| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.8431372549019605, |
| "eval_steps": 500, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.49019607843137253, |
| "grad_norm": 0.2035752534866333, |
| "learning_rate": 0.00019282051282051282, |
| "loss": 1.563564453125, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.9803921568627451, |
| "grad_norm": 0.24140749871730804, |
| "learning_rate": 0.00018, |
| "loss": 1.0983147430419922, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4705882352941178, |
| "grad_norm": 0.3325779438018799, |
| "learning_rate": 0.0001671794871794872, |
| "loss": 0.9258917999267579, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.9607843137254903, |
| "grad_norm": 0.36317479610443115, |
| "learning_rate": 0.00015435897435897436, |
| "loss": 0.857663803100586, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.450980392156863, |
| "grad_norm": 0.35873135924339294, |
| "learning_rate": 0.00014153846153846156, |
| "loss": 0.6795298767089843, |
| "step": 125 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 0.33606770634651184, |
| "learning_rate": 0.00012871794871794875, |
| "loss": 0.670477294921875, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.431372549019608, |
| "grad_norm": 0.46920403838157654, |
| "learning_rate": 0.00011589743589743591, |
| "loss": 0.5143154525756836, |
| "step": 175 |
| }, |
| { |
| "epoch": 3.9215686274509802, |
| "grad_norm": 0.4206116795539856, |
| "learning_rate": 0.00010307692307692307, |
| "loss": 0.4760634613037109, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.411764705882353, |
| "grad_norm": 0.5420668125152588, |
| "learning_rate": 9.025641025641026e-05, |
| "loss": 0.40361675262451174, |
| "step": 225 |
| }, |
| { |
| "epoch": 4.901960784313726, |
| "grad_norm": 0.5001614093780518, |
| "learning_rate": 7.743589743589744e-05, |
| "loss": 0.34306228637695313, |
| "step": 250 |
| }, |
| { |
| "epoch": 5.392156862745098, |
| "grad_norm": 0.5027152299880981, |
| "learning_rate": 6.461538461538462e-05, |
| "loss": 0.2619362449645996, |
| "step": 275 |
| }, |
| { |
| "epoch": 5.882352941176471, |
| "grad_norm": 0.41253331303596497, |
| "learning_rate": 5.17948717948718e-05, |
| "loss": 0.23906656265258788, |
| "step": 300 |
| }, |
| { |
| "epoch": 6.372549019607844, |
| "grad_norm": 0.39397698640823364, |
| "learning_rate": 3.8974358974358976e-05, |
| "loss": 0.18135608673095704, |
| "step": 325 |
| }, |
| { |
| "epoch": 6.862745098039216, |
| "grad_norm": 0.7866493463516235, |
| "learning_rate": 2.6153846153846157e-05, |
| "loss": 0.17253772735595704, |
| "step": 350 |
| }, |
| { |
| "epoch": 7.352941176470588, |
| "grad_norm": 0.31321847438812256, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.15704892158508302, |
| "step": 375 |
| }, |
| { |
| "epoch": 7.8431372549019605, |
| "grad_norm": 0.4624473750591278, |
| "learning_rate": 5.128205128205128e-07, |
| "loss": 0.12092487335205078, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 400, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.355851682817147e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
