Training in progress, step 3600, 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, 0.6213, 0.1034],
-#         [0.6213, 1.0000, 0.1548],
-#         [0.1034, 0.1548, 1.0000]])
+# tensor([[1.0000, 0.6194, 0.1435],
+#         [0.6194, 1.0000, 0.1726],
+#         [0.1435, 0.1726, 1.0000]])
 ```
 
 <!--
@@ -1292,6 +1292,10 @@ You can finetune this model on your own dataset.
 | 0.0583 | 3300 | 0.4647        |
 | 0.0592 | 3350 | 0.4652        |
 | 0.0601 | 3400 | 0.4914        |
+| 0.0610 | 3450 | 0.5449        |
+| 0.0618 | 3500 | 0.5072        |
+| 0.0627 | 3550 | 0.5639        |
+| 0.0636 | 3600 | 0.4729        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96302fbbd7e0f6d0492ce6ba1f9f65f0cba90c6cb4cd835da0c1f3411654d653
+oid sha256:8ca20a406e292e76470b215099de7fd529457d8cb2dcb51edb2d8cc0c54a7d84
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e781618525c9855e4f157136a16d3e26d3f42648498f20aa5fe31fe6a0aed0f2
+oid sha256:893256695d57723f84eb532bbc6684a2823d6b7a86ce840bdff5d57803b4ee3d
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0305d5c9d4f21839e046a110958334e61d6cefa97054a71fb45b4a1a270d4081
+oid sha256:338476a870fd77d6e2a600e13b412756ba4bcad01f47d9e17c52ffe1b9d95af9
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f0057f1a0cc52de60522c168cd59fee011d5489cd8505c56661af314a337f0
+oid sha256:7788c7cc60bd991bb584c9a8631c7010707cb818c6f2829b9625a72fb3ec1a89
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1431f76ecd1262a7cee93f19f73849ff3ccfef9b13f029cc43fe09b5880dedb6
+oid sha256:78830fc2cf66f7695494cde0cc4ab780d875d3f710f7c385f24ad0580d00b60e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06008022477072326,
+  "epoch": 0.06361435563958934,
   "eval_steps": 500,
-  "global_step": 3400,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -484,6 +484,34 @@
       "learning_rate": 3.0026501766784454e-05,
       "loss": 0.4914,
       "step": 3400
+    },
+    {
+      "epoch": 0.06096375748793978,
+      "grad_norm": 1.844643235206604,
+      "learning_rate": 3.0468197879858658e-05,
+      "loss": 0.5449,
+      "step": 3450
+    },
+    {
+      "epoch": 0.061847290205156294,
+      "grad_norm": 1.6973118782043457,
+      "learning_rate": 3.090989399293286e-05,
+      "loss": 0.5072,
+      "step": 3500
+    },
+    {
+      "epoch": 0.06273082292237281,
+      "grad_norm": 2.626692295074463,
+      "learning_rate": 3.135159010600707e-05,
+      "loss": 0.5639,
+      "step": 3550
+    },
+    {
+      "epoch": 0.06361435563958934,
+      "grad_norm": 2.971773624420166,
+      "learning_rate": 3.179328621908128e-05,
+      "loss": 0.4729,
+      "step": 3600
     }
   ],
   "logging_steps": 50,