Training in progress, step 1800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef8c04b17ad19cb132ef20b5b1a1912424354dd87c3760dbafc1f82f4998feb
+oid sha256:2af98deca1bdedf2c438bafbb4e4a4bda82f05a9d3f61df9c1056c21b8056ccf
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41b495d7e858c250a6b90039f9524914ea51d03a32937b352f996067227212d
+oid sha256:1b74bd3c8c835573059a161d0a582b79de2540d78ae310548a081c3f43be5b48
 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([[ 0.5546, -0.0938,  0.1724]])
+# tensor([[ 0.5477, -0.1184,  0.2774]])
 ```
 
 <!--
@@ -719,6 +719,10 @@ You can finetune this model on your own dataset.
 | 0.4964 | 1500 | 0.0801        |
 | 0.5129 | 1550 | 0.0694        |
 | 0.5295 | 1600 | 0.0681        |
+| 0.5460 | 1650 | 0.0741        |
+| 0.5625 | 1700 | 0.0855        |
+| 0.5791 | 1750 | 0.0789        |
+| 0.5956 | 1800 | 0.061         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b4fd7c2f9f44ed46fd6caca70cf6aebe1f901b80125453289a207674ea6322
+oid sha256:46d18c910556766cdb393fa461e5eb0bbb29197d25fa3aef856f25d8a2869f7d
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d22bc43d0ea91abbc9c61e88421b8d7b9f75756021d1e9a3876bbcd9caea969
+oid sha256:171ade8b34abc98359451568301cb5e7eac16a20609a6cbad41a18fdc48c659b
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de07336841d438b92ac2af437c756d5b1eee4a3bd0fc209eb2ee92c1bfa99d5
+oid sha256:6ea1ac8b50e0389ab9d8a7c921ce6a1975198ca3afd3f0ac69f0f2408d305ada
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5730fd993b5a94a8fdb013ee342013b2eea3ce6c8a5a4ded39a304962934fc3
+oid sha256:97d8f648f97acc4d8f0d0540741a3df11f09f70b565f391e664dc832d4ffedcb
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5294506949040371,
+  "epoch": 0.5956320317670417,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -232,6 +232,34 @@
       "learning_rate": 1.0467083486575949e-05,
       "loss": 0.0681,
       "step": 1600
+    },
+    {
+      "epoch": 0.5459960291197882,
+      "grad_norm": 1.2746665477752686,
+      "learning_rate": 1.00993012136815e-05,
+      "loss": 0.0741,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5625413633355394,
+      "grad_norm": 5.447134017944336,
+      "learning_rate": 9.731518940787054e-06,
+      "loss": 0.0855,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5790866975512905,
+      "grad_norm": 5.253468036651611,
+      "learning_rate": 9.363736667892607e-06,
+      "loss": 0.0789,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5956320317670417,
+      "grad_norm": 9.73345947265625,
+      "learning_rate": 8.995954394998163e-06,
+      "loss": 0.061,
+      "step": 1800
     }
   ],
   "logging_steps": 50,