Training in progress, step 2400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc70cd979bc0f8d6854ac24389fb9983bd7c1348da5adf8b9ce14ea9c13e1437
+oid sha256:752759552186625515f43f84888e4663ecb27e5287441c157d3977055f4bf32c
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da87d038bf430393d72e8162a91cdaf090b88f744ba76c25999544816381f7ca
+oid sha256:9ca6cce4de8154cbea27337a182b1a58e5d9844958825a4a2739bdcc67bc2773
 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([[ 0.5013, -0.1183,  0.2914]])
+# tensor([[ 0.5471, -0.1429,  0.2361]])
 ```
 
 <!--
@@ -731,6 +731,10 @@ You can finetune this model on your own dataset.
 | 0.6949 | 2100 | 0.0734        |
 | 0.7114 | 2150 | 0.0653        |
 | 0.7280 | 2200 | 0.0751        |
+| 0.7445 | 2250 | 0.064         |
+| 0.7611 | 2300 | 0.0624        |
+| 0.7776 | 2350 | 0.064         |
+| 0.7942 | 2400 | 0.0584        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0473cfcb7e3c364fd02654b46c9d660aaf46bf1670ce0cb4ce0ebb6d79517a7f
+oid sha256:abfbf4784354dd4af7855c8f6f7878fd0604264cd0c3b1804ab0875dce6fb244
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46eae69537d2228e82f1efd9242173793094fb832fc89a291b843d223ca72e45
+oid sha256:50fc6b8a0afd1376d6cec248ec2b5d0cf43afc19c320cd448ae6ff944132b7cc
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514519403b4ca514f8ce9852255fb8898d761d1af37eddca5abb7c9fcbc625f2
+oid sha256:910fb5401e351aa449c1f6217c02dcacaa380310a63bab91d5c0135ff0cfeed4
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5514a935e35b6a4a520541aa5fd6620a939141d2380504a718d93807ed07a4
+oid sha256:7611f5499deb7d96ffc28c7f3dfb4ef45dd7e292266150e1e19f8f8080a6257c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.727994705493051,
+  "epoch": 0.7941760423560555,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,34 @@
       "learning_rate": 6.05369621184259e-06,
       "loss": 0.0751,
       "step": 2200
+    },
+    {
+      "epoch": 0.7445400397088021,
+      "grad_norm": 5.65716028213501,
+      "learning_rate": 5.685913938948143e-06,
+      "loss": 0.064,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7610853739245532,
+      "grad_norm": 4.843678951263428,
+      "learning_rate": 5.318131666053696e-06,
+      "loss": 0.0624,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7776307081403044,
+      "grad_norm": 4.933941841125488,
+      "learning_rate": 4.95034939315925e-06,
+      "loss": 0.064,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7941760423560555,
+      "grad_norm": 4.032420635223389,
+      "learning_rate": 4.582567120264804e-06,
+      "loss": 0.0584,
+      "step": 2400
     }
   ],
   "logging_steps": 50,