| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014803849000740192, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014803849000740192, | |
| "grad_norm": 0.02995922788977623, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014803849000740192, | |
| "eval_loss": 10.37421703338623, | |
| "eval_runtime": 1.1264, | |
| "eval_samples_per_second": 253.028, | |
| "eval_steps_per_second": 126.958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029607698001480384, | |
| "grad_norm": 0.0324353463947773, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3751, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0044411547002220575, | |
| "grad_norm": 0.04028886556625366, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3746, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0044411547002220575, | |
| "eval_loss": 10.374184608459473, | |
| "eval_runtime": 1.1389, | |
| "eval_samples_per_second": 250.233, | |
| "eval_steps_per_second": 125.556, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005921539600296077, | |
| "grad_norm": 0.027431325986981392, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3741, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007401924500370096, | |
| "grad_norm": 0.028998393565416336, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3758, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008882309400444115, | |
| "grad_norm": 0.03407181054353714, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3745, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008882309400444115, | |
| "eval_loss": 10.374056816101074, | |
| "eval_runtime": 1.2091, | |
| "eval_samples_per_second": 235.721, | |
| "eval_steps_per_second": 118.274, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 0.03717741370201111, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3757, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011843079200592153, | |
| "grad_norm": 0.03833466023206711, | |
| "learning_rate": 0.00016, | |
| "loss": 10.372, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013323464100666173, | |
| "grad_norm": 0.036701519042253494, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3729, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013323464100666173, | |
| "eval_loss": 10.373818397521973, | |
| "eval_runtime": 1.1504, | |
| "eval_samples_per_second": 247.738, | |
| "eval_steps_per_second": 124.304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014803849000740192, | |
| "grad_norm": 0.03882726654410362, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3736, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 258618163200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |