| { | |
| "best_metric": 5.530978679656982, | |
| "best_model_checkpoint": "autotrain-r8zdq-nww6o/checkpoint-64", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 64, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.046875, | |
| "grad_norm": 15.872576713562012, | |
| "learning_rate": 2.5e-06, | |
| "loss": 4.0459, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 14.468564987182617, | |
| "learning_rate": 1e-05, | |
| "loss": 3.8906, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.140625, | |
| "grad_norm": 12.806556701660156, | |
| "learning_rate": 1.75e-05, | |
| "loss": 3.1036, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 7.326994895935059, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.1466, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.234375, | |
| "grad_norm": 2.5583295822143555, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 1.7102, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 3.5812530517578125, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5867, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.328125, | |
| "grad_norm": 1.4613455533981323, | |
| "learning_rate": 4.75e-05, | |
| "loss": 1.3785, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 3.1722567081451416, | |
| "learning_rate": 4.941860465116279e-05, | |
| "loss": 1.4526, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.421875, | |
| "grad_norm": 3.3172366619110107, | |
| "learning_rate": 4.854651162790698e-05, | |
| "loss": 1.3307, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 2.2563154697418213, | |
| "learning_rate": 4.7674418604651164e-05, | |
| "loss": 1.4428, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.515625, | |
| "grad_norm": 2.1187117099761963, | |
| "learning_rate": 4.680232558139535e-05, | |
| "loss": 1.4933, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 3.107919931411743, | |
| "learning_rate": 4.593023255813954e-05, | |
| "loss": 1.3909, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.609375, | |
| "grad_norm": 2.8481452465057373, | |
| "learning_rate": 4.505813953488372e-05, | |
| "loss": 1.4789, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 1.2975138425827026, | |
| "learning_rate": 4.418604651162791e-05, | |
| "loss": 1.3402, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.703125, | |
| "grad_norm": 2.2250919342041016, | |
| "learning_rate": 4.3313953488372096e-05, | |
| "loss": 1.5143, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.7821475267410278, | |
| "learning_rate": 4.2441860465116276e-05, | |
| "loss": 1.2815, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.796875, | |
| "grad_norm": 1.3603293895721436, | |
| "learning_rate": 4.156976744186047e-05, | |
| "loss": 1.2912, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 1.1273295879364014, | |
| "learning_rate": 4.0697674418604655e-05, | |
| "loss": 1.3891, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.890625, | |
| "grad_norm": 1.2710983753204346, | |
| "learning_rate": 3.9825581395348835e-05, | |
| "loss": 1.4103, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 1.6584129333496094, | |
| "learning_rate": 3.895348837209303e-05, | |
| "loss": 1.4676, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.984375, | |
| "grad_norm": 1.8036679029464722, | |
| "learning_rate": 3.8081395348837215e-05, | |
| "loss": 1.3896, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.0026870229007633587, | |
| "eval_f1": 0.0, | |
| "eval_loss": 5.530978679656982, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 0.3581, | |
| "eval_samples_per_second": 388.142, | |
| "eval_steps_per_second": 25.132, | |
| "step": 64 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 192, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 33260533691136.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |