Upload 10 files
Browse files- adapter_config.json +16 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
- trainer_state.json +304 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "nlpai-lab/kullm-polyglot-12.8b-v2",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 32,
|
| 8 |
+
"lora_dropout": 0.1,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 16,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"query_key_value"
|
| 14 |
+
],
|
| 15 |
+
"task_type": "CAUSAL_LM"
|
| 16 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:829ac1d837e60cb6735eedda22590bc7f08e00e45a37be0cbd656c128a22aa45
|
| 3 |
+
size 52458401
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e6c3880990866f3620b0975b3fa4472f26e55c99bf08b0b72483e02c6cbe7d7
|
| 3 |
+
size 104904965
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e385bd544a3268e68fc03cd018eec48ab0a12b4604c30ba49dec0c287963d01
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637774ea089d5753f8eb5f354f492778493603d2a122d7f3032082f4a9082d16
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|acc|>",
|
| 6 |
+
"<|tel|>",
|
| 7 |
+
"<|rrn|>"
|
| 8 |
+
],
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"pad_token": "<|sep|>"
|
| 11 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"model_max_length": 1024,
|
| 5 |
+
"pad_token": "<|endoftext|>",
|
| 6 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.2,
|
| 5 |
+
"global_step": 240,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.4,
|
| 12 |
+
"learning_rate": 0.0001,
|
| 13 |
+
"loss": 2.3459,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.8,
|
| 18 |
+
"learning_rate": 9.787234042553192e-05,
|
| 19 |
+
"loss": 2.1597,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.2,
|
| 24 |
+
"learning_rate": 9.574468085106384e-05,
|
| 25 |
+
"loss": 1.7456,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.6,
|
| 30 |
+
"learning_rate": 9.361702127659576e-05,
|
| 31 |
+
"loss": 1.5638,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"learning_rate": 9.148936170212766e-05,
|
| 37 |
+
"loss": 1.4497,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.4,
|
| 42 |
+
"learning_rate": 8.936170212765958e-05,
|
| 43 |
+
"loss": 1.3674,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.8,
|
| 48 |
+
"learning_rate": 8.723404255319149e-05,
|
| 49 |
+
"loss": 1.3003,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.2,
|
| 54 |
+
"learning_rate": 8.510638297872341e-05,
|
| 55 |
+
"loss": 1.2443,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.6,
|
| 60 |
+
"learning_rate": 8.297872340425533e-05,
|
| 61 |
+
"loss": 1.2049,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"learning_rate": 8.085106382978723e-05,
|
| 67 |
+
"loss": 1.2089,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.4,
|
| 72 |
+
"learning_rate": 7.872340425531916e-05,
|
| 73 |
+
"loss": 1.1278,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.8,
|
| 78 |
+
"learning_rate": 7.659574468085106e-05,
|
| 79 |
+
"loss": 1.1186,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.2,
|
| 84 |
+
"learning_rate": 7.446808510638298e-05,
|
| 85 |
+
"loss": 1.0933,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.6,
|
| 90 |
+
"learning_rate": 7.23404255319149e-05,
|
| 91 |
+
"loss": 1.0794,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.0,
|
| 96 |
+
"learning_rate": 7.021276595744681e-05,
|
| 97 |
+
"loss": 1.0174,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.4,
|
| 102 |
+
"learning_rate": 6.808510638297873e-05,
|
| 103 |
+
"loss": 0.9832,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.8,
|
| 108 |
+
"learning_rate": 6.595744680851063e-05,
|
| 109 |
+
"loss": 0.9853,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.2,
|
| 114 |
+
"learning_rate": 6.382978723404256e-05,
|
| 115 |
+
"loss": 0.9455,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.6,
|
| 120 |
+
"learning_rate": 6.170212765957447e-05,
|
| 121 |
+
"loss": 0.9044,
|
| 122 |
+
"step": 95
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.0,
|
| 126 |
+
"learning_rate": 5.9574468085106384e-05,
|
| 127 |
+
"loss": 0.9453,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.4,
|
| 132 |
+
"learning_rate": 5.744680851063831e-05,
|
| 133 |
+
"loss": 0.8726,
|
| 134 |
+
"step": 105
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.8,
|
| 138 |
+
"learning_rate": 5.531914893617022e-05,
|
| 139 |
+
"loss": 0.8506,
|
| 140 |
+
"step": 110
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 9.2,
|
| 144 |
+
"learning_rate": 5.319148936170213e-05,
|
| 145 |
+
"loss": 0.8197,
|
| 146 |
+
"step": 115
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 9.6,
|
| 150 |
+
"learning_rate": 5.1063829787234044e-05,
|
| 151 |
+
"loss": 0.794,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 4.893617021276596e-05,
|
| 157 |
+
"loss": 0.806,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.4,
|
| 162 |
+
"learning_rate": 4.680851063829788e-05,
|
| 163 |
+
"loss": 0.7553,
|
| 164 |
+
"step": 130
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.8,
|
| 168 |
+
"learning_rate": 4.468085106382979e-05,
|
| 169 |
+
"loss": 0.7085,
|
| 170 |
+
"step": 135
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11.2,
|
| 174 |
+
"learning_rate": 4.2553191489361704e-05,
|
| 175 |
+
"loss": 0.7396,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.6,
|
| 180 |
+
"learning_rate": 4.0425531914893614e-05,
|
| 181 |
+
"loss": 0.6653,
|
| 182 |
+
"step": 145
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.0,
|
| 186 |
+
"learning_rate": 3.829787234042553e-05,
|
| 187 |
+
"loss": 0.6648,
|
| 188 |
+
"step": 150
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.4,
|
| 192 |
+
"learning_rate": 3.617021276595745e-05,
|
| 193 |
+
"loss": 0.6164,
|
| 194 |
+
"step": 155
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.8,
|
| 198 |
+
"learning_rate": 3.4042553191489365e-05,
|
| 199 |
+
"loss": 0.6197,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.2,
|
| 204 |
+
"learning_rate": 3.191489361702128e-05,
|
| 205 |
+
"loss": 0.5731,
|
| 206 |
+
"step": 165
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.6,
|
| 210 |
+
"learning_rate": 2.9787234042553192e-05,
|
| 211 |
+
"loss": 0.5713,
|
| 212 |
+
"step": 170
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.0,
|
| 216 |
+
"learning_rate": 2.765957446808511e-05,
|
| 217 |
+
"loss": 0.5612,
|
| 218 |
+
"step": 175
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.4,
|
| 222 |
+
"learning_rate": 2.5531914893617022e-05,
|
| 223 |
+
"loss": 0.5372,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.8,
|
| 228 |
+
"learning_rate": 2.340425531914894e-05,
|
| 229 |
+
"loss": 0.5098,
|
| 230 |
+
"step": 185
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 15.2,
|
| 234 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 235 |
+
"loss": 0.4798,
|
| 236 |
+
"step": 190
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 15.6,
|
| 240 |
+
"learning_rate": 1.9148936170212766e-05,
|
| 241 |
+
"loss": 0.4931,
|
| 242 |
+
"step": 195
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 16.0,
|
| 246 |
+
"learning_rate": 1.7021276595744682e-05,
|
| 247 |
+
"loss": 0.4652,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.4,
|
| 252 |
+
"learning_rate": 1.4893617021276596e-05,
|
| 253 |
+
"loss": 0.4244,
|
| 254 |
+
"step": 205
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.8,
|
| 258 |
+
"learning_rate": 1.2765957446808511e-05,
|
| 259 |
+
"loss": 0.4701,
|
| 260 |
+
"step": 210
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 17.2,
|
| 264 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 265 |
+
"loss": 0.4204,
|
| 266 |
+
"step": 215
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 17.6,
|
| 270 |
+
"learning_rate": 8.510638297872341e-06,
|
| 271 |
+
"loss": 0.4216,
|
| 272 |
+
"step": 220
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.0,
|
| 276 |
+
"learning_rate": 6.3829787234042555e-06,
|
| 277 |
+
"loss": 0.4294,
|
| 278 |
+
"step": 225
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 18.4,
|
| 282 |
+
"learning_rate": 4.255319148936171e-06,
|
| 283 |
+
"loss": 0.4151,
|
| 284 |
+
"step": 230
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 18.8,
|
| 288 |
+
"learning_rate": 2.1276595744680853e-06,
|
| 289 |
+
"loss": 0.4077,
|
| 290 |
+
"step": 235
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 19.2,
|
| 294 |
+
"learning_rate": 0.0,
|
| 295 |
+
"loss": 0.4046,
|
| 296 |
+
"step": 240
|
| 297 |
+
}
|
| 298 |
+
],
|
| 299 |
+
"max_steps": 240,
|
| 300 |
+
"num_train_epochs": 20,
|
| 301 |
+
"total_flos": 6.017479499317248e+17,
|
| 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 sha256:265c59d3b6e97d1307c85cf2682ae2123451c6db740cbbc7d926144c9b325602
|
| 3 |
+
size 4027
|