gniemiec commited on
Commit
51d855a
1 Parent(s): 4b857da
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - xsum
7
+ metrics:
8
+ - rouge
9
+ model-index:
10
+ - name: mt5-small-finetuned-xsum
11
+ results:
12
+ - task:
13
+ name: Sequence-to-sequence Language Modeling
14
+ type: text2text-generation
15
+ dataset:
16
+ name: xsum
17
+ type: xsum
18
+ args: default
19
+ metrics:
20
+ - name: Rouge1
21
+ type: rouge
22
+ value: 2.4762
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # mt5-small-finetuned-xsum
29
+
30
+ This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xsum dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: nan
33
+ - Rouge1: 2.4762
34
+ - Rouge2: 0.2236
35
+ - Rougel: 2.2834
36
+ - Rougelsum: 2.2792
37
+ - Gen Len: 4.6402
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 2e-05
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 1
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
69
+ | nan | 1.0 | 1276 | nan | 2.4762 | 0.2236 | 2.2834 | 2.2792 | 4.6402 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.10.2
75
+ - Pytorch 1.9.0+cu102
76
+ - Datasets 1.12.1
77
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 8,
18
+ "num_heads": 6,
19
+ "num_layers": 8,
20
+ "pad_token_id": 0,
21
+ "relative_attention_num_buckets": 32,
22
+ "tie_word_embeddings": false,
23
+ "tokenizer_class": "T5Tokenizer",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.10.2",
26
+ "use_cache": true,
27
+ "vocab_size": 250112
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672b266857da449c8e1759ff96da0d8e7dc4402f0722687fee84220d436fe544
3
+ size 1200770885
runs/Sep21_08-37-20_02df3a22b2fc/1632213476.886618/events.out.tfevents.1632213476.02df3a22b2fc.136.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4af06400c854eb0f47e33af8f0d28099db2b0b38cb47a5718094ddd565f3dd
3
+ size 4450
runs/Sep21_08-37-20_02df3a22b2fc/events.out.tfevents.1632213476.02df3a22b2fc.136.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d810d5e90de31d9f57d0a21f96ac91e3ba8e3f8e8e57e531522c10bcd9459942
3
+ size 4302
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7d64759e49a09449abc38a81c8bc3c42d538ad4a5574fc56cb959d6ee63981
3
+ size 2799