| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014233018230124183, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.7443394100413944e-05, | |
| "eval_loss": 5.9001851081848145, | |
| "eval_runtime": 215.7426, | |
| "eval_samples_per_second": 41.137, | |
| "eval_steps_per_second": 20.571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014233018230124184, | |
| "grad_norm": 0.5502749681472778, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6588, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002846603646024837, | |
| "grad_norm": 1.031740427017212, | |
| "learning_rate": 0.00012, | |
| "loss": 3.6699, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00037954715280331155, | |
| "eval_loss": 5.776932239532471, | |
| "eval_runtime": 215.3488, | |
| "eval_samples_per_second": 41.212, | |
| "eval_steps_per_second": 20.608, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004269905469037255, | |
| "grad_norm": 1.4804857969284058, | |
| "learning_rate": 0.00018, | |
| "loss": 2.639, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005693207292049674, | |
| "grad_norm": 1.224292278289795, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.0038, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007116509115062091, | |
| "grad_norm": 1.004064679145813, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.4787, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007590943056066231, | |
| "eval_loss": 5.0633463859558105, | |
| "eval_runtime": 211.9278, | |
| "eval_samples_per_second": 41.877, | |
| "eval_steps_per_second": 20.941, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.000853981093807451, | |
| "grad_norm": 0.9390115141868591, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.4008, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009963112761086927, | |
| "grad_norm": 1.7044845819473267, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.7965, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011386414584099347, | |
| "grad_norm": 0.8411383628845215, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.6778, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011386414584099347, | |
| "eval_loss": 4.626430511474609, | |
| "eval_runtime": 215.1854, | |
| "eval_samples_per_second": 41.244, | |
| "eval_steps_per_second": 20.624, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012809716407111765, | |
| "grad_norm": 0.9061992168426514, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.0869, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0014233018230124183, | |
| "grad_norm": 1.1482539176940918, | |
| "learning_rate": 0.0, | |
| "loss": 2.738, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 213462788603904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |