| { | |
| "best_metric": 0.326568067073822, | |
| "best_model_checkpoint": "sep-20/checkpoint-184", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 184, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04891304347826087, | |
| "grad_norm": 6.508527755737305, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.9057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09782608695652174, | |
| "grad_norm": 6.560257434844971, | |
| "learning_rate": 4.736842105263158e-05, | |
| "loss": 0.4782, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14673913043478262, | |
| "grad_norm": 5.121021270751953, | |
| "learning_rate": 4.7575757575757576e-05, | |
| "loss": 0.3964, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1956521739130435, | |
| "grad_norm": 5.416026592254639, | |
| "learning_rate": 4.484848484848485e-05, | |
| "loss": 0.461, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.24456521739130435, | |
| "grad_norm": 3.697016716003418, | |
| "learning_rate": 4.212121212121212e-05, | |
| "loss": 0.6009, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29347826086956524, | |
| "grad_norm": 3.856910467147827, | |
| "learning_rate": 3.939393939393939e-05, | |
| "loss": 0.2506, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3423913043478261, | |
| "grad_norm": 14.140103340148926, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.396, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.391304347826087, | |
| "grad_norm": 4.570571422576904, | |
| "learning_rate": 3.3939393939393945e-05, | |
| "loss": 0.3124, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.44021739130434784, | |
| "grad_norm": 11.288423538208008, | |
| "learning_rate": 3.121212121212122e-05, | |
| "loss": 0.5017, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4891304347826087, | |
| "grad_norm": 10.446467399597168, | |
| "learning_rate": 2.8484848484848486e-05, | |
| "loss": 0.2368, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5380434782608695, | |
| "grad_norm": 1.5973994731903076, | |
| "learning_rate": 2.575757575757576e-05, | |
| "loss": 0.2517, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5869565217391305, | |
| "grad_norm": 0.7517912983894348, | |
| "learning_rate": 2.3030303030303034e-05, | |
| "loss": 0.571, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6358695652173914, | |
| "grad_norm": 7.41497278213501, | |
| "learning_rate": 2.0303030303030303e-05, | |
| "loss": 0.2846, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.6847826086956522, | |
| "grad_norm": 4.097425937652588, | |
| "learning_rate": 1.7575757575757576e-05, | |
| "loss": 0.4801, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7336956521739131, | |
| "grad_norm": 4.8678669929504395, | |
| "learning_rate": 1.484848484848485e-05, | |
| "loss": 0.3254, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 0.7251734733581543, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.1278, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.8315217391304348, | |
| "grad_norm": 10.660299301147461, | |
| "learning_rate": 9.393939393939394e-06, | |
| "loss": 0.5605, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.8804347826086957, | |
| "grad_norm": 0.7391616702079773, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.3178, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.9293478260869565, | |
| "grad_norm": 0.3952378034591675, | |
| "learning_rate": 3.939393939393939e-06, | |
| "loss": 0.3842, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.9782608695652174, | |
| "grad_norm": 5.111515522003174, | |
| "learning_rate": 1.2121212121212122e-06, | |
| "loss": 0.2226, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8994565217391305, | |
| "eval_f1_macro": 0.574992771283407, | |
| "eval_f1_micro": 0.8994565217391305, | |
| "eval_f1_weighted": 0.8962362631935303, | |
| "eval_loss": 0.326568067073822, | |
| "eval_precision_macro": 0.5852941598199051, | |
| "eval_precision_micro": 0.8994565217391305, | |
| "eval_precision_weighted": 0.8948775064010129, | |
| "eval_recall_macro": 0.566717099325795, | |
| "eval_recall_micro": 0.8994565217391305, | |
| "eval_recall_weighted": 0.8994565217391305, | |
| "eval_runtime": 108.1675, | |
| "eval_samples_per_second": 3.402, | |
| "eval_steps_per_second": 0.213, | |
| "step": 184 | |
| } | |
| ], | |
| "logging_steps": 9, | |
| "max_steps": 184, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.138367530175017e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |