| { | |
| "best_metric": 1.3160691261291504, | |
| "best_model_checkpoint": "Models/checkpoint-400", | |
| "epoch": 1.853997682502897, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.1801, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.1794, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.0713, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.8861, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00015, | |
| "loss": 1.8091, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.7075, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 1.5947, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.6255, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00027, | |
| "loss": 1.598, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5142, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00029449541284403666, | |
| "loss": 1.5258, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00028899082568807334, | |
| "loss": 1.4687, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0002834862385321101, | |
| "loss": 1.4434, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00027798165137614677, | |
| "loss": 1.4302, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00027247706422018345, | |
| "loss": 1.3928, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00026697247706422014, | |
| "loss": 1.4525, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0002614678899082569, | |
| "loss": 1.4681, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00025596330275229356, | |
| "loss": 1.4105, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00025045871559633025, | |
| "loss": 1.3371, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00024495412844036693, | |
| "loss": 1.3493, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.4036030769348145, | |
| "eval_runtime": 87.4611, | |
| "eval_samples_per_second": 22.867, | |
| "eval_steps_per_second": 2.858, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00023944954128440364, | |
| "loss": 1.3139, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00023394495412844035, | |
| "loss": 1.3878, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00022844036697247704, | |
| "loss": 1.3011, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00022293577981651375, | |
| "loss": 1.3121, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00021743119266055044, | |
| "loss": 1.3234, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00021192660550458712, | |
| "loss": 1.2722, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00020642201834862383, | |
| "loss": 1.2897, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00020091743119266052, | |
| "loss": 1.2723, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00019541284403669723, | |
| "loss": 1.2375, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00018990825688073391, | |
| "loss": 1.2756, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00018440366972477063, | |
| "loss": 1.2567, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001788990825688073, | |
| "loss": 1.2491, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00017339449541284402, | |
| "loss": 1.2501, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0001678899082568807, | |
| "loss": 1.2702, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 0.00016238532110091742, | |
| "loss": 1.2882, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0001568807339449541, | |
| "loss": 1.2681, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.00015137614678899082, | |
| "loss": 1.2652, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00014587155963302753, | |
| "loss": 1.2324, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0001403669724770642, | |
| "loss": 1.2817, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00013486238532110092, | |
| "loss": 1.2244, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 1.3160691261291504, | |
| "eval_runtime": 87.8417, | |
| "eval_samples_per_second": 22.768, | |
| "eval_steps_per_second": 2.846, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 645, | |
| "num_train_epochs": 3, | |
| "total_flos": 3.853804232717107e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |