| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.02559836170485089, |
| "eval_steps": 1000, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0012799180852425445, |
| "grad_norm": 89788.1796875, |
| "learning_rate": 2.304147465437788e-08, |
| "loss": 0.7088, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002559836170485089, |
| "grad_norm": 39479.36328125, |
| "learning_rate": 4.86431131592422e-08, |
| "loss": 0.7087, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0038397542557276334, |
| "grad_norm": 82478.765625, |
| "learning_rate": 7.424475166410652e-08, |
| "loss": 0.7074, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.005119672340970178, |
| "grad_norm": 58003.75390625, |
| "learning_rate": 9.984639016897082e-08, |
| "loss": 0.703, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006399590426212722, |
| "grad_norm": 95491.0859375, |
| "learning_rate": 1.2544802867383514e-07, |
| "loss": 0.7073, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007679508511455267, |
| "grad_norm": 44903.296875, |
| "learning_rate": 1.5104966717869944e-07, |
| "loss": 0.7061, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008959426596697812, |
| "grad_norm": 142410.484375, |
| "learning_rate": 1.7665130568356375e-07, |
| "loss": 0.7082, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.010239344681940356, |
| "grad_norm": 148763.109375, |
| "learning_rate": 2.0225294418842808e-07, |
| "loss": 0.707, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.011519262767182901, |
| "grad_norm": 62031.30859375, |
| "learning_rate": 2.2785458269329238e-07, |
| "loss": 0.7036, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.012799180852425445, |
| "grad_norm": 135708.875, |
| "learning_rate": 2.5345622119815674e-07, |
| "loss": 0.7078, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.01407909893766799, |
| "grad_norm": 91129.421875, |
| "learning_rate": 2.79057859703021e-07, |
| "loss": 0.7035, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.015359017022910534, |
| "grad_norm": 39290.72265625, |
| "learning_rate": 3.0465949820788535e-07, |
| "loss": 0.7083, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.016638935108153077, |
| "grad_norm": 49473.61328125, |
| "learning_rate": 3.302611367127496e-07, |
| "loss": 0.7023, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.017918853193395624, |
| "grad_norm": 61292.984375, |
| "learning_rate": 3.5586277521761395e-07, |
| "loss": 0.7014, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.019198771278638168, |
| "grad_norm": 79102.0390625, |
| "learning_rate": 3.814644137224783e-07, |
| "loss": 0.7041, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02047868936388071, |
| "grad_norm": 61779.62890625, |
| "learning_rate": 4.0706605222734256e-07, |
| "loss": 0.7039, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.021758607449123255, |
| "grad_norm": 63492.18359375, |
| "learning_rate": 4.326676907322069e-07, |
| "loss": 0.7035, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.023038525534365802, |
| "grad_norm": 44190.3203125, |
| "learning_rate": 4.582693292370712e-07, |
| "loss": 0.7019, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.024318443619608346, |
| "grad_norm": 67509.15625, |
| "learning_rate": 4.838709677419355e-07, |
| "loss": 0.6991, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.02559836170485089, |
| "grad_norm": 94820.5078125, |
| "learning_rate": 5.094726062467999e-07, |
| "loss": 0.7011, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 39065, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3367821508608000.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
