| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012949733451319795, | |
| "eval_steps": 13, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.316577817106598e-05, | |
| "eval_loss": 2.0471103191375732, | |
| "eval_runtime": 952.5392, | |
| "eval_samples_per_second": 10.241, | |
| "eval_steps_per_second": 5.121, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012949733451319794, | |
| "grad_norm": 8.12905216217041, | |
| "learning_rate": 6e-05, | |
| "loss": 8.1991, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002589946690263959, | |
| "grad_norm": 8.616674423217773, | |
| "learning_rate": 0.00012, | |
| "loss": 7.7102, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003884920035395938, | |
| "grad_norm": 6.983860492706299, | |
| "learning_rate": 0.00018, | |
| "loss": 7.6783, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005179893380527918, | |
| "grad_norm": 8.666030883789062, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 7.3833, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005611551162238577, | |
| "eval_loss": 1.7469043731689453, | |
| "eval_runtime": 956.4149, | |
| "eval_samples_per_second": 10.2, | |
| "eval_steps_per_second": 5.1, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006474866725659897, | |
| "grad_norm": 4.685945510864258, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 7.0577, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007769840070791876, | |
| "grad_norm": 5.418538570404053, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 6.7296, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009064813415923856, | |
| "grad_norm": 3.6164493560791016, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 6.2438, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0010359786761055835, | |
| "grad_norm": 4.651533603668213, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 6.3792, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011223102324477154, | |
| "eval_loss": 1.5663001537322998, | |
| "eval_runtime": 956.4981, | |
| "eval_samples_per_second": 10.199, | |
| "eval_steps_per_second": 5.1, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0011654760106187814, | |
| "grad_norm": 3.52091383934021, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 6.5441, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0012949733451319795, | |
| "grad_norm": 4.742680549621582, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3389, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801969665310720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |