| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 58, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08733624454148471, |
| "grad_norm": 4.145501613616943, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.4128, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.17467248908296942, |
| "grad_norm": 5.076199531555176, |
| "learning_rate": 9.992134075089085e-06, |
| "loss": 0.3862, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.26200873362445415, |
| "grad_norm": 4.170598983764648, |
| "learning_rate": 9.944154131125643e-06, |
| "loss": 0.3491, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.34934497816593885, |
| "grad_norm": 3.074150562286377, |
| "learning_rate": 9.852982837266955e-06, |
| "loss": 0.2981, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4366812227074236, |
| "grad_norm": 2.965071201324463, |
| "learning_rate": 9.719416651541839e-06, |
| "loss": 0.2567, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5240174672489083, |
| "grad_norm": 2.526233673095703, |
| "learning_rate": 9.544622387061055e-06, |
| "loss": 0.1965, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.611353711790393, |
| "grad_norm": 2.4919331073760986, |
| "learning_rate": 9.330127018922195e-06, |
| "loss": 0.2105, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6986899563318777, |
| "grad_norm": 2.2303683757781982, |
| "learning_rate": 9.077804344796302e-06, |
| "loss": 0.1874, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7860262008733624, |
| "grad_norm": 2.2244021892547607, |
| "learning_rate": 8.789858615727266e-06, |
| "loss": 0.1631, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.8733624454148472, |
| "grad_norm": 1.7161848545074463, |
| "learning_rate": 8.46880528014271e-06, |
| "loss": 0.1682, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9606986899563319, |
| "grad_norm": 2.00079083442688, |
| "learning_rate": 8.117449009293668e-06, |
| "loss": 0.1569, |
| "step": 55 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 174, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.746584933774131e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
