Training in progress, step 6400, 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, 0.6439, 0.1032],
-#         [0.6439, 1.0000, 0.1639],
-#         [0.1032, 0.1639, 1.0000]])
+# tensor([[1.0000, 0.6415, 0.0981],
+#         [0.6415, 1.0000, 0.1488],
+#         [0.0981, 0.1488, 1.0000]])
 ```
 
 <!--
@@ -1240,6 +1240,10 @@ You can finetune this model on your own dataset.
 | 0.1078 | 6100 | 0.3949        |
 | 0.1087 | 6150 | 0.4491        |
 | 0.1096 | 6200 | 0.435         |
+| 0.1104 | 6250 | 0.3865        |
+| 0.1113 | 6300 | 0.4175        |
+| 0.1122 | 6350 | 0.4387        |
+| 0.1131 | 6400 | 0.4554        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5270b151b39c586df44055763986b001c438f14893a5a40f6c947ee59b4dc8
+oid sha256:5d95e3d0943240c31da6df746f9f3cca8daffbcbf4c519e4d4baa811b80a13fb
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:427a25cee731ef25ec82aa31f31d5a9a97bf0eeea4714138f8d9bf9fc951230f
+oid sha256:f29fd6ade8a7591354a162ab7d03eaddfcef75d266f53ddc2969b95870d3ff8d
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbae8b7e39c2440f246453cba4933379e4e2419770e59220962ebd5772f6447
+oid sha256:9d3d8144207555c6ec60990d6474d3fd0ec58c08d1eca3fbe5bc862bb1b86096
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aced43cc9ad9f7501c29ad5e5ca57ee953f249e122ae417e48492911cc37f15d
+oid sha256:1838e2ba3161fe9cda5ffbc1228be866f2d720c99e25c4fc0f69015d501e1608
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0476ebd1df369b140089da74c2363c20e1328e3a729f4bbbf994d19625550ab9
+oid sha256:526489e33cb7a870777fedd3daf2b089d8bfd92de79a88cf54c04050587dcfea
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1095580569348483,
+  "epoch": 0.11309218780371437,
   "eval_steps": 500,
-  "global_step": 6200,
+  "global_step": 6400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -876,6 +876,34 @@
       "learning_rate": 4.947085272231058e-05,
       "loss": 0.435,
       "step": 6200
+    },
+    {
+      "epoch": 0.11044158965206481,
+      "grad_norm": 2.447551727294922,
+      "learning_rate": 4.9421766703972046e-05,
+      "loss": 0.3865,
+      "step": 6250
+    },
+    {
+      "epoch": 0.11132512236928134,
+      "grad_norm": 2.126950740814209,
+      "learning_rate": 4.9372680685633504e-05,
+      "loss": 0.4175,
+      "step": 6300
+    },
+    {
+      "epoch": 0.11220865508649785,
+      "grad_norm": 2.22995924949646,
+      "learning_rate": 4.932359466729497e-05,
+      "loss": 0.4387,
+      "step": 6350
+    },
+    {
+      "epoch": 0.11309218780371437,
+      "grad_norm": 1.5801736116409302,
+      "learning_rate": 4.927450864895643e-05,
+      "loss": 0.4554,
+      "step": 6400
     }
   ],
   "logging_steps": 50,