| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 224, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 0.848931074142456, |
| "learning_rate": 9.53153893518325e-05, |
| "loss": 6.0403, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.975097894668579, |
| "learning_rate": 6.294095225512603e-05, |
| "loss": 5.4718, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5128205128205128, |
| "grad_norm": 2.3797974586486816, |
| "learning_rate": 2.132117818244771e-05, |
| "loss": 4.8283, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.789046287536621, |
| "learning_rate": 1.9026509541272275e-07, |
| "loss": 4.6286, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1355932203389831, |
| "grad_norm": 1.8822929859161377, |
| "learning_rate": 9.596765194911181e-05, |
| "loss": 5.0217, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3615819209039548, |
| "grad_norm": 1.4929884672164917, |
| "learning_rate": 9.236573524788887e-05, |
| "loss": 3.9458, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.5875706214689265, |
| "grad_norm": 0.9337669014930725, |
| "learning_rate": 8.774114695766286e-05, |
| "loss": 3.6254, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.8135593220338984, |
| "grad_norm": 0.8921490907669067, |
| "learning_rate": 8.22055205725199e-05, |
| "loss": 3.4809, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.022598870056497, |
| "grad_norm": 0.9192579984664917, |
| "learning_rate": 7.589248124491627e-05, |
| "loss": 3.4035, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.248587570621469, |
| "grad_norm": 1.1187790632247925, |
| "learning_rate": 6.895442019201897e-05, |
| "loss": 3.3861, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.4745762711864407, |
| "grad_norm": 1.2873858213424683, |
| "learning_rate": 6.15588161057485e-05, |
| "loss": 3.3066, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.7005649717514126, |
| "grad_norm": 1.34447181224823, |
| "learning_rate": 5.3884192364450325e-05, |
| "loss": 3.2884, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.926553672316384, |
| "grad_norm": 0.7228454947471619, |
| "learning_rate": 4.611580763554969e-05, |
| "loss": 3.2397, |
| "step": 130 |
| }, |
| { |
| "epoch": 3.135593220338983, |
| "grad_norm": 1.1347743272781372, |
| "learning_rate": 3.844118389425153e-05, |
| "loss": 3.1814, |
| "step": 140 |
| }, |
| { |
| "epoch": 3.361581920903955, |
| "grad_norm": 1.3022897243499756, |
| "learning_rate": 3.104557980798104e-05, |
| "loss": 3.1947, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.5875706214689265, |
| "grad_norm": 1.1423296928405762, |
| "learning_rate": 2.410751875508373e-05, |
| "loss": 3.2494, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.8135593220338984, |
| "grad_norm": 0.9820030927658081, |
| "learning_rate": 1.7794479427480117e-05, |
| "loss": 3.199, |
| "step": 170 |
| }, |
| { |
| "epoch": 4.022598870056497, |
| "grad_norm": 1.5156248807907104, |
| "learning_rate": 1.225885304233716e-05, |
| "loss": 3.1656, |
| "step": 180 |
| }, |
| { |
| "epoch": 4.248587570621469, |
| "grad_norm": 0.8429480195045471, |
| "learning_rate": 7.63426475211113e-06, |
| "loss": 3.2354, |
| "step": 190 |
| }, |
| { |
| "epoch": 4.47457627118644, |
| "grad_norm": 1.0040243864059448, |
| "learning_rate": 4.032348050888179e-06, |
| "loss": 3.216, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.700564971751413, |
| "grad_norm": 1.4402868747711182, |
| "learning_rate": 1.5400500400166939e-06, |
| "loss": 3.1459, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.926553672316384, |
| "grad_norm": 1.0170223712921143, |
| "learning_rate": 2.1753260154906973e-07, |
| "loss": 3.2043, |
| "step": 220 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 224, |
| "total_flos": 2.2662781232726016e+17, |
| "train_loss": 2.800803001437868, |
| "train_runtime": 303.5624, |
| "train_samples_per_second": 23.29, |
| "train_steps_per_second": 0.741 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 225, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.2662781232726016e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
