| { |
| "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": 0.94771409034729, |
| "learning_rate": 0.0, |
| "loss": 0.82177734375, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09523809523809523, |
| "grad_norm": 1.5331836938858032, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 1.030029296875, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 1.3439949750900269, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.786376953125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 1.7871679067611694, |
| "learning_rate": 1e-05, |
| "loss": 1.161376953125, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "grad_norm": 2.040626287460327, |
| "learning_rate": 9.931634888554937e-06, |
| "loss": 1.0858154296875, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23809523809523808, |
| "eval_loss": 0.89599609375, |
| "eval_runtime": 13.0821, |
| "eval_samples_per_second": 0.229, |
| "eval_steps_per_second": 0.076, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 1.32891845703125, |
| "learning_rate": 9.728616793536588e-06, |
| "loss": 0.83447265625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 1.272424340248108, |
| "learning_rate": 9.397114317029975e-06, |
| "loss": 0.7705078125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 1.9414798021316528, |
| "learning_rate": 8.947199994035402e-06, |
| "loss": 1.12548828125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 1.7536942958831787, |
| "learning_rate": 8.392544243589428e-06, |
| "loss": 0.78173828125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "eval_loss": 0.888671875, |
| "eval_runtime": 2.9172, |
| "eval_samples_per_second": 1.028, |
| "eval_steps_per_second": 0.343, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.47619047619047616, |
| "grad_norm": 1.3101036548614502, |
| "learning_rate": 7.75e-06, |
| "loss": 1.006103515625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5238095238095238, |
| "grad_norm": 1.4956482648849487, |
| "learning_rate": 7.0390906449655104e-06, |
| "loss": 1.017333984375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 1.1593928337097168, |
| "learning_rate": 6.281416799501188e-06, |
| "loss": 0.773681640625, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "grad_norm": 1.1063566207885742, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.828369140625, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6190476190476191, |
| "eval_loss": 0.8779296875, |
| "eval_runtime": 2.9267, |
| "eval_samples_per_second": 1.025, |
| "eval_steps_per_second": 0.342, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 1.55467689037323, |
| "learning_rate": 4.718583200498814e-06, |
| "loss": 0.9912109375, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 2.003232479095459, |
| "learning_rate": 3.960909355034491e-06, |
| "loss": 0.82373046875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 1.6703325510025024, |
| "learning_rate": 3.2500000000000015e-06, |
| "loss": 0.926025390625, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "grad_norm": 1.2591973543167114, |
| "learning_rate": 2.607455756410573e-06, |
| "loss": 0.751953125, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8095238095238095, |
| "eval_loss": 0.875, |
| "eval_runtime": 2.9333, |
| "eval_samples_per_second": 1.023, |
| "eval_steps_per_second": 0.341, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 1.1961588859558105, |
| "learning_rate": 2.0528000059646e-06, |
| "loss": 0.814208984375, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9047619047619048, |
| "grad_norm": 1.0266940593719482, |
| "learning_rate": 1.602885682970026e-06, |
| "loss": 0.704833984375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 1.2737773656845093, |
| "learning_rate": 1.2713832064634127e-06, |
| "loss": 0.871337890625, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.16634202003479, |
| "learning_rate": 1.0683651114450641e-06, |
| "loss": 0.8125, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.8681640625, |
| "eval_runtime": 2.9371, |
| "eval_samples_per_second": 1.021, |
| "eval_steps_per_second": 0.34, |
| "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": 1.2429634227195085e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
