Training in progress, step 800, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd0cd5325744cbadf85834360afa08f075907c48439302dd9bd1990dcba7c09
+oid sha256:56b28b74545c8174d80d1900fffbe59b2a7435a9e928a3f943266d2d96667067
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618d79044611c03845fd3d5cfff9c6517211438370c9270043bd8df5fd157566
+oid sha256:40f17852afeb04a7d81bc4e27fdae244ba00112c63322abe9f6c299a666b57b5
 size 4718680

last-checkpoint/README.md

@@ -511,7 +511,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.6990, -0.1064,  0.0055]])
+# tensor([[ 0.7210, -0.0779, -0.0314]])
 ```
 
 <!--
@@ -732,6 +732,10 @@ You can finetune this model on your own dataset.
 | 0.4798 | 500  | 0.177         |
 | 0.5278 | 550  | 0.1739        |
 | 0.5758 | 600  | 0.1743        |
+| 0.6238 | 650  | 0.1574        |
+| 0.6718 | 700  | 0.1586        |
+| 0.7198 | 750  | 0.1473        |
+| 0.7678 | 800  | 0.1547        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688b779211f9d7729cdb8b7a1f33de65e70bf757e770157591258607c47b7f93
+oid sha256:fe81efee97c0f5f6e85eab9e97762a9d281501c3388cc280a9df8ee7217683d3
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4cb7e1ce7f84c978a72dad631b014ca653d4764aa7b2675e53c47546614601d
+oid sha256:5dbba28742d6013f6fc692c0d332059d2e00fb3286712afea40fb65838ac9adc
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edab5dd7827df6c860a06cbc8d688873b247f37062ba5008ca6bb63249a0eb13
+oid sha256:d57a1899b276deaf9bc6c347b576a36bf470824199b1d1731a5698c732cc5649
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5758157389635317,
+  "epoch": 0.7677543186180422,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 2.3639274279615796e-05,
       "loss": 0.1743,
       "step": 600
+    },
+    {
+      "epoch": 0.6238003838771593,
+      "grad_norm": 3.28125,
+      "learning_rate": 2.097118463180363e-05,
+      "loss": 0.1574,
+      "step": 650
+    },
+    {
+      "epoch": 0.6717850287907869,
+      "grad_norm": 4.125,
+      "learning_rate": 1.830309498399146e-05,
+      "loss": 0.1586,
+      "step": 700
+    },
+    {
+      "epoch": 0.7197696737044146,
+      "grad_norm": 3.875,
+      "learning_rate": 1.5635005336179295e-05,
+      "loss": 0.1473,
+      "step": 750
+    },
+    {
+      "epoch": 0.7677543186180422,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.2966915688367129e-05,
+      "loss": 0.1547,
+      "step": 800
     }
   ],
   "logging_steps": 50,