| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03372681281618887, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003372681281618887, | |
| "grad_norm": 1.5322465896606445, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003372681281618887, | |
| "eval_loss": 3.238746166229248, | |
| "eval_runtime": 5.1939, | |
| "eval_samples_per_second": 24.067, | |
| "eval_steps_per_second": 12.13, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006745362563237774, | |
| "grad_norm": 1.212786078453064, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7946, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01011804384485666, | |
| "grad_norm": 1.168325662612915, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9507, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01011804384485666, | |
| "eval_loss": 3.235896348953247, | |
| "eval_runtime": 3.8081, | |
| "eval_samples_per_second": 32.824, | |
| "eval_steps_per_second": 16.544, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013490725126475547, | |
| "grad_norm": 0.9074205756187439, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6808, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016863406408094434, | |
| "grad_norm": 1.4937058687210083, | |
| "learning_rate": 0.0001, | |
| "loss": 3.447, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02023608768971332, | |
| "grad_norm": 1.14553701877594, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9082, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02023608768971332, | |
| "eval_loss": 3.201192617416382, | |
| "eval_runtime": 3.8303, | |
| "eval_samples_per_second": 32.635, | |
| "eval_steps_per_second": 16.448, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023608768971332208, | |
| "grad_norm": 1.8054167032241821, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1859, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.026981450252951095, | |
| "grad_norm": 1.2994825839996338, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0584, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03035413153456998, | |
| "grad_norm": 1.7081750631332397, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9828, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03035413153456998, | |
| "eval_loss": 3.005418062210083, | |
| "eval_runtime": 3.8304, | |
| "eval_samples_per_second": 32.634, | |
| "eval_steps_per_second": 16.447, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03372681281618887, | |
| "grad_norm": 2.3658268451690674, | |
| "learning_rate": 0.0002, | |
| "loss": 3.236, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |