Training in progress, step 1000, checkpoint

last-checkpoint/README.md

@@ -418,9 +418,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[    1.0000,     0.8238,     0.0007],
-#         [    0.8238,     1.0000,     0.0379],
-#         [    0.0007,     0.0379,     1.0000]])
+# tensor([[1.0000, 0.8345, 0.0036],
+#         [0.8345, 1.0000, 0.0463],
+#         [0.0036, 0.0463, 1.0000]])
 ```
 
 <!--
@@ -641,6 +641,10 @@ You can finetune this model on your own dataset.
 | 0.6481 | 700  | 0.2233        |
 | 0.6944 | 750  | 0.2239        |
 | 0.7407 | 800  | 0.2107        |
+| 0.7870 | 850  | 0.2205        |
+| 0.8333 | 900  | 0.2087        |
+| 0.8796 | 950  | 0.2129        |
+| 0.9259 | 1000 | 0.2103        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56ae000ad3df8b9ddbc58f562eabbf1eb1c4635d3298efe2688ce7e1f3939c5
+oid sha256:9e6982a03a13069dbd7b223ad85adad16126456dd21e17f9bd1ae85ca8193120
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbb6df4b0c6b1eeabf081b1e19d2abd93a909d4231185afdbaccb35c459fc1c
+oid sha256:c2d233c33a97447e6a9abb3c8e8e512eb8909f5d83f758b39d62a45a2af03c91
 size 180608203

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b66082d265e60bf5570bafb6654a76e495fb2c00d97a2e2d702d4cef23c098
+oid sha256:f1372d08aae4c539a42dc762c4bad69d2ee0d24aad936d7a04cbe426c002b491
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fef122931c86c2d2736773be787da21ac6460d41580735381e953556fb410be
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad211f85f7952dd56f43d381e1780d6a978df68441ca57ba5688f4ef0c8d4b7
+oid sha256:71506dd75ffea4620eca46bea4d3e2da666baa9d78fa9907096978fc32ffdb98
 size 1465

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": 0.2107,
       "step": 800
+    },
+    {
+      "epoch": 0.7870370370370371,
+      "grad_norm": 1.1493163108825684,
+      "learning_rate": 1.1882716049382716e-05,
+      "loss": 0.2205,
+      "step": 850
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.197800636291504,
+      "learning_rate": 9.310699588477368e-06,
+      "loss": 0.2087,
+      "step": 900
+    },
+    {
+      "epoch": 0.8796296296296297,
+      "grad_norm": 1.2553362846374512,
+      "learning_rate": 6.7386831275720164e-06,
+      "loss": 0.2129,
+      "step": 950
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 1.1241569519042969,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.2103,
+      "step": 1000
     }
   ],
   "logging_steps": 50,