Training in progress, step 6000, 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, 0.6669, 0.1451],
-#         [0.6669, 1.0000, 0.1936],
-#         [0.1451, 0.1936, 1.0000]])
+# tensor([[1.0000, 0.6825, 0.0849],
+#         [0.6825, 1.0000, 0.1574],
+#         [0.0849, 0.1574, 1.0000]])
 ```
 
 <!--
@@ -1232,6 +1232,10 @@ You can finetune this model on your own dataset.
 | 0.1007 | 5700 | 0.4184        |
 | 0.1016 | 5750 | 0.4071        |
 | 0.1025 | 5800 | 0.4712        |
+| 0.1034 | 5850 | 0.4912        |
+| 0.1043 | 5900 | 0.5589        |
+| 0.1051 | 5950 | 0.4507        |
+| 0.1060 | 6000 | 0.5429        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1fc49cbbc6de240aabdb3e829a6fb3a584632f32e0ea34f9bb45772c0982c3
+oid sha256:7789fd8be583c6cd52a2b3c49d3926b4c97ae306770f1629fc1b7121d168f986
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0b3ed8d536c4513e2829f064dedb563ad605e8571308e2634efeb29d7ca8e1
+oid sha256:d02388678163538169399bda8fffa8df551692b3bfa9b7ca53bde07a66c2a6e0
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fe30117f944b13ee1472ebd35dfced5e5d0513a4a73eff292237f1226a5bd67
+oid sha256:f72d2db1e1a80b4db59e84d70863f853ea4793c1b3630fdd9ffed5098f03c668
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7593f1811ddf23427f9722ba36181188ba02d4c1acd9e1296ff517e858104491
+oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a1656fa44372deb310837f6e5c3a0395ee0a01d6c02b0b4d93ed8ab693ca68
+oid sha256:df255e26e463b4fc70f27b3a2f6c9b68f20dc79363ed0890520e03d68a77d6b1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10248979519711615,
+  "epoch": 0.10602392606598222,
   "eval_steps": 500,
-  "global_step": 5800,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -820,6 +820,34 @@
       "learning_rate": 4.986354086901887e-05,
       "loss": 0.4712,
       "step": 5800
+    },
+    {
+      "epoch": 0.10337332791433267,
+      "grad_norm": 4.2943434715271,
+      "learning_rate": 4.9814454850680335e-05,
+      "loss": 0.4912,
+      "step": 5850
+    },
+    {
+      "epoch": 0.10425686063154918,
+      "grad_norm": 2.398043632507324,
+      "learning_rate": 4.97653688323418e-05,
+      "loss": 0.5589,
+      "step": 5900
+    },
+    {
+      "epoch": 0.10514039334876571,
+      "grad_norm": 1.9587973356246948,
+      "learning_rate": 4.9716282814003265e-05,
+      "loss": 0.4507,
+      "step": 5950
+    },
+    {
+      "epoch": 0.10602392606598222,
+      "grad_norm": 2.0629475116729736,
+      "learning_rate": 4.966719679566473e-05,
+      "loss": 0.5429,
+      "step": 6000
     }
   ],
   "logging_steps": 50,