| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.99867197875166, | |
| "eval_steps": 500, | |
| "global_step": 376, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.991278696516879e-05, | |
| "loss": 1.0017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9651756349750716e-05, | |
| "loss": 0.881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.9218729375518135e-05, | |
| "loss": 0.7979, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.861672729019797e-05, | |
| "loss": 0.7022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.784995028809707e-05, | |
| "loss": 0.5844, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.692374820516679e-05, | |
| "loss": 0.4454, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.584458319296868e-05, | |
| "loss": 0.4076, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.4619984631966524e-05, | |
| "loss": 0.4111, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.3258496598716736e-05, | |
| "loss": 0.4115, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.176961825348059e-05, | |
| "loss": 0.3566, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.016373756417669e-05, | |
| "loss": 0.4302, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.845205882908432e-05, | |
| "loss": 0.4271, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.6646524503974955e-05, | |
| "loss": 0.4625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.475973187908737e-05, | |
| "loss": 0.5066, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.280484518729466e-05, | |
| "loss": 0.3887, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.079550375668821e-05, | |
| "loss": 0.3675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.8745726848402036e-05, | |
| "loss": 0.4095, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6669815843628042e-05, | |
| "loss": 0.3782, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.4582254462267476e-05, | |
| "loss": 0.4195, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.2497607709397543e-05, | |
| "loss": 0.3392, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.0430420254607748e-05, | |
| "loss": 0.3347, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.8395114953217852e-05, | |
| "loss": 0.4117, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.640589221739926e-05, | |
| "loss": 0.3772, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.447663093929163e-05, | |
| "loss": 0.4403, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.2620791657378664e-05, | |
| "loss": 0.3867, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.0851322641735118e-05, | |
| "loss": 0.3688, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 9.180569553392535e-06, | |
| "loss": 0.3655, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.620189308133943e-06, | |
| "loss": 0.4144, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.181068745693716e-06, | |
| "loss": 0.3298, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.873248671810928e-06, | |
| "loss": 0.3337, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.7058538030980942e-06, | |
| "loss": 0.3217, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2.687029103502972e-06, | |
| "loss": 0.3222, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.823882956546566e-06, | |
| "loss": 0.3989, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.1224375698271894e-06, | |
| "loss": 0.3805, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.875869578203824e-07, | |
| "loss": 0.4108, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.230627961304993e-07, | |
| "loss": 0.3578, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.1408385430356516e-08, | |
| "loss": 0.3453, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.35242682695388794, | |
| "eval_runtime": 28.2403, | |
| "eval_samples_per_second": 11.862, | |
| "eval_steps_per_second": 5.949, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 376, | |
| "total_flos": 2.22435081191424e+16, | |
| "train_loss": 0.4441075046011742, | |
| "train_runtime": 553.4721, | |
| "train_samples_per_second": 5.44, | |
| "train_steps_per_second": 0.679 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 376, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 2.22435081191424e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |