Training in progress, step 2200, 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, 0.5880, 0.1308],
-#         [0.5880, 1.0000, 0.1611],
-#         [0.1308, 0.1611, 1.0000]])
+# tensor([[1.0000, 0.6084, 0.1042],
+#         [0.6084, 1.0000, 0.1457],
+#         [0.1042, 0.1457, 1.0000]])
 ```
 
 <!--
@@ -1264,6 +1264,10 @@ You can finetune this model on your own dataset.
 | 0.0336 | 1900 | 0.5298        |
 | 0.0345 | 1950 | 0.5759        |
 | 0.0353 | 2000 | 0.5782        |
+| 0.0362 | 2050 | 0.5221        |
+| 0.0371 | 2100 | 0.5966        |
+| 0.0380 | 2150 | 0.5989        |
+| 0.0389 | 2200 | 0.5097        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814104de2dc74a0f467b27e454f11429bcabde4ec4e6cb0bee382acda4bd2af8
+oid sha256:43e276da028dbf8b1ad5144673c6ce3925a2b3aabd87a44547c55a6459e20d87
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00eef042f462bb454219ea2918cf958fd5615f13c9bb9103c136a3d4d342d822
+oid sha256:93cc133162fde43973a8ccb2ec2dfc87437cbd187213b067665594adaa028144
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639c58a7c0af444791cd5711ba19270a82e589f2ee67d587a74f8240b2f70eec
+oid sha256:e3c956e4b6b1160a43d807052e2f2f064099f54437c58331d632ad556682176f
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+oid sha256:1f6829e47549862e022b4eedf087cf81394f448150e958ad6663988076bf8691
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3bd0299fa211f42a5bbf3d13d4c1b67f9745816753ebca5d122c47f94c26a70
+oid sha256:fdfc272a547d5b2f74b766d251fe9186a84058fe1c0528c0560d11ed37d05aa5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03534130868866074,
+  "epoch": 0.038875439557526814,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,34 @@
       "learning_rate": 1.7659010600706715e-05,
       "loss": 0.5782,
       "step": 2000
+    },
+    {
+      "epoch": 0.03622484140587726,
+      "grad_norm": 2.3239428997039795,
+      "learning_rate": 1.810070671378092e-05,
+      "loss": 0.5221,
+      "step": 2050
+    },
+    {
+      "epoch": 0.03710837412309378,
+      "grad_norm": 4.565939426422119,
+      "learning_rate": 1.8542402826855124e-05,
+      "loss": 0.5966,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0379919068403103,
+      "grad_norm": 2.6089091300964355,
+      "learning_rate": 1.898409893992933e-05,
+      "loss": 0.5989,
+      "step": 2150
+    },
+    {
+      "epoch": 0.038875439557526814,
+      "grad_norm": 2.4395945072174072,
+      "learning_rate": 1.9425795053003533e-05,
+      "loss": 0.5097,
+      "step": 2200
     }
   ],
   "logging_steps": 50,