Upload folder using huggingface_hub
Browse files- commongen_pythia-31m/checkpoint-8000/config.json +30 -0
- commongen_pythia-31m/checkpoint-8000/generation_config.json +6 -0
- commongen_pythia-31m/checkpoint-8000/model.safetensors +3 -0
- commongen_pythia-31m/checkpoint-8000/optimizer.pt +3 -0
- commongen_pythia-31m/checkpoint-8000/rng_state.pth +3 -0
- commongen_pythia-31m/checkpoint-8000/scheduler.pt +3 -0
- commongen_pythia-31m/checkpoint-8000/special_tokens_map.json +6 -0
- commongen_pythia-31m/checkpoint-8000/tokenizer.json +0 -0
- commongen_pythia-31m/checkpoint-8000/tokenizer_config.json +212 -0
- commongen_pythia-31m/checkpoint-8000/trainer_state.json +435 -0
- commongen_pythia-31m/checkpoint-8000/training_args.bin +3 -0
- commongen_pythia-31m/config.json +30 -0
- commongen_pythia-31m/eval_results_lm.txt +1 -0
- commongen_pythia-31m/generation_config.json +6 -0
- commongen_pythia-31m/model.safetensors +3 -0
- commongen_pythia-31m/special_tokens_map.json +6 -0
- commongen_pythia-31m/tokenizer.json +0 -0
- commongen_pythia-31m/tokenizer_config.json +212 -0
- commongen_pythia-31m/training_args.bin +3 -0
commongen_pythia-31m/checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/models/pythia-31m",
|
| 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": 256,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1024,
|
| 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 |
+
"pad_token_id": 0,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rotary_emb_base": 10000,
|
| 23 |
+
"rotary_pct": 0.25,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.35.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_parallel_residual": true,
|
| 29 |
+
"vocab_size": 50304
|
| 30 |
+
}
|
commongen_pythia-31m/checkpoint-8000/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": "4.35.0"
|
| 6 |
+
}
|
commongen_pythia-31m/checkpoint-8000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9527b9612977cad35f18c3b798df98da63c626796e7c358f9b055aed96c7d98f
|
| 3 |
+
size 121987544
|
commongen_pythia-31m/checkpoint-8000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4d819c21b17f2496b16df9d03b83a43e6179ff1dd28aec99030dfd8dea2f35
|
| 3 |
+
size 244021626
|
commongen_pythia-31m/checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:618ef55f6c5423457249c94a2577645800716eebc494bf2745faa205a24bad51
|
| 3 |
+
size 14244
|
commongen_pythia-31m/checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdef972e1a0ff1e11e16586cda971ad22d33c909fff68ecf1a26b775487e3da5
|
| 3 |
+
size 1064
|
commongen_pythia-31m/checkpoint-8000/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 |
+
}
|
commongen_pythia-31m/checkpoint-8000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
commongen_pythia-31m/checkpoint-8000/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 |
+
}
|
commongen_pythia-31m/checkpoint-8000/trainer_state.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 48.41484069824219,
|
| 3 |
+
"best_model_checkpoint": "/root/autodl-tmp/commongen_pythia-31m/checkpoint-8000",
|
| 4 |
+
"epoch": 3.798670465337132,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"eval_loss": 52.970680236816406,
|
| 14 |
+
"eval_runtime": 12.5645,
|
| 15 |
+
"eval_samples_per_second": 319.791,
|
| 16 |
+
"eval_steps_per_second": 20.057,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19,
|
| 21 |
+
"eval_loss": 52.02605056762695,
|
| 22 |
+
"eval_runtime": 12.5784,
|
| 23 |
+
"eval_samples_per_second": 319.436,
|
| 24 |
+
"eval_steps_per_second": 20.034,
|
| 25 |
+
"step": 400
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.24,
|
| 29 |
+
"learning_rate": 2.857549857549858e-06,
|
| 30 |
+
"loss": 52.0627,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.28,
|
| 35 |
+
"eval_loss": 51.40311813354492,
|
| 36 |
+
"eval_runtime": 12.566,
|
| 37 |
+
"eval_samples_per_second": 319.752,
|
| 38 |
+
"eval_steps_per_second": 20.054,
|
| 39 |
+
"step": 600
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.38,
|
| 43 |
+
"eval_loss": 50.70226287841797,
|
| 44 |
+
"eval_runtime": 12.5745,
|
| 45 |
+
"eval_samples_per_second": 319.536,
|
| 46 |
+
"eval_steps_per_second": 20.041,
|
| 47 |
+
"step": 800
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.47,
|
| 51 |
+
"learning_rate": 2.7150997150997152e-06,
|
| 52 |
+
"loss": 47.8887,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.47,
|
| 57 |
+
"eval_loss": 50.75849914550781,
|
| 58 |
+
"eval_runtime": 12.5717,
|
| 59 |
+
"eval_samples_per_second": 319.606,
|
| 60 |
+
"eval_steps_per_second": 20.045,
|
| 61 |
+
"step": 1000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.57,
|
| 65 |
+
"eval_loss": 50.17426300048828,
|
| 66 |
+
"eval_runtime": 12.5765,
|
| 67 |
+
"eval_samples_per_second": 319.485,
|
| 68 |
+
"eval_steps_per_second": 20.037,
|
| 69 |
+
"step": 1200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.66,
|
| 73 |
+
"eval_loss": 50.077945709228516,
|
| 74 |
+
"eval_runtime": 12.5588,
|
| 75 |
+
"eval_samples_per_second": 319.935,
|
| 76 |
+
"eval_steps_per_second": 20.066,
|
| 77 |
+
"step": 1400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.71,
|
| 81 |
+
"learning_rate": 2.5726495726495726e-06,
|
| 82 |
+
"loss": 46.0161,
|
| 83 |
+
"step": 1500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.76,
|
| 87 |
+
"eval_loss": 49.861305236816406,
|
| 88 |
+
"eval_runtime": 12.6412,
|
| 89 |
+
"eval_samples_per_second": 317.85,
|
| 90 |
+
"eval_steps_per_second": 19.935,
|
| 91 |
+
"step": 1600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.85,
|
| 95 |
+
"eval_loss": 49.89344024658203,
|
| 96 |
+
"eval_runtime": 12.5888,
|
| 97 |
+
"eval_samples_per_second": 319.173,
|
| 98 |
+
"eval_steps_per_second": 20.018,
|
| 99 |
+
"step": 1800
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.95,
|
| 103 |
+
"learning_rate": 2.43019943019943e-06,
|
| 104 |
+
"loss": 45.0075,
|
| 105 |
+
"step": 2000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.95,
|
| 109 |
+
"eval_loss": 49.6607666015625,
|
| 110 |
+
"eval_runtime": 12.5715,
|
| 111 |
+
"eval_samples_per_second": 319.611,
|
| 112 |
+
"eval_steps_per_second": 20.045,
|
| 113 |
+
"step": 2000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.04,
|
| 117 |
+
"eval_loss": 49.48630142211914,
|
| 118 |
+
"eval_runtime": 12.5778,
|
| 119 |
+
"eval_samples_per_second": 319.452,
|
| 120 |
+
"eval_steps_per_second": 20.035,
|
| 121 |
+
"step": 2200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.14,
|
| 125 |
+
"eval_loss": 49.40906524658203,
|
| 126 |
+
"eval_runtime": 12.5781,
|
| 127 |
+
"eval_samples_per_second": 319.445,
|
| 128 |
+
"eval_steps_per_second": 20.035,
|
| 129 |
+
"step": 2400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.19,
|
| 133 |
+
"learning_rate": 2.2877492877492878e-06,
|
| 134 |
+
"loss": 44.1407,
|
| 135 |
+
"step": 2500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.23,
|
| 139 |
+
"eval_loss": 49.23854446411133,
|
| 140 |
+
"eval_runtime": 12.6005,
|
| 141 |
+
"eval_samples_per_second": 318.875,
|
| 142 |
+
"eval_steps_per_second": 19.999,
|
| 143 |
+
"step": 2600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.33,
|
| 147 |
+
"eval_loss": 49.09724807739258,
|
| 148 |
+
"eval_runtime": 12.5887,
|
| 149 |
+
"eval_samples_per_second": 319.176,
|
| 150 |
+
"eval_steps_per_second": 20.018,
|
| 151 |
+
"step": 2800
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.42,
|
| 155 |
+
"learning_rate": 2.1452991452991456e-06,
|
| 156 |
+
"loss": 43.5951,
|
| 157 |
+
"step": 3000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.42,
|
| 161 |
+
"eval_loss": 49.57240676879883,
|
| 162 |
+
"eval_runtime": 12.5959,
|
| 163 |
+
"eval_samples_per_second": 318.994,
|
| 164 |
+
"eval_steps_per_second": 20.007,
|
| 165 |
+
"step": 3000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.52,
|
| 169 |
+
"eval_loss": 48.90445327758789,
|
| 170 |
+
"eval_runtime": 12.5867,
|
| 171 |
+
"eval_samples_per_second": 319.225,
|
| 172 |
+
"eval_steps_per_second": 20.021,
|
| 173 |
+
"step": 3200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.61,
|
| 177 |
+
"eval_loss": 49.11627960205078,
|
| 178 |
+
"eval_runtime": 12.5909,
|
| 179 |
+
"eval_samples_per_second": 319.12,
|
| 180 |
+
"eval_steps_per_second": 20.014,
|
| 181 |
+
"step": 3400
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.66,
|
| 185 |
+
"learning_rate": 2.002849002849003e-06,
|
| 186 |
+
"loss": 42.9995,
|
| 187 |
+
"step": 3500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.71,
|
| 191 |
+
"eval_loss": 48.88859176635742,
|
| 192 |
+
"eval_runtime": 12.5894,
|
| 193 |
+
"eval_samples_per_second": 319.158,
|
| 194 |
+
"eval_steps_per_second": 20.017,
|
| 195 |
+
"step": 3600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.8,
|
| 199 |
+
"eval_loss": 48.93570327758789,
|
| 200 |
+
"eval_runtime": 12.5645,
|
| 201 |
+
"eval_samples_per_second": 319.791,
|
| 202 |
+
"eval_steps_per_second": 20.057,
|
| 203 |
+
"step": 3800
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.9,
|
| 207 |
+
"learning_rate": 1.8603988603988605e-06,
|
| 208 |
+
"loss": 42.8735,
|
| 209 |
+
"step": 4000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.9,
|
| 213 |
+
"eval_loss": 48.8524055480957,
|
| 214 |
+
"eval_runtime": 12.5959,
|
| 215 |
+
"eval_samples_per_second": 318.993,
|
| 216 |
+
"eval_steps_per_second": 20.007,
|
| 217 |
+
"step": 4000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.99,
|
| 221 |
+
"eval_loss": 48.787391662597656,
|
| 222 |
+
"eval_runtime": 12.592,
|
| 223 |
+
"eval_samples_per_second": 319.091,
|
| 224 |
+
"eval_steps_per_second": 20.013,
|
| 225 |
+
"step": 4200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.09,
|
| 229 |
+
"eval_loss": 48.82841110229492,
|
| 230 |
+
"eval_runtime": 12.5823,
|
| 231 |
+
"eval_samples_per_second": 319.337,
|
| 232 |
+
"eval_steps_per_second": 20.028,
|
| 233 |
+
"step": 4400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.14,
|
| 237 |
+
"learning_rate": 1.7179487179487179e-06,
|
| 238 |
+
"loss": 42.0832,
|
| 239 |
+
"step": 4500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.18,
|
| 243 |
+
"eval_loss": 48.749610900878906,
|
| 244 |
+
"eval_runtime": 12.5741,
|
| 245 |
+
"eval_samples_per_second": 319.546,
|
| 246 |
+
"eval_steps_per_second": 20.041,
|
| 247 |
+
"step": 4600
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.28,
|
| 251 |
+
"eval_loss": 48.68989944458008,
|
| 252 |
+
"eval_runtime": 12.5987,
|
| 253 |
+
"eval_samples_per_second": 318.923,
|
| 254 |
+
"eval_steps_per_second": 20.002,
|
| 255 |
+
"step": 4800
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.37,
|
| 259 |
+
"learning_rate": 1.5754985754985755e-06,
|
| 260 |
+
"loss": 41.8331,
|
| 261 |
+
"step": 5000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.37,
|
| 265 |
+
"eval_loss": 48.606868743896484,
|
| 266 |
+
"eval_runtime": 12.5733,
|
| 267 |
+
"eval_samples_per_second": 319.567,
|
| 268 |
+
"eval_steps_per_second": 20.043,
|
| 269 |
+
"step": 5000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.47,
|
| 273 |
+
"eval_loss": 48.69475555419922,
|
| 274 |
+
"eval_runtime": 12.5785,
|
| 275 |
+
"eval_samples_per_second": 319.433,
|
| 276 |
+
"eval_steps_per_second": 20.034,
|
| 277 |
+
"step": 5200
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.56,
|
| 281 |
+
"eval_loss": 48.63117599487305,
|
| 282 |
+
"eval_runtime": 12.5823,
|
| 283 |
+
"eval_samples_per_second": 319.339,
|
| 284 |
+
"eval_steps_per_second": 20.028,
|
| 285 |
+
"step": 5400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.61,
|
| 289 |
+
"learning_rate": 1.433048433048433e-06,
|
| 290 |
+
"loss": 41.5916,
|
| 291 |
+
"step": 5500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.66,
|
| 295 |
+
"eval_loss": 48.66645431518555,
|
| 296 |
+
"eval_runtime": 12.5828,
|
| 297 |
+
"eval_samples_per_second": 319.325,
|
| 298 |
+
"eval_steps_per_second": 20.027,
|
| 299 |
+
"step": 5600
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.75,
|
| 303 |
+
"eval_loss": 48.68837356567383,
|
| 304 |
+
"eval_runtime": 12.5633,
|
| 305 |
+
"eval_samples_per_second": 319.82,
|
| 306 |
+
"eval_steps_per_second": 20.058,
|
| 307 |
+
"step": 5800
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.85,
|
| 311 |
+
"learning_rate": 1.2905982905982906e-06,
|
| 312 |
+
"loss": 41.7327,
|
| 313 |
+
"step": 6000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.85,
|
| 317 |
+
"eval_loss": 48.66307067871094,
|
| 318 |
+
"eval_runtime": 12.5978,
|
| 319 |
+
"eval_samples_per_second": 318.943,
|
| 320 |
+
"eval_steps_per_second": 20.003,
|
| 321 |
+
"step": 6000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.94,
|
| 325 |
+
"eval_loss": 48.6628303527832,
|
| 326 |
+
"eval_runtime": 12.5756,
|
| 327 |
+
"eval_samples_per_second": 319.507,
|
| 328 |
+
"eval_steps_per_second": 20.039,
|
| 329 |
+
"step": 6200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.04,
|
| 333 |
+
"eval_loss": 48.6637077331543,
|
| 334 |
+
"eval_runtime": 12.5794,
|
| 335 |
+
"eval_samples_per_second": 319.412,
|
| 336 |
+
"eval_steps_per_second": 20.033,
|
| 337 |
+
"step": 6400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.09,
|
| 341 |
+
"learning_rate": 1.1481481481481482e-06,
|
| 342 |
+
"loss": 41.2561,
|
| 343 |
+
"step": 6500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 3.13,
|
| 347 |
+
"eval_loss": 48.63277816772461,
|
| 348 |
+
"eval_runtime": 12.6071,
|
| 349 |
+
"eval_samples_per_second": 318.709,
|
| 350 |
+
"eval_steps_per_second": 19.989,
|
| 351 |
+
"step": 6600
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.23,
|
| 355 |
+
"eval_loss": 48.62044143676758,
|
| 356 |
+
"eval_runtime": 12.645,
|
| 357 |
+
"eval_samples_per_second": 317.755,
|
| 358 |
+
"eval_steps_per_second": 19.929,
|
| 359 |
+
"step": 6800
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.32,
|
| 363 |
+
"learning_rate": 1.0056980056980058e-06,
|
| 364 |
+
"loss": 40.9138,
|
| 365 |
+
"step": 7000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.32,
|
| 369 |
+
"eval_loss": 48.741756439208984,
|
| 370 |
+
"eval_runtime": 12.605,
|
| 371 |
+
"eval_samples_per_second": 318.762,
|
| 372 |
+
"eval_steps_per_second": 19.992,
|
| 373 |
+
"step": 7000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.42,
|
| 377 |
+
"eval_loss": 48.55778121948242,
|
| 378 |
+
"eval_runtime": 12.574,
|
| 379 |
+
"eval_samples_per_second": 319.549,
|
| 380 |
+
"eval_steps_per_second": 20.041,
|
| 381 |
+
"step": 7200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.51,
|
| 385 |
+
"eval_loss": 48.64768981933594,
|
| 386 |
+
"eval_runtime": 12.6171,
|
| 387 |
+
"eval_samples_per_second": 318.456,
|
| 388 |
+
"eval_steps_per_second": 19.973,
|
| 389 |
+
"step": 7400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.56,
|
| 393 |
+
"learning_rate": 8.632478632478633e-07,
|
| 394 |
+
"loss": 40.6184,
|
| 395 |
+
"step": 7500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.61,
|
| 399 |
+
"eval_loss": 48.60110855102539,
|
| 400 |
+
"eval_runtime": 12.5962,
|
| 401 |
+
"eval_samples_per_second": 318.985,
|
| 402 |
+
"eval_steps_per_second": 20.006,
|
| 403 |
+
"step": 7600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.7,
|
| 407 |
+
"eval_loss": 48.50035858154297,
|
| 408 |
+
"eval_runtime": 12.579,
|
| 409 |
+
"eval_samples_per_second": 319.42,
|
| 410 |
+
"eval_steps_per_second": 20.033,
|
| 411 |
+
"step": 7800
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.8,
|
| 415 |
+
"learning_rate": 7.207977207977208e-07,
|
| 416 |
+
"loss": 40.7413,
|
| 417 |
+
"step": 8000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.8,
|
| 421 |
+
"eval_loss": 48.41484069824219,
|
| 422 |
+
"eval_runtime": 12.5819,
|
| 423 |
+
"eval_samples_per_second": 319.347,
|
| 424 |
+
"eval_steps_per_second": 20.029,
|
| 425 |
+
"step": 8000
|
| 426 |
+
}
|
| 427 |
+
],
|
| 428 |
+
"logging_steps": 500,
|
| 429 |
+
"max_steps": 10530,
|
| 430 |
+
"num_train_epochs": 5,
|
| 431 |
+
"save_steps": 200,
|
| 432 |
+
"total_flos": 1.3854003683131392e+16,
|
| 433 |
+
"trial_name": null,
|
| 434 |
+
"trial_params": null
|
| 435 |
+
}
|
commongen_pythia-31m/checkpoint-8000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc19eb9fb38c4a919e40e6d7b37f043566aa3e66fd498983fa89877d8b5b063
|
| 3 |
+
size 4600
|
commongen_pythia-31m/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/models/pythia-31m",
|
| 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": 256,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1024,
|
| 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 |
+
"pad_token_id": 0,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rotary_emb_base": 10000,
|
| 23 |
+
"rotary_pct": 0.25,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.35.0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_parallel_residual": true,
|
| 29 |
+
"vocab_size": 50304
|
| 30 |
+
}
|
commongen_pythia-31m/eval_results_lm.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
perplexity = 1.0624246964413739e+21
|
commongen_pythia-31m/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": "4.35.0"
|
| 6 |
+
}
|
commongen_pythia-31m/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9527b9612977cad35f18c3b798df98da63c626796e7c358f9b055aed96c7d98f
|
| 3 |
+
size 121987544
|
commongen_pythia-31m/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 |
+
}
|
commongen_pythia-31m/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
commongen_pythia-31m/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 |
+
}
|
commongen_pythia-31m/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc19eb9fb38c4a919e40e6d7b37f043566aa3e66fd498983fa89877d8b5b063
|
| 3 |
+
size 4600
|