|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.1142204454597373, |
|
"eval_steps": 5, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.002284408909194746, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.002284408909194746, |
|
"eval_loss": NaN, |
|
"eval_runtime": 121.7405, |
|
"eval_samples_per_second": 3.031, |
|
"eval_steps_per_second": 1.52, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.004568817818389492, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.006853226727584237, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.009137635636778984, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.011422044545973729, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.011422044545973729, |
|
"eval_loss": NaN, |
|
"eval_runtime": 121.9164, |
|
"eval_samples_per_second": 3.027, |
|
"eval_steps_per_second": 1.517, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.013706453455168474, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00012, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.01599086236436322, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00014, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.018275271273557967, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00016, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.020559680182752713, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.022844089091947458, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.022844089091947458, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.0054, |
|
"eval_samples_per_second": 3.024, |
|
"eval_steps_per_second": 1.516, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.025128498001142203, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001996917333733128, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.02741290691033695, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00019876883405951377, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.029697315819531698, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00019723699203976766, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.03198172472872644, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00019510565162951537, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.034266133637921185, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001923879532511287, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.034266133637921185, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.1464, |
|
"eval_samples_per_second": 3.021, |
|
"eval_steps_per_second": 1.515, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.036550542547115934, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001891006524188368, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.038834951456310676, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018526401643540922, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.041119360365505425, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.043403769274700174, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001760405965600031, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.045688178183894916, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00017071067811865476, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.045688178183894916, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.164, |
|
"eval_samples_per_second": 3.021, |
|
"eval_steps_per_second": 1.514, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.047972587093089665, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00016494480483301836, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.05025699600228441, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00015877852522924732, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.052541404911479156, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001522498564715949, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.0548258138206739, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00014539904997395468, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.05711022272986865, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.000138268343236509, |
|
"loss": 0.0, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.05711022272986865, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.2721, |
|
"eval_samples_per_second": 3.018, |
|
"eval_steps_per_second": 1.513, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.059394631639063396, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00013090169943749476, |
|
"loss": 0.0, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.06167904054825814, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.00012334453638559057, |
|
"loss": 0.0, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.06396344945745289, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001156434465040231, |
|
"loss": 0.0, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.06624785836664764, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001078459095727845, |
|
"loss": 0.0, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.06853226727584237, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.06853226727584237, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.1363, |
|
"eval_samples_per_second": 3.021, |
|
"eval_steps_per_second": 1.515, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.07081667618503712, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.215409042721552e-05, |
|
"loss": 0.0, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.07310108509423187, |
|
"grad_norm": NaN, |
|
"learning_rate": 8.435655349597689e-05, |
|
"loss": 0.0, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.07538549400342662, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.66554636144095e-05, |
|
"loss": 0.0, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.07766990291262135, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.0, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.0799543118218161, |
|
"grad_norm": NaN, |
|
"learning_rate": 6.173165676349103e-05, |
|
"loss": 0.0, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.0799543118218161, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.239, |
|
"eval_samples_per_second": 3.019, |
|
"eval_steps_per_second": 1.513, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.08223872073101085, |
|
"grad_norm": NaN, |
|
"learning_rate": 5.4600950026045326e-05, |
|
"loss": 0.0, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.0845231296402056, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.7750143528405126e-05, |
|
"loss": 0.0, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.08680753854940035, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.12214747707527e-05, |
|
"loss": 0.0, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.08909194745859508, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.5055195166981645e-05, |
|
"loss": 0.0, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.09137635636778983, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.9289321881345254e-05, |
|
"loss": 0.0, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.09137635636778983, |
|
"eval_loss": NaN, |
|
"eval_runtime": 121.8912, |
|
"eval_samples_per_second": 3.027, |
|
"eval_steps_per_second": 1.518, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.09366076527698458, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.3959403439996907e-05, |
|
"loss": 0.0, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.09594517418617933, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.9098300562505266e-05, |
|
"loss": 0.0, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.09822958309537407, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.4735983564590783e-05, |
|
"loss": 0.0, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.10051399200456881, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.0899347581163221e-05, |
|
"loss": 0.0, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.10279840091376356, |
|
"grad_norm": NaN, |
|
"learning_rate": 7.612046748871327e-06, |
|
"loss": 0.0, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.10279840091376356, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.0921, |
|
"eval_samples_per_second": 3.022, |
|
"eval_steps_per_second": 1.515, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.10508280982295831, |
|
"grad_norm": NaN, |
|
"learning_rate": 4.8943483704846475e-06, |
|
"loss": 0.0, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.10736721873215306, |
|
"grad_norm": NaN, |
|
"learning_rate": 2.7630079602323442e-06, |
|
"loss": 0.0, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.1096516276413478, |
|
"grad_norm": NaN, |
|
"learning_rate": 1.231165940486234e-06, |
|
"loss": 0.0, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.11193603655054254, |
|
"grad_norm": NaN, |
|
"learning_rate": 3.0826662668720364e-07, |
|
"loss": 0.0, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.1142204454597373, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0, |
|
"loss": 0.0, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1142204454597373, |
|
"eval_loss": NaN, |
|
"eval_runtime": 122.0479, |
|
"eval_samples_per_second": 3.023, |
|
"eval_steps_per_second": 1.516, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 50, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.14364023570432e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|