Training in progress, step 5000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:065b0553ba7b625058bbc54e3b3e27c491e8ccc08fd588730cb0ecf41b13d909
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c15daf481efa3729e5a025f1cd3f5b2786cecfaaa7fdaaaf1ae1c82d0daee5
|
| 3 |
size 10707706
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c099333e451994d42ef6a1a4186a67f46e72967ddbe49de900a735186c809291
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd435f2d2df02dd69f00b4ffef1b8f08ed9d2c925d3492fd0d5a1484e32202ff
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3067,13 +3067,353 @@
|
|
| 3067 |
"eval_samples_per_second": 91.356,
|
| 3068 |
"eval_steps_per_second": 11.468,
|
| 3069 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3070 |
}
|
| 3071 |
],
|
| 3072 |
"logging_steps": 10,
|
| 3073 |
"max_steps": 6130,
|
| 3074 |
"num_train_epochs": 10,
|
| 3075 |
"save_steps": 500,
|
| 3076 |
-
"total_flos":
|
| 3077 |
"trial_name": null,
|
| 3078 |
"trial_params": null
|
| 3079 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4176868200302124,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-5000",
|
| 4 |
+
"epoch": 8.156606851549755,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3067 |
"eval_samples_per_second": 91.356,
|
| 3068 |
"eval_steps_per_second": 11.468,
|
| 3069 |
"step": 4500
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 7.36,
|
| 3073 |
+
"learning_rate": 0.0002877442273534636,
|
| 3074 |
+
"loss": 0.4006,
|
| 3075 |
+
"step": 4510
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 7.37,
|
| 3079 |
+
"learning_rate": 0.00028596802841918297,
|
| 3080 |
+
"loss": 0.4024,
|
| 3081 |
+
"step": 4520
|
| 3082 |
+
},
|
| 3083 |
+
{
|
| 3084 |
+
"epoch": 7.39,
|
| 3085 |
+
"learning_rate": 0.0002841918294849023,
|
| 3086 |
+
"loss": 0.3959,
|
| 3087 |
+
"step": 4530
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"epoch": 7.41,
|
| 3091 |
+
"learning_rate": 0.0002824156305506217,
|
| 3092 |
+
"loss": 0.3917,
|
| 3093 |
+
"step": 4540
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 7.42,
|
| 3097 |
+
"learning_rate": 0.00028063943161634104,
|
| 3098 |
+
"loss": 0.3994,
|
| 3099 |
+
"step": 4550
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 7.44,
|
| 3103 |
+
"learning_rate": 0.0002788632326820604,
|
| 3104 |
+
"loss": 0.4246,
|
| 3105 |
+
"step": 4560
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 7.46,
|
| 3109 |
+
"learning_rate": 0.00027708703374777977,
|
| 3110 |
+
"loss": 0.3905,
|
| 3111 |
+
"step": 4570
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 7.47,
|
| 3115 |
+
"learning_rate": 0.0002753108348134991,
|
| 3116 |
+
"loss": 0.4076,
|
| 3117 |
+
"step": 4580
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 7.49,
|
| 3121 |
+
"learning_rate": 0.00027353463587921845,
|
| 3122 |
+
"loss": 0.3924,
|
| 3123 |
+
"step": 4590
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 7.5,
|
| 3127 |
+
"learning_rate": 0.00027175843694493784,
|
| 3128 |
+
"loss": 0.3863,
|
| 3129 |
+
"step": 4600
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"epoch": 7.5,
|
| 3133 |
+
"eval_loss": 0.4166851341724396,
|
| 3134 |
+
"eval_runtime": 12.731,
|
| 3135 |
+
"eval_samples_per_second": 91.98,
|
| 3136 |
+
"eval_steps_per_second": 11.547,
|
| 3137 |
+
"step": 4600
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 7.52,
|
| 3141 |
+
"learning_rate": 0.0002699822380106572,
|
| 3142 |
+
"loss": 0.3949,
|
| 3143 |
+
"step": 4610
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"epoch": 7.54,
|
| 3147 |
+
"learning_rate": 0.0002682060390763766,
|
| 3148 |
+
"loss": 0.3966,
|
| 3149 |
+
"step": 4620
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 7.55,
|
| 3153 |
+
"learning_rate": 0.0002664298401420959,
|
| 3154 |
+
"loss": 0.3899,
|
| 3155 |
+
"step": 4630
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 7.57,
|
| 3159 |
+
"learning_rate": 0.00026465364120781525,
|
| 3160 |
+
"loss": 0.41,
|
| 3161 |
+
"step": 4640
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 7.59,
|
| 3165 |
+
"learning_rate": 0.00026287744227353465,
|
| 3166 |
+
"loss": 0.3993,
|
| 3167 |
+
"step": 4650
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 7.6,
|
| 3171 |
+
"learning_rate": 0.000261101243339254,
|
| 3172 |
+
"loss": 0.4216,
|
| 3173 |
+
"step": 4660
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 7.62,
|
| 3177 |
+
"learning_rate": 0.0002593250444049733,
|
| 3178 |
+
"loss": 0.4144,
|
| 3179 |
+
"step": 4670
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 7.63,
|
| 3183 |
+
"learning_rate": 0.0002575488454706927,
|
| 3184 |
+
"loss": 0.4117,
|
| 3185 |
+
"step": 4680
|
| 3186 |
+
},
|
| 3187 |
+
{
|
| 3188 |
+
"epoch": 7.65,
|
| 3189 |
+
"learning_rate": 0.00025577264653641206,
|
| 3190 |
+
"loss": 0.4288,
|
| 3191 |
+
"step": 4690
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 7.67,
|
| 3195 |
+
"learning_rate": 0.0002539964476021314,
|
| 3196 |
+
"loss": 0.3837,
|
| 3197 |
+
"step": 4700
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 7.67,
|
| 3201 |
+
"eval_loss": 0.4177791476249695,
|
| 3202 |
+
"eval_runtime": 12.7781,
|
| 3203 |
+
"eval_samples_per_second": 91.642,
|
| 3204 |
+
"eval_steps_per_second": 11.504,
|
| 3205 |
+
"step": 4700
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 7.68,
|
| 3209 |
+
"learning_rate": 0.0002522202486678508,
|
| 3210 |
+
"loss": 0.3894,
|
| 3211 |
+
"step": 4710
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 7.7,
|
| 3215 |
+
"learning_rate": 0.00025044404973357013,
|
| 3216 |
+
"loss": 0.4109,
|
| 3217 |
+
"step": 4720
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 7.72,
|
| 3221 |
+
"learning_rate": 0.0002486678507992895,
|
| 3222 |
+
"loss": 0.4211,
|
| 3223 |
+
"step": 4730
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 7.73,
|
| 3227 |
+
"learning_rate": 0.0002468916518650089,
|
| 3228 |
+
"loss": 0.3984,
|
| 3229 |
+
"step": 4740
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 7.75,
|
| 3233 |
+
"learning_rate": 0.00024511545293072826,
|
| 3234 |
+
"loss": 0.3988,
|
| 3235 |
+
"step": 4750
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 7.77,
|
| 3239 |
+
"learning_rate": 0.0002433392539964476,
|
| 3240 |
+
"loss": 0.4185,
|
| 3241 |
+
"step": 4760
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"epoch": 7.78,
|
| 3245 |
+
"learning_rate": 0.00024156305506216696,
|
| 3246 |
+
"loss": 0.3986,
|
| 3247 |
+
"step": 4770
|
| 3248 |
+
},
|
| 3249 |
+
{
|
| 3250 |
+
"epoch": 7.8,
|
| 3251 |
+
"learning_rate": 0.00023978685612788633,
|
| 3252 |
+
"loss": 0.4035,
|
| 3253 |
+
"step": 4780
|
| 3254 |
+
},
|
| 3255 |
+
{
|
| 3256 |
+
"epoch": 7.81,
|
| 3257 |
+
"learning_rate": 0.00023801065719360567,
|
| 3258 |
+
"loss": 0.4028,
|
| 3259 |
+
"step": 4790
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 7.83,
|
| 3263 |
+
"learning_rate": 0.00023623445825932503,
|
| 3264 |
+
"loss": 0.3998,
|
| 3265 |
+
"step": 4800
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 7.83,
|
| 3269 |
+
"eval_loss": 0.42066851258277893,
|
| 3270 |
+
"eval_runtime": 12.801,
|
| 3271 |
+
"eval_samples_per_second": 91.477,
|
| 3272 |
+
"eval_steps_per_second": 11.483,
|
| 3273 |
+
"step": 4800
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 7.85,
|
| 3277 |
+
"learning_rate": 0.00023445825932504443,
|
| 3278 |
+
"loss": 0.4137,
|
| 3279 |
+
"step": 4810
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 7.86,
|
| 3283 |
+
"learning_rate": 0.0002326820603907638,
|
| 3284 |
+
"loss": 0.3972,
|
| 3285 |
+
"step": 4820
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 7.88,
|
| 3289 |
+
"learning_rate": 0.00023090586145648313,
|
| 3290 |
+
"loss": 0.4158,
|
| 3291 |
+
"step": 4830
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 7.9,
|
| 3295 |
+
"learning_rate": 0.0002291296625222025,
|
| 3296 |
+
"loss": 0.3972,
|
| 3297 |
+
"step": 4840
|
| 3298 |
+
},
|
| 3299 |
+
{
|
| 3300 |
+
"epoch": 7.91,
|
| 3301 |
+
"learning_rate": 0.00022735346358792187,
|
| 3302 |
+
"loss": 0.4246,
|
| 3303 |
+
"step": 4850
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 7.93,
|
| 3307 |
+
"learning_rate": 0.0002255772646536412,
|
| 3308 |
+
"loss": 0.3866,
|
| 3309 |
+
"step": 4860
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 7.94,
|
| 3313 |
+
"learning_rate": 0.00022380106571936057,
|
| 3314 |
+
"loss": 0.4359,
|
| 3315 |
+
"step": 4870
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 7.96,
|
| 3319 |
+
"learning_rate": 0.00022202486678507994,
|
| 3320 |
+
"loss": 0.386,
|
| 3321 |
+
"step": 4880
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 7.98,
|
| 3325 |
+
"learning_rate": 0.0002202486678507993,
|
| 3326 |
+
"loss": 0.38,
|
| 3327 |
+
"step": 4890
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 7.99,
|
| 3331 |
+
"learning_rate": 0.00021847246891651864,
|
| 3332 |
+
"loss": 0.3936,
|
| 3333 |
+
"step": 4900
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 7.99,
|
| 3337 |
+
"eval_loss": 0.41456684470176697,
|
| 3338 |
+
"eval_runtime": 12.7936,
|
| 3339 |
+
"eval_samples_per_second": 91.53,
|
| 3340 |
+
"eval_steps_per_second": 11.49,
|
| 3341 |
+
"step": 4900
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 8.01,
|
| 3345 |
+
"learning_rate": 0.000216696269982238,
|
| 3346 |
+
"loss": 0.3634,
|
| 3347 |
+
"step": 4910
|
| 3348 |
+
},
|
| 3349 |
+
{
|
| 3350 |
+
"epoch": 8.03,
|
| 3351 |
+
"learning_rate": 0.00021492007104795738,
|
| 3352 |
+
"loss": 0.3883,
|
| 3353 |
+
"step": 4920
|
| 3354 |
+
},
|
| 3355 |
+
{
|
| 3356 |
+
"epoch": 8.04,
|
| 3357 |
+
"learning_rate": 0.00021314387211367671,
|
| 3358 |
+
"loss": 0.3864,
|
| 3359 |
+
"step": 4930
|
| 3360 |
+
},
|
| 3361 |
+
{
|
| 3362 |
+
"epoch": 8.06,
|
| 3363 |
+
"learning_rate": 0.00021136767317939608,
|
| 3364 |
+
"loss": 0.3848,
|
| 3365 |
+
"step": 4940
|
| 3366 |
+
},
|
| 3367 |
+
{
|
| 3368 |
+
"epoch": 8.08,
|
| 3369 |
+
"learning_rate": 0.00020959147424511545,
|
| 3370 |
+
"loss": 0.4164,
|
| 3371 |
+
"step": 4950
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 8.09,
|
| 3375 |
+
"learning_rate": 0.00020781527531083484,
|
| 3376 |
+
"loss": 0.3963,
|
| 3377 |
+
"step": 4960
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 8.11,
|
| 3381 |
+
"learning_rate": 0.00020603907637655418,
|
| 3382 |
+
"loss": 0.3873,
|
| 3383 |
+
"step": 4970
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 8.12,
|
| 3387 |
+
"learning_rate": 0.00020426287744227355,
|
| 3388 |
+
"loss": 0.4306,
|
| 3389 |
+
"step": 4980
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 8.14,
|
| 3393 |
+
"learning_rate": 0.0002024866785079929,
|
| 3394 |
+
"loss": 0.3966,
|
| 3395 |
+
"step": 4990
|
| 3396 |
+
},
|
| 3397 |
+
{
|
| 3398 |
+
"epoch": 8.16,
|
| 3399 |
+
"learning_rate": 0.00020071047957371228,
|
| 3400 |
+
"loss": 0.3672,
|
| 3401 |
+
"step": 5000
|
| 3402 |
+
},
|
| 3403 |
+
{
|
| 3404 |
+
"epoch": 8.16,
|
| 3405 |
+
"eval_loss": 0.4176868200302124,
|
| 3406 |
+
"eval_runtime": 12.7243,
|
| 3407 |
+
"eval_samples_per_second": 92.029,
|
| 3408 |
+
"eval_steps_per_second": 11.553,
|
| 3409 |
+
"step": 5000
|
| 3410 |
}
|
| 3411 |
],
|
| 3412 |
"logging_steps": 10,
|
| 3413 |
"max_steps": 6130,
|
| 3414 |
"num_train_epochs": 10,
|
| 3415 |
"save_steps": 500,
|
| 3416 |
+
"total_flos": 9451155609649152.0,
|
| 3417 |
"trial_name": null,
|
| 3418 |
"trial_params": null
|
| 3419 |
}
|