Training in progress, step 1000, 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([[ 0.8944,  0.0180, -0.0196]])
+# tensor([[ 0.8672, -0.0147, -0.0254]])
 ```
 
 <!--
@@ -648,6 +648,10 @@ Query:
 | 0.6481 | 700  | 0.1018        |
 | 0.6944 | 750  | 0.0992        |
 | 0.7407 | 800  | 0.0924        |
+| 0.7870 | 850  | 0.0909        |
+| 0.8333 | 900  | 0.0847        |
+| 0.8796 | 950  | 0.0914        |
+| 0.9259 | 1000 | 0.0847        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07956077330ee7f6fb360a1cd17ccf50211080eebd155e6b363392fe384374aa
+oid sha256:3c33d61cffa33493edbadf676b157d37c41cb3a5c5fca7f920f1ccd505300f22
 size 2383139480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774d8cf0bc4b7d95fc6b9de709258429b86ff70a9f6b6426eb1e7bb9a64532e1
+oid sha256:84db4700a8bb0936e936db6653a4d4281969c72265e40f14c5ac9720efe3b617
 size 4766477350

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfdc638aa6aa3071d5018c01d2f29e2de986d8bf74fea34b8e3b76afa8622ba
+oid sha256:a16c8942124de0a7ec965a9112f2b847966689d0d650d6ff8cc8f1b2761c8b2a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7407407407407407,
+  "epoch": 0.9259259259259259,
   "eval_steps": 500,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,34 @@
       "learning_rate": 1.4454732510288065e-05,
       "loss": 0.0924,
       "step": 800
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 1.134878158569336,
+      "learning_rate": 1.1882716049382716e-05,
+      "loss": 0.0909,
+      "step": 850
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.0749645233154297,
+      "learning_rate": 9.310699588477368e-06,
+      "loss": 0.0847,
+      "step": 900
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 1.171762228012085,
+      "learning_rate": 6.7386831275720164e-06,
+      "loss": 0.0914,
+      "step": 950
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 1.245627522468567,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0847,
+      "step": 1000
     }
   ],
   "logging_steps": 50,