commit fe673a1dc2efbb0c8f3edcd5c2db3da3fc5e967d Author: ModelHub XC Date: Sat Aug 22 20:13:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-cwm-plus-qwen Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..abe522e --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +library_name: transformers +license: other +base_model: Qwen/Qwen3-4B-Instruct-2507 +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only-opus-distill-32k-multiturn + results: [] +--- + + + +# qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only-opus-distill-32k-multiturn + +This model is a fine-tuned version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on the prm_sft_train dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- total_train_batch_size: 8 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 0.1 +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- Transformers 5.2.0 +- Pytorch 2.9.1+cu128 +- Datasets 4.0.0 +- Tokenizers 0.22.2 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..7e43b83 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 1.329254778357678e+18, + "train_loss": 0.361527387419449, + "train_runtime": 121252.8356, + "train_samples_per_second": 0.16, + "train_steps_per_second": 0.02 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..70adff8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,61 @@ +{%- 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 %} +{%- 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" %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- 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' }} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b1284b3 --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "float32", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "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": 262144, + "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_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.2.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..736d51d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..1f5eee8 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9933bae439396d56aa1c81b04fec36cdeadf0be209a087742ad52792cedab3 +size 17645743048 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..48efd78 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "model_max_length": 1010000, + "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..7e43b83 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 1.329254778357678e+18, + "train_loss": 0.361527387419449, + "train_runtime": 121252.8356, + "train_samples_per_second": 0.16, + "train_steps_per_second": 0.02 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..6b0b181 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,242 @@ +{"current_steps": 10, "total_steps": 2418, "loss": 1.1434167861938476, "lr": 1.8595041322314052e-07, "epoch": 0.01240694789081886, "percentage": 0.41, "elapsed_time": "0:08:30", "remaining_time": "1 day, 10:08:51"} +{"current_steps": 20, "total_steps": 2418, "loss": 1.0735555648803712, "lr": 3.925619834710744e-07, "epoch": 0.02481389578163772, "percentage": 0.83, "elapsed_time": "0:16:44", "remaining_time": "1 day, 9:27:51"} +{"current_steps": 30, "total_steps": 2418, "loss": 0.9607119560241699, "lr": 5.991735537190084e-07, "epoch": 0.03722084367245657, "percentage": 1.24, "elapsed_time": "0:24:53", "remaining_time": "1 day, 9:00:43"} +{"current_steps": 40, "total_steps": 2418, "loss": 0.8850795745849609, "lr": 8.057851239669421e-07, "epoch": 0.04962779156327544, "percentage": 1.65, "elapsed_time": "0:33:16", "remaining_time": "1 day, 8:58:29"} +{"current_steps": 50, "total_steps": 2418, "loss": 0.718876838684082, "lr": 1.012396694214876e-06, "epoch": 0.062034739454094295, "percentage": 2.07, "elapsed_time": "0:41:36", "remaining_time": "1 day, 8:50:14"} +{"current_steps": 60, "total_steps": 2418, "loss": 0.6400353908538818, "lr": 1.21900826446281e-06, "epoch": 0.07444168734491315, "percentage": 2.48, "elapsed_time": "0:49:20", "remaining_time": "1 day, 8:19:17"} +{"current_steps": 70, "total_steps": 2418, "loss": 0.6471079826354981, "lr": 1.425619834710744e-06, "epoch": 0.08684863523573201, "percentage": 2.89, "elapsed_time": "0:57:30", "remaining_time": "1 day, 8:09:11"} +{"current_steps": 80, "total_steps": 2418, "loss": 0.6312197685241699, "lr": 1.632231404958678e-06, "epoch": 0.09925558312655088, "percentage": 3.31, "elapsed_time": "1:05:49", "remaining_time": "1 day, 8:03:46"} +{"current_steps": 90, "total_steps": 2418, "loss": 0.6425768375396729, "lr": 1.8388429752066117e-06, "epoch": 0.11166253101736973, "percentage": 3.72, "elapsed_time": "1:14:10", "remaining_time": "1 day, 7:58:48"} +{"current_steps": 100, "total_steps": 2418, "loss": 0.5865562438964844, "lr": 2.0454545454545457e-06, "epoch": 0.12406947890818859, "percentage": 4.14, "elapsed_time": "1:22:33", "remaining_time": "1 day, 7:53:33"} +{"current_steps": 110, "total_steps": 2418, "loss": 0.5968480110168457, "lr": 2.2520661157024796e-06, "epoch": 0.13647642679900746, "percentage": 4.55, "elapsed_time": "1:30:52", "remaining_time": "1 day, 7:46:42"} +{"current_steps": 120, "total_steps": 2418, "loss": 0.6055496215820313, "lr": 2.4586776859504134e-06, "epoch": 0.1488833746898263, "percentage": 4.96, "elapsed_time": "1:39:07", "remaining_time": "1 day, 7:38:14"} +{"current_steps": 130, "total_steps": 2418, "loss": 0.5692682266235352, "lr": 2.6652892561983473e-06, "epoch": 0.16129032258064516, "percentage": 5.38, "elapsed_time": "1:47:21", "remaining_time": "1 day, 7:29:31"} +{"current_steps": 140, "total_steps": 2418, "loss": 0.5657201290130616, "lr": 2.871900826446281e-06, "epoch": 0.17369727047146402, "percentage": 5.79, "elapsed_time": "1:55:29", "remaining_time": "1 day, 7:19:19"} +{"current_steps": 150, "total_steps": 2418, "loss": 0.5565766334533692, "lr": 3.078512396694215e-06, "epoch": 0.18610421836228289, "percentage": 6.2, "elapsed_time": "2:03:55", "remaining_time": "1 day, 7:13:38"} +{"current_steps": 160, "total_steps": 2418, "loss": 0.5623440742492676, "lr": 3.2851239669421493e-06, "epoch": 0.19851116625310175, "percentage": 6.62, "elapsed_time": "2:12:17", "remaining_time": "1 day, 7:06:51"} +{"current_steps": 170, "total_steps": 2418, "loss": 0.5390286445617676, "lr": 3.491735537190083e-06, "epoch": 0.2109181141439206, "percentage": 7.03, "elapsed_time": "2:20:09", "remaining_time": "1 day, 6:53:26"} +{"current_steps": 180, "total_steps": 2418, "loss": 0.504794979095459, "lr": 3.6983471074380165e-06, "epoch": 0.22332506203473945, "percentage": 7.44, "elapsed_time": "2:28:24", "remaining_time": "1 day, 6:45:11"} +{"current_steps": 190, "total_steps": 2418, "loss": 0.5398801326751709, "lr": 3.904958677685951e-06, "epoch": 0.23573200992555832, "percentage": 7.86, "elapsed_time": "2:36:21", "remaining_time": "1 day, 6:33:28"} +{"current_steps": 200, "total_steps": 2418, "loss": 0.5164627075195313, "lr": 4.111570247933885e-06, "epoch": 0.24813895781637718, "percentage": 8.27, "elapsed_time": "2:44:36", "remaining_time": "1 day, 6:25:31"} +{"current_steps": 210, "total_steps": 2418, "loss": 0.5611258506774902, "lr": 4.3181818181818185e-06, "epoch": 0.26054590570719605, "percentage": 8.68, "elapsed_time": "2:56:25", "remaining_time": "1 day, 6:54:59"} +{"current_steps": 220, "total_steps": 2418, "loss": 0.5151082038879394, "lr": 4.524793388429753e-06, "epoch": 0.2729528535980149, "percentage": 9.1, "elapsed_time": "3:04:13", "remaining_time": "1 day, 6:40:34"} +{"current_steps": 230, "total_steps": 2418, "loss": 0.5357322216033935, "lr": 4.731404958677686e-06, "epoch": 0.2853598014888337, "percentage": 9.51, "elapsed_time": "3:12:33", "remaining_time": "1 day, 6:31:45"} +{"current_steps": 240, "total_steps": 2418, "loss": 0.5303369998931885, "lr": 4.9380165289256205e-06, "epoch": 0.2977667493796526, "percentage": 9.93, "elapsed_time": "3:20:50", "remaining_time": "1 day, 6:22:38"} +{"current_steps": 250, "total_steps": 2418, "loss": 0.49518985748291017, "lr": 4.999872331322402e-06, "epoch": 0.31017369727047145, "percentage": 10.34, "elapsed_time": "3:28:39", "remaining_time": "1 day, 6:09:26"} +{"current_steps": 260, "total_steps": 2418, "loss": 0.505528736114502, "lr": 4.999247046740511e-06, "epoch": 0.3225806451612903, "percentage": 10.75, "elapsed_time": "3:36:15", "remaining_time": "1 day, 5:54:58"} +{"current_steps": 270, "total_steps": 2418, "loss": 0.542401123046875, "lr": 4.998100827074778e-06, "epoch": 0.3349875930521092, "percentage": 11.17, "elapsed_time": "3:43:43", "remaining_time": "1 day, 5:39:51"} +{"current_steps": 280, "total_steps": 2418, "loss": 0.511073637008667, "lr": 4.996433911239573e-06, "epoch": 0.34739454094292804, "percentage": 11.58, "elapsed_time": "3:51:59", "remaining_time": "1 day, 5:31:25"} +{"current_steps": 290, "total_steps": 2418, "loss": 0.5162837982177735, "lr": 4.994246646681518e-06, "epoch": 0.3598014888337469, "percentage": 11.99, "elapsed_time": "4:00:14", "remaining_time": "1 day, 5:22:55"} +{"current_steps": 300, "total_steps": 2418, "loss": 0.4840500831604004, "lr": 4.991539489307062e-06, "epoch": 0.37220843672456577, "percentage": 12.41, "elapsed_time": "4:08:28", "remaining_time": "1 day, 5:14:15"} +{"current_steps": 310, "total_steps": 2418, "loss": 0.48565964698791503, "lr": 4.988313003387454e-06, "epoch": 0.38461538461538464, "percentage": 12.82, "elapsed_time": "4:16:42", "remaining_time": "1 day, 5:05:40"} +{"current_steps": 320, "total_steps": 2418, "loss": 0.5017996788024902, "lr": 4.984567861441129e-06, "epoch": 0.3970223325062035, "percentage": 13.23, "elapsed_time": "4:25:02", "remaining_time": "1 day, 4:57:40"} +{"current_steps": 330, "total_steps": 2418, "loss": 0.4949507713317871, "lr": 4.980304844093531e-06, "epoch": 0.4094292803970223, "percentage": 13.65, "elapsed_time": "4:33:22", "remaining_time": "1 day, 4:49:43"} +{"current_steps": 340, "total_steps": 2418, "loss": 0.4920314311981201, "lr": 4.975524839914399e-06, "epoch": 0.4218362282878412, "percentage": 14.06, "elapsed_time": "4:41:44", "remaining_time": "1 day, 4:41:54"} +{"current_steps": 350, "total_steps": 2418, "loss": 0.4833060264587402, "lr": 4.970228845232561e-06, "epoch": 0.43424317617866004, "percentage": 14.47, "elapsed_time": "4:49:56", "remaining_time": "1 day, 4:33:08"} +{"current_steps": 360, "total_steps": 2418, "loss": 0.4611049652099609, "lr": 4.9644179639282595e-06, "epoch": 0.4466501240694789, "percentage": 14.89, "elapsed_time": "4:58:05", "remaining_time": "1 day, 4:24:05"} +{"current_steps": 370, "total_steps": 2418, "loss": 0.4815668106079102, "lr": 4.958093407203059e-06, "epoch": 0.45905707196029777, "percentage": 15.3, "elapsed_time": "5:06:10", "remaining_time": "1 day, 4:14:44"} +{"current_steps": 380, "total_steps": 2418, "loss": 0.5097352981567382, "lr": 4.951256493327394e-06, "epoch": 0.47146401985111663, "percentage": 15.72, "elapsed_time": "5:14:33", "remaining_time": "1 day, 4:06:58"} +{"current_steps": 390, "total_steps": 2418, "loss": 0.46744871139526367, "lr": 4.943908647365789e-06, "epoch": 0.4838709677419355, "percentage": 16.13, "elapsed_time": "5:22:40", "remaining_time": "1 day, 3:57:57"} +{"current_steps": 400, "total_steps": 2418, "loss": 0.49645652770996096, "lr": 4.936051400879823e-06, "epoch": 0.49627791563275436, "percentage": 16.54, "elapsed_time": "5:31:03", "remaining_time": "1 day, 3:50:09"} +{"current_steps": 410, "total_steps": 2418, "loss": 0.45388307571411135, "lr": 4.9276863916088944e-06, "epoch": 0.5086848635235732, "percentage": 16.96, "elapsed_time": "5:41:40", "remaining_time": "1 day, 3:53:23"} +{"current_steps": 420, "total_steps": 2418, "loss": 0.48491249084472654, "lr": 4.9188153631288584e-06, "epoch": 0.5210918114143921, "percentage": 17.37, "elapsed_time": "5:49:38", "remaining_time": "1 day, 3:43:15"} +{"current_steps": 430, "total_steps": 2418, "loss": 0.48116121292114256, "lr": 4.9094401644886e-06, "epoch": 0.533498759305211, "percentage": 17.78, "elapsed_time": "5:57:57", "remaining_time": "1 day, 3:34:54"} +{"current_steps": 440, "total_steps": 2418, "loss": 0.45473780632019045, "lr": 4.899562749824624e-06, "epoch": 0.5459057071960298, "percentage": 18.2, "elapsed_time": "6:06:17", "remaining_time": "1 day, 3:26:38"} +{"current_steps": 450, "total_steps": 2418, "loss": 0.5124542236328125, "lr": 4.889185177953743e-06, "epoch": 0.5583126550868487, "percentage": 18.61, "elapsed_time": "6:14:27", "remaining_time": "1 day, 3:17:39"} +{"current_steps": 460, "total_steps": 2418, "loss": 0.4542418956756592, "lr": 4.878309611943939e-06, "epoch": 0.5707196029776674, "percentage": 19.02, "elapsed_time": "6:22:43", "remaining_time": "1 day, 3:09:06"} +{"current_steps": 470, "total_steps": 2418, "loss": 0.4757439136505127, "lr": 4.86693831866351e-06, "epoch": 0.5831265508684863, "percentage": 19.44, "elapsed_time": "6:30:40", "remaining_time": "1 day, 2:59:14"} +{"current_steps": 480, "total_steps": 2418, "loss": 0.48748092651367186, "lr": 4.855073668308561e-06, "epoch": 0.5955334987593052, "percentage": 19.85, "elapsed_time": "6:38:53", "remaining_time": "1 day, 2:50:31"} +{"current_steps": 490, "total_steps": 2418, "loss": 0.48392572402954104, "lr": 4.842718133908973e-06, "epoch": 0.607940446650124, "percentage": 20.26, "elapsed_time": "6:47:09", "remaining_time": "1 day, 2:42:03"} +{"current_steps": 500, "total_steps": 2418, "loss": 0.49219765663146975, "lr": 4.829874290812932e-06, "epoch": 0.6203473945409429, "percentage": 20.68, "elapsed_time": "6:55:25", "remaining_time": "1 day, 2:33:32"} +{"current_steps": 510, "total_steps": 2418, "loss": 0.46747660636901855, "lr": 4.816544816150132e-06, "epoch": 0.6327543424317618, "percentage": 21.09, "elapsed_time": "7:03:44", "remaining_time": "1 day, 2:25:18"} +{"current_steps": 520, "total_steps": 2418, "loss": 0.4878196716308594, "lr": 4.802732488273762e-06, "epoch": 0.6451612903225806, "percentage": 21.51, "elapsed_time": "7:11:59", "remaining_time": "1 day, 2:16:45"} +{"current_steps": 530, "total_steps": 2418, "loss": 0.4586039066314697, "lr": 4.788440186181393e-06, "epoch": 0.6575682382133995, "percentage": 21.92, "elapsed_time": "7:20:19", "remaining_time": "1 day, 2:08:34"} +{"current_steps": 540, "total_steps": 2418, "loss": 0.5078807353973389, "lr": 4.773670888914891e-06, "epoch": 0.6699751861042184, "percentage": 22.33, "elapsed_time": "7:28:33", "remaining_time": "1 day, 1:59:59"} +{"current_steps": 550, "total_steps": 2418, "loss": 0.4683982372283936, "lr": 4.75842767493948e-06, "epoch": 0.6823821339950372, "percentage": 22.75, "elapsed_time": "7:36:51", "remaining_time": "1 day, 1:51:39"} +{"current_steps": 560, "total_steps": 2418, "loss": 0.45024881362915037, "lr": 4.742713721502065e-06, "epoch": 0.6947890818858561, "percentage": 23.16, "elapsed_time": "7:44:30", "remaining_time": "1 day, 1:41:08"} +{"current_steps": 570, "total_steps": 2418, "loss": 0.45893230438232424, "lr": 4.726532303968986e-06, "epoch": 0.707196029776675, "percentage": 23.57, "elapsed_time": "7:52:44", "remaining_time": "1 day, 1:32:40"} +{"current_steps": 580, "total_steps": 2418, "loss": 0.4667107582092285, "lr": 4.709886795143307e-06, "epoch": 0.7196029776674938, "percentage": 23.99, "elapsed_time": "8:01:03", "remaining_time": "1 day, 1:24:27"} +{"current_steps": 590, "total_steps": 2418, "loss": 0.43797926902770995, "lr": 4.6927806645618034e-06, "epoch": 0.7320099255583127, "percentage": 24.4, "elapsed_time": "8:09:14", "remaining_time": "1 day, 1:15:50"} +{"current_steps": 600, "total_steps": 2418, "loss": 0.4455252647399902, "lr": 4.675217477771779e-06, "epoch": 0.7444168734491315, "percentage": 24.81, "elapsed_time": "8:17:33", "remaining_time": "1 day, 1:07:34"} +{"current_steps": 610, "total_steps": 2418, "loss": 0.48641119003295896, "lr": 4.657200895587874e-06, "epoch": 0.7568238213399504, "percentage": 25.23, "elapsed_time": "8:28:20", "remaining_time": "1 day, 1:06:42"} +{"current_steps": 620, "total_steps": 2418, "loss": 0.4687007427215576, "lr": 4.638734673329023e-06, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "8:36:30", "remaining_time": "1 day, 0:57:51"} +{"current_steps": 630, "total_steps": 2418, "loss": 0.48453760147094727, "lr": 4.6198226600357e-06, "epoch": 0.7816377171215881, "percentage": 26.05, "elapsed_time": "8:44:47", "remaining_time": "1 day, 0:49:24"} +{"current_steps": 640, "total_steps": 2418, "loss": 0.44130840301513674, "lr": 4.600468797667641e-06, "epoch": 0.794044665012407, "percentage": 26.47, "elapsed_time": "8:53:06", "remaining_time": "1 day, 0:41:02"} +{"current_steps": 650, "total_steps": 2418, "loss": 0.42711877822875977, "lr": 4.580677120282197e-06, "epoch": 0.8064516129032258, "percentage": 26.88, "elapsed_time": "9:01:23", "remaining_time": "1 day, 0:32:35"} +{"current_steps": 660, "total_steps": 2418, "loss": 0.4542987823486328, "lr": 4.56045175319348e-06, "epoch": 0.8188585607940446, "percentage": 27.3, "elapsed_time": "9:09:16", "remaining_time": "1 day, 0:23:03"} +{"current_steps": 670, "total_steps": 2418, "loss": 0.42932806015014646, "lr": 4.539796912112505e-06, "epoch": 0.8312655086848635, "percentage": 27.71, "elapsed_time": "9:17:35", "remaining_time": "1 day, 0:14:43"} +{"current_steps": 680, "total_steps": 2418, "loss": 0.46704769134521484, "lr": 4.518716902268475e-06, "epoch": 0.8436724565756824, "percentage": 28.12, "elapsed_time": "9:25:52", "remaining_time": "1 day, 0:06:18"} +{"current_steps": 690, "total_steps": 2418, "loss": 0.4675713539123535, "lr": 4.497216117511413e-06, "epoch": 0.8560794044665012, "percentage": 28.54, "elapsed_time": "9:34:13", "remaining_time": "23:58:03"} +{"current_steps": 700, "total_steps": 2418, "loss": 0.4250528335571289, "lr": 4.475299039396324e-06, "epoch": 0.8684863523573201, "percentage": 28.95, "elapsed_time": "9:42:29", "remaining_time": "23:49:37"} +{"current_steps": 710, "total_steps": 2418, "loss": 0.4666771411895752, "lr": 4.452970236249071e-06, "epoch": 0.8808933002481389, "percentage": 29.36, "elapsed_time": "9:50:39", "remaining_time": "23:40:53"} +{"current_steps": 720, "total_steps": 2418, "loss": 0.4492027282714844, "lr": 4.4302343622141734e-06, "epoch": 0.8933002481389578, "percentage": 29.78, "elapsed_time": "9:58:58", "remaining_time": "23:32:34"} +{"current_steps": 730, "total_steps": 2418, "loss": 0.428986644744873, "lr": 4.4070961562847044e-06, "epoch": 0.9057071960297767, "percentage": 30.19, "elapsed_time": "10:06:54", "remaining_time": "23:23:22"} +{"current_steps": 740, "total_steps": 2418, "loss": 0.4693061351776123, "lr": 4.3835604413145175e-06, "epoch": 0.9181141439205955, "percentage": 30.6, "elapsed_time": "10:15:15", "remaining_time": "23:15:08"} +{"current_steps": 750, "total_steps": 2418, "loss": 0.46426753997802733, "lr": 4.3596321230129786e-06, "epoch": 0.9305210918114144, "percentage": 31.02, "elapsed_time": "10:23:30", "remaining_time": "23:06:41"} +{"current_steps": 760, "total_steps": 2418, "loss": 0.42464771270751955, "lr": 4.335316188922444e-06, "epoch": 0.9429280397022333, "percentage": 31.43, "elapsed_time": "10:31:27", "remaining_time": "22:57:34"} +{"current_steps": 770, "total_steps": 2418, "loss": 0.4731471061706543, "lr": 4.3106177073786684e-06, "epoch": 0.9553349875930521, "percentage": 31.84, "elapsed_time": "10:39:42", "remaining_time": "22:49:07"} +{"current_steps": 780, "total_steps": 2418, "loss": 0.43342103958129885, "lr": 4.285541826454374e-06, "epoch": 0.967741935483871, "percentage": 32.26, "elapsed_time": "10:47:49", "remaining_time": "22:40:25"} +{"current_steps": 790, "total_steps": 2418, "loss": 0.4437389850616455, "lr": 4.26009377288621e-06, "epoch": 0.9801488833746899, "percentage": 32.67, "elapsed_time": "10:56:04", "remaining_time": "22:32:00"} +{"current_steps": 800, "total_steps": 2418, "loss": 0.4493260860443115, "lr": 4.234278850985305e-06, "epoch": 0.9925558312655087, "percentage": 33.09, "elapsed_time": "11:04:10", "remaining_time": "22:23:17"} +{"current_steps": 810, "total_steps": 2418, "loss": 0.4088118553161621, "lr": 4.208102441531648e-06, "epoch": 1.0049627791563276, "percentage": 33.5, "elapsed_time": "11:14:54", "remaining_time": "22:19:48"} +{"current_steps": 820, "total_steps": 2418, "loss": 0.33449294567108157, "lr": 4.181570000652547e-06, "epoch": 1.0173697270471465, "percentage": 33.91, "elapsed_time": "11:23:02", "remaining_time": "22:11:06"} +{"current_steps": 830, "total_steps": 2418, "loss": 0.3250420093536377, "lr": 4.15468705868536e-06, "epoch": 1.0297766749379653, "percentage": 34.33, "elapsed_time": "11:31:23", "remaining_time": "22:02:48"} +{"current_steps": 840, "total_steps": 2418, "loss": 0.35315914154052735, "lr": 4.127459219024778e-06, "epoch": 1.0421836228287842, "percentage": 34.74, "elapsed_time": "11:39:43", "remaining_time": "21:54:28"} +{"current_steps": 850, "total_steps": 2418, "loss": 0.3586670637130737, "lr": 4.099892156954861e-06, "epoch": 1.054590570719603, "percentage": 35.15, "elapsed_time": "11:47:56", "remaining_time": "21:45:57"} +{"current_steps": 860, "total_steps": 2418, "loss": 0.3647527933120728, "lr": 4.071991618466114e-06, "epoch": 1.066997518610422, "percentage": 35.57, "elapsed_time": "11:56:02", "remaining_time": "21:37:12"} +{"current_steps": 870, "total_steps": 2418, "loss": 0.32327847480773925, "lr": 4.043763419057797e-06, "epoch": 1.0794044665012408, "percentage": 35.98, "elapsed_time": "12:04:16", "remaining_time": "21:28:43"} +{"current_steps": 880, "total_steps": 2418, "loss": 0.35637316703796384, "lr": 4.015213442525771e-06, "epoch": 1.0918114143920596, "percentage": 36.39, "elapsed_time": "12:11:58", "remaining_time": "21:19:18"} +{"current_steps": 890, "total_steps": 2418, "loss": 0.33382978439331057, "lr": 3.986347639736092e-06, "epoch": 1.1042183622828785, "percentage": 36.81, "elapsed_time": "12:20:08", "remaining_time": "21:10:43"} +{"current_steps": 900, "total_steps": 2418, "loss": 0.33941695690155027, "lr": 3.957172027384635e-06, "epoch": 1.1166253101736974, "percentage": 37.22, "elapsed_time": "12:28:25", "remaining_time": "21:02:20"} +{"current_steps": 910, "total_steps": 2418, "loss": 0.3642054319381714, "lr": 3.927692686742993e-06, "epoch": 1.129032258064516, "percentage": 37.63, "elapsed_time": "12:36:44", "remaining_time": "20:54:01"} +{"current_steps": 920, "total_steps": 2418, "loss": 0.3299143314361572, "lr": 3.897915762390912e-06, "epoch": 1.141439205955335, "percentage": 38.05, "elapsed_time": "12:45:02", "remaining_time": "20:45:40"} +{"current_steps": 930, "total_steps": 2418, "loss": 0.34182562828063967, "lr": 3.867847460935542e-06, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "12:53:19", "remaining_time": "20:37:18"} +{"current_steps": 940, "total_steps": 2418, "loss": 0.36127467155456544, "lr": 3.8374940497177435e-06, "epoch": 1.1662531017369726, "percentage": 38.88, "elapsed_time": "13:01:20", "remaining_time": "20:28:31"} +{"current_steps": 950, "total_steps": 2418, "loss": 0.3463557958602905, "lr": 3.806861855505748e-06, "epoch": 1.1786600496277915, "percentage": 39.29, "elapsed_time": "13:09:43", "remaining_time": "20:20:19"} +{"current_steps": 960, "total_steps": 2418, "loss": 0.34737136363983157, "lr": 3.7759572631764243e-06, "epoch": 1.1910669975186103, "percentage": 39.7, "elapsed_time": "13:18:06", "remaining_time": "20:12:07"} +{"current_steps": 970, "total_steps": 2418, "loss": 0.3464951038360596, "lr": 3.7447867143844373e-06, "epoch": 1.2034739454094292, "percentage": 40.12, "elapsed_time": "13:26:18", "remaining_time": "20:03:38"} +{"current_steps": 980, "total_steps": 2418, "loss": 0.3240300178527832, "lr": 3.7133567062195697e-06, "epoch": 1.215880893300248, "percentage": 40.53, "elapsed_time": "13:34:28", "remaining_time": "19:55:06"} +{"current_steps": 990, "total_steps": 2418, "loss": 0.33942902088165283, "lr": 3.6816737898524844e-06, "epoch": 1.228287841191067, "percentage": 40.94, "elapsed_time": "13:42:43", "remaining_time": "19:46:42"} +{"current_steps": 1000, "total_steps": 2418, "loss": 0.3586859226226807, "lr": 3.649744569169229e-06, "epoch": 1.2406947890818858, "percentage": 41.36, "elapsed_time": "13:51:00", "remaining_time": "19:38:22"} +{"current_steps": 1010, "total_steps": 2418, "loss": 0.33882172107696534, "lr": 3.617575699394732e-06, "epoch": 1.2531017369727047, "percentage": 41.77, "elapsed_time": "14:02:04", "remaining_time": "19:33:54"} +{"current_steps": 1020, "total_steps": 2418, "loss": 0.34563610553741453, "lr": 3.5851738857056174e-06, "epoch": 1.2655086848635235, "percentage": 42.18, "elapsed_time": "14:10:20", "remaining_time": "19:25:27"} +{"current_steps": 1030, "total_steps": 2418, "loss": 0.3259500741958618, "lr": 3.552545881832594e-06, "epoch": 1.2779156327543424, "percentage": 42.6, "elapsed_time": "14:18:20", "remaining_time": "19:16:40"} +{"current_steps": 1040, "total_steps": 2418, "loss": 0.35965259075164796, "lr": 3.519698488652734e-06, "epoch": 1.2903225806451613, "percentage": 43.01, "elapsed_time": "14:26:28", "remaining_time": "19:08:04"} +{"current_steps": 1050, "total_steps": 2418, "loss": 0.34020233154296875, "lr": 3.486638552771914e-06, "epoch": 1.3027295285359801, "percentage": 43.42, "elapsed_time": "14:34:44", "remaining_time": "18:59:39"} +{"current_steps": 1060, "total_steps": 2418, "loss": 0.33164680004119873, "lr": 3.4533729650977344e-06, "epoch": 1.315136476426799, "percentage": 43.84, "elapsed_time": "14:42:41", "remaining_time": "18:50:50"} +{"current_steps": 1070, "total_steps": 2418, "loss": 0.3493825435638428, "lr": 3.4199086594031998e-06, "epoch": 1.3275434243176178, "percentage": 44.25, "elapsed_time": "14:50:36", "remaining_time": "18:41:59"} +{"current_steps": 1080, "total_steps": 2418, "loss": 0.3430775165557861, "lr": 3.386252610881465e-06, "epoch": 1.3399503722084367, "percentage": 44.67, "elapsed_time": "14:58:52", "remaining_time": "18:33:36"} +{"current_steps": 1090, "total_steps": 2418, "loss": 0.3269376277923584, "lr": 3.3524118346919486e-06, "epoch": 1.3523573200992556, "percentage": 45.08, "elapsed_time": "15:07:10", "remaining_time": "18:25:15"} +{"current_steps": 1100, "total_steps": 2418, "loss": 0.3524430274963379, "lr": 3.318393384498114e-06, "epoch": 1.3647642679900744, "percentage": 45.49, "elapsed_time": "15:15:19", "remaining_time": "18:16:43"} +{"current_steps": 1110, "total_steps": 2418, "loss": 0.35284743309020994, "lr": 3.2842043509972294e-06, "epoch": 1.3771712158808933, "percentage": 45.91, "elapsed_time": "15:23:39", "remaining_time": "18:08:25"} +{"current_steps": 1120, "total_steps": 2418, "loss": 0.35561535358428953, "lr": 3.2498518604424005e-06, "epoch": 1.3895781637717122, "percentage": 46.32, "elapsed_time": "15:32:02", "remaining_time": "18:00:09"} +{"current_steps": 1130, "total_steps": 2418, "loss": 0.36517820358276365, "lr": 3.215343073157204e-06, "epoch": 1.401985111662531, "percentage": 46.73, "elapsed_time": "15:40:02", "remaining_time": "17:51:29"} +{"current_steps": 1140, "total_steps": 2418, "loss": 0.34882569313049316, "lr": 3.180685182043205e-06, "epoch": 1.41439205955335, "percentage": 47.15, "elapsed_time": "15:48:24", "remaining_time": "17:43:13"} +{"current_steps": 1150, "total_steps": 2418, "loss": 0.344951868057251, "lr": 3.1458854110806976e-06, "epoch": 1.4267990074441688, "percentage": 47.56, "elapsed_time": "15:56:40", "remaining_time": "17:34:49"} +{"current_steps": 1160, "total_steps": 2418, "loss": 0.3353364706039429, "lr": 3.1109510138229565e-06, "epoch": 1.4392059553349876, "percentage": 47.97, "elapsed_time": "16:04:45", "remaining_time": "17:26:15"} +{"current_steps": 1170, "total_steps": 2418, "loss": 0.33848204612731936, "lr": 3.0758892718843352e-06, "epoch": 1.4516129032258065, "percentage": 48.39, "elapsed_time": "16:13:04", "remaining_time": "17:17:56"} +{"current_steps": 1180, "total_steps": 2418, "loss": 0.3388556480407715, "lr": 3.0407074934225038e-06, "epoch": 1.4640198511166254, "percentage": 48.8, "elapsed_time": "16:21:19", "remaining_time": "17:09:33"} +{"current_steps": 1190, "total_steps": 2418, "loss": 0.3524498224258423, "lr": 3.005413011615165e-06, "epoch": 1.4764267990074442, "percentage": 49.21, "elapsed_time": "16:29:30", "remaining_time": "17:01:06"} +{"current_steps": 1200, "total_steps": 2418, "loss": 0.3347229719161987, "lr": 2.9700131831315425e-06, "epoch": 1.488833746898263, "percentage": 49.63, "elapsed_time": "16:37:49", "remaining_time": "16:52:47"} +{"current_steps": 1210, "total_steps": 2418, "loss": 0.321802020072937, "lr": 2.9345153865989918e-06, "epoch": 1.501240694789082, "percentage": 50.04, "elapsed_time": "16:48:37", "remaining_time": "16:46:57"} +{"current_steps": 1220, "total_steps": 2418, "loss": 0.3323647499084473, "lr": 2.898927021065011e-06, "epoch": 1.5136476426799006, "percentage": 50.45, "elapsed_time": "16:56:48", "remaining_time": "16:38:28"} +{"current_steps": 1230, "total_steps": 2418, "loss": 0.3432508945465088, "lr": 2.8632555044550152e-06, "epoch": 1.5260545905707197, "percentage": 50.87, "elapsed_time": "17:05:03", "remaining_time": "16:30:03"} +{"current_steps": 1240, "total_steps": 2418, "loss": 0.3417309522628784, "lr": 2.8275082720261623e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "17:13:18", "remaining_time": "16:21:38"} +{"current_steps": 1250, "total_steps": 2418, "loss": 0.3290053606033325, "lr": 2.791692774817576e-06, "epoch": 1.5508684863523574, "percentage": 51.7, "elapsed_time": "17:21:29", "remaining_time": "16:13:10"} +{"current_steps": 1260, "total_steps": 2418, "loss": 0.33008174896240233, "lr": 2.75581647809727e-06, "epoch": 1.563275434243176, "percentage": 52.11, "elapsed_time": "17:29:45", "remaining_time": "16:04:46"} +{"current_steps": 1270, "total_steps": 2418, "loss": 0.3164780616760254, "lr": 2.7198868598061177e-06, "epoch": 1.5756823821339951, "percentage": 52.52, "elapsed_time": "17:38:05", "remaining_time": "15:56:27"} +{"current_steps": 1280, "total_steps": 2418, "loss": 0.3081036567687988, "lr": 2.683911408999169e-06, "epoch": 1.5880893300248138, "percentage": 52.94, "elapsed_time": "17:46:20", "remaining_time": "15:48:02"} +{"current_steps": 1290, "total_steps": 2418, "loss": 0.35092926025390625, "lr": 2.6478976242846576e-06, "epoch": 1.6004962779156329, "percentage": 53.35, "elapsed_time": "17:54:40", "remaining_time": "15:39:42"} +{"current_steps": 1300, "total_steps": 2418, "loss": 0.37850337028503417, "lr": 2.6118530122610138e-06, "epoch": 1.6129032258064515, "percentage": 53.76, "elapsed_time": "18:03:05", "remaining_time": "15:31:27"} +{"current_steps": 1310, "total_steps": 2418, "loss": 0.35753021240234373, "lr": 2.575785085952216e-06, "epoch": 1.6253101736972706, "percentage": 54.18, "elapsed_time": "18:11:13", "remaining_time": "15:22:57"} +{"current_steps": 1320, "total_steps": 2418, "loss": 0.34999761581420896, "lr": 2.539701363241795e-06, "epoch": 1.6377171215880892, "percentage": 54.59, "elapsed_time": "18:19:03", "remaining_time": "15:14:13"} +{"current_steps": 1330, "total_steps": 2418, "loss": 0.3304608345031738, "lr": 2.503609365305835e-06, "epoch": 1.6501240694789083, "percentage": 55.0, "elapsed_time": "18:27:18", "remaining_time": "15:05:50"} +{"current_steps": 1340, "total_steps": 2418, "loss": 0.3420397281646729, "lr": 2.4675166150452814e-06, "epoch": 1.662531017369727, "percentage": 55.42, "elapsed_time": "18:35:22", "remaining_time": "14:57:17"} +{"current_steps": 1350, "total_steps": 2418, "loss": 0.31749625205993653, "lr": 2.4314306355178924e-06, "epoch": 1.674937965260546, "percentage": 55.83, "elapsed_time": "18:43:45", "remaining_time": "14:49:01"} +{"current_steps": 1360, "total_steps": 2418, "loss": 0.33247082233428954, "lr": 2.3953589483701556e-06, "epoch": 1.6873449131513647, "percentage": 56.24, "elapsed_time": "18:51:32", "remaining_time": "14:40:16"} +{"current_steps": 1370, "total_steps": 2418, "loss": 0.3121840000152588, "lr": 2.3593090722694995e-06, "epoch": 1.6997518610421838, "percentage": 56.66, "elapsed_time": "18:59:50", "remaining_time": "14:31:56"} +{"current_steps": 1380, "total_steps": 2418, "loss": 0.3375117778778076, "lr": 2.3232885213371297e-06, "epoch": 1.7121588089330024, "percentage": 57.07, "elapsed_time": "19:08:06", "remaining_time": "14:23:34"} +{"current_steps": 1390, "total_steps": 2418, "loss": 0.3526495695114136, "lr": 2.2873048035818043e-06, "epoch": 1.7245657568238213, "percentage": 57.49, "elapsed_time": "19:16:26", "remaining_time": "14:15:16"} +{"current_steps": 1400, "total_steps": 2418, "loss": 0.3385695219039917, "lr": 2.251365419334895e-06, "epoch": 1.7369727047146402, "percentage": 57.9, "elapsed_time": "19:24:41", "remaining_time": "14:06:53"} +{"current_steps": 1410, "total_steps": 2418, "loss": 0.3281654119491577, "lr": 2.2154778596870365e-06, "epoch": 1.749379652605459, "percentage": 58.31, "elapsed_time": "19:35:10", "remaining_time": "14:00:07"} +{"current_steps": 1420, "total_steps": 2418, "loss": 0.3286000728607178, "lr": 2.179649604926708e-06, "epoch": 1.7617866004962779, "percentage": 58.73, "elapsed_time": "19:43:29", "remaining_time": "13:51:46"} +{"current_steps": 1430, "total_steps": 2418, "loss": 0.31292095184326174, "lr": 2.14388812298107e-06, "epoch": 1.7741935483870968, "percentage": 59.14, "elapsed_time": "19:51:48", "remaining_time": "13:43:25"} +{"current_steps": 1440, "total_steps": 2418, "loss": 0.32442235946655273, "lr": 2.108200867859369e-06, "epoch": 1.7866004962779156, "percentage": 59.55, "elapsed_time": "19:59:42", "remaining_time": "13:34:48"} +{"current_steps": 1450, "total_steps": 2418, "loss": 0.3294026851654053, "lr": 2.072595278099247e-06, "epoch": 1.7990074441687345, "percentage": 59.97, "elapsed_time": "20:07:57", "remaining_time": "13:26:25"} +{"current_steps": 1460, "total_steps": 2418, "loss": 0.3263838768005371, "lr": 2.037078775216283e-06, "epoch": 1.8114143920595533, "percentage": 60.38, "elapsed_time": "20:16:18", "remaining_time": "13:18:06"} +{"current_steps": 1470, "total_steps": 2418, "loss": 0.33864445686340333, "lr": 2.0016587621570682e-06, "epoch": 1.8238213399503722, "percentage": 60.79, "elapsed_time": "20:24:31", "remaining_time": "13:09:41"} +{"current_steps": 1480, "total_steps": 2418, "loss": 0.31294050216674807, "lr": 1.966342621756163e-06, "epoch": 1.836228287841191, "percentage": 61.21, "elapsed_time": "20:32:27", "remaining_time": "13:01:06"} +{"current_steps": 1490, "total_steps": 2418, "loss": 0.31308484077453613, "lr": 1.931137715197242e-06, "epoch": 1.84863523573201, "percentage": 61.62, "elapsed_time": "20:40:40", "remaining_time": "12:52:42"} +{"current_steps": 1500, "total_steps": 2418, "loss": 0.333689284324646, "lr": 1.8960513804787557e-06, "epoch": 1.8610421836228288, "percentage": 62.03, "elapsed_time": "20:48:27", "remaining_time": "12:44:03"} +{"current_steps": 1510, "total_steps": 2418, "loss": 0.33293652534484863, "lr": 1.861090930884412e-06, "epoch": 1.8734491315136477, "percentage": 62.45, "elapsed_time": "20:56:50", "remaining_time": "12:35:46"} +{"current_steps": 1520, "total_steps": 2418, "loss": 0.3332956790924072, "lr": 1.8262636534588316e-06, "epoch": 1.8858560794044665, "percentage": 62.86, "elapsed_time": "21:05:09", "remaining_time": "12:27:26"} +{"current_steps": 1530, "total_steps": 2418, "loss": 0.32119269371032716, "lr": 1.7915768074886497e-06, "epoch": 1.8982630272952854, "percentage": 63.28, "elapsed_time": "21:13:10", "remaining_time": "12:18:56"} +{"current_steps": 1540, "total_steps": 2418, "loss": 0.32526330947875975, "lr": 1.7570376229894164e-06, "epoch": 1.9106699751861043, "percentage": 63.69, "elapsed_time": "21:21:26", "remaining_time": "12:10:35"} +{"current_steps": 1550, "total_steps": 2418, "loss": 0.3218840599060059, "lr": 1.7226532991985976e-06, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "21:29:33", "remaining_time": "12:02:08"} +{"current_steps": 1560, "total_steps": 2418, "loss": 0.3307999610900879, "lr": 1.688431003074985e-06, "epoch": 1.935483870967742, "percentage": 64.52, "elapsed_time": "21:37:34", "remaining_time": "11:53:39"} +{"current_steps": 1570, "total_steps": 2418, "loss": 0.34044556617736815, "lr": 1.654377867804841e-06, "epoch": 1.9478908188585606, "percentage": 64.93, "elapsed_time": "21:45:49", "remaining_time": "11:45:18"} +{"current_steps": 1580, "total_steps": 2418, "loss": 0.31292636394500734, "lr": 1.6205009913150815e-06, "epoch": 1.9602977667493797, "percentage": 65.34, "elapsed_time": "21:54:10", "remaining_time": "11:37:00"} +{"current_steps": 1590, "total_steps": 2418, "loss": 0.32329092025756834, "lr": 1.5868074347937993e-06, "epoch": 1.9727047146401984, "percentage": 65.76, "elapsed_time": "22:02:17", "remaining_time": "11:28:35"} +{"current_steps": 1600, "total_steps": 2418, "loss": 0.3566758155822754, "lr": 1.553304221218462e-06, "epoch": 1.9851116625310175, "percentage": 66.17, "elapsed_time": "22:10:36", "remaining_time": "11:20:16"} +{"current_steps": 1610, "total_steps": 2418, "loss": 0.3069176197052002, "lr": 1.5199983338920594e-06, "epoch": 1.997518610421836, "percentage": 66.58, "elapsed_time": "22:21:19", "remaining_time": "11:13:09"} +{"current_steps": 1620, "total_steps": 2418, "loss": 0.25013885498046873, "lr": 1.4868967149875257e-06, "epoch": 2.009925558312655, "percentage": 67.0, "elapsed_time": "22:29:36", "remaining_time": "11:04:48"} +{"current_steps": 1630, "total_steps": 2418, "loss": 0.22131125926971434, "lr": 1.4540062641007383e-06, "epoch": 2.022332506203474, "percentage": 67.41, "elapsed_time": "22:37:47", "remaining_time": "10:56:24"} +{"current_steps": 1640, "total_steps": 2418, "loss": 0.2237858295440674, "lr": 1.421333836812387e-06, "epoch": 2.034739454094293, "percentage": 67.82, "elapsed_time": "22:46:01", "remaining_time": "10:48:01"} +{"current_steps": 1650, "total_steps": 2418, "loss": 0.22658278942108154, "lr": 1.3888862432590167e-06, "epoch": 2.0471464019851116, "percentage": 68.24, "elapsed_time": "22:53:49", "remaining_time": "10:39:27"} +{"current_steps": 1660, "total_steps": 2418, "loss": 0.2289585828781128, "lr": 1.3566702467135445e-06, "epoch": 2.0595533498759306, "percentage": 68.65, "elapsed_time": "23:02:08", "remaining_time": "10:31:07"} +{"current_steps": 1670, "total_steps": 2418, "loss": 0.22105908393859863, "lr": 1.3246925621755496e-06, "epoch": 2.0719602977667493, "percentage": 69.07, "elapsed_time": "23:10:02", "remaining_time": "10:22:36"} +{"current_steps": 1680, "total_steps": 2418, "loss": 0.20758159160614015, "lr": 1.2929598549716122e-06, "epoch": 2.0843672456575684, "percentage": 69.48, "elapsed_time": "23:18:23", "remaining_time": "10:14:17"} +{"current_steps": 1690, "total_steps": 2418, "loss": 0.2294921875, "lr": 1.2614787393660215e-06, "epoch": 2.096774193548387, "percentage": 69.89, "elapsed_time": "23:26:37", "remaining_time": "10:05:55"} +{"current_steps": 1700, "total_steps": 2418, "loss": 0.22693567276000975, "lr": 1.2302557771821154e-06, "epoch": 2.109181141439206, "percentage": 70.31, "elapsed_time": "23:34:50", "remaining_time": "9:57:33"} +{"current_steps": 1710, "total_steps": 2418, "loss": 0.23366827964782716, "lr": 1.199297476434553e-06, "epoch": 2.1215880893300247, "percentage": 70.72, "elapsed_time": "23:43:10", "remaining_time": "9:49:14"} +{"current_steps": 1720, "total_steps": 2418, "loss": 0.204612398147583, "lr": 1.168610289972813e-06, "epoch": 2.133995037220844, "percentage": 71.13, "elapsed_time": "23:51:31", "remaining_time": "9:40:55"} +{"current_steps": 1730, "total_steps": 2418, "loss": 0.23412892818450928, "lr": 1.138200614136172e-06, "epoch": 2.1464019851116625, "percentage": 71.55, "elapsed_time": "23:59:44", "remaining_time": "9:32:33"} +{"current_steps": 1740, "total_steps": 2418, "loss": 0.23051118850708008, "lr": 1.1080747874204809e-06, "epoch": 2.1588089330024816, "percentage": 71.96, "elapsed_time": "1 day, 0:07:23", "remaining_time": "9:23:58"} +{"current_steps": 1750, "total_steps": 2418, "loss": 0.223101806640625, "lr": 1.0782390891569822e-06, "epoch": 2.1712158808933, "percentage": 72.37, "elapsed_time": "1 day, 0:15:38", "remaining_time": "9:15:38"} +{"current_steps": 1760, "total_steps": 2418, "loss": 0.21067981719970702, "lr": 1.0486997382034695e-06, "epoch": 2.1836228287841193, "percentage": 72.79, "elapsed_time": "1 day, 0:23:42", "remaining_time": "9:07:13"} +{"current_steps": 1770, "total_steps": 2418, "loss": 0.21455581188201905, "lr": 1.0194628916480504e-06, "epoch": 2.196029776674938, "percentage": 73.2, "elapsed_time": "1 day, 0:32:00", "remaining_time": "8:58:54"} +{"current_steps": 1780, "total_steps": 2418, "loss": 0.25631544589996336, "lr": 9.905346435257784e-07, "epoch": 2.208436724565757, "percentage": 73.61, "elapsed_time": "1 day, 0:40:03", "remaining_time": "8:50:29"} +{"current_steps": 1790, "total_steps": 2418, "loss": 0.2324852466583252, "lr": 9.619210235484333e-07, "epoch": 2.2208436724565757, "percentage": 74.03, "elapsed_time": "1 day, 0:48:08", "remaining_time": "8:42:05"} +{"current_steps": 1800, "total_steps": 2418, "loss": 0.2013075351715088, "lr": 9.336279958477096e-07, "epoch": 2.2332506203473947, "percentage": 74.44, "elapsed_time": "1 day, 0:56:24", "remaining_time": "8:33:45"} +{"current_steps": 1810, "total_steps": 2418, "loss": 0.23809702396392823, "lr": 9.056614577320702e-07, "epoch": 2.2456575682382134, "percentage": 74.86, "elapsed_time": "1 day, 1:07:19", "remaining_time": "8:26:19"} +{"current_steps": 1820, "total_steps": 2418, "loss": 0.22165682315826415, "lr": 8.780272384575289e-07, "epoch": 2.258064516129032, "percentage": 75.27, "elapsed_time": "1 day, 1:15:27", "remaining_time": "8:17:56"} +{"current_steps": 1830, "total_steps": 2418, "loss": 0.21906075477600098, "lr": 8.507310980126188e-07, "epoch": 2.270471464019851, "percentage": 75.68, "elapsed_time": "1 day, 1:23:29", "remaining_time": "8:09:31"} +{"current_steps": 1840, "total_steps": 2418, "loss": 0.21673779487609862, "lr": 8.237787259178037e-07, "epoch": 2.28287841191067, "percentage": 76.1, "elapsed_time": "1 day, 1:31:29", "remaining_time": "8:01:05"} +{"current_steps": 1850, "total_steps": 2418, "loss": 0.23625686168670654, "lr": 7.971757400395652e-07, "epoch": 2.295285359801489, "percentage": 76.51, "elapsed_time": "1 day, 1:39:42", "remaining_time": "7:52:43"} +{"current_steps": 1860, "total_steps": 2418, "loss": 0.21259665489196777, "lr": 7.709276854194392e-07, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "1 day, 1:47:57", "remaining_time": "7:44:23"} +{"current_steps": 1870, "total_steps": 2418, "loss": 0.23154499530792236, "lr": 7.450400331182198e-07, "epoch": 2.3200992555831266, "percentage": 77.34, "elapsed_time": "1 day, 1:56:21", "remaining_time": "7:36:05"} +{"current_steps": 1880, "total_steps": 2418, "loss": 0.2277855396270752, "lr": 7.19518179075591e-07, "epoch": 2.332506203473945, "percentage": 77.75, "elapsed_time": "1 day, 2:04:38", "remaining_time": "7:27:45"} +{"current_steps": 1890, "total_steps": 2418, "loss": 0.22485933303833008, "lr": 6.943674429854172e-07, "epoch": 2.3449131513647643, "percentage": 78.16, "elapsed_time": "1 day, 2:12:56", "remaining_time": "7:19:25"} +{"current_steps": 1900, "total_steps": 2418, "loss": 0.23359484672546388, "lr": 6.695930671869175e-07, "epoch": 2.357320099255583, "percentage": 78.58, "elapsed_time": "1 day, 2:21:12", "remaining_time": "7:11:05"} +{"current_steps": 1910, "total_steps": 2418, "loss": 0.19909019470214845, "lr": 6.452002155719725e-07, "epoch": 2.369727047146402, "percentage": 78.99, "elapsed_time": "1 day, 2:29:22", "remaining_time": "7:02:43"} +{"current_steps": 1920, "total_steps": 2418, "loss": 0.23796792030334474, "lr": 6.211939725087806e-07, "epoch": 2.3821339950372207, "percentage": 79.4, "elapsed_time": "1 day, 2:37:34", "remaining_time": "6:54:22"} +{"current_steps": 1930, "total_steps": 2418, "loss": 0.22071402072906493, "lr": 5.975793417820841e-07, "epoch": 2.3945409429280398, "percentage": 79.82, "elapsed_time": "1 day, 2:45:54", "remaining_time": "6:46:03"} +{"current_steps": 1940, "total_steps": 2418, "loss": 0.22007994651794432, "lr": 5.743612455502016e-07, "epoch": 2.4069478908188584, "percentage": 80.23, "elapsed_time": "1 day, 2:54:11", "remaining_time": "6:37:43"} +{"current_steps": 1950, "total_steps": 2418, "loss": 0.21707756519317628, "lr": 5.515445233190636e-07, "epoch": 2.4193548387096775, "percentage": 80.65, "elapsed_time": "1 day, 3:02:26", "remaining_time": "6:29:23"} +{"current_steps": 1960, "total_steps": 2418, "loss": 0.2090601682662964, "lr": 5.291339309334845e-07, "epoch": 2.431761786600496, "percentage": 81.06, "elapsed_time": "1 day, 3:10:47", "remaining_time": "6:21:04"} +{"current_steps": 1970, "total_steps": 2418, "loss": 0.2203066825866699, "lr": 5.071341395858703e-07, "epoch": 2.444168734491315, "percentage": 81.47, "elapsed_time": "1 day, 3:19:05", "remaining_time": "6:12:44"} +{"current_steps": 1980, "total_steps": 2418, "loss": 0.22847747802734375, "lr": 4.855497348425686e-07, "epoch": 2.456575682382134, "percentage": 81.89, "elapsed_time": "1 day, 3:26:51", "remaining_time": "6:04:18"} +{"current_steps": 1990, "total_steps": 2418, "loss": 0.20745439529418946, "lr": 4.6438521568806625e-07, "epoch": 2.468982630272953, "percentage": 82.3, "elapsed_time": "1 day, 3:35:01", "remaining_time": "5:55:57"} +{"current_steps": 2000, "total_steps": 2418, "loss": 0.23231451511383056, "lr": 4.436449935872378e-07, "epoch": 2.4813895781637716, "percentage": 82.71, "elapsed_time": "1 day, 3:43:17", "remaining_time": "5:47:37"} +{"current_steps": 2010, "total_steps": 2418, "loss": 0.2055814266204834, "lr": 4.2333339156583467e-07, "epoch": 2.4937965260545907, "percentage": 83.13, "elapsed_time": "1 day, 3:53:56", "remaining_time": "5:39:47"} +{"current_steps": 2020, "total_steps": 2418, "loss": 0.22689828872680665, "lr": 4.034546433094036e-07, "epoch": 2.5062034739454093, "percentage": 83.54, "elapsed_time": "1 day, 4:01:54", "remaining_time": "5:31:23"} +{"current_steps": 2030, "total_steps": 2418, "loss": 0.23529858589172364, "lr": 3.8401289228083395e-07, "epoch": 2.5186104218362284, "percentage": 83.95, "elapsed_time": "1 day, 4:10:03", "remaining_time": "5:23:01"} +{"current_steps": 2040, "total_steps": 2418, "loss": 0.2225353479385376, "lr": 3.6501219085670724e-07, "epoch": 2.531017369727047, "percentage": 84.37, "elapsed_time": "1 day, 4:18:18", "remaining_time": "5:14:41"} +{"current_steps": 2050, "total_steps": 2418, "loss": 0.2311680793762207, "lr": 3.4645649948263085e-07, "epoch": 2.543424317617866, "percentage": 84.78, "elapsed_time": "1 day, 4:26:30", "remaining_time": "5:06:20"} +{"current_steps": 2060, "total_steps": 2418, "loss": 0.21333532333374022, "lr": 3.2834968584773754e-07, "epoch": 2.555831265508685, "percentage": 85.19, "elapsed_time": "1 day, 4:34:49", "remaining_time": "4:58:00"} +{"current_steps": 2070, "total_steps": 2418, "loss": 0.2413243293762207, "lr": 3.106955240785153e-07, "epoch": 2.568238213399504, "percentage": 85.61, "elapsed_time": "1 day, 4:43:08", "remaining_time": "4:49:41"} +{"current_steps": 2080, "total_steps": 2418, "loss": 0.21133730411529542, "lr": 2.9349769395214e-07, "epoch": 2.5806451612903225, "percentage": 86.02, "elapsed_time": "1 day, 4:51:29", "remaining_time": "4:41:22"} +{"current_steps": 2090, "total_steps": 2418, "loss": 0.21675755977630615, "lr": 2.767597801294772e-07, "epoch": 2.5930521091811416, "percentage": 86.44, "elapsed_time": "1 day, 4:59:49", "remaining_time": "4:33:02"} +{"current_steps": 2100, "total_steps": 2418, "loss": 0.22542505264282225, "lr": 2.604852714079023e-07, "epoch": 2.6054590570719602, "percentage": 86.85, "elapsed_time": "1 day, 5:08:08", "remaining_time": "4:24:43"} +{"current_steps": 2110, "total_steps": 2418, "loss": 0.23392457962036134, "lr": 2.4467755999411204e-07, "epoch": 2.617866004962779, "percentage": 87.26, "elapsed_time": "1 day, 5:15:40", "remaining_time": "4:16:16"} +{"current_steps": 2120, "total_steps": 2418, "loss": 0.19952282905578614, "lr": 2.2933994079705896e-07, "epoch": 2.630272952853598, "percentage": 87.68, "elapsed_time": "1 day, 5:24:00", "remaining_time": "4:07:57"} +{"current_steps": 2130, "total_steps": 2418, "loss": 0.2230466365814209, "lr": 2.144756107411733e-07, "epoch": 2.642679900744417, "percentage": 88.09, "elapsed_time": "1 day, 5:32:12", "remaining_time": "3:59:37"} +{"current_steps": 2140, "total_steps": 2418, "loss": 0.23057200908660888, "lr": 2.0008766810000801e-07, "epoch": 2.6550868486352357, "percentage": 88.5, "elapsed_time": "1 day, 5:40:24", "remaining_time": "3:51:17"} +{"current_steps": 2150, "total_steps": 2418, "loss": 0.2180851459503174, "lr": 1.861791118504408e-07, "epoch": 2.6674937965260543, "percentage": 88.92, "elapsed_time": "1 day, 5:48:39", "remaining_time": "3:42:57"} +{"current_steps": 2160, "total_steps": 2418, "loss": 0.2167917251586914, "lr": 1.7275284104757844e-07, "epoch": 2.6799007444168734, "percentage": 89.33, "elapsed_time": "1 day, 5:57:01", "remaining_time": "3:34:38"} +{"current_steps": 2170, "total_steps": 2418, "loss": 0.22899148464202881, "lr": 1.598116542204889e-07, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "1 day, 6:05:21", "remaining_time": "3:26:19"} +{"current_steps": 2180, "total_steps": 2418, "loss": 0.2170346736907959, "lr": 1.4735824878888277e-07, "epoch": 2.704714640198511, "percentage": 90.16, "elapsed_time": "1 day, 6:13:35", "remaining_time": "3:17:59"} +{"current_steps": 2190, "total_steps": 2418, "loss": 0.2242295265197754, "lr": 1.353952205008713e-07, "epoch": 2.71712158808933, "percentage": 90.57, "elapsed_time": "1 day, 6:21:57", "remaining_time": "3:09:40"} +{"current_steps": 2200, "total_steps": 2418, "loss": 0.2131351947784424, "lr": 1.2392506289191837e-07, "epoch": 2.729528535980149, "percentage": 90.98, "elapsed_time": "1 day, 6:30:10", "remaining_time": "3:01:21"} +{"current_steps": 2210, "total_steps": 2418, "loss": 0.21861982345581055, "lr": 1.1295016676509618e-07, "epoch": 2.741935483870968, "percentage": 91.4, "elapsed_time": "1 day, 6:42:17", "remaining_time": "2:53:23"} +{"current_steps": 2220, "total_steps": 2418, "loss": 0.1985526442527771, "lr": 1.0247281969275131e-07, "epoch": 2.7543424317617866, "percentage": 91.81, "elapsed_time": "1 day, 6:50:36", "remaining_time": "2:45:03"} +{"current_steps": 2230, "total_steps": 2418, "loss": 0.23580389022827147, "lr": 9.249520553969465e-08, "epoch": 2.7667493796526053, "percentage": 92.22, "elapsed_time": "1 day, 6:58:47", "remaining_time": "2:36:42"} +{"current_steps": 2240, "total_steps": 2418, "loss": 0.21973462104797364, "lr": 8.301940400799818e-08, "epoch": 2.7791563275434243, "percentage": 92.64, "elapsed_time": "1 day, 7:07:08", "remaining_time": "2:28:22"} +{"current_steps": 2250, "total_steps": 2418, "loss": 0.22958881855010987, "lr": 7.404739020351381e-08, "epoch": 2.7915632754342434, "percentage": 93.05, "elapsed_time": "1 day, 7:15:24", "remaining_time": "2:20:01"} +{"current_steps": 2260, "total_steps": 2418, "loss": 0.23037824630737305, "lr": 6.558103422418555e-08, "epoch": 2.803970223325062, "percentage": 93.47, "elapsed_time": "1 day, 7:23:36", "remaining_time": "2:11:41"} +{"current_steps": 2270, "total_steps": 2418, "loss": 0.2314563512802124, "lr": 5.762210077025293e-08, "epoch": 2.8163771712158807, "percentage": 93.88, "elapsed_time": "1 day, 7:31:52", "remaining_time": "2:03:20"} +{"current_steps": 2280, "total_steps": 2418, "loss": 0.21394333839416504, "lr": 5.017224877642196e-08, "epoch": 2.8287841191067, "percentage": 94.29, "elapsed_time": "1 day, 7:40:11", "remaining_time": "1:55:00"} +{"current_steps": 2290, "total_steps": 2418, "loss": 0.22109608650207518, "lr": 4.323303106608362e-08, "epoch": 2.8411910669975184, "percentage": 94.71, "elapsed_time": "1 day, 7:48:09", "remaining_time": "1:46:39"} +{"current_steps": 2300, "total_steps": 2418, "loss": 0.21065773963928222, "lr": 3.680589402764695e-08, "epoch": 2.8535980148883375, "percentage": 95.12, "elapsed_time": "1 day, 7:55:56", "remaining_time": "1:38:17"} +{"current_steps": 2310, "total_steps": 2418, "loss": 0.21384596824645996, "lr": 3.089217731305882e-08, "epoch": 2.866004962779156, "percentage": 95.53, "elapsed_time": "1 day, 8:04:01", "remaining_time": "1:29:57"} +{"current_steps": 2320, "total_steps": 2418, "loss": 0.2103095531463623, "lr": 2.5493113558571203e-08, "epoch": 2.8784119106699753, "percentage": 95.95, "elapsed_time": "1 day, 8:11:58", "remaining_time": "1:21:36"} +{"current_steps": 2330, "total_steps": 2418, "loss": 0.22623074054718018, "lr": 2.0609828127814425e-08, "epoch": 2.890818858560794, "percentage": 96.36, "elapsed_time": "1 day, 8:20:16", "remaining_time": "1:13:16"} +{"current_steps": 2340, "total_steps": 2418, "loss": 0.2561406373977661, "lr": 1.624333887723012e-08, "epoch": 2.903225806451613, "percentage": 96.77, "elapsed_time": "1 day, 8:28:26", "remaining_time": "1:04:56"} +{"current_steps": 2350, "total_steps": 2418, "loss": 0.22645580768585205, "lr": 1.2394555943911757e-08, "epoch": 2.9156327543424316, "percentage": 97.19, "elapsed_time": "1 day, 8:36:45", "remaining_time": "0:56:37"} +{"current_steps": 2360, "total_steps": 2418, "loss": 0.21149790287017822, "lr": 9.0642815559e-09, "epoch": 2.9280397022332507, "percentage": 97.6, "elapsed_time": "1 day, 8:44:55", "remaining_time": "0:48:17"} +{"current_steps": 2370, "total_steps": 2418, "loss": 0.2031836986541748, "lr": 6.253209864966747e-09, "epoch": 2.9404466501240694, "percentage": 98.01, "elapsed_time": "1 day, 8:52:38", "remaining_time": "0:39:57"} +{"current_steps": 2380, "total_steps": 2418, "loss": 0.2176318883895874, "lr": 3.9619268019305825e-09, "epoch": 2.9528535980148884, "percentage": 98.43, "elapsed_time": "1 day, 9:00:57", "remaining_time": "0:31:37"} +{"current_steps": 2390, "total_steps": 2418, "loss": 0.2153688907623291, "lr": 2.190909954525866e-09, "epoch": 2.965260545905707, "percentage": 98.84, "elapsed_time": "1 day, 9:09:04", "remaining_time": "0:23:18"} +{"current_steps": 2400, "total_steps": 2418, "loss": 0.21965882778167725, "lr": 9.405284678556948e-10, "epoch": 2.977667493796526, "percentage": 99.26, "elapsed_time": "1 day, 9:17:25", "remaining_time": "0:14:58"} +{"current_steps": 2410, "total_steps": 2418, "loss": 0.2195052146911621, "lr": 2.1104296745011466e-10, "epoch": 2.990074441687345, "percentage": 99.67, "elapsed_time": "1 day, 9:30:46", "remaining_time": "0:06:40"} +{"current_steps": 2418, "total_steps": 2418, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1 day, 9:40:52", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..77772f5 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1730 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 2418, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01240694789081886, + "grad_norm": 24.380937576293945, + "learning_rate": 1.8595041322314052e-07, + "loss": 1.1434167861938476, + "step": 10 + }, + { + "epoch": 0.02481389578163772, + "grad_norm": 21.075366973876953, + "learning_rate": 3.925619834710744e-07, + "loss": 1.0735555648803712, + "step": 20 + }, + { + "epoch": 0.03722084367245657, + "grad_norm": 16.02638053894043, + "learning_rate": 5.991735537190084e-07, + "loss": 0.9607119560241699, + "step": 30 + }, + { + "epoch": 0.04962779156327544, + "grad_norm": 10.198869705200195, + "learning_rate": 8.057851239669421e-07, + "loss": 0.8850795745849609, + "step": 40 + }, + { + "epoch": 0.062034739454094295, + "grad_norm": 3.556870222091675, + "learning_rate": 1.012396694214876e-06, + "loss": 0.718876838684082, + "step": 50 + }, + { + "epoch": 0.07444168734491315, + "grad_norm": 4.056130886077881, + "learning_rate": 1.21900826446281e-06, + "loss": 0.6400353908538818, + "step": 60 + }, + { + "epoch": 0.08684863523573201, + "grad_norm": 3.1343917846679688, + "learning_rate": 1.425619834710744e-06, + "loss": 0.6471079826354981, + "step": 70 + }, + { + "epoch": 0.09925558312655088, + "grad_norm": 3.1576831340789795, + "learning_rate": 1.632231404958678e-06, + "loss": 0.6312197685241699, + "step": 80 + }, + { + "epoch": 0.11166253101736973, + "grad_norm": 3.7458317279815674, + "learning_rate": 1.8388429752066117e-06, + "loss": 0.6425768375396729, + "step": 90 + }, + { + "epoch": 0.12406947890818859, + "grad_norm": 3.5856683254241943, + "learning_rate": 2.0454545454545457e-06, + "loss": 0.5865562438964844, + "step": 100 + }, + { + "epoch": 0.13647642679900746, + "grad_norm": 3.186936616897583, + "learning_rate": 2.2520661157024796e-06, + "loss": 0.5968480110168457, + "step": 110 + }, + { + "epoch": 0.1488833746898263, + "grad_norm": 2.963216781616211, + "learning_rate": 2.4586776859504134e-06, + "loss": 0.6055496215820313, + "step": 120 + }, + { + "epoch": 0.16129032258064516, + "grad_norm": 3.0101115703582764, + "learning_rate": 2.6652892561983473e-06, + "loss": 0.5692682266235352, + "step": 130 + }, + { + "epoch": 0.17369727047146402, + "grad_norm": 2.968893527984619, + "learning_rate": 2.871900826446281e-06, + "loss": 0.5657201290130616, + "step": 140 + }, + { + "epoch": 0.18610421836228289, + "grad_norm": 3.103032112121582, + "learning_rate": 3.078512396694215e-06, + "loss": 0.5565766334533692, + "step": 150 + }, + { + "epoch": 0.19851116625310175, + "grad_norm": 3.6906442642211914, + "learning_rate": 3.2851239669421493e-06, + "loss": 0.5623440742492676, + "step": 160 + }, + { + "epoch": 0.2109181141439206, + "grad_norm": 3.6191394329071045, + "learning_rate": 3.491735537190083e-06, + "loss": 0.5390286445617676, + "step": 170 + }, + { + "epoch": 0.22332506203473945, + "grad_norm": 3.119192600250244, + "learning_rate": 3.6983471074380165e-06, + "loss": 0.504794979095459, + "step": 180 + }, + { + "epoch": 0.23573200992555832, + "grad_norm": 3.5379598140716553, + "learning_rate": 3.904958677685951e-06, + "loss": 0.5398801326751709, + "step": 190 + }, + { + "epoch": 0.24813895781637718, + "grad_norm": 3.455927848815918, + "learning_rate": 4.111570247933885e-06, + "loss": 0.5164627075195313, + "step": 200 + }, + { + "epoch": 0.26054590570719605, + "grad_norm": 3.3440027236938477, + "learning_rate": 4.3181818181818185e-06, + "loss": 0.5611258506774902, + "step": 210 + }, + { + "epoch": 0.2729528535980149, + "grad_norm": 3.941814661026001, + "learning_rate": 4.524793388429753e-06, + "loss": 0.5151082038879394, + "step": 220 + }, + { + "epoch": 0.2853598014888337, + "grad_norm": 3.3939054012298584, + "learning_rate": 4.731404958677686e-06, + "loss": 0.5357322216033935, + "step": 230 + }, + { + "epoch": 0.2977667493796526, + "grad_norm": 3.399260997772217, + "learning_rate": 4.9380165289256205e-06, + "loss": 0.5303369998931885, + "step": 240 + }, + { + "epoch": 0.31017369727047145, + "grad_norm": 3.109227180480957, + "learning_rate": 4.999872331322402e-06, + "loss": 0.49518985748291017, + "step": 250 + }, + { + "epoch": 0.3225806451612903, + "grad_norm": 3.147308588027954, + "learning_rate": 4.999247046740511e-06, + "loss": 0.505528736114502, + "step": 260 + }, + { + "epoch": 0.3349875930521092, + "grad_norm": 2.949301242828369, + "learning_rate": 4.998100827074778e-06, + "loss": 0.542401123046875, + "step": 270 + }, + { + "epoch": 0.34739454094292804, + "grad_norm": 3.650075912475586, + "learning_rate": 4.996433911239573e-06, + "loss": 0.511073637008667, + "step": 280 + }, + { + "epoch": 0.3598014888337469, + "grad_norm": 3.273531675338745, + "learning_rate": 4.994246646681518e-06, + "loss": 0.5162837982177735, + "step": 290 + }, + { + "epoch": 0.37220843672456577, + "grad_norm": 3.32936954498291, + "learning_rate": 4.991539489307062e-06, + "loss": 0.4840500831604004, + "step": 300 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 2.9847359657287598, + "learning_rate": 4.988313003387454e-06, + "loss": 0.48565964698791503, + "step": 310 + }, + { + "epoch": 0.3970223325062035, + "grad_norm": 3.2663910388946533, + "learning_rate": 4.984567861441129e-06, + "loss": 0.5017996788024902, + "step": 320 + }, + { + "epoch": 0.4094292803970223, + "grad_norm": 2.7149908542633057, + "learning_rate": 4.980304844093531e-06, + "loss": 0.4949507713317871, + "step": 330 + }, + { + "epoch": 0.4218362282878412, + "grad_norm": 3.2583069801330566, + "learning_rate": 4.975524839914399e-06, + "loss": 0.4920314311981201, + "step": 340 + }, + { + "epoch": 0.43424317617866004, + "grad_norm": 3.2360751628875732, + "learning_rate": 4.970228845232561e-06, + "loss": 0.4833060264587402, + "step": 350 + }, + { + "epoch": 0.4466501240694789, + "grad_norm": 3.0809836387634277, + "learning_rate": 4.9644179639282595e-06, + "loss": 0.4611049652099609, + "step": 360 + }, + { + "epoch": 0.45905707196029777, + "grad_norm": 2.903007984161377, + "learning_rate": 4.958093407203059e-06, + "loss": 0.4815668106079102, + "step": 370 + }, + { + "epoch": 0.47146401985111663, + "grad_norm": 3.1230084896087646, + "learning_rate": 4.951256493327394e-06, + "loss": 0.5097352981567382, + "step": 380 + }, + { + "epoch": 0.4838709677419355, + "grad_norm": 3.1644937992095947, + "learning_rate": 4.943908647365789e-06, + "loss": 0.46744871139526367, + "step": 390 + }, + { + "epoch": 0.49627791563275436, + "grad_norm": 3.0167317390441895, + "learning_rate": 4.936051400879823e-06, + "loss": 0.49645652770996096, + "step": 400 + }, + { + "epoch": 0.5086848635235732, + "grad_norm": 3.1851320266723633, + "learning_rate": 4.9276863916088944e-06, + "loss": 0.45388307571411135, + "step": 410 + }, + { + "epoch": 0.5210918114143921, + "grad_norm": 3.688347578048706, + "learning_rate": 4.9188153631288584e-06, + "loss": 0.48491249084472654, + "step": 420 + }, + { + "epoch": 0.533498759305211, + "grad_norm": 2.895963668823242, + "learning_rate": 4.9094401644886e-06, + "loss": 0.48116121292114256, + "step": 430 + }, + { + "epoch": 0.5459057071960298, + "grad_norm": 2.6067240238189697, + "learning_rate": 4.899562749824624e-06, + "loss": 0.45473780632019045, + "step": 440 + }, + { + "epoch": 0.5583126550868487, + "grad_norm": 2.9146952629089355, + "learning_rate": 4.889185177953743e-06, + "loss": 0.5124542236328125, + "step": 450 + }, + { + "epoch": 0.5707196029776674, + "grad_norm": 3.009894847869873, + "learning_rate": 4.878309611943939e-06, + "loss": 0.4542418956756592, + "step": 460 + }, + { + "epoch": 0.5831265508684863, + "grad_norm": 2.952033042907715, + "learning_rate": 4.86693831866351e-06, + "loss": 0.4757439136505127, + "step": 470 + }, + { + "epoch": 0.5955334987593052, + "grad_norm": 2.9270098209381104, + "learning_rate": 4.855073668308561e-06, + "loss": 0.48748092651367186, + "step": 480 + }, + { + "epoch": 0.607940446650124, + "grad_norm": 2.9587056636810303, + "learning_rate": 4.842718133908973e-06, + "loss": 0.48392572402954104, + "step": 490 + }, + { + "epoch": 0.6203473945409429, + "grad_norm": 2.895169734954834, + "learning_rate": 4.829874290812932e-06, + "loss": 0.49219765663146975, + "step": 500 + }, + { + "epoch": 0.6327543424317618, + "grad_norm": 2.6126275062561035, + "learning_rate": 4.816544816150132e-06, + "loss": 0.46747660636901855, + "step": 510 + }, + { + "epoch": 0.6451612903225806, + "grad_norm": 2.7628698348999023, + "learning_rate": 4.802732488273762e-06, + "loss": 0.4878196716308594, + "step": 520 + }, + { + "epoch": 0.6575682382133995, + "grad_norm": 2.8378942012786865, + "learning_rate": 4.788440186181393e-06, + "loss": 0.4586039066314697, + "step": 530 + }, + { + "epoch": 0.6699751861042184, + "grad_norm": 2.957749605178833, + "learning_rate": 4.773670888914891e-06, + "loss": 0.5078807353973389, + "step": 540 + }, + { + "epoch": 0.6823821339950372, + "grad_norm": 3.1145918369293213, + "learning_rate": 4.75842767493948e-06, + "loss": 0.4683982372283936, + "step": 550 + }, + { + "epoch": 0.6947890818858561, + "grad_norm": 2.674837827682495, + "learning_rate": 4.742713721502065e-06, + "loss": 0.45024881362915037, + "step": 560 + }, + { + "epoch": 0.707196029776675, + "grad_norm": 3.1005373001098633, + "learning_rate": 4.726532303968986e-06, + "loss": 0.45893230438232424, + "step": 570 + }, + { + "epoch": 0.7196029776674938, + "grad_norm": 2.7729763984680176, + "learning_rate": 4.709886795143307e-06, + "loss": 0.4667107582092285, + "step": 580 + }, + { + "epoch": 0.7320099255583127, + "grad_norm": 4.1112060546875, + "learning_rate": 4.6927806645618034e-06, + "loss": 0.43797926902770995, + "step": 590 + }, + { + "epoch": 0.7444168734491315, + "grad_norm": 3.006535291671753, + "learning_rate": 4.675217477771779e-06, + "loss": 0.4455252647399902, + "step": 600 + }, + { + "epoch": 0.7568238213399504, + "grad_norm": 2.7127737998962402, + "learning_rate": 4.657200895587874e-06, + "loss": 0.48641119003295896, + "step": 610 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 3.1489853858947754, + "learning_rate": 4.638734673329023e-06, + "loss": 0.4687007427215576, + "step": 620 + }, + { + "epoch": 0.7816377171215881, + "grad_norm": 2.6937718391418457, + "learning_rate": 4.6198226600357e-06, + "loss": 0.48453760147094727, + "step": 630 + }, + { + "epoch": 0.794044665012407, + "grad_norm": 3.03733229637146, + "learning_rate": 4.600468797667641e-06, + "loss": 0.44130840301513674, + "step": 640 + }, + { + "epoch": 0.8064516129032258, + "grad_norm": 2.9481587409973145, + "learning_rate": 4.580677120282197e-06, + "loss": 0.42711877822875977, + "step": 650 + }, + { + "epoch": 0.8188585607940446, + "grad_norm": 2.9542925357818604, + "learning_rate": 4.56045175319348e-06, + "loss": 0.4542987823486328, + "step": 660 + }, + { + "epoch": 0.8312655086848635, + "grad_norm": 2.777961492538452, + "learning_rate": 4.539796912112505e-06, + "loss": 0.42932806015014646, + "step": 670 + }, + { + "epoch": 0.8436724565756824, + "grad_norm": 3.0970194339752197, + "learning_rate": 4.518716902268475e-06, + "loss": 0.46704769134521484, + "step": 680 + }, + { + "epoch": 0.8560794044665012, + "grad_norm": 2.6771323680877686, + "learning_rate": 4.497216117511413e-06, + "loss": 0.4675713539123535, + "step": 690 + }, + { + "epoch": 0.8684863523573201, + "grad_norm": 3.0414323806762695, + "learning_rate": 4.475299039396324e-06, + "loss": 0.4250528335571289, + "step": 700 + }, + { + "epoch": 0.8808933002481389, + "grad_norm": 2.52348256111145, + "learning_rate": 4.452970236249071e-06, + "loss": 0.4666771411895752, + "step": 710 + }, + { + "epoch": 0.8933002481389578, + "grad_norm": 3.3117287158966064, + "learning_rate": 4.4302343622141734e-06, + "loss": 0.4492027282714844, + "step": 720 + }, + { + "epoch": 0.9057071960297767, + "grad_norm": 2.8878304958343506, + "learning_rate": 4.4070961562847044e-06, + "loss": 0.428986644744873, + "step": 730 + }, + { + "epoch": 0.9181141439205955, + "grad_norm": 2.7645702362060547, + "learning_rate": 4.3835604413145175e-06, + "loss": 0.4693061351776123, + "step": 740 + }, + { + "epoch": 0.9305210918114144, + "grad_norm": 2.759788751602173, + "learning_rate": 4.3596321230129786e-06, + "loss": 0.46426753997802733, + "step": 750 + }, + { + "epoch": 0.9429280397022333, + "grad_norm": 2.815812349319458, + "learning_rate": 4.335316188922444e-06, + "loss": 0.42464771270751955, + "step": 760 + }, + { + "epoch": 0.9553349875930521, + "grad_norm": 2.893314838409424, + "learning_rate": 4.3106177073786684e-06, + "loss": 0.4731471061706543, + "step": 770 + }, + { + "epoch": 0.967741935483871, + "grad_norm": 2.6007916927337646, + "learning_rate": 4.285541826454374e-06, + "loss": 0.43342103958129885, + "step": 780 + }, + { + "epoch": 0.9801488833746899, + "grad_norm": 2.937251329421997, + "learning_rate": 4.26009377288621e-06, + "loss": 0.4437389850616455, + "step": 790 + }, + { + "epoch": 0.9925558312655087, + "grad_norm": 2.6743578910827637, + "learning_rate": 4.234278850985305e-06, + "loss": 0.4493260860443115, + "step": 800 + }, + { + "epoch": 1.0049627791563276, + "grad_norm": 2.905144214630127, + "learning_rate": 4.208102441531648e-06, + "loss": 0.4088118553161621, + "step": 810 + }, + { + "epoch": 1.0173697270471465, + "grad_norm": 2.634845495223999, + "learning_rate": 4.181570000652547e-06, + "loss": 0.33449294567108157, + "step": 820 + }, + { + "epoch": 1.0297766749379653, + "grad_norm": 2.6692142486572266, + "learning_rate": 4.15468705868536e-06, + "loss": 0.3250420093536377, + "step": 830 + }, + { + "epoch": 1.0421836228287842, + "grad_norm": 2.6853787899017334, + "learning_rate": 4.127459219024778e-06, + "loss": 0.35315914154052735, + "step": 840 + }, + { + "epoch": 1.054590570719603, + "grad_norm": 3.406165361404419, + "learning_rate": 4.099892156954861e-06, + "loss": 0.3586670637130737, + "step": 850 + }, + { + "epoch": 1.066997518610422, + "grad_norm": 2.948725461959839, + "learning_rate": 4.071991618466114e-06, + "loss": 0.3647527933120728, + "step": 860 + }, + { + "epoch": 1.0794044665012408, + "grad_norm": 2.896860122680664, + "learning_rate": 4.043763419057797e-06, + "loss": 0.32327847480773925, + "step": 870 + }, + { + "epoch": 1.0918114143920596, + "grad_norm": 3.324622869491577, + "learning_rate": 4.015213442525771e-06, + "loss": 0.35637316703796384, + "step": 880 + }, + { + "epoch": 1.1042183622828785, + "grad_norm": 3.4257752895355225, + "learning_rate": 3.986347639736092e-06, + "loss": 0.33382978439331057, + "step": 890 + }, + { + "epoch": 1.1166253101736974, + "grad_norm": 3.2966017723083496, + "learning_rate": 3.957172027384635e-06, + "loss": 0.33941695690155027, + "step": 900 + }, + { + "epoch": 1.129032258064516, + "grad_norm": 3.0130667686462402, + "learning_rate": 3.927692686742993e-06, + "loss": 0.3642054319381714, + "step": 910 + }, + { + "epoch": 1.141439205955335, + "grad_norm": 3.649632453918457, + "learning_rate": 3.897915762390912e-06, + "loss": 0.3299143314361572, + "step": 920 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 3.1730785369873047, + "learning_rate": 3.867847460935542e-06, + "loss": 0.34182562828063967, + "step": 930 + }, + { + "epoch": 1.1662531017369726, + "grad_norm": 3.1270976066589355, + "learning_rate": 3.8374940497177435e-06, + "loss": 0.36127467155456544, + "step": 940 + }, + { + "epoch": 1.1786600496277915, + "grad_norm": 2.9266204833984375, + "learning_rate": 3.806861855505748e-06, + "loss": 0.3463557958602905, + "step": 950 + }, + { + "epoch": 1.1910669975186103, + "grad_norm": 3.1734328269958496, + "learning_rate": 3.7759572631764243e-06, + "loss": 0.34737136363983157, + "step": 960 + }, + { + "epoch": 1.2034739454094292, + "grad_norm": 3.387535333633423, + "learning_rate": 3.7447867143844373e-06, + "loss": 0.3464951038360596, + "step": 970 + }, + { + "epoch": 1.215880893300248, + "grad_norm": 3.2590081691741943, + "learning_rate": 3.7133567062195697e-06, + "loss": 0.3240300178527832, + "step": 980 + }, + { + "epoch": 1.228287841191067, + "grad_norm": 2.911224603652954, + "learning_rate": 3.6816737898524844e-06, + "loss": 0.33942902088165283, + "step": 990 + }, + { + "epoch": 1.2406947890818858, + "grad_norm": 3.3266444206237793, + "learning_rate": 3.649744569169229e-06, + "loss": 0.3586859226226807, + "step": 1000 + }, + { + "epoch": 1.2531017369727047, + "grad_norm": 3.285763740539551, + "learning_rate": 3.617575699394732e-06, + "loss": 0.33882172107696534, + "step": 1010 + }, + { + "epoch": 1.2655086848635235, + "grad_norm": 3.605529308319092, + "learning_rate": 3.5851738857056174e-06, + "loss": 0.34563610553741453, + "step": 1020 + }, + { + "epoch": 1.2779156327543424, + "grad_norm": 2.4176876544952393, + "learning_rate": 3.552545881832594e-06, + "loss": 0.3259500741958618, + "step": 1030 + }, + { + "epoch": 1.2903225806451613, + "grad_norm": 3.1849021911621094, + "learning_rate": 3.519698488652734e-06, + "loss": 0.35965259075164796, + "step": 1040 + }, + { + "epoch": 1.3027295285359801, + "grad_norm": 3.008430004119873, + "learning_rate": 3.486638552771914e-06, + "loss": 0.34020233154296875, + "step": 1050 + }, + { + "epoch": 1.315136476426799, + "grad_norm": 3.7227566242218018, + "learning_rate": 3.4533729650977344e-06, + "loss": 0.33164680004119873, + "step": 1060 + }, + { + "epoch": 1.3275434243176178, + "grad_norm": 3.4713714122772217, + "learning_rate": 3.4199086594031998e-06, + "loss": 0.3493825435638428, + "step": 1070 + }, + { + "epoch": 1.3399503722084367, + "grad_norm": 3.2516400814056396, + "learning_rate": 3.386252610881465e-06, + "loss": 0.3430775165557861, + "step": 1080 + }, + { + "epoch": 1.3523573200992556, + "grad_norm": 3.756378650665283, + "learning_rate": 3.3524118346919486e-06, + "loss": 0.3269376277923584, + "step": 1090 + }, + { + "epoch": 1.3647642679900744, + "grad_norm": 2.7790579795837402, + "learning_rate": 3.318393384498114e-06, + "loss": 0.3524430274963379, + "step": 1100 + }, + { + "epoch": 1.3771712158808933, + "grad_norm": 3.254763603210449, + "learning_rate": 3.2842043509972294e-06, + "loss": 0.35284743309020994, + "step": 1110 + }, + { + "epoch": 1.3895781637717122, + "grad_norm": 3.231228828430176, + "learning_rate": 3.2498518604424005e-06, + "loss": 0.35561535358428953, + "step": 1120 + }, + { + "epoch": 1.401985111662531, + "grad_norm": 3.0170490741729736, + "learning_rate": 3.215343073157204e-06, + "loss": 0.36517820358276365, + "step": 1130 + }, + { + "epoch": 1.41439205955335, + "grad_norm": 3.0740880966186523, + "learning_rate": 3.180685182043205e-06, + "loss": 0.34882569313049316, + "step": 1140 + }, + { + "epoch": 1.4267990074441688, + "grad_norm": 3.487521171569824, + "learning_rate": 3.1458854110806976e-06, + "loss": 0.344951868057251, + "step": 1150 + }, + { + "epoch": 1.4392059553349876, + "grad_norm": 2.7537150382995605, + "learning_rate": 3.1109510138229565e-06, + "loss": 0.3353364706039429, + "step": 1160 + }, + { + "epoch": 1.4516129032258065, + "grad_norm": 2.8499064445495605, + "learning_rate": 3.0758892718843352e-06, + "loss": 0.33848204612731936, + "step": 1170 + }, + { + "epoch": 1.4640198511166254, + "grad_norm": 3.2181148529052734, + "learning_rate": 3.0407074934225038e-06, + "loss": 0.3388556480407715, + "step": 1180 + }, + { + "epoch": 1.4764267990074442, + "grad_norm": 3.099386215209961, + "learning_rate": 3.005413011615165e-06, + "loss": 0.3524498224258423, + "step": 1190 + }, + { + "epoch": 1.488833746898263, + "grad_norm": 3.1054389476776123, + "learning_rate": 2.9700131831315425e-06, + "loss": 0.3347229719161987, + "step": 1200 + }, + { + "epoch": 1.501240694789082, + "grad_norm": 2.9575774669647217, + "learning_rate": 2.9345153865989918e-06, + "loss": 0.321802020072937, + "step": 1210 + }, + { + "epoch": 1.5136476426799006, + "grad_norm": 2.824366569519043, + "learning_rate": 2.898927021065011e-06, + "loss": 0.3323647499084473, + "step": 1220 + }, + { + "epoch": 1.5260545905707197, + "grad_norm": 3.0914690494537354, + "learning_rate": 2.8632555044550152e-06, + "loss": 0.3432508945465088, + "step": 1230 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 3.0662307739257812, + "learning_rate": 2.8275082720261623e-06, + "loss": 0.3417309522628784, + "step": 1240 + }, + { + "epoch": 1.5508684863523574, + "grad_norm": 3.1436731815338135, + "learning_rate": 2.791692774817576e-06, + "loss": 0.3290053606033325, + "step": 1250 + }, + { + "epoch": 1.563275434243176, + "grad_norm": 2.940727472305298, + "learning_rate": 2.75581647809727e-06, + "loss": 0.33008174896240233, + "step": 1260 + }, + { + "epoch": 1.5756823821339951, + "grad_norm": 2.7560057640075684, + "learning_rate": 2.7198868598061177e-06, + "loss": 0.3164780616760254, + "step": 1270 + }, + { + "epoch": 1.5880893300248138, + "grad_norm": 3.87307071685791, + "learning_rate": 2.683911408999169e-06, + "loss": 0.3081036567687988, + "step": 1280 + }, + { + "epoch": 1.6004962779156329, + "grad_norm": 2.84149169921875, + "learning_rate": 2.6478976242846576e-06, + "loss": 0.35092926025390625, + "step": 1290 + }, + { + "epoch": 1.6129032258064515, + "grad_norm": 3.040497303009033, + "learning_rate": 2.6118530122610138e-06, + "loss": 0.37850337028503417, + "step": 1300 + }, + { + "epoch": 1.6253101736972706, + "grad_norm": 2.946133613586426, + "learning_rate": 2.575785085952216e-06, + "loss": 0.35753021240234373, + "step": 1310 + }, + { + "epoch": 1.6377171215880892, + "grad_norm": 3.4700191020965576, + "learning_rate": 2.539701363241795e-06, + "loss": 0.34999761581420896, + "step": 1320 + }, + { + "epoch": 1.6501240694789083, + "grad_norm": 2.9002044200897217, + "learning_rate": 2.503609365305835e-06, + "loss": 0.3304608345031738, + "step": 1330 + }, + { + "epoch": 1.662531017369727, + "grad_norm": 3.0107545852661133, + "learning_rate": 2.4675166150452814e-06, + "loss": 0.3420397281646729, + "step": 1340 + }, + { + "epoch": 1.674937965260546, + "grad_norm": 2.818993330001831, + "learning_rate": 2.4314306355178924e-06, + "loss": 0.31749625205993653, + "step": 1350 + }, + { + "epoch": 1.6873449131513647, + "grad_norm": 2.8868680000305176, + "learning_rate": 2.3953589483701556e-06, + "loss": 0.33247082233428954, + "step": 1360 + }, + { + "epoch": 1.6997518610421838, + "grad_norm": 2.5516133308410645, + "learning_rate": 2.3593090722694995e-06, + "loss": 0.3121840000152588, + "step": 1370 + }, + { + "epoch": 1.7121588089330024, + "grad_norm": 2.8889875411987305, + "learning_rate": 2.3232885213371297e-06, + "loss": 0.3375117778778076, + "step": 1380 + }, + { + "epoch": 1.7245657568238213, + "grad_norm": 3.4715304374694824, + "learning_rate": 2.2873048035818043e-06, + "loss": 0.3526495695114136, + "step": 1390 + }, + { + "epoch": 1.7369727047146402, + "grad_norm": 2.6388895511627197, + "learning_rate": 2.251365419334895e-06, + "loss": 0.3385695219039917, + "step": 1400 + }, + { + "epoch": 1.749379652605459, + "grad_norm": 3.295314311981201, + "learning_rate": 2.2154778596870365e-06, + "loss": 0.3281654119491577, + "step": 1410 + }, + { + "epoch": 1.7617866004962779, + "grad_norm": 2.9345321655273438, + "learning_rate": 2.179649604926708e-06, + "loss": 0.3286000728607178, + "step": 1420 + }, + { + "epoch": 1.7741935483870968, + "grad_norm": 3.245892286300659, + "learning_rate": 2.14388812298107e-06, + "loss": 0.31292095184326174, + "step": 1430 + }, + { + "epoch": 1.7866004962779156, + "grad_norm": 2.8466174602508545, + "learning_rate": 2.108200867859369e-06, + "loss": 0.32442235946655273, + "step": 1440 + }, + { + "epoch": 1.7990074441687345, + "grad_norm": 3.2279984951019287, + "learning_rate": 2.072595278099247e-06, + "loss": 0.3294026851654053, + "step": 1450 + }, + { + "epoch": 1.8114143920595533, + "grad_norm": 3.1583516597747803, + "learning_rate": 2.037078775216283e-06, + "loss": 0.3263838768005371, + "step": 1460 + }, + { + "epoch": 1.8238213399503722, + "grad_norm": 3.04581356048584, + "learning_rate": 2.0016587621570682e-06, + "loss": 0.33864445686340333, + "step": 1470 + }, + { + "epoch": 1.836228287841191, + "grad_norm": 3.7386040687561035, + "learning_rate": 1.966342621756163e-06, + "loss": 0.31294050216674807, + "step": 1480 + }, + { + "epoch": 1.84863523573201, + "grad_norm": 2.868602991104126, + "learning_rate": 1.931137715197242e-06, + "loss": 0.31308484077453613, + "step": 1490 + }, + { + "epoch": 1.8610421836228288, + "grad_norm": 3.055979013442993, + "learning_rate": 1.8960513804787557e-06, + "loss": 0.333689284324646, + "step": 1500 + }, + { + "epoch": 1.8734491315136477, + "grad_norm": 3.1473002433776855, + "learning_rate": 1.861090930884412e-06, + "loss": 0.33293652534484863, + "step": 1510 + }, + { + "epoch": 1.8858560794044665, + "grad_norm": 2.9485549926757812, + "learning_rate": 1.8262636534588316e-06, + "loss": 0.3332956790924072, + "step": 1520 + }, + { + "epoch": 1.8982630272952854, + "grad_norm": 2.9611082077026367, + "learning_rate": 1.7915768074886497e-06, + "loss": 0.32119269371032716, + "step": 1530 + }, + { + "epoch": 1.9106699751861043, + "grad_norm": 2.7273433208465576, + "learning_rate": 1.7570376229894164e-06, + "loss": 0.32526330947875975, + "step": 1540 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 3.0661497116088867, + "learning_rate": 1.7226532991985976e-06, + "loss": 0.3218840599060059, + "step": 1550 + }, + { + "epoch": 1.935483870967742, + "grad_norm": 2.9829108715057373, + "learning_rate": 1.688431003074985e-06, + "loss": 0.3307999610900879, + "step": 1560 + }, + { + "epoch": 1.9478908188585606, + "grad_norm": 3.018162488937378, + "learning_rate": 1.654377867804841e-06, + "loss": 0.34044556617736815, + "step": 1570 + }, + { + "epoch": 1.9602977667493797, + "grad_norm": 2.9301137924194336, + "learning_rate": 1.6205009913150815e-06, + "loss": 0.31292636394500734, + "step": 1580 + }, + { + "epoch": 1.9727047146401984, + "grad_norm": 2.9100582599639893, + "learning_rate": 1.5868074347937993e-06, + "loss": 0.32329092025756834, + "step": 1590 + }, + { + "epoch": 1.9851116625310175, + "grad_norm": 2.979872465133667, + "learning_rate": 1.553304221218462e-06, + "loss": 0.3566758155822754, + "step": 1600 + }, + { + "epoch": 1.997518610421836, + "grad_norm": 2.6494853496551514, + "learning_rate": 1.5199983338920594e-06, + "loss": 0.3069176197052002, + "step": 1610 + }, + { + "epoch": 2.009925558312655, + "grad_norm": 2.3948535919189453, + "learning_rate": 1.4868967149875257e-06, + "loss": 0.25013885498046873, + "step": 1620 + }, + { + "epoch": 2.022332506203474, + "grad_norm": 2.941615343093872, + "learning_rate": 1.4540062641007383e-06, + "loss": 0.22131125926971434, + "step": 1630 + }, + { + "epoch": 2.034739454094293, + "grad_norm": 3.205547332763672, + "learning_rate": 1.421333836812387e-06, + "loss": 0.2237858295440674, + "step": 1640 + }, + { + "epoch": 2.0471464019851116, + "grad_norm": 3.0743908882141113, + "learning_rate": 1.3888862432590167e-06, + "loss": 0.22658278942108154, + "step": 1650 + }, + { + "epoch": 2.0595533498759306, + "grad_norm": 2.8300976753234863, + "learning_rate": 1.3566702467135445e-06, + "loss": 0.2289585828781128, + "step": 1660 + }, + { + "epoch": 2.0719602977667493, + "grad_norm": 2.5701904296875, + "learning_rate": 1.3246925621755496e-06, + "loss": 0.22105908393859863, + "step": 1670 + }, + { + "epoch": 2.0843672456575684, + "grad_norm": 2.67372727394104, + "learning_rate": 1.2929598549716122e-06, + "loss": 0.20758159160614015, + "step": 1680 + }, + { + "epoch": 2.096774193548387, + "grad_norm": 3.0295441150665283, + "learning_rate": 1.2614787393660215e-06, + "loss": 0.2294921875, + "step": 1690 + }, + { + "epoch": 2.109181141439206, + "grad_norm": 3.321169137954712, + "learning_rate": 1.2302557771821154e-06, + "loss": 0.22693567276000975, + "step": 1700 + }, + { + "epoch": 2.1215880893300247, + "grad_norm": 3.0045440196990967, + "learning_rate": 1.199297476434553e-06, + "loss": 0.23366827964782716, + "step": 1710 + }, + { + "epoch": 2.133995037220844, + "grad_norm": 3.3027615547180176, + "learning_rate": 1.168610289972813e-06, + "loss": 0.204612398147583, + "step": 1720 + }, + { + "epoch": 2.1464019851116625, + "grad_norm": 3.4568586349487305, + "learning_rate": 1.138200614136172e-06, + "loss": 0.23412892818450928, + "step": 1730 + }, + { + "epoch": 2.1588089330024816, + "grad_norm": 3.1891727447509766, + "learning_rate": 1.1080747874204809e-06, + "loss": 0.23051118850708008, + "step": 1740 + }, + { + "epoch": 2.1712158808933, + "grad_norm": 2.898972511291504, + "learning_rate": 1.0782390891569822e-06, + "loss": 0.223101806640625, + "step": 1750 + }, + { + "epoch": 2.1836228287841193, + "grad_norm": 3.198352098464966, + "learning_rate": 1.0486997382034695e-06, + "loss": 0.21067981719970702, + "step": 1760 + }, + { + "epoch": 2.196029776674938, + "grad_norm": 3.239396095275879, + "learning_rate": 1.0194628916480504e-06, + "loss": 0.21455581188201905, + "step": 1770 + }, + { + "epoch": 2.208436724565757, + "grad_norm": 3.6431620121002197, + "learning_rate": 9.905346435257784e-07, + "loss": 0.25631544589996336, + "step": 1780 + }, + { + "epoch": 2.2208436724565757, + "grad_norm": 3.2421746253967285, + "learning_rate": 9.619210235484333e-07, + "loss": 0.2324852466583252, + "step": 1790 + }, + { + "epoch": 2.2332506203473947, + "grad_norm": 3.0301804542541504, + "learning_rate": 9.336279958477096e-07, + "loss": 0.2013075351715088, + "step": 1800 + }, + { + "epoch": 2.2456575682382134, + "grad_norm": 3.0917258262634277, + "learning_rate": 9.056614577320702e-07, + "loss": 0.23809702396392823, + "step": 1810 + }, + { + "epoch": 2.258064516129032, + "grad_norm": 3.2016923427581787, + "learning_rate": 8.780272384575289e-07, + "loss": 0.22165682315826415, + "step": 1820 + }, + { + "epoch": 2.270471464019851, + "grad_norm": 3.2964746952056885, + "learning_rate": 8.507310980126188e-07, + "loss": 0.21906075477600098, + "step": 1830 + }, + { + "epoch": 2.28287841191067, + "grad_norm": 3.021667242050171, + "learning_rate": 8.237787259178037e-07, + "loss": 0.21673779487609862, + "step": 1840 + }, + { + "epoch": 2.295285359801489, + "grad_norm": 3.4305264949798584, + "learning_rate": 7.971757400395652e-07, + "loss": 0.23625686168670654, + "step": 1850 + }, + { + "epoch": 2.3076923076923075, + "grad_norm": 2.7715115547180176, + "learning_rate": 7.709276854194392e-07, + "loss": 0.21259665489196777, + "step": 1860 + }, + { + "epoch": 2.3200992555831266, + "grad_norm": 3.520462989807129, + "learning_rate": 7.450400331182198e-07, + "loss": 0.23154499530792236, + "step": 1870 + }, + { + "epoch": 2.332506203473945, + "grad_norm": 3.7826356887817383, + "learning_rate": 7.19518179075591e-07, + "loss": 0.2277855396270752, + "step": 1880 + }, + { + "epoch": 2.3449131513647643, + "grad_norm": 3.4630792140960693, + "learning_rate": 6.943674429854172e-07, + "loss": 0.22485933303833008, + "step": 1890 + }, + { + "epoch": 2.357320099255583, + "grad_norm": 3.305630922317505, + "learning_rate": 6.695930671869175e-07, + "loss": 0.23359484672546388, + "step": 1900 + }, + { + "epoch": 2.369727047146402, + "grad_norm": 2.659604787826538, + "learning_rate": 6.452002155719725e-07, + "loss": 0.19909019470214845, + "step": 1910 + }, + { + "epoch": 2.3821339950372207, + "grad_norm": 3.414795398712158, + "learning_rate": 6.211939725087806e-07, + "loss": 0.23796792030334474, + "step": 1920 + }, + { + "epoch": 2.3945409429280398, + "grad_norm": 3.0635950565338135, + "learning_rate": 5.975793417820841e-07, + "loss": 0.22071402072906493, + "step": 1930 + }, + { + "epoch": 2.4069478908188584, + "grad_norm": 3.123188018798828, + "learning_rate": 5.743612455502016e-07, + "loss": 0.22007994651794432, + "step": 1940 + }, + { + "epoch": 2.4193548387096775, + "grad_norm": 2.785230875015259, + "learning_rate": 5.515445233190636e-07, + "loss": 0.21707756519317628, + "step": 1950 + }, + { + "epoch": 2.431761786600496, + "grad_norm": 3.8641016483306885, + "learning_rate": 5.291339309334845e-07, + "loss": 0.2090601682662964, + "step": 1960 + }, + { + "epoch": 2.444168734491315, + "grad_norm": 2.880202054977417, + "learning_rate": 5.071341395858703e-07, + "loss": 0.2203066825866699, + "step": 1970 + }, + { + "epoch": 2.456575682382134, + "grad_norm": 3.224031448364258, + "learning_rate": 4.855497348425686e-07, + "loss": 0.22847747802734375, + "step": 1980 + }, + { + "epoch": 2.468982630272953, + "grad_norm": 3.334984302520752, + "learning_rate": 4.6438521568806625e-07, + "loss": 0.20745439529418946, + "step": 1990 + }, + { + "epoch": 2.4813895781637716, + "grad_norm": 3.121742010116577, + "learning_rate": 4.436449935872378e-07, + "loss": 0.23231451511383056, + "step": 2000 + }, + { + "epoch": 2.4937965260545907, + "grad_norm": 2.765779972076416, + "learning_rate": 4.2333339156583467e-07, + "loss": 0.2055814266204834, + "step": 2010 + }, + { + "epoch": 2.5062034739454093, + "grad_norm": 3.019102096557617, + "learning_rate": 4.034546433094036e-07, + "loss": 0.22689828872680665, + "step": 2020 + }, + { + "epoch": 2.5186104218362284, + "grad_norm": 3.2937521934509277, + "learning_rate": 3.8401289228083395e-07, + "loss": 0.23529858589172364, + "step": 2030 + }, + { + "epoch": 2.531017369727047, + "grad_norm": 3.353877544403076, + "learning_rate": 3.6501219085670724e-07, + "loss": 0.2225353479385376, + "step": 2040 + }, + { + "epoch": 2.543424317617866, + "grad_norm": 3.6522250175476074, + "learning_rate": 3.4645649948263085e-07, + "loss": 0.2311680793762207, + "step": 2050 + }, + { + "epoch": 2.555831265508685, + "grad_norm": 3.3297574520111084, + "learning_rate": 3.2834968584773754e-07, + "loss": 0.21333532333374022, + "step": 2060 + }, + { + "epoch": 2.568238213399504, + "grad_norm": 3.3023574352264404, + "learning_rate": 3.106955240785153e-07, + "loss": 0.2413243293762207, + "step": 2070 + }, + { + "epoch": 2.5806451612903225, + "grad_norm": 2.7704153060913086, + "learning_rate": 2.9349769395214e-07, + "loss": 0.21133730411529542, + "step": 2080 + }, + { + "epoch": 2.5930521091811416, + "grad_norm": 3.1937754154205322, + "learning_rate": 2.767597801294772e-07, + "loss": 0.21675755977630615, + "step": 2090 + }, + { + "epoch": 2.6054590570719602, + "grad_norm": 3.397535562515259, + "learning_rate": 2.604852714079023e-07, + "loss": 0.22542505264282225, + "step": 2100 + }, + { + "epoch": 2.617866004962779, + "grad_norm": 3.3038713932037354, + "learning_rate": 2.4467755999411204e-07, + "loss": 0.23392457962036134, + "step": 2110 + }, + { + "epoch": 2.630272952853598, + "grad_norm": 4.148429870605469, + "learning_rate": 2.2933994079705896e-07, + "loss": 0.19952282905578614, + "step": 2120 + }, + { + "epoch": 2.642679900744417, + "grad_norm": 3.0992136001586914, + "learning_rate": 2.144756107411733e-07, + "loss": 0.2230466365814209, + "step": 2130 + }, + { + "epoch": 2.6550868486352357, + "grad_norm": 3.451746940612793, + "learning_rate": 2.0008766810000801e-07, + "loss": 0.23057200908660888, + "step": 2140 + }, + { + "epoch": 2.6674937965260543, + "grad_norm": 3.058110237121582, + "learning_rate": 1.861791118504408e-07, + "loss": 0.2180851459503174, + "step": 2150 + }, + { + "epoch": 2.6799007444168734, + "grad_norm": 2.745176315307617, + "learning_rate": 1.7275284104757844e-07, + "loss": 0.2167917251586914, + "step": 2160 + }, + { + "epoch": 2.6923076923076925, + "grad_norm": 3.708021402359009, + "learning_rate": 1.598116542204889e-07, + "loss": 0.22899148464202881, + "step": 2170 + }, + { + "epoch": 2.704714640198511, + "grad_norm": 3.6781704425811768, + "learning_rate": 1.4735824878888277e-07, + "loss": 0.2170346736907959, + "step": 2180 + }, + { + "epoch": 2.71712158808933, + "grad_norm": 2.478654623031616, + "learning_rate": 1.353952205008713e-07, + "loss": 0.2242295265197754, + "step": 2190 + }, + { + "epoch": 2.729528535980149, + "grad_norm": 2.7087976932525635, + "learning_rate": 1.2392506289191837e-07, + "loss": 0.2131351947784424, + "step": 2200 + }, + { + "epoch": 2.741935483870968, + "grad_norm": 2.867835283279419, + "learning_rate": 1.1295016676509618e-07, + "loss": 0.21861982345581055, + "step": 2210 + }, + { + "epoch": 2.7543424317617866, + "grad_norm": 2.9449636936187744, + "learning_rate": 1.0247281969275131e-07, + "loss": 0.1985526442527771, + "step": 2220 + }, + { + "epoch": 2.7667493796526053, + "grad_norm": 3.0885448455810547, + "learning_rate": 9.249520553969465e-08, + "loss": 0.23580389022827147, + "step": 2230 + }, + { + "epoch": 2.7791563275434243, + "grad_norm": 3.1814591884613037, + "learning_rate": 8.301940400799818e-08, + "loss": 0.21973462104797364, + "step": 2240 + }, + { + "epoch": 2.7915632754342434, + "grad_norm": 3.26047682762146, + "learning_rate": 7.404739020351381e-08, + "loss": 0.22958881855010987, + "step": 2250 + }, + { + "epoch": 2.803970223325062, + "grad_norm": 3.2021138668060303, + "learning_rate": 6.558103422418555e-08, + "loss": 0.23037824630737305, + "step": 2260 + }, + { + "epoch": 2.8163771712158807, + "grad_norm": 3.562350273132324, + "learning_rate": 5.762210077025293e-08, + "loss": 0.2314563512802124, + "step": 2270 + }, + { + "epoch": 2.8287841191067, + "grad_norm": 3.15472412109375, + "learning_rate": 5.017224877642196e-08, + "loss": 0.21394333839416504, + "step": 2280 + }, + { + "epoch": 2.8411910669975184, + "grad_norm": 2.9189085960388184, + "learning_rate": 4.323303106608362e-08, + "loss": 0.22109608650207518, + "step": 2290 + }, + { + "epoch": 2.8535980148883375, + "grad_norm": 3.364637851715088, + "learning_rate": 3.680589402764695e-08, + "loss": 0.21065773963928222, + "step": 2300 + }, + { + "epoch": 2.866004962779156, + "grad_norm": 3.1239407062530518, + "learning_rate": 3.089217731305882e-08, + "loss": 0.21384596824645996, + "step": 2310 + }, + { + "epoch": 2.8784119106699753, + "grad_norm": 3.2410709857940674, + "learning_rate": 2.5493113558571203e-08, + "loss": 0.2103095531463623, + "step": 2320 + }, + { + "epoch": 2.890818858560794, + "grad_norm": 3.29823899269104, + "learning_rate": 2.0609828127814425e-08, + "loss": 0.22623074054718018, + "step": 2330 + }, + { + "epoch": 2.903225806451613, + "grad_norm": 3.447692632675171, + "learning_rate": 1.624333887723012e-08, + "loss": 0.2561406373977661, + "step": 2340 + }, + { + "epoch": 2.9156327543424316, + "grad_norm": 3.5823864936828613, + "learning_rate": 1.2394555943911757e-08, + "loss": 0.22645580768585205, + "step": 2350 + }, + { + "epoch": 2.9280397022332507, + "grad_norm": 3.032896041870117, + "learning_rate": 9.0642815559e-09, + "loss": 0.21149790287017822, + "step": 2360 + }, + { + "epoch": 2.9404466501240694, + "grad_norm": 3.0762665271759033, + "learning_rate": 6.253209864966747e-09, + "loss": 0.2031836986541748, + "step": 2370 + }, + { + "epoch": 2.9528535980148884, + "grad_norm": 3.5435872077941895, + "learning_rate": 3.9619268019305825e-09, + "loss": 0.2176318883895874, + "step": 2380 + }, + { + "epoch": 2.965260545905707, + "grad_norm": 3.506044387817383, + "learning_rate": 2.190909954525866e-09, + "loss": 0.2153688907623291, + "step": 2390 + }, + { + "epoch": 2.977667493796526, + "grad_norm": 3.4698026180267334, + "learning_rate": 9.405284678556948e-10, + "loss": 0.21965882778167725, + "step": 2400 + }, + { + "epoch": 2.990074441687345, + "grad_norm": 3.0432729721069336, + "learning_rate": 2.1104296745011466e-10, + "loss": 0.2195052146911621, + "step": 2410 + }, + { + "epoch": 3.0, + "step": 2418, + "total_flos": 1.329254778357678e+18, + "train_loss": 0.361527387419449, + "train_runtime": 121252.8356, + "train_samples_per_second": 0.16, + "train_steps_per_second": 0.02 + } + ], + "logging_steps": 10, + "max_steps": 2418, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.329254778357678e+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..d49a86a --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f275f0af9f7e7a5393aba11b6369870a7a92f86d7e9471e7c6b2471835c81572 +size 5649 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..ea66604 Binary files /dev/null and b/training_loss.png differ