| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00032841321680745865, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "grad_norm": 1.0083673000335693, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "eval_loss": 1.98862886428833, | |
| "eval_runtime": 461.0785, | |
| "eval_samples_per_second": 25.026, | |
| "eval_steps_per_second": 12.514, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.298071484610192e-05, | |
| "grad_norm": 1.4298427104949951, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2947, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "grad_norm": 1.2467610836029053, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2746, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "eval_loss": 1.979784369468689, | |
| "eval_runtime": 486.1146, | |
| "eval_samples_per_second": 23.737, | |
| "eval_steps_per_second": 11.87, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014596142969220384, | |
| "grad_norm": 0.9535866975784302, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7232, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001824517871152548, | |
| "grad_norm": 0.9923235774040222, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7717, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "grad_norm": 0.9086453318595886, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7031, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "eval_loss": 1.8454196453094482, | |
| "eval_runtime": 473.638, | |
| "eval_samples_per_second": 24.362, | |
| "eval_steps_per_second": 12.182, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002554325019613567, | |
| "grad_norm": 1.836844563484192, | |
| "learning_rate": 0.00014, | |
| "loss": 1.9654, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029192285938440767, | |
| "grad_norm": 1.6875149011611938, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8015, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "grad_norm": 0.9613115787506104, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7253, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "eval_loss": 1.612996220588684, | |
| "eval_runtime": 663.2626, | |
| "eval_samples_per_second": 17.397, | |
| "eval_steps_per_second": 8.699, | |
| "step": 9 | |
| } | |
| ], | |
| "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": 1953769004728320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |