Training in progress, step 800, 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([[ 0.8485,  0.0267, -0.0033]])
+# tensor([[ 0.8944,  0.0180, -0.0196]])
 ```
 
 <!--
@@ -644,6 +644,10 @@ Query:
 | 0.4630 | 500  | 0.1096        |
 | 0.5093 | 550  | 0.1065        |
 | 0.5556 | 600  | 0.0995        |
+| 0.6019 | 650  | 0.1042        |
+| 0.6481 | 700  | 0.1018        |
+| 0.6944 | 750  | 0.0992        |
+| 0.7407 | 800  | 0.0924        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b15a40b80e34149141a4af2f12f9b615310f676cd261da7d8056fad0358de6f
+oid sha256:07956077330ee7f6fb360a1cd17ccf50211080eebd155e6b363392fe384374aa
 size 2383139480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb93723bcc1c156cdbdabc33bc0cefc3e311f3ef2ea25a7089300cea7d8017b4
+oid sha256:774d8cf0bc4b7d95fc6b9de709258429b86ff70a9f6b6426eb1e7bb9a64532e1
 size 4766477350

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53450fd31baea826198572e11ab296f59633f54090c51d1df33de7136a72f847
+oid sha256:1cfdc638aa6aa3071d5018c01d2f29e2de986d8bf74fea34b8e3b76afa8622ba
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5555555555555556,
+  "epoch": 0.7407407407407407,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,34 @@
       "learning_rate": 2.4742798353909465e-05,
       "loss": 0.0995,
       "step": 600
+    },
+    {
+      "epoch": 0.6018518518518519,
+      "grad_norm": 1.5060992240905762,
+      "learning_rate": 2.2170781893004118e-05,
+      "loss": 0.1042,
+      "step": 650
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 1.104844570159912,
+      "learning_rate": 1.9598765432098768e-05,
+      "loss": 0.1018,
+      "step": 700
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 1.426213264465332,
+      "learning_rate": 1.7026748971193414e-05,
+      "loss": 0.0992,
+      "step": 750
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.1723966598510742,
+      "learning_rate": 1.4454732510288065e-05,
+      "loss": 0.0924,
+      "step": 800
     }
   ],
   "logging_steps": 50,