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 sha256:8385504144ad50228e1459ea5b1da17bd7f4d3aac19f5476c1c8296b68f4f05b
+oid sha256:27c35bbbe0b3b4648d206a86b9a22ed14cdd5ba12f681b9329d51cc3594ed874
 size 4718680

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac472c212bf6ebd5d336507924eb651104467de24dfbfaa520db97b7708d09b9
+oid sha256:a4cec3b48c616eb4b62540bb0ef79466b8968a49111b3b79390a007de3e0f383
 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([[ 0.5851, -0.1180, -0.1336]])
+# tensor([[ 0.6778, -0.0608, -0.0575]])
 ```
 
 <!--
@@ -689,6 +689,10 @@ You can finetune this model on your own dataset.
 | 0.1524 | 300  | 0.2123        |
 | 0.1778 | 350  | 0.186         |
 | 0.2033 | 400  | 0.1693        |
+| 0.2287 | 450  | 0.1645        |
+| 0.2541 | 500  | 0.1625        |
+| 0.2795 | 550  | 0.1496        |
+| 0.3049 | 600  | 0.1443        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5538ec5f6c8499fe8ef0de1e93c420e403b0b4f926f25aa62e05b6f0e23991b0
+oid sha256:bc1843a41fe2dd32d660c15e8784bd2856c6414131db4c135fd8dff36f2c1ad8
 size 605759848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9addc9d33db5aa5f32bbfd79d0f8ab2168d1aa307bb30b7aa8355f331a85fd
+oid sha256:0dc4a0287e603c73e34c64d56fe7746287894b2e986c2ef471e4e5419ebf89b5
 size 1230592267

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc56140e5c37825482a26f377f07f74eaa4028a1b2f8b46eaa880f0215c9abf
+oid sha256:a7eb57b4b6586ca069ba10818f8421f503ffe2fcc4027df0b3bf8a2421cac2a7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2032520325203252,
+  "epoch": 0.3048780487804878,
   "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": 4.42970073404856e-05,
       "loss": 0.1693,
       "step": 400
+    },
+    {
+      "epoch": 0.22865853658536586,
+      "grad_norm": 5.75,
+      "learning_rate": 4.288537549407115e-05,
+      "loss": 0.1645,
+      "step": 450
+    },
+    {
+      "epoch": 0.2540650406504065,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.147374364765669e-05,
+      "loss": 0.1625,
+      "step": 500
+    },
+    {
+      "epoch": 0.27947154471544716,
+      "grad_norm": 3.984375,
+      "learning_rate": 4.006211180124224e-05,
+      "loss": 0.1496,
+      "step": 550
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "grad_norm": 3.625,
+      "learning_rate": 3.8650479954827784e-05,
+      "loss": 0.1443,
+      "step": 600
     }
   ],
   "logging_steps": 50,