Training in progress, step 2000, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af98deca1bdedf2c438bafbb4e4a4bda82f05a9d3f61df9c1056c21b8056ccf
+oid sha256:dae24f44899cd59be1cdc752b8619c96627a0482f17d71b8e1601b3ef053d587
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b74bd3c8c835573059a161d0a582b79de2540d78ae310548a081c3f43be5b48
+oid sha256:aab7218d6090405ddfccdb53a2ae64ceadcd09eb15d69a392554421520450e3d
 size 9437272

last-checkpoint/README.md

@@ -450,7 +450,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.5477, -0.1184,  0.2774]])
+# tensor([[ 0.5786, -0.1183,  0.2822]])
 ```
 
 <!--
@@ -723,6 +723,10 @@ You can finetune this model on your own dataset.
 | 0.5625 | 1700 | 0.0855        |
 | 0.5791 | 1750 | 0.0789        |
 | 0.5956 | 1800 | 0.061         |
+| 0.6122 | 1850 | 0.077         |
+| 0.6287 | 1900 | 0.085         |
+| 0.6453 | 1950 | 0.0661        |
+| 0.6618 | 2000 | 0.0676        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d18c910556766cdb393fa461e5eb0bbb29197d25fa3aef856f25d8a2869f7d
+oid sha256:7e48e6fe8b194f288825636e04d930d85909b6fe40fd47036087f107ec513026
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171ade8b34abc98359451568301cb5e7eac16a20609a6cbad41a18fdc48c659b
+oid sha256:36850b1bf7028e83ab8d18e79fbc7b55dafb3d89320d4d3acbfec88767143bf1
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea1ac8b50e0389ab9d8a7c921ce6a1975198ca3afd3f0ac69f0f2408d305ada
+oid sha256:88df7445be7005515f07c4b02155cabbc487c89f5a1f597fab296ac0ffe48b81
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d8f648f97acc4d8f0d0540741a3df11f09f70b565f391e664dc832d4ffedcb
+oid sha256:2f9a8575ecdf4fa819a09c8f3ae03b619c376812328c6c0652361283efc7e44c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5956320317670417,
+  "epoch": 0.6618133686300464,
   "eval_steps": 500,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -260,6 +260,34 @@
       "learning_rate": 8.995954394998163e-06,
       "loss": 0.061,
       "step": 1800
+    },
+    {
+      "epoch": 0.6121773659827928,
+      "grad_norm": 6.357212066650391,
+      "learning_rate": 8.628172122103716e-06,
+      "loss": 0.077,
+      "step": 1850
+    },
+    {
+      "epoch": 0.628722700198544,
+      "grad_norm": 4.212811470031738,
+      "learning_rate": 8.26038984920927e-06,
+      "loss": 0.085,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6452680344142951,
+      "grad_norm": 5.546814441680908,
+      "learning_rate": 7.892607576314823e-06,
+      "loss": 0.0661,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6618133686300464,
+      "grad_norm": 5.276381492614746,
+      "learning_rate": 7.524825303420375e-06,
+      "loss": 0.0676,
+      "step": 2000
     }
   ],
   "logging_steps": 50,