| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0144927536231885, | |
| "eval_steps": 25, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 0.19229012727737427, | |
| "learning_rate": 9.869238178417235e-05, | |
| "loss": 0.8456, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "eval_loss": 1.0139143466949463, | |
| "eval_runtime": 2.4726, | |
| "eval_samples_per_second": 20.222, | |
| "eval_steps_per_second": 5.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.463768115942029, | |
| "grad_norm": 0.1821756809949875, | |
| "learning_rate": 9.484552115439445e-05, | |
| "loss": 0.8218, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.17129157483577728, | |
| "learning_rate": 8.868298366769954e-05, | |
| "loss": 0.8314, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.927536231884058, | |
| "grad_norm": 0.1404978334903717, | |
| "learning_rate": 8.056291360290201e-05, | |
| "loss": 0.8128, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.1594202898550725, | |
| "grad_norm": 0.23700346052646637, | |
| "learning_rate": 7.095721991691411e-05, | |
| "loss": 1.3179, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 0.12950977683067322, | |
| "learning_rate": 6.042415061148954e-05, | |
| "loss": 0.6833, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.6231884057971016, | |
| "grad_norm": 0.1283191591501236, | |
| "learning_rate": 4.9575849388510473e-05, | |
| "loss": 0.7132, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.855072463768116, | |
| "grad_norm": 0.10768551379442215, | |
| "learning_rate": 3.904278008308589e-05, | |
| "loss": 0.7146, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0869565217391304, | |
| "grad_norm": 0.2074042111635208, | |
| "learning_rate": 2.9437086397097995e-05, | |
| "loss": 1.188, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.318840579710145, | |
| "grad_norm": 0.09767608344554901, | |
| "learning_rate": 2.1317016332300447e-05, | |
| "loss": 0.658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.550724637681159, | |
| "grad_norm": 0.09478430449962616, | |
| "learning_rate": 1.515447884560556e-05, | |
| "loss": 0.7209, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.782608695652174, | |
| "grad_norm": 0.09528922289609909, | |
| "learning_rate": 1.130761821582766e-05, | |
| "loss": 0.6974, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0144927536231885, | |
| "grad_norm": 0.15585486590862274, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9582, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4745576854152806e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |