Upload folder using huggingface_hub
Browse files- commongen_pythia-70m/checkpoint-8600/config.json +30 -0
- commongen_pythia-70m/checkpoint-8600/generation_config.json +6 -0
- commongen_pythia-70m/checkpoint-8600/model.safetensors +3 -0
- commongen_pythia-70m/checkpoint-8600/optimizer.pt +3 -0
- commongen_pythia-70m/checkpoint-8600/rng_state.pth +3 -0
- commongen_pythia-70m/checkpoint-8600/scheduler.pt +3 -0
- commongen_pythia-70m/checkpoint-8600/special_tokens_map.json +6 -0
- commongen_pythia-70m/checkpoint-8600/tokenizer.json +0 -0
- commongen_pythia-70m/checkpoint-8600/tokenizer_config.json +212 -0
- commongen_pythia-70m/checkpoint-8600/trainer_state.json +465 -0
- commongen_pythia-70m/checkpoint-8600/training_args.bin +3 -0
- commongen_pythia-70m/config.json +6 -2
- commongen_pythia-70m/eval_results_lm.txt +1 -1
- commongen_pythia-70m/generation_config.json +6 -0
- commongen_pythia-70m/model.safetensors +3 -0
- commongen_pythia-70m/tokenizer_config.json +205 -2
- commongen_pythia-70m/training_args.bin +2 -2
commongen_pythia-70m/checkpoint-8600/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/autodl-tmp/models/pythia-70m",
|
| 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 |
+
"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-70m/checkpoint-8600/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-70m/checkpoint-8600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:743a48e3cb179148757389826df60de89f68ab05aa4d09b52d3562c04b287749
|
| 3 |
+
size 281715176
|
commongen_pythia-70m/checkpoint-8600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:583ad5be7f1d1ded87deb47845814628af849dd31423cd9fa36bf4b7af67aa03
|
| 3 |
+
size 563476858
|
commongen_pythia-70m/checkpoint-8600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76c0b77b75b104d52df7208449e713d15585ed674305a174ce34842d80400b09
|
| 3 |
+
size 14244
|
commongen_pythia-70m/checkpoint-8600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:190755b55d537470411618a77ef4166f486ecd76e22fa67093441787add8c1a8
|
| 3 |
+
size 1064
|
commongen_pythia-70m/checkpoint-8600/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-70m/checkpoint-8600/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
commongen_pythia-70m/checkpoint-8600/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-70m/checkpoint-8600/trainer_state.json
ADDED
|
@@ -0,0 +1,465 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 43.046226501464844,
|
| 3 |
+
"best_model_checkpoint": "/root/autodl-tmp/commongen_pythia-70m/checkpoint-8600",
|
| 4 |
+
"epoch": 4.083570750237417,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 8600,
|
| 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": 47.83369445800781,
|
| 14 |
+
"eval_runtime": 17.5902,
|
| 15 |
+
"eval_samples_per_second": 228.422,
|
| 16 |
+
"eval_steps_per_second": 14.326,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19,
|
| 21 |
+
"eval_loss": 46.72831726074219,
|
| 22 |
+
"eval_runtime": 17.8066,
|
| 23 |
+
"eval_samples_per_second": 225.646,
|
| 24 |
+
"eval_steps_per_second": 14.152,
|
| 25 |
+
"step": 400
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.24,
|
| 29 |
+
"learning_rate": 2.857549857549858e-06,
|
| 30 |
+
"loss": 47.1254,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.28,
|
| 35 |
+
"eval_loss": 46.19195556640625,
|
| 36 |
+
"eval_runtime": 17.912,
|
| 37 |
+
"eval_samples_per_second": 224.32,
|
| 38 |
+
"eval_steps_per_second": 14.069,
|
| 39 |
+
"step": 600
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.38,
|
| 43 |
+
"eval_loss": 45.1739387512207,
|
| 44 |
+
"eval_runtime": 17.6872,
|
| 45 |
+
"eval_samples_per_second": 227.17,
|
| 46 |
+
"eval_steps_per_second": 14.248,
|
| 47 |
+
"step": 800
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.47,
|
| 51 |
+
"learning_rate": 2.7150997150997152e-06,
|
| 52 |
+
"loss": 43.0537,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.47,
|
| 57 |
+
"eval_loss": 45.1984748840332,
|
| 58 |
+
"eval_runtime": 17.5532,
|
| 59 |
+
"eval_samples_per_second": 228.904,
|
| 60 |
+
"eval_steps_per_second": 14.356,
|
| 61 |
+
"step": 1000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.57,
|
| 65 |
+
"eval_loss": 44.58640670776367,
|
| 66 |
+
"eval_runtime": 17.582,
|
| 67 |
+
"eval_samples_per_second": 228.529,
|
| 68 |
+
"eval_steps_per_second": 14.333,
|
| 69 |
+
"step": 1200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.66,
|
| 73 |
+
"eval_loss": 44.28689956665039,
|
| 74 |
+
"eval_runtime": 17.3637,
|
| 75 |
+
"eval_samples_per_second": 231.403,
|
| 76 |
+
"eval_steps_per_second": 14.513,
|
| 77 |
+
"step": 1400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.71,
|
| 81 |
+
"learning_rate": 2.5726495726495726e-06,
|
| 82 |
+
"loss": 41.1501,
|
| 83 |
+
"step": 1500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.76,
|
| 87 |
+
"eval_loss": 44.08658218383789,
|
| 88 |
+
"eval_runtime": 17.5561,
|
| 89 |
+
"eval_samples_per_second": 228.866,
|
| 90 |
+
"eval_steps_per_second": 14.354,
|
| 91 |
+
"step": 1600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.85,
|
| 95 |
+
"eval_loss": 44.149330139160156,
|
| 96 |
+
"eval_runtime": 17.5361,
|
| 97 |
+
"eval_samples_per_second": 229.127,
|
| 98 |
+
"eval_steps_per_second": 14.37,
|
| 99 |
+
"step": 1800
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.95,
|
| 103 |
+
"learning_rate": 2.43019943019943e-06,
|
| 104 |
+
"loss": 40.1033,
|
| 105 |
+
"step": 2000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.95,
|
| 109 |
+
"eval_loss": 43.90538024902344,
|
| 110 |
+
"eval_runtime": 17.5312,
|
| 111 |
+
"eval_samples_per_second": 229.191,
|
| 112 |
+
"eval_steps_per_second": 14.374,
|
| 113 |
+
"step": 2000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.04,
|
| 117 |
+
"eval_loss": 43.843971252441406,
|
| 118 |
+
"eval_runtime": 17.407,
|
| 119 |
+
"eval_samples_per_second": 230.827,
|
| 120 |
+
"eval_steps_per_second": 14.477,
|
| 121 |
+
"step": 2200
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.14,
|
| 125 |
+
"eval_loss": 43.878173828125,
|
| 126 |
+
"eval_runtime": 17.4348,
|
| 127 |
+
"eval_samples_per_second": 230.459,
|
| 128 |
+
"eval_steps_per_second": 14.454,
|
| 129 |
+
"step": 2400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.19,
|
| 133 |
+
"learning_rate": 2.2877492877492878e-06,
|
| 134 |
+
"loss": 39.036,
|
| 135 |
+
"step": 2500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.23,
|
| 139 |
+
"eval_loss": 43.662635803222656,
|
| 140 |
+
"eval_runtime": 17.7227,
|
| 141 |
+
"eval_samples_per_second": 226.715,
|
| 142 |
+
"eval_steps_per_second": 14.219,
|
| 143 |
+
"step": 2600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.33,
|
| 147 |
+
"eval_loss": 43.485931396484375,
|
| 148 |
+
"eval_runtime": 17.791,
|
| 149 |
+
"eval_samples_per_second": 225.845,
|
| 150 |
+
"eval_steps_per_second": 14.164,
|
| 151 |
+
"step": 2800
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.42,
|
| 155 |
+
"learning_rate": 2.1452991452991456e-06,
|
| 156 |
+
"loss": 38.4263,
|
| 157 |
+
"step": 3000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.42,
|
| 161 |
+
"eval_loss": 43.90846633911133,
|
| 162 |
+
"eval_runtime": 17.5707,
|
| 163 |
+
"eval_samples_per_second": 228.676,
|
| 164 |
+
"eval_steps_per_second": 14.342,
|
| 165 |
+
"step": 3000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.52,
|
| 169 |
+
"eval_loss": 43.372650146484375,
|
| 170 |
+
"eval_runtime": 17.5187,
|
| 171 |
+
"eval_samples_per_second": 229.355,
|
| 172 |
+
"eval_steps_per_second": 14.385,
|
| 173 |
+
"step": 3200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.61,
|
| 177 |
+
"eval_loss": 43.63519287109375,
|
| 178 |
+
"eval_runtime": 17.5622,
|
| 179 |
+
"eval_samples_per_second": 228.787,
|
| 180 |
+
"eval_steps_per_second": 14.349,
|
| 181 |
+
"step": 3400
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.66,
|
| 185 |
+
"learning_rate": 2.002849002849003e-06,
|
| 186 |
+
"loss": 37.7644,
|
| 187 |
+
"step": 3500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.71,
|
| 191 |
+
"eval_loss": 43.45486068725586,
|
| 192 |
+
"eval_runtime": 17.7543,
|
| 193 |
+
"eval_samples_per_second": 226.311,
|
| 194 |
+
"eval_steps_per_second": 14.194,
|
| 195 |
+
"step": 3600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.8,
|
| 199 |
+
"eval_loss": 43.57573318481445,
|
| 200 |
+
"eval_runtime": 17.458,
|
| 201 |
+
"eval_samples_per_second": 230.153,
|
| 202 |
+
"eval_steps_per_second": 14.435,
|
| 203 |
+
"step": 3800
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.9,
|
| 207 |
+
"learning_rate": 1.8603988603988605e-06,
|
| 208 |
+
"loss": 37.6616,
|
| 209 |
+
"step": 4000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.9,
|
| 213 |
+
"eval_loss": 43.24225997924805,
|
| 214 |
+
"eval_runtime": 17.7066,
|
| 215 |
+
"eval_samples_per_second": 226.922,
|
| 216 |
+
"eval_steps_per_second": 14.232,
|
| 217 |
+
"step": 4000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.99,
|
| 221 |
+
"eval_loss": 43.16454315185547,
|
| 222 |
+
"eval_runtime": 17.4231,
|
| 223 |
+
"eval_samples_per_second": 230.614,
|
| 224 |
+
"eval_steps_per_second": 14.464,
|
| 225 |
+
"step": 4200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.09,
|
| 229 |
+
"eval_loss": 43.32307815551758,
|
| 230 |
+
"eval_runtime": 18.0286,
|
| 231 |
+
"eval_samples_per_second": 222.868,
|
| 232 |
+
"eval_steps_per_second": 13.978,
|
| 233 |
+
"step": 4400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.14,
|
| 237 |
+
"learning_rate": 1.7179487179487179e-06,
|
| 238 |
+
"loss": 36.7498,
|
| 239 |
+
"step": 4500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.18,
|
| 243 |
+
"eval_loss": 43.287681579589844,
|
| 244 |
+
"eval_runtime": 17.9722,
|
| 245 |
+
"eval_samples_per_second": 223.568,
|
| 246 |
+
"eval_steps_per_second": 14.022,
|
| 247 |
+
"step": 4600
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.28,
|
| 251 |
+
"eval_loss": 43.1135368347168,
|
| 252 |
+
"eval_runtime": 17.4596,
|
| 253 |
+
"eval_samples_per_second": 230.131,
|
| 254 |
+
"eval_steps_per_second": 14.433,
|
| 255 |
+
"step": 4800
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.37,
|
| 259 |
+
"learning_rate": 1.5754985754985755e-06,
|
| 260 |
+
"loss": 36.4399,
|
| 261 |
+
"step": 5000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.37,
|
| 265 |
+
"eval_loss": 43.195556640625,
|
| 266 |
+
"eval_runtime": 17.4782,
|
| 267 |
+
"eval_samples_per_second": 229.886,
|
| 268 |
+
"eval_steps_per_second": 14.418,
|
| 269 |
+
"step": 5000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.47,
|
| 273 |
+
"eval_loss": 43.21245193481445,
|
| 274 |
+
"eval_runtime": 17.4824,
|
| 275 |
+
"eval_samples_per_second": 229.832,
|
| 276 |
+
"eval_steps_per_second": 14.415,
|
| 277 |
+
"step": 5200
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.56,
|
| 281 |
+
"eval_loss": 43.142669677734375,
|
| 282 |
+
"eval_runtime": 18.1523,
|
| 283 |
+
"eval_samples_per_second": 221.349,
|
| 284 |
+
"eval_steps_per_second": 13.883,
|
| 285 |
+
"step": 5400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.61,
|
| 289 |
+
"learning_rate": 1.433048433048433e-06,
|
| 290 |
+
"loss": 36.1872,
|
| 291 |
+
"step": 5500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.66,
|
| 295 |
+
"eval_loss": 43.24208450317383,
|
| 296 |
+
"eval_runtime": 17.6173,
|
| 297 |
+
"eval_samples_per_second": 228.071,
|
| 298 |
+
"eval_steps_per_second": 14.304,
|
| 299 |
+
"step": 5600
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.75,
|
| 303 |
+
"eval_loss": 43.28342056274414,
|
| 304 |
+
"eval_runtime": 17.6228,
|
| 305 |
+
"eval_samples_per_second": 228.0,
|
| 306 |
+
"eval_steps_per_second": 14.3,
|
| 307 |
+
"step": 5800
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.85,
|
| 311 |
+
"learning_rate": 1.2905982905982906e-06,
|
| 312 |
+
"loss": 36.2919,
|
| 313 |
+
"step": 6000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.85,
|
| 317 |
+
"eval_loss": 43.10586166381836,
|
| 318 |
+
"eval_runtime": 17.4803,
|
| 319 |
+
"eval_samples_per_second": 229.859,
|
| 320 |
+
"eval_steps_per_second": 14.416,
|
| 321 |
+
"step": 6000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.94,
|
| 325 |
+
"eval_loss": 43.27060317993164,
|
| 326 |
+
"eval_runtime": 17.4806,
|
| 327 |
+
"eval_samples_per_second": 229.855,
|
| 328 |
+
"eval_steps_per_second": 14.416,
|
| 329 |
+
"step": 6200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.04,
|
| 333 |
+
"eval_loss": 43.2691650390625,
|
| 334 |
+
"eval_runtime": 17.5127,
|
| 335 |
+
"eval_samples_per_second": 229.434,
|
| 336 |
+
"eval_steps_per_second": 14.39,
|
| 337 |
+
"step": 6400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.09,
|
| 341 |
+
"learning_rate": 1.1481481481481482e-06,
|
| 342 |
+
"loss": 35.7585,
|
| 343 |
+
"step": 6500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 3.13,
|
| 347 |
+
"eval_loss": 43.2242546081543,
|
| 348 |
+
"eval_runtime": 17.6198,
|
| 349 |
+
"eval_samples_per_second": 228.039,
|
| 350 |
+
"eval_steps_per_second": 14.302,
|
| 351 |
+
"step": 6600
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.23,
|
| 355 |
+
"eval_loss": 43.14311981201172,
|
| 356 |
+
"eval_runtime": 17.4694,
|
| 357 |
+
"eval_samples_per_second": 230.002,
|
| 358 |
+
"eval_steps_per_second": 14.425,
|
| 359 |
+
"step": 6800
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.32,
|
| 363 |
+
"learning_rate": 1.0056980056980058e-06,
|
| 364 |
+
"loss": 35.3139,
|
| 365 |
+
"step": 7000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.32,
|
| 369 |
+
"eval_loss": 43.319889068603516,
|
| 370 |
+
"eval_runtime": 17.4795,
|
| 371 |
+
"eval_samples_per_second": 229.87,
|
| 372 |
+
"eval_steps_per_second": 14.417,
|
| 373 |
+
"step": 7000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.42,
|
| 377 |
+
"eval_loss": 43.201454162597656,
|
| 378 |
+
"eval_runtime": 17.5518,
|
| 379 |
+
"eval_samples_per_second": 228.922,
|
| 380 |
+
"eval_steps_per_second": 14.357,
|
| 381 |
+
"step": 7200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.51,
|
| 385 |
+
"eval_loss": 43.31747817993164,
|
| 386 |
+
"eval_runtime": 17.5833,
|
| 387 |
+
"eval_samples_per_second": 228.512,
|
| 388 |
+
"eval_steps_per_second": 14.332,
|
| 389 |
+
"step": 7400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.56,
|
| 393 |
+
"learning_rate": 8.632478632478633e-07,
|
| 394 |
+
"loss": 35.083,
|
| 395 |
+
"step": 7500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.61,
|
| 399 |
+
"eval_loss": 43.189640045166016,
|
| 400 |
+
"eval_runtime": 17.401,
|
| 401 |
+
"eval_samples_per_second": 230.906,
|
| 402 |
+
"eval_steps_per_second": 14.482,
|
| 403 |
+
"step": 7600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.7,
|
| 407 |
+
"eval_loss": 43.152198791503906,
|
| 408 |
+
"eval_runtime": 17.4202,
|
| 409 |
+
"eval_samples_per_second": 230.651,
|
| 410 |
+
"eval_steps_per_second": 14.466,
|
| 411 |
+
"step": 7800
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.8,
|
| 415 |
+
"learning_rate": 7.207977207977208e-07,
|
| 416 |
+
"loss": 35.1642,
|
| 417 |
+
"step": 8000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.8,
|
| 421 |
+
"eval_loss": 43.091575622558594,
|
| 422 |
+
"eval_runtime": 17.4485,
|
| 423 |
+
"eval_samples_per_second": 230.278,
|
| 424 |
+
"eval_steps_per_second": 14.443,
|
| 425 |
+
"step": 8000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.89,
|
| 429 |
+
"eval_loss": 43.17302703857422,
|
| 430 |
+
"eval_runtime": 17.8351,
|
| 431 |
+
"eval_samples_per_second": 225.286,
|
| 432 |
+
"eval_steps_per_second": 14.129,
|
| 433 |
+
"step": 8200
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.99,
|
| 437 |
+
"eval_loss": 43.283023834228516,
|
| 438 |
+
"eval_runtime": 17.5983,
|
| 439 |
+
"eval_samples_per_second": 228.317,
|
| 440 |
+
"eval_steps_per_second": 14.32,
|
| 441 |
+
"step": 8400
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.04,
|
| 445 |
+
"learning_rate": 5.783475783475783e-07,
|
| 446 |
+
"loss": 35.0789,
|
| 447 |
+
"step": 8500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.08,
|
| 451 |
+
"eval_loss": 43.046226501464844,
|
| 452 |
+
"eval_runtime": 17.3807,
|
| 453 |
+
"eval_samples_per_second": 231.176,
|
| 454 |
+
"eval_steps_per_second": 14.499,
|
| 455 |
+
"step": 8600
|
| 456 |
+
}
|
| 457 |
+
],
|
| 458 |
+
"logging_steps": 500,
|
| 459 |
+
"max_steps": 10530,
|
| 460 |
+
"num_train_epochs": 5,
|
| 461 |
+
"save_steps": 200,
|
| 462 |
+
"total_flos": 3.776383962159514e+16,
|
| 463 |
+
"trial_name": null,
|
| 464 |
+
"trial_params": null
|
| 465 |
+
}
|
commongen_pythia-70m/checkpoint-8600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d05386879138ef07d94f9c1db20dc01aa2192c995abcf3e647fb68159f27d71
|
| 3 |
+
size 4600
|
commongen_pythia-70m/config.json
CHANGED
|
@@ -1,11 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/root/autodl-tmp/models/pythia-70m
|
| 3 |
"architectures": [
|
| 4 |
"GPTNeoXForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"bos_token_id": 0,
|
|
|
|
| 7 |
"eos_token_id": 0,
|
| 8 |
"hidden_act": "gelu",
|
|
|
|
| 9 |
"hidden_size": 512,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 2048,
|
|
@@ -15,11 +18,12 @@
|
|
| 15 |
"num_attention_heads": 8,
|
| 16 |
"num_hidden_layers": 6,
|
| 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-70m",
|
| 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,
|
|
|
|
| 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
|
commongen_pythia-70m/eval_results_lm.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
perplexity =
|
|
|
|
| 1 |
+
perplexity = 4.951521126079323e+18
|
commongen_pythia-70m/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-70m/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:743a48e3cb179148757389826df60de89f68ab05aa4d09b52d3562c04b287749
|
| 3 |
+
size 281715176
|
commongen_pythia-70m/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-70m/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 sha256:3d05386879138ef07d94f9c1db20dc01aa2192c995abcf3e647fb68159f27d71
|
| 3 |
+
size 4600
|