| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05847953216374269, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011695906432748538, | |
| "eval_loss": 1.673849105834961, | |
| "eval_runtime": 25.7736, | |
| "eval_samples_per_second": 14.007, | |
| "eval_steps_per_second": 7.023, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005847953216374269, | |
| "grad_norm": 14.895322799682617, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3817, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 25.017160415649414, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "eval_loss": 1.5868688821792603, | |
| "eval_runtime": 25.9777, | |
| "eval_samples_per_second": 13.897, | |
| "eval_steps_per_second": 6.968, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 16.532119750976562, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.2486, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 9.334230422973633, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.3903, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "eval_loss": 1.4316128492355347, | |
| "eval_runtime": 26.1089, | |
| "eval_samples_per_second": 13.827, | |
| "eval_steps_per_second": 6.932, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.029239766081871343, | |
| "grad_norm": 17.485925674438477, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.8952, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 9.96809196472168, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8127, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "eval_loss": 1.3962314128875732, | |
| "eval_runtime": 26.2943, | |
| "eval_samples_per_second": 13.729, | |
| "eval_steps_per_second": 6.884, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04093567251461988, | |
| "grad_norm": 17.325239181518555, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.5318, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 21.39069938659668, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.6708, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 1.379729986190796, | |
| "eval_runtime": 26.1353, | |
| "eval_samples_per_second": 13.813, | |
| "eval_steps_per_second": 6.926, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 21.884801864624023, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.4665, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 15.496908187866211, | |
| "learning_rate": 0.0, | |
| "loss": 6.0602, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "eval_loss": 1.3773027658462524, | |
| "eval_runtime": 26.0969, | |
| "eval_samples_per_second": 13.833, | |
| "eval_steps_per_second": 6.936, | |
| "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": 9814962075598848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |