| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.024891101431238332, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002489110143123833, | |
| "grad_norm": 0.298843115568161, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8329, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002489110143123833, | |
| "eval_loss": 0.8898334503173828, | |
| "eval_runtime": 9.0774, | |
| "eval_samples_per_second": 18.728, | |
| "eval_steps_per_second": 9.364, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004978220286247666, | |
| "grad_norm": 0.3175828158855438, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0074673304293715, | |
| "grad_norm": 0.304165780544281, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8174, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0074673304293715, | |
| "eval_loss": 0.887511134147644, | |
| "eval_runtime": 9.0704, | |
| "eval_samples_per_second": 18.742, | |
| "eval_steps_per_second": 9.371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009956440572495333, | |
| "grad_norm": 0.3128150999546051, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8598, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "grad_norm": 0.3292211890220642, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8604, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014934660858743, | |
| "grad_norm": 0.3900112807750702, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8871, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014934660858743, | |
| "eval_loss": 0.8656075596809387, | |
| "eval_runtime": 9.0783, | |
| "eval_samples_per_second": 18.726, | |
| "eval_steps_per_second": 9.363, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017423771001866834, | |
| "grad_norm": 0.3883002996444702, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8498, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019912881144990666, | |
| "grad_norm": 0.4265586733818054, | |
| "learning_rate": 0.00016, | |
| "loss": 0.8089, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0224019912881145, | |
| "grad_norm": 0.38517630100250244, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0224019912881145, | |
| "eval_loss": 0.7998427152633667, | |
| "eval_runtime": 9.0772, | |
| "eval_samples_per_second": 18.728, | |
| "eval_steps_per_second": 9.364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "grad_norm": 0.3209020793437958, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7818, | |
| "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": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |