| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036869757581343902, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000368697575813439, | |
| "grad_norm": 1677.300537109375, | |
| "learning_rate": 2e-05, | |
| "loss": 12.6957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000368697575813439, | |
| "eval_loss": 3.3392767906188965, | |
| "eval_runtime": 7.9206, | |
| "eval_samples_per_second": 144.181, | |
| "eval_steps_per_second": 72.091, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000737395151626878, | |
| "grad_norm": 1517.3170166015625, | |
| "learning_rate": 4e-05, | |
| "loss": 15.0632, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011060927274403171, | |
| "grad_norm": 1854.6907958984375, | |
| "learning_rate": 6e-05, | |
| "loss": 15.58, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011060927274403171, | |
| "eval_loss": 3.330427885055542, | |
| "eval_runtime": 7.6187, | |
| "eval_samples_per_second": 149.894, | |
| "eval_steps_per_second": 74.947, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001474790303253756, | |
| "grad_norm": 3209.78515625, | |
| "learning_rate": 8e-05, | |
| "loss": 13.4768, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018434878790671951, | |
| "grad_norm": 1317.3623046875, | |
| "learning_rate": 0.0001, | |
| "loss": 14.8405, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0022121854548806342, | |
| "grad_norm": 5505.111328125, | |
| "learning_rate": 0.00012, | |
| "loss": 12.3499, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022121854548806342, | |
| "eval_loss": 3.3136801719665527, | |
| "eval_runtime": 7.5736, | |
| "eval_samples_per_second": 150.787, | |
| "eval_steps_per_second": 75.394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002580883030694073, | |
| "grad_norm": 1388.295166015625, | |
| "learning_rate": 0.00014, | |
| "loss": 13.092, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002949580606507512, | |
| "grad_norm": 3225.14892578125, | |
| "learning_rate": 0.00016, | |
| "loss": 13.2834, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0033182781823209513, | |
| "grad_norm": 1204.6895751953125, | |
| "learning_rate": 0.00018, | |
| "loss": 12.4885, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0033182781823209513, | |
| "eval_loss": 3.274616003036499, | |
| "eval_runtime": 7.5691, | |
| "eval_samples_per_second": 150.876, | |
| "eval_steps_per_second": 75.438, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036869757581343902, | |
| "grad_norm": 1386.0103759765625, | |
| "learning_rate": 0.0002, | |
| "loss": 11.0184, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 30687834931200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |