Training in progress, step 1100

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d39e66e7f52d16c9cc4f24176793bc3d6bc7495f18af703341e3c4506ef40b
+oid sha256:a4f478c8c0035a561ffadd493b087178f85d7e427e572ea2c04c2ee719413918
 size 435640934

trainer_state.json

@@ -153,22 +153,22 @@
       "step": 1000,
       "total_flos": 6.687707580928205e+16,
       "train_loss": 0.0,
-      "train_runtime": 7.1169,
-      "train_samples_per_second": 73347.754,
-      "train_steps_per_second": 71.379
+      "train_runtime": 0.4984,
+      "train_samples_per_second": 523694.092,
+      "train_steps_per_second": 1023.287
     },
     {
       "epoch": 1.96,
-      "eval_loss": 1.2041162252426147,
-      "eval_runtime": 16.97,
-      "eval_samples_per_second": 705.304,
-      "eval_steps_per_second": 2.77,
+      "eval_loss": 1.204106092453003,
+      "eval_runtime": 16.8904,
+      "eval_samples_per_second": 708.629,
+      "eval_steps_per_second": 5.565,
       "step": 1000
     }
   ],
   "logging_steps": 100,
-  "max_steps": 508,
-  "num_train_epochs": 4,
+  "max_steps": 510,
+  "num_train_epochs": 2,
   "save_steps": 100,
   "total_flos": 6.687707580928205e+16,
   "trial_name": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8ad8e1cec322d3bb15dd021fe3953da579ea9c171547e83361375356a9013b
+oid sha256:70fee3b7bd294388999199c1504a58fc60448d7cb1f0ed955e6f90ab85468bbf
 size 4664