| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 19.060803474484256, |
| "eval_steps": 500, |
| "global_step": 2200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8686210640608035, |
| "grad_norm": 101458.078125, |
| "learning_rate": 9.569565217391306e-05, |
| "loss": 2.2122, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.7296416938110748, |
| "grad_norm": 88871.9140625, |
| "learning_rate": 9.134782608695652e-05, |
| "loss": 1.6679, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.5906623235613466, |
| "grad_norm": 87018.21875, |
| "learning_rate": 8.7e-05, |
| "loss": 1.3907, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.451682953311618, |
| "grad_norm": 95422.171875, |
| "learning_rate": 8.265217391304348e-05, |
| "loss": 1.1543, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.312703583061889, |
| "grad_norm": 101183.1015625, |
| "learning_rate": 7.830434782608697e-05, |
| "loss": 0.953, |
| "step": 500 |
| }, |
| { |
| "epoch": 5.173724212812161, |
| "grad_norm": 102791.4140625, |
| "learning_rate": 7.395652173913044e-05, |
| "loss": 0.7616, |
| "step": 600 |
| }, |
| { |
| "epoch": 6.034744842562432, |
| "grad_norm": 98049.21875, |
| "learning_rate": 6.960869565217392e-05, |
| "loss": 0.601, |
| "step": 700 |
| }, |
| { |
| "epoch": 6.903365906623236, |
| "grad_norm": 109523.0546875, |
| "learning_rate": 6.52608695652174e-05, |
| "loss": 0.4493, |
| "step": 800 |
| }, |
| { |
| "epoch": 7.764386536373507, |
| "grad_norm": 100472.09375, |
| "learning_rate": 6.0913043478260866e-05, |
| "loss": 0.3366, |
| "step": 900 |
| }, |
| { |
| "epoch": 8.625407166123779, |
| "grad_norm": 86156.8671875, |
| "learning_rate": 5.656521739130435e-05, |
| "loss": 0.2622, |
| "step": 1000 |
| }, |
| { |
| "epoch": 9.48642779587405, |
| "grad_norm": 82576.2421875, |
| "learning_rate": 5.221739130434783e-05, |
| "loss": 0.1988, |
| "step": 1100 |
| }, |
| { |
| "epoch": 10.347448425624322, |
| "grad_norm": 74134.609375, |
| "learning_rate": 4.78695652173913e-05, |
| "loss": 0.1554, |
| "step": 1200 |
| }, |
| { |
| "epoch": 11.304017372421281, |
| "grad_norm": 62766.73828125, |
| "learning_rate": 4.352173913043479e-05, |
| "loss": 0.1092, |
| "step": 1300 |
| }, |
| { |
| "epoch": 12.165038002171553, |
| "grad_norm": 57664.94140625, |
| "learning_rate": 3.917391304347826e-05, |
| "loss": 0.0969, |
| "step": 1400 |
| }, |
| { |
| "epoch": 13.026058631921824, |
| "grad_norm": 54558.6484375, |
| "learning_rate": 3.4826086956521744e-05, |
| "loss": 0.076, |
| "step": 1500 |
| }, |
| { |
| "epoch": 13.894679695982628, |
| "grad_norm": 54939.7890625, |
| "learning_rate": 3.0478260869565216e-05, |
| "loss": 0.0594, |
| "step": 1600 |
| }, |
| { |
| "epoch": 14.7557003257329, |
| "grad_norm": 54442.1171875, |
| "learning_rate": 2.6130434782608698e-05, |
| "loss": 0.047, |
| "step": 1700 |
| }, |
| { |
| "epoch": 15.61672095548317, |
| "grad_norm": 32560.03125, |
| "learning_rate": 2.1782608695652177e-05, |
| "loss": 0.0386, |
| "step": 1800 |
| }, |
| { |
| "epoch": 16.477741585233442, |
| "grad_norm": 41235.45703125, |
| "learning_rate": 1.7434782608695652e-05, |
| "loss": 0.0319, |
| "step": 1900 |
| }, |
| { |
| "epoch": 17.338762214983714, |
| "grad_norm": 34761.0, |
| "learning_rate": 1.308695652173913e-05, |
| "loss": 0.027, |
| "step": 2000 |
| }, |
| { |
| "epoch": 18.199782844733985, |
| "grad_norm": 30058.4453125, |
| "learning_rate": 8.73913043478261e-06, |
| "loss": 0.0224, |
| "step": 2100 |
| }, |
| { |
| "epoch": 19.060803474484256, |
| "grad_norm": 26620.322265625, |
| "learning_rate": 4.391304347826087e-06, |
| "loss": 0.0189, |
| "step": 2200 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 3.0286180289347584e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
