emilstabil commited on
Commit
646def4
·
1 Parent(s): 1e8d25e

Training in progress, step 500

Browse files
.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 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: emilstabil/mt5-base_V25775_V44105
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - rouge
8
+ model-index:
9
+ - name: mt5-base_V25775_V44105_V65464
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-base_V25775_V44105_V65464
17
+
18
+ This model is a fine-tuned version of [emilstabil/mt5-base_V25775_V44105](https://huggingface.co/emilstabil/mt5-base_V25775_V44105) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.2155
21
+ - Rouge1: 31.936
22
+ - Rouge2: 11.6826
23
+ - Rougel: 21.8491
24
+ - Rougelsum: 26.1962
25
+ - Gen Len: 86.4335
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 3
46
+ - eval_batch_size: 3
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 20
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | 1.794 | 0.81 | 500 | 2.1891 | 29.9862 | 11.266 | 20.9904 | 24.6444 | 83.9571 |
57
+ | 1.7476 | 1.61 | 1000 | 2.1461 | 29.9736 | 10.782 | 20.6739 | 24.663 | 80.7039 |
58
+ | 1.7381 | 2.42 | 1500 | 2.1835 | 30.4805 | 11.0774 | 21.0063 | 24.9859 | 85.1545 |
59
+ | 1.6956 | 3.23 | 2000 | 2.1836 | 30.0028 | 10.9574 | 20.721 | 24.5095 | 79.6266 |
60
+ | 1.6593 | 4.03 | 2500 | 2.1878 | 29.7076 | 10.7504 | 20.4333 | 24.3183 | 77.3948 |
61
+ | 1.6416 | 4.84 | 3000 | 2.1937 | 30.4163 | 11.0254 | 20.9501 | 24.8448 | 82.9185 |
62
+ | 1.613 | 5.65 | 3500 | 2.2060 | 30.518 | 11.1385 | 21.0192 | 24.9011 | 80.5408 |
63
+ | 1.6199 | 6.45 | 4000 | 2.2267 | 30.7458 | 11.2048 | 21.3743 | 25.2027 | 82.6524 |
64
+ | 1.5769 | 7.26 | 4500 | 2.2113 | 31.6325 | 11.4758 | 21.3606 | 25.8015 | 88.4292 |
65
+ | 1.5765 | 8.06 | 5000 | 2.2101 | 31.3878 | 11.2897 | 21.3136 | 25.729 | 86.4936 |
66
+ | 1.5706 | 8.87 | 5500 | 2.2115 | 32.2878 | 11.5704 | 21.9421 | 26.3874 | 91.7768 |
67
+ | 1.5625 | 9.68 | 6000 | 2.2145 | 31.5711 | 11.4538 | 21.3608 | 25.8527 | 88.7167 |
68
+ | 1.5278 | 10.48 | 6500 | 2.2219 | 30.6581 | 11.2777 | 21.1534 | 25.0079 | 80.9785 |
69
+ | 1.5295 | 11.29 | 7000 | 2.2340 | 30.6276 | 11.0522 | 21.1302 | 25.0254 | 82.7854 |
70
+ | 1.5286 | 12.1 | 7500 | 2.2155 | 30.614 | 11.4733 | 21.3702 | 25.0853 | 78.309 |
71
+ | 1.5138 | 12.9 | 8000 | 2.2298 | 30.6334 | 11.3644 | 21.1625 | 25.0588 | 81.133 |
72
+ | 1.4935 | 13.71 | 8500 | 2.2163 | 31.0745 | 11.1841 | 21.1997 | 25.3718 | 84.8412 |
73
+ | 1.5309 | 14.52 | 9000 | 2.2133 | 31.0237 | 11.5053 | 21.5787 | 25.6145 | 80.7725 |
74
+ | 1.4852 | 15.32 | 9500 | 2.2239 | 31.9443 | 11.5394 | 21.5817 | 26.0822 | 88.2532 |
75
+ | 1.5247 | 16.13 | 10000 | 2.2258 | 31.6514 | 11.6206 | 21.5841 | 25.8946 | 85.6052 |
76
+ | 1.4931 | 16.94 | 10500 | 2.2205 | 31.522 | 11.5251 | 21.1916 | 25.587 | 87.8069 |
77
+ | 1.5085 | 17.74 | 11000 | 2.2110 | 31.4641 | 11.3441 | 21.3223 | 25.7801 | 85.7983 |
78
+ | 1.5014 | 18.55 | 11500 | 2.2162 | 31.5727 | 11.6335 | 21.6467 | 25.949 | 84.2918 |
79
+ | 1.5057 | 19.35 | 12000 | 2.2155 | 31.936 | 11.6826 | 21.8491 | 26.1962 | 86.4335 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.32.1
85
+ - Pytorch 2.1.0
86
+ - Datasets 2.12.0
87
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "emilstabil/mt5-base_V25775_V44105",
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
+ "length_penalty": 0.6,
20
+ "max_length": 500,
21
+ "model_type": "mt5",
22
+ "no_repeat_ngram_size": 2,
23
+ "num_beams": 15,
24
+ "num_decoder_layers": 12,
25
+ "num_heads": 12,
26
+ "num_layers": 12,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "relative_attention_max_distance": 128,
30
+ "relative_attention_num_buckets": 32,
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "T5Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.32.1",
35
+ "use_cache": true,
36
+ "vocab_size": 250112
37
+ }
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": 500,
6
+ "no_repeat_ngram_size": 2,
7
+ "num_beams": 15,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.32.1"
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60914926d0bceff90a1fd229a81cdf2d99ae4b058979e41ebba3b1eb33a14125
3
+ size 2329703026
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
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 sha256:61fa978880dcd297d518232c51d8aad321ab6a6ef9a8fd59f80d1451530118fa
3
+ size 16315219
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "legacy": true,
7
+ "max_length": 500,
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "<pad>",
10
+ "sp_model_kwargs": {},
11
+ "stride": 0,
12
+ "tokenizer_class": "T5Tokenizer",
13
+ "truncation_side": "right",
14
+ "truncation_strategy": "longest_first",
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2a2f5b24641d2957b85d1b1ab71956391cd4a7a9df6dfd76c0df08be478fdd
3
+ size 4664