| { |
| "best_metric": 0.2871530055999756, |
| "best_model_checkpoint": "./opt_trained/checkpoint-1365", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 3185, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.2876647710800171, |
| "eval_runtime": 209.7509, |
| "eval_samples_per_second": 26.999, |
| "eval_steps_per_second": 6.751, |
| "step": 455 |
| }, |
| { |
| "epoch": 1.098901098901099, |
| "grad_norm": 1.794409990310669, |
| "learning_rate": 3.9702779780337476e-05, |
| "loss": 0.2912, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.2875623404979706, |
| "eval_runtime": 210.8389, |
| "eval_samples_per_second": 26.859, |
| "eval_steps_per_second": 6.716, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.197802197802198, |
| "grad_norm": 2.2356488704681396, |
| "learning_rate": 3.881995310724753e-05, |
| "loss": 0.2884, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.2871530055999756, |
| "eval_runtime": 209.7649, |
| "eval_samples_per_second": 26.997, |
| "eval_steps_per_second": 6.75, |
| "step": 1365 |
| }, |
| { |
| "epoch": 3.2967032967032965, |
| "grad_norm": 2.192455530166626, |
| "learning_rate": 3.7377759374500135e-05, |
| "loss": 0.2862, |
| "step": 1500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.2879991829395294, |
| "eval_runtime": 209.596, |
| "eval_samples_per_second": 27.019, |
| "eval_steps_per_second": 6.756, |
| "step": 1820 |
| }, |
| { |
| "epoch": 4.395604395604396, |
| "grad_norm": 2.1842732429504395, |
| "learning_rate": 3.541906349589959e-05, |
| "loss": 0.2843, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.28739306330680847, |
| "eval_runtime": 210.4986, |
| "eval_samples_per_second": 26.903, |
| "eval_steps_per_second": 6.727, |
| "step": 2275 |
| }, |
| { |
| "epoch": 5.4945054945054945, |
| "grad_norm": 2.2816271781921387, |
| "learning_rate": 3.300208187337489e-05, |
| "loss": 0.282, |
| "step": 2500 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.28762978315353394, |
| "eval_runtime": 210.5772, |
| "eval_samples_per_second": 26.893, |
| "eval_steps_per_second": 6.724, |
| "step": 2730 |
| }, |
| { |
| "epoch": 6.593406593406593, |
| "grad_norm": 2.745879650115967, |
| "learning_rate": 3.0198652087802722e-05, |
| "loss": 0.28, |
| "step": 3000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.288526713848114, |
| "eval_runtime": 210.0108, |
| "eval_samples_per_second": 26.965, |
| "eval_steps_per_second": 6.743, |
| "step": 3185 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 9100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 1.40898892829184e+17, |
| "train_batch_size": 14, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
