Training in progress, step 600, 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([[ 0.8449, -0.0204,  0.0232]])
+# tensor([[ 0.8485,  0.0267, -0.0033]])
 ```
 
 <!--
@@ -640,6 +640,10 @@ Query:
 | 0.2778 | 300  | 0.1344        |
 | 0.3241 | 350  | 0.1342        |
 | 0.3704 | 400  | 0.1257        |
+| 0.4167 | 450  | 0.1289        |
+| 0.4630 | 500  | 0.1096        |
+| 0.5093 | 550  | 0.1065        |
+| 0.5556 | 600  | 0.0995        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6681aa8630cad7142f0907d83e521db38cea6aa7b53cd42d32b0b04a7ecef5
+oid sha256:9b15a40b80e34149141a4af2f12f9b615310f676cd261da7d8056fad0358de6f
 size 2383139480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b89571c4a0ed55a7af630658c6fb1da97cfda3b1452712577eddaec31a1146
+oid sha256:eb93723bcc1c156cdbdabc33bc0cefc3e311f3ef2ea25a7089300cea7d8017b4
 size 4766477350

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded0c2b7e651137c24c13f7215b8be6b6de571e67fd433bf0b03a5d0808823e5
+oid sha256:53450fd31baea826198572e11ab296f59633f54090c51d1df33de7136a72f847
 size 1064

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": 0.1257,
       "step": 400
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 1.5447418689727783,
+      "learning_rate": 3.245884773662551e-05,
+      "loss": 0.1289,
+      "step": 450
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 1.405887484550476,
+      "learning_rate": 2.9886831275720166e-05,
+      "loss": 0.1096,
+      "step": 500
+    },
+    {
+      "epoch": 0.5092592592592593,
+      "grad_norm": 1.608939528465271,
+      "learning_rate": 2.7314814814814816e-05,
+      "loss": 0.1065,
+      "step": 550
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 1.4359056949615479,
+      "learning_rate": 2.4742798353909465e-05,
+      "loss": 0.0995,
+      "step": 600
     }
   ],
   "logging_steps": 50,