| { | |
| "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": 140.594, | |
| "eval_samples_per_second": 17.711, | |
| "eval_steps_per_second": 8.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 0.23109857738018036, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5982, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 0.32216212153434753, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "eval_loss": 0.6111032962799072, | |
| "eval_runtime": 141.3399, | |
| "eval_samples_per_second": 17.617, | |
| "eval_steps_per_second": 8.809, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025364616360177552, | |
| "grad_norm": 0.2761354446411133, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5525, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "grad_norm": 0.3936506509780884, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5134, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033819488480236735, | |
| "eval_loss": 0.5297576189041138, | |
| "eval_runtime": 142.7855, | |
| "eval_samples_per_second": 17.439, | |
| "eval_steps_per_second": 8.719, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004227436060029592, | |
| "grad_norm": 0.4028269946575165, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4533, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "grad_norm": 0.3197304308414459, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4767, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0050729232720355105, | |
| "eval_loss": 0.5105544328689575, | |
| "eval_runtime": 142.8654, | |
| "eval_samples_per_second": 17.429, | |
| "eval_steps_per_second": 8.714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005918410484041429, | |
| "grad_norm": 0.33733314275741577, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "grad_norm": 0.4488641023635864, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4668, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006763897696047347, | |
| "eval_loss": 0.50519859790802, | |
| "eval_runtime": 142.7619, | |
| "eval_samples_per_second": 17.442, | |
| "eval_steps_per_second": 8.721, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007609384908053266, | |
| "grad_norm": 0.3778371512889862, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5074, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "grad_norm": 0.33311334252357483, | |
| "learning_rate": 0.0, | |
| "loss": 0.4794, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008454872120059184, | |
| "eval_loss": 0.5040430426597595, | |
| "eval_runtime": 141.9754, | |
| "eval_samples_per_second": 17.538, | |
| "eval_steps_per_second": 8.769, | |
| "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 | |
| } | |