Training in progress, step 1800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c9ce80711acc5708fa03ca5c1abc26071fb1461cb7e0831999e447eff9cd1a
+oid sha256:400e4f138cc26c5d165ba04ccda48bd7296f46c05e26190bd789555593817a22
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019263c58bc2b520dec5e0ad177732b5a097fc826cae937845d0a4226930995c
+oid sha256:1ec6c2be4f316baca2bdc5689a13674de1c91858439ed131ad1507b0ae68a407
 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([[ 0.6973, -0.0965, -0.1011]])
+# tensor([[ 0.7067, -0.0843, -0.0921]])
 ```
 
 <!--
@@ -713,6 +713,10 @@ You can finetune this model on your own dataset.
 | 0.7622 | 1500 | 0.0882        |
 | 0.7876 | 1550 | 0.0816        |
 | 0.8130 | 1600 | 0.0847        |
+| 0.8384 | 1650 | 0.0824        |
+| 0.8638 | 1700 | 0.0878        |
+| 0.8892 | 1750 | 0.0822        |
+| 0.9146 | 1800 | 0.0792        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0951f19e6e47bf8b0d7afa9b9188827b158337d188c1cbb45f30a48fc06d1b
+oid sha256:c44e01cf741acb803d6e04527da1f664016682833461b366d42997159b0416e6
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8ea1af8787344f7eb6b924f0aa1551e33e51330ba17797ae085e9c68294c47
+oid sha256:184cdfd28ea4214abe2fcbc868f15877077a7bc59cc6a0683bb50c1246efdbef
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac15faca44126ea757af3cc9233a4970a99a30bf6b2f36cfb0d4ae9816273ed
+oid sha256:ec29327b2c793ef05a01c6bae10cd1cf49d3fd34bb421765aad2d8f09bc372c0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8130081300813008,
+  "epoch": 0.9146341463414634,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,34 @@
       "learning_rate": 1.0417843026538679e-05,
       "loss": 0.0847,
       "step": 1600
+    },
+    {
+      "epoch": 0.8384146341463414,
+      "grad_norm": 2.8125,
+      "learning_rate": 9.006211180124225e-06,
+      "loss": 0.0824,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8638211382113821,
+      "grad_norm": 3.0,
+      "learning_rate": 7.594579333709768e-06,
+      "loss": 0.0878,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8892276422764228,
+      "grad_norm": 2.6875,
+      "learning_rate": 6.1829474872953135e-06,
+      "loss": 0.0822,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9146341463414634,
+      "grad_norm": 2.515625,
+      "learning_rate": 4.771315640880859e-06,
+      "loss": 0.0792,
+      "step": 1800
     }
   ],
   "logging_steps": 50,