| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001101513663359066, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.6717122111968867e-05, | |
| "eval_loss": 3.2656073570251465, | |
| "eval_runtime": 1460.1195, | |
| "eval_samples_per_second": 7.854, | |
| "eval_steps_per_second": 3.927, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011015136633590659, | |
| "grad_norm": 5.594817161560059, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022030273267181319, | |
| "grad_norm": 5.5571393966674805, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00029373697689575093, | |
| "eval_loss": 1.1682640314102173, | |
| "eval_runtime": 1465.6652, | |
| "eval_samples_per_second": 7.824, | |
| "eval_steps_per_second": 3.912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00033045409900771977, | |
| "grad_norm": 3.6698296070098877, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6419, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00044060546534362637, | |
| "grad_norm": 7.199770927429199, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.877, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000550756831679533, | |
| "grad_norm": 2.474736452102661, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7117, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005874739537915019, | |
| "eval_loss": 0.5969021916389465, | |
| "eval_runtime": 1466.0408, | |
| "eval_samples_per_second": 7.822, | |
| "eval_steps_per_second": 3.911, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006609081980154395, | |
| "grad_norm": 2.2165749073028564, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.5978, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007710595643513462, | |
| "grad_norm": 2.09437894821167, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.5218, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008812109306872527, | |
| "grad_norm": 2.8492116928100586, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.3608, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008812109306872527, | |
| "eval_loss": 0.5038470029830933, | |
| "eval_runtime": 1465.3643, | |
| "eval_samples_per_second": 7.826, | |
| "eval_steps_per_second": 3.913, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009913622970231593, | |
| "grad_norm": 2.557734727859497, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.4596, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001101513663359066, | |
| "grad_norm": 1.8476332426071167, | |
| "learning_rate": 0.0, | |
| "loss": 0.4065, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |