| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 5780, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00017301038062283736, |
| "grad_norm": 7.641876220703125, |
| "learning_rate": 0.0, |
| "loss": 3.1444, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.17301038062283736, |
| "grad_norm": 5.932699203491211, |
| "learning_rate": 3.4532871972318343e-06, |
| "loss": 2.8902, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.17301038062283736, |
| "eval_cosine_accuracy": 0.9446839690208435, |
| "eval_loss": 0.5921438336372375, |
| "eval_runtime": 34.6127, |
| "eval_samples_per_second": 274.726, |
| "eval_steps_per_second": 2.167, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3460207612456747, |
| "grad_norm": 5.819000244140625, |
| "learning_rate": 6.913494809688582e-06, |
| "loss": 2.3137, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.3460207612456747, |
| "eval_cosine_accuracy": 0.9536228775978088, |
| "eval_loss": 0.5212574601173401, |
| "eval_runtime": 34.0023, |
| "eval_samples_per_second": 279.658, |
| "eval_steps_per_second": 2.206, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5190311418685121, |
| "grad_norm": 6.0497145652771, |
| "learning_rate": 1.0373702422145328e-05, |
| "loss": 2.0646, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.5190311418685121, |
| "eval_cosine_accuracy": 0.9586707353591919, |
| "eval_loss": 0.48181453347206116, |
| "eval_runtime": 34.1002, |
| "eval_samples_per_second": 278.855, |
| "eval_steps_per_second": 2.199, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.6920415224913494, |
| "grad_norm": 8.783215522766113, |
| "learning_rate": 1.3833910034602079e-05, |
| "loss": 1.7373, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.6920415224913494, |
| "eval_cosine_accuracy": 0.9621411561965942, |
| "eval_loss": 0.45189711451530457, |
| "eval_runtime": 34.4171, |
| "eval_samples_per_second": 276.287, |
| "eval_steps_per_second": 2.179, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8650519031141869, |
| "grad_norm": 9.1194486618042, |
| "learning_rate": 1.7290657439446367e-05, |
| "loss": 1.2623, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.8650519031141869, |
| "eval_cosine_accuracy": 0.9628772735595703, |
| "eval_loss": 0.43156424164772034, |
| "eval_runtime": 34.3791, |
| "eval_samples_per_second": 276.592, |
| "eval_steps_per_second": 2.182, |
| "step": 5000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 28900, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 0.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
