| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.615384615384615, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 4.175181381576624, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.4696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 1.503753521929454, | |
| "learning_rate": 0.00019730448705798239, | |
| "loss": 3.0165, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "eval_loss": 2.010913372039795, | |
| "eval_runtime": 2.4589, | |
| "eval_samples_per_second": 8.134, | |
| "eval_steps_per_second": 1.22, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.8730564384326724, | |
| "learning_rate": 0.0001686241637868734, | |
| "loss": 1.7821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 1.796317458152771, | |
| "eval_runtime": 1.2677, | |
| "eval_samples_per_second": 15.777, | |
| "eval_steps_per_second": 2.367, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.1576812971715764, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 1.6447, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "eval_loss": 1.6973062753677368, | |
| "eval_runtime": 1.2497, | |
| "eval_samples_per_second": 16.004, | |
| "eval_steps_per_second": 2.401, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 1.5774660880973734, | |
| "learning_rate": 6.039202339608432e-05, | |
| "loss": 1.3804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "eval_loss": 1.6806764602661133, | |
| "eval_runtime": 1.2646, | |
| "eval_samples_per_second": 15.815, | |
| "eval_steps_per_second": 2.372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 2.5198228193911474, | |
| "learning_rate": 1.6451218858706374e-05, | |
| "loss": 1.2411, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "eval_loss": 1.7175524234771729, | |
| "eval_runtime": 1.2668, | |
| "eval_samples_per_second": 15.788, | |
| "eval_steps_per_second": 2.368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 2.2100441487221283, | |
| "learning_rate": 0.0, | |
| "loss": 1.22, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "eval_loss": 1.7226861715316772, | |
| "eval_runtime": 1.2657, | |
| "eval_samples_per_second": 15.801, | |
| "eval_steps_per_second": 2.37, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "step": 30, | |
| "total_flos": 689460707328.0, | |
| "train_loss": 1.7292537927627563, | |
| "train_runtime": 112.1921, | |
| "train_samples_per_second": 4.278, | |
| "train_steps_per_second": 0.267 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 689460707328.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |