Training in progress, step 1080, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e59b6eeab109132425badd739781747497d523d81e67c7da5995b47a105606
+oid sha256:0c68d8733c2421d74d33d27a71b8faaca3577b4d3491998c21ad9e220bf4bc9c
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236ee3f6c76e6dd53cb72f79ed12aacb7f2bcdc6d9653f7ff3049589d714a456
+oid sha256:a93f64eae2465bfb76abdbc720e1670309c42f6ef5fde5847b9b4a72a7045183
 size 4718680

last-checkpoint/README.md

@@ -424,7 +424,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[0.9082, 0.0190, 0.0399]])
+# tensor([[0.9084, 0.0169, 0.0379]])
 ```
 
 <!--
@@ -653,6 +653,7 @@ You can finetune this model on your own dataset.
 | 0.8333 | 900  | 0.0716        |
 | 0.8796 | 950  | 0.0806        |
 | 0.9259 | 1000 | 0.0751        |
+| 0.9722 | 1050 | 0.0752        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7043ac46a43b67270262de15fa756613b340ca4d39f45c6b1ad2d3d62b923215
+oid sha256:a0adb6e0dcc2c1d8aebddbe41abccae842f2a544ef23db913500bd2aace7fd60
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a36d649cfa382270fa9cb34ecdc0eaa34459ba7d1d01e0d8f5a0dcd009dec103
+oid sha256:8bbd11bbe752ed8b3b39e9d5af2e0df6f8479b431d6865197530e6cbe826f825
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71506dd75ffea4620eca46bea4d3e2da666baa9d78fa9907096978fc32ffdb98
+oid sha256:b75241c49962959a89b485b0bfbbc2bd5c21f6fee93db9750e118593960c9892
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9259259259259259,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1080,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,13 @@
       "learning_rate": 4.166666666666667e-06,
       "loss": 0.0751,
       "step": 1000
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 3.734375,
+      "learning_rate": 1.5946502057613169e-06,
+      "loss": 0.0752,
+      "step": 1050
     }
   ],
   "logging_steps": 50,
@@ -162,7 +169,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }