Training in progress, step 1080, checkpoint

last-checkpoint/README.md

@@ -422,7 +422,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.8672, -0.0147, -0.0254]])
+# tensor([[ 0.8638, -0.0123, -0.0135]])
 ```
 
 <!--
@@ -652,6 +652,7 @@ Query:
 | 0.8333 | 900  | 0.0847        |
 | 0.8796 | 950  | 0.0914        |
 | 0.9259 | 1000 | 0.0847        |
+| 0.9722 | 1050 | 0.0842        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c33d61cffa33493edbadf676b157d37c41cb3a5c5fca7f920f1ccd505300f22
+oid sha256:cb5872bb140cabd9bac9264d36c4f1c7df18c18d622dc2d73b61e53c4f70528e
 size 2383139480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84db4700a8bb0936e936db6653a4d4281969c72265e40f14c5ac9720efe3b617
+oid sha256:14f1c7e409fe6c3d29945f38bed6816c6d70157f91d0e1bffd7065e3434ec37f
 size 4766477350

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16c8942124de0a7ec965a9112f2b847966689d0d650d6ff8cc8f1b2761c8b2a
+oid sha256:143a5b3812f11a0ce92f4896d57f598a2f196c87d5b52f7101c582a4b86122c2
 size 1064

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": 0.0847,
       "step": 1000
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 1.3060165643692017,
+      "learning_rate": 1.5946502057613169e-06,
+      "loss": 0.0842,
+      "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": {}
     }