| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028070175438596492, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 12.58973503112793, | |
| "learning_rate": 2e-05, | |
| "loss": 7.8229, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 7.685409069061279, | |
| "eval_runtime": 1.1679, | |
| "eval_samples_per_second": 38.532, | |
| "eval_steps_per_second": 38.532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 13.469074249267578, | |
| "learning_rate": 4e-05, | |
| "loss": 7.7073, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 13.288359642028809, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3078, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "eval_loss": 7.650800704956055, | |
| "eval_runtime": 1.1725, | |
| "eval_samples_per_second": 38.378, | |
| "eval_steps_per_second": 38.378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 10.393665313720703, | |
| "learning_rate": 8e-05, | |
| "loss": 7.893, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 10.401045799255371, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6955, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 12.121800422668457, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9641, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "eval_loss": 7.324780464172363, | |
| "eval_runtime": 1.2063, | |
| "eval_samples_per_second": 37.305, | |
| "eval_steps_per_second": 37.305, | |
| "step": 6 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1628971204608.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |