| { | |
| "best_metric": 1.3449772596359253, | |
| "best_model_checkpoint": "/kaggle/working/checkpoint-40", | |
| "epoch": 4.444444444444445, | |
| "eval_steps": 10, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.022282764315605164, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 2.0424, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "eval_loss": 1.733155369758606, | |
| "eval_runtime": 34.5543, | |
| "eval_samples_per_second": 1.042, | |
| "eval_steps_per_second": 0.145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.018981408327817917, | |
| "learning_rate": 0.00017037037037037037, | |
| "loss": 1.6072, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "eval_loss": 1.5428930521011353, | |
| "eval_runtime": 34.6485, | |
| "eval_samples_per_second": 1.039, | |
| "eval_steps_per_second": 0.144, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.023157037794589996, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 1.4025, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "eval_loss": 1.4176721572875977, | |
| "eval_runtime": 34.5433, | |
| "eval_samples_per_second": 1.042, | |
| "eval_steps_per_second": 0.145, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.021338749676942825, | |
| "learning_rate": 0.00014074074074074076, | |
| "loss": 1.285, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "eval_loss": 1.3449772596359253, | |
| "eval_runtime": 34.5594, | |
| "eval_samples_per_second": 1.042, | |
| "eval_steps_per_second": 0.145, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 135, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "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": 1.0684017993449472e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |