Training in progress, step 400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32bfa5f6e9259dec81cc5bba77922c05ea4450cb5363b9e39a8e3b6efee4c13
+oid sha256:3b7d8e26502bef66cd394804c119c53925b8a95a8eb515ceb99e319b4419777b
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4776c819cbf9cd976833c5cb4487169ab05deae90b4dabcc292d2a9d8737e2
+oid sha256:d09f31d2c27e5777899f38f12efbefe39861b67d41a06033747f50629b7b75d2
 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([[ 0.6404, -0.0838,  0.1479]])
+# tensor([[ 0.6146, -0.1275,  0.1947]])
 ```
 
 <!--
@@ -691,6 +691,10 @@ You can finetune this model on your own dataset.
 | 0.0331 | 100  | 0.1448        |
 | 0.0496 | 150  | 0.1364        |
 | 0.0662 | 200  | 0.1064        |
+| 0.0827 | 250  | 0.119         |
+| 0.0993 | 300  | 0.1209        |
+| 0.1158 | 350  | 0.1335        |
+| 0.1324 | 400  | 0.122         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43fd0b9b8721c9ea306dd8f4764df5603c03aa7978abc57d73a44d69f7b42300
+oid sha256:9e965f79ca7debd6b4f4c1d6d6929455a31acfbacae1439a742a8e671b5ceace
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e061afeaae568c474e3f579c8acb359c0b7dd5ce97fa97f1910796df7e71b90
+oid sha256:6462fbe9a03bbd4290b927d8c65c7721ae87f57e10581410935d03f7c5aac998
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd605bcdfda1a9d9eac4f3ea7ab051df8ad1e55668c146cc899ab908c9d1ebe
+oid sha256:a82daf79aef8e8b5ecd74ff5d2377b7a09a1c4d4504ecc0c2a12006214be596b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc057fbca03ad393f5dd382b07edb53abde6442bd92793df58cb201522d6453
+oid sha256:861bac2b72011625e6f591b75aa2d64e2a0d0044b33ec2c6f9d76288e8aff747
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06618133686300463,
+  "epoch": 0.13236267372600927,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,34 @@
       "learning_rate": 1.3135313531353136e-05,
       "loss": 0.1064,
       "step": 200
+    },
+    {
+      "epoch": 0.0827266710787558,
+      "grad_norm": 5.249364376068115,
+      "learning_rate": 1.6435643564356436e-05,
+      "loss": 0.119,
+      "step": 250
+    },
+    {
+      "epoch": 0.09927200529450694,
+      "grad_norm": 10.57626724243164,
+      "learning_rate": 1.9735973597359735e-05,
+      "loss": 0.1209,
+      "step": 300
+    },
+    {
+      "epoch": 0.1158173395102581,
+      "grad_norm": 9.12836742401123,
+      "learning_rate": 1.966164030893711e-05,
+      "loss": 0.1335,
+      "step": 350
+    },
+    {
+      "epoch": 0.13236267372600927,
+      "grad_norm": 7.3058061599731445,
+      "learning_rate": 1.9293858036042665e-05,
+      "loss": 0.122,
+      "step": 400
     }
   ],
   "logging_steps": 50,