| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04296455424274973, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 12.051056861877441, | |
| "learning_rate": 1e-05, | |
| "loss": 14.6953, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 14.64533805847168, | |
| "eval_runtime": 63.6842, | |
| "eval_samples_per_second": 3.078, | |
| "eval_steps_per_second": 1.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 12.647685050964355, | |
| "learning_rate": 2e-05, | |
| "loss": 14.4343, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "eval_loss": 14.304277420043945, | |
| "eval_runtime": 11.4061, | |
| "eval_samples_per_second": 17.184, | |
| "eval_steps_per_second": 8.592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 9.809382438659668, | |
| "learning_rate": 3e-05, | |
| "loss": 14.3006, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 8.627123832702637, | |
| "learning_rate": 4e-05, | |
| "loss": 13.9773, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "eval_loss": 13.759343147277832, | |
| "eval_runtime": 11.3254, | |
| "eval_samples_per_second": 17.306, | |
| "eval_steps_per_second": 8.653, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 8.462392807006836, | |
| "learning_rate": 5e-05, | |
| "loss": 13.6344, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |