Commit
·
84eb833
1
Parent(s):
4c0dbc0
manual push
Browse files- README.md +69 -0
- config.json +28 -0
- runs/Dec23_20-49-42_ip-172-31-12-71/1640292592.435321/events.out.tfevents.1640292592.ip-172-31-12-71.41176.1 +3 -0
- runs/Dec23_20-49-42_ip-172-31-12-71/events.out.tfevents.1640292592.ip-172-31-12-71.41176.0 +3 -0
- runs/Dec23_20-53-49_ip-172-31-12-71/1640292837.337157/events.out.tfevents.1640292837.ip-172-31-12-71.43830.1 +3 -0
- runs/Dec23_20-53-49_ip-172-31-12-71/events.out.tfevents.1640292837.ip-172-31-12-71.43830.0 +3 -0
- runs/Dec23_20-53-49_ip-172-31-12-71/events.out.tfevents.1640324828.ip-172-31-12-71.43830.2 +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- rouge
|
7 |
+
model-index:
|
8 |
+
- name: mt5-small-prompted-germanquad-1
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# mt5-small-prompted-germanquad-1
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.6835
|
20 |
+
- Rouge1: 27.7309
|
21 |
+
- Rouge2: 18.7311
|
22 |
+
- Rougel: 27.4704
|
23 |
+
- Rougelsum: 27.4818
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 5.6e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 500
|
49 |
+
- num_epochs: 7
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|
54 |
+
|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|
|
55 |
+
| 3.3795 | 1.0 | 17496 | 2.0693 | 15.8652 | 9.2569 | 15.6237 | 15.6142 |
|
56 |
+
| 2.3582 | 2.0 | 34992 | 1.9057 | 21.9348 | 14.0057 | 21.6769 | 21.6825 |
|
57 |
+
| 2.1809 | 3.0 | 52488 | 1.8143 | 24.3401 | 16.0354 | 24.0862 | 24.0914 |
|
58 |
+
| 2.0721 | 4.0 | 69984 | 1.7563 | 25.8672 | 17.2442 | 25.5854 | 25.6051 |
|
59 |
+
| 2.0004 | 5.0 | 87480 | 1.7152 | 27.0275 | 18.0548 | 26.7561 | 26.7685 |
|
60 |
+
| 1.9531 | 6.0 | 104976 | 1.6939 | 27.4702 | 18.5156 | 27.2027 | 27.2107 |
|
61 |
+
| 1.9218 | 7.0 | 122472 | 1.6835 | 27.7309 | 18.7311 | 27.4704 | 27.4818 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.14.1
|
67 |
+
- Pytorch 1.10.1+cu102
|
68 |
+
- Datasets 1.16.1
|
69 |
+
- 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": "4.14.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250112
|
28 |
+
}
|
runs/Dec23_20-49-42_ip-172-31-12-71/1640292592.435321/events.out.tfevents.1640292592.ip-172-31-12-71.41176.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38d56788cf099e3b790c239ddd71cb1e427f7492b2f4ff9eba1c73e3ad45588b
|
3 |
+
size 4985
|
runs/Dec23_20-49-42_ip-172-31-12-71/events.out.tfevents.1640292592.ip-172-31-12-71.41176.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e13f1543eba10a517e56a1b5dd0d5d819966004b04384c1a56948a9075c58a73
|
3 |
+
size 3456
|
runs/Dec23_20-53-49_ip-172-31-12-71/1640292837.337157/events.out.tfevents.1640292837.ip-172-31-12-71.43830.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99536983ab5c59ca44f5be02b0c9d531e09eee5e580d41e030948383df5a015e
|
3 |
+
size 4985
|
runs/Dec23_20-53-49_ip-172-31-12-71/events.out.tfevents.1640292837.ip-172-31-12-71.43830.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:062c9e1142a4deaf5118ce437189349710e6e68e438bb4d7115086c5ec93b1fc
|
3 |
+
size 8317
|
runs/Dec23_20-53-49_ip-172-31-12-71/events.out.tfevents.1640324828.ip-172-31-12-71.43830.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2aa9eb1e283758a4648d0d912fc1a3b4dcdf7dba39f599c0e4580c7b92ad6f14
|
3 |
+
size 523
|
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": "/home/ubuntu/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|