| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.30208, |
| "eval_steps": 100, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00256, |
| "grad_norm": 14.952803611755371, |
| "learning_rate": 0.0, |
| "loss": 1.0238, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 2.3984222412109375, |
| "learning_rate": 4.212765957446809e-06, |
| "loss": 0.6317, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.256, |
| "eval_loss": 0.3901349604129791, |
| "eval_runtime": 76.1829, |
| "eval_samples_per_second": 16.408, |
| "eval_steps_per_second": 8.204, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 2.158310890197754, |
| "learning_rate": 8.46808510638298e-06, |
| "loss": 0.4072, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.512, |
| "eval_loss": 0.3636568784713745, |
| "eval_runtime": 76.1675, |
| "eval_samples_per_second": 16.411, |
| "eval_steps_per_second": 8.206, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 2.0863559246063232, |
| "learning_rate": 9.885572470188207e-06, |
| "loss": 0.3826, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.768, |
| "eval_loss": 0.3526187837123871, |
| "eval_runtime": 76.2073, |
| "eval_samples_per_second": 16.403, |
| "eval_steps_per_second": 8.201, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.02304, |
| "grad_norm": 2.2784180641174316, |
| "learning_rate": 9.2645127658466e-06, |
| "loss": 0.3653, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.02304, |
| "eval_loss": 0.3516922891139984, |
| "eval_runtime": 76.1603, |
| "eval_samples_per_second": 16.413, |
| "eval_steps_per_second": 8.206, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.27904, |
| "grad_norm": 2.1337344646453857, |
| "learning_rate": 8.169538606063647e-06, |
| "loss": 0.3122, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.27904, |
| "eval_loss": 0.3464358150959015, |
| "eval_runtime": 76.195, |
| "eval_samples_per_second": 16.405, |
| "eval_steps_per_second": 8.203, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.53504, |
| "grad_norm": 2.1311352252960205, |
| "learning_rate": 6.722334251421665e-06, |
| "loss": 0.3107, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.53504, |
| "eval_loss": 0.34351983666419983, |
| "eval_runtime": 76.1475, |
| "eval_samples_per_second": 16.415, |
| "eval_steps_per_second": 8.208, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.79104, |
| "grad_norm": 1.905997633934021, |
| "learning_rate": 5.083727233997775e-06, |
| "loss": 0.301, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.79104, |
| "eval_loss": 0.3379676640033722, |
| "eval_runtime": 76.2095, |
| "eval_samples_per_second": 16.402, |
| "eval_steps_per_second": 8.201, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.04608, |
| "grad_norm": 2.4192748069763184, |
| "learning_rate": 3.4358156257133644e-06, |
| "loss": 0.2912, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.04608, |
| "eval_loss": 0.35626986622810364, |
| "eval_runtime": 76.1989, |
| "eval_samples_per_second": 16.404, |
| "eval_steps_per_second": 8.202, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.30208, |
| "grad_norm": 2.3621625900268555, |
| "learning_rate": 1.9617315158214363e-06, |
| "loss": 0.2201, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.30208, |
| "eval_loss": 0.3607979118824005, |
| "eval_runtime": 76.2076, |
| "eval_samples_per_second": 16.403, |
| "eval_steps_per_second": 8.201, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1173, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 900, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.5574906692226253e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
