| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013733905579399141, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027467811158798285, | |
| "grad_norm": 2.970282793045044, | |
| "learning_rate": 1e-05, | |
| "loss": 3.7627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027467811158798285, | |
| "eval_loss": 3.8651254177093506, | |
| "eval_runtime": 52.0509, | |
| "eval_samples_per_second": 11.796, | |
| "eval_steps_per_second": 5.898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005493562231759657, | |
| "grad_norm": 2.7814884185791016, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9638, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005493562231759657, | |
| "eval_loss": 3.798861503601074, | |
| "eval_runtime": 6.2913, | |
| "eval_samples_per_second": 97.596, | |
| "eval_steps_per_second": 48.798, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008240343347639486, | |
| "grad_norm": 2.901226282119751, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7123, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010987124463519314, | |
| "grad_norm": 2.9844248294830322, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7242, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010987124463519314, | |
| "eval_loss": 3.700958728790283, | |
| "eval_runtime": 6.4961, | |
| "eval_samples_per_second": 94.518, | |
| "eval_steps_per_second": 47.259, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013733905579399141, | |
| "grad_norm": 2.8463168144226074, | |
| "learning_rate": 5e-05, | |
| "loss": 3.715, | |
| "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": 648596517027840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |