| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 11.11111111111111, |
| "eval_steps": 200, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05555555555555555, |
| "eval_loss": 3.0254549980163574, |
| "eval_runtime": 19.3939, |
| "eval_samples_per_second": 77.395, |
| "eval_steps_per_second": 1.959, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.7109375, |
| "learning_rate": 0.0001, |
| "loss": 2.2097, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.71875, |
| "learning_rate": 0.0002, |
| "loss": 1.9869, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.000199658449300667, |
| "loss": 1.6439, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 1.40625, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 1.3908, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00019694002659393305, |
| "loss": 0.9319, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 0.6271, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.888888888888889, |
| "grad_norm": 0.89453125, |
| "learning_rate": 0.00019157733266550575, |
| "loss": 0.4473, |
| "step": 70 |
| }, |
| { |
| "epoch": 4.444444444444445, |
| "grad_norm": 0.76953125, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 0.247, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.74609375, |
| "learning_rate": 0.00018371664782625287, |
| "loss": 0.2054, |
| "step": 90 |
| }, |
| { |
| "epoch": 5.555555555555555, |
| "grad_norm": 0.49609375, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 0.096, |
| "step": 100 |
| }, |
| { |
| "epoch": 6.111111111111111, |
| "grad_norm": 0.244140625, |
| "learning_rate": 0.00017357239106731317, |
| "loss": 0.0806, |
| "step": 110 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.41796875, |
| "learning_rate": 0.00016772815716257412, |
| "loss": 0.0332, |
| "step": 120 |
| }, |
| { |
| "epoch": 7.222222222222222, |
| "grad_norm": 0.130859375, |
| "learning_rate": 0.0001614212712689668, |
| "loss": 0.0287, |
| "step": 130 |
| }, |
| { |
| "epoch": 7.777777777777778, |
| "grad_norm": 0.283203125, |
| "learning_rate": 0.00015469481581224272, |
| "loss": 0.0125, |
| "step": 140 |
| }, |
| { |
| "epoch": 8.333333333333334, |
| "grad_norm": 0.08740234375, |
| "learning_rate": 0.00014759473930370736, |
| "loss": 0.0085, |
| "step": 150 |
| }, |
| { |
| "epoch": 8.88888888888889, |
| "grad_norm": 0.06591796875, |
| "learning_rate": 0.00014016954246529696, |
| "loss": 0.0051, |
| "step": 160 |
| }, |
| { |
| "epoch": 9.444444444444445, |
| "grad_norm": 0.057861328125, |
| "learning_rate": 0.00013246994692046836, |
| "loss": 0.0036, |
| "step": 170 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.0322265625, |
| "learning_rate": 0.00012454854871407994, |
| "loss": 0.003, |
| "step": 180 |
| }, |
| { |
| "epoch": 10.555555555555555, |
| "grad_norm": 0.05078125, |
| "learning_rate": 0.00011645945902807341, |
| "loss": 0.0026, |
| "step": 190 |
| }, |
| { |
| "epoch": 11.11111111111111, |
| "grad_norm": 0.036865234375, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 0.0026, |
| "step": 200 |
| }, |
| { |
| "epoch": 11.11111111111111, |
| "eval_loss": 4.190612316131592, |
| "eval_runtime": 18.3153, |
| "eval_samples_per_second": 81.953, |
| "eval_steps_per_second": 2.075, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 23, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.2881172782645248e+17, |
| "train_batch_size": 10, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
