Training in progress, step 8000, 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, 0.6731, 0.0859],
-#         [0.6731, 1.0000, 0.1039],
-#         [0.0859, 0.1039, 1.0000]])
+# tensor([[1.0000, 0.7084, 0.1070],
+#         [0.7084, 1.0000, 0.1535],
+#         [0.1070, 0.1535, 1.0000]])
 ```
 
 <!--
@@ -1272,6 +1272,10 @@ You can finetune this model on your own dataset.
 | 0.1361 | 7700 | 0.3508        |
 | 0.1369 | 7750 | 0.5145        |
 | 0.1378 | 7800 | 0.3505        |
+| 0.1387 | 7850 | 0.3354        |
+| 0.1396 | 7900 | 0.4474        |
+| 0.1405 | 7950 | 0.3524        |
+| 0.1414 | 8000 | 0.4957        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30363d096c58d92d4b21124e0d20899b83f2936057d84481288b276849800da
+oid sha256:c2da1461ee3c2c456dcf6f8e527f2db46ecd02b950cb9f11180de998e104b262
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b40de5614fe99b525d99f7ae3d9359f7a6761883a046bcd2268fc4693168a255
+oid sha256:9bb3ac284c860eb3e450dfee8fb9c59f3e73309b53d4441e8ab3eca7e6fd0c1f
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1edc586d66d6370fa77d636b436ae7dbcdf36bd23372d9a0cfe0aacbfb7c097
+oid sha256:924de27a7d312b976334871f5500b60f3ac826256585b053482668db5a3e0fd8
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dcd40ad341a8a975b38dbdcfaddae63cf7d7e04b0cc6cd6eae6ee6f1a79543
+oid sha256:74ef2fcd6c891b91eb5bdb472a78ed689674800853972656dbbbd1178ed4b062
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f33b2ef6b57ca3fea92dbaf20099472c840d5302f57356bd6135bfd1110e82
+oid sha256:0d965eb3daad0b2a439e895ad852db3800ac9a1641cf69b4958e035a573e3539
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13783110388577688,
+  "epoch": 0.14136523475464297,
   "eval_steps": 500,
-  "global_step": 7800,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1100,6 +1100,34 @@
       "learning_rate": 4.790010013547741e-05,
       "loss": 0.3505,
       "step": 7800
+    },
+    {
+      "epoch": 0.1387146366029934,
+      "grad_norm": 1.761982798576355,
+      "learning_rate": 4.7851014117138874e-05,
+      "loss": 0.3354,
+      "step": 7850
+    },
+    {
+      "epoch": 0.13959816932020994,
+      "grad_norm": 3.417602777481079,
+      "learning_rate": 4.780192809880034e-05,
+      "loss": 0.4474,
+      "step": 7900
+    },
+    {
+      "epoch": 0.14048170203742644,
+      "grad_norm": 1.7687017917633057,
+      "learning_rate": 4.7752842080461804e-05,
+      "loss": 0.3524,
+      "step": 7950
+    },
+    {
+      "epoch": 0.14136523475464297,
+      "grad_norm": 3.2442593574523926,
+      "learning_rate": 4.770375606212327e-05,
+      "loss": 0.4957,
+      "step": 8000
     }
   ],
   "logging_steps": 50,