Training in progress, step 1000, 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,  0.5419, -0.0536],
-#         [ 0.5419,  1.0000, -0.0603],
-#         [-0.0536, -0.0603,  1.0000]])
+# tensor([[ 1.0000,  0.5433, -0.0509],
+#         [ 0.5433,  1.0000, -0.0602],
+#         [-0.0509, -0.0602,  1.0000]])
 ```
 
 <!--
@@ -692,6 +692,10 @@ You can finetune this model on your own dataset.
 | 0.3557 | 700  | 0.4942        |
 | 0.3811 | 750  | 0.4981        |
 | 0.4065 | 800  | 0.4983        |
+| 0.4319 | 850  | 0.4882        |
+| 0.4573 | 900  | 0.4869        |
+| 0.4827 | 950  | 0.4898        |
+| 0.5081 | 1000 | 0.501         |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83389a56acb41d0a1917c61a6404affa2f39e3aea8c2d79163946b220cb15ea
+oid sha256:e2e1e9d5eff6c41809cc50c6c706e397f17bdefc78c905246322008dcb6296db
 size 45437864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c5ce4a9c10d4eddde5fcecaa6f889d2244e95913f07ab978ddb77e2cd0092b
+oid sha256:5dcbdfcd46b4c04eb85077625bdbae7131e652ba94a811efcd17b9990ba6743b
 size 90346763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f142a1fe70eca00a55d0386edee20a5cc0cc4371069ed8cc8489431723b0160c
+oid sha256:dffc0ceb65e8c69d366f764cae9f9d5143c5e98038853351451b525757197063
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cf700515bb029e36ca46412b96b02750cd1dce66cb44278ee1c691b7d1aa79
+oid sha256:ab6c56263d0a3d675d4f747bb77db752789302abc7e0c5864efa40f605c0194a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4065040650406504,
+  "epoch": 0.508130081300813,
   "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": 3.300395256916996e-05,
       "loss": 0.4983,
       "step": 800
+    },
+    {
+      "epoch": 0.43191056910569103,
+      "grad_norm": 2.046875,
+      "learning_rate": 3.159232072275551e-05,
+      "loss": 0.4882,
+      "step": 850
+    },
+    {
+      "epoch": 0.4573170731707317,
+      "grad_norm": 1.7890625,
+      "learning_rate": 3.018068887634105e-05,
+      "loss": 0.4869,
+      "step": 900
+    },
+    {
+      "epoch": 0.48272357723577236,
+      "grad_norm": 1.9375,
+      "learning_rate": 2.8769057029926593e-05,
+      "loss": 0.4898,
+      "step": 950
+    },
+    {
+      "epoch": 0.508130081300813,
+      "grad_norm": 1.7265625,
+      "learning_rate": 2.7357425183512143e-05,
+      "loss": 0.501,
+      "step": 1000
     }
   ],
   "logging_steps": 50,