Upload with huggingface_hub
Browse files- README.md +79 -0
- config.json +32 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: t0-all_tasksv2-m1-t1
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# t0-all_tasksv2-m1-t1
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [bigscience/T0_3B](https://huggingface.co/bigscience/T0_3B) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.1591
|
18 |
+
- Train Runtime: 31498.6176
|
19 |
+
- Train Samples Per Second: 15.232
|
20 |
+
- Train Steps Per Second: 0.212
|
21 |
+
- Train Loss: 1.4163
|
22 |
+
- Train Samples: 239899
|
23 |
+
- Gen Len: 9.847
|
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: 5e-05
|
43 |
+
- train_batch_size: 3
|
44 |
+
- eval_batch_size: 3
|
45 |
+
- seed: 42
|
46 |
+
- distributed_type: multi-GPU
|
47 |
+
- num_devices: 8
|
48 |
+
- gradient_accumulation_steps: 3
|
49 |
+
- total_train_batch_size: 72
|
50 |
+
- total_eval_batch_size: 24
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- num_epochs: 2.0
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Accuracy | F1 | Recall | Precision | Bleu 1 | Bleu 2 | Bleu 3 | Bleu 4 | Rouge L | Gen Len |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:--------:|:-------:|:-------:|:---------:|:------:|:------:|:------:|:------:|:-------:|:-------:|
|
59 |
+
| 1.5957 | 0.15 | 500 | 1.3177 | 51.7673 | 5.9934 | 51.3052 | 51.4889 | 58.2201 | 58.2201 | 58.2201 | 58.2201 | 0.5452 | 0.0004 | 0.0 | 0.0 | 0.5025 | 6.144 |
|
60 |
+
| 1.5657 | 0.3 | 1000 | 1.2654 | 56.3471 | 6.2554 | 55.9191 | 56.0106 | 64.5902 | 64.5902 | 64.5902 | 64.5902 | 0.5834 | 0.0005 | 0.0 | 0.0 | 0.5423 | 6.363 |
|
61 |
+
| 1.4614 | 0.45 | 1500 | 1.2279 | 60.3041 | 6.4454 | 59.881 | 60.0203 | 69.9766 | 69.9766 | 69.9766 | 69.9766 | 0.6223 | 0.0005 | 0.0 | 0.0 | 0.5799 | 6.319 |
|
62 |
+
| 1.4733 | 0.6 | 2000 | 1.2001 | 63.1864 | 6.4428 | 62.7935 | 63.0146 | 74.192 | 74.192 | 74.192 | 74.192 | 0.6527 | 0.0005 | 0.0001 | 0.0 | 0.6102 | 6.319 |
|
63 |
+
| 1.3982 | 0.75 | 2500 | 1.1888 | 64.2445 | 6.6019 | 63.8196 | 63.9475 | 75.0351 | 75.0351 | 75.0351 | 75.0351 | 0.6606 | 0.0005 | 0.0001 | 0.0 | 0.6151 | 6.3657 |
|
64 |
+
| 1.4344 | 0.9 | 3000 | 1.1827 | 63.9356 | 6.7482 | 63.5225 | 63.72 | 74.6136 | 74.6136 | 74.6136 | 74.6136 | 0.6576 | 0.0005 | 0.0001 | 0.0 | 0.6123 | 6.3577 |
|
65 |
+
| 1.3281 | 1.05 | 3500 | 1.1725 | 65.0553 | 6.6823 | 64.6434 | 64.8219 | 76.2529 | 76.2529 | 76.2529 | 76.2529 | 0.6679 | 0.0005 | 0.0001 | 0.0 | 0.6206 | 6.374 |
|
66 |
+
| 1.3033 | 1.2 | 4000 | 1.1753 | 64.7545 | 6.5216 | 64.3853 | 64.5344 | 76.1124 | 76.1124 | 76.1124 | 76.1124 | 0.6628 | 0.0005 | 0.0001 | 0.0 | 0.619 | 6.4473 |
|
67 |
+
| 1.2871 | 1.35 | 4500 | 1.1656 | 65.6713 | 6.7135 | 65.185 | 65.4454 | 77.0023 | 77.0023 | 77.0023 | 77.0023 | 0.6718 | 0.0005 | 0.0001 | 0.0 | 0.6246 | 6.472 |
|
68 |
+
| 1.3423 | 1.5 | 5000 | 1.1669 | 65.8966 | 6.7928 | 65.5016 | 65.6741 | 77.377 | 77.377 | 77.377 | 77.377 | 0.6772 | 0.0005 | 0.0001 | 0.0 | 0.6288 | 6.36 |
|
69 |
+
| 1.333 | 1.65 | 5500 | 1.1627 | 65.9726 | 6.7915 | 65.5878 | 65.7582 | 77.4239 | 77.4239 | 77.4239 | 77.4239 | 0.6742 | 0.0005 | 0.0001 | 0.0 | 0.6273 | 6.4767 |
|
70 |
+
| 1.2749 | 1.8 | 6000 | 1.1591 | 66.5212 | 6.9115 | 66.0695 | 66.3204 | 77.9859 | 77.9859 | 77.9859 | 77.9859 | 0.681 | 0.0006 | 0.0001 | 0.0 | 0.6324 | 6.4403 |
|
71 |
+
| 1.2891 | 1.95 | 6500 | 1.1571 | 66.2478 | 6.8368 | 65.8198 | 66.0423 | 77.5644 | 77.5644 | 77.5644 | 77.5644 | 0.6778 | 0.0005 | 0.0001 | 0.0 | 0.6298 | 6.4417 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.20.1
|
77 |
+
- Pytorch 1.11.0
|
78 |
+
- Datasets 2.3.2
|
79 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/T0_3B",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 5120,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 2048,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"gradient_checkpointing": false,
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 32,
|
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 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.20.1",
|
30 |
+
"use_cache": false,
|
31 |
+
"vocab_size": 32100
|
32 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3d6a368ba055474fb998a9ca9e733708e35b66898d5bd366ed27057b7da58a1
|
3 |
+
size 5699366811
|
special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"extra_ids": 100,
|
106 |
+
"model_max_length": 512,
|
107 |
+
"name_or_path": "bigscience/T0_3B",
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"sp_model_kwargs": {},
|
110 |
+
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/transformers/303fbee39a17e96552ac07e02b70ba62ff0ad760609687e3a1b92b4ad2dff58c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46",
|
111 |
+
"tokenizer_class": "T5Tokenizer",
|
112 |
+
"unk_token": "<unk>"
|
113 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1ff9c3437c851445a9bca1019601e7914c9d0f696accd1a92bcacd0979660af
|
3 |
+
size 4527
|