Training in progress, step 2800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60070dd67aa609f2ec4f6099d7d305d359dcc87b0243c555b4c92a408ce9d712
+oid sha256:032edebe5f429dd79fba4966fcbde9a9cc40387fbb5ff3037fee5320982f533d
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f7cffbf560a28dbdda8e392d68b3a6612c84a2695c8f5f18a821a6d39735e6
+oid sha256:a83690af4caa724b099279db73cf30ae7344e4b81bfbf12086b7460efc44b21e
 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([[ 0.5888, -0.1134,  0.2544]])
+# tensor([[ 0.5930, -0.1253,  0.2933]])
 ```
 
 <!--
@@ -739,6 +739,10 @@ You can finetune this model on your own dataset.
 | 0.8273 | 2500 | 0.0536        |
 | 0.8438 | 2550 | 0.0562        |
 | 0.8604 | 2600 | 0.0546        |
+| 0.8769 | 2650 | 0.0551        |
+| 0.8934 | 2700 | 0.0619        |
+| 0.9100 | 2750 | 0.0501        |
+| 0.9265 | 2800 | 0.0488        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9269f4be93991384c4f927cab218c96e7647244f18be47d991875eefe31fe1b4
+oid sha256:b1fb884bddc343ee71ee047c5c0febe2b1e7e4993b3fc969c8ebc7e8ce609f95
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7831d803c865f7e99a7918d82c3c406fbd5cc5f5d3e8383554847671b1ac4256
+oid sha256:fbcf9758ec6185612baccc164b5f73985fbc506bec38cb9c649eb13a9fdc06d7
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ccbe8068d53f3cc47989534cf2cf09a26c0622368fe1ff0065518632dc4752
+oid sha256:e788658da60471d70bc971aa62815f67253d726fc76137a47b5e2b2bda689438
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615edf11d6f1cfab17840ec8946b503fd418735a16b0c229a49e61367753f384
+oid sha256:7aec44cdda33ef7dab0fb72bc661b8cbbd0d3c4d93e1602b0ef95ed38aa2a425
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8603573792190602,
+  "epoch": 0.9265387160820648,
   "eval_steps": 500,
-  "global_step": 2600,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -372,6 +372,34 @@
       "learning_rate": 3.1114380286870177e-06,
       "loss": 0.0546,
       "step": 2600
+    },
+    {
+      "epoch": 0.8769027134348114,
+      "grad_norm": 5.102752208709717,
+      "learning_rate": 2.7436557557925706e-06,
+      "loss": 0.0551,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8934480476505625,
+      "grad_norm": 4.97892951965332,
+      "learning_rate": 2.3758734828981244e-06,
+      "loss": 0.0619,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9099933818663137,
+      "grad_norm": 8.729324340820312,
+      "learning_rate": 2.008091210003678e-06,
+      "loss": 0.0501,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9265387160820648,
+      "grad_norm": 6.92756462097168,
+      "learning_rate": 1.6403089371092316e-06,
+      "loss": 0.0488,
+      "step": 2800
     }
   ],
   "logging_steps": 50,