Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7353692ff981605c93cf22b096dbd246c5cf5bf5fc543b490cf3abeac82a7a31
+oid sha256:3136b9dabce6a4ae406f1d3498508a41caaee6e48e4f89e5e650e30fb89be72a
 size 59001752

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149be6cff081d78c7d5b1ec35545a1530746b35e6a028f2e35055b6d9fbeb68c
+oid sha256:006d09f6e0c431d7ae5b9eb4fbaae5108b8d1e413f666ee8fca34360e86c1c0e
 size 118086731

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3365689e6d26d46f2bfa2d42b0b54103889b4f6a6bad2f60268c5b6325623d
+oid sha256:2e2db19db6959d99d7cf488b002f6d817e98d33ad082cb99f1481611b97a8b6d
 size 14645

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3656c0abce9576d0b5083188f2c7d6efcbee0134d27c94bb8b76920474ad16de
+oid sha256:7bd565e4d2ccaef156f334400d2b3c0f963cb4267afcfb22f72d1c02240578ac
 size 1383

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebaf2e9a58bbd47b2799ce9fd04cb408b13ca7015b9a1b4e2b2bcad498171ac
+oid sha256:5367250aa3dbe18a71a87c36f9a3373d602c91495e0cb8690451d95250cc0609
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035555028814387934,
+  "epoch": 0.04740670508585058,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 0.00048228253140554636,
       "loss": 1.0983,
       "step": 600
+    },
+    {
+      "epoch": 0.03851794788225359,
+      "grad_norm": 0.09815791249275208,
+      "learning_rate": 0.0004808011377103579,
+      "loss": 1.1235,
+      "step": 650
+    },
+    {
+      "epoch": 0.04148086695011926,
+      "grad_norm": 0.07672577351331711,
+      "learning_rate": 0.0004793197440151695,
+      "loss": 1.0744,
+      "step": 700
+    },
+    {
+      "epoch": 0.04444378601798492,
+      "grad_norm": 0.08625241369009018,
+      "learning_rate": 0.0004778679781938848,
+      "loss": 1.0897,
+      "step": 750
+    },
+    {
+      "epoch": 0.04740670508585058,
+      "grad_norm": 0.10188218951225281,
+      "learning_rate": 0.0004763865844986964,
+      "loss": 1.0737,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -111,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.1133136674816e+16,
+  "total_flos": 5.4844182233088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null