| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014216914574114553, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.108457287057277e-05, | |
| "eval_loss": 1.6025950908660889, | |
| "eval_runtime": 203.3782, | |
| "eval_samples_per_second": 29.128, | |
| "eval_steps_per_second": 14.564, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035542286435286385, | |
| "grad_norm": 0.32894086837768555, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3078, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007108457287057277, | |
| "grad_norm": 0.5316031575202942, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010662685930585914, | |
| "grad_norm": 0.22600068151950836, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.3483, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014216914574114554, | |
| "grad_norm": 0.32068952918052673, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.3313, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017771143217643192, | |
| "grad_norm": 0.31301984190940857, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.2896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0021325371861171828, | |
| "grad_norm": 0.47712332010269165, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.2427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0024879600504700465, | |
| "grad_norm": 0.4070054590702057, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.2394, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028433829148229108, | |
| "grad_norm": 0.5145549178123474, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.2066, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0031988057791757746, | |
| "grad_norm": 0.5820503234863281, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0762, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0035542286435286384, | |
| "grad_norm": 0.6279653310775757, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.0131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035542286435286384, | |
| "eval_loss": 1.0860192775726318, | |
| "eval_runtime": 203.332, | |
| "eval_samples_per_second": 29.135, | |
| "eval_steps_per_second": 14.567, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003909651507881502, | |
| "grad_norm": 0.34148985147476196, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.1582, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0042650743722343655, | |
| "grad_norm": 0.2676335573196411, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.0721, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004620497236587229, | |
| "grad_norm": 0.27544882893562317, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.1066, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004975920100940093, | |
| "grad_norm": 0.3091588616371155, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.0596, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005331342965292957, | |
| "grad_norm": 0.3925229609012604, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.0647, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0056867658296458215, | |
| "grad_norm": 0.47207650542259216, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.957, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.006042188693998685, | |
| "grad_norm": 0.4618014991283417, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.8818, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.006397611558351549, | |
| "grad_norm": 0.6277055740356445, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.8484, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006753034422704413, | |
| "grad_norm": 0.5092412233352661, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.7792, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.007108457287057277, | |
| "grad_norm": 0.8425192832946777, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.8068, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007108457287057277, | |
| "eval_loss": 0.9189969301223755, | |
| "eval_runtime": 203.1123, | |
| "eval_samples_per_second": 29.166, | |
| "eval_steps_per_second": 14.583, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0074638801514101405, | |
| "grad_norm": 0.5134663581848145, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0384, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.007819303015763003, | |
| "grad_norm": 0.35175126791000366, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.9458, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.008174725880115868, | |
| "grad_norm": 0.4536231756210327, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 1.077, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.008530148744468731, | |
| "grad_norm": 0.41004303097724915, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 1.0068, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.008885571608821596, | |
| "grad_norm": 0.47319185733795166, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.9159, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.009240994473174459, | |
| "grad_norm": 0.748140811920166, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.9558, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009596417337527323, | |
| "grad_norm": 0.7021692395210266, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.9694, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.009951840201880186, | |
| "grad_norm": 0.5735881328582764, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.6431, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01030726306623305, | |
| "grad_norm": 0.7242112755775452, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.7265, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.010662685930585914, | |
| "grad_norm": 1.036838412284851, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.8044, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010662685930585914, | |
| "eval_loss": 0.8387618660926819, | |
| "eval_runtime": 203.5878, | |
| "eval_samples_per_second": 29.098, | |
| "eval_steps_per_second": 14.549, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.011018108794938778, | |
| "grad_norm": 0.48848214745521545, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 1.0428, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.011373531659291643, | |
| "grad_norm": 0.38314196467399597, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.8563, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.011728954523644506, | |
| "grad_norm": 0.46951794624328613, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 1.0063, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.01208437738799737, | |
| "grad_norm": 0.4432726502418518, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.9649, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.012439800252350234, | |
| "grad_norm": 0.5523079037666321, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.8765, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.012795223116703098, | |
| "grad_norm": 0.8644940853118896, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.7888, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.013150645981055961, | |
| "grad_norm": 0.7664920091629028, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.7794, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.013506068845408826, | |
| "grad_norm": 0.6504991054534912, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.6936, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.013861491709761689, | |
| "grad_norm": 0.7600428462028503, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.6089, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.014216914574114553, | |
| "grad_norm": 1.446298599243164, | |
| "learning_rate": 0.0, | |
| "loss": 0.7815, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.014216914574114553, | |
| "eval_loss": 0.8283114433288574, | |
| "eval_runtime": 203.69, | |
| "eval_samples_per_second": 29.083, | |
| "eval_steps_per_second": 14.542, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "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": 1.59228597633024e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |