spidersouris
commited on
Commit
•
cfa3363
1
Parent(s):
953d0a3
genre-t5-small
Browse files- README.md +138 -0
- config.json +61 -0
- events.out.tfevents.1706187535.28382c0e50a0 +3 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: t5-small
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: results_t5small
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# results_t5small
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0050
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.005
|
38 |
+
- train_batch_size: 48
|
39 |
+
- eval_batch_size: 48
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 500
|
44 |
+
- num_epochs: 10
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
51 |
+
| 0.0235 | 0.12 | 500 | 0.0144 |
|
52 |
+
| 0.0151 | 0.25 | 1000 | 0.0119 |
|
53 |
+
| 0.0153 | 0.37 | 1500 | 0.0101 |
|
54 |
+
| 0.0173 | 0.5 | 2000 | 0.0109 |
|
55 |
+
| 0.0132 | 0.62 | 2500 | 0.0100 |
|
56 |
+
| 0.0123 | 0.75 | 3000 | 0.0092 |
|
57 |
+
| 0.0136 | 0.87 | 3500 | 0.0110 |
|
58 |
+
| 0.014 | 0.99 | 4000 | 0.0089 |
|
59 |
+
| 0.0123 | 1.12 | 4500 | 0.0094 |
|
60 |
+
| 0.0155 | 1.24 | 5000 | 0.0088 |
|
61 |
+
| 0.0119 | 1.37 | 5500 | 0.0095 |
|
62 |
+
| 0.0126 | 1.49 | 6000 | 0.0089 |
|
63 |
+
| 0.0111 | 1.61 | 6500 | 0.0083 |
|
64 |
+
| 0.0129 | 1.74 | 7000 | 0.0081 |
|
65 |
+
| 0.0115 | 1.86 | 7500 | 0.0087 |
|
66 |
+
| 0.0133 | 1.99 | 8000 | 0.0085 |
|
67 |
+
| 0.0167 | 2.11 | 8500 | 0.0105 |
|
68 |
+
| 0.0113 | 2.24 | 9000 | 0.0088 |
|
69 |
+
| 0.0106 | 2.36 | 9500 | 0.0077 |
|
70 |
+
| 0.0101 | 2.48 | 10000 | 0.0075 |
|
71 |
+
| 0.0086 | 2.61 | 10500 | 0.0076 |
|
72 |
+
| 0.0112 | 2.73 | 11000 | 0.0075 |
|
73 |
+
| 0.0097 | 2.86 | 11500 | 0.0076 |
|
74 |
+
| 0.0093 | 2.98 | 12000 | 0.0078 |
|
75 |
+
| 0.0086 | 3.1 | 12500 | 0.0076 |
|
76 |
+
| 0.0092 | 3.23 | 13000 | 0.0077 |
|
77 |
+
| 0.0089 | 3.35 | 13500 | 0.0074 |
|
78 |
+
| 0.0086 | 3.48 | 14000 | 0.0072 |
|
79 |
+
| 0.0084 | 3.6 | 14500 | 0.0072 |
|
80 |
+
| 0.0083 | 3.73 | 15000 | 0.0073 |
|
81 |
+
| 0.0076 | 3.85 | 15500 | 0.0072 |
|
82 |
+
| 0.0097 | 3.97 | 16000 | 0.0071 |
|
83 |
+
| 0.0074 | 4.1 | 16500 | 0.0071 |
|
84 |
+
| 0.0074 | 4.22 | 17000 | 0.0070 |
|
85 |
+
| 0.0089 | 4.35 | 17500 | 0.0069 |
|
86 |
+
| 0.0072 | 4.47 | 18000 | 0.0069 |
|
87 |
+
| 0.0072 | 4.6 | 18500 | 0.0068 |
|
88 |
+
| 0.0084 | 4.72 | 19000 | 0.0067 |
|
89 |
+
| 0.0076 | 4.84 | 19500 | 0.0072 |
|
90 |
+
| 0.0084 | 4.97 | 20000 | 0.0067 |
|
91 |
+
| 0.0062 | 5.09 | 20500 | 0.0065 |
|
92 |
+
| 0.007 | 5.22 | 21000 | 0.0064 |
|
93 |
+
| 0.0075 | 5.34 | 21500 | 0.0063 |
|
94 |
+
| 0.0067 | 5.46 | 22000 | 0.0064 |
|
95 |
+
| 0.0063 | 5.59 | 22500 | 0.0065 |
|
96 |
+
| 0.007 | 5.71 | 23000 | 0.0062 |
|
97 |
+
| 0.0064 | 5.84 | 23500 | 0.0062 |
|
98 |
+
| 0.0073 | 5.96 | 24000 | 0.0062 |
|
99 |
+
| 0.0064 | 6.09 | 24500 | 0.0063 |
|
100 |
+
| 0.0059 | 6.21 | 25000 | 0.0060 |
|
101 |
+
| 0.0062 | 6.33 | 25500 | 0.0060 |
|
102 |
+
| 0.0057 | 6.46 | 26000 | 0.0060 |
|
103 |
+
| 0.006 | 6.58 | 26500 | 0.0058 |
|
104 |
+
| 0.0053 | 6.71 | 27000 | 0.0058 |
|
105 |
+
| 0.0064 | 6.83 | 27500 | 0.0057 |
|
106 |
+
| 0.0061 | 6.95 | 28000 | 0.0057 |
|
107 |
+
| 0.0055 | 7.08 | 28500 | 0.0057 |
|
108 |
+
| 0.0065 | 7.2 | 29000 | 0.0057 |
|
109 |
+
| 0.0058 | 7.33 | 29500 | 0.0057 |
|
110 |
+
| 0.0052 | 7.45 | 30000 | 0.0055 |
|
111 |
+
| 0.0058 | 7.58 | 30500 | 0.0056 |
|
112 |
+
| 0.0055 | 7.7 | 31000 | 0.0055 |
|
113 |
+
| 0.0049 | 7.82 | 31500 | 0.0054 |
|
114 |
+
| 0.0053 | 7.95 | 32000 | 0.0053 |
|
115 |
+
| 0.005 | 8.07 | 32500 | 0.0054 |
|
116 |
+
| 0.0051 | 8.2 | 33000 | 0.0053 |
|
117 |
+
| 0.0047 | 8.32 | 33500 | 0.0053 |
|
118 |
+
| 0.0057 | 8.45 | 34000 | 0.0052 |
|
119 |
+
| 0.0049 | 8.57 | 34500 | 0.0053 |
|
120 |
+
| 0.0051 | 8.69 | 35000 | 0.0052 |
|
121 |
+
| 0.0047 | 8.82 | 35500 | 0.0052 |
|
122 |
+
| 0.0051 | 8.94 | 36000 | 0.0051 |
|
123 |
+
| 0.0044 | 9.07 | 36500 | 0.0052 |
|
124 |
+
| 0.0042 | 9.19 | 37000 | 0.0052 |
|
125 |
+
| 0.0045 | 9.31 | 37500 | 0.0051 |
|
126 |
+
| 0.0043 | 9.44 | 38000 | 0.0051 |
|
127 |
+
| 0.0041 | 9.56 | 38500 | 0.0051 |
|
128 |
+
| 0.0042 | 9.69 | 39000 | 0.0051 |
|
129 |
+
| 0.004 | 9.81 | 39500 | 0.0050 |
|
130 |
+
| 0.0038 | 9.94 | 40000 | 0.0050 |
|
131 |
+
|
132 |
+
|
133 |
+
### Framework versions
|
134 |
+
|
135 |
+
- Transformers 4.37.1
|
136 |
+
- Pytorch 2.1.2
|
137 |
+
- Datasets 2.16.1
|
138 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-small",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 6,
|
22 |
+
"num_heads": 8,
|
23 |
+
"num_layers": 6,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.37.1",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
events.out.tfevents.1706187535.28382c0e50a0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d0df320c36b2046f0e27e01d27149570401da5989e2afcc92831067a2bc3d14
|
3 |
+
size 666588
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.37.1"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ffa6cce93a2d7824c9e242b4c116c7344784574c84a47b68ca01cdf7f6d3adf
|
3 |
+
size 242041896
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cde75153e11ae3e357054a44c62be66953c5bc9bbc4d221947c8f688eb8a88e
|
3 |
+
size 4664
|