Training in progress, step 24000, 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 1520630616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a5e5a99de9ebd5a605eb747b364712a2371d3faff976fb42a4e2c4eff124586
|
| 3 |
size 1520630616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3041448587
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b90f9e040c4d2727932a8fb5449e7e222d2b34c261ceee7f00e20f78d73acb5
|
| 3 |
size 3041448587
|
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:cf31faff1a59206513a6140313f60a81b0b7bbfaceaf131da05eee348e2a75b6
|
| 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:a5b896146d5d8a1fece26c83d1cdd06bac435f33fada598258a6302b90095e53
|
| 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": 6.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3088,6 +3088,286 @@
|
|
| 3088 |
"learning_rate": 0.00026558709954008095,
|
| 3089 |
"loss": 1.566,
|
| 3090 |
"step": 22000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3091 |
}
|
| 3092 |
],
|
| 3093 |
"logging_steps": 50,
|
|
@@ -3107,7 +3387,7 @@
|
|
| 3107 |
"attributes": {}
|
| 3108 |
}
|
| 3109 |
},
|
| 3110 |
-
"total_flos": 1.
|
| 3111 |
"train_batch_size": 16,
|
| 3112 |
"trial_name": null,
|
| 3113 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.036524590163935,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 24000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3088 |
"learning_rate": 0.00026558709954008095,
|
| 3089 |
"loss": 1.566,
|
| 3090 |
"step": 22000
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 6.015213114754098,
|
| 3094 |
+
"grad_norm": 0.62890625,
|
| 3095 |
+
"learning_rate": 0.00026541837871893367,
|
| 3096 |
+
"loss": 1.5595,
|
| 3097 |
+
"step": 22050
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 6.01575956284153,
|
| 3101 |
+
"grad_norm": 0.5625,
|
| 3102 |
+
"learning_rate": 0.0002652492991748029,
|
| 3103 |
+
"loss": 1.5206,
|
| 3104 |
+
"step": 22100
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 6.016306010928962,
|
| 3108 |
+
"grad_norm": 0.640625,
|
| 3109 |
+
"learning_rate": 0.00026507986143319164,
|
| 3110 |
+
"loss": 1.5374,
|
| 3111 |
+
"step": 22150
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 6.016852459016394,
|
| 3115 |
+
"grad_norm": 0.703125,
|
| 3116 |
+
"learning_rate": 0.0002649100660207164,
|
| 3117 |
+
"loss": 1.522,
|
| 3118 |
+
"step": 22200
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 6.017398907103825,
|
| 3122 |
+
"grad_norm": 0.65625,
|
| 3123 |
+
"learning_rate": 0.0002647399134651053,
|
| 3124 |
+
"loss": 1.5532,
|
| 3125 |
+
"step": 22250
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 6.017945355191257,
|
| 3129 |
+
"grad_norm": 0.63671875,
|
| 3130 |
+
"learning_rate": 0.0002645694042951963,
|
| 3131 |
+
"loss": 1.5274,
|
| 3132 |
+
"step": 22300
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 6.018491803278689,
|
| 3136 |
+
"grad_norm": 0.65625,
|
| 3137 |
+
"learning_rate": 0.00026439853904093586,
|
| 3138 |
+
"loss": 1.517,
|
| 3139 |
+
"step": 22350
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 6.01903825136612,
|
| 3143 |
+
"grad_norm": 0.6875,
|
| 3144 |
+
"learning_rate": 0.00026422731823337717,
|
| 3145 |
+
"loss": 1.5197,
|
| 3146 |
+
"step": 22400
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 6.019584699453552,
|
| 3150 |
+
"grad_norm": 0.59765625,
|
| 3151 |
+
"learning_rate": 0.0002640557424046784,
|
| 3152 |
+
"loss": 1.5081,
|
| 3153 |
+
"step": 22450
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 6.020131147540984,
|
| 3157 |
+
"grad_norm": 0.65234375,
|
| 3158 |
+
"learning_rate": 0.0002638838120881012,
|
| 3159 |
+
"loss": 1.5526,
|
| 3160 |
+
"step": 22500
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 6.020677595628415,
|
| 3164 |
+
"grad_norm": 0.62109375,
|
| 3165 |
+
"learning_rate": 0.000263711527818009,
|
| 3166 |
+
"loss": 1.534,
|
| 3167 |
+
"step": 22550
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 6.021224043715847,
|
| 3171 |
+
"grad_norm": 0.60546875,
|
| 3172 |
+
"learning_rate": 0.0002635388901298652,
|
| 3173 |
+
"loss": 1.5156,
|
| 3174 |
+
"step": 22600
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 6.021770491803279,
|
| 3178 |
+
"grad_norm": 0.71875,
|
| 3179 |
+
"learning_rate": 0.0002633658995602318,
|
| 3180 |
+
"loss": 1.5402,
|
| 3181 |
+
"step": 22650
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 6.02231693989071,
|
| 3185 |
+
"grad_norm": 0.68359375,
|
| 3186 |
+
"learning_rate": 0.0002631925566467674,
|
| 3187 |
+
"loss": 1.5367,
|
| 3188 |
+
"step": 22700
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 6.022863387978142,
|
| 3192 |
+
"grad_norm": 0.62890625,
|
| 3193 |
+
"learning_rate": 0.00026301886192822585,
|
| 3194 |
+
"loss": 1.5126,
|
| 3195 |
+
"step": 22750
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 6.023409836065574,
|
| 3199 |
+
"grad_norm": 0.625,
|
| 3200 |
+
"learning_rate": 0.00026284481594445434,
|
| 3201 |
+
"loss": 1.5097,
|
| 3202 |
+
"step": 22800
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 6.023956284153005,
|
| 3206 |
+
"grad_norm": 0.60546875,
|
| 3207 |
+
"learning_rate": 0.00026267041923639175,
|
| 3208 |
+
"loss": 1.5058,
|
| 3209 |
+
"step": 22850
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 6.024502732240437,
|
| 3213 |
+
"grad_norm": 0.703125,
|
| 3214 |
+
"learning_rate": 0.00026249567234606707,
|
| 3215 |
+
"loss": 1.5004,
|
| 3216 |
+
"step": 22900
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 6.025049180327869,
|
| 3220 |
+
"grad_norm": 0.60546875,
|
| 3221 |
+
"learning_rate": 0.00026232057581659777,
|
| 3222 |
+
"loss": 1.4884,
|
| 3223 |
+
"step": 22950
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 6.0255956284153,
|
| 3227 |
+
"grad_norm": 0.65234375,
|
| 3228 |
+
"learning_rate": 0.0002621451301921878,
|
| 3229 |
+
"loss": 1.5884,
|
| 3230 |
+
"step": 23000
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 6.026142076502732,
|
| 3234 |
+
"grad_norm": 0.6484375,
|
| 3235 |
+
"learning_rate": 0.00026196933601812616,
|
| 3236 |
+
"loss": 1.565,
|
| 3237 |
+
"step": 23050
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 6.026688524590164,
|
| 3241 |
+
"grad_norm": 0.69140625,
|
| 3242 |
+
"learning_rate": 0.00026179319384078535,
|
| 3243 |
+
"loss": 1.5399,
|
| 3244 |
+
"step": 23100
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 6.027234972677595,
|
| 3248 |
+
"grad_norm": 0.57421875,
|
| 3249 |
+
"learning_rate": 0.0002616167042076192,
|
| 3250 |
+
"loss": 1.5319,
|
| 3251 |
+
"step": 23150
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 6.027781420765027,
|
| 3255 |
+
"grad_norm": 0.62890625,
|
| 3256 |
+
"learning_rate": 0.0002614398676671616,
|
| 3257 |
+
"loss": 1.5379,
|
| 3258 |
+
"step": 23200
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 6.028327868852459,
|
| 3262 |
+
"grad_norm": 0.69921875,
|
| 3263 |
+
"learning_rate": 0.0002612626847690247,
|
| 3264 |
+
"loss": 1.5344,
|
| 3265 |
+
"step": 23250
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 6.02887431693989,
|
| 3269 |
+
"grad_norm": 0.59765625,
|
| 3270 |
+
"learning_rate": 0.0002610851560638968,
|
| 3271 |
+
"loss": 1.5054,
|
| 3272 |
+
"step": 23300
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 6.029420765027322,
|
| 3276 |
+
"grad_norm": 0.6484375,
|
| 3277 |
+
"learning_rate": 0.0002609072821035415,
|
| 3278 |
+
"loss": 1.5421,
|
| 3279 |
+
"step": 23350
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 6.029967213114754,
|
| 3283 |
+
"grad_norm": 0.69921875,
|
| 3284 |
+
"learning_rate": 0.00026072906344079484,
|
| 3285 |
+
"loss": 1.5625,
|
| 3286 |
+
"step": 23400
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 6.0305136612021855,
|
| 3290 |
+
"grad_norm": 0.59765625,
|
| 3291 |
+
"learning_rate": 0.0002605505006295648,
|
| 3292 |
+
"loss": 1.5476,
|
| 3293 |
+
"step": 23450
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 6.031060109289617,
|
| 3297 |
+
"grad_norm": 0.609375,
|
| 3298 |
+
"learning_rate": 0.00026037159422482865,
|
| 3299 |
+
"loss": 1.537,
|
| 3300 |
+
"step": 23500
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 6.031606557377049,
|
| 3304 |
+
"grad_norm": 0.60546875,
|
| 3305 |
+
"learning_rate": 0.00026019234478263155,
|
| 3306 |
+
"loss": 1.5204,
|
| 3307 |
+
"step": 23550
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 6.0321530054644805,
|
| 3311 |
+
"grad_norm": 0.69921875,
|
| 3312 |
+
"learning_rate": 0.000260012752860085,
|
| 3313 |
+
"loss": 1.5479,
|
| 3314 |
+
"step": 23600
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 6.0326994535519125,
|
| 3318 |
+
"grad_norm": 0.6171875,
|
| 3319 |
+
"learning_rate": 0.00025983281901536474,
|
| 3320 |
+
"loss": 1.5304,
|
| 3321 |
+
"step": 23650
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 6.0332459016393445,
|
| 3325 |
+
"grad_norm": 0.6171875,
|
| 3326 |
+
"learning_rate": 0.00025965254380770945,
|
| 3327 |
+
"loss": 1.5738,
|
| 3328 |
+
"step": 23700
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 6.033792349726776,
|
| 3332 |
+
"grad_norm": 0.62109375,
|
| 3333 |
+
"learning_rate": 0.0002594719277974185,
|
| 3334 |
+
"loss": 1.5168,
|
| 3335 |
+
"step": 23750
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 6.034338797814208,
|
| 3339 |
+
"grad_norm": 0.6328125,
|
| 3340 |
+
"learning_rate": 0.0002592909715458506,
|
| 3341 |
+
"loss": 1.4984,
|
| 3342 |
+
"step": 23800
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 6.0348852459016395,
|
| 3346 |
+
"grad_norm": 0.57421875,
|
| 3347 |
+
"learning_rate": 0.0002591096756154221,
|
| 3348 |
+
"loss": 1.5721,
|
| 3349 |
+
"step": 23850
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 6.035431693989071,
|
| 3353 |
+
"grad_norm": 0.6015625,
|
| 3354 |
+
"learning_rate": 0.0002589280405696048,
|
| 3355 |
+
"loss": 1.5369,
|
| 3356 |
+
"step": 23900
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 6.035978142076503,
|
| 3360 |
+
"grad_norm": 0.61328125,
|
| 3361 |
+
"learning_rate": 0.00025874606697292473,
|
| 3362 |
+
"loss": 1.5236,
|
| 3363 |
+
"step": 23950
|
| 3364 |
+
},
|
| 3365 |
+
{
|
| 3366 |
+
"epoch": 6.036524590163935,
|
| 3367 |
+
"grad_norm": 0.6953125,
|
| 3368 |
+
"learning_rate": 0.00025856375539095986,
|
| 3369 |
+
"loss": 1.577,
|
| 3370 |
+
"step": 24000
|
| 3371 |
}
|
| 3372 |
],
|
| 3373 |
"logging_steps": 50,
|
|
|
|
| 3387 |
"attributes": {}
|
| 3388 |
}
|
| 3389 |
},
|
| 3390 |
+
"total_flos": 1.2834709186604433e+19,
|
| 3391 |
"train_batch_size": 16,
|
| 3392 |
"trial_name": null,
|
| 3393 |
"trial_params": null
|