| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023833167825223437, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007944389275074479, | |
| "eval_loss": 2.4429898262023926, | |
| "eval_runtime": 24.9706, | |
| "eval_samples_per_second": 21.225, | |
| "eval_steps_per_second": 10.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023833167825223437, | |
| "grad_norm": 2.550875663757324, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0701, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004766633565044687, | |
| "grad_norm": 3.2429614067077637, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1285, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006355511420059583, | |
| "eval_loss": 2.4274704456329346, | |
| "eval_runtime": 23.7795, | |
| "eval_samples_per_second": 22.288, | |
| "eval_steps_per_second": 11.144, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007149950347567031, | |
| "grad_norm": 4.693836688995361, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009533267130089375, | |
| "grad_norm": 4.991544723510742, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.2315, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011916583912611719, | |
| "grad_norm": 2.781949520111084, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.8344, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012711022840119166, | |
| "eval_loss": 2.3441569805145264, | |
| "eval_runtime": 23.8029, | |
| "eval_samples_per_second": 22.266, | |
| "eval_steps_per_second": 11.133, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014299900695134062, | |
| "grad_norm": 4.244014263153076, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.137, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016683217477656404, | |
| "grad_norm": 3.2235708236694336, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.7062, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01906653426017875, | |
| "grad_norm": 4.751963138580322, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.165, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01906653426017875, | |
| "eval_loss": 2.263413429260254, | |
| "eval_runtime": 23.7723, | |
| "eval_samples_per_second": 22.295, | |
| "eval_steps_per_second": 11.147, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02144985104270109, | |
| "grad_norm": 4.580427169799805, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0876, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023833167825223437, | |
| "grad_norm": 4.650568962097168, | |
| "learning_rate": 0.0, | |
| "loss": 2.0238, | |
| "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": 4826899729612800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |