Training in progress, step 1200, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00693ca726c3aa172fe54b2bbf0f5a2ac7ef3e0f15e6ef10272ea4e790f1a7ea
+oid sha256:13c09a5e85744071f43b660f276c30dd0c78a002e829d09339df6553d68e5e9c
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec4b258539975d8b345245718777e000a517241aa23cc10eb37dd6ffc792aab
+oid sha256:9bce4267c7916e7b1d39e730977890918f472a20904f7cdb5c6470b3bb959efc
 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([[ 0.4709, -0.1225,  0.1580]])
+# tensor([[ 0.6289, -0.0545,  0.2478]])
 ```
 
 <!--
@@ -707,6 +707,10 @@ You can finetune this model on your own dataset.
 | 0.2978 | 900  | 0.0927        |
 | 0.3144 | 950  | 0.0946        |
 | 0.3309 | 1000 | 0.0988        |
+| 0.3475 | 1050 | 0.091         |
+| 0.3640 | 1100 | 0.091         |
+| 0.3805 | 1150 | 0.0802        |
+| 0.3971 | 1200 | 0.0824        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ac8f3e49e96856b9bc03370f38b3741180dcb037151388805051f7ea3ffe8f
+oid sha256:ba9d8f01d2057279be1dd562ae68b04fc16b9056d28e910d54d2259bf7168206
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45310978fd3a8f93b72bef2a6c703555d44d1cb9ff7e494d4ad2616538a9ff9b
+oid sha256:763bdcee7c6c388f0295a0946aba7ea97cd1965328c61b7d56cab32345452a48
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc83c3e7cbaa37ce1778897d2e62cb7b8c41ece6f6ed0596eecff4f3f73fcd86
+oid sha256:c53cf553f6434449959e590b32ad22ac0c6e07ffae962a4164d31ea3a75d345e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:220ab6d106cef455c6160d9f0f26a124a8032f6a0351c6a17f6905e5df60789d
+oid sha256:781bdd0549418e8b91230f3cd2918472966507e472c42f0916b387b617b2e59a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3309066843150232,
+  "epoch": 0.3970880211780278,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,34 @@
       "learning_rate": 1.4880470761309307e-05,
       "loss": 0.0988,
       "step": 1000
+    },
+    {
+      "epoch": 0.34745201853077434,
+      "grad_norm": 5.365964889526367,
+      "learning_rate": 1.4512688488414859e-05,
+      "loss": 0.091,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3639973527465255,
+      "grad_norm": 7.908538341522217,
+      "learning_rate": 1.4144906215520414e-05,
+      "loss": 0.091,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3805426869622766,
+      "grad_norm": 6.80029821395874,
+      "learning_rate": 1.3777123942625967e-05,
+      "loss": 0.0802,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3970880211780278,
+      "grad_norm": 4.817410945892334,
+      "learning_rate": 1.3409341669731519e-05,
+      "loss": 0.0824,
+      "step": 1200
     }
   ],
   "logging_steps": 50,