| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5133470225872689, |
| "eval_steps": 500, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.034223134839151265, |
| "grad_norm": 0.4172394275665283, |
| "learning_rate": 0.00019800000000000002, |
| "loss": 1.1892, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06844626967830253, |
| "grad_norm": 0.41112303733825684, |
| "learning_rate": 0.00019754247929410995, |
| "loss": 1.0497, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1026694045174538, |
| "grad_norm": 0.4096732437610626, |
| "learning_rate": 0.00019019402315000752, |
| "loss": 1.0129, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13689253935660506, |
| "grad_norm": 0.34457647800445557, |
| "learning_rate": 0.00017832286206772186, |
| "loss": 1.0343, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.17111567419575632, |
| "grad_norm": 0.4272993206977844, |
| "learning_rate": 0.00016252426563357055, |
| "loss": 0.9878, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2053388090349076, |
| "grad_norm": 0.383188933134079, |
| "learning_rate": 0.00014359044144195547, |
| "loss": 1.0277, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.23956194387405885, |
| "grad_norm": 0.41364046931266785, |
| "learning_rate": 0.00012247081049860883, |
| "loss": 0.9947, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.2737850787132101, |
| "grad_norm": 0.4872409999370575, |
| "learning_rate": 0.00010022439928692875, |
| "loss": 0.9475, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3080082135523614, |
| "grad_norm": 0.4362848103046417, |
| "learning_rate": 7.796673575799224e-05, |
| "loss": 0.9456, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.34223134839151265, |
| "grad_norm": 0.44856351613998413, |
| "learning_rate": 5.681391210104916e-05, |
| "loss": 0.9583, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.37645448323066394, |
| "grad_norm": 0.348608136177063, |
| "learning_rate": 3.782661922075803e-05, |
| "loss": 0.914, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4106776180698152, |
| "grad_norm": 0.39325082302093506, |
| "learning_rate": 2.195695926616702e-05, |
| "loss": 0.9214, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.44490075290896647, |
| "grad_norm": 0.5586904883384705, |
| "learning_rate": 1.0000703253328414e-05, |
| "loss": 0.9282, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.4791238877481177, |
| "grad_norm": 0.3972143530845642, |
| "learning_rate": 2.5573877837031137e-06, |
| "loss": 0.9231, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.5133470225872689, |
| "grad_norm": 0.4245308041572571, |
| "learning_rate": 2.5177551682409317e-10, |
| "loss": 0.8962, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 1500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.770604684680233e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
