| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9993211133740665, |
| "eval_steps": 500, |
| "global_step": 184, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05431093007467753, |
| "grad_norm": 1.0013175010681152, |
| "learning_rate": 2e-05, |
| "loss": 1.8305, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10862186014935506, |
| "grad_norm": 0.6650476455688477, |
| "learning_rate": 4e-05, |
| "loss": 1.6895, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1629327902240326, |
| "grad_norm": 0.2262110561132431, |
| "learning_rate": 6e-05, |
| "loss": 1.4921, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2172437202987101, |
| "grad_norm": 0.22021710872650146, |
| "learning_rate": 8e-05, |
| "loss": 1.4074, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.27155465037338766, |
| "grad_norm": 0.18622460961341858, |
| "learning_rate": 0.0001, |
| "loss": 1.2593, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3258655804480652, |
| "grad_norm": 0.18928822875022888, |
| "learning_rate": 0.00012, |
| "loss": 1.1828, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3801765105227427, |
| "grad_norm": 4.061775207519531, |
| "learning_rate": 0.00014, |
| "loss": 1.0697, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.4344874405974202, |
| "grad_norm": 0.20349960029125214, |
| "learning_rate": 0.00016, |
| "loss": 1.0102, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.48879837067209775, |
| "grad_norm": 0.23872722685337067, |
| "learning_rate": 0.00018, |
| "loss": 0.9941, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5431093007467753, |
| "grad_norm": 0.20515283942222595, |
| "learning_rate": 0.0002, |
| "loss": 0.9608, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.5974202308214528, |
| "grad_norm": 0.22473494708538055, |
| "learning_rate": 0.00019931371771625544, |
| "loss": 0.9308, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6517311608961304, |
| "grad_norm": 0.24142144620418549, |
| "learning_rate": 0.0001972642905324813, |
| "loss": 0.9381, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7060420909708078, |
| "grad_norm": 0.260145902633667, |
| "learning_rate": 0.00019387984816003867, |
| "loss": 0.8955, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7603530210454854, |
| "grad_norm": 0.22235779464244843, |
| "learning_rate": 0.00018920684425573865, |
| "loss": 0.8667, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.814663951120163, |
| "grad_norm": 0.23329713940620422, |
| "learning_rate": 0.00018330941881540915, |
| "loss": 0.873, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8689748811948405, |
| "grad_norm": 0.2553715109825134, |
| "learning_rate": 0.0001762685178110382, |
| "loss": 0.8651, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.923285811269518, |
| "grad_norm": 0.22536128759384155, |
| "learning_rate": 0.0001681807821550438, |
| "loss": 0.8504, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9775967413441955, |
| "grad_norm": 0.22558774054050446, |
| "learning_rate": 0.00015915722124135227, |
| "loss": 0.8414, |
| "step": 180 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 368, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 2.562379271897088e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
