| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.09521920253917873, |
| "eval_steps": 50, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0023804800634794686, |
| "grad_norm": 43.0, |
| "learning_rate": 1.6875e-07, |
| "loss": 1.6633, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.004760960126958937, |
| "grad_norm": 63.5, |
| "learning_rate": 3.5625000000000003e-07, |
| "loss": 1.6375, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.007141440190438405, |
| "grad_norm": 49.25, |
| "learning_rate": 5.4375e-07, |
| "loss": 1.6325, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.009521920253917874, |
| "grad_norm": 43.25, |
| "learning_rate": 7.312500000000001e-07, |
| "loss": 1.6621, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.011902400317397342, |
| "grad_norm": 39.75, |
| "learning_rate": 9.1875e-07, |
| "loss": 1.5987, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01428288038087681, |
| "grad_norm": 35.25, |
| "learning_rate": 1.10625e-06, |
| "loss": 1.6187, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.01666336044435628, |
| "grad_norm": 37.25, |
| "learning_rate": 1.29375e-06, |
| "loss": 1.5005, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.01904384050783575, |
| "grad_norm": 23.875, |
| "learning_rate": 1.48125e-06, |
| "loss": 1.4614, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.021424320571315214, |
| "grad_norm": 15.5625, |
| "learning_rate": 1.6687500000000001e-06, |
| "loss": 1.3327, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.023804800634794683, |
| "grad_norm": 17.0, |
| "learning_rate": 1.85625e-06, |
| "loss": 1.3133, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.026185280698274152, |
| "grad_norm": 14.0625, |
| "learning_rate": 2.04375e-06, |
| "loss": 1.2393, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.02856576076175362, |
| "grad_norm": 10.6875, |
| "learning_rate": 2.23125e-06, |
| "loss": 1.2397, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.03094624082523309, |
| "grad_norm": 8.9375, |
| "learning_rate": 2.41875e-06, |
| "loss": 1.1328, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.03332672088871256, |
| "grad_norm": 7.75, |
| "learning_rate": 2.60625e-06, |
| "loss": 1.1205, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.03570720095219203, |
| "grad_norm": 10.3125, |
| "learning_rate": 2.79375e-06, |
| "loss": 1.0921, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0380876810156715, |
| "grad_norm": 7.90625, |
| "learning_rate": 2.98125e-06, |
| "loss": 1.0515, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.04046816107915096, |
| "grad_norm": 6.90625, |
| "learning_rate": 3.16875e-06, |
| "loss": 1.0178, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.04284864114263043, |
| "grad_norm": 7.78125, |
| "learning_rate": 3.3562500000000003e-06, |
| "loss": 0.9527, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.0452291212061099, |
| "grad_norm": 9.8125, |
| "learning_rate": 3.5437499999999997e-06, |
| "loss": 0.9037, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.047609601269589366, |
| "grad_norm": 7.03125, |
| "learning_rate": 3.73125e-06, |
| "loss": 0.8909, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.049990081333068835, |
| "grad_norm": 7.34375, |
| "learning_rate": 3.9187499999999995e-06, |
| "loss": 0.8759, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.052370561396548304, |
| "grad_norm": 8.9375, |
| "learning_rate": 4.10625e-06, |
| "loss": 0.8669, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.05475104146002777, |
| "grad_norm": 9.5625, |
| "learning_rate": 4.29375e-06, |
| "loss": 0.8139, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.05713152152350724, |
| "grad_norm": 6.0625, |
| "learning_rate": 4.4812500000000005e-06, |
| "loss": 0.813, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.05951200158698671, |
| "grad_norm": 9.875, |
| "learning_rate": 4.668750000000001e-06, |
| "loss": 0.7689, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.06189248165046618, |
| "grad_norm": 40.0, |
| "learning_rate": 4.8562499999999995e-06, |
| "loss": 0.7372, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.06427296171394564, |
| "grad_norm": 7.34375, |
| "learning_rate": 5.04375e-06, |
| "loss": 0.7333, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.06665344177742512, |
| "grad_norm": 7.15625, |
| "learning_rate": 5.23125e-06, |
| "loss": 0.706, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.06903392184090458, |
| "grad_norm": 10.8125, |
| "learning_rate": 5.41875e-06, |
| "loss": 0.6806, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.07141440190438406, |
| "grad_norm": 10.75, |
| "learning_rate": 5.606250000000001e-06, |
| "loss": 0.6685, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.07379488196786352, |
| "grad_norm": 7.59375, |
| "learning_rate": 5.79375e-06, |
| "loss": 0.6782, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.076175362031343, |
| "grad_norm": 10.625, |
| "learning_rate": 5.98125e-06, |
| "loss": 0.6117, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.07855584209482246, |
| "grad_norm": 11.0625, |
| "learning_rate": 6.16875e-06, |
| "loss": 0.6061, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.08093632215830192, |
| "grad_norm": 11.125, |
| "learning_rate": 6.35625e-06, |
| "loss": 0.5569, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.0833168022217814, |
| "grad_norm": 12.375, |
| "learning_rate": 6.543750000000001e-06, |
| "loss": 0.5565, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.08569728228526086, |
| "grad_norm": 9.875, |
| "learning_rate": 6.73125e-06, |
| "loss": 0.5461, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.08807776234874033, |
| "grad_norm": 13.0625, |
| "learning_rate": 6.9187500000000005e-06, |
| "loss": 0.5104, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.0904582424122198, |
| "grad_norm": 12.375, |
| "learning_rate": 7.10625e-06, |
| "loss": 0.4818, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.09283872247569927, |
| "grad_norm": 12.75, |
| "learning_rate": 7.29375e-06, |
| "loss": 0.4644, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.09521920253917873, |
| "grad_norm": 23.375, |
| "learning_rate": 7.481250000000001e-06, |
| "loss": 0.4571, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 4201, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.08921310253056e+16, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
