Training in progress, step 4000, checkpoint
Browse files- last-checkpoint/global_step4000/mp_rank_00_model_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/global_step4000/zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- last-checkpoint/latest +1 -1
- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +2 -2
- last-checkpoint/rng_state_5.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +331 -629
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/global_step4000/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c5d32c0a772af4dbee65ad1a00c1716d28a7d08f8c615bb042942d553e069c0
|
| 3 |
+
size 197282509
|
last-checkpoint/global_step4000/zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52944272e11fbf6d1b80dd30f91da9fe76f2310c0264c54038b1bff04f60332a
|
| 3 |
+
size 180416968
|
last-checkpoint/global_step4000/zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b89320d37b4274212eae501862122331d33974c44f94bef2b67672203ccd5d48
|
| 3 |
+
size 180416776
|
last-checkpoint/global_step4000/zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63d209a5738732e2fb6d02f90c8706dfb271296572285626f5d15d58f74b7c5c
|
| 3 |
+
size 180416776
|
last-checkpoint/global_step4000/zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2971581128d1a37471527c0d18947f037ad1582558d8e215a30839d57824470
|
| 3 |
+
size 180416904
|
last-checkpoint/global_step4000/zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2560ed7e050ec5c29442de6b34fe5113cd07d8e7b476b736be57b6d656a79d5
|
| 3 |
+
size 180416712
|
last-checkpoint/global_step4000/zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef0c7079605563319b5dd1afada9b7aa986127b321f031dca73e4d2325dee45e
|
| 3 |
+
size 180417096
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step4000
|
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 188836816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c58337fef44eb64b6a836e64f9822d87d574565c1d4747cb3f62a0896064c30
|
| 3 |
size 188836816
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1120d6b90c959e6013002d9cd97f09e528d1b42ae693d2827c2d54e16c694bbc
|
| 3 |
+
size 15536
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d99b0f2716b6bbd2656ca2579fc6e066d6cb7eea792a1703bf7c506b83aa1d0
|
| 3 |
size 15536
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76db77f420d621e8fac6b0fd0bf21b1ecd3f60cfa225a5b1931114779487d72a
|
| 3 |
+
size 15536
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15536
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0453137c5c7c5fc34c2f256c3c93e22036b6cd2a92e8ffc1d74379bf993729d0
|
| 3 |
size 15536
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f5102e93b3b130237df21a5f2bace34bae17ff3505215cc0b26c12f787c0c0b
|
| 3 |
+
size 15472
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17c3cf9ecb1946bfeabec74341670b2af7e53a439f2ca46db571f9d71890d4ef
|
| 3 |
+
size 15536
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc90a6007365e39e7e0345f81ac15b6e4bfb01eb7fc36962492017af5025d392
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,885 +1,587 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 50
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch":
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 150
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 200
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 250
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 300
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 350
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 400
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 450
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 500
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 550
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 600
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss":
|
| 100 |
"step": 650
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss":
|
| 107 |
"step": 700
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss":
|
| 114 |
"step": 750
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss":
|
| 121 |
"step": 800
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss":
|
| 128 |
"step": 850
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss":
|
| 135 |
"step": 900
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss":
|
| 142 |
"step": 950
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss":
|
| 149 |
"step": 1000
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss":
|
| 156 |
"step": 1050
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm":
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss":
|
| 163 |
"step": 1100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss":
|
| 170 |
"step": 1150
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss":
|
| 177 |
"step": 1200
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss":
|
| 184 |
"step": 1250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch":
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss":
|
| 191 |
"step": 1300
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch":
|
| 195 |
-
"grad_norm":
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss":
|
| 198 |
"step": 1350
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"grad_norm":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss":
|
| 205 |
"step": 1400
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 1450
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 1500
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 1550
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch":
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate":
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 1600
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate":
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 1650
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"grad_norm":
|
| 245 |
-
"learning_rate":
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 1700
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch":
|
| 251 |
-
"grad_norm":
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 1750
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch":
|
| 258 |
-
"grad_norm":
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 1800
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"grad_norm":
|
| 266 |
-
"learning_rate":
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 1850
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch":
|
| 272 |
-
"grad_norm":
|
| 273 |
-
"learning_rate":
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 1900
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"grad_norm":
|
| 280 |
-
"learning_rate":
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 1950
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"grad_norm":
|
| 287 |
-
"learning_rate":
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 2000
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch":
|
| 293 |
-
"grad_norm":
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 2050
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch":
|
| 300 |
-
"grad_norm":
|
| 301 |
-
"learning_rate":
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 2100
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"grad_norm":
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 2150
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch":
|
| 314 |
-
"grad_norm":
|
| 315 |
-
"learning_rate":
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 2200
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch":
|
| 321 |
-
"grad_norm":
|
| 322 |
-
"learning_rate":
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 2250
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"grad_norm":
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 2300
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch":
|
| 335 |
-
"grad_norm":
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 2350
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch":
|
| 342 |
-
"grad_norm":
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 2400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"grad_norm":
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 2450
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch":
|
| 356 |
-
"grad_norm":
|
| 357 |
-
"learning_rate":
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 2500
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch":
|
| 363 |
-
"grad_norm":
|
| 364 |
-
"learning_rate":
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 2550
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch":
|
| 370 |
-
"grad_norm":
|
| 371 |
-
"learning_rate":
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 2600
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch":
|
| 377 |
-
"grad_norm":
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 2650
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch":
|
| 384 |
-
"grad_norm":
|
| 385 |
-
"learning_rate":
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 2700
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch":
|
| 391 |
-
"grad_norm":
|
| 392 |
-
"learning_rate":
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 2750
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"epoch":
|
| 398 |
-
"grad_norm":
|
| 399 |
-
"learning_rate":
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 2800
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch":
|
| 405 |
-
"grad_norm":
|
| 406 |
-
"learning_rate":
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 2850
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch":
|
| 412 |
-
"grad_norm":
|
| 413 |
-
"learning_rate":
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 2900
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
-
"grad_norm":
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 2950
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch":
|
| 426 |
-
"grad_norm":
|
| 427 |
-
"learning_rate":
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 3000
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"eval_loss": 0.
|
| 434 |
-
"eval_runtime":
|
| 435 |
-
"eval_samples_per_second":
|
| 436 |
-
"eval_steps_per_second": 0.
|
| 437 |
-
"eval_wer": 0.
|
| 438 |
"step": 3000
|
| 439 |
},
|
| 440 |
{
|
| 441 |
-
"epoch":
|
| 442 |
-
"grad_norm":
|
| 443 |
-
"learning_rate":
|
| 444 |
-
"loss": 0.
|
| 445 |
"step": 3050
|
| 446 |
},
|
| 447 |
{
|
| 448 |
-
"epoch":
|
| 449 |
-
"grad_norm":
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 3100
|
| 453 |
},
|
| 454 |
{
|
| 455 |
-
"epoch":
|
| 456 |
-
"grad_norm":
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 3150
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch":
|
| 463 |
-
"grad_norm":
|
| 464 |
-
"learning_rate":
|
| 465 |
-
"loss": 0.
|
| 466 |
"step": 3200
|
| 467 |
},
|
| 468 |
{
|
| 469 |
-
"epoch":
|
| 470 |
-
"grad_norm":
|
| 471 |
-
"learning_rate":
|
| 472 |
-
"loss": 0.
|
| 473 |
"step": 3250
|
| 474 |
},
|
| 475 |
{
|
| 476 |
-
"epoch":
|
| 477 |
-
"grad_norm":
|
| 478 |
-
"learning_rate":
|
| 479 |
-
"loss": 0.
|
| 480 |
"step": 3300
|
| 481 |
},
|
| 482 |
{
|
| 483 |
-
"epoch":
|
| 484 |
-
"grad_norm":
|
| 485 |
-
"learning_rate": 9.
|
| 486 |
-
"loss": 0.
|
| 487 |
"step": 3350
|
| 488 |
},
|
| 489 |
{
|
| 490 |
-
"epoch":
|
| 491 |
-
"grad_norm":
|
| 492 |
-
"learning_rate": 9.
|
| 493 |
-
"loss": 0.
|
| 494 |
"step": 3400
|
| 495 |
},
|
| 496 |
{
|
| 497 |
-
"epoch":
|
| 498 |
-
"grad_norm":
|
| 499 |
-
"learning_rate": 9.
|
| 500 |
-
"loss": 0.
|
| 501 |
"step": 3450
|
| 502 |
},
|
| 503 |
{
|
| 504 |
-
"epoch":
|
| 505 |
-
"grad_norm":
|
| 506 |
-
"learning_rate": 9.
|
| 507 |
-
"loss": 0.
|
| 508 |
"step": 3500
|
| 509 |
},
|
| 510 |
{
|
| 511 |
-
"epoch":
|
| 512 |
-
"grad_norm":
|
| 513 |
-
"learning_rate": 9.
|
| 514 |
-
"loss": 0.
|
| 515 |
"step": 3550
|
| 516 |
},
|
| 517 |
{
|
| 518 |
-
"epoch":
|
| 519 |
-
"grad_norm":
|
| 520 |
-
"learning_rate": 9.
|
| 521 |
-
"loss": 0.
|
| 522 |
"step": 3600
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"epoch":
|
| 526 |
-
"grad_norm":
|
| 527 |
-
"learning_rate": 9.
|
| 528 |
-
"loss": 0.
|
| 529 |
"step": 3650
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch":
|
| 533 |
-
"grad_norm":
|
| 534 |
-
"learning_rate": 9.
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 3700
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"epoch":
|
| 540 |
-
"grad_norm":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 3750
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch":
|
| 547 |
-
"grad_norm":
|
| 548 |
-
"learning_rate":
|
| 549 |
-
"loss": 0.
|
| 550 |
"step": 3800
|
| 551 |
},
|
| 552 |
{
|
| 553 |
-
"epoch":
|
| 554 |
-
"grad_norm":
|
| 555 |
-
"learning_rate":
|
| 556 |
-
"loss": 0.
|
| 557 |
"step": 3850
|
| 558 |
},
|
| 559 |
{
|
| 560 |
-
"epoch":
|
| 561 |
-
"grad_norm":
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 0.
|
| 564 |
"step": 3900
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"epoch":
|
| 568 |
-
"grad_norm":
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 3950
|
| 572 |
},
|
| 573 |
{
|
| 574 |
-
"epoch":
|
| 575 |
-
"grad_norm":
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss": 0.
|
| 578 |
"step": 4000
|
| 579 |
-
},
|
| 580 |
-
{
|
| 581 |
-
"epoch": 58.69565217391305,
|
| 582 |
-
"grad_norm": 1.3925776481628418,
|
| 583 |
-
"learning_rate": 9.606706753006477e-05,
|
| 584 |
-
"loss": 0.5858,
|
| 585 |
-
"step": 4050
|
| 586 |
-
},
|
| 587 |
-
{
|
| 588 |
-
"epoch": 59.42028985507246,
|
| 589 |
-
"grad_norm": 1.3453298807144165,
|
| 590 |
-
"learning_rate": 9.593987049028678e-05,
|
| 591 |
-
"loss": 0.5715,
|
| 592 |
-
"step": 4100
|
| 593 |
-
},
|
| 594 |
-
{
|
| 595 |
-
"epoch": 60.14492753623188,
|
| 596 |
-
"grad_norm": 1.5027530193328857,
|
| 597 |
-
"learning_rate": 9.581267345050879e-05,
|
| 598 |
-
"loss": 0.5599,
|
| 599 |
-
"step": 4150
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 60.869565217391305,
|
| 603 |
-
"grad_norm": 1.3528389930725098,
|
| 604 |
-
"learning_rate": 9.568547641073081e-05,
|
| 605 |
-
"loss": 0.5492,
|
| 606 |
-
"step": 4200
|
| 607 |
-
},
|
| 608 |
-
{
|
| 609 |
-
"epoch": 61.594202898550726,
|
| 610 |
-
"grad_norm": 1.344739317893982,
|
| 611 |
-
"learning_rate": 9.555827937095283e-05,
|
| 612 |
-
"loss": 0.5386,
|
| 613 |
-
"step": 4250
|
| 614 |
-
},
|
| 615 |
-
{
|
| 616 |
-
"epoch": 62.31884057971015,
|
| 617 |
-
"grad_norm": 1.4145418405532837,
|
| 618 |
-
"learning_rate": 9.543108233117484e-05,
|
| 619 |
-
"loss": 0.5349,
|
| 620 |
-
"step": 4300
|
| 621 |
-
},
|
| 622 |
-
{
|
| 623 |
-
"epoch": 63.04347826086956,
|
| 624 |
-
"grad_norm": 1.4277065992355347,
|
| 625 |
-
"learning_rate": 9.530388529139686e-05,
|
| 626 |
-
"loss": 0.5177,
|
| 627 |
-
"step": 4350
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 63.768115942028984,
|
| 631 |
-
"grad_norm": 1.4313771724700928,
|
| 632 |
-
"learning_rate": 9.517668825161888e-05,
|
| 633 |
-
"loss": 0.5193,
|
| 634 |
-
"step": 4400
|
| 635 |
-
},
|
| 636 |
-
{
|
| 637 |
-
"epoch": 64.4927536231884,
|
| 638 |
-
"grad_norm": 1.3793104887008667,
|
| 639 |
-
"learning_rate": 9.504949121184089e-05,
|
| 640 |
-
"loss": 0.5119,
|
| 641 |
-
"step": 4450
|
| 642 |
-
},
|
| 643 |
-
{
|
| 644 |
-
"epoch": 65.21739130434783,
|
| 645 |
-
"grad_norm": 1.312393307685852,
|
| 646 |
-
"learning_rate": 9.492229417206291e-05,
|
| 647 |
-
"loss": 0.4959,
|
| 648 |
-
"step": 4500
|
| 649 |
-
},
|
| 650 |
-
{
|
| 651 |
-
"epoch": 65.21739130434783,
|
| 652 |
-
"eval_loss": 1.0089221000671387,
|
| 653 |
-
"eval_runtime": 304.2405,
|
| 654 |
-
"eval_samples_per_second": 19.281,
|
| 655 |
-
"eval_steps_per_second": 0.026,
|
| 656 |
-
"eval_wer": 0.4844446722361745,
|
| 657 |
-
"step": 4500
|
| 658 |
-
},
|
| 659 |
-
{
|
| 660 |
-
"epoch": 65.94202898550725,
|
| 661 |
-
"grad_norm": 1.6502594947814941,
|
| 662 |
-
"learning_rate": 9.479509713228492e-05,
|
| 663 |
-
"loss": 0.4997,
|
| 664 |
-
"step": 4550
|
| 665 |
-
},
|
| 666 |
-
{
|
| 667 |
-
"epoch": 66.66666666666667,
|
| 668 |
-
"grad_norm": 1.2879911661148071,
|
| 669 |
-
"learning_rate": 9.466790009250694e-05,
|
| 670 |
-
"loss": 0.4935,
|
| 671 |
-
"step": 4600
|
| 672 |
-
},
|
| 673 |
-
{
|
| 674 |
-
"epoch": 67.3913043478261,
|
| 675 |
-
"grad_norm": 1.3771027326583862,
|
| 676 |
-
"learning_rate": 9.454070305272896e-05,
|
| 677 |
-
"loss": 0.4821,
|
| 678 |
-
"step": 4650
|
| 679 |
-
},
|
| 680 |
-
{
|
| 681 |
-
"epoch": 68.1159420289855,
|
| 682 |
-
"grad_norm": 1.8583579063415527,
|
| 683 |
-
"learning_rate": 9.441350601295097e-05,
|
| 684 |
-
"loss": 0.4733,
|
| 685 |
-
"step": 4700
|
| 686 |
-
},
|
| 687 |
-
{
|
| 688 |
-
"epoch": 68.84057971014492,
|
| 689 |
-
"grad_norm": 1.495661735534668,
|
| 690 |
-
"learning_rate": 9.428630897317299e-05,
|
| 691 |
-
"loss": 0.4737,
|
| 692 |
-
"step": 4750
|
| 693 |
-
},
|
| 694 |
-
{
|
| 695 |
-
"epoch": 69.56521739130434,
|
| 696 |
-
"grad_norm": 1.5063421726226807,
|
| 697 |
-
"learning_rate": 9.415911193339501e-05,
|
| 698 |
-
"loss": 0.4716,
|
| 699 |
-
"step": 4800
|
| 700 |
-
},
|
| 701 |
-
{
|
| 702 |
-
"epoch": 70.28985507246377,
|
| 703 |
-
"grad_norm": 1.748350977897644,
|
| 704 |
-
"learning_rate": 9.403191489361702e-05,
|
| 705 |
-
"loss": 0.4653,
|
| 706 |
-
"step": 4850
|
| 707 |
-
},
|
| 708 |
-
{
|
| 709 |
-
"epoch": 71.01449275362319,
|
| 710 |
-
"grad_norm": 1.3581229448318481,
|
| 711 |
-
"learning_rate": 9.390471785383905e-05,
|
| 712 |
-
"loss": 0.4521,
|
| 713 |
-
"step": 4900
|
| 714 |
-
},
|
| 715 |
-
{
|
| 716 |
-
"epoch": 71.73913043478261,
|
| 717 |
-
"grad_norm": 1.439302921295166,
|
| 718 |
-
"learning_rate": 9.377752081406106e-05,
|
| 719 |
-
"loss": 0.4538,
|
| 720 |
-
"step": 4950
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 72.46376811594203,
|
| 724 |
-
"grad_norm": 1.3644930124282837,
|
| 725 |
-
"learning_rate": 9.365032377428307e-05,
|
| 726 |
-
"loss": 0.4435,
|
| 727 |
-
"step": 5000
|
| 728 |
-
},
|
| 729 |
-
{
|
| 730 |
-
"epoch": 73.18840579710145,
|
| 731 |
-
"grad_norm": 1.3828235864639282,
|
| 732 |
-
"learning_rate": 9.35231267345051e-05,
|
| 733 |
-
"loss": 0.4377,
|
| 734 |
-
"step": 5050
|
| 735 |
-
},
|
| 736 |
-
{
|
| 737 |
-
"epoch": 73.91304347826087,
|
| 738 |
-
"grad_norm": 1.3479715585708618,
|
| 739 |
-
"learning_rate": 9.339592969472711e-05,
|
| 740 |
-
"loss": 0.4358,
|
| 741 |
-
"step": 5100
|
| 742 |
-
},
|
| 743 |
-
{
|
| 744 |
-
"epoch": 74.6376811594203,
|
| 745 |
-
"grad_norm": 1.5974297523498535,
|
| 746 |
-
"learning_rate": 9.326873265494912e-05,
|
| 747 |
-
"loss": 0.4332,
|
| 748 |
-
"step": 5150
|
| 749 |
-
},
|
| 750 |
-
{
|
| 751 |
-
"epoch": 75.3623188405797,
|
| 752 |
-
"grad_norm": 1.2654752731323242,
|
| 753 |
-
"learning_rate": 9.314153561517115e-05,
|
| 754 |
-
"loss": 0.4235,
|
| 755 |
-
"step": 5200
|
| 756 |
-
},
|
| 757 |
-
{
|
| 758 |
-
"epoch": 76.08695652173913,
|
| 759 |
-
"grad_norm": 1.6698533296585083,
|
| 760 |
-
"learning_rate": 9.301433857539316e-05,
|
| 761 |
-
"loss": 0.4137,
|
| 762 |
-
"step": 5250
|
| 763 |
-
},
|
| 764 |
-
{
|
| 765 |
-
"epoch": 76.81159420289855,
|
| 766 |
-
"grad_norm": 1.6293294429779053,
|
| 767 |
-
"learning_rate": 9.288714153561517e-05,
|
| 768 |
-
"loss": 0.4151,
|
| 769 |
-
"step": 5300
|
| 770 |
-
},
|
| 771 |
-
{
|
| 772 |
-
"epoch": 77.53623188405797,
|
| 773 |
-
"grad_norm": 1.9236047267913818,
|
| 774 |
-
"learning_rate": 9.27599444958372e-05,
|
| 775 |
-
"loss": 0.4069,
|
| 776 |
-
"step": 5350
|
| 777 |
-
},
|
| 778 |
-
{
|
| 779 |
-
"epoch": 78.26086956521739,
|
| 780 |
-
"grad_norm": 1.5525872707366943,
|
| 781 |
-
"learning_rate": 9.263274745605921e-05,
|
| 782 |
-
"loss": 0.4052,
|
| 783 |
-
"step": 5400
|
| 784 |
-
},
|
| 785 |
-
{
|
| 786 |
-
"epoch": 78.98550724637681,
|
| 787 |
-
"grad_norm": 1.4388564825057983,
|
| 788 |
-
"learning_rate": 9.250555041628122e-05,
|
| 789 |
-
"loss": 0.4043,
|
| 790 |
-
"step": 5450
|
| 791 |
-
},
|
| 792 |
-
{
|
| 793 |
-
"epoch": 79.71014492753623,
|
| 794 |
-
"grad_norm": 1.520162582397461,
|
| 795 |
-
"learning_rate": 9.237835337650325e-05,
|
| 796 |
-
"loss": 0.3965,
|
| 797 |
-
"step": 5500
|
| 798 |
-
},
|
| 799 |
-
{
|
| 800 |
-
"epoch": 80.43478260869566,
|
| 801 |
-
"grad_norm": 1.4822075366973877,
|
| 802 |
-
"learning_rate": 9.225115633672526e-05,
|
| 803 |
-
"loss": 0.3948,
|
| 804 |
-
"step": 5550
|
| 805 |
-
},
|
| 806 |
-
{
|
| 807 |
-
"epoch": 81.15942028985508,
|
| 808 |
-
"grad_norm": 1.5057759284973145,
|
| 809 |
-
"learning_rate": 9.212395929694727e-05,
|
| 810 |
-
"loss": 0.3867,
|
| 811 |
-
"step": 5600
|
| 812 |
-
},
|
| 813 |
-
{
|
| 814 |
-
"epoch": 81.8840579710145,
|
| 815 |
-
"grad_norm": 2.7516353130340576,
|
| 816 |
-
"learning_rate": 9.19967622571693e-05,
|
| 817 |
-
"loss": 0.3871,
|
| 818 |
-
"step": 5650
|
| 819 |
-
},
|
| 820 |
-
{
|
| 821 |
-
"epoch": 82.6086956521739,
|
| 822 |
-
"grad_norm": 1.4540650844573975,
|
| 823 |
-
"learning_rate": 9.186956521739131e-05,
|
| 824 |
-
"loss": 0.38,
|
| 825 |
-
"step": 5700
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 83.33333333333333,
|
| 829 |
-
"grad_norm": 1.484658122062683,
|
| 830 |
-
"learning_rate": 9.174236817761332e-05,
|
| 831 |
-
"loss": 0.378,
|
| 832 |
-
"step": 5750
|
| 833 |
-
},
|
| 834 |
-
{
|
| 835 |
-
"epoch": 84.05797101449275,
|
| 836 |
-
"grad_norm": 1.5327116250991821,
|
| 837 |
-
"learning_rate": 9.161517113783534e-05,
|
| 838 |
-
"loss": 0.371,
|
| 839 |
-
"step": 5800
|
| 840 |
-
},
|
| 841 |
-
{
|
| 842 |
-
"epoch": 84.78260869565217,
|
| 843 |
-
"grad_norm": 1.7103629112243652,
|
| 844 |
-
"learning_rate": 9.148797409805736e-05,
|
| 845 |
-
"loss": 0.3768,
|
| 846 |
-
"step": 5850
|
| 847 |
-
},
|
| 848 |
-
{
|
| 849 |
-
"epoch": 85.5072463768116,
|
| 850 |
-
"grad_norm": 1.3443946838378906,
|
| 851 |
-
"learning_rate": 9.136077705827937e-05,
|
| 852 |
-
"loss": 0.364,
|
| 853 |
-
"step": 5900
|
| 854 |
-
},
|
| 855 |
-
{
|
| 856 |
-
"epoch": 86.23188405797102,
|
| 857 |
-
"grad_norm": 1.4796549081802368,
|
| 858 |
-
"learning_rate": 9.12335800185014e-05,
|
| 859 |
-
"loss": 0.3613,
|
| 860 |
-
"step": 5950
|
| 861 |
-
},
|
| 862 |
-
{
|
| 863 |
-
"epoch": 86.95652173913044,
|
| 864 |
-
"grad_norm": 1.3333659172058105,
|
| 865 |
-
"learning_rate": 9.11063829787234e-05,
|
| 866 |
-
"loss": 0.3584,
|
| 867 |
-
"step": 6000
|
| 868 |
-
},
|
| 869 |
-
{
|
| 870 |
-
"epoch": 86.95652173913044,
|
| 871 |
-
"eval_loss": 1.1995052099227905,
|
| 872 |
-
"eval_runtime": 473.8923,
|
| 873 |
-
"eval_samples_per_second": 12.378,
|
| 874 |
-
"eval_steps_per_second": 0.017,
|
| 875 |
-
"eval_wer": 0.4768592076264671,
|
| 876 |
-
"step": 6000
|
| 877 |
}
|
| 878 |
],
|
| 879 |
"logging_steps": 50,
|
| 880 |
-
"max_steps":
|
| 881 |
"num_input_tokens_seen": 0,
|
| 882 |
-
"num_train_epochs":
|
| 883 |
"save_steps": 500,
|
| 884 |
"stateful_callbacks": {
|
| 885 |
"TrainerControl": {
|
|
@@ -893,7 +595,7 @@
|
|
| 893 |
"attributes": {}
|
| 894 |
}
|
| 895 |
},
|
| 896 |
-
"total_flos":
|
| 897 |
"train_batch_size": 64,
|
| 898 |
"trial_name": null,
|
| 899 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 108.10810810810811,
|
| 5 |
"eval_steps": 1500,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 1.3513513513513513,
|
| 13 |
+
"grad_norm": 0.5760506987571716,
|
| 14 |
+
"learning_rate": 1.9364864864864865e-06,
|
| 15 |
+
"loss": 0.0736,
|
| 16 |
"step": 50
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 2.7027027027027026,
|
| 20 |
+
"grad_norm": 0.4748266339302063,
|
| 21 |
+
"learning_rate": 3.2743243243243245e-06,
|
| 22 |
+
"loss": 0.0682,
|
| 23 |
"step": 100
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 4.054054054054054,
|
| 27 |
+
"grad_norm": 0.4784703552722931,
|
| 28 |
+
"learning_rate": 4.612162162162162e-06,
|
| 29 |
+
"loss": 0.0661,
|
| 30 |
"step": 150
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 5.405405405405405,
|
| 34 |
+
"grad_norm": 0.4363403022289276,
|
| 35 |
+
"learning_rate": 5.95e-06,
|
| 36 |
+
"loss": 0.0646,
|
| 37 |
"step": 200
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 6.756756756756757,
|
| 41 |
+
"grad_norm": 0.49891752004623413,
|
| 42 |
+
"learning_rate": 7.287837837837838e-06,
|
| 43 |
+
"loss": 0.0624,
|
| 44 |
"step": 250
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 8.108108108108109,
|
| 48 |
+
"grad_norm": 0.47630417346954346,
|
| 49 |
+
"learning_rate": 8.625675675675676e-06,
|
| 50 |
+
"loss": 0.0635,
|
| 51 |
"step": 300
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 9.45945945945946,
|
| 55 |
+
"grad_norm": 0.5554671287536621,
|
| 56 |
+
"learning_rate": 9.963513513513515e-06,
|
| 57 |
+
"loss": 0.0617,
|
| 58 |
"step": 350
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 10.81081081081081,
|
| 62 |
+
"grad_norm": 0.4327123165130615,
|
| 63 |
+
"learning_rate": 1.1301351351351353e-05,
|
| 64 |
+
"loss": 0.0595,
|
| 65 |
"step": 400
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 12.162162162162161,
|
| 69 |
+
"grad_norm": 0.5002420544624329,
|
| 70 |
+
"learning_rate": 1.263918918918919e-05,
|
| 71 |
+
"loss": 0.0585,
|
| 72 |
"step": 450
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 13.513513513513514,
|
| 76 |
+
"grad_norm": 0.42524299025535583,
|
| 77 |
+
"learning_rate": 1.3977027027027028e-05,
|
| 78 |
+
"loss": 0.0579,
|
| 79 |
"step": 500
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 14.864864864864865,
|
| 83 |
+
"grad_norm": 0.44030219316482544,
|
| 84 |
+
"learning_rate": 1.5314864864864867e-05,
|
| 85 |
+
"loss": 0.0575,
|
| 86 |
"step": 550
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 16.216216216216218,
|
| 90 |
+
"grad_norm": 0.46804261207580566,
|
| 91 |
+
"learning_rate": 1.6625945945945947e-05,
|
| 92 |
+
"loss": 0.0579,
|
| 93 |
"step": 600
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 17.56756756756757,
|
| 97 |
+
"grad_norm": 0.5248824954032898,
|
| 98 |
+
"learning_rate": 1.7963783783783787e-05,
|
| 99 |
+
"loss": 0.0556,
|
| 100 |
"step": 650
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 18.91891891891892,
|
| 104 |
+
"grad_norm": 0.43462327122688293,
|
| 105 |
+
"learning_rate": 1.9301621621621623e-05,
|
| 106 |
+
"loss": 0.0546,
|
| 107 |
"step": 700
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 20.27027027027027,
|
| 111 |
+
"grad_norm": 0.48718762397766113,
|
| 112 |
+
"learning_rate": 2.0639459459459462e-05,
|
| 113 |
+
"loss": 0.0529,
|
| 114 |
"step": 750
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 21.62162162162162,
|
| 118 |
+
"grad_norm": 0.40828168392181396,
|
| 119 |
+
"learning_rate": 2.19772972972973e-05,
|
| 120 |
+
"loss": 0.0523,
|
| 121 |
"step": 800
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 22.972972972972972,
|
| 125 |
+
"grad_norm": 0.4686122238636017,
|
| 126 |
+
"learning_rate": 2.3315135135135137e-05,
|
| 127 |
+
"loss": 0.0531,
|
| 128 |
"step": 850
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 24.324324324324323,
|
| 132 |
+
"grad_norm": 0.4426785707473755,
|
| 133 |
+
"learning_rate": 2.4652972972972976e-05,
|
| 134 |
+
"loss": 0.051,
|
| 135 |
"step": 900
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 25.675675675675677,
|
| 139 |
+
"grad_norm": 0.4910499155521393,
|
| 140 |
+
"learning_rate": 2.5990810810810812e-05,
|
| 141 |
+
"loss": 0.0486,
|
| 142 |
"step": 950
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 27.027027027027028,
|
| 146 |
+
"grad_norm": 0.4253314435482025,
|
| 147 |
+
"learning_rate": 2.7328648648648652e-05,
|
| 148 |
+
"loss": 0.0491,
|
| 149 |
"step": 1000
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 28.37837837837838,
|
| 153 |
+
"grad_norm": 0.3838571012020111,
|
| 154 |
+
"learning_rate": 2.866648648648649e-05,
|
| 155 |
+
"loss": 0.049,
|
| 156 |
"step": 1050
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 29.72972972972973,
|
| 160 |
+
"grad_norm": 0.39428308606147766,
|
| 161 |
+
"learning_rate": 3.0004324324324327e-05,
|
| 162 |
+
"loss": 0.0478,
|
| 163 |
"step": 1100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 31.08108108108108,
|
| 167 |
+
"grad_norm": 0.3973025381565094,
|
| 168 |
+
"learning_rate": 3.134216216216216e-05,
|
| 169 |
+
"loss": 0.0473,
|
| 170 |
"step": 1150
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 32.432432432432435,
|
| 174 |
+
"grad_norm": 0.47299668192863464,
|
| 175 |
+
"learning_rate": 3.268e-05,
|
| 176 |
+
"loss": 0.047,
|
| 177 |
"step": 1200
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 33.78378378378378,
|
| 181 |
+
"grad_norm": 0.5077139139175415,
|
| 182 |
+
"learning_rate": 3.4017837837837835e-05,
|
| 183 |
+
"loss": 0.0459,
|
| 184 |
"step": 1250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 35.13513513513514,
|
| 188 |
+
"grad_norm": 0.3789336085319519,
|
| 189 |
+
"learning_rate": 3.535567567567568e-05,
|
| 190 |
+
"loss": 0.0462,
|
| 191 |
"step": 1300
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 36.486486486486484,
|
| 195 |
+
"grad_norm": 0.3798762857913971,
|
| 196 |
+
"learning_rate": 3.669351351351351e-05,
|
| 197 |
+
"loss": 0.045,
|
| 198 |
"step": 1350
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 37.83783783783784,
|
| 202 |
+
"grad_norm": 0.41409873962402344,
|
| 203 |
+
"learning_rate": 3.803135135135135e-05,
|
| 204 |
+
"loss": 0.0438,
|
| 205 |
"step": 1400
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 39.189189189189186,
|
| 209 |
+
"grad_norm": 0.4816993176937103,
|
| 210 |
+
"learning_rate": 3.936918918918919e-05,
|
| 211 |
+
"loss": 0.0432,
|
| 212 |
"step": 1450
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 40.54054054054054,
|
| 216 |
+
"grad_norm": 0.31075775623321533,
|
| 217 |
+
"learning_rate": 4.070702702702703e-05,
|
| 218 |
+
"loss": 0.0415,
|
| 219 |
"step": 1500
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 41.891891891891895,
|
| 223 |
+
"grad_norm": 0.5353565812110901,
|
| 224 |
+
"learning_rate": 4.2044864864864864e-05,
|
| 225 |
+
"loss": 0.0414,
|
| 226 |
"step": 1550
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 43.24324324324324,
|
| 230 |
+
"grad_norm": 0.3337886333465576,
|
| 231 |
+
"learning_rate": 4.3382702702702707e-05,
|
| 232 |
+
"loss": 0.0406,
|
| 233 |
"step": 1600
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 44.5945945945946,
|
| 237 |
+
"grad_norm": 0.3847792446613312,
|
| 238 |
+
"learning_rate": 4.472054054054054e-05,
|
| 239 |
+
"loss": 0.0404,
|
| 240 |
"step": 1650
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 45.945945945945944,
|
| 244 |
+
"grad_norm": 0.4075019657611847,
|
| 245 |
+
"learning_rate": 4.605837837837838e-05,
|
| 246 |
+
"loss": 0.0409,
|
| 247 |
"step": 1700
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 47.2972972972973,
|
| 251 |
+
"grad_norm": 0.4205191433429718,
|
| 252 |
+
"learning_rate": 4.7396216216216214e-05,
|
| 253 |
+
"loss": 0.0399,
|
| 254 |
"step": 1750
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 48.648648648648646,
|
| 258 |
+
"grad_norm": 0.5053867101669312,
|
| 259 |
+
"learning_rate": 4.873405405405406e-05,
|
| 260 |
+
"loss": 0.0387,
|
| 261 |
"step": 1800
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 50.0,
|
| 265 |
+
"grad_norm": 0.43625885248184204,
|
| 266 |
+
"learning_rate": 5.007189189189189e-05,
|
| 267 |
+
"loss": 0.0393,
|
| 268 |
"step": 1850
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 51.351351351351354,
|
| 272 |
+
"grad_norm": 0.44896236062049866,
|
| 273 |
+
"learning_rate": 5.140972972972973e-05,
|
| 274 |
+
"loss": 0.0376,
|
| 275 |
"step": 1900
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 52.7027027027027,
|
| 279 |
+
"grad_norm": 0.42207279801368713,
|
| 280 |
+
"learning_rate": 5.274756756756757e-05,
|
| 281 |
+
"loss": 0.0392,
|
| 282 |
"step": 1950
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 54.054054054054056,
|
| 286 |
+
"grad_norm": 0.4605530798435211,
|
| 287 |
+
"learning_rate": 5.408540540540541e-05,
|
| 288 |
+
"loss": 0.0384,
|
| 289 |
"step": 2000
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 55.4054054054054,
|
| 293 |
+
"grad_norm": 0.4523848295211792,
|
| 294 |
+
"learning_rate": 5.5423243243243243e-05,
|
| 295 |
+
"loss": 0.0366,
|
| 296 |
"step": 2050
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 56.75675675675676,
|
| 300 |
+
"grad_norm": 0.37463346123695374,
|
| 301 |
+
"learning_rate": 5.6761081081081086e-05,
|
| 302 |
+
"loss": 0.037,
|
| 303 |
"step": 2100
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 58.108108108108105,
|
| 307 |
+
"grad_norm": 0.5655389428138733,
|
| 308 |
+
"learning_rate": 5.809891891891892e-05,
|
| 309 |
+
"loss": 0.0383,
|
| 310 |
"step": 2150
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 59.45945945945946,
|
| 314 |
+
"grad_norm": 0.441587895154953,
|
| 315 |
+
"learning_rate": 5.943675675675676e-05,
|
| 316 |
+
"loss": 0.0392,
|
| 317 |
"step": 2200
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 60.810810810810814,
|
| 321 |
+
"grad_norm": 0.44860920310020447,
|
| 322 |
+
"learning_rate": 6.074783783783784e-05,
|
| 323 |
+
"loss": 0.0372,
|
| 324 |
"step": 2250
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 62.16216216216216,
|
| 328 |
+
"grad_norm": 0.4874947965145111,
|
| 329 |
+
"learning_rate": 6.208567567567567e-05,
|
| 330 |
+
"loss": 0.0372,
|
| 331 |
"step": 2300
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 63.513513513513516,
|
| 335 |
+
"grad_norm": 0.44674238562583923,
|
| 336 |
+
"learning_rate": 6.342351351351351e-05,
|
| 337 |
+
"loss": 0.0368,
|
| 338 |
"step": 2350
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 64.86486486486487,
|
| 342 |
+
"grad_norm": 0.535265326499939,
|
| 343 |
+
"learning_rate": 6.476135135135136e-05,
|
| 344 |
+
"loss": 0.0372,
|
| 345 |
"step": 2400
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 66.21621621621621,
|
| 349 |
+
"grad_norm": 0.38546523451805115,
|
| 350 |
+
"learning_rate": 6.60991891891892e-05,
|
| 351 |
+
"loss": 0.0349,
|
| 352 |
"step": 2450
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 67.56756756756756,
|
| 356 |
+
"grad_norm": 0.4751232862472534,
|
| 357 |
+
"learning_rate": 6.743702702702703e-05,
|
| 358 |
+
"loss": 0.038,
|
| 359 |
"step": 2500
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 68.91891891891892,
|
| 363 |
+
"grad_norm": 0.6618958115577698,
|
| 364 |
+
"learning_rate": 6.877486486486487e-05,
|
| 365 |
+
"loss": 0.0512,
|
| 366 |
"step": 2550
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 70.27027027027027,
|
| 370 |
+
"grad_norm": 0.4467822015285492,
|
| 371 |
+
"learning_rate": 7.01127027027027e-05,
|
| 372 |
+
"loss": 0.0517,
|
| 373 |
"step": 2600
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 71.62162162162163,
|
| 377 |
+
"grad_norm": 0.5807027816772461,
|
| 378 |
+
"learning_rate": 7.145054054054054e-05,
|
| 379 |
+
"loss": 0.0506,
|
| 380 |
"step": 2650
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 72.97297297297297,
|
| 384 |
+
"grad_norm": 0.44088873267173767,
|
| 385 |
+
"learning_rate": 7.278837837837837e-05,
|
| 386 |
+
"loss": 0.0517,
|
| 387 |
"step": 2700
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 74.32432432432432,
|
| 391 |
+
"grad_norm": 0.5117065906524658,
|
| 392 |
+
"learning_rate": 7.412621621621622e-05,
|
| 393 |
+
"loss": 0.0497,
|
| 394 |
"step": 2750
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"epoch": 75.67567567567568,
|
| 398 |
+
"grad_norm": 0.5457988381385803,
|
| 399 |
+
"learning_rate": 7.546405405405406e-05,
|
| 400 |
+
"loss": 0.0494,
|
| 401 |
"step": 2800
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 77.02702702702703,
|
| 405 |
+
"grad_norm": 0.35911738872528076,
|
| 406 |
+
"learning_rate": 7.68018918918919e-05,
|
| 407 |
+
"loss": 0.0476,
|
| 408 |
"step": 2850
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 78.37837837837837,
|
| 412 |
+
"grad_norm": 0.5895106196403503,
|
| 413 |
+
"learning_rate": 7.813972972972973e-05,
|
| 414 |
+
"loss": 0.0479,
|
| 415 |
"step": 2900
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 79.72972972972973,
|
| 419 |
+
"grad_norm": 0.39779385924339294,
|
| 420 |
+
"learning_rate": 7.947756756756757e-05,
|
| 421 |
+
"loss": 0.0479,
|
| 422 |
"step": 2950
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 81.08108108108108,
|
| 426 |
+
"grad_norm": 0.5251230001449585,
|
| 427 |
+
"learning_rate": 8.08154054054054e-05,
|
| 428 |
+
"loss": 0.0468,
|
| 429 |
"step": 3000
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 81.08108108108108,
|
| 433 |
+
"eval_loss": 0.5344434976577759,
|
| 434 |
+
"eval_runtime": 19.3274,
|
| 435 |
+
"eval_samples_per_second": 81.076,
|
| 436 |
+
"eval_steps_per_second": 0.259,
|
| 437 |
+
"eval_wer": 0.18456803226491192,
|
| 438 |
"step": 3000
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"epoch": 82.43243243243244,
|
| 442 |
+
"grad_norm": 0.44322407245635986,
|
| 443 |
+
"learning_rate": 8.215324324324325e-05,
|
| 444 |
+
"loss": 0.0458,
|
| 445 |
"step": 3050
|
| 446 |
},
|
| 447 |
{
|
| 448 |
+
"epoch": 83.78378378378379,
|
| 449 |
+
"grad_norm": 0.47398409247398376,
|
| 450 |
+
"learning_rate": 8.349108108108109e-05,
|
| 451 |
+
"loss": 0.0461,
|
| 452 |
"step": 3100
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 85.13513513513513,
|
| 456 |
+
"grad_norm": 0.452659010887146,
|
| 457 |
+
"learning_rate": 8.482891891891893e-05,
|
| 458 |
+
"loss": 0.045,
|
| 459 |
"step": 3150
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 86.48648648648648,
|
| 463 |
+
"grad_norm": 0.6125317215919495,
|
| 464 |
+
"learning_rate": 8.616675675675676e-05,
|
| 465 |
+
"loss": 0.046,
|
| 466 |
"step": 3200
|
| 467 |
},
|
| 468 |
{
|
| 469 |
+
"epoch": 87.83783783783784,
|
| 470 |
+
"grad_norm": 0.4655373692512512,
|
| 471 |
+
"learning_rate": 8.75045945945946e-05,
|
| 472 |
+
"loss": 0.0462,
|
| 473 |
"step": 3250
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"epoch": 89.1891891891892,
|
| 477 |
+
"grad_norm": 0.5071247220039368,
|
| 478 |
+
"learning_rate": 8.884243243243243e-05,
|
| 479 |
+
"loss": 0.0455,
|
| 480 |
"step": 3300
|
| 481 |
},
|
| 482 |
{
|
| 483 |
+
"epoch": 90.54054054054055,
|
| 484 |
+
"grad_norm": 0.4586324691772461,
|
| 485 |
+
"learning_rate": 9.018027027027027e-05,
|
| 486 |
+
"loss": 0.0443,
|
| 487 |
"step": 3350
|
| 488 |
},
|
| 489 |
{
|
| 490 |
+
"epoch": 91.89189189189189,
|
| 491 |
+
"grad_norm": 0.49810245633125305,
|
| 492 |
+
"learning_rate": 9.151810810810812e-05,
|
| 493 |
+
"loss": 0.0444,
|
| 494 |
"step": 3400
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"epoch": 93.24324324324324,
|
| 498 |
+
"grad_norm": 0.4874321222305298,
|
| 499 |
+
"learning_rate": 9.285594594594595e-05,
|
| 500 |
+
"loss": 0.0424,
|
| 501 |
"step": 3450
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 94.5945945945946,
|
| 505 |
+
"grad_norm": 0.5060502886772156,
|
| 506 |
+
"learning_rate": 9.419378378378379e-05,
|
| 507 |
+
"loss": 0.0432,
|
| 508 |
"step": 3500
|
| 509 |
},
|
| 510 |
{
|
| 511 |
+
"epoch": 95.94594594594595,
|
| 512 |
+
"grad_norm": 0.4356514513492584,
|
| 513 |
+
"learning_rate": 9.553162162162163e-05,
|
| 514 |
+
"loss": 0.042,
|
| 515 |
"step": 3550
|
| 516 |
},
|
| 517 |
{
|
| 518 |
+
"epoch": 97.29729729729729,
|
| 519 |
+
"grad_norm": 0.5080994367599487,
|
| 520 |
+
"learning_rate": 9.684270270270271e-05,
|
| 521 |
+
"loss": 0.0424,
|
| 522 |
"step": 3600
|
| 523 |
},
|
| 524 |
{
|
| 525 |
+
"epoch": 98.64864864864865,
|
| 526 |
+
"grad_norm": 0.6090648174285889,
|
| 527 |
+
"learning_rate": 9.818054054054055e-05,
|
| 528 |
+
"loss": 0.0423,
|
| 529 |
"step": 3650
|
| 530 |
},
|
| 531 |
{
|
| 532 |
+
"epoch": 100.0,
|
| 533 |
+
"grad_norm": 0.6025941967964172,
|
| 534 |
+
"learning_rate": 9.951837837837838e-05,
|
| 535 |
+
"loss": 0.0445,
|
| 536 |
"step": 3700
|
| 537 |
},
|
| 538 |
{
|
| 539 |
+
"epoch": 101.35135135135135,
|
| 540 |
+
"grad_norm": 0.592052161693573,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 0.0425,
|
| 543 |
"step": 3750
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 102.70270270270271,
|
| 547 |
+
"grad_norm": 0.5158424973487854,
|
| 548 |
+
"learning_rate": 0.0001,
|
| 549 |
+
"loss": 0.0423,
|
| 550 |
"step": 3800
|
| 551 |
},
|
| 552 |
{
|
| 553 |
+
"epoch": 104.05405405405405,
|
| 554 |
+
"grad_norm": 0.45459866523742676,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"loss": 0.0411,
|
| 557 |
"step": 3850
|
| 558 |
},
|
| 559 |
{
|
| 560 |
+
"epoch": 105.4054054054054,
|
| 561 |
+
"grad_norm": 0.4477308392524719,
|
| 562 |
+
"learning_rate": 0.0001,
|
| 563 |
+
"loss": 0.0426,
|
| 564 |
"step": 3900
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 106.75675675675676,
|
| 568 |
+
"grad_norm": 0.5172644853591919,
|
| 569 |
+
"learning_rate": 0.0001,
|
| 570 |
+
"loss": 0.0413,
|
| 571 |
"step": 3950
|
| 572 |
},
|
| 573 |
{
|
| 574 |
+
"epoch": 108.10810810810811,
|
| 575 |
+
"grad_norm": 0.4363681674003601,
|
| 576 |
+
"learning_rate": 0.0001,
|
| 577 |
+
"loss": 0.0418,
|
| 578 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 579 |
}
|
| 580 |
],
|
| 581 |
"logging_steps": 50,
|
| 582 |
+
"max_steps": 37000,
|
| 583 |
"num_input_tokens_seen": 0,
|
| 584 |
+
"num_train_epochs": 1000,
|
| 585 |
"save_steps": 500,
|
| 586 |
"stateful_callbacks": {
|
| 587 |
"TrainerControl": {
|
|
|
|
| 595 |
"attributes": {}
|
| 596 |
}
|
| 597 |
},
|
| 598 |
+
"total_flos": 1.1227882820640702e+20,
|
| 599 |
"train_batch_size": 64,
|
| 600 |
"trial_name": null,
|
| 601 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:947b426ccbf2210bfedcbd5a6451184b0ef96e0b87c9ffe2057287fdde11bc1c
|
| 3 |
size 6264
|