Training in progress, step 1400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2189eb62627bdac98795adf703b4963d7bb5806a18140f0705bd0846bdcb81
+oid sha256:e9de3911d78d49f5e358bf6a8327668ac0e973b45cc4979d725d4b97ca07d1d3
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec50e543099a6bb0c1f8e5fdd57d0d9e86ebe7e6b5160cc004a39d435e0eea0
+oid sha256:5342ab255569127d2a57921eb447e27465679d97ae34009461aa6e2a8f8a0d22
 size 4718680

last-checkpoint/README.md

@@ -472,7 +472,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.7396, -0.0637, -0.0765]])
+# tensor([[ 0.6983, -0.0765, -0.0742]])
 ```
 
 <!--
@@ -705,6 +705,10 @@ You can finetune this model on your own dataset.
 | 0.5589 | 1100 | 0.1075        |
 | 0.5843 | 1150 | 0.0994        |
 | 0.6098 | 1200 | 0.0911        |
+| 0.6352 | 1250 | 0.0944        |
+| 0.6606 | 1300 | 0.0903        |
+| 0.6860 | 1350 | 0.0869        |
+| 0.7114 | 1400 | 0.0927        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10ebdd6d376d88b30ef3bdc290fee724cdcdb9834c31657cb9b7e697616ef0b
+oid sha256:e02263d2d38933f4d16ab093d1f3edda8036bd5b3aea5a9365ae1418f869e9fa
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92bc90f9a7af2adcce32e0343802524c333d41bf01c18a9ae80cb07c5024b317
+oid sha256:6b75939fb5dcf7b176da089b9be847529fdf776c360625eaa9f4542c8457f341
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e232785d1786cb94e8889d9a79973e568b9bfb82c9ff8f8a12783934ff997c
+oid sha256:0299032156c99cc748a49daedbaed704010a8fef256e5ec9b90ef95f2e77d9cd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6097560975609756,
+  "epoch": 0.7113821138211383,
   "eval_steps": 500,
-  "global_step": 1200,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,6 +176,34 @@
       "learning_rate": 2.171089779785432e-05,
       "loss": 0.0911,
       "step": 1200
+    },
+    {
+      "epoch": 0.6351626016260162,
+      "grad_norm": 3.5,
+      "learning_rate": 2.0299265951439866e-05,
+      "loss": 0.0944,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6605691056910569,
+      "grad_norm": 3.484375,
+      "learning_rate": 1.888763410502541e-05,
+      "loss": 0.0903,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6859756097560976,
+      "grad_norm": 3.0,
+      "learning_rate": 1.7476002258610955e-05,
+      "loss": 0.0869,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7113821138211383,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.60643704121965e-05,
+      "loss": 0.0927,
+      "step": 1400
     }
   ],
   "logging_steps": 50,