| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005592293819117256, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.864097939705752e-05, | |
| "eval_loss": 2.621065616607666, | |
| "eval_runtime": 1349.6662, | |
| "eval_samples_per_second": 16.736, | |
| "eval_steps_per_second": 8.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.592293819117256e-05, | |
| "grad_norm": 2.7079131603240967, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5585, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.320489698528761e-05, | |
| "eval_loss": 2.578003168106079, | |
| "eval_runtime": 1350.5319, | |
| "eval_samples_per_second": 16.725, | |
| "eval_steps_per_second": 8.363, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011184587638234512, | |
| "grad_norm": 1.4092097282409668, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016776881457351768, | |
| "grad_norm": 1.0350408554077148, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00018640979397057522, | |
| "eval_loss": 2.3993470668792725, | |
| "eval_runtime": 1350.9472, | |
| "eval_samples_per_second": 16.72, | |
| "eval_steps_per_second": 8.36, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00022369175276469025, | |
| "grad_norm": 0.8830559849739075, | |
| "learning_rate": 0.00016, | |
| "loss": 2.4659, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002796146909558628, | |
| "grad_norm": 0.8916003704071045, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4098, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002796146909558628, | |
| "eval_loss": 2.33770751953125, | |
| "eval_runtime": 1709.3108, | |
| "eval_samples_per_second": 13.215, | |
| "eval_steps_per_second": 6.607, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00033553762914703537, | |
| "grad_norm": 0.7203744649887085, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.2017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00037281958794115045, | |
| "eval_loss": 2.3048362731933594, | |
| "eval_runtime": 1351.5842, | |
| "eval_samples_per_second": 16.712, | |
| "eval_steps_per_second": 8.356, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00039146056733820793, | |
| "grad_norm": 0.8622225522994995, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2012, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004473835055293805, | |
| "grad_norm": 0.6934110522270203, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 2.1377, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00046602448492643803, | |
| "eval_loss": 2.282181739807129, | |
| "eval_runtime": 1350.9454, | |
| "eval_samples_per_second": 16.72, | |
| "eval_steps_per_second": 8.36, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000503306443720553, | |
| "grad_norm": 0.7300806641578674, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.4247, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005592293819117256, | |
| "grad_norm": 0.7322918176651001, | |
| "learning_rate": 0.0, | |
| "loss": 2.3124, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005592293819117256, | |
| "eval_loss": 2.2772910594940186, | |
| "eval_runtime": 1350.7059, | |
| "eval_samples_per_second": 16.723, | |
| "eval_steps_per_second": 8.362, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3425666715353088.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |