| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.394648829431438, | |
| "eval_steps": 200, | |
| "global_step": 236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1e-06, | |
| "loss": 0.8728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.8297, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.7256, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6035, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.99770621018718e-05, | |
| "loss": 0.4872, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.990831856044326e-05, | |
| "loss": 0.476, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.979397962002776e-05, | |
| "loss": 0.4522, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.9634394973287605e-05, | |
| "loss": 0.4198, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.943005269173876e-05, | |
| "loss": 0.434, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.9181577733039554e-05, | |
| "loss": 0.4245, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.8889730029628665e-05, | |
| "loss": 0.4332, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.8555402164558058e-05, | |
| "loss": 0.418, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.8179616641629125e-05, | |
| "loss": 0.4121, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.776352275818093e-05, | |
| "loss": 0.3505, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 2.730839309009485e-05, | |
| "loss": 0.3558, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.6815619599765775e-05, | |
| "loss": 0.3613, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 2.628670937894323e-05, | |
| "loss": 0.3646, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.572328003946244e-05, | |
| "loss": 0.3456, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.512705476596226e-05, | |
| "loss": 0.3435, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.4499857045720705e-05, | |
| "loss": 0.3614, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.3843605091726184e-05, | |
| "loss": 0.3374, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.5180116295814514, | |
| "eval_runtime": 6.8175, | |
| "eval_samples_per_second": 20.535, | |
| "eval_steps_per_second": 5.134, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.3160305976040984e-05, | |
| "loss": 0.3647, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.2452049491399336e-05, | |
| "loss": 0.3271, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.1721001759813677e-05, | |
| "loss": 0.3519, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "step": 236, | |
| "total_flos": 4.241630717752115e+16, | |
| "train_loss": 0.4328786596908408, | |
| "train_runtime": 504.1662, | |
| "train_samples_per_second": 4.744, | |
| "train_steps_per_second": 1.186 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 598, | |
| "num_train_epochs": 2, | |
| "save_steps": 200, | |
| "total_flos": 4.241630717752115e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |