| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 126, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1593625498007968, |
| "grad_norm": 2.5085183893251894, |
| "learning_rate": 4.996516025803835e-06, |
| "loss": 0.9423772811889648, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3187250996015936, |
| "grad_norm": 0.6745998643856522, |
| "learning_rate": 4.875593500152538e-06, |
| "loss": 0.7159957885742188, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.47808764940239046, |
| "grad_norm": 0.3994331007892087, |
| "learning_rate": 4.590061770891086e-06, |
| "loss": 0.6354275226593018, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.6374501992031872, |
| "grad_norm": 0.35863572583668746, |
| "learning_rate": 4.159705851977521e-06, |
| "loss": 0.6005132675170899, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.796812749003984, |
| "grad_norm": 0.33318627857676825, |
| "learning_rate": 3.6143458894413463e-06, |
| "loss": 0.5814944267272949, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9561752988047809, |
| "grad_norm": 0.3151638684107094, |
| "learning_rate": 2.9917708691120705e-06, |
| "loss": 0.5695013999938965, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.1115537848605577, |
| "grad_norm": 0.31796133604968607, |
| "learning_rate": 2.3351201489132617e-06, |
| "loss": 0.5564343452453613, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2709163346613546, |
| "grad_norm": 0.33580557405602346, |
| "learning_rate": 1.6898942541220858e-06, |
| "loss": 0.5476729393005371, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.4302788844621515, |
| "grad_norm": 0.29699455714161394, |
| "learning_rate": 1.1008020630392302e-06, |
| "loss": 0.5446982383728027, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5896414342629481, |
| "grad_norm": 0.29864817516261594, |
| "learning_rate": 6.086628473207607e-07, |
| "loss": 0.5441547393798828, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.749003984063745, |
| "grad_norm": 0.4352038127392715, |
| "learning_rate": 2.4757783024395244e-07, |
| "loss": 0.5438386917114257, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.908366533864542, |
| "grad_norm": 0.2853434288016432, |
| "learning_rate": 4.256725079024554e-08, |
| "loss": 0.5426751136779785, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 126, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.9294785839824896e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
