Text Generation
Transformers
Safetensors
PEFT
English
lora
grpo
reinforcement-learning
reasoning
corporate strategy
decision making
business strategy
business analysis
competitive analysis
strategic planning
decision support
management consulting
market analysis
business intelligence
business planning
organizational development
performance improvement
strategic thinking
executive support
conversational
Eval Results (legacy)
Upload checkpoint-500/trainer_state.json with huggingface_hub
Browse files
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 2.3459789752960205,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.4508,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 0.7824317216873169,
|
| 21 |
+
"learning_rate": 4e-05,
|
| 22 |
+
"loss": 2.0751,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 0.754115641117096,
|
| 28 |
+
"learning_rate": 4.9986331433523156e-05,
|
| 29 |
+
"loss": 1.663,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 0.7826311588287354,
|
| 35 |
+
"learning_rate": 4.9877072563625285e-05,
|
| 36 |
+
"loss": 1.2938,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 0.9058009386062622,
|
| 42 |
+
"learning_rate": 4.965903258506806e-05,
|
| 43 |
+
"loss": 0.9719,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 0.8621117472648621,
|
| 49 |
+
"learning_rate": 4.933316493120015e-05,
|
| 50 |
+
"loss": 0.7141,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.28,
|
| 55 |
+
"grad_norm": 0.8602449297904968,
|
| 56 |
+
"learning_rate": 4.8900894538358944e-05,
|
| 57 |
+
"loss": 0.5491,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32,
|
| 62 |
+
"grad_norm": 0.8764705657958984,
|
| 63 |
+
"learning_rate": 4.8364111614986527e-05,
|
| 64 |
+
"loss": 0.4541,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.36,
|
| 69 |
+
"grad_norm": 0.8664467334747314,
|
| 70 |
+
"learning_rate": 4.7725163376229064e-05,
|
| 71 |
+
"loss": 0.3817,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.4,
|
| 76 |
+
"grad_norm": 0.752210795879364,
|
| 77 |
+
"learning_rate": 4.698684378016222e-05,
|
| 78 |
+
"loss": 0.3162,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.44,
|
| 83 |
+
"grad_norm": 0.9347196817398071,
|
| 84 |
+
"learning_rate": 4.6152381310523387e-05,
|
| 85 |
+
"loss": 0.2979,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"grad_norm": 0.661382794380188,
|
| 91 |
+
"learning_rate": 4.522542485937369e-05,
|
| 92 |
+
"loss": 0.2545,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.52,
|
| 97 |
+
"grad_norm": 0.7543488144874573,
|
| 98 |
+
"learning_rate": 4.421002777142148e-05,
|
| 99 |
+
"loss": 0.2436,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.56,
|
| 104 |
+
"grad_norm": 0.6346200108528137,
|
| 105 |
+
"learning_rate": 4.311063011977723e-05,
|
| 106 |
+
"loss": 0.2363,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6,
|
| 111 |
+
"grad_norm": 0.7474273443222046,
|
| 112 |
+
"learning_rate": 4.193203929064353e-05,
|
| 113 |
+
"loss": 0.2278,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.64,
|
| 118 |
+
"grad_norm": 0.7145452499389648,
|
| 119 |
+
"learning_rate": 4.067940896183843e-05,
|
| 120 |
+
"loss": 0.2233,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.68,
|
| 125 |
+
"grad_norm": 0.6111130714416504,
|
| 126 |
+
"learning_rate": 3.935821656707359e-05,
|
| 127 |
+
"loss": 0.222,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"grad_norm": 0.588006317615509,
|
| 133 |
+
"learning_rate": 3.797423934453038e-05,
|
| 134 |
+
"loss": 0.2136,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.76,
|
| 139 |
+
"grad_norm": 0.5854628682136536,
|
| 140 |
+
"learning_rate": 3.65335290744672e-05,
|
| 141 |
+
"loss": 0.2162,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8,
|
| 146 |
+
"grad_norm": 0.500828206539154,
|
| 147 |
+
"learning_rate": 3.504238561632424e-05,
|
| 148 |
+
"loss": 0.2114,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.84,
|
| 153 |
+
"grad_norm": 0.4557226896286011,
|
| 154 |
+
"learning_rate": 3.350732936104108e-05,
|
| 155 |
+
"loss": 0.2229,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.88,
|
| 160 |
+
"grad_norm": 0.5085278153419495,
|
| 161 |
+
"learning_rate": 3.1935072719046115e-05,
|
| 162 |
+
"loss": 0.212,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.92,
|
| 167 |
+
"grad_norm": 0.47359195351600647,
|
| 168 |
+
"learning_rate": 3.0332490768593675e-05,
|
| 169 |
+
"loss": 0.2056,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"grad_norm": 0.5809552073478699,
|
| 175 |
+
"learning_rate": 2.870659119279605e-05,
|
| 176 |
+
"loss": 0.2132,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0,
|
| 181 |
+
"grad_norm": 0.5612187385559082,
|
| 182 |
+
"learning_rate": 2.7064483636808313e-05,
|
| 183 |
+
"loss": 0.2087,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.04,
|
| 188 |
+
"grad_norm": 0.49165409803390503,
|
| 189 |
+
"learning_rate": 2.5413348619158967e-05,
|
| 190 |
+
"loss": 0.2064,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.08,
|
| 195 |
+
"grad_norm": 0.5103522539138794,
|
| 196 |
+
"learning_rate": 2.3760406133169443e-05,
|
| 197 |
+
"loss": 0.2061,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.12,
|
| 202 |
+
"grad_norm": 0.48928719758987427,
|
| 203 |
+
"learning_rate": 2.2112884075760347e-05,
|
| 204 |
+
"loss": 0.2041,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.16,
|
| 209 |
+
"grad_norm": 0.5604917407035828,
|
| 210 |
+
"learning_rate": 2.047798664169726e-05,
|
| 211 |
+
"loss": 0.2021,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"grad_norm": 0.5653706789016724,
|
| 217 |
+
"learning_rate": 1.8862862821480025e-05,
|
| 218 |
+
"loss": 0.2009,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.24,
|
| 223 |
+
"grad_norm": 0.5317566394805908,
|
| 224 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 225 |
+
"loss": 0.2053,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.28,
|
| 230 |
+
"grad_norm": 0.5173370838165283,
|
| 231 |
+
"learning_rate": 1.5720068777044476e-05,
|
| 232 |
+
"loss": 0.2046,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.32,
|
| 237 |
+
"grad_norm": 0.5695991516113281,
|
| 238 |
+
"learning_rate": 1.4206141191537682e-05,
|
| 239 |
+
"loss": 0.2043,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3599999999999999,
|
| 244 |
+
"grad_norm": 0.5045269131660461,
|
| 245 |
+
"learning_rate": 1.2739412404237306e-05,
|
| 246 |
+
"loss": 0.2026,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.4,
|
| 251 |
+
"grad_norm": 0.5585351586341858,
|
| 252 |
+
"learning_rate": 1.1326296046939333e-05,
|
| 253 |
+
"loss": 0.2006,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.44,
|
| 258 |
+
"grad_norm": 0.5607123374938965,
|
| 259 |
+
"learning_rate": 9.972971317924374e-06,
|
| 260 |
+
"loss": 0.2004,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.48,
|
| 265 |
+
"grad_norm": 0.5031062960624695,
|
| 266 |
+
"learning_rate": 8.685355961895784e-06,
|
| 267 |
+
"loss": 0.2007,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.52,
|
| 272 |
+
"grad_norm": 0.579496443271637,
|
| 273 |
+
"learning_rate": 7.469080393187786e-06,
|
| 274 |
+
"loss": 0.2003,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.56,
|
| 279 |
+
"grad_norm": 0.5717282891273499,
|
| 280 |
+
"learning_rate": 6.329463075396161e-06,
|
| 281 |
+
"loss": 0.2018,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.6,
|
| 286 |
+
"grad_norm": 0.5317989587783813,
|
| 287 |
+
"learning_rate": 5.271487265090163e-06,
|
| 288 |
+
"loss": 0.2002,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6400000000000001,
|
| 293 |
+
"grad_norm": 0.5046743750572205,
|
| 294 |
+
"learning_rate": 4.299779221299499e-06,
|
| 295 |
+
"loss": 0.1981,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6800000000000002,
|
| 300 |
+
"grad_norm": 0.5230479836463928,
|
| 301 |
+
"learning_rate": 3.418587976060653e-06,
|
| 302 |
+
"loss": 0.2,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.72,
|
| 307 |
+
"grad_norm": 0.5649706721305847,
|
| 308 |
+
"learning_rate": 2.6317667544809134e-06,
|
| 309 |
+
"loss": 0.2014,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.76,
|
| 314 |
+
"grad_norm": 0.6512070894241333,
|
| 315 |
+
"learning_rate": 1.9427561255653816e-06,
|
| 316 |
+
"loss": 0.199,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.8,
|
| 321 |
+
"grad_norm": 0.48896294832229614,
|
| 322 |
+
"learning_rate": 1.3545689574841342e-06,
|
| 323 |
+
"loss": 0.2012,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8399999999999999,
|
| 328 |
+
"grad_norm": 0.559664785861969,
|
| 329 |
+
"learning_rate": 8.697772430662859e-07,
|
| 330 |
+
"loss": 0.2005,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.88,
|
| 335 |
+
"grad_norm": 0.529403030872345,
|
| 336 |
+
"learning_rate": 4.905008531297661e-07,
|
| 337 |
+
"loss": 0.1994,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.92,
|
| 342 |
+
"grad_norm": 0.6188033223152161,
|
| 343 |
+
"learning_rate": 2.1839826682562015e-07,
|
| 344 |
+
"loss": 0.1945,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.96,
|
| 349 |
+
"grad_norm": 0.5380053520202637,
|
| 350 |
+
"learning_rate": 5.4659319530636633e-08,
|
| 351 |
+
"loss": 0.1973,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0,
|
| 356 |
+
"grad_norm": 0.5263402462005615,
|
| 357 |
+
"learning_rate": 0.0,
|
| 358 |
+
"loss": 0.1982,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 500,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 2,
|
| 366 |
+
"save_steps": 0,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": true
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.505320079425536e+16,
|
| 380 |
+
"train_batch_size": 1,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|