Training in progress, step 44000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1b4eb62e0fcdc8d3a810aceb36afb64f22f1ea6d26a83aa96829502ed3bddd7
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3db83ad78622f7a5388f826ec38184d84eaea94ecb11d8534774dd1bc46ce45
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:752c23b16f0b286a12046bd803bd32f280dd78420031d337d9d0b8ad8d9c480b
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:419a73c41e3de0ebe2db15bfe3b49945cbd97c4de2356752fbadf096577c3d0b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3128,6 +3128,318 @@
|
|
| 3128 |
"eval_samples_per_second": 76.703,
|
| 3129 |
"eval_steps_per_second": 19.176,
|
| 3130 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 100,
|
|
@@ -3147,7 +3459,7 @@
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
-
"total_flos":
|
| 3151 |
"train_batch_size": 22,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.07272727272727272,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 44000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3128 |
"eval_samples_per_second": 76.703,
|
| 3129 |
"eval_steps_per_second": 19.176,
|
| 3130 |
"step": 40000
|
| 3131 |
+
},
|
| 3132 |
+
{
|
| 3133 |
+
"epoch": 0.03727272727272727,
|
| 3134 |
+
"grad_norm": 0.15226680040359497,
|
| 3135 |
+
"learning_rate": 0.0007076613888136895,
|
| 3136 |
+
"loss": 2.7523992919921874,
|
| 3137 |
+
"step": 40100
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 0.038181818181818185,
|
| 3141 |
+
"grad_norm": 0.16509854793548584,
|
| 3142 |
+
"learning_rate": 0.0007063597559645352,
|
| 3143 |
+
"loss": 2.7390933227539063,
|
| 3144 |
+
"step": 40200
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 0.03909090909090909,
|
| 3148 |
+
"grad_norm": 0.1810932159423828,
|
| 3149 |
+
"learning_rate": 0.0007050564353023619,
|
| 3150 |
+
"loss": 2.7575619506835936,
|
| 3151 |
+
"step": 40300
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.04,
|
| 3155 |
+
"grad_norm": 0.14917488396167755,
|
| 3156 |
+
"learning_rate": 0.0007037514374870077,
|
| 3157 |
+
"loss": 2.700941162109375,
|
| 3158 |
+
"step": 40400
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.04090909090909091,
|
| 3162 |
+
"grad_norm": 0.1438620686531067,
|
| 3163 |
+
"learning_rate": 0.0007024447731920284,
|
| 3164 |
+
"loss": 2.7219302368164064,
|
| 3165 |
+
"step": 40500
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 0.04181818181818182,
|
| 3169 |
+
"grad_norm": 0.1588471382856369,
|
| 3170 |
+
"learning_rate": 0.000701136453104609,
|
| 3171 |
+
"loss": 2.7354092407226562,
|
| 3172 |
+
"step": 40600
|
| 3173 |
+
},
|
| 3174 |
+
{
|
| 3175 |
+
"epoch": 0.042727272727272725,
|
| 3176 |
+
"grad_norm": 0.18232181668281555,
|
| 3177 |
+
"learning_rate": 0.0006998264879254782,
|
| 3178 |
+
"loss": 2.7257977294921876,
|
| 3179 |
+
"step": 40700
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 0.04363636363636364,
|
| 3183 |
+
"grad_norm": 0.15463081002235413,
|
| 3184 |
+
"learning_rate": 0.0006985148883688194,
|
| 3185 |
+
"loss": 2.7430325317382813,
|
| 3186 |
+
"step": 40800
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 0.04454545454545455,
|
| 3190 |
+
"grad_norm": 0.16292454302310944,
|
| 3191 |
+
"learning_rate": 0.0006972016651621834,
|
| 3192 |
+
"loss": 2.725971374511719,
|
| 3193 |
+
"step": 40900
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 0.045454545454545456,
|
| 3197 |
+
"grad_norm": 0.14817778766155243,
|
| 3198 |
+
"learning_rate": 0.0006958868290464014,
|
| 3199 |
+
"loss": 2.7598446655273436,
|
| 3200 |
+
"step": 41000
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.045454545454545456,
|
| 3204 |
+
"eval_loss": 3.1211743354797363,
|
| 3205 |
+
"eval_runtime": 7.424,
|
| 3206 |
+
"eval_samples_per_second": 77.586,
|
| 3207 |
+
"eval_steps_per_second": 19.396,
|
| 3208 |
+
"step": 41000
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.046363636363636364,
|
| 3212 |
+
"grad_norm": 0.1458057463169098,
|
| 3213 |
+
"learning_rate": 0.0006945703907754957,
|
| 3214 |
+
"loss": 2.7241558837890625,
|
| 3215 |
+
"step": 41100
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.04727272727272727,
|
| 3219 |
+
"grad_norm": 0.1644594669342041,
|
| 3220 |
+
"learning_rate": 0.0006932523611165934,
|
| 3221 |
+
"loss": 2.737247314453125,
|
| 3222 |
+
"step": 41200
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.04818181818181818,
|
| 3226 |
+
"grad_norm": 0.1583612859249115,
|
| 3227 |
+
"learning_rate": 0.000691932750849837,
|
| 3228 |
+
"loss": 2.7208633422851562,
|
| 3229 |
+
"step": 41300
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.04909090909090909,
|
| 3233 |
+
"grad_norm": 0.15082280337810516,
|
| 3234 |
+
"learning_rate": 0.000690611570768297,
|
| 3235 |
+
"loss": 2.7353948974609374,
|
| 3236 |
+
"step": 41400
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.05,
|
| 3240 |
+
"grad_norm": 0.16890287399291992,
|
| 3241 |
+
"learning_rate": 0.0006892888316778836,
|
| 3242 |
+
"loss": 2.7053826904296874,
|
| 3243 |
+
"step": 41500
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.05090909090909091,
|
| 3247 |
+
"grad_norm": 0.15229052305221558,
|
| 3248 |
+
"learning_rate": 0.0006879645443972575,
|
| 3249 |
+
"loss": 2.6989901733398436,
|
| 3250 |
+
"step": 41600
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.05181818181818182,
|
| 3254 |
+
"grad_norm": 0.15202166140079498,
|
| 3255 |
+
"learning_rate": 0.0006866387197577427,
|
| 3256 |
+
"loss": 2.7251095581054687,
|
| 3257 |
+
"step": 41700
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.05272727272727273,
|
| 3261 |
+
"grad_norm": 0.1463591307401657,
|
| 3262 |
+
"learning_rate": 0.0006853113686032368,
|
| 3263 |
+
"loss": 2.7278387451171877,
|
| 3264 |
+
"step": 41800
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.053636363636363635,
|
| 3268 |
+
"grad_norm": 0.14916226267814636,
|
| 3269 |
+
"learning_rate": 0.0006839825017901229,
|
| 3270 |
+
"loss": 2.71453369140625,
|
| 3271 |
+
"step": 41900
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.05454545454545454,
|
| 3275 |
+
"grad_norm": 0.15262916684150696,
|
| 3276 |
+
"learning_rate": 0.0006826521301871804,
|
| 3277 |
+
"loss": 2.712431640625,
|
| 3278 |
+
"step": 42000
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.05454545454545454,
|
| 3282 |
+
"eval_loss": 3.1164402961730957,
|
| 3283 |
+
"eval_runtime": 7.416,
|
| 3284 |
+
"eval_samples_per_second": 77.67,
|
| 3285 |
+
"eval_steps_per_second": 19.418,
|
| 3286 |
+
"step": 42000
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.05545454545454546,
|
| 3290 |
+
"grad_norm": 0.14367501437664032,
|
| 3291 |
+
"learning_rate": 0.0006813202646754969,
|
| 3292 |
+
"loss": 2.770457458496094,
|
| 3293 |
+
"step": 42100
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.056363636363636366,
|
| 3297 |
+
"grad_norm": 0.16685152053833008,
|
| 3298 |
+
"learning_rate": 0.000679986916148378,
|
| 3299 |
+
"loss": 2.7458120727539064,
|
| 3300 |
+
"step": 42200
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.057272727272727274,
|
| 3304 |
+
"grad_norm": 0.1416223794221878,
|
| 3305 |
+
"learning_rate": 0.0006786520955112592,
|
| 3306 |
+
"loss": 2.737471923828125,
|
| 3307 |
+
"step": 42300
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.05818181818181818,
|
| 3311 |
+
"grad_norm": 0.19099284708499908,
|
| 3312 |
+
"learning_rate": 0.0006773158136816167,
|
| 3313 |
+
"loss": 2.7410955810546875,
|
| 3314 |
+
"step": 42400
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.05909090909090909,
|
| 3318 |
+
"grad_norm": 0.14040355384349823,
|
| 3319 |
+
"learning_rate": 0.0006759780815888771,
|
| 3320 |
+
"loss": 2.7524224853515626,
|
| 3321 |
+
"step": 42500
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.06,
|
| 3325 |
+
"grad_norm": 0.14514034986495972,
|
| 3326 |
+
"learning_rate": 0.0006746389101743291,
|
| 3327 |
+
"loss": 2.7450900268554688,
|
| 3328 |
+
"step": 42600
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.060909090909090906,
|
| 3332 |
+
"grad_norm": 0.1578412503004074,
|
| 3333 |
+
"learning_rate": 0.0006732983103910333,
|
| 3334 |
+
"loss": 2.7615512084960936,
|
| 3335 |
+
"step": 42700
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.06181818181818182,
|
| 3339 |
+
"grad_norm": 0.18139956891536713,
|
| 3340 |
+
"learning_rate": 0.0006719562932037332,
|
| 3341 |
+
"loss": 2.709564514160156,
|
| 3342 |
+
"step": 42800
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.06272727272727273,
|
| 3346 |
+
"grad_norm": 0.15958115458488464,
|
| 3347 |
+
"learning_rate": 0.000670612869588765,
|
| 3348 |
+
"loss": 2.7086691284179687,
|
| 3349 |
+
"step": 42900
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.06363636363636363,
|
| 3353 |
+
"grad_norm": 0.18487316370010376,
|
| 3354 |
+
"learning_rate": 0.0006692680505339684,
|
| 3355 |
+
"loss": 2.7571722412109376,
|
| 3356 |
+
"step": 43000
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.06363636363636363,
|
| 3360 |
+
"eval_loss": 3.1164326667785645,
|
| 3361 |
+
"eval_runtime": 7.4455,
|
| 3362 |
+
"eval_samples_per_second": 77.362,
|
| 3363 |
+
"eval_steps_per_second": 19.34,
|
| 3364 |
+
"step": 43000
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 0.06454545454545454,
|
| 3368 |
+
"grad_norm": 0.14378763735294342,
|
| 3369 |
+
"learning_rate": 0.0006679218470385959,
|
| 3370 |
+
"loss": 2.713703308105469,
|
| 3371 |
+
"step": 43100
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 0.06545454545454546,
|
| 3375 |
+
"grad_norm": 0.14831411838531494,
|
| 3376 |
+
"learning_rate": 0.0006665742701132233,
|
| 3377 |
+
"loss": 2.7057376098632813,
|
| 3378 |
+
"step": 43200
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 0.06636363636363636,
|
| 3382 |
+
"grad_norm": 0.14014075696468353,
|
| 3383 |
+
"learning_rate": 0.0006652253307796605,
|
| 3384 |
+
"loss": 2.732189025878906,
|
| 3385 |
+
"step": 43300
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 0.06727272727272728,
|
| 3389 |
+
"grad_norm": 0.1462206244468689,
|
| 3390 |
+
"learning_rate": 0.0006638750400708597,
|
| 3391 |
+
"loss": 2.735457763671875,
|
| 3392 |
+
"step": 43400
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.06818181818181818,
|
| 3396 |
+
"grad_norm": 0.15208710730075836,
|
| 3397 |
+
"learning_rate": 0.0006625234090308261,
|
| 3398 |
+
"loss": 2.7204766845703126,
|
| 3399 |
+
"step": 43500
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 0.06909090909090909,
|
| 3403 |
+
"grad_norm": 0.17330685257911682,
|
| 3404 |
+
"learning_rate": 0.0006611704487145273,
|
| 3405 |
+
"loss": 2.7174346923828123,
|
| 3406 |
+
"step": 43600
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 0.07,
|
| 3410 |
+
"grad_norm": 0.14701761305332184,
|
| 3411 |
+
"learning_rate": 0.000659816170187804,
|
| 3412 |
+
"loss": 2.7171310424804687,
|
| 3413 |
+
"step": 43700
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 0.07090909090909091,
|
| 3417 |
+
"grad_norm": 0.15500852465629578,
|
| 3418 |
+
"learning_rate": 0.0006584605845272769,
|
| 3419 |
+
"loss": 2.7264663696289064,
|
| 3420 |
+
"step": 43800
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 0.07181818181818182,
|
| 3424 |
+
"grad_norm": 0.173856720328331,
|
| 3425 |
+
"learning_rate": 0.0006571037028202593,
|
| 3426 |
+
"loss": 2.7247988891601564,
|
| 3427 |
+
"step": 43900
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 0.07272727272727272,
|
| 3431 |
+
"grad_norm": 0.152163565158844,
|
| 3432 |
+
"learning_rate": 0.0006557455361646638,
|
| 3433 |
+
"loss": 2.7246688842773437,
|
| 3434 |
+
"step": 44000
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.07272727272727272,
|
| 3438 |
+
"eval_loss": 3.1064937114715576,
|
| 3439 |
+
"eval_runtime": 7.4422,
|
| 3440 |
+
"eval_samples_per_second": 77.396,
|
| 3441 |
+
"eval_steps_per_second": 19.349,
|
| 3442 |
+
"step": 44000
|
| 3443 |
}
|
| 3444 |
],
|
| 3445 |
"logging_steps": 100,
|
|
|
|
| 3459 |
"attributes": {}
|
| 3460 |
}
|
| 3461 |
},
|
| 3462 |
+
"total_flos": 1.096241563828224e+18,
|
| 3463 |
"train_batch_size": 22,
|
| 3464 |
"trial_name": null,
|
| 3465 |
"trial_params": null
|