| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.8152866242038215, |
| "eval_steps": 500, |
| "global_step": 27, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.10191082802547771, |
| "grad_norm": 12.47473534276904, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 1.0789, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.20382165605095542, |
| "grad_norm": 12.39014398076934, |
| "learning_rate": 5.333333333333333e-05, |
| "loss": 1.0801, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.3057324840764331, |
| "grad_norm": 6.395094250124753, |
| "learning_rate": 8e-05, |
| "loss": 0.836, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.40764331210191085, |
| "grad_norm": 26.311206966183367, |
| "learning_rate": 7.965779445495243e-05, |
| "loss": 1.0767, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.5095541401273885, |
| "grad_norm": 11.25576912821989, |
| "learning_rate": 7.863703305156273e-05, |
| "loss": 0.8788, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6114649681528662, |
| "grad_norm": 5.381707843861206, |
| "learning_rate": 7.695518130045147e-05, |
| "loss": 0.7433, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.7133757961783439, |
| "grad_norm": 4.565550283372428, |
| "learning_rate": 7.464101615137756e-05, |
| "loss": 0.6874, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.8152866242038217, |
| "grad_norm": 4.696769947926018, |
| "learning_rate": 7.173413361164941e-05, |
| "loss": 0.6547, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.9171974522292994, |
| "grad_norm": 2.9158515793084625, |
| "learning_rate": 6.828427124746191e-05, |
| "loss": 0.617, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.0509554140127388, |
| "grad_norm": 3.102382711933173, |
| "learning_rate": 6.435045716034883e-05, |
| "loss": 0.5693, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.1528662420382165, |
| "grad_norm": 1.687077457288962, |
| "learning_rate": 6.000000000000001e-05, |
| "loss": 0.503, |
| "step": 11 |
| }, |
| { |
| "epoch": 1.2547770700636942, |
| "grad_norm": 2.3257897294695096, |
| "learning_rate": 5.5307337294603595e-05, |
| "loss": 0.4926, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.356687898089172, |
| "grad_norm": 1.4402523839291397, |
| "learning_rate": 5.0352761804100835e-05, |
| "loss": 0.4731, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.4585987261146496, |
| "grad_norm": 1.3808853862793107, |
| "learning_rate": 4.522104768880208e-05, |
| "loss": 0.4547, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.5605095541401273, |
| "grad_norm": 0.9578234878432542, |
| "learning_rate": 4e-05, |
| "loss": 0.4472, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.662420382165605, |
| "grad_norm": 0.9292208522466473, |
| "learning_rate": 3.477895231119795e-05, |
| "loss": 0.4269, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.7643312101910829, |
| "grad_norm": 1.476502771585173, |
| "learning_rate": 2.9647238195899168e-05, |
| "loss": 0.4292, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.8662420382165605, |
| "grad_norm": 0.8971188219328079, |
| "learning_rate": 2.4692662705396412e-05, |
| "loss": 0.4158, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.9681528662420382, |
| "grad_norm": 1.3135323399830248, |
| "learning_rate": 2.0000000000000012e-05, |
| "loss": 0.4148, |
| "step": 19 |
| }, |
| { |
| "epoch": 2.1019108280254777, |
| "grad_norm": 1.0870240067310442, |
| "learning_rate": 1.5649542839651175e-05, |
| "loss": 0.3746, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.2038216560509554, |
| "grad_norm": 0.8181262463085681, |
| "learning_rate": 1.1715728752538103e-05, |
| "loss": 0.3667, |
| "step": 21 |
| }, |
| { |
| "epoch": 2.305732484076433, |
| "grad_norm": 0.7339831733754733, |
| "learning_rate": 8.265866388350598e-06, |
| "loss": 0.3586, |
| "step": 22 |
| }, |
| { |
| "epoch": 2.4076433121019107, |
| "grad_norm": 0.5999620195398642, |
| "learning_rate": 5.358983848622452e-06, |
| "loss": 0.3518, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.5095541401273884, |
| "grad_norm": 0.5771864208810155, |
| "learning_rate": 3.0448186995485307e-06, |
| "loss": 0.3523, |
| "step": 24 |
| }, |
| { |
| "epoch": 2.611464968152866, |
| "grad_norm": 0.49629073342358554, |
| "learning_rate": 1.3629669484372722e-06, |
| "loss": 0.3449, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.713375796178344, |
| "grad_norm": 0.3982937273876754, |
| "learning_rate": 3.4220554504758475e-07, |
| "loss": 0.3497, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.8152866242038215, |
| "grad_norm": 0.3878183711620192, |
| "learning_rate": 0.0, |
| "loss": 0.3479, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.8152866242038215, |
| "step": 27, |
| "total_flos": 9.553729118692966e+16, |
| "train_loss": 0.5602199137210846, |
| "train_runtime": 1508.7557, |
| "train_samples_per_second": 9.942, |
| "train_steps_per_second": 0.018 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 27, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.553729118692966e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
