Commit ·
b0b8438
1
Parent(s): ec2872d
End of training
Browse files- .gitattributes +1 -0
- README.md +115 -0
- config.json +36 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- runs/Nov04_11-55-28_011e4f6cabd7/events.out.tfevents.1699098928.011e4f6cabd7.199.0 +3 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +38 -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 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/mt5-small
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt5-summarize-te
|
| 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 |
+
# mt5-summarize-te
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.1257
|
| 21 |
+
- Rouge1: 0.5211
|
| 22 |
+
- Rouge2: 0.4338
|
| 23 |
+
- Rougel: 0.4813
|
| 24 |
+
- Rougelsum: 0.4819
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0005
|
| 44 |
+
- train_batch_size: 2
|
| 45 |
+
- eval_batch_size: 1
|
| 46 |
+
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 16
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 90
|
| 52 |
+
- num_epochs: 10
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
|
| 58 |
+
| 3.8667 | 0.2 | 100 | 2.5990 | 0.4450 | 0.3695 | 0.4151 | 0.4154 |
|
| 59 |
+
| 3.2326 | 0.39 | 200 | 2.5107 | 0.5023 | 0.4156 | 0.4567 | 0.4571 |
|
| 60 |
+
| 3.1169 | 0.59 | 300 | 2.4503 | 0.5092 | 0.4204 | 0.4775 | 0.4762 |
|
| 61 |
+
| 2.9083 | 0.79 | 400 | 2.4005 | 0.5053 | 0.4179 | 0.4699 | 0.4709 |
|
| 62 |
+
| 2.9652 | 0.98 | 500 | 2.3218 | 0.4833 | 0.4003 | 0.4528 | 0.4555 |
|
| 63 |
+
| 2.8848 | 1.18 | 600 | 2.3262 | 0.5309 | 0.4415 | 0.4868 | 0.4879 |
|
| 64 |
+
| 2.6585 | 1.37 | 700 | 2.3118 | 0.5168 | 0.4273 | 0.4780 | 0.4773 |
|
| 65 |
+
| 2.6662 | 1.57 | 800 | 2.2823 | 0.5112 | 0.4233 | 0.4713 | 0.4727 |
|
| 66 |
+
| 2.7628 | 1.77 | 900 | 2.2381 | 0.5158 | 0.4269 | 0.4798 | 0.4798 |
|
| 67 |
+
| 2.7156 | 1.96 | 1000 | 2.2466 | 0.5280 | 0.4452 | 0.4836 | 0.4844 |
|
| 68 |
+
| 2.5683 | 2.16 | 1100 | 2.2495 | 0.5184 | 0.4300 | 0.4779 | 0.4773 |
|
| 69 |
+
| 2.5248 | 2.36 | 1200 | 2.2498 | 0.5179 | 0.4282 | 0.4790 | 0.4803 |
|
| 70 |
+
| 2.5809 | 2.55 | 1300 | 2.2336 | 0.5233 | 0.4385 | 0.4895 | 0.4920 |
|
| 71 |
+
| 2.7113 | 2.75 | 1400 | 2.2368 | 0.5079 | 0.4207 | 0.4707 | 0.4716 |
|
| 72 |
+
| 2.6151 | 2.95 | 1500 | 2.1993 | 0.5108 | 0.4236 | 0.4681 | 0.4679 |
|
| 73 |
+
| 2.5172 | 3.14 | 1600 | 2.2197 | 0.5138 | 0.4257 | 0.4778 | 0.4781 |
|
| 74 |
+
| 2.5873 | 3.34 | 1700 | 2.1900 | 0.5185 | 0.4312 | 0.4823 | 0.4821 |
|
| 75 |
+
| 2.4245 | 3.53 | 1800 | 2.1982 | 0.5222 | 0.4332 | 0.4837 | 0.4853 |
|
| 76 |
+
| 2.4983 | 3.73 | 1900 | 2.1756 | 0.5125 | 0.4247 | 0.4809 | 0.4810 |
|
| 77 |
+
| 2.3963 | 3.93 | 2000 | 2.1900 | 0.5259 | 0.4400 | 0.4870 | 0.4884 |
|
| 78 |
+
| 2.3465 | 4.12 | 2100 | 2.1963 | 0.5300 | 0.4412 | 0.4900 | 0.4915 |
|
| 79 |
+
| 2.4625 | 4.32 | 2200 | 2.1818 | 0.5277 | 0.4384 | 0.4868 | 0.4882 |
|
| 80 |
+
| 2.4257 | 4.52 | 2300 | 2.1504 | 0.5212 | 0.4342 | 0.4833 | 0.4842 |
|
| 81 |
+
| 2.368 | 4.71 | 2400 | 2.1463 | 0.5252 | 0.4418 | 0.4856 | 0.4869 |
|
| 82 |
+
| 2.427 | 4.91 | 2500 | 2.1581 | 0.5161 | 0.4267 | 0.4766 | 0.4771 |
|
| 83 |
+
| 2.3443 | 5.11 | 2600 | 2.1551 | 0.5167 | 0.4281 | 0.4794 | 0.4794 |
|
| 84 |
+
| 2.2923 | 5.3 | 2700 | 2.1596 | 0.5183 | 0.4255 | 0.4668 | 0.4686 |
|
| 85 |
+
| 2.2956 | 5.5 | 2800 | 2.1438 | 0.5125 | 0.4268 | 0.4747 | 0.4754 |
|
| 86 |
+
| 2.2973 | 5.69 | 2900 | 2.1523 | 0.5139 | 0.4259 | 0.4712 | 0.4722 |
|
| 87 |
+
| 2.3013 | 5.89 | 3000 | 2.1514 | 0.5138 | 0.4236 | 0.4741 | 0.4742 |
|
| 88 |
+
| 2.2222 | 6.09 | 3100 | 2.1558 | 0.5172 | 0.4300 | 0.4773 | 0.4784 |
|
| 89 |
+
| 2.3957 | 6.28 | 3200 | 2.1451 | 0.5203 | 0.4326 | 0.4815 | 0.4817 |
|
| 90 |
+
| 2.1995 | 6.48 | 3300 | 2.1476 | 0.5146 | 0.4264 | 0.4747 | 0.4752 |
|
| 91 |
+
| 2.2931 | 6.68 | 3400 | 2.1252 | 0.5120 | 0.4252 | 0.4683 | 0.4683 |
|
| 92 |
+
| 2.3062 | 6.87 | 3500 | 2.1313 | 0.5197 | 0.4339 | 0.4803 | 0.4807 |
|
| 93 |
+
| 2.2844 | 7.07 | 3600 | 2.1281 | 0.5197 | 0.4339 | 0.4868 | 0.4876 |
|
| 94 |
+
| 2.1158 | 7.27 | 3700 | 2.1438 | 0.5208 | 0.4333 | 0.4818 | 0.4823 |
|
| 95 |
+
| 2.2523 | 7.46 | 3800 | 2.1221 | 0.5197 | 0.4324 | 0.4783 | 0.4788 |
|
| 96 |
+
| 2.2389 | 7.66 | 3900 | 2.1336 | 0.5144 | 0.4262 | 0.4769 | 0.4771 |
|
| 97 |
+
| 2.2209 | 7.85 | 4000 | 2.1317 | 0.5211 | 0.4338 | 0.4813 | 0.4819 |
|
| 98 |
+
| 2.1828 | 8.05 | 4100 | 2.1366 | 0.5208 | 0.4336 | 0.4814 | 0.4816 |
|
| 99 |
+
| 2.2746 | 8.25 | 4200 | 2.1325 | 0.5219 | 0.4342 | 0.4819 | 0.4823 |
|
| 100 |
+
| 2.229 | 8.44 | 4300 | 2.1334 | 0.5214 | 0.4329 | 0.4809 | 0.4812 |
|
| 101 |
+
| 2.2762 | 8.64 | 4400 | 2.1223 | 0.5161 | 0.4288 | 0.4761 | 0.4769 |
|
| 102 |
+
| 2.2005 | 8.84 | 4500 | 2.1322 | 0.5197 | 0.4320 | 0.4793 | 0.4799 |
|
| 103 |
+
| 2.1975 | 9.03 | 4600 | 2.1294 | 0.5211 | 0.4338 | 0.4813 | 0.4819 |
|
| 104 |
+
| 2.3219 | 9.23 | 4700 | 2.1251 | 0.5148 | 0.4260 | 0.4768 | 0.4772 |
|
| 105 |
+
| 2.252 | 9.43 | 4800 | 2.1261 | 0.5211 | 0.4338 | 0.4813 | 0.4819 |
|
| 106 |
+
| 2.2594 | 9.62 | 4900 | 2.1236 | 0.5200 | 0.4331 | 0.4808 | 0.4814 |
|
| 107 |
+
| 2.1675 | 9.82 | 5000 | 2.1257 | 0.5211 | 0.4338 | 0.4813 | 0.4819 |
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
### Framework versions
|
| 111 |
+
|
| 112 |
+
- Transformers 4.35.0
|
| 113 |
+
- Pytorch 2.1.0+cu118
|
| 114 |
+
- Datasets 2.14.6
|
| 115 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 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 |
+
"length_penalty": 0.6,
|
| 20 |
+
"max_length": 128,
|
| 21 |
+
"model_type": "mt5",
|
| 22 |
+
"no_repeat_ngram_size": 2,
|
| 23 |
+
"num_beams": 15,
|
| 24 |
+
"num_decoder_layers": 8,
|
| 25 |
+
"num_heads": 6,
|
| 26 |
+
"num_layers": 8,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"relative_attention_max_distance": 128,
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"tokenizer_class": "T5Tokenizer",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.35.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 250112
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"length_penalty": 0.6,
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"no_repeat_ngram_size": 2,
|
| 7 |
+
"num_beams": 15,
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"transformers_version": "4.35.0"
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dee95b3342f482c16e2999470a9d4e8fe8eadc637db5f2b5c541fb63bfc7c62
|
| 3 |
+
size 1200729512
|
runs/Nov04_11-55-28_011e4f6cabd7/events.out.tfevents.1699098928.011e4f6cabd7.199.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58a6600e62e9b35e5069037081e200f78b7d294abc859437a9962bcd152a09b5
|
| 3 |
+
size 108508
|
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 sha256:312eb8d5be03ad38b677f813ef3a3d0d384568a2171251925d9db4a759f05ef4
|
| 3 |
+
size 16330397
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"clean_up_tokenization_spaces": true,
|
| 30 |
+
"eos_token": "</s>",
|
| 31 |
+
"extra_ids": 0,
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "<pad>",
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"unk_token": "<unk>"
|
| 38 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:482181ec6f38685c677665b5d5e22b4e50c86754b540811187389b269d87e3c2
|
| 3 |
+
size 4664
|