| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 5, |
| "global_step": 26, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.038461538461538464, |
| "grad_norm": 0.2212931364774704, |
| "learning_rate": 0.0, |
| "loss": 1.7529296875, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07692307692307693, |
| "grad_norm": 0.22290921211242676, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 1.7490234375, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11538461538461539, |
| "grad_norm": 0.22765517234802246, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 1.74609375, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 0.22061161696910858, |
| "learning_rate": 1e-05, |
| "loss": 1.744140625, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19230769230769232, |
| "grad_norm": 0.2319454401731491, |
| "learning_rate": 9.958086757163489e-06, |
| "loss": 1.751953125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.48178428411483765, |
| "learning_rate": 9.833127793065098e-06, |
| "loss": 1.56982421875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "eval_loss": 1.7353515625, |
| "eval_runtime": 2.0834, |
| "eval_samples_per_second": 1.44, |
| "eval_steps_per_second": 0.48, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2692307692307692, |
| "grad_norm": 0.2260776311159134, |
| "learning_rate": 9.62745085677454e-06, |
| "loss": 1.791015625, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.2357121706008911, |
| "learning_rate": 9.3448873204592e-06, |
| "loss": 1.69921875, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.34615384615384615, |
| "grad_norm": 0.23338496685028076, |
| "learning_rate": 8.99070080816989e-06, |
| "loss": 1.7509765625, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 0.23721955716609955, |
| "learning_rate": 8.571489144483945e-06, |
| "loss": 1.7265625, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4230769230769231, |
| "grad_norm": 0.23105652630329132, |
| "learning_rate": 8.095061449516904e-06, |
| "loss": 1.7294921875, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4230769230769231, |
| "eval_loss": 1.732421875, |
| "eval_runtime": 2.0926, |
| "eval_samples_per_second": 1.434, |
| "eval_steps_per_second": 0.478, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.2563953697681427, |
| "learning_rate": 7.570292669790186e-06, |
| "loss": 1.7392578125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.25942760705947876, |
| "learning_rate": 7.006958254769438e-06, |
| "loss": 1.7412109375, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5384615384615384, |
| "grad_norm": 0.2547960579395294, |
| "learning_rate": 6.415552058736854e-06, |
| "loss": 1.7392578125, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5769230769230769, |
| "grad_norm": 0.24564571678638458, |
| "learning_rate": 5.80709086014102e-06, |
| "loss": 1.7451171875, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.27695149183273315, |
| "learning_rate": 5.192909139858981e-06, |
| "loss": 1.7431640625, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "eval_loss": 1.71875, |
| "eval_runtime": 2.0908, |
| "eval_samples_per_second": 1.435, |
| "eval_steps_per_second": 0.478, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.6538461538461539, |
| "grad_norm": 0.2455541342496872, |
| "learning_rate": 4.584447941263149e-06, |
| "loss": 1.716796875, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.6923076923076923, |
| "grad_norm": 0.2493320256471634, |
| "learning_rate": 3.993041745230562e-06, |
| "loss": 1.7353515625, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7307692307692307, |
| "grad_norm": 0.23711146414279938, |
| "learning_rate": 3.429707330209816e-06, |
| "loss": 1.7275390625, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.25111886858940125, |
| "learning_rate": 2.9049385504830987e-06, |
| "loss": 1.7197265625, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8076923076923077, |
| "grad_norm": 0.2591613829135895, |
| "learning_rate": 2.4285108555160576e-06, |
| "loss": 1.6494140625, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8076923076923077, |
| "eval_loss": 1.71875, |
| "eval_runtime": 2.09, |
| "eval_samples_per_second": 1.435, |
| "eval_steps_per_second": 0.478, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8461538461538461, |
| "grad_norm": 0.262620747089386, |
| "learning_rate": 2.0092991918301106e-06, |
| "loss": 1.7138671875, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.8846153846153846, |
| "grad_norm": 0.2580265402793884, |
| "learning_rate": 1.6551126795408017e-06, |
| "loss": 1.720703125, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.25043341517448425, |
| "learning_rate": 1.3725491432254627e-06, |
| "loss": 1.701171875, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9615384615384616, |
| "grad_norm": 0.24621684849262238, |
| "learning_rate": 1.1668722069349041e-06, |
| "loss": 1.7333984375, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.24163366854190826, |
| "learning_rate": 1.0419132428365116e-06, |
| "loss": 1.7197265625, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.71875, |
| "eval_runtime": 2.1006, |
| "eval_samples_per_second": 1.428, |
| "eval_steps_per_second": 0.476, |
| "step": 26 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 26, |
| "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": 4.6427144448691405e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
