Training in progress, step 1600, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14549a8f2b505a8545ac674725066f9c305d15592336942bb065ad4f6ddeb306
+oid sha256:5ef8c04b17ad19cb132ef20b5b1a1912424354dd87c3760dbafc1f82f4998feb
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0952aa81b7cdd3daf666c37d0854e5bff5e7a14e28b4874444f7772caeb46f9d
+oid sha256:b41b495d7e858c250a6b90039f9524914ea51d03a32937b352f996067227212d
 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([[ 0.6231, -0.0744,  0.1279]])
+# tensor([[ 0.5546, -0.0938,  0.1724]])
 ```
 
 <!--
@@ -715,6 +715,10 @@ You can finetune this model on your own dataset.
 | 0.4302 | 1300 | 0.09          |
 | 0.4467 | 1350 | 0.0866        |
 | 0.4633 | 1400 | 0.0826        |
+| 0.4798 | 1450 | 0.0735        |
+| 0.4964 | 1500 | 0.0801        |
+| 0.5129 | 1550 | 0.0694        |
+| 0.5295 | 1600 | 0.0681        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477457ae6906b9786bffa8dd6309187edd28e664410a059cfffacf1f2cae3bc6
+oid sha256:01b4fd7c2f9f44ed46fd6caca70cf6aebe1f901b80125453289a207674ea6322
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fcb82c0030f2e69a729cae162131808daef058010082ee7c6a1cdc5a1109b47
+oid sha256:7d22bc43d0ea91abbc9c61e88421b8d7b9f75756021d1e9a3876bbcd9caea969
 size 2460923467

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcfe456f41c489958b10f637ef851405e803e7363ed9925c3152e6d7cebd14a
+oid sha256:0de07336841d438b92ac2af437c756d5b1eee4a3bd0fc209eb2ee92c1bfa99d5
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1807d5c010828dc5af6863500632317772ab24748d2f2f3dc9b74b307531f182
+oid sha256:f5730fd993b5a94a8fdb013ee342013b2eea3ce6c8a5a4ded39a304962934fc3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4632693580410324,
+  "epoch": 0.5294506949040371,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -204,6 +204,34 @@
       "learning_rate": 1.1938212578153734e-05,
       "loss": 0.0826,
       "step": 1400
+    },
+    {
+      "epoch": 0.4798146922567836,
+      "grad_norm": 4.941124439239502,
+      "learning_rate": 1.1570430305259287e-05,
+      "loss": 0.0735,
+      "step": 1450
+    },
+    {
+      "epoch": 0.49636002647253474,
+      "grad_norm": 4.166671276092529,
+      "learning_rate": 1.120264803236484e-05,
+      "loss": 0.0801,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5129053606882858,
+      "grad_norm": 4.212963581085205,
+      "learning_rate": 1.0834865759470394e-05,
+      "loss": 0.0694,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5294506949040371,
+      "grad_norm": 4.659167766571045,
+      "learning_rate": 1.0467083486575949e-05,
+      "loss": 0.0681,
+      "step": 1600
     }
   ],
   "logging_steps": 50,