Upload folder using huggingface_hub

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a8a9cde4c46113cbbf48ae220d46fa6219fad20c081a6bf0aedee0e9719f7e
+oid sha256:667777c452190f8efb5e339659cf4fa836a754a548e0733c79257adbd40e4a11
 size 9949048046

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4e0301bb2e41ff4ff0efb7bdc0cfe5cab5e5713aa08138b7624806cfa7450f
+oid sha256:cc05ba86ee883984ddcd71eb936a37e3d0b8c83ba9eff9d9f8a9a921dc0dacf9
 size 9904474400

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c085de478c04c9209f03c904d8d33b01895c7622458b9895f775f397e6a75cf4
+oid sha256:75fcd7c91eeaf5a795d2fcc071e019dfcfdce82b861e42071e758e82882d68b6
 size 6179210249

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51edccd6f9855740cdfe1d96d81afba5cfd7b32b28cf15897f8fbadf588f1179
+oid sha256:dae77d1d86eb7275f2a9fab8fdd0f3d2e9b085c5393ceeb24294803290f3941e
 size 14511

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0a535d2c9c4c62a74336a7f93b6d947a1152f53a6066eccd4123d6b477c15c
+oid sha256:3415aff70181afd51efc048fb7c4348442ee37b0317e7e93f002f0a59e0e3ea3
 size 627

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005037789125310321,
-  "global_step": 8000,
+  "epoch": 0.005352650945642216,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2782,11 +2782,79 @@
       "eval_samples_per_second": 2.969,
       "eval_steps_per_second": 0.742,
       "step": 8000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9936,
+      "step": 8050
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9682,
+      "step": 8100
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 2.0048,
+      "step": 8150
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9783,
+      "step": 8200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9703,
+      "step": 8250
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 2.0042,
+      "step": 8300
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9848,
+      "step": 8350
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9808,
+      "step": 8400
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9871,
+      "step": 8450
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 1.9733,
+      "step": 8500
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 2.0437986850738525,
+      "eval_runtime": 34093.5093,
+      "eval_samples_per_second": 2.97,
+      "eval_steps_per_second": 0.743,
+      "step": 8500
     }
   ],
   "max_steps": 10000,
   "num_train_epochs": 1,
-  "total_flos": 2.484742130335789e+19,
+  "total_flos": 2.679889113792e+19,
   "trial_name": null,
   "trial_params": null
 }