Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/bert_uncased_L-4_H-128_A-2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_uncased_L-4_H-128_A-2_sst2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert_uncased_L-4_H-128_A-2_sst2
+
+This model is a fine-tuned version of [google/bert_uncased_L-4_H-128_A-2](https://huggingface.co/google/bert_uncased_L-4_H-128_A-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4869
+- Accuracy: 0.8222
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 10
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.497         | 1.0   | 264  | 0.4757          | 0.7787   |
+| 0.3535        | 2.0   | 528  | 0.4270          | 0.8108   |
+| 0.2951        | 3.0   | 792  | 0.4281          | 0.8211   |
+| 0.2539        | 4.0   | 1056 | 0.4254          | 0.8131   |
+| 0.2259        | 5.0   | 1320 | 0.4344          | 0.8257   |
+| 0.2048        | 6.0   | 1584 | 0.4487          | 0.8314   |
+| 0.1892        | 7.0   | 1848 | 0.4820          | 0.8222   |
+| 0.1754        | 8.0   | 2112 | 0.4954          | 0.8349   |
+| 0.1643        | 9.0   | 2376 | 0.4869          | 0.8222   |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.2.1+cu118
+- Datasets 2.17.0
+- Tokenizers 0.20.3

logs/events.out.tfevents.1733338504.ki-g0008.1764072.28

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21899e539af91f926c695762380ed87d48528cbd91db00c9f450f09ce2e75f3f
-size 9381
+oid sha256:533689483a6e3685412de300485fe2ad0adde284731013d8234372f436eadfcb
+size 10269

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a25485c41c66b3cbcc5a29f54d3cb5ba62332fb58c25bf76d408c0f0117e28
+oid sha256:97c5f3b0e5ceecca33e22518d9ae99d41b00f52b0d7d177cfa51a8e69e5ca09d
 size 19139184