Training in progress, step 2800, 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, 0.6640, 0.1013],
-#         [0.6640, 1.0000, 0.1387],
-#         [0.1013, 0.1387, 1.0000]])
+# tensor([[1.0000, 0.6549, 0.0935],
+#         [0.6549, 1.0000, 0.1232],
+#         [0.0935, 0.1232, 1.0000]])
 ```
 
 <!--
@@ -1276,6 +1276,10 @@ You can finetune this model on your own dataset.
 | 0.0442 | 2500 | 0.5418        |
 | 0.0451 | 2550 | 0.5944        |
 | 0.0459 | 2600 | 0.4945        |
+| 0.0468 | 2650 | 0.5225        |
+| 0.0477 | 2700 | 0.5661        |
+| 0.0486 | 2750 | 0.6125        |
+| 0.0495 | 2800 | 0.5105        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae5685c6a0c1fe0ed28db5c9949645da1874fee361ce188af171f0dc464b051
+oid sha256:3e151efa72ee25c48973734218defa123cf60ee46518a0b274dfcbca393fb422
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582e7af731a5a8f6fce6c6c33c280e4b6a1edc557f2edfd6c016d9eab1c38ec7
+oid sha256:73660affbc9d00f2fca3a340ebf70404475af29a08ec697b69c11c1edfc06ecd
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4c0352f6445f2b7c6c3c51f895d528e2207f898cdc30fd189336a0b7b111fb
+oid sha256:64b89b481388e8776a92f8ffb923a2d2f40d85d6a0313cf7ed6f16d7e6a29dcb
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea2b6a5675bb9dc7d6d847844f168cbc539a3493d586a8e2634d29c173b0f88
+oid sha256:091185d50211af5c59ac65d06f51cb55a1ff4a1312de54456a306e4731eb1fa7
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed639e61f6a926a63462947428e7442536feff636cd037001a4560c56e961f18
+oid sha256:d4232c28bf6d44f06b5f73efd0dc91c5ec7abf414fa6e4b4449aae1bd59d8543
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04594370129525897,
+  "epoch": 0.04947783216412504,
   "eval_steps": 500,
-  "global_step": 2600,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -372,6 +372,34 @@
       "learning_rate": 2.2959363957597176e-05,
       "loss": 0.4945,
       "step": 2600
+    },
+    {
+      "epoch": 0.04682723401247548,
+      "grad_norm": 2.389902114868164,
+      "learning_rate": 2.340106007067138e-05,
+      "loss": 0.5225,
+      "step": 2650
+    },
+    {
+      "epoch": 0.047710766729692,
+      "grad_norm": 2.2676665782928467,
+      "learning_rate": 2.3842756183745584e-05,
+      "loss": 0.5661,
+      "step": 2700
+    },
+    {
+      "epoch": 0.04859429944690852,
+      "grad_norm": 2.340926170349121,
+      "learning_rate": 2.428445229681979e-05,
+      "loss": 0.6125,
+      "step": 2750
+    },
+    {
+      "epoch": 0.04947783216412504,
+      "grad_norm": 1.925943374633789,
+      "learning_rate": 2.4726148409893997e-05,
+      "loss": 0.5105,
+      "step": 2800
     }
   ],
   "logging_steps": 50,