Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_10_v1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_rand_10_v1_mnli
+  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. -->
+
+# tiny_bert_rand_10_v1_mnli
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v1](https://huggingface.co/Hartunka/tiny_bert_rand_10_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9181
+- Accuracy: 0.6486
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9909        | 1.0   | 1534  | 0.9389          | 0.5459   |
+| 0.9076        | 2.0   | 3068  | 0.8835          | 0.5857   |
+| 0.8477        | 3.0   | 4602  | 0.8486          | 0.6207   |
+| 0.7883        | 4.0   | 6136  | 0.8233          | 0.6344   |
+| 0.7357        | 5.0   | 7670  | 0.8027          | 0.6485   |
+| 0.6888        | 6.0   | 9204  | 0.8329          | 0.6493   |
+| 0.6483        | 7.0   | 10738 | 0.8231          | 0.6502   |
+| 0.6075        | 8.0   | 12272 | 0.8673          | 0.6528   |
+| 0.5713        | 9.0   | 13806 | 0.8915          | 0.6456   |
+| 0.5346        | 10.0  | 15340 | 0.9181          | 0.6486   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1744649999.s_005_m.2701049.88

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a1f6575f6fa0d8dbf8c76b640a8eb7c6dfda43c90b8ff9912c870f682bc0f3
-size 9899
+oid sha256:22910efb4ed1949aeb3e2ebb988d71a2b6348625867837b5da9e7a56b63fb1e9
+size 10787

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4377dabaaa85ac30a996f5ce90549949b4e3de4da9b128ce0316ed4b0d8831e9
+oid sha256:e207d45a6a8b532560d40cbe53be1eb19180dd770b389b2a9ccbfe3b3e297c53
 size 131858796