Training in progress, step 1800, checkpoint

last-checkpoint/README.md

@@ -466,9 +466,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.5466, -0.0451],
-#         [ 0.5466,  1.0000, -0.0569],
-#         [-0.0451, -0.0569,  1.0000]])
+# tensor([[ 1.0000,  0.5466, -0.0454],
+#         [ 0.5466,  1.0000, -0.0568],
+#         [-0.0454, -0.0568,  1.0000]])
 ```
 
 <!--
@@ -708,6 +708,10 @@ You can finetune this model on your own dataset.
 | 0.7622 | 1500 | 0.4874        |
 | 0.7876 | 1550 | 0.4725        |
 | 0.8130 | 1600 | 0.4819        |
+| 0.8384 | 1650 | 0.4808        |
+| 0.8638 | 1700 | 0.4797        |
+| 0.8892 | 1750 | 0.4836        |
+| 0.9146 | 1800 | 0.4832        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854754df8ec84609cad82f36d53d753aec51ba9c534b5f7b71a1982a04c1c64d
+oid sha256:17554aba416dac32662ee4493f2bcaa68570b7683a6b8940eb5d0031827f3358
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bcd768d6c419625a038d8e3c0adb38c0af2ee7c4104d330447beecd4087778b
+oid sha256:0c7df775c39fa3b71bbba8fbfd34191533c8b284b769351bdb0714a10d07e26c
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f849d8544efef0e1ff23cfbc0ca401c847e9bbacee1179c6d68fa07318aa06b4
+oid sha256:4383e099fde8143073bc583376ee59e15bec296ef152a2f16e0f5296290e06e4
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac15faca44126ea757af3cc9233a4970a99a30bf6b2f36cfb0d4ae9816273ed
+oid sha256:ec29327b2c793ef05a01c6bae10cd1cf49d3fd34bb421765aad2d8f09bc372c0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8130081300813008,
+  "epoch": 0.9146341463414634,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,34 @@
       "learning_rate": 1.0417843026538679e-05,
       "loss": 0.4819,
       "step": 1600
+    },
+    {
+      "epoch": 0.8384146341463414,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.006211180124225e-06,
+      "loss": 0.4808,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8638211382113821,
+      "grad_norm": 1.8125,
+      "learning_rate": 7.594579333709768e-06,
+      "loss": 0.4797,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8892276422764228,
+      "grad_norm": 1.71875,
+      "learning_rate": 6.1829474872953135e-06,
+      "loss": 0.4836,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9146341463414634,
+      "grad_norm": 1.8359375,
+      "learning_rate": 4.771315640880859e-06,
+      "loss": 0.4832,
+      "step": 1800
     }
   ],
   "logging_steps": 50,