| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.1428571428571428, | |
| "eval_steps": 1, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.6347044110298157, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "eval_loss": 1.1075571775436401, | |
| "eval_runtime": 0.136, | |
| "eval_samples_per_second": 14.707, | |
| "eval_steps_per_second": 7.354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.8404815196990967, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1995, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "eval_loss": 1.1097619533538818, | |
| "eval_runtime": 0.1358, | |
| "eval_samples_per_second": 14.732, | |
| "eval_steps_per_second": 7.366, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.661170482635498, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1462, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "eval_loss": 1.094909906387329, | |
| "eval_runtime": 0.1365, | |
| "eval_samples_per_second": 14.656, | |
| "eval_steps_per_second": 7.328, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.031323790550232, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7308, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "eval_loss": 1.0933914184570312, | |
| "eval_runtime": 0.1364, | |
| "eval_samples_per_second": 14.661, | |
| "eval_steps_per_second": 7.331, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1528873133015040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |