Training in progress, step 7400, 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, 0.6879, 0.1286],
-#         [0.6879, 1.0000, 0.1688],
-#         [0.1286, 0.1688, 1.0000]])
+# tensor([[1.0000, 0.6815, 0.1033],
+#         [0.6815, 1.0000, 0.1434],
+#         [0.1033, 0.1434, 1.0000]])
 ```
 
 <!--
@@ -1260,6 +1260,10 @@ You can finetune this model on your own dataset.
 | 0.1255 | 7100 | 0.5155        |
 | 0.1263 | 7150 | 0.4282        |
 | 0.1272 | 7200 | 0.4639        |
+| 0.1281 | 7250 | 0.5294        |
+| 0.1290 | 7300 | 0.4121        |
+| 0.1299 | 7350 | 0.4139        |
+| 0.1308 | 7400 | 0.4311        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e0640c0093f6938269cf5b0ca154261896c0baa13615b9ac24acbc00815c24
+oid sha256:7640a8c5c08cd84ea9d34e9a392788849c161e51fab1fb1e24cf029e4bd1e02b
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fca48ccb7c4a584f7af19fddac5f49e519b33cedea2b5a68a882138149c59ef
+oid sha256:d8bba72a7f616d924ad3ea248b2f6cbefe36b03a9a05b0265d1aae461c6b1d0f
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309540c657541ac81d087cbb68ec4167d38f8c9f78a01a5baabdd0e371dee4d2
+oid sha256:234f75280c102551c5f624e1ddf7b22e58abe72b0541e05f85525df9445290c6
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1789ba0d507fa201879591abbc90e77d1dba00075efb5f28f2624ffc56affbc2
+oid sha256:d4c7f383c5c3caed78012349896a057bf1feaccde880a982830ace58530daa75
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2d3fce775411949a9aaee54964b6ea09aaa40534b915c7642ea1c1b586b54a
+oid sha256:86c610364818334e39ecc9c71264546e8b8d4a41c51d290cd21e1ca096739e20
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12722871127917867,
+  "epoch": 0.13076284214804473,
   "eval_steps": 500,
-  "global_step": 7200,
+  "global_step": 7400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1016,6 +1016,34 @@
       "learning_rate": 4.8489132355539854e-05,
       "loss": 0.4639,
       "step": 7200
+    },
+    {
+      "epoch": 0.12811224399639518,
+      "grad_norm": 1.7154817581176758,
+      "learning_rate": 4.844004633720131e-05,
+      "loss": 0.5294,
+      "step": 7250
+    },
+    {
+      "epoch": 0.1289957767136117,
+      "grad_norm": 2.130659580230713,
+      "learning_rate": 4.839096031886278e-05,
+      "loss": 0.4121,
+      "step": 7300
+    },
+    {
+      "epoch": 0.12987930943082823,
+      "grad_norm": 1.8878060579299927,
+      "learning_rate": 4.834187430052424e-05,
+      "loss": 0.4139,
+      "step": 7350
+    },
+    {
+      "epoch": 0.13076284214804473,
+      "grad_norm": 1.9885565042495728,
+      "learning_rate": 4.82927882821857e-05,
+      "loss": 0.4311,
+      "step": 7400
     }
   ],
   "logging_steps": 50,