| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005055931239335145, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.055931239335145e-05, | |
| "grad_norm": 3.686462514451705e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.055931239335145e-05, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 55.9728, | |
| "eval_samples_per_second": 148.786, | |
| "eval_steps_per_second": 74.393, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001011186247867029, | |
| "grad_norm": 1.792136754374951e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00015167793718005436, | |
| "grad_norm": 2.3431130102835596e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015167793718005436, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.0147, | |
| "eval_samples_per_second": 148.675, | |
| "eval_steps_per_second": 74.338, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002022372495734058, | |
| "grad_norm": 7.08585575921461e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00025279656196675726, | |
| "grad_norm": 9.789110663405154e-06, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030335587436010873, | |
| "grad_norm": 2.0988200049032457e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00030335587436010873, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.3455, | |
| "eval_samples_per_second": 147.803, | |
| "eval_steps_per_second": 73.901, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00035391518675346014, | |
| "grad_norm": 3.647402627393603e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0004044744991468116, | |
| "grad_norm": 2.1768866645288654e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00045503381154016307, | |
| "grad_norm": 3.181512147421017e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00045503381154016307, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 56.4484, | |
| "eval_samples_per_second": 147.533, | |
| "eval_steps_per_second": 73.767, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005055931239335145, | |
| "grad_norm": 6.877647683722898e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 368573251584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |