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 sha256:72b9c82bfed0ef2030970c9f30b4352b5627c1df06426da4a77edb7810418944
+oid sha256:3b6c776b093b837b0cfe9d25fef404f3dee032b8cafb171d812cfd30cd885e3b
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a88ee4f6617fb4562e1446b4a7b0c1d2bbcb3e599145beb6f78a94915b5670e
+oid sha256:70807611011deb9d648984e4201362594f4128f2399b18fb763a243b933061ba
 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([[ 0.6605, -0.0307, -0.0678]])
+# tensor([[ 0.6607, -0.0923, -0.0703]])
 ```
 
 <!--
@@ -697,6 +697,10 @@ You can finetune this model on your own dataset.
 | 0.3557 | 700  | 0.1335        |
 | 0.3811 | 750  | 0.1241        |
 | 0.4065 | 800  | 0.1212        |
+| 0.4319 | 850  | 0.1147        |
+| 0.4573 | 900  | 0.111         |
+| 0.4827 | 950  | 0.1163        |
+| 0.5081 | 1000 | 0.1133        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be0e439b975be2bf8c7efaab52c0c6da20f27d30d56fa0f57c0d227c23e5f279
+oid sha256:d73d930444c3a62a922f022e9b1dd8c90fa0101e0f9d6a5b5e7b445f20cc9f4c
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc335a7c43ac002a024d775f06947950474016b02da4ee0e61390a1ee809165
+oid sha256:d1c2b36aa1ed8b386c5ed3b537cdf298144b552b7011463c205e695056f73f6e
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cf700515bb029e36ca46412b96b02750cd1dce66cb44278ee1c691b7d1aa79
+oid sha256:ab6c56263d0a3d675d4f747bb77db752789302abc7e0c5864efa40f605c0194a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4065040650406504,
+  "epoch": 0.508130081300813,
   "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": 3.300395256916996e-05,
       "loss": 0.1212,
       "step": 800
+    },
+    {
+      "epoch": 0.43191056910569103,
+      "grad_norm": 3.703125,
+      "learning_rate": 3.159232072275551e-05,
+      "loss": 0.1147,
+      "step": 850
+    },
+    {
+      "epoch": 0.4573170731707317,
+      "grad_norm": 4.09375,
+      "learning_rate": 3.018068887634105e-05,
+      "loss": 0.111,
+      "step": 900
+    },
+    {
+      "epoch": 0.48272357723577236,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.8769057029926593e-05,
+      "loss": 0.1163,
+      "step": 950
+    },
+    {
+      "epoch": 0.508130081300813,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.7357425183512143e-05,
+      "loss": 0.1133,
+      "step": 1000
     }
   ],
   "logging_steps": 50,