "step": 940, + "valid_targets_mean": 6872.3, + "valid_targets_min": 844 + }, + { + "epoch": 4.871134020618557, + "grad_norm": 0.21111742947633577, + "learning_rate": 1.0298311676787474e-05, + "loss": 0.2715, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08679303526878357, + "step": 945, + "valid_targets_mean": 5815.4, + "valid_targets_min": 518 + }, + { + "epoch": 4.896907216494846, + "grad_norm": 0.21632908151924193, + "learning_rate": 1.0074305945606684e-05, + "loss": 0.2656, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08715079724788666, + "step": 950, + "valid_targets_mean": 5100.9, + "valid_targets_min": 574 + }, + { + "epoch": 4.922680412371134, + "grad_norm": 0.20770269931366217, + "learning_rate": 9.851940246141888e-06, + "loss": 0.2653, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10157003253698349, + "step": 955, + "valid_targets_mean": 6592.1, + "valid_targets_min": 669 + }, + { + "epoch": 4.948453608247423, + "grad_norm": 0.21189368814109807, + "learning_rate": 9.63125132008569e-06, + "loss": 0.2655, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07998209446668625, + "step": 960, + "valid_targets_mean": 5278.8, + "valid_targets_min": 640 + }, + { + "epoch": 4.974226804123711, + "grad_norm": 0.22322550354193166, + "learning_rate": 9.412275632075827e-06, + "loss": 0.2633, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09199348092079163, + "step": 965, + "valid_targets_mean": 5675.4, + "valid_targets_min": 705 + }, + { + "epoch": 5.0, + "grad_norm": 0.20908447032677452, + "learning_rate": 9.195049363670125e-06, + "loss": 0.266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08515501767396927, + "step": 970, + "valid_targets_mean": 5548.7, + "valid_targets_min": 542 + }, + { + "epoch": 5.025773195876289, + "grad_norm": 0.20769139189806285, + "learning_rate": 8.979608407368182e-06, + "loss": 0.2674, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0799143984913826, + "step": 975, + "valid_targets_mean": 5533.4, + "valid_targets_min": 549 + }, + { + "epoch": 5.051546391752577, + "grad_norm": 0.20853254730464704, + "learning_rate": 8.765988360680772e-06, + "loss": 0.2621, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07116574048995972, + "step": 980, + "valid_targets_mean": 5815.3, + "valid_targets_min": 663 + }, + { + "epoch": 5.077319587628866, + "grad_norm": 0.2121997853645642, + "learning_rate": 8.554224520248115e-06, + "loss": 0.2641, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08537183701992035, + "step": 985, + "valid_targets_mean": 5817.0, + "valid_targets_min": 317 + }, + { + "epoch": 5.103092783505154, + "grad_norm": 0.21085290904277704, + "learning_rate": 8.344351876007686e-06, + "loss": 0.2644, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.097097247838974, + "step": 990, + "valid_targets_mean": 6354.1, + "valid_targets_min": 625 + }, + { + "epoch": 5.128865979381443, + "grad_norm": 0.21286339815700664, + "learning_rate": 8.136405105412897e-06, + "loss": 0.266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07448627799749374, + "step": 995, + "valid_targets_mean": 5040.7, + "valid_targets_min": 710 + }, + { + "epoch": 5.154639175257732, + "grad_norm": 0.21468210382569625, + "learning_rate": 7.930418567703215e-06, + "loss": 0.2541, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0872785896062851, + "step": 1000, + "valid_targets_mean": 6107.7, + "valid_targets_min": 601 + }, + { + "epoch": 5.180412371134021, + "grad_norm": 0.1997157686733035, + "learning_rate": 7.726426298226996e-06, + "loss": 0.2656, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08862429857254028, + "step": 1005, + "valid_targets_mean": 6700.6, + "valid_targets_min": 687 + }, + { + "epoch": 5.206185567010309, + "grad_norm": 0.20206102721595298, + "learning_rate": 7.524462002817809e-06, + "loss": 0.2592, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08948960900306702, + "step": 1010, + "valid_targets_mean": 5725.0, + "valid_targets_min": 574 + }, + { + "epoch": 5.231958762886598, + "grad_norm": 0.2440073772913018, + "learning_rate": 7.324559052225162e-06, + "loss": 0.2559, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09645431488752365, + "step": 1015, + "valid_targets_mean": 6422.7, + "valid_targets_min": 915 + }, + { + "epoch": 5.257731958762887, + "grad_norm": 0.21606760726516505, + "learning_rate": 7.126750476600635e-06, + "loss": 0.2595, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08492911607027054, + "step": 1020, + "valid_targets_mean": 6023.5, + "valid_targets_min": 560 + }, + { + "epoch": 5.283505154639175, + "grad_norm": 0.20849113781355197, + "learning_rate": 6.931068960040248e-06, + "loss": 0.2688, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.1017090231180191, + "step": 1025, + "valid_targets_mean": 6501.2, + "valid_targets_min": 663 + }, + { + "epoch": 5.309278350515464, + "grad_norm": 0.2513768070437953, + "learning_rate": 6.737546835184101e-06, + "loss": 0.2632, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08266648650169373, + "step": 1030, + "valid_targets_mean": 5260.0, + "valid_targets_min": 828 + }, + { + "epoch": 5.335051546391752, + "grad_norm": 0.21151722209757032, + "learning_rate": 6.546216077873941e-06, + "loss": 0.2673, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08756110072135925, + "step": 1035, + "valid_targets_mean": 6145.3, + "valid_targets_min": 657 + }, + { + "epoch": 5.360824742268041, + "grad_norm": 0.22684065543714102, + "learning_rate": 6.3571083018698385e-06, + "loss": 0.2631, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09769861400127411, + "step": 1040, + "valid_targets_mean": 6334.3, + "valid_targets_min": 615 + }, + { + "epoch": 5.38659793814433, + "grad_norm": 0.20785089313976238, + "learning_rate": 6.17025475362657e-06, + "loss": 0.2594, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07463595271110535, + "step": 1045, + "valid_targets_mean": 5333.0, + "valid_targets_min": 345 + }, + { + "epoch": 5.412371134020619, + "grad_norm": 0.2213657046336635, + "learning_rate": 5.985686307130738e-06, + "loss": 0.2646, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09124470502138138, + "step": 1050, + "valid_targets_mean": 5560.1, + "valid_targets_min": 749 + }, + { + "epoch": 5.438144329896907, + "grad_norm": 0.21717198912442856, + "learning_rate": 5.80343345879947e-06, + "loss": 0.2628, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09935463219881058, + "step": 1055, + "valid_targets_mean": 5976.7, + "valid_targets_min": 748 + }, + { + "epoch": 5.463917525773196, + "grad_norm": 0.22034970299362733, + "learning_rate": 5.623526322441417e-06, + "loss": 0.2652, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09560218453407288, + "step": 1060, + "valid_targets_mean": 5304.5, + "valid_targets_min": 568 + }, + { + "epoch": 5.489690721649485, + "grad_norm": 0.21099542255888487, + "learning_rate": 5.445994624281059e-06, + "loss": 0.255, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07948188483715057, + "step": 1065, + "valid_targets_mean": 4990.7, + "valid_targets_min": 613 + }, + { + "epoch": 5.515463917525773, + "grad_norm": 0.24965216915028757, + "learning_rate": 5.270867698047009e-06, + "loss": 0.2588, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09611229598522186, + "step": 1070, + "valid_targets_mean": 6180.8, + "valid_targets_min": 839 + }, + { + "epoch": 5.541237113402062, + "grad_norm": 0.21537926365810592, + "learning_rate": 5.098174480125138e-06, + "loss": 0.266, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07472441345453262, + "step": 1075, + "valid_targets_mean": 5670.4, + "valid_targets_min": 685 + }, + { + "epoch": 5.56701030927835, + "grad_norm": 0.2062264532200198, + "learning_rate": 4.927943504777439e-06, + "loss": 0.2625, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08477666974067688, + "step": 1080, + "valid_targets_mean": 6193.4, + "valid_targets_min": 787 + }, + { + "epoch": 5.592783505154639, + "grad_norm": 0.22807479360755165, + "learning_rate": 4.760202899427251e-06, + "loss": 0.2662, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10754773020744324, + "step": 1085, + "valid_targets_mean": 6542.5, + "valid_targets_min": 716 + }, + { + "epoch": 5.618556701030927, + "grad_norm": 0.25063151638562114, + "learning_rate": 4.594980380011756e-06, + "loss": 0.2648, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08312106132507324, + "step": 1090, + "valid_targets_mean": 5348.1, + "valid_targets_min": 661 + }, + { + "epoch": 5.644329896907217, + "grad_norm": 0.2123995849638101, + "learning_rate": 4.432303246402423e-06, + "loss": 0.2609, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08281916379928589, + "step": 1095, + "valid_targets_mean": 5451.6, + "valid_targets_min": 682 + }, + { + "epoch": 5.670103092783505, + "grad_norm": 0.21442466144358932, + "learning_rate": 4.272198377894266e-06, + "loss": 0.2682, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08195334672927856, + "step": 1100, + "valid_targets_mean": 5530.9, + "valid_targets_min": 432 + }, + { + "epoch": 5.695876288659794, + "grad_norm": 0.2205772428631778, + "learning_rate": 4.114692228764506e-06, + "loss": 0.2615, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08610519766807556, + "step": 1105, + "valid_targets_mean": 5663.6, + "valid_targets_min": 659 + }, + { + "epoch": 5.721649484536083, + "grad_norm": 0.21322779902205768, + "learning_rate": 3.959810823901544e-06, + "loss": 0.2613, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08498895913362503, + "step": 1110, + "valid_targets_mean": 5395.2, + "valid_targets_min": 634 + }, + { + "epoch": 5.747422680412371, + "grad_norm": 0.20512049497797466, + "learning_rate": 3.8075797545048352e-06, + "loss": 0.2606, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10353204607963562, + "step": 1115, + "valid_targets_mean": 6570.0, + "valid_targets_min": 715 + }, + { + "epoch": 5.77319587628866, + "grad_norm": 0.20013648862760422, + "learning_rate": 3.658024173856407e-06, + "loss": 0.2607, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08529584854841232, + "step": 1120, + "valid_targets_mean": 5956.6, + "valid_targets_min": 654 + }, + { + "epoch": 5.798969072164948, + "grad_norm": 0.21094661785666766, + "learning_rate": 3.5111687931647984e-06, + "loss": 0.2605, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08977287262678146, + "step": 1125, + "valid_targets_mean": 6174.0, + "valid_targets_min": 775 + }, + { + "epoch": 5.824742268041237, + "grad_norm": 0.22215911229802232, + "learning_rate": 3.3670378774819602e-06, + "loss": 0.2577, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08660276234149933, + "step": 1130, + "valid_targets_mean": 5474.1, + "valid_targets_min": 804 + }, + { + "epoch": 5.850515463917525, + "grad_norm": 0.2133539586562487, + "learning_rate": 3.225655241693959e-06, + "loss": 0.2595, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0850963145494461, + "step": 1135, + "valid_targets_mean": 5754.8, + "valid_targets_min": 760 + }, + { + "epoch": 5.876288659793815, + "grad_norm": 0.20575597260563536, + "learning_rate": 3.0870442465859995e-06, + "loss": 0.2667, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08850501477718353, + "step": 1140, + "valid_targets_mean": 6029.8, + "valid_targets_min": 566 + }, + { + "epoch": 5.902061855670103, + "grad_norm": 0.2343081260192309, + "learning_rate": 2.9512277949824964e-06, + "loss": 0.2575, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08381161838769913, + "step": 1145, + "valid_targets_mean": 5860.2, + "valid_targets_min": 664 + }, + { + "epoch": 5.927835051546392, + "grad_norm": 0.20310701719507557, + "learning_rate": 2.8182283279628286e-06, + "loss": 0.2589, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0917319804430008, + "step": 1150, + "valid_targets_mean": 5665.4, + "valid_targets_min": 492 + }, + { + "epoch": 5.953608247422681, + "grad_norm": 0.21157422016009103, + "learning_rate": 2.688067821153384e-06, + "loss": 0.2542, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08067169785499573, + "step": 1155, + "valid_targets_mean": 5880.8, + "valid_targets_min": 831 + }, + { + "epoch": 5.979381443298969, + "grad_norm": 0.2526644899017494, + "learning_rate": 2.5607677810964936e-06, + "loss": 0.2565, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.06718919426202774, + "step": 1160, + "valid_targets_mean": 5461.6, + "valid_targets_min": 481 + }, + { + "epoch": 6.005154639175258, + "grad_norm": 0.20806354652395836, + "learning_rate": 2.436349241696885e-06, + "loss": 0.2605, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07857988774776459, + "step": 1165, + "valid_targets_mean": 5099.2, + "valid_targets_min": 536 + }, + { + "epoch": 6.030927835051546, + "grad_norm": 0.19114186705459127, + "learning_rate": 2.314832760746244e-06, + "loss": 0.2577, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07678833603858948, + "step": 1170, + "valid_targets_mean": 5982.6, + "valid_targets_min": 521 + }, + { + "epoch": 6.056701030927835, + "grad_norm": 0.21278822715210383, + "learning_rate": 2.196238416526415e-06, + "loss": 0.2567, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08630746603012085, + "step": 1175, + "valid_targets_mean": 5385.6, + "valid_targets_min": 801 + }, + { + "epoch": 6.082474226804123, + "grad_norm": 0.19982606934036368, + "learning_rate": 2.0805858044918638e-06, + "loss": 0.2603, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07132503390312195, + "step": 1180, + "valid_targets_mean": 5036.2, + "valid_targets_min": 703 + }, + { + "epoch": 6.108247422680412, + "grad_norm": 0.2025276145294527, + "learning_rate": 1.9678940340318984e-06, + "loss": 0.2543, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08077646791934967, + "step": 1185, + "valid_targets_mean": 6119.1, + "valid_targets_min": 593 + }, + { + "epoch": 6.134020618556701, + "grad_norm": 0.2146826565190349, + "learning_rate": 1.8581817253131861e-06, + "loss": 0.2585, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08421634137630463, + "step": 1190, + "valid_targets_mean": 5804.8, + "valid_targets_min": 721 + }, + { + "epoch": 6.15979381443299, + "grad_norm": 0.21850253076866163, + "learning_rate": 1.751467006203158e-06, + "loss": 0.2571, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08505451679229736, + "step": 1195, + "valid_targets_mean": 5829.6, + "valid_targets_min": 438 + }, + { + "epoch": 6.185567010309279, + "grad_norm": 0.3345352586895775, + "learning_rate": 1.6477675092747113e-06, + "loss": 0.256, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08121395111083984, + "step": 1200, + "valid_targets_mean": 5465.2, + "valid_targets_min": 828 + }, + { + "epoch": 6.211340206185567, + "grad_norm": 0.20015585293909394, + "learning_rate": 1.5471003688927423e-06, + "loss": 0.2606, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09846120327711105, + "step": 1205, + "valid_targets_mean": 6461.5, + "valid_targets_min": 714 + }, + { + "epoch": 6.237113402061856, + "grad_norm": 0.22613313561787032, + "learning_rate": 1.4494822183830604e-06, + "loss": 0.2615, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.083452008664608, + "step": 1210, + "valid_targets_mean": 5220.8, + "valid_targets_min": 799 + }, + { + "epoch": 6.262886597938144, + "grad_norm": 0.21798846465090554, + "learning_rate": 1.3549291872840087e-06, + "loss": 0.2617, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08671265840530396, + "step": 1215, + "valid_targets_mean": 5615.6, + "valid_targets_min": 775 + }, + { + "epoch": 6.288659793814433, + "grad_norm": 0.206486585157575, + "learning_rate": 1.2634568986813878e-06, + "loss": 0.2652, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08534083515405655, + "step": 1220, + "valid_targets_mean": 5792.2, + "valid_targets_min": 616 + }, + { + "epoch": 6.314432989690721, + "grad_norm": 0.2625585223869907, + "learning_rate": 1.1750804666270365e-06, + "loss": 0.2576, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10572131723165512, + "step": 1225, + "valid_targets_mean": 6684.8, + "valid_targets_min": 811 + }, + { + "epoch": 6.34020618556701, + "grad_norm": 0.20979953889098482, + "learning_rate": 1.0898144936415168e-06, + "loss": 0.2672, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09444086253643036, + "step": 1230, + "valid_targets_mean": 5211.2, + "valid_targets_min": 562 + }, + { + "epoch": 6.365979381443299, + "grad_norm": 0.2039944878938327, + "learning_rate": 1.007673068301327e-06, + "loss": 0.2564, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08865610510110855, + "step": 1235, + "valid_targets_mean": 6050.2, + "valid_targets_min": 756 + }, + { + "epoch": 6.391752577319588, + "grad_norm": 0.20895313957264638, + "learning_rate": 9.286697629110319e-07, + "loss": 0.2603, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10159533470869064, + "step": 1240, + "valid_targets_mean": 6348.9, + "valid_targets_min": 749 + }, + { + "epoch": 6.417525773195877, + "grad_norm": 0.20966345980821396, + "learning_rate": 8.528176312607072e-07, + "loss": 0.2599, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08785787224769592, + "step": 1245, + "valid_targets_mean": 6008.3, + "valid_targets_min": 701 + }, + { + "epoch": 6.443298969072165, + "grad_norm": 0.20376284624443033, + "learning_rate": 7.80129206469038e-07, + "loss": 0.2599, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07996776700019836, + "step": 1250, + "valid_targets_mean": 5809.2, + "valid_targets_min": 763 + }, + { + "epoch": 6.469072164948454, + "grad_norm": 0.20952438750802332, + "learning_rate": 7.106164989124708e-07, + "loss": 0.2577, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10448366403579712, + "step": 1255, + "valid_targets_mean": 6406.7, + "valid_targets_min": 829 + }, + { + "epoch": 6.494845360824742, + "grad_norm": 0.20402910434899638, + "learning_rate": 6.442909942407105e-07, + "loss": 0.2589, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08333670347929001, + "step": 1260, + "valid_targets_mean": 6146.5, + "valid_targets_min": 721 + }, + { + "epoch": 6.520618556701031, + "grad_norm": 0.2039557306296135, + "learning_rate": 5.811636514789598e-07, + "loss": 0.275, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0835859477519989, + "step": 1265, + "valid_targets_mean": 6323.6, + "valid_targets_min": 732 + }, + { + "epoch": 6.546391752577319, + "grad_norm": 0.20320012215508462, + "learning_rate": 5.212449012171306e-07, + "loss": 0.2588, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09487879276275635, + "step": 1270, + "valid_targets_mean": 6336.9, + "valid_targets_min": 634 + }, + { + "epoch": 6.572164948453608, + "grad_norm": 0.2025812510858642, + "learning_rate": 4.64544643886391e-07, + "loss": 0.2622, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0825139656662941, + "step": 1275, + "valid_targets_mean": 5189.3, + "valid_targets_min": 644 + }, + { + "epoch": 6.597938144329897, + "grad_norm": 0.1982534662923328, + "learning_rate": 4.1107224812331867e-07, + "loss": 0.2633, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08331938087940216, + "step": 1280, + "valid_targets_mean": 5979.3, + "valid_targets_min": 549 + }, + { + "epoch": 6.623711340206185, + "grad_norm": 0.2056936358029195, + "learning_rate": 3.6083654922189237e-07, + "loss": 0.2535, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08464473485946655, + "step": 1285, + "valid_targets_mean": 5499.7, + "valid_targets_min": 594 + }, + { + "epoch": 6.649484536082475, + "grad_norm": 0.19965629057607698, + "learning_rate": 3.1384584767365276e-07, + "loss": 0.2625, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08106464892625809, + "step": 1290, + "valid_targets_mean": 6474.9, + "valid_targets_min": 475 + }, + { + "epoch": 6.675257731958763, + "grad_norm": 0.21892884828822426, + "learning_rate": 2.701079077961821e-07, + "loss": 0.2582, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08687181770801544, + "step": 1295, + "valid_targets_mean": 5231.6, + "valid_targets_min": 666 + }, + { + "epoch": 6.701030927835052, + "grad_norm": 0.20896179005298743, + "learning_rate": 2.2962995645021469e-07, + "loss": 0.263, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08677627146244049, + "step": 1300, + "valid_targets_mean": 5321.3, + "valid_targets_min": 497 + }, + { + "epoch": 6.72680412371134, + "grad_norm": 0.20409776458009016, + "learning_rate": 1.9241868184552537e-07, + "loss": 0.2718, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08831295371055603, + "step": 1305, + "valid_targets_mean": 6504.9, + "valid_targets_min": 820 + }, + { + "epoch": 6.752577319587629, + "grad_norm": 0.20230584513721114, + "learning_rate": 1.5848023243583143e-07, + "loss": 0.261, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09413200616836548, + "step": 1310, + "valid_targets_mean": 6212.2, + "valid_targets_min": 689 + }, + { + "epoch": 6.778350515463917, + "grad_norm": 0.21423837116119837, + "learning_rate": 1.278202159028896e-07, + "loss": 0.2663, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07308657467365265, + "step": 1315, + "valid_targets_mean": 4973.8, + "valid_targets_min": 675 + }, + { + "epoch": 6.804123711340206, + "grad_norm": 0.1912335151833021, + "learning_rate": 1.0044369822991729e-07, + "loss": 0.2565, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.0846131220459938, + "step": 1320, + "valid_targets_mean": 6746.4, + "valid_targets_min": 707 + }, + { + "epoch": 6.829896907216495, + "grad_norm": 0.2214596123527528, + "learning_rate": 7.635520286454868e-08, + "loss": 0.2505, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09434468299150467, + "step": 1325, + "valid_targets_mean": 5639.7, + "valid_targets_min": 661 + }, + { + "epoch": 6.855670103092783, + "grad_norm": 0.20921188363271367, + "learning_rate": 5.555870997140833e-08, + "loss": 0.2571, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.07504785060882568, + "step": 1330, + "valid_targets_mean": 5425.8, + "valid_targets_min": 759 + }, + { + "epoch": 6.881443298969073, + "grad_norm": 0.20876849858807778, + "learning_rate": 3.8057655774479395e-08, + "loss": 0.2577, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09874755144119263, + "step": 1335, + "valid_targets_mean": 6840.6, + "valid_targets_min": 694 + }, + { + "epoch": 6.907216494845361, + "grad_norm": 0.20718159609812295, + "learning_rate": 2.3854931989319986e-08, + "loss": 0.2604, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08516525477170944, + "step": 1340, + "valid_targets_mean": 6252.4, + "valid_targets_min": 804 + }, + { + "epoch": 6.93298969072165, + "grad_norm": 0.2050064910368948, + "learning_rate": 1.295288534527206e-08, + "loss": 0.26, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.09851793199777603, + "step": 1345, + "valid_targets_mean": 6319.2, + "valid_targets_min": 734 + }, + { + "epoch": 6.958762886597938, + "grad_norm": 0.2216176200645684, + "learning_rate": 5.353317197702712e-09, + "loss": 0.2617, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.10352624952793121, + "step": 1350, + "valid_targets_mean": 6360.4, + "valid_targets_min": 669 + }, + { + "epoch": 6.984536082474227, + "grad_norm": 0.20373965786689494, + "learning_rate": 1.0574832303689164e-09, + "loss": 0.2569, + "loss_nan_ranks": 0, + "loss_rank_avg": 0.08267886936664581, + "step": 1355, + "valid_targets_mean": 6156.2, + "valid_targets_min": 664 + }, + { + "epoch": 7.0, + "step": 1358, + "total_flos": 6.436468142603502e+18, + "train_loss": 0.0, + "train_runtime": 0.8245, + "train_samples_per_second": 157900.906, + "train_steps_per_second": 1647.012 + } + ], + "logging_steps": 5, + "max_steps": 1358, + "num_input_tokens_seen": 0, + "num_train_epochs": 7, + "save_steps": 300, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 6.436468142603502e+18, + "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..5b3ac3e --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a158cee6e0821b8b929fcb020fdb37cf5a50d7115926175eaf878b7d444a2f +size 8977 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..85e6aae 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