| { | |
| "best_metric": 0.5204629898071289, | |
| "best_model_checkpoint": "autotrain/checkpoint-485", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 485, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.049484536082474224, | |
| "grad_norm": 13.852910041809082, | |
| "learning_rate": 8.21917808219178e-06, | |
| "loss": 0.9486, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09896907216494845, | |
| "grad_norm": 13.40283203125, | |
| "learning_rate": 1.643835616438356e-05, | |
| "loss": 0.7154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14845360824742268, | |
| "grad_norm": 24.096817016601562, | |
| "learning_rate": 2.4657534246575342e-05, | |
| "loss": 0.4573, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1979381443298969, | |
| "grad_norm": 8.489076614379883, | |
| "learning_rate": 3.287671232876712e-05, | |
| "loss": 0.6314, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 23.408002853393555, | |
| "learning_rate": 4.1095890410958905e-05, | |
| "loss": 0.446, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.29690721649484536, | |
| "grad_norm": 89.99927520751953, | |
| "learning_rate": 4.9315068493150684e-05, | |
| "loss": 0.4341, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3463917525773196, | |
| "grad_norm": 17.79033851623535, | |
| "learning_rate": 4.9159663865546216e-05, | |
| "loss": 0.6628, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.3958762886597938, | |
| "grad_norm": 21.725704193115234, | |
| "learning_rate": 4.8242933537051186e-05, | |
| "loss": 0.6229, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.44536082474226807, | |
| "grad_norm": 7.025701522827148, | |
| "learning_rate": 4.732620320855615e-05, | |
| "loss": 0.3756, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.4948453608247423, | |
| "grad_norm": 7.281248569488525, | |
| "learning_rate": 4.6409472880061113e-05, | |
| "loss": 0.453, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5443298969072164, | |
| "grad_norm": 5.907578468322754, | |
| "learning_rate": 4.5492742551566084e-05, | |
| "loss": 0.5642, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.5938144329896907, | |
| "grad_norm": 23.55532455444336, | |
| "learning_rate": 4.4576012223071054e-05, | |
| "loss": 0.3995, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.643298969072165, | |
| "grad_norm": 34.66104507446289, | |
| "learning_rate": 4.365928189457602e-05, | |
| "loss": 0.4468, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.6927835051546392, | |
| "grad_norm": 24.519365310668945, | |
| "learning_rate": 4.274255156608098e-05, | |
| "loss": 0.4816, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.7422680412371134, | |
| "grad_norm": 5.479645729064941, | |
| "learning_rate": 4.1825821237585944e-05, | |
| "loss": 0.482, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7917525773195876, | |
| "grad_norm": 15.753713607788086, | |
| "learning_rate": 4.0909090909090915e-05, | |
| "loss": 0.4679, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.8412371134020619, | |
| "grad_norm": 16.035234451293945, | |
| "learning_rate": 3.999236058059588e-05, | |
| "loss": 0.469, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.8907216494845361, | |
| "grad_norm": 13.605697631835938, | |
| "learning_rate": 3.907563025210084e-05, | |
| "loss": 0.3936, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.9402061855670103, | |
| "grad_norm": 5.289237976074219, | |
| "learning_rate": 3.8158899923605805e-05, | |
| "loss": 0.4539, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.9896907216494846, | |
| "grad_norm": 6.887050151824951, | |
| "learning_rate": 3.724216959511077e-05, | |
| "loss": 0.4396, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8391752577319588, | |
| "eval_f1_macro": 0.8248638325526141, | |
| "eval_f1_micro": 0.8391752577319588, | |
| "eval_f1_weighted": 0.8401728559000128, | |
| "eval_loss": 0.5204629898071289, | |
| "eval_precision_macro": 0.8043237511636941, | |
| "eval_precision_micro": 0.8391752577319588, | |
| "eval_precision_weighted": 0.845019702890122, | |
| "eval_recall_macro": 0.853526208639845, | |
| "eval_recall_micro": 0.8391752577319588, | |
| "eval_recall_weighted": 0.8391752577319588, | |
| "eval_runtime": 97.441, | |
| "eval_samples_per_second": 9.955, | |
| "eval_steps_per_second": 0.626, | |
| "step": 485 | |
| } | |
| ], | |
| "logging_steps": 24, | |
| "max_steps": 1455, | |
| "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": 128363198432256.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |