Training in progress, step 3000, 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, 0.6549, 0.0935],
-#         [0.6549, 1.0000, 0.1232],
-#         [0.0935, 0.1232, 1.0000]])
+# tensor([[1.0000, 0.5851, 0.1104],
+#         [0.5851, 1.0000, 0.1499],
+#         [0.1104, 0.1499, 1.0000]])
 ```
 
 <!--
@@ -1280,6 +1280,10 @@ You can finetune this model on your own dataset.
 | 0.0477 | 2700 | 0.5661        |
 | 0.0486 | 2750 | 0.6125        |
 | 0.0495 | 2800 | 0.5105        |
+| 0.0504 | 2850 | 0.5893        |
+| 0.0512 | 2900 | 0.545         |
+| 0.0521 | 2950 | 0.5299        |
+| 0.0530 | 3000 | 0.5186        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e151efa72ee25c48973734218defa123cf60ee46518a0b274dfcbca393fb422
+oid sha256:59bbbce60ef16e762bba9f8a3d9a23a215afa3ee462d98aeaeff69de27f89341
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73660affbc9d00f2fca3a340ebf70404475af29a08ec697b69c11c1edfc06ecd
+oid sha256:6b5d645070344294324c8e72697f2c1b516db72cb3276a26e4ef639ee18da667
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b89b481388e8776a92f8ffb923a2d2f40d85d6a0313cf7ed6f16d7e6a29dcb
+oid sha256:2e56f09343792c3d21faf51137b042a641d6fa07972ad9c4af87d2751a155e0e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091185d50211af5c59ac65d06f51cb55a1ff4a1312de54456a306e4731eb1fa7
+oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4232c28bf6d44f06b5f73efd0dc91c5ec7abf414fa6e4b4449aae1bd59d8543
+oid sha256:301ffba56ec75fdb730415687e7a885bf8c0dc112cbdcb4314fb3614afb6e000
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04947783216412504,
+  "epoch": 0.05301196303299111,
   "eval_steps": 500,
-  "global_step": 2800,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -400,6 +400,34 @@
       "learning_rate": 2.4726148409893997e-05,
       "loss": 0.5105,
       "step": 2800
+    },
+    {
+      "epoch": 0.050361364881341554,
+      "grad_norm": 3.1281192302703857,
+      "learning_rate": 2.5167844522968198e-05,
+      "loss": 0.5893,
+      "step": 2850
+    },
+    {
+      "epoch": 0.051244897598558076,
+      "grad_norm": 2.345649242401123,
+      "learning_rate": 2.5609540636042406e-05,
+      "loss": 0.545,
+      "step": 2900
+    },
+    {
+      "epoch": 0.05212843031577459,
+      "grad_norm": 2.9023561477661133,
+      "learning_rate": 2.605123674911661e-05,
+      "loss": 0.5299,
+      "step": 2950
+    },
+    {
+      "epoch": 0.05301196303299111,
+      "grad_norm": 2.491269588470459,
+      "learning_rate": 2.649293286219081e-05,
+      "loss": 0.5186,
+      "step": 3000
     }
   ],
   "logging_steps": 50,