Training in progress, step 1200, checkpoint

last-checkpoint/README.md

@@ -286,9 +286,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.5961, 0.1032],
-#         [0.5961, 1.0000, 0.1553],
-#         [0.1032, 0.1553, 1.0000]])
+# tensor([[1.0000, 0.6149, 0.1330],
+#         [0.6149, 1.0000, 0.1618],
+#         [0.1330, 0.1618, 1.0000]])
 ```
 
 <!--
@@ -1244,6 +1244,10 @@ You can finetune this model on your own dataset.
 | 0.0159 | 900  | 0.6899        |
 | 0.0168 | 950  | 0.6655        |
 | 0.0177 | 1000 | 0.6601        |
+| 0.0186 | 1050 | 0.6925        |
+| 0.0194 | 1100 | 0.6169        |
+| 0.0203 | 1150 | 0.6367        |
+| 0.0212 | 1200 | 0.615         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897e48ca4a1b0c79cf2429b6ef4ca73b309f3c5bcc06ba0c170b921c50590ea0
+oid sha256:a9a3361ca69436d4dea95cdcd29cea53aad0e253053cdc5876ca978a2c32a909
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5b75bdfd9f13b9fd5af71157d29fb1f2150a495f511bd4c3ae1ede089c6f6e
+oid sha256:7762e45714247d845b98566f70065d2e826d2dad86f6f5a0df3a0f6e4cc3e852
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435c96c122df13db75824be5f8aff8593c48e01c0d3f8f0275499435e34f1b52
+oid sha256:92073e2121fa1a50d2393b4b193256ae067f8269c786bb12674760941abf850b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:18783150ac09b6b81cea5af47876a10bfe5f36c3d76aca4ffce5382bdfaf7b28
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb73f8c20bf0b1f8fb2141f8979207ef099f052597bee612ca21a5ed63b4554
+oid sha256:8ed3eff7033631ee9ecca3bfddfbb19428dfe42f7f70d962500698dee83c17e2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01767065434433037,
+  "epoch": 0.021204785213196443,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,34 @@
       "learning_rate": 8.825088339222614e-06,
       "loss": 0.6601,
       "step": 1000
+    },
+    {
+      "epoch": 0.01855418706154689,
+      "grad_norm": 4.492621898651123,
+      "learning_rate": 9.26678445229682e-06,
+      "loss": 0.6925,
+      "step": 1050
+    },
+    {
+      "epoch": 0.019437719778763407,
+      "grad_norm": 3.8099517822265625,
+      "learning_rate": 9.708480565371025e-06,
+      "loss": 0.6169,
+      "step": 1100
+    },
+    {
+      "epoch": 0.020321252495979925,
+      "grad_norm": 4.58193826675415,
+      "learning_rate": 1.0150176678445231e-05,
+      "loss": 0.6367,
+      "step": 1150
+    },
+    {
+      "epoch": 0.021204785213196443,
+      "grad_norm": 4.745123863220215,
+      "learning_rate": 1.0591872791519434e-05,
+      "loss": 0.615,
+      "step": 1200
     }
   ],
   "logging_steps": 50,