| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00016036820539959748, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6036820539959746e-05, | |
| "grad_norm": 1.1800854206085205, | |
| "learning_rate": 2e-05, | |
| "loss": 5.8615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6036820539959746e-05, | |
| "eval_loss": 5.424288749694824, | |
| "eval_runtime": 214.3148, | |
| "eval_samples_per_second": 122.511, | |
| "eval_steps_per_second": 61.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.207364107991949e-05, | |
| "grad_norm": 1.0589226484298706, | |
| "learning_rate": 4e-05, | |
| "loss": 5.3043, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.811046161987924e-05, | |
| "grad_norm": 1.095107078552246, | |
| "learning_rate": 6e-05, | |
| "loss": 5.559, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.811046161987924e-05, | |
| "eval_loss": 5.421957015991211, | |
| "eval_runtime": 214.2079, | |
| "eval_samples_per_second": 122.573, | |
| "eval_steps_per_second": 61.286, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.414728215983899e-05, | |
| "grad_norm": 1.239835500717163, | |
| "learning_rate": 8e-05, | |
| "loss": 5.6186, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.018410269979874e-05, | |
| "grad_norm": 0.9352376461029053, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9858, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.622092323975848e-05, | |
| "grad_norm": 1.0395596027374268, | |
| "learning_rate": 0.00012, | |
| "loss": 5.5779, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.622092323975848e-05, | |
| "eval_loss": 5.395402908325195, | |
| "eval_runtime": 216.9702, | |
| "eval_samples_per_second": 121.012, | |
| "eval_steps_per_second": 60.506, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011225774377971823, | |
| "grad_norm": 1.06486976146698, | |
| "learning_rate": 0.00014, | |
| "loss": 5.162, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00012829456431967797, | |
| "grad_norm": 1.1006083488464355, | |
| "learning_rate": 0.00016, | |
| "loss": 5.232, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014433138485963774, | |
| "grad_norm": 1.3101000785827637, | |
| "learning_rate": 0.00018, | |
| "loss": 5.5333, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014433138485963774, | |
| "eval_loss": 5.314747333526611, | |
| "eval_runtime": 212.8836, | |
| "eval_samples_per_second": 123.335, | |
| "eval_steps_per_second": 61.667, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016036820539959748, | |
| "grad_norm": 0.9229961633682251, | |
| "learning_rate": 0.0002, | |
| "loss": 4.801, | |
| "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": 34292650475520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |