| { | |
| "best_global_step": 2700, | |
| "best_metric": 0.943944556401453, | |
| "best_model_checkpoint": "./results_best_model_params_no_weigths/checkpoint-2700", | |
| "epoch": 9.0, | |
| "eval_steps": 500, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 18.45217514038086, | |
| "learning_rate": 2.392e-05, | |
| "loss": 2.1554, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.68, | |
| "eval_f1": 0.6299231487466781, | |
| "eval_loss": 0.9896876811981201, | |
| "eval_precision": 0.596127184632728, | |
| "eval_recall": 0.68, | |
| "eval_runtime": 1.0363, | |
| "eval_samples_per_second": 289.493, | |
| "eval_steps_per_second": 36.669, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 6.290977954864502, | |
| "learning_rate": 3.989942676395768e-05, | |
| "loss": 0.7249, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8066666666666666, | |
| "eval_f1": 0.7980187651781466, | |
| "eval_loss": 0.6141381859779358, | |
| "eval_precision": 0.7997331959114482, | |
| "eval_recall": 0.8066666666666666, | |
| "eval_runtime": 1.0504, | |
| "eval_samples_per_second": 285.609, | |
| "eval_steps_per_second": 36.177, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 28.53618812561035, | |
| "learning_rate": 3.838713973164638e-05, | |
| "loss": 0.3192, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8566666666666667, | |
| "eval_f1": 0.8396115070833731, | |
| "eval_loss": 0.5440802574157715, | |
| "eval_precision": 0.8610586080586082, | |
| "eval_recall": 0.8566666666666667, | |
| "eval_runtime": 1.0377, | |
| "eval_samples_per_second": 289.091, | |
| "eval_steps_per_second": 36.618, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.3678171932697296, | |
| "learning_rate": 3.518835689779606e-05, | |
| "loss": 0.1273, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9233333333333333, | |
| "eval_f1": 0.9187730445322131, | |
| "eval_loss": 0.4262033700942993, | |
| "eval_precision": 0.9255803144224196, | |
| "eval_recall": 0.9233333333333333, | |
| "eval_runtime": 1.0705, | |
| "eval_samples_per_second": 280.245, | |
| "eval_steps_per_second": 35.498, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.2233057022094727, | |
| "learning_rate": 3.059647538115699e-05, | |
| "loss": 0.0405, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.93, | |
| "eval_f1": 0.9268536796946368, | |
| "eval_loss": 0.44284963607788086, | |
| "eval_precision": 0.9333637444644907, | |
| "eval_recall": 0.93, | |
| "eval_runtime": 1.0417, | |
| "eval_samples_per_second": 287.993, | |
| "eval_steps_per_second": 36.479, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.008498436771333218, | |
| "learning_rate": 2.503266938348105e-05, | |
| "loss": 0.0212, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9166666666666666, | |
| "eval_f1": 0.9130346842305932, | |
| "eval_loss": 0.47316548228263855, | |
| "eval_precision": 0.9186028198606908, | |
| "eval_recall": 0.9166666666666666, | |
| "eval_runtime": 1.0333, | |
| "eval_samples_per_second": 290.331, | |
| "eval_steps_per_second": 36.775, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.016181306913495064, | |
| "learning_rate": 1.9007259465366814e-05, | |
| "loss": 0.0054, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9366666666666666, | |
| "eval_f1": 0.9344433709071391, | |
| "eval_loss": 0.4463816285133362, | |
| "eval_precision": 0.9359492511767221, | |
| "eval_recall": 0.9366666666666666, | |
| "eval_runtime": 1.0605, | |
| "eval_samples_per_second": 282.89, | |
| "eval_steps_per_second": 35.833, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.033235203474760056, | |
| "learning_rate": 1.3072905185492762e-05, | |
| "loss": 0.0092, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.94, | |
| "eval_f1": 0.9370771508185302, | |
| "eval_loss": 0.46151891350746155, | |
| "eval_precision": 0.9371753391213078, | |
| "eval_recall": 0.94, | |
| "eval_runtime": 1.0476, | |
| "eval_samples_per_second": 286.362, | |
| "eval_steps_per_second": 36.272, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.04196559265255928, | |
| "learning_rate": 7.773914343980036e-06, | |
| "loss": 0.0006, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9466666666666667, | |
| "eval_f1": 0.943944556401453, | |
| "eval_loss": 0.4482668936252594, | |
| "eval_precision": 0.9442854589498741, | |
| "eval_recall": 0.9466666666666667, | |
| "eval_runtime": 1.0461, | |
| "eval_samples_per_second": 286.783, | |
| "eval_steps_per_second": 36.326, | |
| "step": 2700 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 577271014162800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |