| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 0.08429125089599755, |
| "learning_rate": 1.97900991538253e-05, |
| "loss": 0.3348, |
| "num_tokens": 24933352.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 0.06528096461855616, |
| "learning_rate": 1.9152411726209176e-05, |
| "loss": 0.303, |
| "num_tokens": 50188017.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.06521160595904736, |
| "learning_rate": 1.8114719988013612e-05, |
| "loss": 0.2864, |
| "num_tokens": 75140399.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 0.05540266810445945, |
| "learning_rate": 1.6722376047595163e-05, |
| "loss": 0.2824, |
| "num_tokens": 99776061.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.05315474648918997, |
| "learning_rate": 1.503623201635761e-05, |
| "loss": 0.2718, |
| "num_tokens": 124720824.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.05146812381778093, |
| "learning_rate": 1.3129980479482783e-05, |
| "loss": 0.2703, |
| "num_tokens": 149955889.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 0.04713721042272043, |
| "learning_rate": 1.1086933776341853e-05, |
| "loss": 0.2696, |
| "num_tokens": 174459310.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.047103672604080514, |
| "learning_rate": 8.996382851487851e-06, |
| "loss": 0.2154, |
| "num_tokens": 198580436.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.0447108501453802, |
| "learning_rate": 6.949694811913226e-06, |
| "loss": 0.1705, |
| "num_tokens": 223443856.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.04937019794910998, |
| "learning_rate": 5.036319746046232e-06, |
| "loss": 0.1682, |
| "num_tokens": 248274242.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4666666666666668, |
| "grad_norm": 0.04250386654279577, |
| "learning_rate": 3.3398813256574847e-06, |
| "loss": 0.164, |
| "num_tokens": 273552485.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.04257904418492056, |
| "learning_rate": 1.934522050132678e-06, |
| "loss": 0.1652, |
| "num_tokens": 298003892.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.7333333333333334, |
| "grad_norm": 0.03851105648922471, |
| "learning_rate": 8.816628634742441e-07, |
| "loss": 0.1608, |
| "num_tokens": 322917489.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.8666666666666667, |
| "grad_norm": 0.03846785998601379, |
| "learning_rate": 2.273187643180652e-07, |
| "loss": 0.1597, |
| "num_tokens": 348199040.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.038081991087767574, |
| "learning_rate": 8.772968862369447e-11, |
| "loss": 0.1596, |
| "num_tokens": 372855314.0, |
| "step": 750 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 750, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 150, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5726266708446413e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
