| { |
| "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": 0.07421150278293136, |
| "grad_norm": 0.08251953125, |
| "learning_rate": 4.970588235294118e-05, |
| "loss": 0.7136603355407715, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.14842300556586271, |
| "grad_norm": 0.07861328125, |
| "learning_rate": 4.933823529411765e-05, |
| "loss": 0.6834848880767822, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22263450834879406, |
| "grad_norm": 0.0830078125, |
| "learning_rate": 4.897058823529412e-05, |
| "loss": 0.707883644104004, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.29684601113172543, |
| "grad_norm": 0.0859375, |
| "learning_rate": 4.860294117647059e-05, |
| "loss": 0.6775740623474121, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37105751391465674, |
| "grad_norm": 0.091796875, |
| "learning_rate": 4.823529411764706e-05, |
| "loss": 0.776744794845581, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.4452690166975881, |
| "grad_norm": 0.0849609375, |
| "learning_rate": 4.7867647058823535e-05, |
| "loss": 0.728224515914917, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5194805194805194, |
| "grad_norm": 0.06884765625, |
| "learning_rate": 4.75e-05, |
| "loss": 0.6960197925567627, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.5936920222634509, |
| "grad_norm": 0.08447265625, |
| "learning_rate": 4.713235294117647e-05, |
| "loss": 0.6611286163330078, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6679035250463822, |
| "grad_norm": 0.07666015625, |
| "learning_rate": 4.6764705882352944e-05, |
| "loss": 0.6967206954956054, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.7421150278293135, |
| "grad_norm": 0.07470703125, |
| "learning_rate": 4.639705882352942e-05, |
| "loss": 0.6535059452056885, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.0830078125, |
| "learning_rate": 4.6029411764705885e-05, |
| "loss": 0.70545973777771, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.8905380333951762, |
| "grad_norm": 0.08740234375, |
| "learning_rate": 4.566176470588235e-05, |
| "loss": 0.6584103107452393, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9647495361781077, |
| "grad_norm": 0.0693359375, |
| "learning_rate": 4.5294117647058826e-05, |
| "loss": 0.6759594917297364, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.0296846011131726, |
| "grad_norm": 0.0693359375, |
| "learning_rate": 4.49264705882353e-05, |
| "loss": 0.6613986492156982, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.103896103896104, |
| "grad_norm": 0.061767578125, |
| "learning_rate": 4.455882352941177e-05, |
| "loss": 0.6283697128295899, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.1781076066790352, |
| "grad_norm": 0.0751953125, |
| "learning_rate": 4.4191176470588235e-05, |
| "loss": 0.5669743061065674, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2523191094619666, |
| "grad_norm": 0.08544921875, |
| "learning_rate": 4.382352941176471e-05, |
| "loss": 0.5851097583770752, |
| "step": 85 |
| }, |
| { |
| "epoch": 1.3265306122448979, |
| "grad_norm": 0.076171875, |
| "learning_rate": 4.345588235294118e-05, |
| "loss": 0.59378023147583, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.4007421150278292, |
| "grad_norm": 0.07080078125, |
| "learning_rate": 4.308823529411765e-05, |
| "loss": 0.561594820022583, |
| "step": 95 |
| }, |
| { |
| "epoch": 1.4749536178107607, |
| "grad_norm": 0.08447265625, |
| "learning_rate": 4.272058823529412e-05, |
| "loss": 0.5819839477539063, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.549165120593692, |
| "grad_norm": 0.08056640625, |
| "learning_rate": 4.235294117647059e-05, |
| "loss": 0.5523958206176758, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.6233766233766234, |
| "grad_norm": 0.06591796875, |
| "learning_rate": 4.198529411764706e-05, |
| "loss": 0.5537418365478516, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6975881261595547, |
| "grad_norm": 0.07470703125, |
| "learning_rate": 4.161764705882353e-05, |
| "loss": 0.551865530014038, |
| "step": 115 |
| }, |
| { |
| "epoch": 1.7717996289424862, |
| "grad_norm": 0.0703125, |
| "learning_rate": 4.125e-05, |
| "loss": 0.602507495880127, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.8460111317254175, |
| "grad_norm": 0.0830078125, |
| "learning_rate": 4.0882352941176474e-05, |
| "loss": 0.5978893280029297, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.9202226345083488, |
| "grad_norm": 0.08154296875, |
| "learning_rate": 4.051470588235294e-05, |
| "loss": 0.625958776473999, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.9944341372912802, |
| "grad_norm": 0.0703125, |
| "learning_rate": 4.0147058823529415e-05, |
| "loss": 0.553464412689209, |
| "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": 6.778077240832819e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
