| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.7199999999999998, |
| "eval_steps": 25, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 90.5236587524414, |
| "learning_rate": 0.0002, |
| "loss": 9.8877, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 60.02783966064453, |
| "learning_rate": 0.0002, |
| "loss": 9.4404, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 102.20321655273438, |
| "learning_rate": 0.0002, |
| "loss": 8.8638, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 82.49861145019531, |
| "learning_rate": 0.0002, |
| "loss": 8.0872, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 81.60125732421875, |
| "learning_rate": 0.0002, |
| "loss": 7.2292, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 52.2266960144043, |
| "learning_rate": 0.0002, |
| "loss": 7.0472, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 75.96226501464844, |
| "learning_rate": 0.0002, |
| "loss": 7.2919, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 70.42675018310547, |
| "learning_rate": 0.0002, |
| "loss": 7.1477, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 52.09629821777344, |
| "learning_rate": 0.0002, |
| "loss": 6.899, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 28.537267684936523, |
| "learning_rate": 0.0002, |
| "loss": 6.7016, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 29.203533172607422, |
| "learning_rate": 0.0002, |
| "loss": 6.1981, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 23.664485931396484, |
| "learning_rate": 0.0002, |
| "loss": 6.3924, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 9.723264694213867, |
| "learning_rate": 0.0002, |
| "loss": 3.2305, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.08, |
| "grad_norm": 18.88973045349121, |
| "learning_rate": 0.0002, |
| "loss": 6.3592, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.16, |
| "grad_norm": 20.770938873291016, |
| "learning_rate": 0.0002, |
| "loss": 6.1203, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 10.570067405700684, |
| "learning_rate": 0.0002, |
| "loss": 6.4217, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.32, |
| "grad_norm": 13.833821296691895, |
| "learning_rate": 0.0002, |
| "loss": 6.439, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 19.160987854003906, |
| "learning_rate": 0.0002, |
| "loss": 5.8242, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.48, |
| "grad_norm": 10.99656867980957, |
| "learning_rate": 0.0002, |
| "loss": 6.1287, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.56, |
| "grad_norm": 16.58768081665039, |
| "learning_rate": 0.0002, |
| "loss": 6.408, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6400000000000001, |
| "grad_norm": 11.93716812133789, |
| "learning_rate": 0.0002, |
| "loss": 6.3103, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.72, |
| "grad_norm": 9.053961753845215, |
| "learning_rate": 0.0002, |
| "loss": 6.2692, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 19.67817497253418, |
| "learning_rate": 0.0002, |
| "loss": 5.9086, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.88, |
| "grad_norm": 10.540741920471191, |
| "learning_rate": 0.0002, |
| "loss": 6.1991, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.96, |
| "grad_norm": 8.84691333770752, |
| "learning_rate": 0.0002, |
| "loss": 6.1812, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.96, |
| "eval_clap": 0.13957726955413818, |
| "eval_loss": 5.896897315979004, |
| "eval_runtime": 206.5396, |
| "eval_samples_per_second": 0.155, |
| "eval_steps_per_second": 0.155, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 3.9374849796295166, |
| "learning_rate": 0.0002, |
| "loss": 3.1408, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.08, |
| "grad_norm": 6.420533180236816, |
| "learning_rate": 0.0002, |
| "loss": 6.196, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.16, |
| "grad_norm": 10.713640213012695, |
| "learning_rate": 0.0002, |
| "loss": 6.4188, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.24, |
| "grad_norm": 13.720645904541016, |
| "learning_rate": 0.0002, |
| "loss": 5.9628, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.32, |
| "grad_norm": 13.317567825317383, |
| "learning_rate": 0.0002, |
| "loss": 6.1474, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 11.3407621383667, |
| "learning_rate": 0.0002, |
| "loss": 5.9697, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.48, |
| "grad_norm": 9.393121719360352, |
| "learning_rate": 0.0002, |
| "loss": 6.1152, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.56, |
| "grad_norm": 14.54958438873291, |
| "learning_rate": 0.0002, |
| "loss": 5.7045, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.64, |
| "grad_norm": 13.25341796875, |
| "learning_rate": 0.0002, |
| "loss": 6.2739, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.7199999999999998, |
| "grad_norm": 10.817360877990723, |
| "learning_rate": 0.0002, |
| "loss": 5.9946, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 18.011138916015625, |
| "learning_rate": 0.0002, |
| "loss": 5.5463, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.88, |
| "grad_norm": 18.857688903808594, |
| "learning_rate": 0.0002, |
| "loss": 6.4324, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 10.496877670288086, |
| "learning_rate": 0.0002, |
| "loss": 5.9915, |
| "step": 38 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.552528381347656, |
| "learning_rate": 0.0002, |
| "loss": 3.1022, |
| "step": 39 |
| }, |
| { |
| "epoch": 3.08, |
| "grad_norm": 9.081900596618652, |
| "learning_rate": 0.0002, |
| "loss": 6.0394, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.16, |
| "grad_norm": 13.829048156738281, |
| "learning_rate": 0.0002, |
| "loss": 5.9436, |
| "step": 41 |
| }, |
| { |
| "epoch": 3.24, |
| "grad_norm": 6.3993120193481445, |
| "learning_rate": 0.0002, |
| "loss": 6.276, |
| "step": 42 |
| }, |
| { |
| "epoch": 3.32, |
| "grad_norm": 20.436588287353516, |
| "learning_rate": 0.0002, |
| "loss": 5.7975, |
| "step": 43 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 7.475179672241211, |
| "learning_rate": 0.0002, |
| "loss": 6.1817, |
| "step": 44 |
| }, |
| { |
| "epoch": 3.48, |
| "grad_norm": 17.927181243896484, |
| "learning_rate": 0.0002, |
| "loss": 5.8574, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.56, |
| "grad_norm": 18.49729347229004, |
| "learning_rate": 0.0002, |
| "loss": 5.4645, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.64, |
| "grad_norm": 16.93431854248047, |
| "learning_rate": 0.0002, |
| "loss": 5.7863, |
| "step": 47 |
| }, |
| { |
| "epoch": 3.7199999999999998, |
| "grad_norm": 10.554439544677734, |
| "learning_rate": 0.0002, |
| "loss": 6.1658, |
| "step": 48 |
| }, |
| { |
| "epoch": 3.7199999999999998, |
| "step": 48, |
| "total_flos": 180716776957944.0, |
| "train_loss": 6.281136025985082, |
| "train_runtime": 1764.029, |
| "train_samples_per_second": 0.907, |
| "train_steps_per_second": 0.027 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 48, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 180716776957944.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
