| { | |
| "best_metric": 0.6081525683403015, | |
| "best_model_checkpoint": "autotrain-cwa7t-r6nu7/checkpoint-500", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 5.120242118835449, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.077, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 3.48054838180542, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 1.0941, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 4.692188262939453, | |
| "learning_rate": 1.44e-05, | |
| "loss": 1.0877, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 4.942972183227539, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.0566, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 10.25078296661377, | |
| "learning_rate": 2.36e-05, | |
| "loss": 0.9183, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 25.465534210205078, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.9146, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 21.620311737060547, | |
| "learning_rate": 3.2800000000000004e-05, | |
| "loss": 0.8352, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 12.405364036560059, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.8715, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 20.498157501220703, | |
| "learning_rate": 4.24e-05, | |
| "loss": 0.7661, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 14.002096176147461, | |
| "learning_rate": 4.72e-05, | |
| "loss": 0.6987, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 15.950400352478027, | |
| "learning_rate": 4.977777777777778e-05, | |
| "loss": 0.7478, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 14.89918327331543, | |
| "learning_rate": 4.928888888888889e-05, | |
| "loss": 0.8167, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 21.52458381652832, | |
| "learning_rate": 4.875555555555556e-05, | |
| "loss": 0.8677, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 9.06266975402832, | |
| "learning_rate": 4.8222222222222225e-05, | |
| "loss": 0.7637, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 17.687030792236328, | |
| "learning_rate": 4.768888888888889e-05, | |
| "loss": 0.7588, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 18.937341690063477, | |
| "learning_rate": 4.715555555555556e-05, | |
| "loss": 0.7809, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 20.595829010009766, | |
| "learning_rate": 4.662222222222222e-05, | |
| "loss": 0.6525, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 14.021669387817383, | |
| "learning_rate": 4.608888888888889e-05, | |
| "loss": 0.7512, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 17.159658432006836, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.6444, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 15.096858978271484, | |
| "learning_rate": 4.502222222222223e-05, | |
| "loss": 0.7502, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7367367367367368, | |
| "eval_f1_macro": 0.6780399587593059, | |
| "eval_f1_micro": 0.7367367367367368, | |
| "eval_f1_weighted": 0.7159182064227351, | |
| "eval_loss": 0.7116303443908691, | |
| "eval_precision_macro": 0.7407168006456986, | |
| "eval_precision_micro": 0.7367367367367368, | |
| "eval_precision_weighted": 0.738750739597193, | |
| "eval_recall_macro": 0.6747808186254532, | |
| "eval_recall_micro": 0.7367367367367368, | |
| "eval_recall_weighted": 0.7367367367367368, | |
| "eval_runtime": 1.2649, | |
| "eval_samples_per_second": 789.799, | |
| "eval_steps_per_second": 25.299, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 3.268965244293213, | |
| "learning_rate": 4.448888888888889e-05, | |
| "loss": 0.6109, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 9.524105072021484, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6676, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 13.357897758483887, | |
| "learning_rate": 4.346666666666667e-05, | |
| "loss": 0.6534, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 12.989001274108887, | |
| "learning_rate": 4.293333333333334e-05, | |
| "loss": 0.5564, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 13.040504455566406, | |
| "learning_rate": 4.24e-05, | |
| "loss": 0.5432, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 27.441036224365234, | |
| "learning_rate": 4.186666666666667e-05, | |
| "loss": 0.5495, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 12.519679069519043, | |
| "learning_rate": 4.133333333333333e-05, | |
| "loss": 0.548, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 19.905864715576172, | |
| "learning_rate": 4.08e-05, | |
| "loss": 0.7036, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 19.19709014892578, | |
| "learning_rate": 4.026666666666667e-05, | |
| "loss": 0.6243, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 25.307151794433594, | |
| "learning_rate": 3.9733333333333335e-05, | |
| "loss": 0.5592, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 12.860663414001465, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.5251, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 14.503999710083008, | |
| "learning_rate": 3.866666666666667e-05, | |
| "loss": 0.5004, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 16.512439727783203, | |
| "learning_rate": 3.8133333333333336e-05, | |
| "loss": 0.5418, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 10.380609512329102, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.6202, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 14.396175384521484, | |
| "learning_rate": 3.706666666666667e-05, | |
| "loss": 0.6095, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 15.407332420349121, | |
| "learning_rate": 3.653333333333334e-05, | |
| "loss": 0.6155, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 21.06899642944336, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.5009, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 9.709734916687012, | |
| "learning_rate": 3.546666666666667e-05, | |
| "loss": 0.4664, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 30.69609260559082, | |
| "learning_rate": 3.493333333333333e-05, | |
| "loss": 0.6268, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 10.711507797241211, | |
| "learning_rate": 3.4399999999999996e-05, | |
| "loss": 0.5064, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 10.850369453430176, | |
| "learning_rate": 3.3866666666666665e-05, | |
| "loss": 0.5403, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7567567567567568, | |
| "eval_f1_macro": 0.7293016589919367, | |
| "eval_f1_micro": 0.7567567567567568, | |
| "eval_f1_weighted": 0.7525753769969824, | |
| "eval_loss": 0.6081525683403015, | |
| "eval_precision_macro": 0.7459781321674904, | |
| "eval_precision_micro": 0.7567567567567568, | |
| "eval_precision_weighted": 0.7607241180619724, | |
| "eval_recall_macro": 0.727181992488115, | |
| "eval_recall_micro": 0.7567567567567568, | |
| "eval_recall_weighted": 0.7567567567567568, | |
| "eval_runtime": 1.2636, | |
| "eval_samples_per_second": 790.605, | |
| "eval_steps_per_second": 25.325, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 12, | |
| "max_steps": 1250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 525305938493952.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |