| { |
| "best_global_step": 1037, |
| "best_metric": 0.5065046548843384, |
| "best_model_checkpoint": "./mcqa_model_test_source/checkpoint-1037", |
| "epoch": 0.9995180722891567, |
| "eval_steps": 500, |
| "global_step": 1037, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04819277108433735, |
| "grad_norm": 40.22263717651367, |
| "learning_rate": 4.326923076923077e-07, |
| "loss": 0.7966, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0963855421686747, |
| "grad_norm": 88.02349853515625, |
| "learning_rate": 9.038461538461538e-07, |
| "loss": 0.6168, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.14457831325301204, |
| "grad_norm": 64.6302719116211, |
| "learning_rate": 9.571275455519828e-07, |
| "loss": 0.6088, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1927710843373494, |
| "grad_norm": 48.12834930419922, |
| "learning_rate": 9.035369774919614e-07, |
| "loss": 0.5406, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.24096385542168675, |
| "grad_norm": 37.15648651123047, |
| "learning_rate": 8.4994640943194e-07, |
| "loss": 0.6103, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2891566265060241, |
| "grad_norm": 70.53849029541016, |
| "learning_rate": 7.963558413719184e-07, |
| "loss": 0.5637, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.3373493975903614, |
| "grad_norm": 43.44021987915039, |
| "learning_rate": 7.42765273311897e-07, |
| "loss": 0.5857, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.3855421686746988, |
| "grad_norm": 71.3525390625, |
| "learning_rate": 6.891747052518756e-07, |
| "loss": 0.5508, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.43373493975903615, |
| "grad_norm": 57.75139617919922, |
| "learning_rate": 6.355841371918542e-07, |
| "loss": 0.5528, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4819277108433735, |
| "grad_norm": 54.9525146484375, |
| "learning_rate": 5.819935691318327e-07, |
| "loss": 0.5326, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.5301204819277109, |
| "grad_norm": 50.39666748046875, |
| "learning_rate": 5.284030010718113e-07, |
| "loss": 0.5683, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.5783132530120482, |
| "grad_norm": 59.521488189697266, |
| "learning_rate": 4.748124330117899e-07, |
| "loss": 0.5337, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.6265060240963856, |
| "grad_norm": 40.77716827392578, |
| "learning_rate": 4.2122186495176846e-07, |
| "loss": 0.5917, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.6746987951807228, |
| "grad_norm": 83.60078430175781, |
| "learning_rate": 3.6763129689174703e-07, |
| "loss": 0.5459, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.7228915662650602, |
| "grad_norm": 46.46372604370117, |
| "learning_rate": 3.140407288317256e-07, |
| "loss": 0.5251, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7710843373493976, |
| "grad_norm": 42.664146423339844, |
| "learning_rate": 2.6045016077170417e-07, |
| "loss": 0.4937, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.8192771084337349, |
| "grad_norm": 78.2928466796875, |
| "learning_rate": 2.0685959271168274e-07, |
| "loss": 0.5579, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.8674698795180723, |
| "grad_norm": 56.88075256347656, |
| "learning_rate": 1.532690246516613e-07, |
| "loss": 0.5014, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.9156626506024096, |
| "grad_norm": 27.720346450805664, |
| "learning_rate": 9.967845659163988e-08, |
| "loss": 0.5585, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.963855421686747, |
| "grad_norm": 54.69992446899414, |
| "learning_rate": 4.608788853161844e-08, |
| "loss": 0.4791, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.9995180722891567, |
| "eval_loss": 0.5065046548843384, |
| "eval_runtime": 69.1291, |
| "eval_samples_per_second": 45.003, |
| "eval_steps_per_second": 5.627, |
| "step": 1037 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1037, |
| "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": 7892894912348160.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
