| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012753272011350411, | |
| "eval_steps": 40, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.376636005675206e-05, | |
| "eval_loss": 2.2926838397979736, | |
| "eval_runtime": 1632.7078, | |
| "eval_samples_per_second": 16.177, | |
| "eval_steps_per_second": 8.089, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025506544022700826, | |
| "grad_norm": 0.242392435669899, | |
| "learning_rate": 1e-05, | |
| "loss": 2.113, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0025506544022700826, | |
| "eval_loss": 2.281226396560669, | |
| "eval_runtime": 1632.736, | |
| "eval_samples_per_second": 16.177, | |
| "eval_steps_per_second": 8.089, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005101308804540165, | |
| "grad_norm": 0.34583497047424316, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0101, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005101308804540165, | |
| "eval_loss": 2.028463840484619, | |
| "eval_runtime": 1632.3499, | |
| "eval_samples_per_second": 16.181, | |
| "eval_steps_per_second": 8.091, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.007651963206810247, | |
| "grad_norm": 0.36259645223617554, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.9321, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.007651963206810247, | |
| "eval_loss": 1.8874897956848145, | |
| "eval_runtime": 1631.9913, | |
| "eval_samples_per_second": 16.185, | |
| "eval_steps_per_second": 8.093, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01020261760908033, | |
| "grad_norm": 0.31786981225013733, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.8486, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01020261760908033, | |
| "eval_loss": 1.86680269241333, | |
| "eval_runtime": 1633.0142, | |
| "eval_samples_per_second": 16.174, | |
| "eval_steps_per_second": 8.087, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.012753272011350411, | |
| "grad_norm": 0.3404850363731384, | |
| "learning_rate": 0.0, | |
| "loss": 1.8747, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.012753272011350411, | |
| "eval_loss": 1.8641034364700317, | |
| "eval_runtime": 1631.9209, | |
| "eval_samples_per_second": 16.185, | |
| "eval_steps_per_second": 8.093, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 40, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.493003432487813e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |