Training in progress, step 600, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c88013d65aeba6cd0320a8bdf542df82418400820ba7cc58b9536963f8a5f6
+oid sha256:89111b92371b9a2deba746060687471336a0d4cfe96973e9574079626d724c62
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841fe46d69b0008634a14be512e1e411ce4d65589bfc375f8ecb345f2e8d7f12
+oid sha256:65d9933e8dc3511fb603634911f867225eb29d7c8fd74a4559dd878cf05993b9
 size 4718680

last-checkpoint/README.md

@@ -424,7 +424,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[0.8570, 0.0561, 0.0702]])
+# tensor([[0.8942, 0.0534, 0.0618]])
 ```
 
 <!--
@@ -641,6 +641,10 @@ You can finetune this model on your own dataset.
 | 0.2778 | 300  | 0.1225        |
 | 0.3241 | 350  | 0.1248        |
 | 0.3704 | 400  | 0.1141        |
+| 0.4167 | 450  | 0.1124        |
+| 0.4630 | 500  | 0.0966        |
+| 0.5093 | 550  | 0.0942        |
+| 0.5556 | 600  | 0.0866        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187b1b756dac2e7a25d7535399df83edcdbe3e7c67adf143f1cc5c2d8d8dd510
+oid sha256:fb9b7a8327bcd9f26fb726f7f314185b56e82623ee2d12b4d931b6652419f10a
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1398abfe945cdadcbfb72545a44274567333ea62c9374fad6a213dc7a74f085
+oid sha256:0511132bcec99cfb81e6cdbe3f440ab29dbefe3ec7dbb1ed13c95d382a5fb775
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf50a8da9b77d1d667aa2be5f7411c48d830b5ed090e0ff1a8209df626c404c4
+oid sha256:e5ef9347676d52185ae368f376cf1fe5dd55cbd5ed84547d819fe30ad5c5892f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37037037037037035,
+  "epoch": 0.5555555555555556,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,34 @@
       "learning_rate": 3.503086419753087e-05,
       "loss": 0.1141,
       "step": 400
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 3.609375,
+      "learning_rate": 3.245884773662551e-05,
+      "loss": 0.1124,
+      "step": 450
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 3.421875,
+      "learning_rate": 2.9886831275720166e-05,
+      "loss": 0.0966,
+      "step": 500
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 3.21875,
+      "learning_rate": 2.7314814814814816e-05,
+      "loss": 0.0942,
+      "step": 550
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 3.671875,
+      "learning_rate": 2.4742798353909465e-05,
+      "loss": 0.0866,
+      "step": 600
     }
   ],
   "logging_steps": 50,