Upload folder using huggingface_hub
Browse files- config.json +29 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +212 -0
- trainer_state.json +246 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./configs/diff_llama-410m.json",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DiffLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_family": "mha",
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "diff_llama",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"num_key_value_heads": 16,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.36.1",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 50277
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.36.1",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed6982cc19fc7e75470deb4f4319d6d7157568d26c53217dc51b778c3ecfc5b2
|
| 3 |
+
size 1011366272
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|padding|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"50254": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50255": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50256": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50257": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50258": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50259": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50260": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50261": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50262": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50263": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50264": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50265": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50266": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50267": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50268": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50269": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50270": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50271": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50272": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50273": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50274": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50275": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50276": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
}
|
| 204 |
+
},
|
| 205 |
+
"bos_token": "<|endoftext|>",
|
| 206 |
+
"clean_up_tokenization_spaces": true,
|
| 207 |
+
"eos_token": "<|endoftext|>",
|
| 208 |
+
"model_max_length": 2048,
|
| 209 |
+
"padding_side": "right",
|
| 210 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 211 |
+
"unk_token": "<|endoftext|>"
|
| 212 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.1834473609924316,
|
| 3 |
+
"best_model_checkpoint": "./snap_diff_llama/diff_llama_410m_mha/checkpoint-13000",
|
| 4 |
+
"epoch": 0.0505,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 14000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.1428571428571426e-07,
|
| 14 |
+
"loss": 11.0337,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 0.00021428571428571427,
|
| 20 |
+
"loss": 6.4482,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"eval_loss": 4.9442644119262695,
|
| 26 |
+
"eval_ppl": 140.36756016320973,
|
| 27 |
+
"eval_runtime": 30.3546,
|
| 28 |
+
"eval_samples_per_second": 16.472,
|
| 29 |
+
"eval_steps_per_second": 0.132,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14,
|
| 34 |
+
"learning_rate": 0.0002983246239337692,
|
| 35 |
+
"loss": 4.3801,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.14,
|
| 40 |
+
"eval_loss": 4.004600524902344,
|
| 41 |
+
"eval_ppl": 54.84990884930932,
|
| 42 |
+
"eval_runtime": 29.9124,
|
| 43 |
+
"eval_samples_per_second": 16.715,
|
| 44 |
+
"eval_steps_per_second": 0.134,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.21,
|
| 49 |
+
"learning_rate": 0.00028822143178056114,
|
| 50 |
+
"loss": 3.794,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21,
|
| 55 |
+
"eval_loss": 3.629385232925415,
|
| 56 |
+
"eval_ppl": 37.6896391443392,
|
| 57 |
+
"eval_runtime": 29.7452,
|
| 58 |
+
"eval_samples_per_second": 16.809,
|
| 59 |
+
"eval_steps_per_second": 0.134,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.29,
|
| 64 |
+
"learning_rate": 0.0002695698760834384,
|
| 65 |
+
"loss": 3.5789,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.29,
|
| 70 |
+
"eval_loss": 3.499099016189575,
|
| 71 |
+
"eval_ppl": 33.08562890966227,
|
| 72 |
+
"eval_runtime": 29.9268,
|
| 73 |
+
"eval_samples_per_second": 16.707,
|
| 74 |
+
"eval_steps_per_second": 0.134,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.00024352347027881003,
|
| 80 |
+
"loss": 3.4461,
|
| 81 |
+
"step": 5000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"eval_loss": 3.4322781562805176,
|
| 86 |
+
"eval_ppl": 30.947064752985586,
|
| 87 |
+
"eval_runtime": 30.1629,
|
| 88 |
+
"eval_samples_per_second": 16.577,
|
| 89 |
+
"eval_steps_per_second": 0.133,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.11,
|
| 94 |
+
"learning_rate": 0.00021169306546959174,
|
| 95 |
+
"loss": 3.3611,
|
| 96 |
+
"step": 6000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.11,
|
| 100 |
+
"eval_loss": 3.3286616802215576,
|
| 101 |
+
"eval_ppl": 27.90097627697978,
|
| 102 |
+
"eval_runtime": 30.5776,
|
| 103 |
+
"eval_samples_per_second": 16.352,
|
| 104 |
+
"eval_steps_per_second": 0.131,
|
| 105 |
+
"step": 6000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.18,
|
| 109 |
+
"learning_rate": 0.00017604722665003956,
|
| 110 |
+
"loss": 3.3525,
|
| 111 |
+
"step": 7000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.18,
|
| 115 |
+
"eval_loss": 3.307777166366577,
|
| 116 |
+
"eval_ppl": 27.324320498654966,
|
| 117 |
+
"eval_runtime": 30.3366,
|
| 118 |
+
"eval_samples_per_second": 16.482,
|
| 119 |
+
"eval_steps_per_second": 0.132,
|
| 120 |
+
"step": 7000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.25,
|
| 124 |
+
"learning_rate": 0.00013879048596203636,
|
| 125 |
+
"loss": 3.2975,
|
| 126 |
+
"step": 8000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.25,
|
| 130 |
+
"eval_loss": 3.2553489208221436,
|
| 131 |
+
"eval_ppl": 25.928660005196736,
|
| 132 |
+
"eval_runtime": 30.0498,
|
| 133 |
+
"eval_samples_per_second": 16.639,
|
| 134 |
+
"eval_steps_per_second": 0.133,
|
| 135 |
+
"step": 8000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.01,
|
| 139 |
+
"learning_rate": 0.00010222700246224735,
|
| 140 |
+
"loss": 3.2508,
|
| 141 |
+
"step": 9000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.01,
|
| 145 |
+
"eval_loss": 3.2358081340789795,
|
| 146 |
+
"eval_ppl": 25.426911832146725,
|
| 147 |
+
"eval_runtime": 30.3885,
|
| 148 |
+
"eval_samples_per_second": 16.454,
|
| 149 |
+
"eval_steps_per_second": 0.132,
|
| 150 |
+
"step": 9000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.08,
|
| 154 |
+
"learning_rate": 6.86180604201361e-05,
|
| 155 |
+
"loss": 3.2163,
|
| 156 |
+
"step": 10000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.08,
|
| 160 |
+
"eval_loss": 3.2036635875701904,
|
| 161 |
+
"eval_ppl": 24.622572107305388,
|
| 162 |
+
"eval_runtime": 30.4758,
|
| 163 |
+
"eval_samples_per_second": 16.406,
|
| 164 |
+
"eval_steps_per_second": 0.131,
|
| 165 |
+
"step": 10000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.15,
|
| 169 |
+
"learning_rate": 4.004221922552608e-05,
|
| 170 |
+
"loss": 3.2326,
|
| 171 |
+
"step": 11000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15,
|
| 175 |
+
"eval_loss": 3.188652753829956,
|
| 176 |
+
"eval_ppl": 24.255726984975077,
|
| 177 |
+
"eval_runtime": 29.8586,
|
| 178 |
+
"eval_samples_per_second": 16.746,
|
| 179 |
+
"eval_steps_per_second": 0.134,
|
| 180 |
+
"step": 11000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.22,
|
| 184 |
+
"learning_rate": 1.82667639944657e-05,
|
| 185 |
+
"loss": 3.2173,
|
| 186 |
+
"step": 12000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.22,
|
| 190 |
+
"eval_loss": 3.1875133514404297,
|
| 191 |
+
"eval_ppl": 24.228105690561378,
|
| 192 |
+
"eval_runtime": 29.7409,
|
| 193 |
+
"eval_samples_per_second": 16.812,
|
| 194 |
+
"eval_steps_per_second": 0.134,
|
| 195 |
+
"step": 12000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.3,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 3.2315,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.3,
|
| 205 |
+
"eval_loss": 3.1834473609924316,
|
| 206 |
+
"eval_ppl": 24.129794445983528,
|
| 207 |
+
"eval_runtime": 29.6158,
|
| 208 |
+
"eval_samples_per_second": 16.883,
|
| 209 |
+
"eval_steps_per_second": 0.135,
|
| 210 |
+
"step": 13000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.05,
|
| 214 |
+
"learning_rate": 1e-05,
|
| 215 |
+
"loss": 3.2219,
|
| 216 |
+
"step": 14000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.05,
|
| 220 |
+
"eval_loss": 3.184858560562134,
|
| 221 |
+
"eval_ppl": 24.163870439881514,
|
| 222 |
+
"eval_runtime": 30.4568,
|
| 223 |
+
"eval_samples_per_second": 16.417,
|
| 224 |
+
"eval_steps_per_second": 0.131,
|
| 225 |
+
"step": 14000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.05,
|
| 229 |
+
"step": 14000,
|
| 230 |
+
"total_flos": 2.0002483519409357e+19,
|
| 231 |
+
"train_loss": 0.16270504324776786,
|
| 232 |
+
"train_runtime": 2272.7407,
|
| 233 |
+
"train_samples_per_second": 1576.951,
|
| 234 |
+
"train_steps_per_second": 6.16
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 1000,
|
| 238 |
+
"max_steps": 14000,
|
| 239 |
+
"num_input_tokens_seen": 0,
|
| 240 |
+
"num_train_epochs": 9223372036854775807,
|
| 241 |
+
"save_steps": 1000,
|
| 242 |
+
"total_flos": 2.0002483519409357e+19,
|
| 243 |
+
"train_batch_size": 16,
|
| 244 |
+
"trial_name": null,
|
| 245 |
+
"trial_params": null
|
| 246 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63d71799a8fa6efcb04864b2541de397995be3077ff6d4fb64a4018c6d8bc709
|
| 3 |
+
size 4856
|