Training in progress, step 160000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +203 -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 202194449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce756be38c7d806962a75c4ecd24790cdff6367292efa2cdf7ed0fff4145bbe4
|
3 |
size 202194449
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
|
3 |
size 102501541
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
last-checkpoint/rng_state_6.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 sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
last-checkpoint/rng_state_7.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 sha256:0e3deb747f474d2d0563b125ac601cf8de26ef8f9fd17f727b1a014aa5e2d9d4
|
3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bc0c53c979a7805930dacd44e26c88894a437860c12a8b9fd2b0695ce7c583e
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -3006,11 +3006,211 @@
|
|
3006 |
"eval_samples_per_second": 725.588,
|
3007 |
"eval_steps_per_second": 11.609,
|
3008 |
"step": 150000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3009 |
}
|
3010 |
],
|
3011 |
"max_steps": 500000,
|
3012 |
"num_train_epochs": 13,
|
3013 |
-
"total_flos":
|
3014 |
"trial_name": null,
|
3015 |
"trial_params": null
|
3016 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.07767980019369,
|
5 |
+
"global_step": 160000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
3006 |
"eval_samples_per_second": 725.588,
|
3007 |
"eval_steps_per_second": 11.609,
|
3008 |
"step": 150000
|
3009 |
+
},
|
3010 |
+
{
|
3011 |
+
"epoch": 3.84,
|
3012 |
+
"learning_rate": 0.000252852507335803,
|
3013 |
+
"loss": 0.3008,
|
3014 |
+
"step": 150500
|
3015 |
+
},
|
3016 |
+
{
|
3017 |
+
"epoch": 3.85,
|
3018 |
+
"learning_rate": 0.0002524981166865307,
|
3019 |
+
"loss": 0.3014,
|
3020 |
+
"step": 151000
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 3.85,
|
3024 |
+
"eval_loss": 0.8369771242141724,
|
3025 |
+
"eval_runtime": 1.2701,
|
3026 |
+
"eval_samples_per_second": 787.344,
|
3027 |
+
"eval_steps_per_second": 12.598,
|
3028 |
+
"step": 151000
|
3029 |
+
},
|
3030 |
+
{
|
3031 |
+
"epoch": 3.86,
|
3032 |
+
"learning_rate": 0.00025214265981347487,
|
3033 |
+
"loss": 0.3007,
|
3034 |
+
"step": 151500
|
3035 |
+
},
|
3036 |
+
{
|
3037 |
+
"epoch": 3.87,
|
3038 |
+
"learning_rate": 0.000251786140603855,
|
3039 |
+
"loss": 0.3012,
|
3040 |
+
"step": 152000
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 3.87,
|
3044 |
+
"eval_loss": 0.8284549117088318,
|
3045 |
+
"eval_runtime": 1.3354,
|
3046 |
+
"eval_samples_per_second": 748.855,
|
3047 |
+
"eval_steps_per_second": 11.982,
|
3048 |
+
"step": 152000
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 3.89,
|
3052 |
+
"learning_rate": 0.00025142856295650795,
|
3053 |
+
"loss": 0.3026,
|
3054 |
+
"step": 152500
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 3.9,
|
3058 |
+
"learning_rate": 0.0002510699307818457,
|
3059 |
+
"loss": 0.3012,
|
3060 |
+
"step": 153000
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 3.9,
|
3064 |
+
"eval_loss": 0.8453160524368286,
|
3065 |
+
"eval_runtime": 1.3185,
|
3066 |
+
"eval_samples_per_second": 758.466,
|
3067 |
+
"eval_steps_per_second": 12.135,
|
3068 |
+
"step": 153000
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 3.91,
|
3072 |
+
"learning_rate": 0.00025071024800181214,
|
3073 |
+
"loss": 0.3009,
|
3074 |
+
"step": 153500
|
3075 |
+
},
|
3076 |
+
{
|
3077 |
+
"epoch": 3.92,
|
3078 |
+
"learning_rate": 0.0002503495185498405,
|
3079 |
+
"loss": 0.3007,
|
3080 |
+
"step": 154000
|
3081 |
+
},
|
3082 |
+
{
|
3083 |
+
"epoch": 3.92,
|
3084 |
+
"eval_loss": 0.8194591999053955,
|
3085 |
+
"eval_runtime": 1.3313,
|
3086 |
+
"eval_samples_per_second": 751.123,
|
3087 |
+
"eval_steps_per_second": 12.018,
|
3088 |
+
"step": 154000
|
3089 |
+
},
|
3090 |
+
{
|
3091 |
+
"epoch": 3.94,
|
3092 |
+
"learning_rate": 0.00024998774637081044,
|
3093 |
+
"loss": 0.3008,
|
3094 |
+
"step": 154500
|
3095 |
+
},
|
3096 |
+
{
|
3097 |
+
"epoch": 3.95,
|
3098 |
+
"learning_rate": 0.00024962493542100443,
|
3099 |
+
"loss": 0.3009,
|
3100 |
+
"step": 155000
|
3101 |
+
},
|
3102 |
+
{
|
3103 |
+
"epoch": 3.95,
|
3104 |
+
"eval_loss": 0.8309118747711182,
|
3105 |
+
"eval_runtime": 1.304,
|
3106 |
+
"eval_samples_per_second": 766.849,
|
3107 |
+
"eval_steps_per_second": 12.27,
|
3108 |
+
"step": 155000
|
3109 |
+
},
|
3110 |
+
{
|
3111 |
+
"epoch": 3.96,
|
3112 |
+
"learning_rate": 0.0002492610896680649,
|
3113 |
+
"loss": 0.3001,
|
3114 |
+
"step": 155500
|
3115 |
+
},
|
3116 |
+
{
|
3117 |
+
"epoch": 3.98,
|
3118 |
+
"learning_rate": 0.00024889621309095067,
|
3119 |
+
"loss": 0.3007,
|
3120 |
+
"step": 156000
|
3121 |
+
},
|
3122 |
+
{
|
3123 |
+
"epoch": 3.98,
|
3124 |
+
"eval_loss": 0.8357002139091492,
|
3125 |
+
"eval_runtime": 1.337,
|
3126 |
+
"eval_samples_per_second": 747.964,
|
3127 |
+
"eval_steps_per_second": 11.967,
|
3128 |
+
"step": 156000
|
3129 |
+
},
|
3130 |
+
{
|
3131 |
+
"epoch": 3.99,
|
3132 |
+
"learning_rate": 0.00024853030967989366,
|
3133 |
+
"loss": 0.3005,
|
3134 |
+
"step": 156500
|
3135 |
+
},
|
3136 |
+
{
|
3137 |
+
"epoch": 4.0,
|
3138 |
+
"learning_rate": 0.00024816338343635485,
|
3139 |
+
"loss": 0.3003,
|
3140 |
+
"step": 157000
|
3141 |
+
},
|
3142 |
+
{
|
3143 |
+
"epoch": 4.0,
|
3144 |
+
"eval_loss": 0.8225012421607971,
|
3145 |
+
"eval_runtime": 1.2983,
|
3146 |
+
"eval_samples_per_second": 770.222,
|
3147 |
+
"eval_steps_per_second": 12.324,
|
3148 |
+
"step": 157000
|
3149 |
+
},
|
3150 |
+
{
|
3151 |
+
"epoch": 4.01,
|
3152 |
+
"learning_rate": 0.0002477954383729809,
|
3153 |
+
"loss": 0.2997,
|
3154 |
+
"step": 157500
|
3155 |
+
},
|
3156 |
+
{
|
3157 |
+
"epoch": 4.03,
|
3158 |
+
"learning_rate": 0.00024742647851355997,
|
3159 |
+
"loss": 0.3014,
|
3160 |
+
"step": 158000
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 4.03,
|
3164 |
+
"eval_loss": 0.8343092203140259,
|
3165 |
+
"eval_runtime": 1.2683,
|
3166 |
+
"eval_samples_per_second": 788.447,
|
3167 |
+
"eval_steps_per_second": 12.615,
|
3168 |
+
"step": 158000
|
3169 |
+
},
|
3170 |
+
{
|
3171 |
+
"epoch": 4.04,
|
3172 |
+
"learning_rate": 0.0002470565078929781,
|
3173 |
+
"loss": 0.3001,
|
3174 |
+
"step": 158500
|
3175 |
+
},
|
3176 |
+
{
|
3177 |
+
"epoch": 4.05,
|
3178 |
+
"learning_rate": 0.00024668553055717465,
|
3179 |
+
"loss": 0.3005,
|
3180 |
+
"step": 159000
|
3181 |
+
},
|
3182 |
+
{
|
3183 |
+
"epoch": 4.05,
|
3184 |
+
"eval_loss": 0.8266953229904175,
|
3185 |
+
"eval_runtime": 1.3214,
|
3186 |
+
"eval_samples_per_second": 756.765,
|
3187 |
+
"eval_steps_per_second": 12.108,
|
3188 |
+
"step": 159000
|
3189 |
+
},
|
3190 |
+
{
|
3191 |
+
"epoch": 4.06,
|
3192 |
+
"learning_rate": 0.0002463135505630984,
|
3193 |
+
"loss": 0.299,
|
3194 |
+
"step": 159500
|
3195 |
+
},
|
3196 |
+
{
|
3197 |
+
"epoch": 4.08,
|
3198 |
+
"learning_rate": 0.00024594057197866283,
|
3199 |
+
"loss": 0.2994,
|
3200 |
+
"step": 160000
|
3201 |
+
},
|
3202 |
+
{
|
3203 |
+
"epoch": 4.08,
|
3204 |
+
"eval_loss": 0.8257858157157898,
|
3205 |
+
"eval_runtime": 1.2672,
|
3206 |
+
"eval_samples_per_second": 789.172,
|
3207 |
+
"eval_steps_per_second": 12.627,
|
3208 |
+
"step": 160000
|
3209 |
}
|
3210 |
],
|
3211 |
"max_steps": 500000,
|
3212 |
"num_train_epochs": 13,
|
3213 |
+
"total_flos": 5.11174030473982e+21,
|
3214 |
"trial_name": null,
|
3215 |
"trial_params": null
|
3216 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102501541
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac08afb5aa40873b91a011a4ac3e7ff40a672e324d1988d9844c7b8fb857f575
|
3 |
size 102501541
|