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:b689863e6d29f1c60b5a2948cb88db8a13c8f7af624a175e1f8603494d46f161
+oid sha256:812bfba1c31117fa38db39436eeebde44eaacff2575200fd14e4dc6ae62f929e
 size 9437272

last-checkpoint/3_Dense/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da6beacd8ad9dfba42f0c182bc53b1c1409d801ccb9334a01737c823da21e054
+oid sha256:27655c85a8aaadee9dacf58cce7dfb1ef47960690b134cbf31a575003007bdf1
 size 9437272

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([[0.8510, 0.1401, 0.0465]])
+# tensor([[ 0.8773,  0.0462, -0.0253]])
 ```
 
 <!--
@@ -633,6 +633,10 @@ You can finetune this model on your own dataset.
 | 0.0058 | 100  | 0.1107        |
 | 0.0087 | 150  | 0.0709        |
 | 0.0116 | 200  | 0.0679        |
+| 0.0145 | 250  | 0.0597        |
+| 0.0174 | 300  | 0.0598        |
+| 0.0203 | 350  | 0.0764        |
+| 0.0232 | 400  | 0.0506        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5578677c98d5e02437aab62b180636ff28d9dda1f9f979cc8d5df10d0c39d61
+oid sha256:6582519cc43472715ff09bc8df56e970c36c8b09bfc714e3e192aee757eaee08
 size 1211486072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c54364594667bfc3bf550b4f837595b03f0409bdb747cbe833803e067cf0a32
+oid sha256:5f2ae5f738d4f327522544fdad61a200aa371a47e470a3064bbdc08ee183ccfb
 size 2460919051

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486e221387d22919b4920650304a8ef852ef9ecb76ad018547408840989fd812
+oid sha256:1a4e9c48a349d0a234c258982447a8a00d011d07b1124aeae1ab41f62980a473
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57dab3efc78fec548075e3471f0d120a04945f52518249d9e6e88bd909eee6e
+oid sha256:f73d856eaa2ecf465e98ae99429ae8f821bc70f284dc9f5844d0faffe2f796d2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011583458820803891,
+  "epoch": 0.023166917641607783,
   "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": 2.8228141285466127e-06,
       "loss": 0.0679,
       "step": 200
+    },
+    {
+      "epoch": 0.014479323526004865,
+      "grad_norm": 4.010167598724365,
+      "learning_rate": 3.546612623045744e-06,
+      "loss": 0.0597,
+      "step": 250
+    },
+    {
+      "epoch": 0.01737518823120584,
+      "grad_norm": 10.415971755981445,
+      "learning_rate": 4.270411117544876e-06,
+      "loss": 0.0598,
+      "step": 300
+    },
+    {
+      "epoch": 0.02027105293640681,
+      "grad_norm": 2.172306537628174,
+      "learning_rate": 4.994209612044008e-06,
+      "loss": 0.0764,
+      "step": 350
+    },
+    {
+      "epoch": 0.023166917641607783,
+      "grad_norm": 15.422524452209473,
+      "learning_rate": 5.718008106543138e-06,
+      "loss": 0.0506,
+      "step": 400
     }
   ],
   "logging_steps": 50,