| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0526315789473684, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14736842105263157, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18947368421052632, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23157894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2736842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.29473684210526313, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.35789473684210527, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.37894736842105264, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4421052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4842105263157895, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5473684210526316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5684210526315789, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6105263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6526315789473685, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6947368421052632, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7157894736842105, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7789473684210526, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8210526315789474, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8631578947368421, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8842105263157894, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9052631578947369, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.968421052631579, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9894736842105263, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9894736842105263, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.1467, | |
| "eval_samples_per_second": 4.373, | |
| "eval_steps_per_second": 2.187, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0105263157894737, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0315789473684212, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.03129901334528e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |