| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 6, |
| "global_step": 33, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.030303030303030304, |
| "grad_norm": 1.4287192821502686, |
| "learning_rate": 0.0, |
| "loss": 2.0361328125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.06060606060606061, |
| "grad_norm": 1.437935471534729, |
| "learning_rate": 2.5e-06, |
| "loss": 2.1640625, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 1.3686531782150269, |
| "learning_rate": 5e-06, |
| "loss": 2.01171875, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.12121212121212122, |
| "grad_norm": 1.286812424659729, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 1.9638671875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.15151515151515152, |
| "grad_norm": 1.0939735174179077, |
| "learning_rate": 1e-05, |
| "loss": 1.8427734375, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 1.7438583374023438, |
| "learning_rate": 9.97362080719462e-06, |
| "loss": 2.0869140625, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.21212121212121213, |
| "grad_norm": 0.9894726872444153, |
| "learning_rate": 9.89479250069539e-06, |
| "loss": 1.76953125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.24242424242424243, |
| "grad_norm": 0.8804801106452942, |
| "learning_rate": 9.764439270322612e-06, |
| "loss": 1.7158203125, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 0.6704576015472412, |
| "learning_rate": 9.584089388519307e-06, |
| "loss": 1.7607421875, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "eval_loss": 2.0078125, |
| "eval_runtime": 2.5535, |
| "eval_samples_per_second": 0.783, |
| "eval_steps_per_second": 0.392, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.30303030303030304, |
| "grad_norm": 1.9209635257720947, |
| "learning_rate": 9.355857292754152e-06, |
| "loss": 2.0673828125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.8329216837882996, |
| "learning_rate": 9.082418795675397e-06, |
| "loss": 1.677734375, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.9212274551391602, |
| "learning_rate": 8.76697971365409e-06, |
| "loss": 1.9130859375, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.3939393939393939, |
| "grad_norm": 1.0851582288742065, |
| "learning_rate": 8.413238281518225e-06, |
| "loss": 1.873046875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.42424242424242425, |
| "grad_norm": 0.9320775270462036, |
| "learning_rate": 8.025341794130722e-06, |
| "loss": 1.7841796875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 0.6170089244842529, |
| "learning_rate": 7.607837983149057e-06, |
| "loss": 1.5927734375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "eval_loss": 1.8125, |
| "eval_runtime": 2.5501, |
| "eval_samples_per_second": 0.784, |
| "eval_steps_per_second": 0.392, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.48484848484848486, |
| "grad_norm": 0.7249671816825867, |
| "learning_rate": 7.165621699029615e-06, |
| "loss": 1.7607421875, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.5151515151515151, |
| "grad_norm": 0.6273460984230042, |
| "learning_rate": 6.703877523381495e-06, |
| "loss": 1.666015625, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.6081604957580566, |
| "learning_rate": 6.228018984487443e-06, |
| "loss": 1.486328125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.5757575757575758, |
| "grad_norm": 0.8183671832084656, |
| "learning_rate": 5.74362508863438e-06, |
| "loss": 1.7958984375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.6060606060606061, |
| "grad_norm": 0.8645656704902649, |
| "learning_rate": 5.256374911365621e-06, |
| "loss": 1.6435546875, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 0.7197942137718201, |
| "learning_rate": 4.771981015512559e-06, |
| "loss": 1.6796875, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "eval_loss": 1.703125, |
| "eval_runtime": 2.5572, |
| "eval_samples_per_second": 0.782, |
| "eval_steps_per_second": 0.391, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 0.6852272152900696, |
| "learning_rate": 4.296122476618507e-06, |
| "loss": 1.71484375, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.696969696969697, |
| "grad_norm": 0.5617450475692749, |
| "learning_rate": 3.834378300970385e-06, |
| "loss": 1.509765625, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.7030121684074402, |
| "learning_rate": 3.392162016850945e-06, |
| "loss": 1.587890625, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.7575757575757576, |
| "grad_norm": 0.5215224623680115, |
| "learning_rate": 2.9746582058692803e-06, |
| "loss": 1.5263671875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.7878787878787878, |
| "grad_norm": 0.5175567269325256, |
| "learning_rate": 2.586761718481776e-06, |
| "loss": 1.5361328125, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 0.505078136920929, |
| "learning_rate": 2.2330202863459123e-06, |
| "loss": 1.5234375, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "eval_loss": 1.6484375, |
| "eval_runtime": 2.5566, |
| "eval_samples_per_second": 0.782, |
| "eval_steps_per_second": 0.391, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.8484848484848485, |
| "grad_norm": 0.4583703279495239, |
| "learning_rate": 1.9175812043246034e-06, |
| "loss": 1.517578125, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.8787878787878788, |
| "grad_norm": 0.47751930356025696, |
| "learning_rate": 1.6441427072458493e-06, |
| "loss": 1.5185546875, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.5964409708976746, |
| "learning_rate": 1.4159106114806943e-06, |
| "loss": 1.4677734375, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9393939393939394, |
| "grad_norm": 0.4563347399234772, |
| "learning_rate": 1.2355607296773896e-06, |
| "loss": 1.54833984375, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.9696969696969697, |
| "grad_norm": 0.48352736234664917, |
| "learning_rate": 1.1052074993046102e-06, |
| "loss": 1.44287109375, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5558485984802246, |
| "learning_rate": 1.026379192805382e-06, |
| "loss": 1.48291015625, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.62109375, |
| "eval_runtime": 2.5478, |
| "eval_samples_per_second": 0.785, |
| "eval_steps_per_second": 0.393, |
| "step": 33 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 33, |
| "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": 6.715828683292017e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
