| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "grad_norm": 4.2845234870910645, |
| "learning_rate": 3.6000000000000003e-06, |
| "loss": 0.1395275592803955, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 3.076885938644409, |
| "learning_rate": 7.600000000000001e-06, |
| "loss": 0.09198258519172668, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 1.2846078872680664, |
| "learning_rate": 9.992203820909906e-06, |
| "loss": 0.07833675146102906, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.7038628458976746, |
| "learning_rate": 9.904775776745959e-06, |
| "loss": 0.06727399826049804, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.9231874346733093, |
| "learning_rate": 9.721881851187406e-06, |
| "loss": 0.06411659717559814, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 1.0481280088424683, |
| "learning_rate": 9.44708186645649e-06, |
| "loss": 0.0525032103061676, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.8314676880836487, |
| "learning_rate": 9.085724491675642e-06, |
| "loss": 0.04806323647499085, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.7113093733787537, |
| "learning_rate": 8.644843137107058e-06, |
| "loss": 0.05030159950256348, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.7916203737258911, |
| "learning_rate": 8.133019056822303e-06, |
| "loss": 0.045130616426467894, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.7043232917785645, |
| "learning_rate": 7.560214324352858e-06, |
| "loss": 0.04170699715614319, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.8150236010551453, |
| "learning_rate": 6.9375779322605154e-06, |
| "loss": 0.03221024870872498, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.7333807349205017, |
| "learning_rate": 6.277228789678953e-06, |
| "loss": 0.02941911220550537, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.821044385433197, |
| "learning_rate": 5.592019841532507e-06, |
| "loss": 0.029835113883018495, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.6930698156356812, |
| "learning_rate": 4.895287900583216e-06, |
| "loss": 0.027946752309799195, |
| "step": 140 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7381048798561096, |
| "learning_rate": 4.200594061540827e-06, |
| "loss": 0.024364133179187775, |
| "step": 150 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 1.0409406423568726, |
| "learning_rate": 3.521459749779769e-06, |
| "loss": 0.015057653188705444, |
| "step": 160 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 0.8659031391143799, |
| "learning_rate": 2.871103542174637e-06, |
| "loss": 0.013981494307518005, |
| "step": 170 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 1.0307326316833496, |
| "learning_rate": 2.2621838825372496e-06, |
| "loss": 0.012463082373142243, |
| "step": 180 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 0.637093186378479, |
| "learning_rate": 1.7065526994065973e-06, |
| "loss": 0.011675777286291123, |
| "step": 190 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.9585095643997192, |
| "learning_rate": 1.2150247217412186e-06, |
| "loss": 0.010881078988313675, |
| "step": 200 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 0.68025803565979, |
| "learning_rate": 7.971669825215789e-07, |
| "loss": 0.003655080869793892, |
| "step": 210 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 0.4042770564556122, |
| "learning_rate": 4.6111260733545714e-07, |
| "loss": 0.003969649970531464, |
| "step": 220 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 0.24554327130317688, |
| "learning_rate": 2.134025123396638e-07, |
| "loss": 0.002969801425933838, |
| "step": 230 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.5440001487731934, |
| "learning_rate": 5.8858092767236084e-08, |
| "loss": 0.002937900647521019, |
| "step": 240 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.607397735118866, |
| "learning_rate": 4.87379953478806e-10, |
| "loss": 0.0023729542270302774, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.7298085253110825e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
