| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "global_step": 21, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.047619047619047616, |
| "grad_norm": 0.9568968415260315, |
| "learning_rate": 0.0, |
| "loss": 2.302734375, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 0.6604674458503723, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 1.83203125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.8862142562866211, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 2.1923828125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 0.9301884174346924, |
| "learning_rate": 0.0001, |
| "loss": 2.099609375, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 0.6462522149085999, |
| "learning_rate": 9.931634888554937e-05, |
| "loss": 1.5146484375, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 1.7890625, |
| "eval_runtime": 5.5258, |
| "eval_samples_per_second": 0.362, |
| "eval_steps_per_second": 0.181, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.7940283417701721, |
| "learning_rate": 9.728616793536588e-05, |
| "loss": 1.609375, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.9866992235183716, |
| "learning_rate": 9.397114317029975e-05, |
| "loss": 1.708984375, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.9356194734573364, |
| "learning_rate": 8.947199994035401e-05, |
| "loss": 1.62109375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 1.2427157163619995, |
| "learning_rate": 8.392544243589427e-05, |
| "loss": 1.72607421875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 1.50390625, |
| "eval_runtime": 6.1677, |
| "eval_samples_per_second": 0.324, |
| "eval_steps_per_second": 0.162, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 0.9093706607818604, |
| "learning_rate": 7.75e-05, |
| "loss": 1.31787109375, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 1.172244668006897, |
| "learning_rate": 7.03909064496551e-05, |
| "loss": 1.61328125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 1.040825605392456, |
| "learning_rate": 6.281416799501188e-05, |
| "loss": 1.18115234375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 1.2616082429885864, |
| "learning_rate": 5.500000000000001e-05, |
| "loss": 1.44921875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 1.244140625, |
| "eval_runtime": 5.5436, |
| "eval_samples_per_second": 0.361, |
| "eval_steps_per_second": 0.18, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 1.064231514930725, |
| "learning_rate": 4.718583200498814e-05, |
| "loss": 1.27685546875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 1.1865931749343872, |
| "learning_rate": 3.960909355034491e-05, |
| "loss": 1.431640625, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 1.041445016860962, |
| "learning_rate": 3.250000000000001e-05, |
| "loss": 1.1904296875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 1.1407253742218018, |
| "learning_rate": 2.6074557564105727e-05, |
| "loss": 1.21337890625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 1.103515625, |
| "eval_runtime": 5.5514, |
| "eval_samples_per_second": 0.36, |
| "eval_steps_per_second": 0.18, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 1.076326608657837, |
| "learning_rate": 2.0528000059645997e-05, |
| "loss": 1.212890625, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 1.2264506816864014, |
| "learning_rate": 1.602885682970026e-05, |
| "loss": 1.15478515625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.922339916229248, |
| "learning_rate": 1.2713832064634126e-05, |
| "loss": 1.0078125, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.0451383590698242, |
| "learning_rate": 1.0683651114450641e-05, |
| "loss": 1.181640625, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.048828125, |
| "eval_runtime": 5.5585, |
| "eval_samples_per_second": 0.36, |
| "eval_steps_per_second": 0.18, |
| "step": 21 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 21, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0171502697560146e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
