Training in progress, step 8200, 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, 0.7084, 0.1070],
-#         [0.7084, 1.0000, 0.1535],
-#         [0.1070, 0.1535, 1.0000]])
+# tensor([[1.0000, 0.7055, 0.1480],
+#         [0.7055, 1.0000, 0.1624],
+#         [0.1480, 0.1624, 1.0000]])
 ```
 
 <!--
@@ -1276,6 +1276,10 @@ You can finetune this model on your own dataset.
 | 0.1396 | 7900 | 0.4474        |
 | 0.1405 | 7950 | 0.3524        |
 | 0.1414 | 8000 | 0.4957        |
+| 0.1422 | 8050 | 0.4461        |
+| 0.1431 | 8100 | 0.4983        |
+| 0.1440 | 8150 | 0.4535        |
+| 0.1449 | 8200 | 0.3668        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2da1461ee3c2c456dcf6f8e527f2db46ecd02b950cb9f11180de998e104b262
+oid sha256:4640bbfebbb11ecea082ff1af6d855d052c0c8e1bdf9168d4f7359599f62aabd
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb3ac284c860eb3e450dfee8fb9c59f3e73309b53d4441e8ab3eca7e6fd0c1f
+oid sha256:ccd29683807f5e0218e2f5d58ca633b3fdf6424d5b06a7fd7dd1632307029b7e
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924de27a7d312b976334871f5500b60f3ac826256585b053482668db5a3e0fd8
+oid sha256:eae3e1579fe71c3a791c337c98621066f7781ea53baa1bbd326d61e1273a7011
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ef2fcd6c891b91eb5bdb472a78ed689674800853972656dbbbd1178ed4b062
+oid sha256:e1b7589e0e51e5ea2c39973809a8f993519f86ffc0bc8e5dc5baeb72e06aa3bb
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d965eb3daad0b2a439e895ad852db3800ac9a1641cf69b4958e035a573e3539
+oid sha256:71575ac6af3608ee2ab21516b68821ed7b385bc77900a19bfec38f30c0387852
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14136523475464297,
+  "epoch": 0.14489936562350905,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1128,6 +1128,34 @@
       "learning_rate": 4.770375606212327e-05,
       "loss": 0.4957,
       "step": 8000
+    },
+    {
+      "epoch": 0.1422487674718595,
+      "grad_norm": 1.813818335533142,
+      "learning_rate": 4.765467004378473e-05,
+      "loss": 0.4461,
+      "step": 8050
+    },
+    {
+      "epoch": 0.143132300189076,
+      "grad_norm": 1.936123013496399,
+      "learning_rate": 4.760558402544619e-05,
+      "loss": 0.4983,
+      "step": 8100
+    },
+    {
+      "epoch": 0.14401583290629252,
+      "grad_norm": 2.0068929195404053,
+      "learning_rate": 4.7556498007107656e-05,
+      "loss": 0.4535,
+      "step": 8150
+    },
+    {
+      "epoch": 0.14489936562350905,
+      "grad_norm": 1.6743545532226562,
+      "learning_rate": 4.750741198876913e-05,
+      "loss": 0.3668,
+      "step": 8200
     }
   ],
   "logging_steps": 50,