Holmeister
commited on
Commit
•
1e3fb02
1
Parent(s):
38f919c
End of training
Browse files- README.md +85 -0
- config.json +32 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- predictions.csv +0 -0
- results.json +1 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: boun-tabi-LMG/TURNA
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- rouge
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: TURNA_spell_correction_product_search
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# TURNA_spell_correction_product_search
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [boun-tabi-LMG/TURNA](https://huggingface.co/boun-tabi-LMG/TURNA) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.1088
|
22 |
+
- Rouge1: 0.8437
|
23 |
+
- Rouge2: 0.7401
|
24 |
+
- Rougel: 0.8435
|
25 |
+
- Rougelsum: 0.8437
|
26 |
+
- Bleu: 0.8713
|
27 |
+
- Precisions: [0.8736109932988378, 0.8306083370157608, 0.8473118279569892, 0.9631336405529954]
|
28 |
+
- Brevity Penalty: 0.9932
|
29 |
+
- Length Ratio: 0.9933
|
30 |
+
- Translation Length: 11789
|
31 |
+
- Reference Length: 11869
|
32 |
+
- Meteor: 0.7484
|
33 |
+
- Score: 14.6658
|
34 |
+
- Num Edits: 1709
|
35 |
+
- Ref Length: 11653.0
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 64
|
56 |
+
- eval_batch_size: 64
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 5
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Meteor | Score | Num Edits | Ref Length |
|
65 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:-------:|:---------:|:----------:|
|
66 |
+
| No log | 0.3335 | 1253 | 0.2447 | 0.7099 | 0.5537 | 0.7097 | 0.7097 | 0.7033 | [0.7548184082863512, 0.6378386771213415, 0.6301176470588236, 0.906832298136646] | 0.9711 | 0.9715 | 22881 | 23553 | 0.5852 | 27.8452 | 6474 | 23250.0 |
|
67 |
+
| No log | 0.6670 | 2506 | 0.1886 | 0.7586 | 0.6231 | 0.7584 | 0.7585 | 0.7555 | [0.7995148154565933, 0.7114032405992051, 0.7142528735632184, 0.8698224852071006] | 0.9799 | 0.9801 | 23084 | 23553 | 0.6454 | 22.8860 | 5321 | 23250.0 |
|
68 |
+
| 0.3827 | 1.0005 | 3759 | 0.1571 | 0.7810 | 0.6561 | 0.7807 | 0.7809 | 0.7947 | [0.8183424557169332, 0.7418011058092858, 0.7430269775948788, 0.939297124600639] | 0.9850 | 0.9851 | 23203 | 23553 | 0.6742 | 20.6710 | 4806 | 23250.0 |
|
69 |
+
| 0.3827 | 1.3340 | 5012 | 0.1458 | 0.7973 | 0.6822 | 0.7973 | 0.7974 | 0.8139 | [0.8318891557995882, 0.7666015625, 0.7682954289574421, 0.9333333333333333] | 0.9897 | 0.9898 | 23312 | 23553 | 0.6955 | 19.1441 | 4451 | 23250.0 |
|
70 |
+
| 0.3827 | 1.6676 | 6265 | 0.1320 | 0.8109 | 0.6993 | 0.8107 | 0.8111 | 0.8294 | [0.8467426359922597, 0.7889852885703508, 0.788783355947535, 0.9453376205787781] | 0.9873 | 0.9873 | 23255 | 23553 | 0.7111 | 17.6258 | 4098 | 23250.0 |
|
71 |
+
| 0.1238 | 2.0011 | 7518 | 0.1218 | 0.8205 | 0.7139 | 0.8205 | 0.8206 | 0.8462 | [0.8559577028885832, 0.8045084439083233, 0.8144353369763205, 0.9607843137254902] | 0.9877 | 0.9877 | 23264 | 23553 | 0.7231 | 16.5720 | 3853 | 23250.0 |
|
72 |
+
| 0.1238 | 2.3346 | 8771 | 0.1223 | 0.8246 | 0.7219 | 0.8247 | 0.8249 | 0.8506 | [0.8575583882282488, 0.8074450590521752, 0.8080267558528428, 0.9639344262295082] | 0.9925 | 0.9926 | 23378 | 23553 | 0.7298 | 16.1978 | 3766 | 23250.0 |
|
73 |
+
| 0.1238 | 2.6681 | 10024 | 0.1177 | 0.8319 | 0.7326 | 0.8320 | 0.8321 | 0.8580 | [0.8628791114908159, 0.8155853840417598, 0.8160765976397238, 0.9671052631578947] | 0.9939 | 0.9939 | 23410 | 23553 | 0.7379 | 15.6602 | 3641 | 23250.0 |
|
74 |
+
| 0.0686 | 3.0016 | 11277 | 0.1122 | 0.8388 | 0.7400 | 0.8391 | 0.8391 | 0.8623 | [0.8686514886164624, 0.8236522257848036, 0.8239625167336011, 0.9607843137254902] | 0.9940 | 0.9940 | 23411 | 23553 | 0.7462 | 15.0237 | 3493 | 23250.0 |
|
75 |
+
| 0.0686 | 3.3351 | 12530 | 0.1184 | 0.8398 | 0.7450 | 0.8397 | 0.8398 | 0.8682 | [0.8676339190741608, 0.8243353328889876, 0.8229854689564069, 0.9735099337748344] | 0.9979 | 0.9979 | 23503 | 23553 | 0.7488 | 14.9677 | 3480 | 23250.0 |
|
76 |
+
| 0.0686 | 3.6686 | 13783 | 0.1148 | 0.8440 | 0.7484 | 0.8441 | 0.8442 | 0.8716 | [0.8706277359853798, 0.8271121294995935, 0.826640333552776, 0.9735099337748344] | 0.9990 | 0.9990 | 23529 | 23553 | 0.7533 | 14.5806 | 3390 | 23250.0 |
|
77 |
+
| 0.0383 | 4.0021 | 15036 | 0.1134 | 0.8498 | 0.7547 | 0.8498 | 0.8500 | 0.8750 | [0.8757069354084279, 0.8344307168750462, 0.8344676180021954, 0.9671052631578947] | 0.9985 | 0.9985 | 23517 | 23553 | 0.7592 | 14.0516 | 3267 | 23250.0 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.41.2
|
83 |
+
- Pytorch 2.3.1+cu121
|
84 |
+
- Datasets 2.19.2
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "boun-tabi-LMG/TURNA",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 36,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 36,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.41.2",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32128
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"max_length": 15,
|
5 |
+
"max_new_tokens": 15,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.41.2"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1feb0bcba0decc1a0e502287cb47c73d3cf1f71e1cf200d04ca70cfe28921bf
|
3 |
+
size 4567400768
|
predictions.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eval_loss": 0.10884405672550201, "eval_rouge1": 0.8436920401820391, "eval_rouge2": 0.740059379509379, "eval_rougeL": 0.8435349805749799, "eval_rougeLsum": 0.843733527028526, "eval_bleu": 0.8712924137776715, "eval_precisions": [0.8736109932988378, 0.8306083370157608, 0.8473118279569892, 0.9631336405529954], "eval_brevity_penalty": 0.993236985878598, "eval_length_ratio": 0.9932597522958969, "eval_translation_length": 11789, "eval_reference_length": 11869, "eval_meteor": 0.7484335454321046, "eval_score": 14.665751308675878, "eval_num_edits": 1709, "eval_ref_length": 11653.0, "eval_runtime": 51.3593, "eval_samples_per_second": 97.353, "eval_steps_per_second": 1.538, "epoch": 4.002129358530743}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d359e087330a6e1e0e3f6eba9cec36a6fe4fc5cb9a8dbd5d8fd803432c8e60c2
|
3 |
+
size 7032
|