Training in progress, step 1600, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9de3911d78d49f5e358bf6a8327668ac0e973b45cc4979d725d4b97ca07d1d3
+oid sha256:40c9ce80711acc5708fa03ca5c1abc26071fb1461cb7e0831999e447eff9cd1a
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5342ab255569127d2a57921eb447e27465679d97ae34009461aa6e2a8f8a0d22
+oid sha256:019263c58bc2b520dec5e0ad177732b5a097fc826cae937845d0a4226930995c
 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([[ 0.6983, -0.0765, -0.0742]])
+# tensor([[ 0.6973, -0.0965, -0.1011]])
 ```
 
 <!--
@@ -709,6 +709,10 @@ You can finetune this model on your own dataset.
 | 0.6606 | 1300 | 0.0903        |
 | 0.6860 | 1350 | 0.0869        |
 | 0.7114 | 1400 | 0.0927        |
+| 0.7368 | 1450 | 0.0919        |
+| 0.7622 | 1500 | 0.0882        |
+| 0.7876 | 1550 | 0.0816        |
+| 0.8130 | 1600 | 0.0847        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02263d2d38933f4d16ab093d1f3edda8036bd5b3aea5a9365ae1418f869e9fa
+oid sha256:6b0951f19e6e47bf8b0d7afa9b9188827b158337d188c1cbb45f30a48fc06d1b
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b75939fb5dcf7b176da089b9be847529fdf776c360625eaa9f4542c8457f341
+oid sha256:ad8ea1af8787344f7eb6b924f0aa1551e33e51330ba17797ae085e9c68294c47
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0299032156c99cc748a49daedbaed704010a8fef256e5ec9b90ef95f2e77d9cd
+oid sha256:7ac15faca44126ea757af3cc9233a4970a99a30bf6b2f36cfb0d4ae9816273ed
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7113821138211383,
+  "epoch": 0.8130081300813008,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,6 +204,34 @@
       "learning_rate": 1.60643704121965e-05,
       "loss": 0.0927,
       "step": 1400
+    },
+    {
+      "epoch": 0.7367886178861789,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.4652738565782046e-05,
+      "loss": 0.0919,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7621951219512195,
+      "grad_norm": 3.421875,
+      "learning_rate": 1.3241106719367592e-05,
+      "loss": 0.0882,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7876016260162602,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.1829474872953134e-05,
+      "loss": 0.0816,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 2.625,
+      "learning_rate": 1.0417843026538679e-05,
+      "loss": 0.0847,
+      "step": 1600
     }
   ],
   "logging_steps": 50,