Training in progress, step 800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063df22142057d2c8696e2ae017f3c74712479c71f4d55eef0fb2e5056c3acd9
+oid sha256:b1a852d6fcae1f2179d5763df7a46fddad1877e145fff513af3347be674ce52b
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d5acf9f98788d6a2922cef011bd936df1b9e1686c779971fca5c10bcefa77a
+oid sha256:3394c00a0b8299e323b6e83e64ef00be5d726f3c420aa6b111200a304b59f62c
 size 9437272

last-checkpoint/README.md

@@ -450,7 +450,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6287, -0.0852,  0.2024]])
+# tensor([[ 0.5962, -0.0191,  0.2550]])
 ```
 
 <!--
@@ -699,6 +699,10 @@ You can finetune this model on your own dataset.
 | 0.1655 | 500  | 0.1147        |
 | 0.1820 | 550  | 0.1224        |
 | 0.1985 | 600  | 0.1113        |
+| 0.2151 | 650  | 0.1054        |
+| 0.2316 | 700  | 0.1013        |
+| 0.2482 | 750  | 0.1019        |
+| 0.2647 | 800  | 0.0964        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033d8f3dceb818090abe62e25c4150d763b8734695c086defcaf1d40dd639814
+oid sha256:a6ff1bb561b9706f1f8512c3b49593b3ccfe975a3a766ab30ffe85567e0af9d8
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8dd546a621af0d9b4e61bb98d55921f58d185839602e1199e76267595fae5f
+oid sha256:308069358a54642120bbc71415a487f71aebf1cfafc7c73bebd447e79b921486
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a7e95a048d31e7d9e5712bbf85fc8632444e30166b0ed25502f6a768b9211d
+oid sha256:39a64593b8ffcc45b5d5cd6de2eb5cadb176a065ce63970660c524f174fa6360
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6deff325eec0670b4e2cbe8cfbf49072d5c3640acac1966fd95e1d68c238f471
+oid sha256:7baf2879871f108cbdcd4157b9794e8d6049aec3cf60c7a2c1c3c5259ba4fe4d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1985440105890139,
+  "epoch": 0.26472534745201853,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 1.782272894446488e-05,
       "loss": 0.1113,
       "step": 600
+    },
+    {
+      "epoch": 0.21508934480476505,
+      "grad_norm": 6.012777328491211,
+      "learning_rate": 1.7454946671570432e-05,
+      "loss": 0.1054,
+      "step": 650
+    },
+    {
+      "epoch": 0.2316346790205162,
+      "grad_norm": 7.861270904541016,
+      "learning_rate": 1.7087164398675985e-05,
+      "loss": 0.1013,
+      "step": 700
+    },
+    {
+      "epoch": 0.24818001323626737,
+      "grad_norm": 6.786500930786133,
+      "learning_rate": 1.671938212578154e-05,
+      "loss": 0.1019,
+      "step": 750
+    },
+    {
+      "epoch": 0.26472534745201853,
+      "grad_norm": 12.52272891998291,
+      "learning_rate": 1.6351599852887092e-05,
+      "loss": 0.0964,
+      "step": 800
     }
   ],
   "logging_steps": 50,