Initial commit
Browse files- config.json +39 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +304 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aliosm/ComVE-distilgpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"eos_token_ids": 0,
|
| 12 |
+
"gradient_checkpointing": false,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"LABEL_0": 0
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_epsilon": 1e-05,
|
| 21 |
+
"model_type": "gpt2",
|
| 22 |
+
"n_ctx": 1024,
|
| 23 |
+
"n_embd": 768,
|
| 24 |
+
"n_head": 12,
|
| 25 |
+
"n_inner": null,
|
| 26 |
+
"n_layer": 6,
|
| 27 |
+
"n_positions": 1024,
|
| 28 |
+
"output_past": true,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"resid_pdrop": 0.1,
|
| 31 |
+
"summary_activation": null,
|
| 32 |
+
"summary_first_dropout": 0.1,
|
| 33 |
+
"summary_proj_to_labels": true,
|
| 34 |
+
"summary_type": "cls_index",
|
| 35 |
+
"summary_use_proj": true,
|
| 36 |
+
"transformers_version": "4.2.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a363884d5e89ac9e5e1c9cb3d3a8631845316796295ba5405abe201b58b3641e
|
| 3 |
+
size 655348359
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9493a0993e1d3029588b7730716d200240dac7dd2902e8e64f705f311b1f81d1
|
| 3 |
+
size 333975623
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcae059eb8425251138f03ae2903777ad81265598a2d25c8a05fca91b24c3fcb
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"max_len": 1024}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9175784099197664,
|
| 5 |
+
"global_step": 24000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 3.2675,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 4.896600215071553e-05,
|
| 19 |
+
"loss": 2.9196,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 4.793200430143105e-05,
|
| 25 |
+
"loss": 2.8585,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 4.689800645214658e-05,
|
| 31 |
+
"loss": 2.8352,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.3,
|
| 36 |
+
"learning_rate": 4.586400860286211e-05,
|
| 37 |
+
"loss": 2.8187,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.36,
|
| 42 |
+
"learning_rate": 4.483001075357763e-05,
|
| 43 |
+
"loss": 2.8061,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.43,
|
| 48 |
+
"learning_rate": 4.379601290429316e-05,
|
| 49 |
+
"loss": 2.8031,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.49,
|
| 54 |
+
"learning_rate": 4.276201505500869e-05,
|
| 55 |
+
"loss": 2.7748,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.55,
|
| 60 |
+
"learning_rate": 4.1728017205724215e-05,
|
| 61 |
+
"loss": 2.7805,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.61,
|
| 66 |
+
"learning_rate": 4.069401935643974e-05,
|
| 67 |
+
"loss": 2.7626,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.67,
|
| 72 |
+
"learning_rate": 3.9660021507155265e-05,
|
| 73 |
+
"loss": 2.7667,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.73,
|
| 78 |
+
"learning_rate": 3.8626023657870794e-05,
|
| 79 |
+
"loss": 2.7543,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.79,
|
| 84 |
+
"learning_rate": 3.7592025808586315e-05,
|
| 85 |
+
"loss": 2.7481,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.85,
|
| 90 |
+
"learning_rate": 3.6558027959301844e-05,
|
| 91 |
+
"loss": 2.756,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.91,
|
| 96 |
+
"learning_rate": 3.552403011001738e-05,
|
| 97 |
+
"loss": 2.7437,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.97,
|
| 102 |
+
"learning_rate": 3.44900322607329e-05,
|
| 103 |
+
"loss": 2.7375,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.03,
|
| 108 |
+
"learning_rate": 3.345603441144843e-05,
|
| 109 |
+
"loss": 2.7159,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.09,
|
| 114 |
+
"learning_rate": 3.242203656216396e-05,
|
| 115 |
+
"loss": 2.697,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"learning_rate": 3.138803871287948e-05,
|
| 121 |
+
"loss": 2.697,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.22,
|
| 126 |
+
"learning_rate": 3.0354040863595007e-05,
|
| 127 |
+
"loss": 2.6973,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.28,
|
| 132 |
+
"learning_rate": 2.932004301431053e-05,
|
| 133 |
+
"loss": 2.6924,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.34,
|
| 138 |
+
"learning_rate": 2.828604516502606e-05,
|
| 139 |
+
"loss": 2.6973,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.4,
|
| 144 |
+
"learning_rate": 2.7252047315741585e-05,
|
| 145 |
+
"loss": 2.6975,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.46,
|
| 150 |
+
"learning_rate": 2.6218049466457113e-05,
|
| 151 |
+
"loss": 2.6978,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.52,
|
| 156 |
+
"learning_rate": 2.5184051617172638e-05,
|
| 157 |
+
"loss": 2.6867,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.58,
|
| 162 |
+
"learning_rate": 2.4150053767888163e-05,
|
| 163 |
+
"loss": 2.6771,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.64,
|
| 168 |
+
"learning_rate": 2.311605591860369e-05,
|
| 169 |
+
"loss": 2.6919,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.7,
|
| 174 |
+
"learning_rate": 2.2082058069319216e-05,
|
| 175 |
+
"loss": 2.6826,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.76,
|
| 180 |
+
"learning_rate": 2.1048060220034745e-05,
|
| 181 |
+
"loss": 2.6865,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.82,
|
| 186 |
+
"learning_rate": 2.001406237075027e-05,
|
| 187 |
+
"loss": 2.6724,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.88,
|
| 192 |
+
"learning_rate": 1.8980064521465795e-05,
|
| 193 |
+
"loss": 2.6768,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.95,
|
| 198 |
+
"learning_rate": 1.7946066672181323e-05,
|
| 199 |
+
"loss": 2.68,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.01,
|
| 204 |
+
"learning_rate": 1.6912068822896848e-05,
|
| 205 |
+
"loss": 2.6798,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.07,
|
| 210 |
+
"learning_rate": 1.5878070973612376e-05,
|
| 211 |
+
"loss": 2.6573,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.13,
|
| 216 |
+
"learning_rate": 1.4844073124327901e-05,
|
| 217 |
+
"loss": 2.6498,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.19,
|
| 222 |
+
"learning_rate": 1.381007527504343e-05,
|
| 223 |
+
"loss": 2.648,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.25,
|
| 228 |
+
"learning_rate": 1.2776077425758956e-05,
|
| 229 |
+
"loss": 2.6586,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.31,
|
| 234 |
+
"learning_rate": 1.1742079576474481e-05,
|
| 235 |
+
"loss": 2.6553,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.37,
|
| 240 |
+
"learning_rate": 1.070808172719001e-05,
|
| 241 |
+
"loss": 2.6484,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.43,
|
| 246 |
+
"learning_rate": 9.674083877905534e-06,
|
| 247 |
+
"loss": 2.656,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.49,
|
| 252 |
+
"learning_rate": 8.640086028621061e-06,
|
| 253 |
+
"loss": 2.6524,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.55,
|
| 258 |
+
"learning_rate": 7.6060881793365875e-06,
|
| 259 |
+
"loss": 2.6489,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.61,
|
| 264 |
+
"learning_rate": 6.572090330052113e-06,
|
| 265 |
+
"loss": 2.6452,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.67,
|
| 270 |
+
"learning_rate": 5.538092480767641e-06,
|
| 271 |
+
"loss": 2.6397,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.74,
|
| 276 |
+
"learning_rate": 4.5040946314831665e-06,
|
| 277 |
+
"loss": 2.6359,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.8,
|
| 282 |
+
"learning_rate": 3.470096782198693e-06,
|
| 283 |
+
"loss": 2.6491,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.86,
|
| 288 |
+
"learning_rate": 2.43609893291422e-06,
|
| 289 |
+
"loss": 2.6369,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.92,
|
| 294 |
+
"learning_rate": 1.402101083629746e-06,
|
| 295 |
+
"loss": 2.6461,
|
| 296 |
+
"step": 24000
|
| 297 |
+
}
|
| 298 |
+
],
|
| 299 |
+
"max_steps": 24678,
|
| 300 |
+
"num_train_epochs": 3,
|
| 301 |
+
"total_flos": 48313248320323584,
|
| 302 |
+
"trial_name": null,
|
| 303 |
+
"trial_params": null
|
| 304 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15ae1aabebf5abfd391c6c1d8525da2b05abeb0a7274ab2f8183610c35dacbfb
|
| 3 |
+
size 2031
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|