| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026307135810588623, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005261427162117725, | |
| "grad_norm": 2.529688835144043, | |
| "learning_rate": 1e-05, | |
| "loss": 7.5013, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005261427162117725, | |
| "eval_loss": 7.8158159255981445, | |
| "eval_runtime": 57.0266, | |
| "eval_samples_per_second": 5.629, | |
| "eval_steps_per_second": 2.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01052285432423545, | |
| "grad_norm": 2.497180461883545, | |
| "learning_rate": 2e-05, | |
| "loss": 7.4303, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01052285432423545, | |
| "eval_loss": 7.8128485679626465, | |
| "eval_runtime": 3.8252, | |
| "eval_samples_per_second": 83.917, | |
| "eval_steps_per_second": 42.089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015784281486353174, | |
| "grad_norm": 2.205127239227295, | |
| "learning_rate": 3e-05, | |
| "loss": 7.4777, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0210457086484709, | |
| "grad_norm": 1.7184529304504395, | |
| "learning_rate": 4e-05, | |
| "loss": 7.8477, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0210457086484709, | |
| "eval_loss": 7.808534622192383, | |
| "eval_runtime": 3.8677, | |
| "eval_samples_per_second": 82.996, | |
| "eval_steps_per_second": 41.627, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.026307135810588623, | |
| "grad_norm": 2.3148210048675537, | |
| "learning_rate": 5e-05, | |
| "loss": 7.551, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2179821600768.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |