Training in progress, step 2600, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752759552186625515f43f84888e4663ecb27e5287441c157d3977055f4bf32c
+oid sha256:60070dd67aa609f2ec4f6099d7d305d359dcc87b0243c555b4c92a408ce9d712
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca6cce4de8154cbea27337a182b1a58e5d9844958825a4a2739bdcc67bc2773
+oid sha256:40f7cffbf560a28dbdda8e392d68b3a6612c84a2695c8f5f18a821a6d39735e6
 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([[ 0.5471, -0.1429,  0.2361]])
+# tensor([[ 0.5888, -0.1134,  0.2544]])
 ```
 
 <!--
@@ -735,6 +735,10 @@ You can finetune this model on your own dataset.
 | 0.7611 | 2300 | 0.0624        |
 | 0.7776 | 2350 | 0.064         |
 | 0.7942 | 2400 | 0.0584        |
+| 0.8107 | 2450 | 0.0577        |
+| 0.8273 | 2500 | 0.0536        |
+| 0.8438 | 2550 | 0.0562        |
+| 0.8604 | 2600 | 0.0546        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfbf4784354dd4af7855c8f6f7878fd0604264cd0c3b1804ab0875dce6fb244
+oid sha256:9269f4be93991384c4f927cab218c96e7647244f18be47d991875eefe31fe1b4
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50fc6b8a0afd1376d6cec248ec2b5d0cf43afc19c320cd448ae6ff944132b7cc
+oid sha256:7831d803c865f7e99a7918d82c3c406fbd5cc5f5d3e8383554847671b1ac4256
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910fb5401e351aa449c1f6217c02dcacaa380310a63bab91d5c0135ff0cfeed4
+oid sha256:b2ccbe8068d53f3cc47989534cf2cf09a26c0622368fe1ff0065518632dc4752
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7611f5499deb7d96ffc28c7f3dfb4ef45dd7e292266150e1e19f8f8080a6257c
+oid sha256:615edf11d6f1cfab17840ec8946b503fd418735a16b0c229a49e61367753f384
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7941760423560555,
+  "epoch": 0.8603573792190602,
   "eval_steps": 500,
-  "global_step": 2400,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -344,6 +344,34 @@
       "learning_rate": 4.582567120264804e-06,
       "loss": 0.0584,
       "step": 2400
+    },
+    {
+      "epoch": 0.8107213765718068,
+      "grad_norm": 4.290740013122559,
+      "learning_rate": 4.214784847370357e-06,
+      "loss": 0.0577,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8272667107875579,
+      "grad_norm": 3.434802293777466,
+      "learning_rate": 3.8470025744759105e-06,
+      "loss": 0.0536,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8438120450033091,
+      "grad_norm": 4.708302021026611,
+      "learning_rate": 3.479220301581464e-06,
+      "loss": 0.0562,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8603573792190602,
+      "grad_norm": 3.8048012256622314,
+      "learning_rate": 3.1114380286870177e-06,
+      "loss": 0.0546,
+      "step": 2600
     }
   ],
   "logging_steps": 50,