Upload folder using huggingface_hub
Browse files- commongen_pythia-160m/checkpoint-4200/config.json +30 -0
- commongen_pythia-160m/checkpoint-4200/generation_config.json +6 -0
- commongen_pythia-160m/checkpoint-4200/model.safetensors +3 -0
- commongen_pythia-160m/checkpoint-4200/optimizer.pt +3 -0
- commongen_pythia-160m/checkpoint-4200/rng_state.pth +3 -0
- commongen_pythia-160m/checkpoint-4200/scheduler.pt +3 -0
- commongen_pythia-160m/checkpoint-4200/special_tokens_map.json +6 -0
- commongen_pythia-160m/checkpoint-4200/tokenizer.json +0 -0
- commongen_pythia-160m/checkpoint-4200/tokenizer_config.json +212 -0
- commongen_pythia-160m/checkpoint-4200/trainer_state.json +235 -0
- commongen_pythia-160m/checkpoint-4200/training_args.bin +3 -0
- commongen_pythia-160m/config.json +6 -2
- commongen_pythia-160m/eval_results_lm.txt +1 -1
- commongen_pythia-160m/generation_config.json +6 -0
- commongen_pythia-160m/model.safetensors +3 -0
- commongen_pythia-160m/tokenizer_config.json +205 -2
- commongen_pythia-160m/training_args.bin +2 -2
commongen_pythia-160m/checkpoint-4200/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/models/pythia-160m",
|
| 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": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 2048,
|
| 17 |
+
"model_type": "gpt_neox",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 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-160m/checkpoint-4200/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-160m/checkpoint-4200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29e6e142d9bf8728dfa3e5bafb2d718c92665a669cdc941aa39d46b5a2770e2d
|
| 3 |
+
size 649308728
|
commongen_pythia-160m/checkpoint-4200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5afe8304d98ead933b197c30826bf4674492ed13bcf3506964d27ed74c054a1c
|
| 3 |
+
size 1298707386
|
commongen_pythia-160m/checkpoint-4200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa162e4b259528d57df6ef1186bb5134c28c62a8f151c30af24d16e51cc8792d
|
| 3 |
+
size 14244
|
commongen_pythia-160m/checkpoint-4200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a08daf663064db9d1d66accb2f5a92ff1bd9d1e7d1cae02985a5e856e4d228
|
| 3 |
+
size 1064
|
commongen_pythia-160m/checkpoint-4200/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-160m/checkpoint-4200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
commongen_pythia-160m/checkpoint-4200/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-160m/checkpoint-4200/trainer_state.json
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 38.17561721801758,
|
| 3 |
+
"best_model_checkpoint": "/root/autodl-tmp/commongen_pythia-160m/checkpoint-4200",
|
| 4 |
+
"epoch": 1.9943019943019942,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 4200,
|
| 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": 40.878292083740234,
|
| 14 |
+
"eval_runtime": 31.6071,
|
| 15 |
+
"eval_samples_per_second": 127.124,
|
| 16 |
+
"eval_steps_per_second": 7.973,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19,
|
| 21 |
+
"eval_loss": 40.0030632019043,
|
| 22 |
+
"eval_runtime": 32.0957,
|
| 23 |
+
"eval_samples_per_second": 125.188,
|
| 24 |
+
"eval_steps_per_second": 7.852,
|
| 25 |
+
"step": 400
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.24,
|
| 29 |
+
"learning_rate": 2.857549857549858e-06,
|
| 30 |
+
"loss": 40.7376,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.28,
|
| 35 |
+
"eval_loss": 39.902565002441406,
|
| 36 |
+
"eval_runtime": 31.7745,
|
| 37 |
+
"eval_samples_per_second": 126.454,
|
| 38 |
+
"eval_steps_per_second": 7.931,
|
| 39 |
+
"step": 600
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.38,
|
| 43 |
+
"eval_loss": 39.43976974487305,
|
| 44 |
+
"eval_runtime": 31.6834,
|
| 45 |
+
"eval_samples_per_second": 126.817,
|
| 46 |
+
"eval_steps_per_second": 7.954,
|
| 47 |
+
"step": 800
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.47,
|
| 51 |
+
"learning_rate": 2.7150997150997152e-06,
|
| 52 |
+
"loss": 37.1707,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.47,
|
| 57 |
+
"eval_loss": 39.4637336730957,
|
| 58 |
+
"eval_runtime": 31.4241,
|
| 59 |
+
"eval_samples_per_second": 127.864,
|
| 60 |
+
"eval_steps_per_second": 8.019,
|
| 61 |
+
"step": 1000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.57,
|
| 65 |
+
"eval_loss": 38.90019226074219,
|
| 66 |
+
"eval_runtime": 31.576,
|
| 67 |
+
"eval_samples_per_second": 127.249,
|
| 68 |
+
"eval_steps_per_second": 7.981,
|
| 69 |
+
"step": 1200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.66,
|
| 73 |
+
"eval_loss": 38.968284606933594,
|
| 74 |
+
"eval_runtime": 31.487,
|
| 75 |
+
"eval_samples_per_second": 127.608,
|
| 76 |
+
"eval_steps_per_second": 8.003,
|
| 77 |
+
"step": 1400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.71,
|
| 81 |
+
"learning_rate": 2.5726495726495726e-06,
|
| 82 |
+
"loss": 35.44,
|
| 83 |
+
"step": 1500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.76,
|
| 87 |
+
"eval_loss": 38.754234313964844,
|
| 88 |
+
"eval_runtime": 31.6366,
|
| 89 |
+
"eval_samples_per_second": 127.005,
|
| 90 |
+
"eval_steps_per_second": 7.965,
|
| 91 |
+
"step": 1600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.85,
|
| 95 |
+
"eval_loss": 39.10488510131836,
|
| 96 |
+
"eval_runtime": 31.4847,
|
| 97 |
+
"eval_samples_per_second": 127.618,
|
| 98 |
+
"eval_steps_per_second": 8.004,
|
| 99 |
+
"step": 1800
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.95,
|
| 103 |
+
"learning_rate": 2.43019943019943e-06,
|
| 104 |
+
"loss": 34.4738,
|
| 105 |
+
"step": 2000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.95,
|
| 109 |
+
"eval_loss": 38.68024444580078,
|
| 110 |
+
"eval_runtime": 31.5379,
|
| 111 |
+
"eval_samples_per_second": 127.402,
|
| 112 |
+
"eval_steps_per_second": 7.99,
|
| 113 |
+
"step": 2000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.04,
|
| 117 |
+
"eval_loss": 38.74475860595703,
|
| 118 |
+
"eval_runtime": 31.4804,
|
| 119 |
+
"eval_samples_per_second": 127.635,
|
| 120 |
+
"eval_steps_per_second": 8.005,
|
| 121 |
+
"step": 2200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.14,
|
| 125 |
+
"eval_loss": 38.3890266418457,
|
| 126 |
+
"eval_runtime": 31.473,
|
| 127 |
+
"eval_samples_per_second": 127.665,
|
| 128 |
+
"eval_steps_per_second": 8.007,
|
| 129 |
+
"step": 2400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.19,
|
| 133 |
+
"learning_rate": 2.2877492877492878e-06,
|
| 134 |
+
"loss": 32.9663,
|
| 135 |
+
"step": 2500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.23,
|
| 139 |
+
"eval_loss": 38.70350646972656,
|
| 140 |
+
"eval_runtime": 31.6528,
|
| 141 |
+
"eval_samples_per_second": 126.94,
|
| 142 |
+
"eval_steps_per_second": 7.961,
|
| 143 |
+
"step": 2600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.33,
|
| 147 |
+
"eval_loss": 38.5815315246582,
|
| 148 |
+
"eval_runtime": 31.6616,
|
| 149 |
+
"eval_samples_per_second": 126.905,
|
| 150 |
+
"eval_steps_per_second": 7.959,
|
| 151 |
+
"step": 2800
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.42,
|
| 155 |
+
"learning_rate": 2.1452991452991456e-06,
|
| 156 |
+
"loss": 32.207,
|
| 157 |
+
"step": 3000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.42,
|
| 161 |
+
"eval_loss": 39.05810546875,
|
| 162 |
+
"eval_runtime": 31.3896,
|
| 163 |
+
"eval_samples_per_second": 128.004,
|
| 164 |
+
"eval_steps_per_second": 8.028,
|
| 165 |
+
"step": 3000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.52,
|
| 169 |
+
"eval_loss": 38.37156295776367,
|
| 170 |
+
"eval_runtime": 31.5129,
|
| 171 |
+
"eval_samples_per_second": 127.503,
|
| 172 |
+
"eval_steps_per_second": 7.997,
|
| 173 |
+
"step": 3200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.61,
|
| 177 |
+
"eval_loss": 38.7572135925293,
|
| 178 |
+
"eval_runtime": 31.6149,
|
| 179 |
+
"eval_samples_per_second": 127.092,
|
| 180 |
+
"eval_steps_per_second": 7.971,
|
| 181 |
+
"step": 3400
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.66,
|
| 185 |
+
"learning_rate": 2.002849002849003e-06,
|
| 186 |
+
"loss": 31.688,
|
| 187 |
+
"step": 3500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.71,
|
| 191 |
+
"eval_loss": 38.529903411865234,
|
| 192 |
+
"eval_runtime": 31.463,
|
| 193 |
+
"eval_samples_per_second": 127.706,
|
| 194 |
+
"eval_steps_per_second": 8.009,
|
| 195 |
+
"step": 3600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.8,
|
| 199 |
+
"eval_loss": 38.76222610473633,
|
| 200 |
+
"eval_runtime": 31.7691,
|
| 201 |
+
"eval_samples_per_second": 126.475,
|
| 202 |
+
"eval_steps_per_second": 7.932,
|
| 203 |
+
"step": 3800
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.9,
|
| 207 |
+
"learning_rate": 1.8603988603988605e-06,
|
| 208 |
+
"loss": 31.6849,
|
| 209 |
+
"step": 4000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.9,
|
| 213 |
+
"eval_loss": 38.42369079589844,
|
| 214 |
+
"eval_runtime": 31.5455,
|
| 215 |
+
"eval_samples_per_second": 127.372,
|
| 216 |
+
"eval_steps_per_second": 7.988,
|
| 217 |
+
"step": 4000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.99,
|
| 221 |
+
"eval_loss": 38.17561721801758,
|
| 222 |
+
"eval_runtime": 31.6756,
|
| 223 |
+
"eval_samples_per_second": 126.848,
|
| 224 |
+
"eval_steps_per_second": 7.956,
|
| 225 |
+
"step": 4200
|
| 226 |
+
}
|
| 227 |
+
],
|
| 228 |
+
"logging_steps": 500,
|
| 229 |
+
"max_steps": 10530,
|
| 230 |
+
"num_train_epochs": 5,
|
| 231 |
+
"save_steps": 200,
|
| 232 |
+
"total_flos": 5.106737347087565e+16,
|
| 233 |
+
"trial_name": null,
|
| 234 |
+
"trial_params": null
|
| 235 |
+
}
|
commongen_pythia-160m/checkpoint-4200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a358522ba11ba088543bfe9410908b8a16515991e75e2a7dc5d3e32858aa69
|
| 3 |
+
size 4600
|
commongen_pythia-160m/config.json
CHANGED
|
@@ -1,11 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/root/autodl-tmp/models/pythia-160m
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"bos_token_id": 0,
|
|
|
|
| 7 |
"eos_token_id": 0,
|
| 8 |
"hidden_act": "gelu",
|
|
|
|
| 9 |
"hidden_size": 768,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 3072,
|
|
@@ -15,11 +18,12 @@
|
|
| 15 |
"num_attention_heads": 12,
|
| 16 |
"num_hidden_layers": 12,
|
| 17 |
"pad_token_id": 0,
|
|
|
|
| 18 |
"rotary_emb_base": 10000,
|
| 19 |
"rotary_pct": 0.25,
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
-
"transformers_version": "4.
|
| 23 |
"use_cache": true,
|
| 24 |
"use_parallel_residual": true,
|
| 25 |
"vocab_size": 50304
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/models/pythia-160m",
|
| 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": 768,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
|
|
|
| 18 |
"num_attention_heads": 12,
|
| 19 |
"num_hidden_layers": 12,
|
| 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
|
commongen_pythia-160m/eval_results_lm.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
perplexity =
|
|
|
|
| 1 |
+
perplexity = 3.7971687760844264e+16
|
commongen_pythia-160m/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-160m/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29e6e142d9bf8728dfa3e5bafb2d718c92665a669cdc941aa39d46b5a2770e2d
|
| 3 |
+
size 649308728
|
commongen_pythia-160m/tokenizer_config.json
CHANGED
|
@@ -1,9 +1,212 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
|
|
|
| 4 |
"eos_token": "<|endoftext|>",
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
"tokenizer_class": "GPTNeoXTokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|
|
|
|
| 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-160m/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a358522ba11ba088543bfe9410908b8a16515991e75e2a7dc5d3e32858aa69
|
| 3 |
+
size 4600
|