| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005457522284882663, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018191740949608878, | |
| "eval_loss": 1.5300930738449097, | |
| "eval_runtime": 140.9104, | |
| "eval_samples_per_second": 16.429, | |
| "eval_steps_per_second": 8.218, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005457522284882663, | |
| "grad_norm": 0.7019155621528625, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7446, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010915044569765327, | |
| "grad_norm": 0.6890488266944885, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014553392759687103, | |
| "eval_loss": 1.2593938112258911, | |
| "eval_runtime": 139.2446, | |
| "eval_samples_per_second": 16.625, | |
| "eval_steps_per_second": 8.316, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001637256685464799, | |
| "grad_norm": 0.5408034920692444, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0539, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021830089139530653, | |
| "grad_norm": 0.4784094989299774, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.2728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0027287611424413314, | |
| "grad_norm": 0.7204845547676086, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0029106785519374206, | |
| "eval_loss": 1.0660419464111328, | |
| "eval_runtime": 139.5658, | |
| "eval_samples_per_second": 16.587, | |
| "eval_steps_per_second": 8.297, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003274513370929598, | |
| "grad_norm": 0.5934667587280273, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.867, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003820265599417864, | |
| "grad_norm": 0.705151379108429, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.0354, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004366017827906131, | |
| "grad_norm": 0.6639145016670227, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.1883, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004366017827906131, | |
| "eval_loss": 1.0460615158081055, | |
| "eval_runtime": 139.4569, | |
| "eval_samples_per_second": 16.6, | |
| "eval_steps_per_second": 8.304, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004911770056394397, | |
| "grad_norm": 0.5988746881484985, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0386, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005457522284882663, | |
| "grad_norm": 0.5009585022926331, | |
| "learning_rate": 0.0, | |
| "loss": 0.8725, | |
| "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": 1.1870196536967168e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |