| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016869095816464238, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.623031938821413e-05, | |
| "eval_loss": 1.5051027536392212, | |
| "eval_runtime": 431.4413, | |
| "eval_samples_per_second": 17.356, | |
| "eval_steps_per_second": 8.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016869095816464237, | |
| "grad_norm": 0.5793789029121399, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00033738191632928474, | |
| "grad_norm": 0.7272114157676697, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4811, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000449842555105713, | |
| "eval_loss": 1.2671171426773071, | |
| "eval_runtime": 430.619, | |
| "eval_samples_per_second": 17.389, | |
| "eval_steps_per_second": 8.694, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005060728744939271, | |
| "grad_norm": 0.8738322854042053, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006747638326585695, | |
| "grad_norm": 0.825180172920227, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.1586, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008434547908232119, | |
| "grad_norm": 0.816776692867279, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1362, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000899685110211426, | |
| "eval_loss": 1.0932092666625977, | |
| "eval_runtime": 430.6378, | |
| "eval_samples_per_second": 17.388, | |
| "eval_steps_per_second": 8.694, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0010121457489878543, | |
| "grad_norm": 0.6970958113670349, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0765, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011808367071524967, | |
| "grad_norm": 0.5732019543647766, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9584, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001349527665317139, | |
| "grad_norm": 0.5618394613265991, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0454, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.001349527665317139, | |
| "eval_loss": 1.0413671731948853, | |
| "eval_runtime": 430.964, | |
| "eval_samples_per_second": 17.375, | |
| "eval_steps_per_second": 8.688, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0015182186234817814, | |
| "grad_norm": 0.6845934987068176, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9827, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0016869095816464238, | |
| "grad_norm": 0.6820257902145386, | |
| "learning_rate": 0.0, | |
| "loss": 1.0895, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |