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 sha256:3c355932b1631d5cc039fe88a412c00c3f3d18cb613c3652c8741e9192cc4806
+oid sha256:4dd0cd5325744cbadf85834360afa08f075907c48439302dd9bd1990dcba7c09
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2dd401d0d4ffa6433f83d4ac597ff641928d6ea494ae387a1a6f1a6d310553
+oid sha256:618d79044611c03845fd3d5cfff9c6517211438370c9270043bd8df5fd157566
 size 4718680

last-checkpoint/README.md

@@ -511,7 +511,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6620, -0.0063, -0.0333]])
+# tensor([[ 0.6990, -0.1064,  0.0055]])
 ```
 
 <!--
@@ -728,6 +728,10 @@ You can finetune this model on your own dataset.
 | 0.2879 | 300  | 0.2219        |
 | 0.3359 | 350  | 0.2227        |
 | 0.3839 | 400  | 0.207         |
+| 0.4319 | 450  | 0.1853        |
+| 0.4798 | 500  | 0.177         |
+| 0.5278 | 550  | 0.1739        |
+| 0.5758 | 600  | 0.1743        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1b5b40b7da70f2a14fdcffdfb517052cafd4a92b303a999515bd5c70bc3b56e
+oid sha256:688b779211f9d7729cdb8b7a1f33de65e70bf757e770157591258607c47b7f93
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef66f6c3146c65c716246a9b9b1a314970b310fa5bce4e1a4c785a225e5e5d8
+oid sha256:e4cb7e1ce7f84c978a72dad631b014ca653d4764aa7b2675e53c47546614601d
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0af633a4f9f804af5866a99325014522ad3b38b189715886b1cb20a1e95ac1
+oid sha256:edab5dd7827df6c860a06cbc8d688873b247f37062ba5008ca6bb63249a0eb13
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3838771593090211,
+  "epoch": 0.5758157389635317,
   "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": 3.431163287086446e-05,
       "loss": 0.207,
       "step": 400
+    },
+    {
+      "epoch": 0.43186180422264875,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.16435432230523e-05,
+      "loss": 0.1853,
+      "step": 450
+    },
+    {
+      "epoch": 0.4798464491362764,
+      "grad_norm": 4.125,
+      "learning_rate": 2.897545357524013e-05,
+      "loss": 0.177,
+      "step": 500
+    },
+    {
+      "epoch": 0.527831094049904,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.6307363927427965e-05,
+      "loss": 0.1739,
+      "step": 550
+    },
+    {
+      "epoch": 0.5758157389635317,
+      "grad_norm": 4.0,
+      "learning_rate": 2.3639274279615796e-05,
+      "loss": 0.1743,
+      "step": 600
     }
   ],
   "logging_steps": 50,