| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010382868267358857, | |
| "eval_steps": 2, | |
| "global_step": 14, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007416334476684898, | |
| "grad_norm": 10.709893226623535, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 18.8184, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007416334476684898, | |
| "eval_loss": 2.656465768814087, | |
| "eval_runtime": 152.8619, | |
| "eval_samples_per_second": 3.716, | |
| "eval_steps_per_second": 3.716, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014832668953369797, | |
| "grad_norm": 12.41769027709961, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 24.6349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014832668953369797, | |
| "eval_loss": 2.657148838043213, | |
| "eval_runtime": 154.2397, | |
| "eval_samples_per_second": 3.683, | |
| "eval_steps_per_second": 3.683, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022249003430054697, | |
| "grad_norm": 10.268001556396484, | |
| "learning_rate": 6e-06, | |
| "loss": 19.4269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029665337906739594, | |
| "grad_norm": 10.185709953308105, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 19.8056, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029665337906739594, | |
| "eval_loss": 2.656468629837036, | |
| "eval_runtime": 153.3523, | |
| "eval_samples_per_second": 3.704, | |
| "eval_steps_per_second": 3.704, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003708167238342449, | |
| "grad_norm": 12.79750919342041, | |
| "learning_rate": 1e-05, | |
| "loss": 20.4855, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004449800686010939, | |
| "grad_norm": 13.541940689086914, | |
| "learning_rate": 1.2e-05, | |
| "loss": 20.2844, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004449800686010939, | |
| "eval_loss": 2.653820514678955, | |
| "eval_runtime": 154.4773, | |
| "eval_samples_per_second": 3.677, | |
| "eval_steps_per_second": 3.677, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005191434133679429, | |
| "grad_norm": 13.248265266418457, | |
| "learning_rate": 1.4e-05, | |
| "loss": 18.3421, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005933067581347919, | |
| "grad_norm": 11.36257266998291, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 21.3146, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005933067581347919, | |
| "eval_loss": 2.6492502689361572, | |
| "eval_runtime": 156.6643, | |
| "eval_samples_per_second": 3.626, | |
| "eval_steps_per_second": 3.626, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006674701029016409, | |
| "grad_norm": 15.255399703979492, | |
| "learning_rate": 1.8e-05, | |
| "loss": 24.5242, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007416334476684898, | |
| "grad_norm": 12.062735557556152, | |
| "learning_rate": 2e-05, | |
| "loss": 18.8994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007416334476684898, | |
| "eval_loss": 2.639418125152588, | |
| "eval_runtime": 162.5206, | |
| "eval_samples_per_second": 3.495, | |
| "eval_steps_per_second": 3.495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008157967924353388, | |
| "grad_norm": 10.88565444946289, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 18.2225, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008899601372021879, | |
| "grad_norm": 16.972797393798828, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 20.6279, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008899601372021879, | |
| "eval_loss": 2.622429132461548, | |
| "eval_runtime": 154.0178, | |
| "eval_samples_per_second": 3.688, | |
| "eval_steps_per_second": 3.688, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009641234819690368, | |
| "grad_norm": 21.521284103393555, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 20.4902, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010382868267358857, | |
| "grad_norm": 16.134960174560547, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 20.8939, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010382868267358857, | |
| "eval_loss": 2.602504253387451, | |
| "eval_runtime": 154.8853, | |
| "eval_samples_per_second": 3.667, | |
| "eval_steps_per_second": 3.667, | |
| "step": 14 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1138405140332544.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |