| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0147492625368733, | |
| "eval_steps": 9, | |
| "global_step": 43, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02359882005899705, | |
| "eval_loss": 11.216988563537598, | |
| "eval_runtime": 1.8833, | |
| "eval_samples_per_second": 151.859, | |
| "eval_steps_per_second": 19.115, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "eval_loss": 11.165812492370605, | |
| "eval_runtime": 0.9078, | |
| "eval_samples_per_second": 315.047, | |
| "eval_steps_per_second": 39.656, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2359882005899705, | |
| "grad_norm": 15.300642967224121, | |
| "learning_rate": 9.089646803833589e-05, | |
| "loss": 179.1345, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "eval_loss": 11.090907096862793, | |
| "eval_runtime": 0.9027, | |
| "eval_samples_per_second": 316.838, | |
| "eval_steps_per_second": 39.882, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.471976401179941, | |
| "grad_norm": 17.81786346435547, | |
| "learning_rate": 5.951955545823342e-05, | |
| "loss": 177.9139, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "eval_loss": 11.031437873840332, | |
| "eval_runtime": 0.9695, | |
| "eval_samples_per_second": 294.993, | |
| "eval_steps_per_second": 37.132, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 19.523183822631836, | |
| "learning_rate": 2.282162249993895e-05, | |
| "loss": 176.7675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "eval_loss": 11.008992195129395, | |
| "eval_runtime": 0.9276, | |
| "eval_samples_per_second": 308.313, | |
| "eval_steps_per_second": 38.809, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.943952802359882, | |
| "grad_norm": 19.834644317626953, | |
| "learning_rate": 1.3152288061110518e-06, | |
| "loss": 176.2137, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 43, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 11, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 13264014016512.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |