Training in progress, step 2600, 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, 0.5939, 0.0989],
-#         [0.5939, 1.0000, 0.1429],
-#         [0.0989, 0.1429, 1.0000]])
+# tensor([[1.0000, 0.6640, 0.1013],
+#         [0.6640, 1.0000, 0.1387],
+#         [0.1013, 0.1387, 1.0000]])
 ```
 
 <!--
@@ -1272,6 +1272,10 @@ You can finetune this model on your own dataset.
 | 0.0406 | 2300 | 0.5354        |
 | 0.0415 | 2350 | 0.5236        |
 | 0.0424 | 2400 | 0.5057        |
+| 0.0433 | 2450 | 0.5448        |
+| 0.0442 | 2500 | 0.5418        |
+| 0.0451 | 2550 | 0.5944        |
+| 0.0459 | 2600 | 0.4945        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c241b1c1e2bc79f90ea3e691425a4d078b73a1355962e0a546f6d5b25945da0
+oid sha256:3ae5685c6a0c1fe0ed28db5c9949645da1874fee361ce188af171f0dc464b051
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ba4f5c69a3d02a5a6823d34b8da6ff44cacb16550bdd25ab1d7402501d6357
+oid sha256:582e7af731a5a8f6fce6c6c33c280e4b6a1edc557f2edfd6c016d9eab1c38ec7
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d318191f63943626d0af0c2a2dffd47f5f97e52b9ffb5b4186681760d24fbc1
+oid sha256:7a4c0352f6445f2b7c6c3c51f895d528e2207f898cdc30fd189336a0b7b111fb
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da7c5085795b13d2bf0030671cbddb9f62ae43221bf1424a3830d4cf8c19012
+oid sha256:aea2b6a5675bb9dc7d6d847844f168cbc539a3493d586a8e2634d29c173b0f88
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f85f103e0fd23f9c136b70ea64be4bf637404426959df56180c10126efe39d0a
+oid sha256:ed639e61f6a926a63462947428e7442536feff636cd037001a4560c56e961f18
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04240957042639289,
+  "epoch": 0.04594370129525897,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -344,6 +344,34 @@
       "learning_rate": 2.1192579505300354e-05,
       "loss": 0.5057,
       "step": 2400
+    },
+    {
+      "epoch": 0.04329310314360941,
+      "grad_norm": 2.2634503841400146,
+      "learning_rate": 2.163427561837456e-05,
+      "loss": 0.5448,
+      "step": 2450
+    },
+    {
+      "epoch": 0.04417663586082592,
+      "grad_norm": 1.6744658946990967,
+      "learning_rate": 2.2075971731448763e-05,
+      "loss": 0.5418,
+      "step": 2500
+    },
+    {
+      "epoch": 0.045060168578042445,
+      "grad_norm": 2.9320178031921387,
+      "learning_rate": 2.2517667844522968e-05,
+      "loss": 0.5944,
+      "step": 2550
+    },
+    {
+      "epoch": 0.04594370129525897,
+      "grad_norm": 2.2643797397613525,
+      "learning_rate": 2.2959363957597176e-05,
+      "loss": 0.4945,
+      "step": 2600
     }
   ],
   "logging_steps": 50,