| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 222, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13513513513513514, |
| "grad_norm": 3.4277374744415283, |
| "learning_rate": 2.9985590229902075e-05, |
| "loss": 0.9087, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 2.8508694171905518, |
| "learning_rate": 2.9730185992421254e-05, |
| "loss": 0.9152, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.40540540540540543, |
| "grad_norm": 2.5549261569976807, |
| "learning_rate": 2.9160833414327637e-05, |
| "loss": 0.8442, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 2.390583038330078, |
| "learning_rate": 2.828966725734167e-05, |
| "loss": 0.7622, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6756756756756757, |
| "grad_norm": 2.3179285526275635, |
| "learning_rate": 2.7135254915624213e-05, |
| "loss": 0.7699, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 2.8123555183410645, |
| "learning_rate": 2.5722200684005718e-05, |
| "loss": 0.7804, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9459459459459459, |
| "grad_norm": 2.627075433731079, |
| "learning_rate": 2.408062136015872e-05, |
| "loss": 0.7135, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 2.431959629058838, |
| "learning_rate": 2.224550435734272e-05, |
| "loss": 0.5884, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2162162162162162, |
| "grad_norm": 1.7864530086517334, |
| "learning_rate": 2.025596200843394e-05, |
| "loss": 0.5148, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 2.0569097995758057, |
| "learning_rate": 1.8154397954454996e-05, |
| "loss": 0.4696, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4864864864864864, |
| "grad_norm": 2.531879186630249, |
| "learning_rate": 1.5985603384585545e-05, |
| "loss": 0.4752, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 2.2602624893188477, |
| "learning_rate": 1.3795802389729185e-05, |
| "loss": 0.472, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7567567567567568, |
| "grad_norm": 2.293375015258789, |
| "learning_rate": 1.1631666776267804e-05, |
| "loss": 0.502, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 2.404690980911255, |
| "learning_rate": 9.5393213375378e-06, |
| "loss": 0.405, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.027027027027027, |
| "grad_norm": 1.698337435722351, |
| "learning_rate": 7.563360783939724e-06, |
| "loss": 0.4296, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 1.9497623443603516, |
| "learning_rate": 5.7458992841091544e-06, |
| "loss": 0.295, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.2972972972972974, |
| "grad_norm": 2.4481585025787354, |
| "learning_rate": 4.125672874528797e-06, |
| "loss": 0.2979, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 2.4400129318237305, |
| "learning_rate": 2.7372138681624246e-06, |
| "loss": 0.3247, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.5675675675675675, |
| "grad_norm": 1.7697392702102661, |
| "learning_rate": 1.6101148581573276e-06, |
| "loss": 0.2649, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 2.042285919189453, |
| "learning_rate": 7.683980030985655e-07, |
| "loss": 0.2507, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.8378378378378377, |
| "grad_norm": 2.1546924114227295, |
| "learning_rate": 2.300030364048139e-07, |
| "loss": 0.2913, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 1.8392692804336548, |
| "learning_rate": 6.404912056610091e-09, |
| "loss": 0.3076, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 222, |
| "total_flos": 7707233982873600.0, |
| "train_loss": 0.5248662203818828, |
| "train_runtime": 373.8725, |
| "train_samples_per_second": 9.436, |
| "train_steps_per_second": 0.594 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 222, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7707233982873600.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
