| { | |
| "best_metric": 2.303269863128662, | |
| "best_model_checkpoint": "autotrain-x03ts-qcf7e/checkpoint-435", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 435, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 6.1133551597595215, | |
| "learning_rate": 2.8409090909090912e-05, | |
| "loss": 3.4255, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 8.178117752075195, | |
| "learning_rate": 4.923273657289003e-05, | |
| "loss": 3.0089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 6.662604808807373, | |
| "learning_rate": 4.603580562659847e-05, | |
| "loss": 2.825, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 9.514023780822754, | |
| "learning_rate": 4.283887468030691e-05, | |
| "loss": 2.8092, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 11.465914726257324, | |
| "learning_rate": 3.964194373401535e-05, | |
| "loss": 2.9111, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.28484848484848485, | |
| "eval_f1_macro": 0.013436249285305889, | |
| "eval_f1_micro": 0.28484848484848485, | |
| "eval_f1_weighted": 0.12630074328187538, | |
| "eval_loss": 2.676663398742676, | |
| "eval_precision_macro": 0.008631772268135905, | |
| "eval_precision_micro": 0.28484848484848485, | |
| "eval_precision_weighted": 0.08113865932047751, | |
| "eval_recall_macro": 0.030303030303030304, | |
| "eval_recall_micro": 0.28484848484848485, | |
| "eval_recall_weighted": 0.28484848484848485, | |
| "eval_runtime": 255.7518, | |
| "eval_samples_per_second": 4.516, | |
| "eval_steps_per_second": 0.285, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 6.465944766998291, | |
| "learning_rate": 3.644501278772379e-05, | |
| "loss": 2.5956, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.206896551724138, | |
| "grad_norm": 8.603558540344238, | |
| "learning_rate": 3.324808184143223e-05, | |
| "loss": 2.6285, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 8.11929702758789, | |
| "learning_rate": 3.0051150895140666e-05, | |
| "loss": 2.6964, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5517241379310345, | |
| "grad_norm": 7.409820556640625, | |
| "learning_rate": 2.6854219948849106e-05, | |
| "loss": 2.7531, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 7.499230861663818, | |
| "learning_rate": 2.3657289002557546e-05, | |
| "loss": 2.5273, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.896551724137931, | |
| "grad_norm": 14.026644706726074, | |
| "learning_rate": 2.0460358056265986e-05, | |
| "loss": 2.5975, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3064935064935065, | |
| "eval_f1_macro": 0.028228053192069863, | |
| "eval_f1_micro": 0.3064935064935065, | |
| "eval_f1_weighted": 0.23352329691937518, | |
| "eval_loss": 2.477508544921875, | |
| "eval_precision_macro": 0.02386167652983027, | |
| "eval_precision_micro": 0.3064935064935065, | |
| "eval_precision_weighted": 0.2057449099744913, | |
| "eval_recall_macro": 0.04448079579994474, | |
| "eval_recall_micro": 0.3064935064935065, | |
| "eval_recall_weighted": 0.3064935064935065, | |
| "eval_runtime": 256.8636, | |
| "eval_samples_per_second": 4.497, | |
| "eval_steps_per_second": 0.284, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 8.43802547454834, | |
| "learning_rate": 1.7263427109974426e-05, | |
| "loss": 2.7131, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.2413793103448274, | |
| "grad_norm": 11.071104049682617, | |
| "learning_rate": 1.4066496163682865e-05, | |
| "loss": 2.4292, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.413793103448276, | |
| "grad_norm": 7.782072067260742, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 2.3514, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 12.599653244018555, | |
| "learning_rate": 7.672634271099745e-06, | |
| "loss": 2.4591, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 8.950291633605957, | |
| "learning_rate": 4.475703324808185e-06, | |
| "loss": 2.3889, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.9310344827586206, | |
| "grad_norm": 8.916004180908203, | |
| "learning_rate": 1.2787723785166241e-06, | |
| "loss": 2.3493, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3367965367965368, | |
| "eval_f1_macro": 0.040508170738823165, | |
| "eval_f1_micro": 0.3367965367965368, | |
| "eval_f1_weighted": 0.2413478397672539, | |
| "eval_loss": 2.303269863128662, | |
| "eval_precision_macro": 0.0434917012251169, | |
| "eval_precision_micro": 0.3367965367965368, | |
| "eval_precision_weighted": 0.21644678791353103, | |
| "eval_recall_macro": 0.05803911531326899, | |
| "eval_recall_micro": 0.3367965367965368, | |
| "eval_recall_weighted": 0.3367965367965368, | |
| "eval_runtime": 261.9634, | |
| "eval_samples_per_second": 4.409, | |
| "eval_steps_per_second": 0.279, | |
| "step": 435 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 435, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 227987477625600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |