| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9925925925925926, | |
| "eval_steps": 500, | |
| "global_step": 67, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014814814814814815, | |
| "grad_norm": 19.4039760393098, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 1.5916, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 2.024285471994628, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 1.4287, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.1211804620853234, | |
| "learning_rate": 1.9876883405951378e-05, | |
| "loss": 1.1475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.14441501230299, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.0186, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.0887457606115902, | |
| "learning_rate": 1.777145961456971e-05, | |
| "loss": 0.9336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.1339781450076967, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.8617, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.1324585725260847, | |
| "learning_rate": 1.3583679495453e-05, | |
| "loss": 0.7875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 1.1020040138984686, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.7257, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.105923599687312, | |
| "learning_rate": 8.43565534959769e-06, | |
| "loss": 0.6779, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 1.0653749318761645, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 0.636, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.0549355896653918, | |
| "learning_rate": 3.7067960895016277e-06, | |
| "loss": 0.6134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.9960657574926672, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.5906, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.9945434588891916, | |
| "learning_rate": 6.641957350279838e-07, | |
| "loss": 0.5828, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9629629629629629, | |
| "grad_norm": 1.0147750878178303, | |
| "learning_rate": 5.4781046317267103e-08, | |
| "loss": 0.5824, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9925925925925926, | |
| "eval_loss": 1.4180262088775635, | |
| "eval_runtime": 0.7571, | |
| "eval_samples_per_second": 11.888, | |
| "eval_steps_per_second": 1.321, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.9925925925925926, | |
| "step": 67, | |
| "total_flos": 27952184033280.0, | |
| "train_loss": 0.8094243202636491, | |
| "train_runtime": 773.5157, | |
| "train_samples_per_second": 44.608, | |
| "train_steps_per_second": 0.087 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 67, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 27952184033280.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |