Training in progress, step 4400, 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, 0.6197, 0.0899],
-#         [0.6197, 1.0000, 0.1018],
-#         [0.0899, 0.1018, 1.0000]])
+# tensor([[1.0000, 0.5709, 0.1243],
+#         [0.5709, 1.0000, 0.1388],
+#         [0.1243, 0.1388, 1.0000]])
 ```
 
 <!--
@@ -1308,6 +1308,10 @@ You can finetune this model on your own dataset.
 | 0.0724 | 4100 | 0.4755        |
 | 0.0733 | 4150 | 0.4897        |
 | 0.0742 | 4200 | 0.4679        |
+| 0.0751 | 4250 | 0.4712        |
+| 0.0760 | 4300 | 0.4779        |
+| 0.0769 | 4350 | 0.4463        |
+| 0.0778 | 4400 | 0.4917        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6edbab9b964e9ca7b0bab9e7c4f66e7e7bc86ba965571aa4d27edf17e6ee9ae
+oid sha256:28ab5af774c8b92f73b8b0edbc8679fe71ea4dfe39546414176fa364cb641370
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49ef51099777f465890db4e01e4666b0ea051323d10a6459c3da580d7d661a3c
+oid sha256:3f00d4b90b013eb15ec92f6d8f7effe9c310c62760f7a18e7788ea316eefca59
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b1fbe40a2f2e085bd8df80fdc83132b78dd273708a845bf0221a8bf75df21c
+oid sha256:bb2a47368e57ccb8578c1be62d33027ebea1fe6bd63bffa18038620abaa273d0
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0563f0c122c10b3bb9fb8ef7a029cf4fe15b88c3307945ff50155d3485ee7edd
+oid sha256:fa01c0faab1a39c11ceba075e1e73b81a5689cfd1ac0d27ee7fece150d320be6
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c82cc641eba2e585eb912c19a748e90231d19cc7c5365b3984d32e47cc490a
+oid sha256:02cdb9f646b45dd98fa4d4f96eec0334a5b44f90a00b9690154aab22c0f05613
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07421674824618756,
+  "epoch": 0.07775087911505363,
   "eval_steps": 500,
-  "global_step": 4200,
+  "global_step": 4400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -596,6 +596,34 @@
       "learning_rate": 3.709363957597173e-05,
       "loss": 0.4679,
       "step": 4200
+    },
+    {
+      "epoch": 0.07510028096340407,
+      "grad_norm": 2.700162649154663,
+      "learning_rate": 3.7535335689045936e-05,
+      "loss": 0.4712,
+      "step": 4250
+    },
+    {
+      "epoch": 0.0759838136806206,
+      "grad_norm": 1.9648590087890625,
+      "learning_rate": 3.797703180212015e-05,
+      "loss": 0.4779,
+      "step": 4300
+    },
+    {
+      "epoch": 0.07686734639783711,
+      "grad_norm": 2.4238970279693604,
+      "learning_rate": 3.8418727915194345e-05,
+      "loss": 0.4463,
+      "step": 4350
+    },
+    {
+      "epoch": 0.07775087911505363,
+      "grad_norm": 1.745356798171997,
+      "learning_rate": 3.8860424028268556e-05,
+      "loss": 0.4917,
+      "step": 4400
     }
   ],
   "logging_steps": 50,