| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012562024998429747, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002512404999685949, | |
| "eval_loss": 3.1154022216796875, | |
| "eval_runtime": 81.4562, | |
| "eval_samples_per_second": 20.575, | |
| "eval_steps_per_second": 10.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012562024998429746, | |
| "grad_norm": 1.319533109664917, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2452, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025124049996859492, | |
| "grad_norm": 1.8629536628723145, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0594, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025124049996859492, | |
| "eval_loss": 2.758345127105713, | |
| "eval_runtime": 81.126, | |
| "eval_samples_per_second": 20.659, | |
| "eval_steps_per_second": 10.33, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003768607499528924, | |
| "grad_norm": 2.178535223007202, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4068, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0050248099993718985, | |
| "grad_norm": 1.5113375186920166, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0050248099993718985, | |
| "eval_loss": 1.6192883253097534, | |
| "eval_runtime": 80.9839, | |
| "eval_samples_per_second": 20.695, | |
| "eval_steps_per_second": 10.348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006281012499214873, | |
| "grad_norm": 1.503976583480835, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5467, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007537214999057848, | |
| "grad_norm": 1.651665449142456, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4176, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007537214999057848, | |
| "eval_loss": 1.496555209159851, | |
| "eval_runtime": 81.4583, | |
| "eval_samples_per_second": 20.575, | |
| "eval_steps_per_second": 10.287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008793417498900823, | |
| "grad_norm": 1.4830455780029297, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010049619998743797, | |
| "grad_norm": 1.5435250997543335, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5101, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010049619998743797, | |
| "eval_loss": 1.459788203239441, | |
| "eval_runtime": 81.209, | |
| "eval_samples_per_second": 20.638, | |
| "eval_steps_per_second": 10.319, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011305822498586773, | |
| "grad_norm": 1.7534375190734863, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4827, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012562024998429747, | |
| "grad_norm": 1.682039737701416, | |
| "learning_rate": 0.0, | |
| "loss": 1.4508, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012562024998429747, | |
| "eval_loss": 1.455602765083313, | |
| "eval_runtime": 80.9896, | |
| "eval_samples_per_second": 20.694, | |
| "eval_steps_per_second": 10.347, | |
| "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": 3428033180467200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |