| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.044444444444444446, | |
| "eval_steps": 8, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022222222222222222, | |
| "eval_loss": 13.0014009475708, | |
| "eval_runtime": 3.0603, | |
| "eval_samples_per_second": 62.086, | |
| "eval_steps_per_second": 31.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006666666666666667, | |
| "grad_norm": 33.16307830810547, | |
| "learning_rate": 6e-05, | |
| "loss": 12.9448, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013333333333333334, | |
| "grad_norm": 23.923620223999023, | |
| "learning_rate": 0.00012, | |
| "loss": 12.6366, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "eval_loss": 11.761878967285156, | |
| "eval_runtime": 3.0443, | |
| "eval_samples_per_second": 62.412, | |
| "eval_steps_per_second": 31.206, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 15.053801536560059, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9302, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 7.928261756896973, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.3322, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 9.614800453186035, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.8628, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "eval_loss": 10.506447792053223, | |
| "eval_runtime": 3.0689, | |
| "eval_samples_per_second": 61.912, | |
| "eval_steps_per_second": 30.956, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 5.540660858154297, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.5127, | |
| "step": 18 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5328093315072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |