Upload folder using huggingface_hub
Browse files- README.md +1 -7
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +341 -0
README.md
CHANGED
|
@@ -1,12 +1,6 @@
|
|
| 1 |
---
|
| 2 |
-
license: bigcode-openrail-m
|
| 3 |
-
base_model: bigcode/starcoder
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
-
model-index:
|
| 7 |
-
- name: peft-lora-zencoder15B-A100-40GB
|
| 8 |
-
results: []
|
| 9 |
library_name: peft
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for Model ID
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
library_name: peft
|
| 3 |
+
base_model: bigcode/starcoder
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbc36e1c878784099b46f5b9a718b335165f7613c64f61d059016e0cedfaa033
|
| 3 |
+
size 110696954
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1dc61da6425213a4ed0c6718da9534c16f880b198a814db7fecbd699176650b
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7b5bf190dc871967c45091d9f1ab233b2d2ed62baca21fee5dfedb5718ffa5d
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,341 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 0.0001666666666666667,
|
| 14 |
+
"loss": 0.8745,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 0.00019979028262377118,
|
| 20 |
+
"loss": 0.8093,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 0.00019893981312363562,
|
| 26 |
+
"loss": 0.7357,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 0.00019744105246469263,
|
| 32 |
+
"loss": 0.7535,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.1,
|
| 37 |
+
"eval_loss": 0.4003306031227112,
|
| 38 |
+
"eval_runtime": 1.7839,
|
| 39 |
+
"eval_samples_per_second": 2.242,
|
| 40 |
+
"eval_steps_per_second": 0.561,
|
| 41 |
+
"step": 100
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.12,
|
| 45 |
+
"learning_rate": 0.0001953038210948861,
|
| 46 |
+
"loss": 0.7249,
|
| 47 |
+
"step": 125
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.15,
|
| 51 |
+
"learning_rate": 0.00019254212296427044,
|
| 52 |
+
"loss": 0.7118,
|
| 53 |
+
"step": 150
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.17,
|
| 57 |
+
"learning_rate": 0.00018917405376582145,
|
| 58 |
+
"loss": 0.7467,
|
| 59 |
+
"step": 175
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2,
|
| 63 |
+
"learning_rate": 0.00018522168236559695,
|
| 64 |
+
"loss": 0.6714,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2,
|
| 69 |
+
"eval_loss": 0.3684937059879303,
|
| 70 |
+
"eval_runtime": 1.7853,
|
| 71 |
+
"eval_samples_per_second": 2.24,
|
| 72 |
+
"eval_steps_per_second": 0.56,
|
| 73 |
+
"step": 200
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.23,
|
| 77 |
+
"learning_rate": 0.00018071090619916093,
|
| 78 |
+
"loss": 0.654,
|
| 79 |
+
"step": 225
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25,
|
| 83 |
+
"learning_rate": 0.00017567128158176953,
|
| 84 |
+
"loss": 0.6392,
|
| 85 |
+
"step": 250
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.28,
|
| 89 |
+
"learning_rate": 0.00017013583004418993,
|
| 90 |
+
"loss": 0.5745,
|
| 91 |
+
"step": 275
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.3,
|
| 95 |
+
"learning_rate": 0.000164140821963114,
|
| 96 |
+
"loss": 0.5364,
|
| 97 |
+
"step": 300
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.3,
|
| 101 |
+
"eval_loss": 0.3665352761745453,
|
| 102 |
+
"eval_runtime": 1.7852,
|
| 103 |
+
"eval_samples_per_second": 2.241,
|
| 104 |
+
"eval_steps_per_second": 0.56,
|
| 105 |
+
"step": 300
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.33,
|
| 109 |
+
"learning_rate": 0.00015772553890390197,
|
| 110 |
+
"loss": 0.5693,
|
| 111 |
+
"step": 325
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.35,
|
| 115 |
+
"learning_rate": 0.00015093201623287631,
|
| 116 |
+
"loss": 0.563,
|
| 117 |
+
"step": 350
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.38,
|
| 121 |
+
"learning_rate": 0.00014380476768566824,
|
| 122 |
+
"loss": 0.5478,
|
| 123 |
+
"step": 375
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.4,
|
| 127 |
+
"learning_rate": 0.00013639049369634876,
|
| 128 |
+
"loss": 0.5763,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.4,
|
| 133 |
+
"eval_loss": 0.3363753855228424,
|
| 134 |
+
"eval_runtime": 1.7851,
|
| 135 |
+
"eval_samples_per_second": 2.241,
|
| 136 |
+
"eval_steps_per_second": 0.56,
|
| 137 |
+
"step": 400
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.42,
|
| 141 |
+
"learning_rate": 0.00012873777539848283,
|
| 142 |
+
"loss": 0.4891,
|
| 143 |
+
"step": 425
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.45,
|
| 147 |
+
"learning_rate": 0.00012089675630312754,
|
| 148 |
+
"loss": 0.5331,
|
| 149 |
+
"step": 450
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.47,
|
| 153 |
+
"learning_rate": 0.00011291881373954065,
|
| 154 |
+
"loss": 0.5679,
|
| 155 |
+
"step": 475
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.5,
|
| 159 |
+
"learning_rate": 0.00010485622221144484,
|
| 160 |
+
"loss": 0.5982,
|
| 161 |
+
"step": 500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.5,
|
| 165 |
+
"eval_loss": 0.3186224400997162,
|
| 166 |
+
"eval_runtime": 1.7828,
|
| 167 |
+
"eval_samples_per_second": 2.244,
|
| 168 |
+
"eval_steps_per_second": 0.561,
|
| 169 |
+
"step": 500
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.53,
|
| 173 |
+
"learning_rate": 9.676181087466444e-05,
|
| 174 |
+
"loss": 0.5467,
|
| 175 |
+
"step": 525
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.55,
|
| 179 |
+
"learning_rate": 8.868861738047158e-05,
|
| 180 |
+
"loss": 0.5706,
|
| 181 |
+
"step": 550
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.57,
|
| 185 |
+
"learning_rate": 8.068954035279121e-05,
|
| 186 |
+
"loss": 0.504,
|
| 187 |
+
"step": 575
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.6,
|
| 191 |
+
"learning_rate": 7.281699277636572e-05,
|
| 192 |
+
"loss": 0.5267,
|
| 193 |
+
"step": 600
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.6,
|
| 197 |
+
"eval_loss": 0.32175499200820923,
|
| 198 |
+
"eval_runtime": 1.7846,
|
| 199 |
+
"eval_samples_per_second": 2.241,
|
| 200 |
+
"eval_steps_per_second": 0.56,
|
| 201 |
+
"step": 600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.62,
|
| 205 |
+
"learning_rate": 6.512255856701177e-05,
|
| 206 |
+
"loss": 0.5414,
|
| 207 |
+
"step": 625
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.65,
|
| 211 |
+
"learning_rate": 5.765665457425102e-05,
|
| 212 |
+
"loss": 0.5412,
|
| 213 |
+
"step": 650
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.68,
|
| 217 |
+
"learning_rate": 5.0468200231001286e-05,
|
| 218 |
+
"loss": 0.4611,
|
| 219 |
+
"step": 675
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7,
|
| 223 |
+
"learning_rate": 4.360429701490934e-05,
|
| 224 |
+
"loss": 0.5073,
|
| 225 |
+
"step": 700
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.7,
|
| 229 |
+
"eval_loss": 0.31275978684425354,
|
| 230 |
+
"eval_runtime": 1.7833,
|
| 231 |
+
"eval_samples_per_second": 2.243,
|
| 232 |
+
"eval_steps_per_second": 0.561,
|
| 233 |
+
"step": 700
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.72,
|
| 237 |
+
"learning_rate": 3.710991982161555e-05,
|
| 238 |
+
"loss": 0.4778,
|
| 239 |
+
"step": 725
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.75,
|
| 243 |
+
"learning_rate": 3.102762227218957e-05,
|
| 244 |
+
"loss": 0.5454,
|
| 245 |
+
"step": 750
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.78,
|
| 249 |
+
"learning_rate": 2.5397257885675397e-05,
|
| 250 |
+
"loss": 0.5612,
|
| 251 |
+
"step": 775
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.8,
|
| 255 |
+
"learning_rate": 2.025571894372794e-05,
|
| 256 |
+
"loss": 0.4983,
|
| 257 |
+
"step": 800
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.8,
|
| 261 |
+
"eval_loss": 0.31457942724227905,
|
| 262 |
+
"eval_runtime": 1.7821,
|
| 263 |
+
"eval_samples_per_second": 2.245,
|
| 264 |
+
"eval_steps_per_second": 0.561,
|
| 265 |
+
"step": 800
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.82,
|
| 269 |
+
"learning_rate": 1.563669475839956e-05,
|
| 270 |
+
"loss": 0.4941,
|
| 271 |
+
"step": 825
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.85,
|
| 275 |
+
"learning_rate": 1.1570450926997655e-05,
|
| 276 |
+
"loss": 0.4926,
|
| 277 |
+
"step": 850
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.88,
|
| 281 |
+
"learning_rate": 8.083631020418791e-06,
|
| 282 |
+
"loss": 0.5094,
|
| 283 |
+
"step": 875
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9,
|
| 287 |
+
"learning_rate": 5.199082004372957e-06,
|
| 288 |
+
"loss": 0.5116,
|
| 289 |
+
"step": 900
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9,
|
| 293 |
+
"eval_loss": 0.31357938051223755,
|
| 294 |
+
"eval_runtime": 1.7811,
|
| 295 |
+
"eval_samples_per_second": 2.246,
|
| 296 |
+
"eval_steps_per_second": 0.561,
|
| 297 |
+
"step": 900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.93,
|
| 301 |
+
"learning_rate": 2.9357045374040825e-06,
|
| 302 |
+
"loss": 0.4244,
|
| 303 |
+
"step": 925
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.95,
|
| 307 |
+
"learning_rate": 1.30832912661093e-06,
|
| 308 |
+
"loss": 0.4511,
|
| 309 |
+
"step": 950
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.97,
|
| 313 |
+
"learning_rate": 3.2761895254306287e-07,
|
| 314 |
+
"loss": 0.4179,
|
| 315 |
+
"step": 975
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.0,
|
| 319 |
+
"learning_rate": 0.0,
|
| 320 |
+
"loss": 0.4662,
|
| 321 |
+
"step": 1000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.0,
|
| 325 |
+
"eval_loss": 0.3136279284954071,
|
| 326 |
+
"eval_runtime": 1.7836,
|
| 327 |
+
"eval_samples_per_second": 2.243,
|
| 328 |
+
"eval_steps_per_second": 0.561,
|
| 329 |
+
"step": 1000
|
| 330 |
+
}
|
| 331 |
+
],
|
| 332 |
+
"logging_steps": 25,
|
| 333 |
+
"max_steps": 1000,
|
| 334 |
+
"num_input_tokens_seen": 0,
|
| 335 |
+
"num_train_epochs": 9223372036854775807,
|
| 336 |
+
"save_steps": 100,
|
| 337 |
+
"total_flos": 1.493507298557952e+18,
|
| 338 |
+
"train_batch_size": 4,
|
| 339 |
+
"trial_name": null,
|
| 340 |
+
"trial_params": null
|
| 341 |
+
}
|