| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002178886588953045, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000435777317790609, | |
| "grad_norm": 0.013318134471774101, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000435777317790609, | |
| "eval_loss": 11.931103706359863, | |
| "eval_runtime": 31.6018, | |
| "eval_samples_per_second": 122.303, | |
| "eval_steps_per_second": 61.167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000871554635581218, | |
| "grad_norm": 0.010755705647170544, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9318, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000871554635581218, | |
| "eval_loss": 11.931102752685547, | |
| "eval_runtime": 14.4159, | |
| "eval_samples_per_second": 268.107, | |
| "eval_steps_per_second": 134.088, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001307331953371827, | |
| "grad_norm": 0.012713954783976078, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001743109271162436, | |
| "grad_norm": 0.011123117990791798, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9358, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001743109271162436, | |
| "eval_loss": 11.931097984313965, | |
| "eval_runtime": 14.4008, | |
| "eval_samples_per_second": 268.388, | |
| "eval_steps_per_second": 134.229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002178886588953045, | |
| "grad_norm": 0.01095407921820879, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9312, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2363228160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |