| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.018473914863755117, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1596, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.01958436031595016, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1592, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.018997349295490185, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1581, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.019098244798499944, | |
| "learning_rate": 4.980286753286195e-05, | |
| "loss": 0.1618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.01986014761183824, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 0.1597, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.026066687910980477, | |
| "learning_rate": 4.8244412147206284e-05, | |
| "loss": 0.1632, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.033262521534120314, | |
| "learning_rate": 4.690766700109659e-05, | |
| "loss": 0.1501, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.034303061725366304, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.1453, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 0.028929042166310412, | |
| "learning_rate": 4.3224215685535294e-05, | |
| "loss": 0.1429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.024596477972911673, | |
| "learning_rate": 4.093559974371725e-05, | |
| "loss": 0.1389, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 0.02095523145172841, | |
| "learning_rate": 3.8395669874474915e-05, | |
| "loss": 0.1403, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.018521244081732214, | |
| "learning_rate": 3.564448228912682e-05, | |
| "loss": 0.131, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 0.019389700999808326, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.1275, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.018717414460688725, | |
| "learning_rate": 2.9684532864643122e-05, | |
| "loss": 0.1267, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.0714285714285714, | |
| "grad_norm": 0.20910676825639798, | |
| "learning_rate": 2.656976298823284e-05, | |
| "loss": 0.1499, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.17013123112157438, | |
| "learning_rate": 2.3430237011767167e-05, | |
| "loss": 0.143, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.2142857142857142, | |
| "grad_norm": 0.15401200255113412, | |
| "learning_rate": 2.031546713535688e-05, | |
| "loss": 0.1358, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.10539625737893336, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.1238, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.3571428571428572, | |
| "grad_norm": 0.0851408863484842, | |
| "learning_rate": 1.4355517710873184e-05, | |
| "loss": 0.1161, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.06421811377219377, | |
| "learning_rate": 1.1604330125525079e-05, | |
| "loss": 0.1107, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.04679299115412706, | |
| "learning_rate": 9.064400256282757e-06, | |
| "loss": 0.1091, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.04496230116925608, | |
| "learning_rate": 6.775784314464717e-06, | |
| "loss": 0.1136, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.6428571428571428, | |
| "grad_norm": 0.03819673601799427, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.1082, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.0347997372216549, | |
| "learning_rate": 3.092332998903416e-06, | |
| "loss": 0.1125, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 0.03227529902193574, | |
| "learning_rate": 1.7555878527937164e-06, | |
| "loss": 0.1064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.029351357581022388, | |
| "learning_rate": 7.854209717842231e-07, | |
| "loss": 0.1041, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.9285714285714286, | |
| "grad_norm": 0.0326274405504393, | |
| "learning_rate": 1.9713246713805588e-07, | |
| "loss": 0.1043, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.02926719898005176, | |
| "learning_rate": 0.0, | |
| "loss": 0.1103, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 28, | |
| "total_flos": 490074470875136.0, | |
| "train_loss": 0.058849748490112166, | |
| "train_runtime": 478.1215, | |
| "train_samples_per_second": 0.904, | |
| "train_steps_per_second": 0.059 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 28, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 490074470875136.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |