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 sha256:80ba4c20eaffda01a7578f0684f2336ed09ec07c7aab125579261832916efe9d
+oid sha256:3c355932b1631d5cc039fe88a412c00c3f3d18cb613c3652c8741e9192cc4806
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97089f7924b8ca62eb91f3741ef27a57ff82b97b5f62f3a66bfd0ab18234833
+oid sha256:fb2dd401d0d4ffa6433f83d4ac597ff641928d6ea494ae387a1a6f1a6d310553
 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([[ 0.6871, -0.1118, -0.0955]])
+# tensor([[ 0.6620, -0.0063, -0.0333]])
 ```
 
 <!--
@@ -724,6 +724,10 @@ You can finetune this model on your own dataset.
 | 0.0960 | 100  | 0.2763        |
 | 0.1440 | 150  | 0.2883        |
 | 0.1919 | 200  | 0.2636        |
+| 0.2399 | 250  | 0.2626        |
+| 0.2879 | 300  | 0.2219        |
+| 0.3359 | 350  | 0.2227        |
+| 0.3839 | 400  | 0.207         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00293b8b4761f0d06286339bd7a4cc183edee2c660dc984093785075d782b637
+oid sha256:b1b5b40b7da70f2a14fdcffdfb517052cafd4a92b303a999515bd5c70bc3b56e
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e772b8cb66794b0681c305d4a6ee5eb7b613bcff465dc3fe7029c205d3e580
+oid sha256:6ef66f6c3146c65c716246a9b9b1a314970b310fa5bce4e1a4c785a225e5e5d8
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d88407aff68ef8509234fd2211bb50888896b55849641ad9180c09511a40fab
+oid sha256:df0af633a4f9f804af5866a99325014522ad3b38b189715886b1cb20a1e95ac1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19193857965451055,
+  "epoch": 0.3838771593090211,
   "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": 4.4983991462113126e-05,
       "loss": 0.2636,
       "step": 200
+    },
+    {
+      "epoch": 0.2399232245681382,
+      "grad_norm": 5.875,
+      "learning_rate": 4.231590181430096e-05,
+      "loss": 0.2626,
+      "step": 250
+    },
+    {
+      "epoch": 0.28790786948176583,
+      "grad_norm": 5.9375,
+      "learning_rate": 3.9647812166488794e-05,
+      "loss": 0.2219,
+      "step": 300
+    },
+    {
+      "epoch": 0.33589251439539347,
+      "grad_norm": 5.125,
+      "learning_rate": 3.697972251867663e-05,
+      "loss": 0.2227,
+      "step": 350
+    },
+    {
+      "epoch": 0.3838771593090211,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.431163287086446e-05,
+      "loss": 0.207,
+      "step": 400
     }
   ],
   "logging_steps": 50,