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:f45d87a3222e8eb06a466ab5dfa5150775275ac497c809e075ffadc6ee21433f
+oid sha256:f4e59b6eeab109132425badd739781747497d523d81e67c7da5995b47a105606
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b563a3aea396a4563642a218726dda67d3f6067140172e6b40ef0d94743c0bc0
+oid sha256:236ee3f6c76e6dd53cb72f79ed12aacb7f2bcdc6d9653f7ff3049589d714a456
 size 4718680

last-checkpoint/README.md

@@ -424,7 +424,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[0.9050, 0.0240, 0.0505]])
+# tensor([[0.9082, 0.0190, 0.0399]])
 ```
 
 <!--
@@ -649,6 +649,10 @@ You can finetune this model on your own dataset.
 | 0.6481 | 700  | 0.0872        |
 | 0.6944 | 750  | 0.087         |
 | 0.7407 | 800  | 0.0771        |
+| 0.7870 | 850  | 0.0808        |
+| 0.8333 | 900  | 0.0716        |
+| 0.8796 | 950  | 0.0806        |
+| 0.9259 | 1000 | 0.0751        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b524fd4d0af037372baac781a7e02bde6af66075c966d2f2ae612f58d66ff03
+oid sha256:7043ac46a43b67270262de15fa756613b340ca4d39f45c6b1ad2d3d62b923215
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c6983bf30f51cc12841bdc8966719604748c2803cd6de5d87dffadf3eb3a01
+oid sha256:a36d649cfa382270fa9cb34ecdc0eaa34459ba7d1d01e0d8f5a0dcd009dec103
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad211f85f7952dd56f43d381e1780d6a978df68441ca57ba5688f4ef0c8d4b7
+oid sha256:71506dd75ffea4620eca46bea4d3e2da666baa9d78fa9907096978fc32ffdb98
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7407407407407407,
+  "epoch": 0.9259259259259259,
   "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": 1.4454732510288065e-05,
       "loss": 0.0771,
       "step": 800
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 2.734375,
+      "learning_rate": 1.1882716049382716e-05,
+      "loss": 0.0808,
+      "step": 850
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.40625,
+      "learning_rate": 9.310699588477368e-06,
+      "loss": 0.0716,
+      "step": 900
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 2.328125,
+      "learning_rate": 6.7386831275720164e-06,
+      "loss": 0.0806,
+      "step": 950
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 2.640625,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0751,
+      "step": 1000
     }
   ],
   "logging_steps": 50,