| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002373675933893125, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047473518677862507, | |
| "grad_norm": 0.6019813418388367, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047473518677862507, | |
| "eval_loss": 1.0513094663619995, | |
| "eval_runtime": 739.5377, | |
| "eval_samples_per_second": 4.798, | |
| "eval_steps_per_second": 2.399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009494703735572501, | |
| "grad_norm": 0.6246649622917175, | |
| "learning_rate": 2e-05, | |
| "loss": 1.15, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009494703735572501, | |
| "eval_loss": 1.028988003730774, | |
| "eval_runtime": 352.9218, | |
| "eval_samples_per_second": 10.053, | |
| "eval_steps_per_second": 5.027, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014242055603358751, | |
| "grad_norm": 0.631195068359375, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1129, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018989407471145003, | |
| "grad_norm": 0.6286895275115967, | |
| "learning_rate": 4e-05, | |
| "loss": 1.044, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018989407471145003, | |
| "eval_loss": 1.0063300132751465, | |
| "eval_runtime": 319.2481, | |
| "eval_samples_per_second": 11.114, | |
| "eval_steps_per_second": 5.557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002373675933893125, | |
| "grad_norm": 0.6102349162101746, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0684, | |
| "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": 3485272092180480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |