Training in progress, step 1000, 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, 0.5922, 0.0910],
-#         [0.5922, 1.0000, 0.1485],
-#         [0.0910, 0.1485, 1.0000]])
+# tensor([[1.0000, 0.5961, 0.1032],
+#         [0.5961, 1.0000, 0.1553],
+#         [0.1032, 0.1553, 1.0000]])
 ```
 
 <!--
@@ -1240,6 +1240,10 @@ You can finetune this model on your own dataset.
 | 0.0124 | 700  | 0.7701        |
 | 0.0133 | 750  | 0.7525        |
 | 0.0141 | 800  | 0.7097        |
+| 0.0150 | 850  | 0.7575        |
+| 0.0159 | 900  | 0.6899        |
+| 0.0168 | 950  | 0.6655        |
+| 0.0177 | 1000 | 0.6601        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edf45758f8655b39949040bb376942e3eaf9cabfbd997bdd27d281a59e48fd7
+oid sha256:897e48ca4a1b0c79cf2429b6ef4ca73b309f3c5bcc06ba0c170b921c50590ea0
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b860245e653a414010bafe2c3c8174c59f95411463e02d1f20aed248e44dc779
+oid sha256:4b5b75bdfd9f13b9fd5af71157d29fb1f2150a495f511bd4c3ae1ede089c6f6e
 size 180609611

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6604fa50a947bb7a8c4e40ff3e2a5641ad506d5aa6a161b0cd0a5fa0c1d78ee8
+oid sha256:435c96c122df13db75824be5f8aff8593c48e01c0d3f8f0275499435e34f1b52
 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 sha256:8ec1539c27d7283f1e5aca2a0dde35cb977a77f34c850320b82d506a15f4bbbb
+oid sha256:dfb73f8c20bf0b1f8fb2141f8979207ef099f052597bee612ca21a5ed63b4554
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014136523475464296,
+  "epoch": 0.01767065434433037,
   "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": 7.058303886925795e-06,
       "loss": 0.7097,
       "step": 800
+    },
+    {
+      "epoch": 0.015020056192680814,
+      "grad_norm": 3.297929286956787,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7575,
+      "step": 850
+    },
+    {
+      "epoch": 0.015903588909897334,
+      "grad_norm": 4.028406143188477,
+      "learning_rate": 7.941696113074205e-06,
+      "loss": 0.6899,
+      "step": 900
+    },
+    {
+      "epoch": 0.016787121627113853,
+      "grad_norm": 2.2513041496276855,
+      "learning_rate": 8.38339222614841e-06,
+      "loss": 0.6655,
+      "step": 950
+    },
+    {
+      "epoch": 0.01767065434433037,
+      "grad_norm": 2.402355670928955,
+      "learning_rate": 8.825088339222614e-06,
+      "loss": 0.6601,
+      "step": 1000
     }
   ],
   "logging_steps": 50,