| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 100, | |
| "global_step": 471, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6369426751592356, | |
| "grad_norm": 11.424042701721191, | |
| "learning_rate": 2.617862969670073e-05, | |
| "loss": 3.8796, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6369426751592356, | |
| "eval_loss": 2.8795037269592285, | |
| "eval_runtime": 3.5583, | |
| "eval_samples_per_second": 140.515, | |
| "eval_steps_per_second": 4.496, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2738853503184713, | |
| "grad_norm": 13.521265029907227, | |
| "learning_rate": 1.9122395277104845e-05, | |
| "loss": 2.306, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2738853503184713, | |
| "eval_loss": 1.97040593624115, | |
| "eval_runtime": 3.6094, | |
| "eval_samples_per_second": 138.528, | |
| "eval_steps_per_second": 4.433, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.910828025477707, | |
| "grad_norm": 16.13125228881836, | |
| "learning_rate": 1.206616085750896e-05, | |
| "loss": 1.6392, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.910828025477707, | |
| "eval_loss": 1.7181620597839355, | |
| "eval_runtime": 3.5951, | |
| "eval_samples_per_second": 139.079, | |
| "eval_steps_per_second": 4.451, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.5477707006369426, | |
| "grad_norm": 11.650218963623047, | |
| "learning_rate": 5.009926437913077e-06, | |
| "loss": 1.2706, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.5477707006369426, | |
| "eval_loss": 1.7209367752075195, | |
| "eval_runtime": 3.5763, | |
| "eval_samples_per_second": 139.808, | |
| "eval_steps_per_second": 4.474, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 471, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1249566248706048.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.323486411629661e-05, | |
| "num_train_epochs": 3, | |
| "per_device_train_batch_size": 16, | |
| "seed": 28 | |
| } | |
| } | |