| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003600110772639158, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027693159789531985, | |
| "eval_loss": 6.243055820465088, | |
| "eval_runtime": 457.8006, | |
| "eval_samples_per_second": 13.285, | |
| "eval_steps_per_second": 1.662, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008307947936859596, | |
| "grad_norm": 27.681867599487305, | |
| "learning_rate": 3e-05, | |
| "loss": 24.6744, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001661589587371919, | |
| "grad_norm": 27.828317642211914, | |
| "learning_rate": 6e-05, | |
| "loss": 22.5088, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0024923843810578787, | |
| "grad_norm": 29.053722381591797, | |
| "learning_rate": 9e-05, | |
| "loss": 17.9623, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003323179174743838, | |
| "grad_norm": 19.01649284362793, | |
| "learning_rate": 9.994965332706573e-05, | |
| "loss": 11.8099, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003600110772639158, | |
| "eval_loss": 1.6348825693130493, | |
| "eval_runtime": 460.8045, | |
| "eval_samples_per_second": 13.199, | |
| "eval_steps_per_second": 1.651, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0622684501049344e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |