| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9559748427672956, |
| "eval_steps": 500, |
| "global_step": 19, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.050314465408805034, |
| "grad_norm": 0.19585087895393372, |
| "learning_rate": 9.931806517013612e-06, |
| "loss": 0.3543, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.10062893081761007, |
| "grad_norm": 0.1947789341211319, |
| "learning_rate": 9.729086208503174e-06, |
| "loss": 0.3289, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.1509433962264151, |
| "grad_norm": 0.2325783669948578, |
| "learning_rate": 9.397368756032445e-06, |
| "loss": 0.3143, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.20125786163522014, |
| "grad_norm": 0.2207995057106018, |
| "learning_rate": 8.94570254698197e-06, |
| "loss": 0.3139, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.25157232704402516, |
| "grad_norm": 0.4233955144882202, |
| "learning_rate": 8.386407858128707e-06, |
| "loss": 0.3272, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3018867924528302, |
| "grad_norm": 0.23675404489040375, |
| "learning_rate": 7.734740790612137e-06, |
| "loss": 0.3184, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3522012578616352, |
| "grad_norm": 0.2159082293510437, |
| "learning_rate": 7.008477123264849e-06, |
| "loss": 0.3088, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.4025157232704403, |
| "grad_norm": 0.2475515902042389, |
| "learning_rate": 6.227427435703997e-06, |
| "loss": 0.2971, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4528301886792453, |
| "grad_norm": 0.2480480670928955, |
| "learning_rate": 5.412896727361663e-06, |
| "loss": 0.3056, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.5031446540880503, |
| "grad_norm": 0.2078869491815567, |
| "learning_rate": 4.587103272638339e-06, |
| "loss": 0.3014, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5534591194968553, |
| "grad_norm": 0.19838862121105194, |
| "learning_rate": 3.7725725642960047e-06, |
| "loss": 0.3073, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.6037735849056604, |
| "grad_norm": 0.20037776231765747, |
| "learning_rate": 2.991522876735154e-06, |
| "loss": 0.2825, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.6540880503144654, |
| "grad_norm": 0.21296867728233337, |
| "learning_rate": 2.265259209387867e-06, |
| "loss": 0.325, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.7044025157232704, |
| "grad_norm": 0.2105196714401245, |
| "learning_rate": 1.6135921418712959e-06, |
| "loss": 0.2887, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.7547169811320755, |
| "grad_norm": 0.1932196021080017, |
| "learning_rate": 1.0542974530180327e-06, |
| "loss": 0.3044, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8050314465408805, |
| "grad_norm": 0.1870521754026413, |
| "learning_rate": 6.026312439675553e-07, |
| "loss": 0.2504, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.8553459119496856, |
| "grad_norm": 0.18833260238170624, |
| "learning_rate": 2.7091379149682683e-07, |
| "loss": 0.3247, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.9056603773584906, |
| "grad_norm": 0.20564253628253937, |
| "learning_rate": 6.819348298638839e-08, |
| "loss": 0.288, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.9559748427672956, |
| "grad_norm": 0.21269722282886505, |
| "learning_rate": 0.0, |
| "loss": 0.2977, |
| "step": 19 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 19, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 2.8521915203190784e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
