Training in progress, step 1600, 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,  0.5480, -0.0458],
-#         [ 0.5480,  1.0000, -0.0586],
-#         [-0.0458, -0.0586,  1.0000]])
+# tensor([[ 1.0000,  0.5466, -0.0451],
+#         [ 0.5466,  1.0000, -0.0569],
+#         [-0.0451, -0.0569,  1.0000]])
 ```
 
 <!--
@@ -704,6 +704,10 @@ You can finetune this model on your own dataset.
 | 0.6606 | 1300 | 0.4868        |
 | 0.6860 | 1350 | 0.4819        |
 | 0.7114 | 1400 | 0.486         |
+| 0.7368 | 1450 | 0.4875        |
+| 0.7622 | 1500 | 0.4874        |
+| 0.7876 | 1550 | 0.4725        |
+| 0.8130 | 1600 | 0.4819        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75920a4e97e5b78b8f2aef96fae35a0db4f205a5343091523547609bce4b1d9f
+oid sha256:854754df8ec84609cad82f36d53d753aec51ba9c534b5f7b71a1982a04c1c64d
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e095a8f770b2b09aeb0a9f8fb5ddd7dac988fa28d75f73b4e4ef2b0581b1b05
+oid sha256:8bcd768d6c419625a038d8e3c0adb38c0af2ee7c4104d330447beecd4087778b
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e4625f78173d74ff3d9f6deda2944ea87976ad1f424f0e59922e3adcae27fc
+oid sha256:f849d8544efef0e1ff23cfbc0ca401c847e9bbacee1179c6d68fa07318aa06b4
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0299032156c99cc748a49daedbaed704010a8fef256e5ec9b90ef95f2e77d9cd
+oid sha256:7ac15faca44126ea757af3cc9233a4970a99a30bf6b2f36cfb0d4ae9816273ed
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7113821138211383,
+  "epoch": 0.8130081300813008,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,6 +204,34 @@
       "learning_rate": 1.60643704121965e-05,
       "loss": 0.486,
       "step": 1400
+    },
+    {
+      "epoch": 0.7367886178861789,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.4652738565782046e-05,
+      "loss": 0.4875,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7621951219512195,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.3241106719367592e-05,
+      "loss": 0.4874,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7876016260162602,
+      "grad_norm": 1.796875,
+      "learning_rate": 1.1829474872953134e-05,
+      "loss": 0.4725,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.0417843026538679e-05,
+      "loss": 0.4819,
+      "step": 1600
     }
   ],
   "logging_steps": 50,