Training in progress, step 3000, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032edebe5f429dd79fba4966fcbde9a9cc40387fbb5ff3037fee5320982f533d
+oid sha256:ea38fe71b4fc93cbe68622a9309bd62ac567ce9362561aae1fb1413f1e1279c5
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a83690af4caa724b099279db73cf30ae7344e4b81bfbf12086b7460efc44b21e
+oid sha256:6578a4180e63149bd07142c934c05e790e222b4bdafe8cbfb13ec6bb7b0eb990
 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([[ 0.5930, -0.1253,  0.2933]])
+# tensor([[ 0.5897, -0.1380,  0.2647]])
 ```
 
 <!--
@@ -743,6 +743,10 @@ You can finetune this model on your own dataset.
 | 0.8934 | 2700 | 0.0619        |
 | 0.9100 | 2750 | 0.0501        |
 | 0.9265 | 2800 | 0.0488        |
+| 0.9431 | 2850 | 0.0596        |
+| 0.9596 | 2900 | 0.0514        |
+| 0.9762 | 2950 | 0.0556        |
+| 0.9927 | 3000 | 0.0395        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1fb884bddc343ee71ee047c5c0febe2b1e7e4993b3fc969c8ebc7e8ce609f95
+oid sha256:ef383b42a96cf989b5ea5f2f57691ed7f173177e227d8af401b1ce939eeeef0e
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcf9758ec6185612baccc164b5f73985fbc506bec38cb9c649eb13a9fdc06d7
+oid sha256:f8682dc9728a848b2d7b2200731d8a05575a66f7e9e9ba3f88c6ec383f5127ac
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e788658da60471d70bc971aa62815f67253d726fc76137a47b5e2b2bda689438
+oid sha256:fb197e441ecbf3d517ec5cc71281886cf0daa798b522fd64348360f6a6763284
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aec44cdda33ef7dab0fb72bc661b8cbbd0d3c4d93e1602b0ef95ed38aa2a425
+oid sha256:879e85e1c6ae493744a544924cd5f86076951c82592e69abf0d8b51b66bc5e1a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9265387160820648,
+  "epoch": 0.9927200529450695,
   "eval_steps": 500,
-  "global_step": 2800,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -400,6 +400,34 @@
       "learning_rate": 1.6403089371092316e-06,
       "loss": 0.0488,
       "step": 2800
+    },
+    {
+      "epoch": 0.9430840502978161,
+      "grad_norm": 8.403130531311035,
+      "learning_rate": 1.272526664214785e-06,
+      "loss": 0.0596,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9596293845135672,
+      "grad_norm": 2.115785837173462,
+      "learning_rate": 9.047443913203384e-07,
+      "loss": 0.0514,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9761747187293184,
+      "grad_norm": 4.952437400817871,
+      "learning_rate": 5.369621184258919e-07,
+      "loss": 0.0556,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9927200529450695,
+      "grad_norm": 3.030841588973999,
+      "learning_rate": 1.691798455314454e-07,
+      "loss": 0.0395,
+      "step": 3000
     }
   ],
   "logging_steps": 50,