Training in progress, step 1200, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6c776b093b837b0cfe9d25fef404f3dee032b8cafb171d812cfd30cd885e3b
+oid sha256:5a2189eb62627bdac98795adf703b4963d7bb5806a18140f0705bd0846bdcb81
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70807611011deb9d648984e4201362594f4128f2399b18fb763a243b933061ba
+oid sha256:4ec50e543099a6bb0c1f8e5fdd57d0d9e86ebe7e6b5160cc004a39d435e0eea0
 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([[ 0.6607, -0.0923, -0.0703]])
+# tensor([[ 0.7396, -0.0637, -0.0765]])
 ```
 
 <!--
@@ -701,6 +701,10 @@ You can finetune this model on your own dataset.
 | 0.4573 | 900  | 0.111         |
 | 0.4827 | 950  | 0.1163        |
 | 0.5081 | 1000 | 0.1133        |
+| 0.5335 | 1050 | 0.1008        |
+| 0.5589 | 1100 | 0.1075        |
+| 0.5843 | 1150 | 0.0994        |
+| 0.6098 | 1200 | 0.0911        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73d930444c3a62a922f022e9b1dd8c90fa0101e0f9d6a5b5e7b445f20cc9f4c
+oid sha256:f10ebdd6d376d88b30ef3bdc290fee724cdcdb9834c31657cb9b7e697616ef0b
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1c2b36aa1ed8b386c5ed3b537cdf298144b552b7011463c205e695056f73f6e
+oid sha256:92bc90f9a7af2adcce32e0343802524c333d41bf01c18a9ae80cb07c5024b317
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6c56263d0a3d675d4f747bb77db752789302abc7e0c5864efa40f605c0194a
+oid sha256:b8e232785d1786cb94e8889d9a79973e568b9bfb82c9ff8f8a12783934ff997c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.508130081300813,
+  "epoch": 0.6097560975609756,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,34 @@
       "learning_rate": 2.7357425183512143e-05,
       "loss": 0.1133,
       "step": 1000
+    },
+    {
+      "epoch": 0.5335365853658537,
+      "grad_norm": 3.34375,
+      "learning_rate": 2.5945793337097685e-05,
+      "loss": 0.1008,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5589430894308943,
+      "grad_norm": 3.890625,
+      "learning_rate": 2.453416149068323e-05,
+      "loss": 0.1075,
+      "step": 1100
+    },
+    {
+      "epoch": 0.584349593495935,
+      "grad_norm": 3.6875,
+      "learning_rate": 2.3122529644268774e-05,
+      "loss": 0.0994,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 2.609375,
+      "learning_rate": 2.171089779785432e-05,
+      "loss": 0.0911,
+      "step": 1200
     }
   ],
   "logging_steps": 50,