Training in progress, step 800, 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,  0.5416, -0.0529],
-#         [ 0.5416,  1.0000, -0.0571],
-#         [-0.0529, -0.0571,  1.0000]])
+# tensor([[ 1.0000,  0.5419, -0.0536],
+#         [ 0.5419,  1.0000, -0.0603],
+#         [-0.0536, -0.0603,  1.0000]])
 ```
 
 <!--
@@ -688,6 +688,10 @@ You can finetune this model on your own dataset.
 | 0.2541 | 500  | 0.5257        |
 | 0.2795 | 550  | 0.5151        |
 | 0.3049 | 600  | 0.5239        |
+| 0.3303 | 650  | 0.5169        |
+| 0.3557 | 700  | 0.4942        |
+| 0.3811 | 750  | 0.4981        |
+| 0.4065 | 800  | 0.4983        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db180de14ad34af5b594eb81db91a48a3f45d6d9dcd3f719d2c809d54b9b71a5
+oid sha256:c83389a56acb41d0a1917c61a6404affa2f39e3aea8c2d79163946b220cb15ea
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e101e09cac9abb18af92e11a5aad1671259c0532e03955910cff367b721b16d8
+oid sha256:d7c5ce4a9c10d4eddde5fcecaa6f889d2244e95913f07ab978ddb77e2cd0092b
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee89ff3a386fc330c8001091c3d124cf617c5bfb2fe56bc351034ede547ca47
+oid sha256:f142a1fe70eca00a55d0386edee20a5cc0cc4371069ed8cc8489431723b0160c
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7eb57b4b6586ca069ba10818f8421f503ffe2fcc4027df0b3bf8a2421cac2a7
+oid sha256:79cf700515bb029e36ca46412b96b02750cd1dce66cb44278ee1c691b7d1aa79
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3048780487804878,
+  "epoch": 0.4065040650406504,
   "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": 3.8650479954827784e-05,
       "loss": 0.5239,
       "step": 600
+    },
+    {
+      "epoch": 0.33028455284552843,
+      "grad_norm": 1.8828125,
+      "learning_rate": 3.7238848108413324e-05,
+      "loss": 0.5169,
+      "step": 650
+    },
+    {
+      "epoch": 0.3556910569105691,
+      "grad_norm": 1.8359375,
+      "learning_rate": 3.5827216261998877e-05,
+      "loss": 0.4942,
+      "step": 700
+    },
+    {
+      "epoch": 0.38109756097560976,
+      "grad_norm": 1.9921875,
+      "learning_rate": 3.4415584415584416e-05,
+      "loss": 0.4981,
+      "step": 750
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 1.7578125,
+      "learning_rate": 3.300395256916996e-05,
+      "loss": 0.4983,
+      "step": 800
     }
   ],
   "logging_steps": 50,