| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008454872120059184, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 0.6357499361038208, | |
| "eval_runtime": 142.1566, | |
| "eval_samples_per_second": 17.516, | |
| "eval_steps_per_second": 8.758, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.25223004817962646, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5982, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 0.33768871426582336, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6729, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 0.609550416469574, | |
| "eval_runtime": 143.4339, | |
| "eval_samples_per_second": 17.36, | |
| "eval_steps_per_second": 8.68, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.2895045876502991, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5513, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 0.40199053287506104, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.5287407636642456, | |
| "eval_runtime": 143.8791, | |
| "eval_samples_per_second": 17.306, | |
| "eval_steps_per_second": 8.653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "grad_norm": 0.4052754342556, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "grad_norm": 0.3301470875740051, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4762, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "eval_loss": 0.5101726651191711, | |
| "eval_runtime": 143.6995, | |
| "eval_samples_per_second": 17.328, | |
| "eval_steps_per_second": 8.664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005918410484041429, | |
| "grad_norm": 0.3366134762763977, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "grad_norm": 0.46769002079963684, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "eval_loss": 0.504737913608551, | |
| "eval_runtime": 143.4632, | |
| "eval_samples_per_second": 17.356, | |
| "eval_steps_per_second": 8.678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007609384908053266, | |
| "grad_norm": 0.384360671043396, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5072, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "grad_norm": 0.3384287357330322, | |
| "learning_rate": 0.0, | |
| "loss": 0.4794, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "eval_loss": 0.5036466121673584, | |
| "eval_runtime": 143.0377, | |
| "eval_samples_per_second": 17.408, | |
| "eval_steps_per_second": 8.704, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5600570517749760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |