| { |
| "best_global_step": 98, |
| "best_metric": 0.6818181818181818, |
| "best_model_checkpoint": "font-identifier/checkpoint-98", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 98, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 9.430075645446777, |
| "learning_rate": 6.428571428571429e-06, |
| "loss": 3.3213, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.06818181818181818, |
| "eval_loss": 3.2453081607818604, |
| "eval_runtime": 2.4333, |
| "eval_samples_per_second": 90.411, |
| "eval_steps_per_second": 5.753, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.4363636363636363, |
| "grad_norm": 9.360711097717285, |
| "learning_rate": 1.357142857142857e-05, |
| "loss": 3.1711, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.12727272727272726, |
| "eval_loss": 3.0051403045654297, |
| "eval_runtime": 2.0612, |
| "eval_samples_per_second": 106.735, |
| "eval_steps_per_second": 6.792, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.1454545454545455, |
| "grad_norm": 8.500679016113281, |
| "learning_rate": 2.0714285714285718e-05, |
| "loss": 2.983, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.8727272727272726, |
| "grad_norm": 9.82868766784668, |
| "learning_rate": 2.785714285714286e-05, |
| "loss": 2.8729, |
| "step": 40 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.20909090909090908, |
| "eval_loss": 2.6284613609313965, |
| "eval_runtime": 2.0503, |
| "eval_samples_per_second": 107.302, |
| "eval_steps_per_second": 6.828, |
| "step": 42 |
| }, |
| { |
| "epoch": 3.581818181818182, |
| "grad_norm": 7.700014114379883, |
| "learning_rate": 3.5e-05, |
| "loss": 2.562, |
| "step": 50 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.37727272727272726, |
| "eval_loss": 2.160020112991333, |
| "eval_runtime": 2.3625, |
| "eval_samples_per_second": 93.121, |
| "eval_steps_per_second": 5.926, |
| "step": 56 |
| }, |
| { |
| "epoch": 4.290909090909091, |
| "grad_norm": 7.527115821838379, |
| "learning_rate": 4.214285714285714e-05, |
| "loss": 2.2406, |
| "step": 60 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 5.579476833343506, |
| "learning_rate": 4.928571428571429e-05, |
| "loss": 1.8675, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.5363636363636364, |
| "eval_loss": 1.639161229133606, |
| "eval_runtime": 2.0879, |
| "eval_samples_per_second": 105.372, |
| "eval_steps_per_second": 6.705, |
| "step": 70 |
| }, |
| { |
| "epoch": 5.7272727272727275, |
| "grad_norm": 6.313197135925293, |
| "learning_rate": 4.928571428571429e-05, |
| "loss": 1.6359, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6681818181818182, |
| "eval_loss": 1.2266921997070312, |
| "eval_runtime": 2.1098, |
| "eval_samples_per_second": 104.274, |
| "eval_steps_per_second": 6.636, |
| "step": 84 |
| }, |
| { |
| "epoch": 6.4363636363636365, |
| "grad_norm": 5.8209004402160645, |
| "learning_rate": 4.84920634920635e-05, |
| "loss": 1.3499, |
| "step": 90 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.6818181818181818, |
| "eval_loss": 1.0587564706802368, |
| "eval_runtime": 2.9116, |
| "eval_samples_per_second": 75.56, |
| "eval_steps_per_second": 4.808, |
| "step": 98 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "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": 6.224348064743424e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
