Training in progress, step 4800, 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, 0.6246, 0.1173],
-#         [0.6246, 1.0000, 0.1638],
-#         [0.1173, 0.1638, 1.0000]])
+# tensor([[1.0000, 0.6133, 0.1462],
+#         [0.6133, 1.0000, 0.1725],
+#         [0.1462, 0.1725, 1.0000]])
 ```
 
 <!--
@@ -1316,6 +1316,10 @@ You can finetune this model on your own dataset.
 | 0.0795 | 4500 | 0.4553        |
 | 0.0804 | 4550 | 0.4598        |
 | 0.0813 | 4600 | 0.5445        |
+| 0.0822 | 4650 | 0.4537        |
+| 0.0831 | 4700 | 0.5158        |
+| 0.0839 | 4750 | 0.4598        |
+| 0.0848 | 4800 | 0.4662        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de4e67c75f4b4a7427b2810b985973120199b61a5e131a31184941440675588
+oid sha256:455ab825540498b5f5b373a58b71653674612a70e8ee7fc5be9b1867efa7eac4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2de7647e7106c94dd0498982cecf5e23bcd6cc4a2d106abd4e0a67ed761131
+oid sha256:3bf9c1feb933a833e9a1940398a123539c973a5c3ef49342b6ba0a21987b8a62
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c125bd90db08e6be99cb0172e0d523e9ccee0b8234c431ef93a30e9252f3b6
+oid sha256:eb98f3b30b900a902f900b8100ff06f09878e462230501b172e1989e2314478f
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5f1d0b668240e318afe61a3e255204044d52e6d78b98d08469e3aaa3293711
+oid sha256:b429070a564985551cfca2e541b4c4fca20d998c67cc7cb6e2b59f638df425a3
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c485dc831eee1163015670289f311918797d3da6236e5f584fb1d2dbee1714b9
+oid sha256:b4d7d41c126e55275e34a7a7f11165206f98f8c233f762fcdd72745ff49aac18
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0812850099839197,
+  "epoch": 0.08481914085278577,
   "eval_steps": 500,
-  "global_step": 4600,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -652,6 +652,34 @@
       "learning_rate": 4.0627208480565374e-05,
       "loss": 0.5445,
       "step": 4600
+    },
+    {
+      "epoch": 0.08216854270113623,
+      "grad_norm": 2.4177329540252686,
+      "learning_rate": 4.106890459363958e-05,
+      "loss": 0.4537,
+      "step": 4650
+    },
+    {
+      "epoch": 0.08305207541835274,
+      "grad_norm": 2.6188764572143555,
+      "learning_rate": 4.151060070671378e-05,
+      "loss": 0.5158,
+      "step": 4700
+    },
+    {
+      "epoch": 0.08393560813556926,
+      "grad_norm": 3.5044455528259277,
+      "learning_rate": 4.195229681978799e-05,
+      "loss": 0.4598,
+      "step": 4750
+    },
+    {
+      "epoch": 0.08481914085278577,
+      "grad_norm": 2.2751505374908447,
+      "learning_rate": 4.239399293286219e-05,
+      "loss": 0.4662,
+      "step": 4800
     }
   ],
   "logging_steps": 50,