| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23573785950023574, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023573785950023574, | |
| "eval_accuracy": 0.6317716870477788, | |
| "eval_loss": 1.8646224737167358, | |
| "eval_runtime": 492.4929, | |
| "eval_samples_per_second": 15.507, | |
| "eval_steps_per_second": 0.485, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04714757190004715, | |
| "eval_accuracy": 0.7021049967171662, | |
| "eval_loss": 1.4454373121261597, | |
| "eval_runtime": 492.5577, | |
| "eval_samples_per_second": 15.505, | |
| "eval_steps_per_second": 0.485, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07072135785007072, | |
| "eval_accuracy": 0.7335578085807225, | |
| "eval_loss": 1.2683207988739014, | |
| "eval_runtime": 492.7056, | |
| "eval_samples_per_second": 15.5, | |
| "eval_steps_per_second": 0.485, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0942951438000943, | |
| "eval_accuracy": 0.7496352846832398, | |
| "eval_loss": 1.1724069118499756, | |
| "eval_runtime": 492.418, | |
| "eval_samples_per_second": 15.509, | |
| "eval_steps_per_second": 0.485, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11786892975011787, | |
| "grad_norm": 3.823148250579834, | |
| "learning_rate": 4.803551783749804e-05, | |
| "loss": 1.7013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11786892975011787, | |
| "eval_accuracy": 0.7622726018519113, | |
| "eval_loss": 1.1071853637695312, | |
| "eval_runtime": 492.5647, | |
| "eval_samples_per_second": 15.505, | |
| "eval_steps_per_second": 0.485, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14144271570014144, | |
| "eval_accuracy": 0.7731863812800325, | |
| "eval_loss": 1.0427114963531494, | |
| "eval_runtime": 492.2995, | |
| "eval_samples_per_second": 15.513, | |
| "eval_steps_per_second": 0.485, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16501650165016502, | |
| "eval_accuracy": 0.7809848069202094, | |
| "eval_loss": 1.003616452217102, | |
| "eval_runtime": 492.5831, | |
| "eval_samples_per_second": 15.504, | |
| "eval_steps_per_second": 0.485, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.1885902876001886, | |
| "eval_accuracy": 0.7868278015496704, | |
| "eval_loss": 0.9764024615287781, | |
| "eval_runtime": 492.4908, | |
| "eval_samples_per_second": 15.507, | |
| "eval_steps_per_second": 0.485, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.21216407355021216, | |
| "eval_accuracy": 0.7921159020990164, | |
| "eval_loss": 0.94410640001297, | |
| "eval_runtime": 492.6567, | |
| "eval_samples_per_second": 15.502, | |
| "eval_steps_per_second": 0.485, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.23573785950023574, | |
| "grad_norm": 2.0617034435272217, | |
| "learning_rate": 4.607103567499607e-05, | |
| "loss": 0.9942, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23573785950023574, | |
| "eval_accuracy": 0.7963057274181528, | |
| "eval_loss": 0.9231188297271729, | |
| "eval_runtime": 492.777, | |
| "eval_samples_per_second": 15.498, | |
| "eval_steps_per_second": 0.485, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12726, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 200, | |
| "total_flos": 7.41887283560448e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |