akk-en-mt5-base
Browse files- .DS_Store +0 -0
- README.md +131 -0
- added_tokens.json +0 -0
- config.json +33 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
README.md
ADDED
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/mt5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: mt5-base-p-l-akk-en-20240709-215100
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# mt5-base-p-l-akk-en-20240709-215100
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.1533
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 4e-05
|
38 |
+
- train_batch_size: 12
|
39 |
+
- eval_batch_size: 12
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 10
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
49 |
+
| 30.893 | 0.1326 | 500 | 5.1945 |
|
50 |
+
| 2.9823 | 0.2651 | 1000 | 0.6672 |
|
51 |
+
| 0.6668 | 0.3977 | 1500 | 0.5089 |
|
52 |
+
| 0.4944 | 0.5302 | 2000 | 0.3100 |
|
53 |
+
| 0.3002 | 0.6628 | 2500 | 0.2663 |
|
54 |
+
| 0.2813 | 0.7953 | 3000 | 0.2493 |
|
55 |
+
| 0.273 | 0.9279 | 3500 | 0.2369 |
|
56 |
+
| 0.2544 | 1.0604 | 4000 | 0.2304 |
|
57 |
+
| 0.2445 | 1.1930 | 4500 | 0.2241 |
|
58 |
+
| 0.2365 | 1.3256 | 5000 | 0.2190 |
|
59 |
+
| 0.2305 | 1.4581 | 5500 | 0.2140 |
|
60 |
+
| 0.2318 | 1.5907 | 6000 | 0.2108 |
|
61 |
+
| 0.2166 | 1.7232 | 6500 | 0.2060 |
|
62 |
+
| 0.2195 | 1.8558 | 7000 | 0.2029 |
|
63 |
+
| 0.2125 | 1.9883 | 7500 | 0.2000 |
|
64 |
+
| 0.2091 | 2.1209 | 8000 | 0.1963 |
|
65 |
+
| 0.2092 | 2.2534 | 8500 | 0.1938 |
|
66 |
+
| 0.2032 | 2.3860 | 9000 | 0.1915 |
|
67 |
+
| 0.2018 | 2.5186 | 9500 | 0.1892 |
|
68 |
+
| 0.2017 | 2.6511 | 10000 | 0.1870 |
|
69 |
+
| 0.1961 | 2.7837 | 10500 | 0.1855 |
|
70 |
+
| 0.2009 | 2.9162 | 11000 | 0.1841 |
|
71 |
+
| 0.1956 | 3.0488 | 11500 | 0.1828 |
|
72 |
+
| 0.1915 | 3.1813 | 12000 | 0.1807 |
|
73 |
+
| 0.1892 | 3.3139 | 12500 | 0.1790 |
|
74 |
+
| 0.1908 | 3.4464 | 13000 | 0.1773 |
|
75 |
+
| 0.1834 | 3.5790 | 13500 | 0.1763 |
|
76 |
+
| 0.1832 | 3.7116 | 14000 | 0.1744 |
|
77 |
+
| 0.189 | 3.8441 | 14500 | 0.1734 |
|
78 |
+
| 0.1848 | 3.9767 | 15000 | 0.1724 |
|
79 |
+
| 0.1838 | 4.1092 | 15500 | 0.1715 |
|
80 |
+
| 0.177 | 4.2418 | 16000 | 0.1703 |
|
81 |
+
| 0.1808 | 4.3743 | 16500 | 0.1692 |
|
82 |
+
| 0.183 | 4.5069 | 17000 | 0.1680 |
|
83 |
+
| 0.1753 | 4.6394 | 17500 | 0.1675 |
|
84 |
+
| 0.1724 | 4.7720 | 18000 | 0.1666 |
|
85 |
+
| 0.1782 | 4.9046 | 18500 | 0.1656 |
|
86 |
+
| 0.1799 | 5.0371 | 19000 | 0.1653 |
|
87 |
+
| 0.1725 | 5.1697 | 19500 | 0.1647 |
|
88 |
+
| 0.17 | 5.3022 | 20000 | 0.1635 |
|
89 |
+
| 0.1722 | 5.4348 | 20500 | 0.1630 |
|
90 |
+
| 0.1697 | 5.5673 | 21000 | 0.1625 |
|
91 |
+
| 0.1719 | 5.6999 | 21500 | 0.1620 |
|
92 |
+
| 0.1709 | 5.8324 | 22000 | 0.1611 |
|
93 |
+
| 0.1727 | 5.9650 | 22500 | 0.1604 |
|
94 |
+
| 0.1721 | 6.0976 | 23000 | 0.1598 |
|
95 |
+
| 0.1681 | 6.2301 | 23500 | 0.1602 |
|
96 |
+
| 0.1699 | 6.3627 | 24000 | 0.1596 |
|
97 |
+
| 0.1639 | 6.4952 | 24500 | 0.1588 |
|
98 |
+
| 0.1646 | 6.6278 | 25000 | 0.1584 |
|
99 |
+
| 0.1691 | 6.7603 | 25500 | 0.1582 |
|
100 |
+
| 0.1653 | 6.8929 | 26000 | 0.1574 |
|
101 |
+
| 0.1648 | 7.0255 | 26500 | 0.1572 |
|
102 |
+
| 0.1669 | 7.1580 | 27000 | 0.1569 |
|
103 |
+
| 0.16 | 7.2906 | 27500 | 0.1568 |
|
104 |
+
| 0.1622 | 7.4231 | 28000 | 0.1562 |
|
105 |
+
| 0.1644 | 7.5557 | 28500 | 0.1561 |
|
106 |
+
| 0.1674 | 7.6882 | 29000 | 0.1557 |
|
107 |
+
| 0.1628 | 7.8208 | 29500 | 0.1552 |
|
108 |
+
| 0.1619 | 7.9533 | 30000 | 0.1551 |
|
109 |
+
| 0.1636 | 8.0859 | 30500 | 0.1549 |
|
110 |
+
| 0.1629 | 8.2185 | 31000 | 0.1546 |
|
111 |
+
| 0.1632 | 8.3510 | 31500 | 0.1545 |
|
112 |
+
| 0.1641 | 8.4836 | 32000 | 0.1543 |
|
113 |
+
| 0.1592 | 8.6161 | 32500 | 0.1541 |
|
114 |
+
| 0.1573 | 8.7487 | 33000 | 0.1539 |
|
115 |
+
| 0.1607 | 8.8812 | 33500 | 0.1540 |
|
116 |
+
| 0.1651 | 9.0138 | 34000 | 0.1537 |
|
117 |
+
| 0.1551 | 9.1463 | 34500 | 0.1537 |
|
118 |
+
| 0.1621 | 9.2789 | 35000 | 0.1536 |
|
119 |
+
| 0.166 | 9.4115 | 35500 | 0.1534 |
|
120 |
+
| 0.1575 | 9.5440 | 36000 | 0.1534 |
|
121 |
+
| 0.1607 | 9.6766 | 36500 | 0.1534 |
|
122 |
+
| 0.1627 | 9.8091 | 37000 | 0.1533 |
|
123 |
+
| 0.1608 | 9.9417 | 37500 | 0.1533 |
|
124 |
+
|
125 |
+
|
126 |
+
### Framework versions
|
127 |
+
|
128 |
+
- Transformers 4.41.2
|
129 |
+
- Pytorch 2.5.0.dev20240625
|
130 |
+
- Datasets 2.20.0
|
131 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-base",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
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": "mt5",
|
20 |
+
"num_decoder_layers": 12,
|
21 |
+
"num_heads": 12,
|
22 |
+
"num_layers": 12,
|
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 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.41.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 264277
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08cfd87e1b4db110ebbf2131c6ca5cb1a84cb5ec361df21a0a85bacbd086b554
|
3 |
+
size 2416668528
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a7ecb7d13cbc768a6a30788a9ea473494ed30474747c85b46856124147cf989
|
3 |
+
size 5304
|