Training in progress, step 1080, checkpoint

last-checkpoint/README.md

@@ -418,9 +418,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.8345, 0.0036],
-#         [0.8345, 1.0000, 0.0463],
-#         [0.0036, 0.0463, 1.0000]])
+# tensor([[1.0000, 0.8355, 0.0051],
+#         [0.8355, 1.0000, 0.0522],
+#         [0.0051, 0.0522, 1.0000]])
 ```
 
 <!--
@@ -645,6 +645,7 @@ You can finetune this model on your own dataset.
 | 0.8333 | 900  | 0.2087        |
 | 0.8796 | 950  | 0.2129        |
 | 0.9259 | 1000 | 0.2103        |
+| 0.9722 | 1050 | 0.2077        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6982a03a13069dbd7b223ad85adad16126456dd21e17f9bd1ae85ca8193120
+oid sha256:c657c601346e9dc34b4fdc1e8b099a6a54467b2b2fe6758139f7a1ab292a0865
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d233c33a97447e6a9abb3c8e8e512eb8909f5d83f758b39d62a45a2af03c91
+oid sha256:878f49566b0fc7aa315a9fa895c747d8ab86ddbf97a6033de03a4d5cd3a42f4f
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1372d08aae4c539a42dc762c4bad69d2ee0d24aad936d7a04cbe426c002b491
+oid sha256:a313be47df684e5fefd5b05c68d005401a7c2b075592a1cbe746ae1b1ffc519c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:bc9210217856a9bbed1dae2edba26cb4f5bfdb3e93cd6bda6ff6d4a1235ae0dd
 size 1383

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": 0.2103,
       "step": 1000
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 1.0842205286026,
+      "learning_rate": 1.5946502057613169e-06,
+      "loss": 0.2077,
+      "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": {}
     }