Training in progress, step 5000, checkpoint

last-checkpoint/README.md

@@ -286,9 +286,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.6133, 0.1462],
-#         [0.6133, 1.0000, 0.1725],
-#         [0.1462, 0.1725, 1.0000]])
+# tensor([[1.0000, 0.6188, 0.1217],
+#         [0.6188, 1.0000, 0.1507],
+#         [0.1217, 0.1507, 1.0000]])
 ```
 
 <!--
@@ -1320,6 +1320,10 @@ You can finetune this model on your own dataset.
 | 0.0831 | 4700 | 0.5158        |
 | 0.0839 | 4750 | 0.4598        |
 | 0.0848 | 4800 | 0.4662        |
+| 0.0857 | 4850 | 0.459         |
+| 0.0866 | 4900 | 0.4275        |
+| 0.0875 | 4950 | 0.5575        |
+| 0.0884 | 5000 | 0.4197        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455ab825540498b5f5b373a58b71653674612a70e8ee7fc5be9b1867efa7eac4
+oid sha256:90e4d2bbf59fbcb40ff4b4462a436528ececec21cfbe639ba0aa1880e8a048b9
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf9c1feb933a833e9a1940398a123539c973a5c3ef49342b6ba0a21987b8a62
+oid sha256:498b25c3a0cdf659b68bca58a1fe81b240dadbd1c0686b5aa30fdf8a0f4407de
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb98f3b30b900a902f900b8100ff06f09878e462230501b172e1989e2314478f
+oid sha256:bbd110dd6b99c908a73a401be3d8438b48f355d5cb710bfb9c01fca2894f5f8e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b429070a564985551cfca2e541b4c4fca20d998c67cc7cb6e2b59f638df425a3
+oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d7d41c126e55275e34a7a7f11165206f98f8c233f762fcdd72745ff49aac18
+oid sha256:77d3a1390f85cf6329aeb072176eb6782a1d00623e0775f00f722a024157ca78
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08481914085278577,
+  "epoch": 0.08835327172165185,
   "eval_steps": 500,
-  "global_step": 4800,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -680,6 +680,34 @@
       "learning_rate": 4.239399293286219e-05,
       "loss": 0.4662,
       "step": 4800
+    },
+    {
+      "epoch": 0.0857026735700023,
+      "grad_norm": 2.0289080142974854,
+      "learning_rate": 4.28356890459364e-05,
+      "loss": 0.459,
+      "step": 4850
+    },
+    {
+      "epoch": 0.08658620628721882,
+      "grad_norm": 2.6102516651153564,
+      "learning_rate": 4.32773851590106e-05,
+      "loss": 0.4275,
+      "step": 4900
+    },
+    {
+      "epoch": 0.08746973900443533,
+      "grad_norm": 2.5842251777648926,
+      "learning_rate": 4.3719081272084805e-05,
+      "loss": 0.5575,
+      "step": 4950
+    },
+    {
+      "epoch": 0.08835327172165185,
+      "grad_norm": 3.6427652835845947,
+      "learning_rate": 4.4160777385159016e-05,
+      "loss": 0.4197,
+      "step": 5000
     }
   ],
   "logging_steps": 50,