Push model using huggingface_hub.

README.md

@@ -109,12 +109,13 @@ preds = model("Have a good day!")
 | 1     | 116                   |
 
 ### Training Hyperparameters
-- batch_size: (32, 32)
-- num_epochs: (2, 2)
+- batch_size: (16, 16)
+- num_epochs: (1, 1)
 - max_steps: -1
 - sampling_strategy: oversampling
-- body_learning_rate: (2e-05, 1e-05)
-- head_learning_rate: 0.01
+- num_iterations: 20
+- body_learning_rate: (2e-05, 2e-05)
+- head_learning_rate: 2e-05
 - loss: CosineSimilarityLoss
 - distance_metric: cosine_distance
 - margin: 0.25
@@ -123,9 +124,8 @@ preds = model("Have a good day!")
 - warmup_proportion: 0.1
 - l2_weight: 0.01
 - seed: 42
-- evaluation_strategy: epoch
 - eval_max_steps: -1
-- load_best_model_at_end: True
+- load_best_model_at_end: False
 
 ### Training Results
 | Epoch  | Step | Training Loss | Validation Loss |
@@ -133,6 +133,19 @@ preds = model("Have a good day!")
 | 0.0009 | 1    | 0.3528        | -               |
 | 1.0    | 1068 | 0.0252        | 0.0729          |
 | 2.0    | 2136 | 0.0001        | 0.0544          |
+| 0.0015 | 1    | 0.0           | -               |
+| 0.0772 | 50   | 0.001         | -               |
+| 0.1543 | 100  | 0.0           | -               |
+| 0.2315 | 150  | 0.0           | -               |
+| 0.3086 | 200  | 0.0           | -               |
+| 0.3858 | 250  | 0.0015        | -               |
+| 0.4630 | 300  | 0.001         | -               |
+| 0.5401 | 350  | 0.0           | -               |
+| 0.6173 | 400  | 0.0           | -               |
+| 0.6944 | 450  | 0.0           | -               |
+| 0.7716 | 500  | 0.0           | -               |
+| 0.8488 | 550  | 0.0           | -               |
+| 0.9259 | 600  | 0.0           | -               |
 
 ### Framework Versions
 - Python: 3.10.12

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c585131f91604902b6cf8a0b77bff2c1912a3d15e27a66ed9b4bad65ecfc6f9
+oid sha256:54f3c99a0285cbcae6e28b4efd74e0bc16c3464208d28b24982dadb693780bd3
 size 98453640

model_head.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f78e0957f07ef79eed134c650e6e7ab56b1b76e734aa092b984d17db0a8ddd
+oid sha256:4761c7f1047edcbea61dab5f490686b765a055af9c42336c6b54f555de2a4da1
 size 5611

tokenizer.json

@@ -7,9 +7,7 @@
     "stride": 0
   },
   "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,