| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23952095808383234, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023952095808383235, | |
| "grad_norm": 13388.2021484375, | |
| "learning_rate": 2e-05, | |
| "loss": 19.1507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023952095808383235, | |
| "eval_loss": 4.564117908477783, | |
| "eval_runtime": 0.5742, | |
| "eval_samples_per_second": 31.349, | |
| "eval_steps_per_second": 15.675, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04790419161676647, | |
| "grad_norm": 18001.2421875, | |
| "learning_rate": 4e-05, | |
| "loss": 18.2525, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "grad_norm": 8843.4833984375, | |
| "learning_rate": 6e-05, | |
| "loss": 17.6166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "eval_loss": 4.605753421783447, | |
| "eval_runtime": 0.0804, | |
| "eval_samples_per_second": 223.976, | |
| "eval_steps_per_second": 111.988, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09580838323353294, | |
| "grad_norm": 25227.427734375, | |
| "learning_rate": 8e-05, | |
| "loss": 18.2125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11976047904191617, | |
| "grad_norm": 21124.734375, | |
| "learning_rate": 0.0001, | |
| "loss": 18.0529, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 26537.466796875, | |
| "learning_rate": 0.00012, | |
| "loss": 17.3078, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "eval_loss": 4.449784278869629, | |
| "eval_runtime": 0.0961, | |
| "eval_samples_per_second": 187.222, | |
| "eval_steps_per_second": 93.611, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16766467065868262, | |
| "grad_norm": 10940.6943359375, | |
| "learning_rate": 0.00014, | |
| "loss": 17.916, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "grad_norm": 13475.0791015625, | |
| "learning_rate": 0.00016, | |
| "loss": 17.6, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "grad_norm": 20018.03515625, | |
| "learning_rate": 0.00018, | |
| "loss": 16.8487, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "eval_loss": 4.048277854919434, | |
| "eval_runtime": 0.0865, | |
| "eval_samples_per_second": 208.205, | |
| "eval_steps_per_second": 104.103, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23952095808383234, | |
| "grad_norm": 25917.783203125, | |
| "learning_rate": 0.0002, | |
| "loss": 17.272, | |
| "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": 1899013079040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |