| { | |
| "best_metric": 0.9531590342521667, | |
| "best_model_checkpoint": "Geodeberta2/checkpoint-126", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 126, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.031746031746031744, | |
| "grad_norm": 3.382016897201538, | |
| "learning_rate": 1.5873015873015873e-06, | |
| "loss": 1.2687, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 3.2359426021575928, | |
| "learning_rate": 3.1746031746031746e-06, | |
| "loss": 1.2944, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 2.8667497634887695, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 1.2725, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 1.7016966342926025, | |
| "learning_rate": 6.349206349206349e-06, | |
| "loss": 1.3089, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 2.4599409103393555, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 1.2902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.53178334236145, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 1.2766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 3.3443331718444824, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 1.2274, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 2.784144878387451, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 1.2141, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 3.0724332332611084, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.2465, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 1.5863182544708252, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 1.2876, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3492063492063492, | |
| "grad_norm": 1.5585477352142334, | |
| "learning_rate": 1.746031746031746e-05, | |
| "loss": 1.2536, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.9539477825164795, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 1.1878, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4126984126984127, | |
| "grad_norm": 1.7762205600738525, | |
| "learning_rate": 2.0634920634920636e-05, | |
| "loss": 1.2631, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 3.783928155899048, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 1.0052, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 1.4549317359924316, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 1.1053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 2.450103521347046, | |
| "learning_rate": 2.5396825396825397e-05, | |
| "loss": 1.0221, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5396825396825397, | |
| "grad_norm": 3.955317258834839, | |
| "learning_rate": 2.6984126984126984e-05, | |
| "loss": 1.1519, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 3.0787367820739746, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.8755, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6031746031746031, | |
| "grad_norm": 2.1669228076934814, | |
| "learning_rate": 3.0158730158730158e-05, | |
| "loss": 1.0728, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 2.1683146953582764, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 1.0817, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.4933903217315674, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0527, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6984126984126984, | |
| "grad_norm": 2.5503716468811035, | |
| "learning_rate": 3.492063492063492e-05, | |
| "loss": 1.1201, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7301587301587301, | |
| "grad_norm": 2.326674461364746, | |
| "learning_rate": 3.650793650793651e-05, | |
| "loss": 0.8091, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 2.899217128753662, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 0.851, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 2.776383399963379, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 1.0539, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8253968253968254, | |
| "grad_norm": 3.472299814224243, | |
| "learning_rate": 4.126984126984127e-05, | |
| "loss": 0.9422, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 4.994964122772217, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.0585, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 7.897761821746826, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.1766, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9206349206349206, | |
| "grad_norm": 3.434422731399536, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 1.0149, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 4.816616535186768, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.8752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9841269841269841, | |
| "grad_norm": 2.6246337890625, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 0.9825, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5271966527196653, | |
| "eval_f1_macro": 0.29448106332528445, | |
| "eval_f1_micro": 0.5271966527196653, | |
| "eval_f1_weighted": 0.47887320097744607, | |
| "eval_loss": 1.0690832138061523, | |
| "eval_precision_macro": 0.2979542433081334, | |
| "eval_precision_micro": 0.5271966527196653, | |
| "eval_precision_weighted": 0.5181255807964261, | |
| "eval_recall_macro": 0.35484535475707013, | |
| "eval_recall_micro": 0.5271966527196653, | |
| "eval_recall_weighted": 0.5271966527196653, | |
| "eval_runtime": 1.6359, | |
| "eval_samples_per_second": 292.199, | |
| "eval_steps_per_second": 4.89, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0158730158730158, | |
| "grad_norm": 4.054161071777344, | |
| "learning_rate": 4.991181657848325e-05, | |
| "loss": 1.0958, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.0476190476190477, | |
| "grad_norm": 2.788057565689087, | |
| "learning_rate": 4.973544973544973e-05, | |
| "loss": 1.1205, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0793650793650793, | |
| "grad_norm": 4.333444595336914, | |
| "learning_rate": 4.955908289241622e-05, | |
| "loss": 0.9343, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 2.873152732849121, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.8455, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 3.179229736328125, | |
| "learning_rate": 4.9206349206349204e-05, | |
| "loss": 0.905, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.1746031746031746, | |
| "grad_norm": 6.202491760253906, | |
| "learning_rate": 4.9029982363315695e-05, | |
| "loss": 0.7701, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2063492063492063, | |
| "grad_norm": 7.958104610443115, | |
| "learning_rate": 4.8853615520282185e-05, | |
| "loss": 0.9304, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.2380952380952381, | |
| "grad_norm": 6.333682537078857, | |
| "learning_rate": 4.8677248677248676e-05, | |
| "loss": 1.0795, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.2698412698412698, | |
| "grad_norm": 5.300474166870117, | |
| "learning_rate": 4.850088183421517e-05, | |
| "loss": 0.9147, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3015873015873016, | |
| "grad_norm": 3.8622822761535645, | |
| "learning_rate": 4.832451499118166e-05, | |
| "loss": 0.7233, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 3.2566518783569336, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.9643, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3650793650793651, | |
| "grad_norm": 3.669085741043091, | |
| "learning_rate": 4.797178130511464e-05, | |
| "loss": 0.5868, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3968253968253967, | |
| "grad_norm": 5.4853363037109375, | |
| "learning_rate": 4.779541446208113e-05, | |
| "loss": 0.9615, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 4.062696933746338, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.827, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4603174603174602, | |
| "grad_norm": 2.2320899963378906, | |
| "learning_rate": 4.744268077601411e-05, | |
| "loss": 0.8415, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.492063492063492, | |
| "grad_norm": 5.46465539932251, | |
| "learning_rate": 4.72663139329806e-05, | |
| "loss": 0.7415, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 2.736971139907837, | |
| "learning_rate": 4.708994708994709e-05, | |
| "loss": 0.8833, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 2.601299524307251, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.7582, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 6.022972106933594, | |
| "learning_rate": 4.673721340388007e-05, | |
| "loss": 0.7518, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.619047619047619, | |
| "grad_norm": 6.7905378341674805, | |
| "learning_rate": 4.656084656084656e-05, | |
| "loss": 1.0717, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6507936507936507, | |
| "grad_norm": 3.2041382789611816, | |
| "learning_rate": 4.638447971781305e-05, | |
| "loss": 0.6562, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6825396825396826, | |
| "grad_norm": 6.4817681312561035, | |
| "learning_rate": 4.620811287477954e-05, | |
| "loss": 0.9219, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 4.928455829620361, | |
| "learning_rate": 4.603174603174603e-05, | |
| "loss": 0.8101, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.746031746031746, | |
| "grad_norm": 4.112485885620117, | |
| "learning_rate": 4.585537918871252e-05, | |
| "loss": 0.8257, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 6.042239189147949, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.6938, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.8095238095238095, | |
| "grad_norm": 2.9191532135009766, | |
| "learning_rate": 4.55026455026455e-05, | |
| "loss": 0.8586, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8412698412698414, | |
| "grad_norm": 2.405008554458618, | |
| "learning_rate": 4.532627865961199e-05, | |
| "loss": 0.6218, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.873015873015873, | |
| "grad_norm": 3.959949016571045, | |
| "learning_rate": 4.5149911816578484e-05, | |
| "loss": 0.7355, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 3.4744226932525635, | |
| "learning_rate": 4.4973544973544974e-05, | |
| "loss": 0.7225, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9365079365079365, | |
| "grad_norm": 3.96034836769104, | |
| "learning_rate": 4.4797178130511465e-05, | |
| "loss": 0.7276, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.9682539682539684, | |
| "grad_norm": 4.284174919128418, | |
| "learning_rate": 4.4620811287477956e-05, | |
| "loss": 0.6909, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 11.619244575500488, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.7797, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6548117154811716, | |
| "eval_f1_macro": 0.4940971741477817, | |
| "eval_f1_micro": 0.6548117154811716, | |
| "eval_f1_weighted": 0.628735443682528, | |
| "eval_loss": 0.9531590342521667, | |
| "eval_precision_macro": 0.6898690717515761, | |
| "eval_precision_micro": 0.6548117154811716, | |
| "eval_precision_weighted": 0.6835107777099136, | |
| "eval_recall_macro": 0.47932568993970953, | |
| "eval_recall_micro": 0.6548117154811716, | |
| "eval_recall_weighted": 0.6548117154811716, | |
| "eval_runtime": 1.6407, | |
| "eval_samples_per_second": 291.337, | |
| "eval_steps_per_second": 4.876, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 630, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 525977876877312.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |