| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04986149584487535, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00554016620498615, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 10.7803, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00554016620498615, | |
| "eval_loss": 10.876238822937012, | |
| "eval_runtime": 1.1366, | |
| "eval_samples_per_second": 66.868, | |
| "eval_steps_per_second": 33.434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0110803324099723, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 10.5694, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01662049861495845, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 10.5919, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01662049861495845, | |
| "eval_loss": 10.876238822937012, | |
| "eval_runtime": 1.1359, | |
| "eval_samples_per_second": 66.907, | |
| "eval_steps_per_second": 33.453, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0221606648199446, | |
| "grad_norm": 17.855396270751953, | |
| "learning_rate": 2e-05, | |
| "loss": 11.1469, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027700831024930747, | |
| "grad_norm": 17.642831802368164, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8969, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0332409972299169, | |
| "grad_norm": 21.13235855102539, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0332409972299169, | |
| "eval_loss": 10.794831275939941, | |
| "eval_runtime": 1.1175, | |
| "eval_samples_per_second": 68.007, | |
| "eval_steps_per_second": 34.004, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.038781163434903045, | |
| "grad_norm": 23.375688552856445, | |
| "learning_rate": 8e-05, | |
| "loss": 10.8872, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0443213296398892, | |
| "grad_norm": 18.43400001525879, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04986149584487535, | |
| "grad_norm": 16.53175163269043, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8378, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04986149584487535, | |
| "eval_loss": 10.476703643798828, | |
| "eval_runtime": 1.1452, | |
| "eval_samples_per_second": 66.363, | |
| "eval_steps_per_second": 33.182, | |
| "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": 4886913613824.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |