| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 165, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18306636155606407, |
| "grad_norm": 1.5561127662658691, |
| "learning_rate": 5.294117647058824e-06, |
| "loss": 0.526791763305664, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.36613272311212813, |
| "grad_norm": 1.0860607624053955, |
| "learning_rate": 9.99549483102341e-06, |
| "loss": 0.49164934158325196, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5491990846681922, |
| "grad_norm": 0.888668417930603, |
| "learning_rate": 9.838664734667496e-06, |
| "loss": 0.4605508804321289, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7322654462242563, |
| "grad_norm": 0.8182327747344971, |
| "learning_rate": 9.464629290747844e-06, |
| "loss": 0.44659934043884275, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.9153318077803204, |
| "grad_norm": 0.8085665106773376, |
| "learning_rate": 8.890178771592198e-06, |
| "loss": 0.4344169616699219, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.091533180778032, |
| "grad_norm": 0.8246002197265625, |
| "learning_rate": 8.141099986478212e-06, |
| "loss": 0.37548739910125734, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.2745995423340961, |
| "grad_norm": 0.8123958110809326, |
| "learning_rate": 7.251018724088367e-06, |
| "loss": 0.32389447689056394, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.4576659038901603, |
| "grad_norm": 0.8456404209136963, |
| "learning_rate": 6.259890306925627e-06, |
| "loss": 0.3151419639587402, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.6407322654462244, |
| "grad_norm": 0.8434184789657593, |
| "learning_rate": 5.212206015980742e-06, |
| "loss": 0.3167291164398193, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.8237986270022883, |
| "grad_norm": 0.8572152853012085, |
| "learning_rate": 4.154995898390756e-06, |
| "loss": 0.31630702018737794, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.9608255624771118, |
| "learning_rate": 3.1357176110984578e-06, |
| "loss": 0.31241421699523925, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.183066361556064, |
| "grad_norm": 0.8458835482597351, |
| "learning_rate": 2.2001260693120236e-06, |
| "loss": 0.23527765274047852, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.3661327231121283, |
| "grad_norm": 0.8755936026573181, |
| "learning_rate": 1.390219530227378e-06, |
| "loss": 0.22828168869018556, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.5491990846681922, |
| "grad_norm": 0.82603520154953, |
| "learning_rate": 7.423543113334436e-07, |
| "loss": 0.22503767013549805, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.732265446224256, |
| "grad_norm": 0.8047221899032593, |
| "learning_rate": 2.85612772694579e-07, |
| "loss": 0.22890465259552, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.9153318077803205, |
| "grad_norm": 0.8530130982398987, |
| "learning_rate": 4.0497823705615836e-08, |
| "loss": 0.22411110401153564, |
| "step": 160 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 165, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 7.087560323258909e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
