Training in progress, step 110000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 586828837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66a5ef622dbe8d56e7b956a8e46b2dc79895c2e55948ea096cb19b5071a69a55
|
| 3 |
size 586828837
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4ef7a37dd78952cbb4fc37873637ea684f070d1e44bde74352b791d0c661cd4
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e483b397451e40991ea9aa448be1d4addf388b682e3c225fd31dfc476ba76800
|
| 3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42dbbdc5cc13bd878c323aa5fdc58a0d0d735dc686a8a6a2c1206cf27279185b
|
| 3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 733555848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:645860789a54b6c41f5c11e77f6f0318ed7d04c0720af434b0a590d8b30f84c0
|
| 3 |
size 733555848
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -3006,11 +3006,311 @@
|
|
| 3006 |
"learning_rate": 0.0027978817870494,
|
| 3007 |
"loss": 8.5906,
|
| 3008 |
"step": 100000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3009 |
}
|
| 3010 |
],
|
| 3011 |
"max_steps": 1000000,
|
| 3012 |
"num_train_epochs": 5,
|
| 3013 |
-
"total_flos": 1.
|
| 3014 |
"trial_name": null,
|
| 3015 |
"trial_params": null
|
| 3016 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.47269742637737583,
|
| 5 |
+
"global_step": 110000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 3006 |
"learning_rate": 0.0027978817870494,
|
| 3007 |
"loss": 8.5906,
|
| 3008 |
"step": 100000
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 0.43,
|
| 3012 |
+
"learning_rate": 0.0028065907522651585,
|
| 3013 |
+
"loss": 8.5938,
|
| 3014 |
+
"step": 100200
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 0.43,
|
| 3018 |
+
"learning_rate": 0.002815310216214826,
|
| 3019 |
+
"loss": 8.5887,
|
| 3020 |
+
"step": 100400
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.43,
|
| 3024 |
+
"learning_rate": 0.00282404014065031,
|
| 3025 |
+
"loss": 8.5922,
|
| 3026 |
+
"step": 100600
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.43,
|
| 3030 |
+
"learning_rate": 0.0028327804872776367,
|
| 3031 |
+
"loss": 8.5926,
|
| 3032 |
+
"step": 100800
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 0.43,
|
| 3036 |
+
"learning_rate": 0.002841531217757113,
|
| 3037 |
+
"loss": 8.5978,
|
| 3038 |
+
"step": 101000
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"epoch": 0.43,
|
| 3042 |
+
"learning_rate": 0.0028502922937035,
|
| 3043 |
+
"loss": 8.5984,
|
| 3044 |
+
"step": 101200
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.44,
|
| 3048 |
+
"learning_rate": 0.0028590636766861726,
|
| 3049 |
+
"loss": 8.6046,
|
| 3050 |
+
"step": 101400
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 0.44,
|
| 3054 |
+
"learning_rate": 0.0028678453282293013,
|
| 3055 |
+
"loss": 8.6093,
|
| 3056 |
+
"step": 101600
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 0.44,
|
| 3060 |
+
"learning_rate": 0.0028766372098120076,
|
| 3061 |
+
"loss": 8.6083,
|
| 3062 |
+
"step": 101800
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.44,
|
| 3066 |
+
"learning_rate": 0.0028854392828685377,
|
| 3067 |
+
"loss": 8.6057,
|
| 3068 |
+
"step": 102000
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.44,
|
| 3072 |
+
"learning_rate": 0.0028942515087884407,
|
| 3073 |
+
"loss": 8.6146,
|
| 3074 |
+
"step": 102200
|
| 3075 |
+
},
|
| 3076 |
+
{
|
| 3077 |
+
"epoch": 0.44,
|
| 3078 |
+
"learning_rate": 0.00290307384891672,
|
| 3079 |
+
"loss": 8.608,
|
| 3080 |
+
"step": 102400
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"epoch": 0.44,
|
| 3084 |
+
"learning_rate": 0.00291190626455402,
|
| 3085 |
+
"loss": 8.6081,
|
| 3086 |
+
"step": 102600
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 0.44,
|
| 3090 |
+
"learning_rate": 0.0029207044797924615,
|
| 3091 |
+
"loss": 8.6164,
|
| 3092 |
+
"step": 102800
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 0.44,
|
| 3096 |
+
"learning_rate": 0.0029295568802797795,
|
| 3097 |
+
"loss": 8.6008,
|
| 3098 |
+
"step": 103000
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 0.44,
|
| 3102 |
+
"learning_rate": 0.0029384192401078115,
|
| 3103 |
+
"loss": 8.6166,
|
| 3104 |
+
"step": 103200
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 0.44,
|
| 3108 |
+
"learning_rate": 0.00294729152040165,
|
| 3109 |
+
"loss": 8.5962,
|
| 3110 |
+
"step": 103400
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.45,
|
| 3114 |
+
"learning_rate": 0.002956173682242877,
|
| 3115 |
+
"loss": 8.6129,
|
| 3116 |
+
"step": 103600
|
| 3117 |
+
},
|
| 3118 |
+
{
|
| 3119 |
+
"epoch": 0.45,
|
| 3120 |
+
"learning_rate": 0.002965065686669722,
|
| 3121 |
+
"loss": 8.6092,
|
| 3122 |
+
"step": 103800
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 0.45,
|
| 3126 |
+
"learning_rate": 0.0029739674946772463,
|
| 3127 |
+
"loss": 8.6189,
|
| 3128 |
+
"step": 104000
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 0.45,
|
| 3132 |
+
"learning_rate": 0.002982879067217503,
|
| 3133 |
+
"loss": 8.612,
|
| 3134 |
+
"step": 104200
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 0.45,
|
| 3138 |
+
"learning_rate": 0.0029918003651997144,
|
| 3139 |
+
"loss": 8.6135,
|
| 3140 |
+
"step": 104400
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 0.45,
|
| 3144 |
+
"learning_rate": 0.003000731349490442,
|
| 3145 |
+
"loss": 8.6182,
|
| 3146 |
+
"step": 104600
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 0.45,
|
| 3150 |
+
"learning_rate": 0.0030096719809137584,
|
| 3151 |
+
"loss": 8.6423,
|
| 3152 |
+
"step": 104800
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.45,
|
| 3156 |
+
"learning_rate": 0.003018622220251419,
|
| 3157 |
+
"loss": 8.6145,
|
| 3158 |
+
"step": 105000
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.45,
|
| 3162 |
+
"learning_rate": 0.0030275372054660438,
|
| 3163 |
+
"loss": 8.6249,
|
| 3164 |
+
"step": 105200
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"epoch": 0.45,
|
| 3168 |
+
"learning_rate": 0.0030365064952603237,
|
| 3169 |
+
"loss": 8.6265,
|
| 3170 |
+
"step": 105400
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 0.45,
|
| 3174 |
+
"learning_rate": 0.0030454852752588536,
|
| 3175 |
+
"loss": 8.6304,
|
| 3176 |
+
"step": 105600
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 0.45,
|
| 3180 |
+
"learning_rate": 0.0030544735060760494,
|
| 3181 |
+
"loss": 8.6309,
|
| 3182 |
+
"step": 105800
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 0.46,
|
| 3186 |
+
"learning_rate": 0.0030634711482848704,
|
| 3187 |
+
"loss": 8.6258,
|
| 3188 |
+
"step": 106000
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 0.46,
|
| 3192 |
+
"learning_rate": 0.003072478162416994,
|
| 3193 |
+
"loss": 8.6328,
|
| 3194 |
+
"step": 106200
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.46,
|
| 3198 |
+
"learning_rate": 0.003081494508962985,
|
| 3199 |
+
"loss": 8.6298,
|
| 3200 |
+
"step": 106400
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.46,
|
| 3204 |
+
"learning_rate": 0.0030905201483724717,
|
| 3205 |
+
"loss": 8.639,
|
| 3206 |
+
"step": 106600
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"epoch": 0.46,
|
| 3210 |
+
"learning_rate": 0.0030995550410543226,
|
| 3211 |
+
"loss": 8.6212,
|
| 3212 |
+
"step": 106800
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 0.46,
|
| 3216 |
+
"learning_rate": 0.0031085991473768114,
|
| 3217 |
+
"loss": 8.6374,
|
| 3218 |
+
"step": 107000
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 0.46,
|
| 3222 |
+
"learning_rate": 0.003117652427667799,
|
| 3223 |
+
"loss": 8.6326,
|
| 3224 |
+
"step": 107200
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 0.46,
|
| 3228 |
+
"learning_rate": 0.0031267148422149046,
|
| 3229 |
+
"loss": 8.6291,
|
| 3230 |
+
"step": 107400
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 0.46,
|
| 3234 |
+
"learning_rate": 0.003135740971163656,
|
| 3235 |
+
"loss": 8.6375,
|
| 3236 |
+
"step": 107600
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.46,
|
| 3240 |
+
"learning_rate": 0.0031448214897512507,
|
| 3241 |
+
"loss": 8.6226,
|
| 3242 |
+
"step": 107800
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 0.46,
|
| 3246 |
+
"learning_rate": 0.003153911023417371,
|
| 3247 |
+
"loss": 8.6359,
|
| 3248 |
+
"step": 108000
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"epoch": 0.46,
|
| 3252 |
+
"learning_rate": 0.003163009532290608,
|
| 3253 |
+
"loss": 8.6491,
|
| 3254 |
+
"step": 108200
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 0.47,
|
| 3258 |
+
"learning_rate": 0.0031721169764601844,
|
| 3259 |
+
"loss": 8.6405,
|
| 3260 |
+
"step": 108400
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 0.47,
|
| 3264 |
+
"learning_rate": 0.0031812333159761293,
|
| 3265 |
+
"loss": 8.632,
|
| 3266 |
+
"step": 108600
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 0.47,
|
| 3270 |
+
"learning_rate": 0.003190358510849451,
|
| 3271 |
+
"loss": 8.6363,
|
| 3272 |
+
"step": 108800
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 0.47,
|
| 3276 |
+
"learning_rate": 0.0031994925210523124,
|
| 3277 |
+
"loss": 8.6316,
|
| 3278 |
+
"step": 109000
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.47,
|
| 3282 |
+
"learning_rate": 0.0032086353065182106,
|
| 3283 |
+
"loss": 8.6423,
|
| 3284 |
+
"step": 109200
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 0.47,
|
| 3288 |
+
"learning_rate": 0.003217786827142146,
|
| 3289 |
+
"loss": 8.6274,
|
| 3290 |
+
"step": 109400
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"epoch": 0.47,
|
| 3294 |
+
"learning_rate": 0.003226947042780804,
|
| 3295 |
+
"loss": 8.6366,
|
| 3296 |
+
"step": 109600
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 0.47,
|
| 3300 |
+
"learning_rate": 0.003236070047437989,
|
| 3301 |
+
"loss": 8.6388,
|
| 3302 |
+
"step": 109800
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 0.47,
|
| 3306 |
+
"learning_rate": 0.003245247489550804,
|
| 3307 |
+
"loss": 8.6364,
|
| 3308 |
+
"step": 110000
|
| 3309 |
}
|
| 3310 |
],
|
| 3311 |
"max_steps": 1000000,
|
| 3312 |
"num_train_epochs": 5,
|
| 3313 |
+
"total_flos": 1.7532129804288e+17,
|
| 3314 |
"trial_name": null,
|
| 3315 |
"trial_params": null
|
| 3316 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4ef7a37dd78952cbb4fc37873637ea684f070d1e44bde74352b791d0c661cd4
|
| 3 |
size 146774203
|