End of training
Browse files- .gitattributes +1 -0
- README.md +110 -0
- config.json +33 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +39 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/mt5-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- bleu
|
8 |
+
model-index:
|
9 |
+
- name: cs_mT5-large2_2e-5_50_v0.3
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# cs_mT5-large2_2e-5_50_v0.3
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 10.7179
|
21 |
+
- Bleu: 8.2299
|
22 |
+
- Gen Len: 19.0
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 50
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
53 |
+
| 22.4209 | 1.0 | 6 | 14.7377 | 5.6697 | 19.0 |
|
54 |
+
| 20.671 | 2.0 | 12 | 14.9637 | 6.7619 | 19.0 |
|
55 |
+
| 17.7208 | 3.0 | 18 | 14.6564 | 5.3777 | 19.0 |
|
56 |
+
| 22.9549 | 4.0 | 24 | 15.1568 | 6.7736 | 19.0 |
|
57 |
+
| 16.6185 | 5.0 | 30 | 14.1533 | 7.0263 | 19.0 |
|
58 |
+
| 22.1158 | 6.0 | 36 | 15.0667 | 7.1851 | 19.0 |
|
59 |
+
| 24.587 | 7.0 | 42 | 15.5166 | 7.6752 | 19.0 |
|
60 |
+
| 16.4955 | 8.0 | 48 | 14.5515 | 7.5521 | 19.0 |
|
61 |
+
| 21.0521 | 9.0 | 54 | 13.0890 | 7.7939 | 19.0 |
|
62 |
+
| 16.1149 | 10.0 | 60 | 11.8305 | 7.7866 | 19.0 |
|
63 |
+
| 12.8454 | 11.0 | 66 | 11.8727 | 7.7197 | 19.0 |
|
64 |
+
| 18.482 | 12.0 | 72 | 11.6011 | 7.5761 | 19.0 |
|
65 |
+
| 18.6175 | 13.0 | 78 | 11.8911 | 7.7925 | 19.0 |
|
66 |
+
| 12.6805 | 14.0 | 84 | 11.8462 | 7.3764 | 19.0 |
|
67 |
+
| 14.3151 | 15.0 | 90 | 11.4554 | 7.6604 | 19.0 |
|
68 |
+
| 17.2287 | 16.0 | 96 | 11.1727 | 8.0204 | 19.0 |
|
69 |
+
| 16.3546 | 17.0 | 102 | 10.7514 | 8.0859 | 19.0 |
|
70 |
+
| 16.3339 | 18.0 | 108 | 11.1960 | 8.1381 | 19.0 |
|
71 |
+
| 16.6065 | 19.0 | 114 | 11.3321 | 8.126 | 19.0 |
|
72 |
+
| 14.3851 | 20.0 | 120 | 10.9074 | 6.3032 | 19.0 |
|
73 |
+
| 15.8189 | 21.0 | 126 | 10.5179 | 6.3626 | 19.0 |
|
74 |
+
| 8.4543 | 22.0 | 132 | 10.6037 | 6.3223 | 19.0 |
|
75 |
+
| 18.0304 | 23.0 | 138 | 10.3665 | 6.236 | 19.0 |
|
76 |
+
| 13.1475 | 24.0 | 144 | 10.3107 | 7.4434 | 19.0 |
|
77 |
+
| 21.3407 | 25.0 | 150 | 10.2976 | 7.4596 | 19.0 |
|
78 |
+
| 15.8901 | 26.0 | 156 | 10.4723 | 7.2047 | 19.0 |
|
79 |
+
| 13.3029 | 27.0 | 162 | 10.7863 | 7.2047 | 19.0 |
|
80 |
+
| 9.6205 | 28.0 | 168 | 11.2429 | 7.2047 | 19.0 |
|
81 |
+
| 15.4244 | 29.0 | 174 | 11.5663 | 7.1797 | 19.0 |
|
82 |
+
| 10.8496 | 30.0 | 180 | 11.9665 | 7.1839 | 19.0 |
|
83 |
+
| 16.4213 | 31.0 | 186 | 12.3102 | 7.1002 | 19.0 |
|
84 |
+
| 19.9358 | 32.0 | 192 | 12.3951 | 7.1693 | 19.0 |
|
85 |
+
| 13.9974 | 33.0 | 198 | 12.6037 | 7.1693 | 19.0 |
|
86 |
+
| 18.1208 | 34.0 | 204 | 12.4725 | 7.0996 | 19.0 |
|
87 |
+
| 10.2059 | 35.0 | 210 | 12.1561 | 7.286 | 19.0 |
|
88 |
+
| 15.9016 | 36.0 | 216 | 11.9896 | 7.286 | 19.0 |
|
89 |
+
| 16.7008 | 37.0 | 222 | 11.4571 | 8.4159 | 19.0 |
|
90 |
+
| 14.4533 | 38.0 | 228 | 11.1535 | 8.4159 | 19.0 |
|
91 |
+
| 15.1107 | 39.0 | 234 | 11.1553 | 8.4159 | 19.0 |
|
92 |
+
| 13.2587 | 40.0 | 240 | 11.0539 | 7.2709 | 19.0 |
|
93 |
+
| 14.9836 | 41.0 | 246 | 11.3945 | 7.1574 | 19.0 |
|
94 |
+
| 13.083 | 42.0 | 252 | 11.3690 | 7.1948 | 19.0 |
|
95 |
+
| 24.9864 | 43.0 | 258 | 11.2586 | 8.2299 | 19.0 |
|
96 |
+
| 22.1657 | 44.0 | 264 | 11.1126 | 8.2299 | 19.0 |
|
97 |
+
| 15.6887 | 45.0 | 270 | 11.0112 | 8.2299 | 19.0 |
|
98 |
+
| 8.581 | 46.0 | 276 | 10.8892 | 8.2299 | 19.0 |
|
99 |
+
| 14.0141 | 47.0 | 282 | 10.8514 | 8.2299 | 19.0 |
|
100 |
+
| 11.8402 | 48.0 | 288 | 10.8129 | 8.2299 | 19.0 |
|
101 |
+
| 14.7845 | 49.0 | 294 | 10.7252 | 8.2299 | 19.0 |
|
102 |
+
| 18.8443 | 50.0 | 300 | 10.7179 | 8.2299 | 19.0 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- Transformers 4.38.2
|
108 |
+
- Pytorch 2.1.0+cu121
|
109 |
+
- Datasets 2.18.0
|
110 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-large",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
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": "mt5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
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": "4.38.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250112
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a96d0c06d1ecf3a53a445bdee6301f4d0e45f79042e7de4958cebd8539f8d0ab
|
3 |
+
size 4918393736
|
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.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0910f648726ceada34086ae80066cd253863e183cbb52ae566659a2d37716f0
|
3 |
+
size 16330660
|
tokenizer_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [],
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"extra_ids": 0,
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "<pad>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "T5Tokenizer",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5dd3ad47b204db76f5ddb8d5fc9264d93b9b61b99e031f6f71f4f25b39e1cb7
|
3 |
+
size 5112
|