| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 136, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07441860465116279, |
| "grad_norm": 0.04150390625, |
| "learning_rate": 4.970588235294118e-05, |
| "loss": 0.8117074966430664, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.14883720930232558, |
| "grad_norm": 0.052001953125, |
| "learning_rate": 4.933823529411765e-05, |
| "loss": 0.8412944793701171, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22325581395348837, |
| "grad_norm": 0.038818359375, |
| "learning_rate": 4.897058823529412e-05, |
| "loss": 0.783283805847168, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.29767441860465116, |
| "grad_norm": 0.043212890625, |
| "learning_rate": 4.860294117647059e-05, |
| "loss": 0.8191794395446778, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37209302325581395, |
| "grad_norm": 0.0390625, |
| "learning_rate": 4.823529411764706e-05, |
| "loss": 0.777860689163208, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.44651162790697674, |
| "grad_norm": 0.04541015625, |
| "learning_rate": 4.7867647058823535e-05, |
| "loss": 0.8589226722717285, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5209302325581395, |
| "grad_norm": 0.041015625, |
| "learning_rate": 4.75e-05, |
| "loss": 0.8166523933410644, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5953488372093023, |
| "grad_norm": 0.0400390625, |
| "learning_rate": 4.713235294117647e-05, |
| "loss": 0.8092836380004883, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6697674418604651, |
| "grad_norm": 0.042724609375, |
| "learning_rate": 4.6764705882352944e-05, |
| "loss": 0.8805876731872558, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.7441860465116279, |
| "grad_norm": 0.03955078125, |
| "learning_rate": 4.639705882352942e-05, |
| "loss": 0.838012409210205, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8186046511627907, |
| "grad_norm": 0.0419921875, |
| "learning_rate": 4.6029411764705885e-05, |
| "loss": 0.8522647857666016, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.8930232558139535, |
| "grad_norm": 0.039306640625, |
| "learning_rate": 4.566176470588235e-05, |
| "loss": 0.7979763507843017, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9674418604651163, |
| "grad_norm": 0.037353515625, |
| "learning_rate": 4.5294117647058826e-05, |
| "loss": 0.7971380233764649, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.0297674418604652, |
| "grad_norm": 0.033935546875, |
| "learning_rate": 4.49264705882353e-05, |
| "loss": 0.7957266807556153, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.104186046511628, |
| "grad_norm": 0.032958984375, |
| "learning_rate": 4.455882352941177e-05, |
| "loss": 0.5031315326690674, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.1786046511627908, |
| "grad_norm": 0.0517578125, |
| "learning_rate": 4.4191176470588235e-05, |
| "loss": 0.5382503509521485, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2530232558139534, |
| "grad_norm": 0.034912109375, |
| "learning_rate": 4.382352941176471e-05, |
| "loss": 0.5200568199157715, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.3274418604651164, |
| "grad_norm": 0.033935546875, |
| "learning_rate": 4.345588235294118e-05, |
| "loss": 0.5138055801391601, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.4018604651162792, |
| "grad_norm": 0.040771484375, |
| "learning_rate": 4.308823529411765e-05, |
| "loss": 0.4661245822906494, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.476279069767442, |
| "grad_norm": 0.04248046875, |
| "learning_rate": 4.272058823529412e-05, |
| "loss": 0.5133561611175537, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.5506976744186045, |
| "grad_norm": 0.031982421875, |
| "learning_rate": 4.235294117647059e-05, |
| "loss": 0.4750948905944824, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.6251162790697675, |
| "grad_norm": 0.031494140625, |
| "learning_rate": 4.198529411764706e-05, |
| "loss": 0.46523518562316896, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.69953488372093, |
| "grad_norm": 0.03515625, |
| "learning_rate": 4.161764705882353e-05, |
| "loss": 0.4725958824157715, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.773953488372093, |
| "grad_norm": 0.0439453125, |
| "learning_rate": 4.125e-05, |
| "loss": 0.4394645690917969, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.8483720930232557, |
| "grad_norm": 0.03515625, |
| "learning_rate": 4.0882352941176474e-05, |
| "loss": 0.463104772567749, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.9227906976744187, |
| "grad_norm": 0.03955078125, |
| "learning_rate": 4.051470588235294e-05, |
| "loss": 0.5168607711791993, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.9972093023255812, |
| "grad_norm": 0.04638671875, |
| "learning_rate": 4.0147058823529415e-05, |
| "loss": 0.5063523292541504, |
| "step": 135 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 680, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.736002021556224e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
