Training in progress, step 600, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b7d8e26502bef66cd394804c119c53925b8a95a8eb515ceb99e319b4419777b
+oid sha256:063df22142057d2c8696e2ae017f3c74712479c71f4d55eef0fb2e5056c3acd9
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09f31d2c27e5777899f38f12efbefe39861b67d41a06033747f50629b7b75d2
+oid sha256:64d5acf9f98788d6a2922cef011bd936df1b9e1686c779971fca5c10bcefa77a
 size 9437272

last-checkpoint/README.md

@@ -450,7 +450,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6146, -0.1275,  0.1947]])
+# tensor([[ 0.6287, -0.0852,  0.2024]])
 ```
 
 <!--
@@ -695,6 +695,10 @@ You can finetune this model on your own dataset.
 | 0.0993 | 300  | 0.1209        |
 | 0.1158 | 350  | 0.1335        |
 | 0.1324 | 400  | 0.122         |
+| 0.1489 | 450  | 0.1231        |
+| 0.1655 | 500  | 0.1147        |
+| 0.1820 | 550  | 0.1224        |
+| 0.1985 | 600  | 0.1113        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e965f79ca7debd6b4f4c1d6d6929455a31acfbacae1439a742a8e671b5ceace
+oid sha256:033d8f3dceb818090abe62e25c4150d763b8734695c086defcaf1d40dd639814
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6462fbe9a03bbd4290b927d8c65c7721ae87f57e10581410935d03f7c5aac998
+oid sha256:8b8dd546a621af0d9b4e61bb98d55921f58d185839602e1199e76267595fae5f
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a82daf79aef8e8b5ecd74ff5d2377b7a09a1c4d4504ecc0c2a12006214be596b
+oid sha256:29a7e95a048d31e7d9e5712bbf85fc8632444e30166b0ed25502f6a768b9211d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861bac2b72011625e6f591b75aa2d64e2a0d0044b33ec2c6f9d76288e8aff747
+oid sha256:6deff325eec0670b4e2cbe8cfbf49072d5c3640acac1966fd95e1d68c238f471
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13236267372600927,
+  "epoch": 0.1985440105890139,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 1.9293858036042665e-05,
       "loss": 0.122,
       "step": 400
+    },
+    {
+      "epoch": 0.14890800794176043,
+      "grad_norm": 9.762269020080566,
+      "learning_rate": 1.8926075763148218e-05,
+      "loss": 0.1231,
+      "step": 450
+    },
+    {
+      "epoch": 0.1654533421575116,
+      "grad_norm": 9.085260391235352,
+      "learning_rate": 1.855829349025377e-05,
+      "loss": 0.1147,
+      "step": 500
+    },
+    {
+      "epoch": 0.18199867637326275,
+      "grad_norm": 3.281120538711548,
+      "learning_rate": 1.8190511217359325e-05,
+      "loss": 0.1224,
+      "step": 550
+    },
+    {
+      "epoch": 0.1985440105890139,
+      "grad_norm": 10.944239616394043,
+      "learning_rate": 1.782272894446488e-05,
+      "loss": 0.1113,
+      "step": 600
     }
   ],
   "logging_steps": 50,