| { | |
| "best_metric": 1.0789222717285156, | |
| "best_model_checkpoint": "output/morgenshtern/checkpoint-97", | |
| "epoch": 1.0, | |
| "global_step": 97, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013630248621914493, | |
| "loss": 1.1495, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013363342974500022, | |
| "loss": 1.133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012926267066407974, | |
| "loss": 1.1617, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012330457680460286, | |
| "loss": 1.1061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001159150511212779, | |
| "loss": 1.2273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010728745224777217, | |
| "loss": 1.0743, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.764753496206386e-05, | |
| "loss": 1.2278, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.724754295541321e-05, | |
| "loss": 1.1852, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.635960847699664e-05, | |
| "loss": 1.1321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.526863156294906e-05, | |
| "loss": 1.0477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.426482517605479e-05, | |
| "loss": 1.1788, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.363612132430507e-05, | |
| "loss": 1.0456, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.36606368642472e-05, | |
| "loss": 1.1629, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.4599396133304144e-05, | |
| "loss": 1.1195, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.6689500834906116e-05, | |
| "loss": 0.9719, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0137925897200545e-05, | |
| "loss": 1.159, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.116103646510543e-06, | |
| "loss": 1.0041, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.7554380092209137e-06, | |
| "loss": 1.0917, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.4386612009299613e-07, | |
| "loss": 1.0484, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.0789222717285156, | |
| "eval_runtime": 7.1308, | |
| "eval_samples_per_second": 21.035, | |
| "eval_steps_per_second": 2.664, | |
| "step": 97 | |
| } | |
| ], | |
| "max_steps": 1552, | |
| "num_train_epochs": 16, | |
| "total_flos": 101381308416000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |