| { |
| "best_metric": 0.6069164872169495, |
| "best_model_checkpoint": "Ruster/checkpoint-498", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 498, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07228915662650602, |
| "grad_norm": 10.613821983337402, |
| "learning_rate": 1.2e-05, |
| "loss": 0.9401, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.14457831325301204, |
| "grad_norm": 6.847902297973633, |
| "learning_rate": 2.4e-05, |
| "loss": 0.4535, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.21686746987951808, |
| "grad_norm": 14.905878067016602, |
| "learning_rate": 3.6e-05, |
| "loss": 0.4731, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.2891566265060241, |
| "grad_norm": 5.860299587249756, |
| "learning_rate": 4.8e-05, |
| "loss": 0.3857, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.3614457831325301, |
| "grad_norm": 8.051860809326172, |
| "learning_rate": 4.888392857142857e-05, |
| "loss": 0.428, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.43373493975903615, |
| "grad_norm": 9.066169738769531, |
| "learning_rate": 4.7544642857142855e-05, |
| "loss": 0.3779, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.5060240963855421, |
| "grad_norm": 0.4762527346611023, |
| "learning_rate": 4.620535714285715e-05, |
| "loss": 0.3174, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.5783132530120482, |
| "grad_norm": 3.7264981269836426, |
| "learning_rate": 4.486607142857143e-05, |
| "loss": 0.3903, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.6506024096385542, |
| "grad_norm": 3.319960117340088, |
| "learning_rate": 4.352678571428572e-05, |
| "loss": 0.2664, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.7228915662650602, |
| "grad_norm": 8.442005157470703, |
| "learning_rate": 4.21875e-05, |
| "loss": 0.4303, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7951807228915663, |
| "grad_norm": 5.5674729347229, |
| "learning_rate": 4.084821428571429e-05, |
| "loss": 0.3758, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.8674698795180723, |
| "grad_norm": 5.097784042358398, |
| "learning_rate": 3.950892857142857e-05, |
| "loss": 0.4321, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.9397590361445783, |
| "grad_norm": 4.135376930236816, |
| "learning_rate": 3.816964285714286e-05, |
| "loss": 0.3334, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5683646112600537, |
| "eval_f1_macro": 0.34514324233232224, |
| "eval_f1_micro": 0.5683646112600537, |
| "eval_f1_weighted": 0.5027366446460666, |
| "eval_loss": 0.8362799286842346, |
| "eval_precision_macro": 0.4779331485680692, |
| "eval_precision_micro": 0.5683646112600537, |
| "eval_precision_weighted": 0.7304906422900805, |
| "eval_recall_macro": 0.40111757925912955, |
| "eval_recall_micro": 0.5683646112600537, |
| "eval_recall_weighted": 0.5683646112600537, |
| "eval_runtime": 197.9274, |
| "eval_samples_per_second": 3.769, |
| "eval_steps_per_second": 0.237, |
| "step": 249 |
| }, |
| { |
| "epoch": 1.0120481927710843, |
| "grad_norm": 2.6794259548187256, |
| "learning_rate": 3.683035714285715e-05, |
| "loss": 0.3526, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.0843373493975903, |
| "grad_norm": 2.575113296508789, |
| "learning_rate": 3.5491071428571435e-05, |
| "loss": 0.2409, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.1566265060240963, |
| "grad_norm": 20.131845474243164, |
| "learning_rate": 3.415178571428572e-05, |
| "loss": 0.57, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.2289156626506024, |
| "grad_norm": 1.7430191040039062, |
| "learning_rate": 3.2812500000000005e-05, |
| "loss": 0.2363, |
| "step": 306 |
| }, |
| { |
| "epoch": 1.3012048192771084, |
| "grad_norm": 2.6502227783203125, |
| "learning_rate": 3.147321428571428e-05, |
| "loss": 0.4027, |
| "step": 324 |
| }, |
| { |
| "epoch": 1.3734939759036144, |
| "grad_norm": 0.4510114789009094, |
| "learning_rate": 3.013392857142857e-05, |
| "loss": 0.1746, |
| "step": 342 |
| }, |
| { |
| "epoch": 1.4457831325301205, |
| "grad_norm": 1.9941872358322144, |
| "learning_rate": 2.8794642857142857e-05, |
| "loss": 0.3129, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.5180722891566265, |
| "grad_norm": 2.4119579792022705, |
| "learning_rate": 2.7455357142857145e-05, |
| "loss": 0.3607, |
| "step": 378 |
| }, |
| { |
| "epoch": 1.5903614457831325, |
| "grad_norm": 3.2550156116485596, |
| "learning_rate": 2.611607142857143e-05, |
| "loss": 0.2441, |
| "step": 396 |
| }, |
| { |
| "epoch": 1.6626506024096386, |
| "grad_norm": 1.5980372428894043, |
| "learning_rate": 2.4776785714285715e-05, |
| "loss": 0.2501, |
| "step": 414 |
| }, |
| { |
| "epoch": 1.7349397590361446, |
| "grad_norm": 7.059596538543701, |
| "learning_rate": 2.34375e-05, |
| "loss": 0.41, |
| "step": 432 |
| }, |
| { |
| "epoch": 1.8072289156626506, |
| "grad_norm": 1.7965036630630493, |
| "learning_rate": 2.2098214285714286e-05, |
| "loss": 0.323, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.8795180722891565, |
| "grad_norm": 7.194454669952393, |
| "learning_rate": 2.0758928571428574e-05, |
| "loss": 0.3068, |
| "step": 468 |
| }, |
| { |
| "epoch": 1.9518072289156625, |
| "grad_norm": 3.057166814804077, |
| "learning_rate": 1.941964285714286e-05, |
| "loss": 0.3792, |
| "step": 486 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7184986595174263, |
| "eval_f1_macro": 0.47612925723870253, |
| "eval_f1_micro": 0.7184986595174263, |
| "eval_f1_weighted": 0.7080336230828008, |
| "eval_loss": 0.6069164872169495, |
| "eval_precision_macro": 0.5134762379528083, |
| "eval_precision_micro": 0.7184986595174263, |
| "eval_precision_weighted": 0.7786303288525843, |
| "eval_recall_macro": 0.4920582814179348, |
| "eval_recall_micro": 0.7184986595174263, |
| "eval_recall_weighted": 0.7184986595174263, |
| "eval_runtime": 193.5156, |
| "eval_samples_per_second": 3.855, |
| "eval_steps_per_second": 0.243, |
| "step": 498 |
| } |
| ], |
| "logging_steps": 18, |
| "max_steps": 747, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 3.076459560786125e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
