| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0027424183559201956, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.141394519733986e-05, | |
| "eval_loss": 2.204296588897705, | |
| "eval_runtime": 1444.1991, | |
| "eval_samples_per_second": 3.19, | |
| "eval_steps_per_second": 1.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027424183559201956, | |
| "grad_norm": 0.5782468318939209, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2117, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005484836711840391, | |
| "grad_norm": 0.5366343855857849, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0656, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007313115615787189, | |
| "eval_loss": 2.0421738624572754, | |
| "eval_runtime": 1450.625, | |
| "eval_samples_per_second": 3.176, | |
| "eval_steps_per_second": 1.588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008227255067760587, | |
| "grad_norm": 0.7202419638633728, | |
| "learning_rate": 0.00018, | |
| "loss": 2.082, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010969673423680782, | |
| "grad_norm": 0.525327742099762, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9954, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0013712091779600978, | |
| "grad_norm": 0.46169307827949524, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014626231231574377, | |
| "eval_loss": 1.8409279584884644, | |
| "eval_runtime": 1453.3557, | |
| "eval_samples_per_second": 3.17, | |
| "eval_steps_per_second": 1.585, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0016454510135521174, | |
| "grad_norm": 0.4116497337818146, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8149, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001919692849144137, | |
| "grad_norm": 0.427301287651062, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.803, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0021939346847361565, | |
| "grad_norm": 0.38913968205451965, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.7879, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0021939346847361565, | |
| "eval_loss": 1.7518465518951416, | |
| "eval_runtime": 1454.9335, | |
| "eval_samples_per_second": 3.166, | |
| "eval_steps_per_second": 1.584, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0024681765203281763, | |
| "grad_norm": 0.4009721875190735, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.7076, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0027424183559201956, | |
| "grad_norm": 0.41326427459716797, | |
| "learning_rate": 0.0, | |
| "loss": 1.7267, | |
| "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": 9178378972692480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |