Training in progress, step 6800, 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, 0.6159, 0.1268],
-#         [0.6159, 1.0000, 0.1762],
-#         [0.1268, 0.1762, 1.0000]])
+# tensor([[1.0000, 0.6386, 0.0907],
+#         [0.6386, 1.0000, 0.1293],
+#         [0.0907, 0.1293, 1.0000]])
 ```
 
 <!--
@@ -1248,6 +1248,10 @@ You can finetune this model on your own dataset.
 | 0.1149 | 6500 | 0.4746        |
 | 0.1157 | 6550 | 0.4511        |
 | 0.1166 | 6600 | 0.3871        |
+| 0.1175 | 6650 | 0.449         |
+| 0.1184 | 6700 | 0.3458        |
+| 0.1193 | 6750 | 0.4791        |
+| 0.1202 | 6800 | 0.4445        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533a4ed7cc131c123cb5372a76db759d112ce54c54aa81a76148675ba2517e16
+oid sha256:b02e9263fae48b1d9ab2f1178fcee32bed4de27687bb815e26abc0ce008c821e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b208b08280c11c448779e04cc3b8922c613d68c1eab949db3e687b7cc69b1e
+oid sha256:913066d7b5165875dea05ddec8312156da1e56f82e24e99d791ccdb18b2f2155
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be44f909c9d108035e113ae97840e629f406742e33dabbb6dac446308a2323aa
+oid sha256:e882bce39886348a50b26b191125b019e0e62425e804cb094d791f2c1855ea8c
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c456427ce8bd7ccdacb5f3df51e3a128141f61214f0829c4af25f2c18a7d9842
+oid sha256:50fb3d1e5c722b019233137abea1c664e37622c6ede4dfdabd46503c9bbc26b1
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825a93f9b8689a94da1d037071f9688200700d005038804108d953a8cdcd62a0
+oid sha256:11e206eec8216dd19609780d011982a4e55c6f1b80f70dfd43f28e3b1dc99011
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11662631867258044,
+  "epoch": 0.12016044954144652,
   "eval_steps": 500,
-  "global_step": 6600,
+  "global_step": 6800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -932,6 +932,34 @@
       "learning_rate": 4.9078164575602285e-05,
       "loss": 0.3871,
       "step": 6600
+    },
+    {
+      "epoch": 0.11750985138979697,
+      "grad_norm": 1.969202995300293,
+      "learning_rate": 4.902907855726375e-05,
+      "loss": 0.449,
+      "step": 6650
+    },
+    {
+      "epoch": 0.11839338410701349,
+      "grad_norm": 1.9535086154937744,
+      "learning_rate": 4.8979992538925214e-05,
+      "loss": 0.3458,
+      "step": 6700
+    },
+    {
+      "epoch": 0.11927691682423,
+      "grad_norm": 1.7251821756362915,
+      "learning_rate": 4.893090652058668e-05,
+      "loss": 0.4791,
+      "step": 6750
+    },
+    {
+      "epoch": 0.12016044954144652,
+      "grad_norm": 1.7175688743591309,
+      "learning_rate": 4.8881820502248144e-05,
+      "loss": 0.4445,
+      "step": 6800
     }
   ],
   "logging_steps": 50,