Training in progress, step 1000, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b28b74545c8174d80d1900fffbe59b2a7435a9e928a3f943266d2d96667067
+oid sha256:7f743aade071c11f48b4b07a7ad3824fde728b2d1fb7633bcdd23f3f3a237ba9
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f17852afeb04a7d81bc4e27fdae244ba00112c63322abe9f6c299a666b57b5
+oid sha256:9e474728fa84de1f91316ae156c4886c0bc7ad35e8900e551687a57dc8c9b59a
 size 4718680

last-checkpoint/README.md

@@ -511,7 +511,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.7210, -0.0779, -0.0314]])
+# tensor([[ 0.6962, -0.0789, -0.0304]])
 ```
 
 <!--
@@ -736,6 +736,10 @@ You can finetune this model on your own dataset.
 | 0.6718 | 700  | 0.1586        |
 | 0.7198 | 750  | 0.1473        |
 | 0.7678 | 800  | 0.1547        |
+| 0.8157 | 850  | 0.146         |
+| 0.8637 | 900  | 0.1453        |
+| 0.9117 | 950  | 0.1349        |
+| 0.9597 | 1000 | 0.1433        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe81efee97c0f5f6e85eab9e97762a9d281501c3388cc280a9df8ee7217683d3
+oid sha256:8c84e8a0a3139ed2ddf3b09b17276e96fdf62d3afa0272819b739fa886c04d8f
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbba28742d6013f6fc692c0d332059d2e00fb3286712afea40fb65838ac9adc
+oid sha256:beb16bd8e4d9e05b451247f0f0fcbaac68f510f27654bf3865401256d54bcec3
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57a1899b276deaf9bc6c347b576a36bf470824199b1d1731a5698c732cc5649
+oid sha256:8f05941cd5d89b2195b06001cebc4cb31c0ae73bf191526abcbbf01177ebf8dc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7677543186180422,
+  "epoch": 0.9596928982725528,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,34 @@
       "learning_rate": 1.2966915688367129e-05,
       "loss": 0.1547,
       "step": 800
+    },
+    {
+      "epoch": 0.8157389635316699,
+      "grad_norm": 3.75,
+      "learning_rate": 1.0298826040554963e-05,
+      "loss": 0.146,
+      "step": 850
+    },
+    {
+      "epoch": 0.8637236084452975,
+      "grad_norm": 4.09375,
+      "learning_rate": 7.630736392742796e-06,
+      "loss": 0.1453,
+      "step": 900
+    },
+    {
+      "epoch": 0.9117082533589251,
+      "grad_norm": 3.765625,
+      "learning_rate": 4.96264674493063e-06,
+      "loss": 0.1349,
+      "step": 950
+    },
+    {
+      "epoch": 0.9596928982725528,
+      "grad_norm": 3.96875,
+      "learning_rate": 2.294557097118463e-06,
+      "loss": 0.1433,
+      "step": 1000
     }
   ],
   "logging_steps": 50,