Training in progress, step 400, checkpoint

last-checkpoint/README.md

@@ -422,7 +422,7 @@ print(query_embeddings.shape, document_embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(query_embeddings, document_embeddings)
 print(similarities)
-# tensor([[ 0.8868,  0.0210, -0.0103]])
+# tensor([[ 0.8449, -0.0204,  0.0232]])
 ```
 
 <!--
@@ -636,6 +636,10 @@ Query:
 | 0.0926 | 100  | 0.1737        |
 | 0.1389 | 150  | 0.1749        |
 | 0.1852 | 200  | 0.1664        |
+| 0.2315 | 250  | 0.1471        |
+| 0.2778 | 300  | 0.1344        |
+| 0.3241 | 350  | 0.1342        |
+| 0.3704 | 400  | 0.1257        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f05b2ecf6c21e4e22e8d86f7d6cdfd66d3c24140fb5da41e4e6fddf88f53062
+oid sha256:3c6681aa8630cad7142f0907d83e521db38cea6aa7b53cd42d32b0b04a7ecef5
 size 2383139480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975fcf4229f439cb652012750fa7242ec08caec72e4b15e47bb0421c42c2d65a
+oid sha256:50b89571c4a0ed55a7af630658c6fb1da97cfda3b1452712577eddaec31a1146
 size 4766477350

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce8ab349effd1adbb6d4237116520cacfb57476eecc98810f044e89e9743cd6
+oid sha256:ded0c2b7e651137c24c13f7215b8be6b6de571e67fd433bf0b03a5d0808823e5
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18518518518518517,
+  "epoch": 0.37037037037037035,
   "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": 4.531893004115226e-05,
       "loss": 0.1664,
       "step": 200
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.235687017440796,
+      "learning_rate": 4.2746913580246915e-05,
+      "loss": 0.1471,
+      "step": 250
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.7896230220794678,
+      "learning_rate": 4.017489711934157e-05,
+      "loss": 0.1344,
+      "step": 300
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 1.2573087215423584,
+      "learning_rate": 3.760288065843622e-05,
+      "loss": 0.1342,
+      "step": 350
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.3279838562011719,
+      "learning_rate": 3.503086419753087e-05,
+      "loss": 0.1257,
+      "step": 400
     }
   ],
   "logging_steps": 50,