End of training
Browse files- README.md +92 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: bert-base-uncased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: BERT_BASE_TS_phonetic_wikitext_0.9
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# BERT_BASE_TS_phonetic_wikitext_0.9
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9809
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 256
|
| 40 |
+
- eval_batch_size: 256
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 10000
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 52 |
+
| 2.2165 | 0.3019 | 2000 | 2.0242 |
|
| 53 |
+
| 2.1139 | 0.6039 | 4000 | 1.9481 |
|
| 54 |
+
| 2.0879 | 0.9058 | 6000 | 1.9204 |
|
| 55 |
+
| 2.0837 | 1.2077 | 8000 | 1.9042 |
|
| 56 |
+
| 2.0957 | 1.5097 | 10000 | 1.9554 |
|
| 57 |
+
| 2.1007 | 1.8116 | 12000 | 1.9287 |
|
| 58 |
+
| 2.1026 | 2.1135 | 14000 | 1.9540 |
|
| 59 |
+
| 2.1126 | 2.4155 | 16000 | 1.9481 |
|
| 60 |
+
| 2.1171 | 2.7174 | 18000 | 1.9878 |
|
| 61 |
+
| 2.1176 | 3.0193 | 20000 | 1.9638 |
|
| 62 |
+
| 2.1232 | 3.3213 | 22000 | 1.9696 |
|
| 63 |
+
| 2.1223 | 3.6232 | 24000 | 1.9904 |
|
| 64 |
+
| 2.1294 | 3.9251 | 26000 | 1.9750 |
|
| 65 |
+
| 2.127 | 4.2271 | 28000 | 1.9654 |
|
| 66 |
+
| 2.1342 | 4.5290 | 30000 | 1.9801 |
|
| 67 |
+
| 2.1402 | 4.8309 | 32000 | 2.0290 |
|
| 68 |
+
| 2.1344 | 5.1329 | 34000 | 2.0142 |
|
| 69 |
+
| 2.1373 | 5.4348 | 36000 | 1.9839 |
|
| 70 |
+
| 2.1325 | 5.7367 | 38000 | 1.9736 |
|
| 71 |
+
| 2.1367 | 6.0386 | 40000 | 1.9824 |
|
| 72 |
+
| 2.1417 | 6.3406 | 42000 | 1.9750 |
|
| 73 |
+
| 2.1319 | 6.6425 | 44000 | 1.9775 |
|
| 74 |
+
| 2.1387 | 6.9444 | 46000 | 2.0075 |
|
| 75 |
+
| 2.1359 | 7.2464 | 48000 | 1.9740 |
|
| 76 |
+
| 2.1315 | 7.5483 | 50000 | 1.9844 |
|
| 77 |
+
| 2.1388 | 7.8502 | 52000 | 2.0143 |
|
| 78 |
+
| 2.1302 | 8.1522 | 54000 | 1.9690 |
|
| 79 |
+
| 2.1368 | 8.4541 | 56000 | 1.9659 |
|
| 80 |
+
| 2.1347 | 8.7560 | 58000 | 1.9806 |
|
| 81 |
+
| 2.1304 | 9.0580 | 60000 | 1.9906 |
|
| 82 |
+
| 2.1268 | 9.3599 | 62000 | 1.9820 |
|
| 83 |
+
| 2.1241 | 9.6618 | 64000 | 1.9683 |
|
| 84 |
+
| 2.1308 | 9.9638 | 66000 | 1.9809 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.45.1
|
| 90 |
+
- Pytorch 2.4.1+cu121
|
| 91 |
+
- Datasets 3.0.1
|
| 92 |
+
- Tokenizers 0.20.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_hidden_states": true,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"return_dict_in_generate": true,
|
| 6 |
+
"transformers_version": "4.45.1"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 438080896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00ef572023a40b180b6cabbecb35337a74dd6ae12c35aa75e3fec76053871253
|
| 3 |
size 438080896
|