| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 260, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07716049382716049, |
| "grad_norm": 0.6794719696044922, |
| "learning_rate": 0.0004955, |
| "loss": 1.8548, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15432098765432098, |
| "grad_norm": 0.5799520611763, |
| "learning_rate": 0.0004905, |
| "loss": 1.3989, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23148148148148148, |
| "grad_norm": 0.44065240025520325, |
| "learning_rate": 0.0004855, |
| "loss": 1.2791, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30864197530864196, |
| "grad_norm": 0.4982340931892395, |
| "learning_rate": 0.00048049999999999997, |
| "loss": 1.2222, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38580246913580246, |
| "grad_norm": 0.441045880317688, |
| "learning_rate": 0.0004755, |
| "loss": 1.1567, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.46296296296296297, |
| "grad_norm": 0.5147080421447754, |
| "learning_rate": 0.0004705, |
| "loss": 1.1233, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5401234567901234, |
| "grad_norm": 0.4304927587509155, |
| "learning_rate": 0.00046550000000000004, |
| "loss": 1.1042, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6172839506172839, |
| "grad_norm": 0.4338945150375366, |
| "learning_rate": 0.0004605, |
| "loss": 1.0991, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6944444444444444, |
| "grad_norm": 0.4131755232810974, |
| "learning_rate": 0.0004555, |
| "loss": 1.0721, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7716049382716049, |
| "grad_norm": 0.42770788073539734, |
| "learning_rate": 0.0004505, |
| "loss": 1.061, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8487654320987654, |
| "grad_norm": 0.40293624997138977, |
| "learning_rate": 0.00044550000000000004, |
| "loss": 1.0456, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9259259259259259, |
| "grad_norm": 0.405519038438797, |
| "learning_rate": 0.00044050000000000003, |
| "loss": 1.0443, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.49841395020484924, |
| "learning_rate": 0.0004355, |
| "loss": 1.0311, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.0771604938271604, |
| "grad_norm": 0.40889298915863037, |
| "learning_rate": 0.0004305, |
| "loss": 0.9679, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.154320987654321, |
| "grad_norm": 0.43716397881507874, |
| "learning_rate": 0.0004255, |
| "loss": 0.963, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2314814814814814, |
| "grad_norm": 0.41822507977485657, |
| "learning_rate": 0.0004205, |
| "loss": 0.9622, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.308641975308642, |
| "grad_norm": 0.4274284541606903, |
| "learning_rate": 0.00041549999999999996, |
| "loss": 0.9557, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.3858024691358024, |
| "grad_norm": 0.4369387924671173, |
| "learning_rate": 0.0004105, |
| "loss": 0.9537, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.462962962962963, |
| "grad_norm": 0.41516125202178955, |
| "learning_rate": 0.00040550000000000004, |
| "loss": 0.9556, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.5401234567901234, |
| "grad_norm": 0.4300761818885803, |
| "learning_rate": 0.00040050000000000003, |
| "loss": 0.9422, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.617283950617284, |
| "grad_norm": 0.4175296723842621, |
| "learning_rate": 0.0003955, |
| "loss": 0.9542, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.6944444444444444, |
| "grad_norm": 0.42389756441116333, |
| "learning_rate": 0.0003905, |
| "loss": 0.9491, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.7716049382716048, |
| "grad_norm": 0.41654592752456665, |
| "learning_rate": 0.0003855, |
| "loss": 0.9419, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.8487654320987654, |
| "grad_norm": 0.43183737993240356, |
| "learning_rate": 0.00038050000000000003, |
| "loss": 0.9379, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.925925925925926, |
| "grad_norm": 0.42406436800956726, |
| "learning_rate": 0.0003755, |
| "loss": 0.9458, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.555463433265686, |
| "learning_rate": 0.0003705, |
| "loss": 0.936, |
| "step": 260 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.120272880294994e+17, |
| "train_batch_size": 20, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
