| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 28.571428571428573, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 2.8734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 2.7517, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.2084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 1.7218, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.3608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 1.046, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.8672, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 7.4e-06, | |
| "loss": 0.6926, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.5528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.4595, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 9.955555555555556e-06, | |
| "loss": 0.3677, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 9.844444444444446e-06, | |
| "loss": 0.2566, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 9.733333333333334e-06, | |
| "loss": 0.2176, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 9.622222222222222e-06, | |
| "loss": 0.1514, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 9.511111111111112e-06, | |
| "loss": 0.0989, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.0644, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 9.28888888888889e-06, | |
| "loss": 0.0445, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 9.17777777777778e-06, | |
| "loss": 0.0279, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 9.066666666666667e-06, | |
| "loss": 0.0191, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 8.955555555555555e-06, | |
| "loss": 0.0139, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_loss": 1.0302417278289795, | |
| "eval_runtime": 1389.5619, | |
| "eval_samples_per_second": 0.368, | |
| "eval_steps_per_second": 0.023, | |
| "eval_wer": 50.12106537530266, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.844444444444445e-06, | |
| "loss": 0.0104, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 8.733333333333333e-06, | |
| "loss": 0.0091, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.43, | |
| "learning_rate": 8.622222222222223e-06, | |
| "loss": 0.0062, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 8.511111111111113e-06, | |
| "loss": 0.0056, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 17.86, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0052, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 8.288888888888889e-06, | |
| "loss": 0.0047, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 8.177777777777779e-06, | |
| "loss": 0.0049, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 8.066666666666667e-06, | |
| "loss": 0.0042, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 20.71, | |
| "learning_rate": 7.955555555555557e-06, | |
| "loss": 0.0033, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 7.844444444444446e-06, | |
| "loss": 0.0028, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 22.14, | |
| "learning_rate": 7.733333333333334e-06, | |
| "loss": 0.002, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 7.622222222222223e-06, | |
| "loss": 0.0018, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 23.57, | |
| "learning_rate": 7.511111111111111e-06, | |
| "loss": 0.0016, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 7.4e-06, | |
| "loss": 0.0014, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 7.28888888888889e-06, | |
| "loss": 0.0013, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 7.177777777777778e-06, | |
| "loss": 0.0013, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 26.43, | |
| "learning_rate": 7.066666666666667e-06, | |
| "loss": 0.0012, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 6.955555555555557e-06, | |
| "loss": 0.0011, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 27.86, | |
| "learning_rate": 6.844444444444445e-06, | |
| "loss": 0.0011, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 6.733333333333334e-06, | |
| "loss": 0.0011, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "eval_loss": 1.2129117250442505, | |
| "eval_runtime": 1370.5005, | |
| "eval_samples_per_second": 0.374, | |
| "eval_steps_per_second": 0.023, | |
| "eval_wer": 49.78056900726393, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 500, | |
| "num_train_epochs": 72, | |
| "total_flos": 1.257793488027648e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |