Training in progress, step 6600, 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, 0.6415, 0.0981],
-#         [0.6415, 1.0000, 0.1488],
-#         [0.0981, 0.1488, 1.0000]])
+# tensor([[1.0000, 0.6159, 0.1268],
+#         [0.6159, 1.0000, 0.1762],
+#         [0.1268, 0.1762, 1.0000]])
 ```
 
 <!--
@@ -1244,6 +1244,10 @@ You can finetune this model on your own dataset.
 | 0.1113 | 6300 | 0.4175        |
 | 0.1122 | 6350 | 0.4387        |
 | 0.1131 | 6400 | 0.4554        |
+| 0.1140 | 6450 | 0.581         |
+| 0.1149 | 6500 | 0.4746        |
+| 0.1157 | 6550 | 0.4511        |
+| 0.1166 | 6600 | 0.3871        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d95e3d0943240c31da6df746f9f3cca8daffbcbf4c519e4d4baa811b80a13fb
+oid sha256:533a4ed7cc131c123cb5372a76db759d112ce54c54aa81a76148675ba2517e16
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29fd6ade8a7591354a162ab7d03eaddfcef75d266f53ddc2969b95870d3ff8d
+oid sha256:e4b208b08280c11c448779e04cc3b8922c613d68c1eab949db3e687b7cc69b1e
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3d8144207555c6ec60990d6474d3fd0ec58c08d1eca3fbe5bc862bb1b86096
+oid sha256:be44f909c9d108035e113ae97840e629f406742e33dabbb6dac446308a2323aa
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1838e2ba3161fe9cda5ffbc1228be866f2d720c99e25c4fc0f69015d501e1608
+oid sha256:c456427ce8bd7ccdacb5f3df51e3a128141f61214f0829c4af25f2c18a7d9842
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526489e33cb7a870777fedd3daf2b089d8bfd92de79a88cf54c04050587dcfea
+oid sha256:825a93f9b8689a94da1d037071f9688200700d005038804108d953a8cdcd62a0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11309218780371437,
+  "epoch": 0.11662631867258044,
   "eval_steps": 500,
-  "global_step": 6400,
+  "global_step": 6600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -904,6 +904,34 @@
       "learning_rate": 4.927450864895643e-05,
       "loss": 0.4554,
       "step": 6400
+    },
+    {
+      "epoch": 0.11397572052093088,
+      "grad_norm": 4.113645553588867,
+      "learning_rate": 4.92254226306179e-05,
+      "loss": 0.581,
+      "step": 6450
+    },
+    {
+      "epoch": 0.11485925323814741,
+      "grad_norm": 1.6027569770812988,
+      "learning_rate": 4.917633661227936e-05,
+      "loss": 0.4746,
+      "step": 6500
+    },
+    {
+      "epoch": 0.11574278595536393,
+      "grad_norm": 2.0555272102355957,
+      "learning_rate": 4.912725059394083e-05,
+      "loss": 0.4511,
+      "step": 6550
+    },
+    {
+      "epoch": 0.11662631867258044,
+      "grad_norm": 2.6827495098114014,
+      "learning_rate": 4.9078164575602285e-05,
+      "loss": 0.3871,
+      "step": 6600
     }
   ],
   "logging_steps": 50,