| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.763267740011926, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11926058437686345, |
| "grad_norm": 8.05271053314209, |
| "learning_rate": 7.35e-06, |
| "loss": 5.4953, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2385211687537269, |
| "grad_norm": 2.7420473098754883, |
| "learning_rate": 1.485e-05, |
| "loss": 1.2318, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.35778175313059035, |
| "grad_norm": 1.7430616617202759, |
| "learning_rate": 2.235e-05, |
| "loss": 0.7734, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4770423375074538, |
| "grad_norm": 1.5376101732254028, |
| "learning_rate": 2.985e-05, |
| "loss": 0.6646, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5963029218843172, |
| "grad_norm": 1.6270289421081543, |
| "learning_rate": 2.9226315789473687e-05, |
| "loss": 0.6334, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7155635062611807, |
| "grad_norm": 1.8452305793762207, |
| "learning_rate": 2.8436842105263156e-05, |
| "loss": 0.6103, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8348240906380441, |
| "grad_norm": 1.8059115409851074, |
| "learning_rate": 2.7647368421052632e-05, |
| "loss": 0.6186, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.9540846750149076, |
| "grad_norm": 1.6886439323425293, |
| "learning_rate": 2.6857894736842105e-05, |
| "loss": 0.6045, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.071556350626118, |
| "grad_norm": 1.4987449645996094, |
| "learning_rate": 2.6068421052631578e-05, |
| "loss": 0.5941, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.1908169350029816, |
| "grad_norm": 1.5386848449707031, |
| "learning_rate": 2.527894736842105e-05, |
| "loss": 0.5678, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.310077519379845, |
| "grad_norm": 1.5747556686401367, |
| "learning_rate": 2.4489473684210527e-05, |
| "loss": 0.5671, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.4293381037567083, |
| "grad_norm": 1.5854023694992065, |
| "learning_rate": 2.37e-05, |
| "loss": 0.5376, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.5485986881335718, |
| "grad_norm": 1.4520505666732788, |
| "learning_rate": 2.2910526315789473e-05, |
| "loss": 0.5632, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.6678592725104353, |
| "grad_norm": 1.4415792226791382, |
| "learning_rate": 2.2121052631578946e-05, |
| "loss": 0.5629, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.7871198568872988, |
| "grad_norm": 1.4224036931991577, |
| "learning_rate": 2.1331578947368422e-05, |
| "loss": 0.5647, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.906380441264162, |
| "grad_norm": 1.4895819425582886, |
| "learning_rate": 2.0542105263157895e-05, |
| "loss": 0.54, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.0238521168753727, |
| "grad_norm": 1.5508358478546143, |
| "learning_rate": 1.9752631578947368e-05, |
| "loss": 0.5695, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.143112701252236, |
| "grad_norm": 1.5374252796173096, |
| "learning_rate": 1.896315789473684e-05, |
| "loss": 0.5228, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.2623732856290997, |
| "grad_norm": 1.639708161354065, |
| "learning_rate": 1.8173684210526317e-05, |
| "loss": 0.5512, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.381633870005963, |
| "grad_norm": 1.6390520334243774, |
| "learning_rate": 1.738421052631579e-05, |
| "loss": 0.5252, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.500894454382826, |
| "grad_norm": 1.4625619649887085, |
| "learning_rate": 1.6594736842105263e-05, |
| "loss": 0.5339, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.62015503875969, |
| "grad_norm": 1.3197258710861206, |
| "learning_rate": 1.5805263157894735e-05, |
| "loss": 0.5479, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.739415623136553, |
| "grad_norm": 1.4443845748901367, |
| "learning_rate": 1.5015789473684212e-05, |
| "loss": 0.5134, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.8586762075134167, |
| "grad_norm": 1.7365626096725464, |
| "learning_rate": 1.4226315789473685e-05, |
| "loss": 0.5253, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.97793679189028, |
| "grad_norm": 1.7469673156738281, |
| "learning_rate": 1.343684210526316e-05, |
| "loss": 0.5452, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.095408467501491, |
| "grad_norm": 1.7984752655029297, |
| "learning_rate": 1.2647368421052632e-05, |
| "loss": 0.5178, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.2146690518783543, |
| "grad_norm": 1.5190192461013794, |
| "learning_rate": 1.1857894736842105e-05, |
| "loss": 0.5261, |
| "step": 1350 |
| }, |
| { |
| "epoch": 3.3339296362552178, |
| "grad_norm": 1.5508211851119995, |
| "learning_rate": 1.106842105263158e-05, |
| "loss": 0.5435, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.4531902206320813, |
| "grad_norm": 1.8733484745025635, |
| "learning_rate": 1.0278947368421052e-05, |
| "loss": 0.5001, |
| "step": 1450 |
| }, |
| { |
| "epoch": 3.5724508050089447, |
| "grad_norm": 1.6355196237564087, |
| "learning_rate": 9.489473684210527e-06, |
| "loss": 0.5005, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.691711389385808, |
| "grad_norm": 1.238028645515442, |
| "learning_rate": 8.7e-06, |
| "loss": 0.5164, |
| "step": 1550 |
| }, |
| { |
| "epoch": 3.8109719737626713, |
| "grad_norm": 1.8155537843704224, |
| "learning_rate": 7.910526315789474e-06, |
| "loss": 0.5049, |
| "step": 1600 |
| }, |
| { |
| "epoch": 3.9302325581395348, |
| "grad_norm": 1.6747583150863647, |
| "learning_rate": 7.121052631578948e-06, |
| "loss": 0.5099, |
| "step": 1650 |
| }, |
| { |
| "epoch": 4.047704233750745, |
| "grad_norm": 1.4803907871246338, |
| "learning_rate": 6.331578947368422e-06, |
| "loss": 0.5148, |
| "step": 1700 |
| }, |
| { |
| "epoch": 4.166964818127608, |
| "grad_norm": 1.571410059928894, |
| "learning_rate": 5.542105263157895e-06, |
| "loss": 0.5128, |
| "step": 1750 |
| }, |
| { |
| "epoch": 4.286225402504472, |
| "grad_norm": 1.606655478477478, |
| "learning_rate": 4.752631578947368e-06, |
| "loss": 0.5116, |
| "step": 1800 |
| }, |
| { |
| "epoch": 4.405485986881335, |
| "grad_norm": 1.6239967346191406, |
| "learning_rate": 3.963157894736842e-06, |
| "loss": 0.5068, |
| "step": 1850 |
| }, |
| { |
| "epoch": 4.524746571258199, |
| "grad_norm": 1.3790518045425415, |
| "learning_rate": 3.173684210526316e-06, |
| "loss": 0.4962, |
| "step": 1900 |
| }, |
| { |
| "epoch": 4.644007155635062, |
| "grad_norm": 1.2910724878311157, |
| "learning_rate": 2.38421052631579e-06, |
| "loss": 0.5172, |
| "step": 1950 |
| }, |
| { |
| "epoch": 4.763267740011926, |
| "grad_norm": 2.057995557785034, |
| "learning_rate": 1.5947368421052633e-06, |
| "loss": 0.5007, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 2100, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1043619221864448.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
