Training in progress, step 600, checkpoint

last-checkpoint/README.md

@@ -466,9 +466,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[ 1.0000,  0.5340, -0.0489],
-#         [ 0.5340,  1.0000, -0.0623],
-#         [-0.0489, -0.0623,  1.0000]])
+# tensor([[ 1.0000,  0.5416, -0.0529],
+#         [ 0.5416,  1.0000, -0.0571],
+#         [-0.0529, -0.0571,  1.0000]])
 ```
 
 <!--
@@ -684,6 +684,10 @@ You can finetune this model on your own dataset.
 | 0.1524 | 300  | 0.5898        |
 | 0.1778 | 350  | 0.5569        |
 | 0.2033 | 400  | 0.5396        |
+| 0.2287 | 450  | 0.5298        |
+| 0.2541 | 500  | 0.5257        |
+| 0.2795 | 550  | 0.5151        |
+| 0.3049 | 600  | 0.5239        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebaadd7ca69549d21e0a9b5a198c58e5df0a12a58aa56635196f10c545d2363b
+oid sha256:db180de14ad34af5b594eb81db91a48a3f45d6d9dcd3f719d2c809d54b9b71a5
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a26a7a0f56cd6950e1e3ae0ec3c0412ad0bcebd9c3dfa88f2162b4a3e97528
+oid sha256:e101e09cac9abb18af92e11a5aad1671259c0532e03955910cff367b721b16d8
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865ec8a72ed85ad9518ab1ebb67049ddc164edcb9400bda4e9e54f2cabcece1
+oid sha256:4ee89ff3a386fc330c8001091c3d124cf617c5bfb2fe56bc351034ede547ca47
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc56140e5c37825482a26f377f07f74eaa4028a1b2f8b46eaa880f0215c9abf
+oid sha256:a7eb57b4b6586ca069ba10818f8421f503ffe2fcc4027df0b3bf8a2421cac2a7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2032520325203252,
+  "epoch": 0.3048780487804878,
   "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": 4.42970073404856e-05,
       "loss": 0.5396,
       "step": 400
+    },
+    {
+      "epoch": 0.22865853658536586,
+      "grad_norm": 1.796875,
+      "learning_rate": 4.288537549407115e-05,
+      "loss": 0.5298,
+      "step": 450
+    },
+    {
+      "epoch": 0.2540650406504065,
+      "grad_norm": 1.859375,
+      "learning_rate": 4.147374364765669e-05,
+      "loss": 0.5257,
+      "step": 500
+    },
+    {
+      "epoch": 0.27947154471544716,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.006211180124224e-05,
+      "loss": 0.5151,
+      "step": 550
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "grad_norm": 1.828125,
+      "learning_rate": 3.8650479954827784e-05,
+      "loss": 0.5239,
+      "step": 600
     }
   ],
   "logging_steps": 50,