| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05052631578947368, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 4.296731948852539, | |
| "eval_runtime": 23.3737, | |
| "eval_samples_per_second": 10.696, | |
| "eval_steps_per_second": 5.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 1.6655466556549072, | |
| "learning_rate": 3e-05, | |
| "loss": 3.8295, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "eval_loss": 4.225728988647461, | |
| "eval_runtime": 23.3758, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 5.347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 1.926052212715149, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7686, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 2.213322877883911, | |
| "learning_rate": 9e-05, | |
| "loss": 3.6866, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "eval_loss": 3.397361993789673, | |
| "eval_runtime": 23.3697, | |
| "eval_samples_per_second": 10.698, | |
| "eval_steps_per_second": 5.349, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020210526315789474, | |
| "grad_norm": 2.382171392440796, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.2415, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 1.840626835823059, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6022, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "eval_loss": 2.4173471927642822, | |
| "eval_runtime": 23.3746, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 5.348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03031578947368421, | |
| "grad_norm": 1.4523637294769287, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9354, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "eval_loss": 1.888671875, | |
| "eval_runtime": 23.3614, | |
| "eval_samples_per_second": 10.701, | |
| "eval_steps_per_second": 5.351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03536842105263158, | |
| "grad_norm": 1.4428808689117432, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.5744, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "grad_norm": 1.6106152534484863, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.4784, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 1.6619267463684082, | |
| "eval_runtime": 23.3713, | |
| "eval_samples_per_second": 10.697, | |
| "eval_steps_per_second": 5.348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04547368421052632, | |
| "grad_norm": 1.8915555477142334, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.4925, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 2.1500985622406006, | |
| "learning_rate": 0.0, | |
| "loss": 1.5562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "eval_loss": 1.603967308998108, | |
| "eval_runtime": 23.3786, | |
| "eval_samples_per_second": 10.694, | |
| "eval_steps_per_second": 5.347, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90433766408192e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |