Training in progress, step 400, checkpoint

last-checkpoint/2_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245987c37984397149e2b7782bea1deeb6b41895e4c73137a0745ae1034fae74
+oid sha256:8385504144ad50228e1459ea5b1da17bd7f4d3aac19f5476c1c8296b68f4f05b
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06029654776794583e6462e88fb48f86fae257f300ef5195e19451cdd07501d
+oid sha256:ac472c212bf6ebd5d336507924eb651104467de24dfbfaa520db97b7708d09b9
 size 4718680

last-checkpoint/README.md

@@ -472,7 +472,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.7186, -0.1245, -0.0664]])
+# tensor([[ 0.5851, -0.1180, -0.1336]])
 ```
 
 <!--
@@ -685,6 +685,10 @@ You can finetune this model on your own dataset.
 | 0.0508 | 100  | 0.2331        |
 | 0.0762 | 150  | 0.2031        |
 | 0.1016 | 200  | 0.2042        |
+| 0.1270 | 250  | 0.2048        |
+| 0.1524 | 300  | 0.2123        |
+| 0.1778 | 350  | 0.186         |
+| 0.2033 | 400  | 0.1693        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dcff2bc35d4b89f9920dbfc24c9784230f133e60b7efd8421b728caa3129765
+oid sha256:5538ec5f6c8499fe8ef0de1e93c420e403b0b4f926f25aa62e05b6f0e23991b0
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89649a22f3916e197be45a082597d611800c3e9d7c9d75aba96246deab4411d1
+oid sha256:fd9addc9d33db5aa5f32bbfd79d0f8ab2168d1aa307bb30b7aa8355f331a85fd
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4e739551319e957e6c472fd8c9bacf3bae41231a764211a8f19abc4bae6961
+oid sha256:8fc56140e5c37825482a26f377f07f74eaa4028a1b2f8b46eaa880f0215c9abf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1016260162601626,
+  "epoch": 0.2032520325203252,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,34 @@
       "learning_rate": 4.994353472614343e-05,
       "loss": 0.2042,
       "step": 200
+    },
+    {
+      "epoch": 0.12703252032520326,
+      "grad_norm": 5.4375,
+      "learning_rate": 4.853190287972897e-05,
+      "loss": 0.2048,
+      "step": 250
+    },
+    {
+      "epoch": 0.1524390243902439,
+      "grad_norm": 5.09375,
+      "learning_rate": 4.7120271033314515e-05,
+      "loss": 0.2123,
+      "step": 300
+    },
+    {
+      "epoch": 0.17784552845528456,
+      "grad_norm": 4.5,
+      "learning_rate": 4.570863918690006e-05,
+      "loss": 0.186,
+      "step": 350
+    },
+    {
+      "epoch": 0.2032520325203252,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.42970073404856e-05,
+      "loss": 0.1693,
+      "step": 400
     }
   ],
   "logging_steps": 50,