| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17035775127768313, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034071550255536627, | |
| "eval_loss": 11.934847831726074, | |
| "eval_runtime": 1.1086, | |
| "eval_samples_per_second": 111.851, | |
| "eval_steps_per_second": 55.925, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017035775127768313, | |
| "grad_norm": 0.011460528708994389, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9349, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.034071550255536626, | |
| "grad_norm": 0.010980741120874882, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.034071550255536626, | |
| "eval_loss": 11.934786796569824, | |
| "eval_runtime": 1.1655, | |
| "eval_samples_per_second": 106.389, | |
| "eval_steps_per_second": 53.195, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05110732538330494, | |
| "grad_norm": 0.010588523931801319, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9332, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06814310051107325, | |
| "grad_norm": 0.010388094000518322, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06814310051107325, | |
| "eval_loss": 11.934656143188477, | |
| "eval_runtime": 1.2115, | |
| "eval_samples_per_second": 102.348, | |
| "eval_steps_per_second": 51.174, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08517887563884156, | |
| "grad_norm": 0.012346145696938038, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9344, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10221465076660988, | |
| "grad_norm": 0.012346740812063217, | |
| "learning_rate": 5e-05, | |
| "loss": 11.933, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10221465076660988, | |
| "eval_loss": 11.934558868408203, | |
| "eval_runtime": 1.1662, | |
| "eval_samples_per_second": 106.33, | |
| "eval_steps_per_second": 53.165, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11925042589437819, | |
| "grad_norm": 0.007833733223378658, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9338, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1362862010221465, | |
| "grad_norm": 0.012729058042168617, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9334, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1362862010221465, | |
| "eval_loss": 11.9345064163208, | |
| "eval_runtime": 1.2243, | |
| "eval_samples_per_second": 101.282, | |
| "eval_steps_per_second": 50.641, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15332197614991483, | |
| "grad_norm": 0.010119827464222908, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9349, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17035775127768313, | |
| "grad_norm": 0.0122945262119174, | |
| "learning_rate": 0.0, | |
| "loss": 11.9337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17035775127768313, | |
| "eval_loss": 11.934497833251953, | |
| "eval_runtime": 1.2202, | |
| "eval_samples_per_second": 101.625, | |
| "eval_steps_per_second": 50.812, | |
| "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": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |