Training in progress, step 2200, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae24f44899cd59be1cdc752b8619c96627a0482f17d71b8e1601b3ef053d587
+oid sha256:bc70cd979bc0f8d6854ac24389fb9983bd7c1348da5adf8b9ce14ea9c13e1437
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab7218d6090405ddfccdb53a2ae64ceadcd09eb15d69a392554421520450e3d
+oid sha256:da87d038bf430393d72e8162a91cdaf090b88f744ba76c25999544816381f7ca
 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([[ 0.5786, -0.1183,  0.2822]])
+# tensor([[ 0.5013, -0.1183,  0.2914]])
 ```
 
 <!--
@@ -727,6 +727,10 @@ You can finetune this model on your own dataset.
 | 0.6287 | 1900 | 0.085         |
 | 0.6453 | 1950 | 0.0661        |
 | 0.6618 | 2000 | 0.0676        |
+| 0.6784 | 2050 | 0.0598        |
+| 0.6949 | 2100 | 0.0734        |
+| 0.7114 | 2150 | 0.0653        |
+| 0.7280 | 2200 | 0.0751        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e48e6fe8b194f288825636e04d930d85909b6fe40fd47036087f107ec513026
+oid sha256:0473cfcb7e3c364fd02654b46c9d660aaf46bf1670ce0cb4ce0ebb6d79517a7f
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36850b1bf7028e83ab8d18e79fbc7b55dafb3d89320d4d3acbfec88767143bf1
+oid sha256:46eae69537d2228e82f1efd9242173793094fb832fc89a291b843d223ca72e45
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88df7445be7005515f07c4b02155cabbc487c89f5a1f597fab296ac0ffe48b81
+oid sha256:514519403b4ca514f8ce9852255fb8898d761d1af37eddca5abb7c9fcbc625f2
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9a8575ecdf4fa819a09c8f3ae03b619c376812328c6c0652361283efc7e44c
+oid sha256:2a5514a935e35b6a4a520541aa5fd6620a939141d2380504a718d93807ed07a4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6618133686300464,
+  "epoch": 0.727994705493051,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,34 @@
       "learning_rate": 7.524825303420375e-06,
       "loss": 0.0676,
       "step": 2000
+    },
+    {
+      "epoch": 0.6783587028457975,
+      "grad_norm": 4.1648077964782715,
+      "learning_rate": 7.157043030525929e-06,
+      "loss": 0.0598,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6949040370615487,
+      "grad_norm": 7.234411716461182,
+      "learning_rate": 6.789260757631483e-06,
+      "loss": 0.0734,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7114493712772998,
+      "grad_norm": 6.458765029907227,
+      "learning_rate": 6.421478484737036e-06,
+      "loss": 0.0653,
+      "step": 2150
+    },
+    {
+      "epoch": 0.727994705493051,
+      "grad_norm": 4.6173930168151855,
+      "learning_rate": 6.05369621184259e-06,
+      "loss": 0.0751,
+      "step": 2200
     }
   ],
   "logging_steps": 50,