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 sha256:27c35bbbe0b3b4648d206a86b9a22ed14cdd5ba12f681b9329d51cc3594ed874
+oid sha256:72b9c82bfed0ef2030970c9f30b4352b5627c1df06426da4a77edb7810418944
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4cec3b48c616eb4b62540bb0ef79466b8968a49111b3b79390a007de3e0f383
+oid sha256:3a88ee4f6617fb4562e1446b4a7b0c1d2bbcb3e599145beb6f78a94915b5670e
 size 4718680

last-checkpoint/README.md

@@ -472,7 +472,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6778, -0.0608, -0.0575]])
+# tensor([[ 0.6605, -0.0307, -0.0678]])
 ```
 
 <!--
@@ -693,6 +693,10 @@ You can finetune this model on your own dataset.
 | 0.2541 | 500  | 0.1625        |
 | 0.2795 | 550  | 0.1496        |
 | 0.3049 | 600  | 0.1443        |
+| 0.3303 | 650  | 0.1417        |
+| 0.3557 | 700  | 0.1335        |
+| 0.3811 | 750  | 0.1241        |
+| 0.4065 | 800  | 0.1212        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1843a41fe2dd32d660c15e8784bd2856c6414131db4c135fd8dff36f2c1ad8
+oid sha256:be0e439b975be2bf8c7efaab52c0c6da20f27d30d56fa0f57c0d227c23e5f279
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc4a0287e603c73e34c64d56fe7746287894b2e986c2ef471e4e5419ebf89b5
+oid sha256:5bc335a7c43ac002a024d775f06947950474016b02da4ee0e61390a1ee809165
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eb57b4b6586ca069ba10818f8421f503ffe2fcc4027df0b3bf8a2421cac2a7
+oid sha256:79cf700515bb029e36ca46412b96b02750cd1dce66cb44278ee1c691b7d1aa79
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3048780487804878,
+  "epoch": 0.4065040650406504,
   "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": 3.8650479954827784e-05,
       "loss": 0.1443,
       "step": 600
+    },
+    {
+      "epoch": 0.33028455284552843,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.7238848108413324e-05,
+      "loss": 0.1417,
+      "step": 650
+    },
+    {
+      "epoch": 0.3556910569105691,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.5827216261998877e-05,
+      "loss": 0.1335,
+      "step": 700
+    },
+    {
+      "epoch": 0.38109756097560976,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.4415584415584416e-05,
+      "loss": 0.1241,
+      "step": 750
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 3.375,
+      "learning_rate": 3.300395256916996e-05,
+      "loss": 0.1212,
+      "step": 800
     }
   ],
   "logging_steps": 50,