| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.31116297160637885, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.015558148580318941, |
| "grad_norm": 2.210095167160034, |
| "learning_rate": 9e-05, |
| "loss": 0.6592, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.031116297160637883, |
| "grad_norm": 0.5916579961776733, |
| "learning_rate": 0.00019, |
| "loss": 0.4339, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.046674445740956826, |
| "grad_norm": 0.6445603370666504, |
| "learning_rate": 0.00019, |
| "loss": 0.3754, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.062232594321275765, |
| "grad_norm": 0.8737533688545227, |
| "learning_rate": 0.0001788888888888889, |
| "loss": 0.3768, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.07779074290159471, |
| "grad_norm": 1.0076223611831665, |
| "learning_rate": 0.0001677777777777778, |
| "loss": 0.3502, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.09334889148191365, |
| "grad_norm": 0.7350986003875732, |
| "learning_rate": 0.00015666666666666666, |
| "loss": 0.282, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.10890704006223259, |
| "grad_norm": 1.2068954706192017, |
| "learning_rate": 0.00014555555555555556, |
| "loss": 0.2791, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.12446518864255153, |
| "grad_norm": 1.3737070560455322, |
| "learning_rate": 0.00013444444444444447, |
| "loss": 0.2764, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.14002333722287047, |
| "grad_norm": 0.7465991377830505, |
| "learning_rate": 0.00012333333333333334, |
| "loss": 0.2814, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.15558148580318942, |
| "grad_norm": 0.630469560623169, |
| "learning_rate": 0.00011222222222222223, |
| "loss": 0.2942, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.17113963438350835, |
| "grad_norm": 0.8204443454742432, |
| "learning_rate": 0.00010111111111111112, |
| "loss": 0.2733, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.1866977829638273, |
| "grad_norm": 0.920691192150116, |
| "learning_rate": 9e-05, |
| "loss": 0.2776, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.20225593154414626, |
| "grad_norm": 0.8861131072044373, |
| "learning_rate": 7.88888888888889e-05, |
| "loss": 0.2915, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.21781408012446518, |
| "grad_norm": 0.7407158017158508, |
| "learning_rate": 6.777777777777778e-05, |
| "loss": 0.2642, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.23337222870478413, |
| "grad_norm": 0.6536486744880676, |
| "learning_rate": 5.666666666666667e-05, |
| "loss": 0.2675, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.24893037728510306, |
| "grad_norm": 1.0072147846221924, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 0.2543, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.26448852586542204, |
| "grad_norm": 1.1627495288848877, |
| "learning_rate": 3.444444444444445e-05, |
| "loss": 0.2614, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.28004667444574094, |
| "grad_norm": 0.8551999926567078, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.24, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.2956048230260599, |
| "grad_norm": 0.8133125901222229, |
| "learning_rate": 1.2222222222222222e-05, |
| "loss": 0.2109, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.31116297160637885, |
| "grad_norm": 1.3373092412948608, |
| "learning_rate": 1.1111111111111112e-06, |
| "loss": 0.2383, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 200, |
| "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": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.6373634155854272e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
