superlazycoder
commited on
Commit
•
42c584e
1
Parent(s):
6bd6f81
End of training
Browse files- README.md +156 -0
- config.json +29 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +212 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: EleutherAI/pythia-70m-deduped
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: chesspythia-70m-random_1M
|
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 |
+
# chesspythia-70m-random_1M
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.9894
|
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: 5e-05
|
38 |
+
- train_batch_size: 64
|
39 |
+
- eval_batch_size: 64
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: cosine
|
43 |
+
- num_epochs: 1
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 1.4951 | 0.01 | 25 | 1.5347 |
|
50 |
+
| 1.356 | 0.02 | 50 | 1.3895 |
|
51 |
+
| 1.316 | 0.03 | 75 | 1.3312 |
|
52 |
+
| 1.2512 | 0.04 | 100 | 1.2981 |
|
53 |
+
| 1.2981 | 0.05 | 125 | 1.2738 |
|
54 |
+
| 1.2777 | 0.06 | 150 | 1.2508 |
|
55 |
+
| 1.2913 | 0.07 | 175 | 1.2362 |
|
56 |
+
| 1.2591 | 0.08 | 200 | 1.2201 |
|
57 |
+
| 1.1763 | 0.09 | 225 | 1.2136 |
|
58 |
+
| 1.1835 | 0.1 | 250 | 1.2001 |
|
59 |
+
| 1.1913 | 0.11 | 275 | 1.1864 |
|
60 |
+
| 1.1828 | 0.12 | 300 | 1.1787 |
|
61 |
+
| 1.1523 | 0.13 | 325 | 1.1708 |
|
62 |
+
| 1.2038 | 0.14 | 350 | 1.1653 |
|
63 |
+
| 1.1555 | 0.15 | 375 | 1.1591 |
|
64 |
+
| 1.1235 | 0.16 | 400 | 1.1611 |
|
65 |
+
| 1.1431 | 0.17 | 425 | 1.1484 |
|
66 |
+
| 1.1355 | 0.18 | 450 | 1.1470 |
|
67 |
+
| 1.1464 | 0.19 | 475 | 1.1354 |
|
68 |
+
| 1.146 | 0.2 | 500 | 1.1335 |
|
69 |
+
| 1.1471 | 0.21 | 525 | 1.1241 |
|
70 |
+
| 1.1568 | 0.22 | 550 | 1.1243 |
|
71 |
+
| 1.1565 | 0.23 | 575 | 1.1247 |
|
72 |
+
| 1.1253 | 0.24 | 600 | 1.1160 |
|
73 |
+
| 1.1002 | 0.25 | 625 | 1.1081 |
|
74 |
+
| 1.1356 | 0.26 | 650 | 1.1067 |
|
75 |
+
| 1.0997 | 0.27 | 675 | 1.1074 |
|
76 |
+
| 1.1092 | 0.28 | 700 | 1.1007 |
|
77 |
+
| 1.1016 | 0.29 | 725 | 1.1019 |
|
78 |
+
| 1.0578 | 0.3 | 750 | 1.0897 |
|
79 |
+
| 1.0588 | 0.31 | 775 | 1.0867 |
|
80 |
+
| 1.063 | 0.32 | 800 | 1.0901 |
|
81 |
+
| 1.0559 | 0.33 | 825 | 1.0885 |
|
82 |
+
| 1.1272 | 0.34 | 850 | 1.0841 |
|
83 |
+
| 1.0762 | 0.35 | 875 | 1.0797 |
|
84 |
+
| 1.0842 | 0.36 | 900 | 1.0793 |
|
85 |
+
| 1.0566 | 0.37 | 925 | 1.0744 |
|
86 |
+
| 1.0712 | 0.38 | 950 | 1.0682 |
|
87 |
+
| 1.076 | 0.39 | 975 | 1.0692 |
|
88 |
+
| 1.0624 | 0.4 | 1000 | 1.0670 |
|
89 |
+
| 1.0541 | 0.41 | 1025 | 1.0599 |
|
90 |
+
| 1.0292 | 0.42 | 1050 | 1.0601 |
|
91 |
+
| 1.0788 | 0.43 | 1075 | 1.0536 |
|
92 |
+
| 1.0846 | 0.44 | 1100 | 1.0530 |
|
93 |
+
| 1.0547 | 0.45 | 1125 | 1.0562 |
|
94 |
+
| 0.9978 | 0.46 | 1150 | 1.0483 |
|
95 |
+
| 1.0261 | 0.47 | 1175 | 1.0470 |
|
96 |
+
| 1.0031 | 0.48 | 1200 | 1.0475 |
|
97 |
+
| 1.0141 | 0.49 | 1225 | 1.0442 |
|
98 |
+
| 1.064 | 0.5 | 1250 | 1.0416 |
|
99 |
+
| 1.0154 | 0.51 | 1275 | 1.0408 |
|
100 |
+
| 1.0474 | 0.52 | 1300 | 1.0383 |
|
101 |
+
| 1.0392 | 0.53 | 1325 | 1.0380 |
|
102 |
+
| 1.036 | 0.54 | 1350 | 1.0360 |
|
103 |
+
| 1.0325 | 0.55 | 1375 | 1.0312 |
|
104 |
+
| 1.062 | 0.56 | 1400 | 1.0308 |
|
105 |
+
| 1.0601 | 0.57 | 1425 | 1.0282 |
|
106 |
+
| 1.0287 | 0.58 | 1450 | 1.0274 |
|
107 |
+
| 0.9944 | 0.59 | 1475 | 1.0249 |
|
108 |
+
| 1.0302 | 0.6 | 1500 | 1.0241 |
|
109 |
+
| 1.0188 | 0.61 | 1525 | 1.0210 |
|
110 |
+
| 0.8968 | 0.62 | 1550 | 1.0211 |
|
111 |
+
| 0.9661 | 0.63 | 1575 | 1.0176 |
|
112 |
+
| 1.0741 | 0.64 | 1600 | 1.0182 |
|
113 |
+
| 1.0666 | 0.65 | 1625 | 1.0156 |
|
114 |
+
| 1.0623 | 0.66 | 1650 | 1.0138 |
|
115 |
+
| 1.0435 | 0.67 | 1675 | 1.0117 |
|
116 |
+
| 0.9892 | 0.68 | 1700 | 1.0117 |
|
117 |
+
| 0.9941 | 0.69 | 1725 | 1.0097 |
|
118 |
+
| 0.967 | 0.7 | 1750 | 1.0092 |
|
119 |
+
| 1.0387 | 0.71 | 1775 | 1.0074 |
|
120 |
+
| 0.9718 | 0.72 | 1800 | 1.0056 |
|
121 |
+
| 0.9841 | 0.73 | 1825 | 1.0049 |
|
122 |
+
| 1.0086 | 0.74 | 1850 | 1.0038 |
|
123 |
+
| 0.9855 | 0.75 | 1875 | 1.0025 |
|
124 |
+
| 1.0174 | 0.76 | 1900 | 1.0022 |
|
125 |
+
| 0.9725 | 0.77 | 1925 | 1.0003 |
|
126 |
+
| 0.987 | 0.78 | 1950 | 0.9989 |
|
127 |
+
| 1.0133 | 0.79 | 1975 | 0.9979 |
|
128 |
+
| 0.9978 | 0.8 | 2000 | 0.9974 |
|
129 |
+
| 1.0193 | 0.81 | 2025 | 0.9960 |
|
130 |
+
| 0.9842 | 0.82 | 2050 | 0.9955 |
|
131 |
+
| 0.9316 | 0.83 | 2075 | 0.9952 |
|
132 |
+
| 1.0233 | 0.84 | 2100 | 0.9940 |
|
133 |
+
| 1.0054 | 0.85 | 2125 | 0.9930 |
|
134 |
+
| 0.922 | 0.86 | 2150 | 0.9933 |
|
135 |
+
| 1.0309 | 0.87 | 2175 | 0.9925 |
|
136 |
+
| 0.975 | 0.88 | 2200 | 0.9917 |
|
137 |
+
| 1.0108 | 0.89 | 2225 | 0.9915 |
|
138 |
+
| 0.9418 | 0.9 | 2250 | 0.9911 |
|
139 |
+
| 0.9445 | 0.91 | 2275 | 0.9907 |
|
140 |
+
| 0.9973 | 0.92 | 2300 | 0.9903 |
|
141 |
+
| 1.0052 | 0.93 | 2325 | 0.9900 |
|
142 |
+
| 0.9347 | 0.94 | 2350 | 0.9899 |
|
143 |
+
| 0.954 | 0.95 | 2375 | 0.9897 |
|
144 |
+
| 0.9857 | 0.96 | 2400 | 0.9896 |
|
145 |
+
| 0.958 | 0.97 | 2425 | 0.9895 |
|
146 |
+
| 1.0051 | 0.98 | 2450 | 0.9894 |
|
147 |
+
| 0.9999 | 0.99 | 2475 | 0.9894 |
|
148 |
+
| 0.959 | 1.0 | 2500 | 0.9894 |
|
149 |
+
|
150 |
+
|
151 |
+
### Framework versions
|
152 |
+
|
153 |
+
- Transformers 4.35.2
|
154 |
+
- Pytorch 2.1.0+cu121
|
155 |
+
- Datasets 2.16.1
|
156 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-70m-deduped",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": 0.1,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout": 0.0,
|
12 |
+
"hidden_size": 512,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 2048,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"model_type": "gpt_neox",
|
18 |
+
"num_attention_heads": 8,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rotary_emb_base": 10000,
|
22 |
+
"rotary_pct": 0.25,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_parallel_residual": true,
|
28 |
+
"vocab_size": 50304
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.35.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:211abffe8672dcaf1c965fdd96e6151442f667d08e796b487f3b79fc2cd3a218
|
3 |
+
size 281715176
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|padding|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50254": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50255": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50256": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50257": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50258": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50259": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50260": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50261": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50262": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50263": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50264": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50265": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50266": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50267": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50268": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50269": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50270": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50271": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50272": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50273": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50274": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50275": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50276": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
}
|
204 |
+
},
|
205 |
+
"bos_token": "<|endoftext|>",
|
206 |
+
"clean_up_tokenization_spaces": true,
|
207 |
+
"eos_token": "<|endoftext|>",
|
208 |
+
"model_max_length": 1000000000000000019884624838656,
|
209 |
+
"pad_token": "<|endoftext|>",
|
210 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
211 |
+
"unk_token": "<|endoftext|>"
|
212 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5de1dfa124beabfd43b7158407fc2e7d46d21dac8b961aee92720b35d1365d4c
|
3 |
+
size 4600
|