Training in progress, step 5800, 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, 0.6467, 0.1007],
-#         [0.6467, 1.0000, 0.1513],
-#         [0.1007, 0.1513, 1.0000]])
+# tensor([[1.0000, 0.6669, 0.1451],
+#         [0.6669, 1.0000, 0.1936],
+#         [0.1451, 0.1936, 1.0000]])
 ```
 
 <!--
@@ -1228,6 +1228,10 @@ You can finetune this model on your own dataset.
 | 0.0972 | 5500 | 0.5258        |
 | 0.0981 | 5550 | 0.4851        |
 | 0.0990 | 5600 | 0.5311        |
+| 0.0998 | 5650 | 0.411         |
+| 0.1007 | 5700 | 0.4184        |
+| 0.1016 | 5750 | 0.4071        |
+| 0.1025 | 5800 | 0.4712        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea0a03b98d68b9630385779c8a8c7e0b7214aab3d11108ff4a7dee8e11165e6
+oid sha256:6b1fc49cbbc6de240aabdb3e829a6fb3a584632f32e0ea34f9bb45772c0982c3
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5970c5e57ca0ba681567ef6a04ad48dff25e78f70e37dc99bc3e34cce512849
+oid sha256:0f0b3ed8d536c4513e2829f064dedb563ad605e8571308e2634efeb29d7ca8e1
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd91aca617b42354ae34eacd85892c172326b446d2385efb45fce4e2caab955
+oid sha256:0fe30117f944b13ee1472ebd35dfced5e5d0513a4a73eff292237f1226a5bd67
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63ba06faceabc247ab7f188765454cd84997a1b39e86a5bcd485fb8077cf90a
+oid sha256:7593f1811ddf23427f9722ba36181188ba02d4c1acd9e1296ff517e858104491
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28df4acdedad4efa6e4629443faf92ab7af434a0b458c6b8097068d89b1dbe79
+oid sha256:b0a1656fa44372deb310837f6e5c3a0395ee0a01d6c02b0b4d93ed8ab693ca68
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09895566432825008,
+  "epoch": 0.10248979519711615,
   "eval_steps": 500,
-  "global_step": 5600,
+  "global_step": 5800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -792,6 +792,34 @@
       "learning_rate": 4.946113074204947e-05,
       "loss": 0.5311,
       "step": 5600
+    },
+    {
+      "epoch": 0.0998391970454666,
+      "grad_norm": 1.7307246923446655,
+      "learning_rate": 4.990282685512368e-05,
+      "loss": 0.411,
+      "step": 5650
+    },
+    {
+      "epoch": 0.10072272976268311,
+      "grad_norm": 1.9073278903961182,
+      "learning_rate": 4.996171290569595e-05,
+      "loss": 0.4184,
+      "step": 5700
+    },
+    {
+      "epoch": 0.10160626247989964,
+      "grad_norm": 1.8571208715438843,
+      "learning_rate": 4.9912626887357406e-05,
+      "loss": 0.4071,
+      "step": 5750
+    },
+    {
+      "epoch": 0.10248979519711615,
+      "grad_norm": 1.7524621486663818,
+      "learning_rate": 4.986354086901887e-05,
+      "loss": 0.4712,
+      "step": 5800
     }
   ],
   "logging_steps": 50,