Training in progress, epoch 12, 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 1324830880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60893f4cdc0b30f89628ba26be3de4b9ff61f3b288b3df5b7bf767994c07ffbe
|
| 3 |
size 1324830880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2649896094
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35408bce52f844276bfb288ef878bcbd54835b7a3cd89bb1099d0e9bebcb0abf
|
| 3 |
size 2649896094
|
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:a9e215d94afa9052fd4cd1ce4d6bff3d47a71e2ce7b809d11eadf4e229c02a89
|
| 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 sha256:9fa10ba488cbe25804fc05e33ca16a3cd8767a31a1ea72f1a8883c9c4b81e7f8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.30803602933883667,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-258",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3097,6 +3097,624 @@
|
|
| 3097 |
"eval_samples_per_second": 61.478,
|
| 3098 |
"eval_steps_per_second": 15.369,
|
| 3099 |
"step": 430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3100 |
}
|
| 3101 |
],
|
| 3102 |
"logging_steps": 1,
|
|
@@ -3116,7 +3734,7 @@
|
|
| 3116 |
"attributes": {}
|
| 3117 |
}
|
| 3118 |
},
|
| 3119 |
-
"total_flos": 2.
|
| 3120 |
"train_batch_size": 12,
|
| 3121 |
"trial_name": null,
|
| 3122 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.30803602933883667,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-258",
|
| 4 |
+
"epoch": 12.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 516,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3097 |
"eval_samples_per_second": 61.478,
|
| 3098 |
"eval_steps_per_second": 15.369,
|
| 3099 |
"step": 430
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 10.023391812865498,
|
| 3103 |
+
"grad_norm": 2.626622200012207,
|
| 3104 |
+
"learning_rate": 7.947619047619048e-05,
|
| 3105 |
+
"loss": 2.1368,
|
| 3106 |
+
"step": 431
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 10.046783625730994,
|
| 3110 |
+
"grad_norm": 3.062572479248047,
|
| 3111 |
+
"learning_rate": 7.942857142857143e-05,
|
| 3112 |
+
"loss": 2.1211,
|
| 3113 |
+
"step": 432
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 10.070175438596491,
|
| 3117 |
+
"grad_norm": 3.3042075634002686,
|
| 3118 |
+
"learning_rate": 7.938095238095238e-05,
|
| 3119 |
+
"loss": 2.1274,
|
| 3120 |
+
"step": 433
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 10.093567251461987,
|
| 3124 |
+
"grad_norm": 3.31258225440979,
|
| 3125 |
+
"learning_rate": 7.933333333333334e-05,
|
| 3126 |
+
"loss": 2.1523,
|
| 3127 |
+
"step": 434
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 10.116959064327485,
|
| 3131 |
+
"grad_norm": 3.294790506362915,
|
| 3132 |
+
"learning_rate": 7.928571428571429e-05,
|
| 3133 |
+
"loss": 2.1665,
|
| 3134 |
+
"step": 435
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 10.140350877192983,
|
| 3138 |
+
"grad_norm": 2.905733585357666,
|
| 3139 |
+
"learning_rate": 7.923809523809524e-05,
|
| 3140 |
+
"loss": 2.1074,
|
| 3141 |
+
"step": 436
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 10.163742690058479,
|
| 3145 |
+
"grad_norm": 3.4812822341918945,
|
| 3146 |
+
"learning_rate": 7.919047619047619e-05,
|
| 3147 |
+
"loss": 2.1628,
|
| 3148 |
+
"step": 437
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 10.187134502923977,
|
| 3152 |
+
"grad_norm": 3.2400975227355957,
|
| 3153 |
+
"learning_rate": 7.914285714285715e-05,
|
| 3154 |
+
"loss": 2.1655,
|
| 3155 |
+
"step": 438
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 10.210526315789474,
|
| 3159 |
+
"grad_norm": 3.523585081100464,
|
| 3160 |
+
"learning_rate": 7.90952380952381e-05,
|
| 3161 |
+
"loss": 2.1843,
|
| 3162 |
+
"step": 439
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 10.23391812865497,
|
| 3166 |
+
"grad_norm": 3.4338159561157227,
|
| 3167 |
+
"learning_rate": 7.904761904761905e-05,
|
| 3168 |
+
"loss": 2.0997,
|
| 3169 |
+
"step": 440
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 10.257309941520468,
|
| 3173 |
+
"grad_norm": 2.533015251159668,
|
| 3174 |
+
"learning_rate": 7.900000000000001e-05,
|
| 3175 |
+
"loss": 2.1057,
|
| 3176 |
+
"step": 441
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 10.280701754385966,
|
| 3180 |
+
"grad_norm": 4.4363322257995605,
|
| 3181 |
+
"learning_rate": 7.895238095238095e-05,
|
| 3182 |
+
"loss": 2.164,
|
| 3183 |
+
"step": 442
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 10.304093567251462,
|
| 3187 |
+
"grad_norm": 4.817160606384277,
|
| 3188 |
+
"learning_rate": 7.89047619047619e-05,
|
| 3189 |
+
"loss": 2.1277,
|
| 3190 |
+
"step": 443
|
| 3191 |
+
},
|
| 3192 |
+
{
|
| 3193 |
+
"epoch": 10.32748538011696,
|
| 3194 |
+
"grad_norm": 3.683321475982666,
|
| 3195 |
+
"learning_rate": 7.885714285714286e-05,
|
| 3196 |
+
"loss": 2.1394,
|
| 3197 |
+
"step": 444
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 10.350877192982455,
|
| 3201 |
+
"grad_norm": 4.308437347412109,
|
| 3202 |
+
"learning_rate": 7.880952380952382e-05,
|
| 3203 |
+
"loss": 2.1484,
|
| 3204 |
+
"step": 445
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 10.374269005847953,
|
| 3208 |
+
"grad_norm": 5.58378791809082,
|
| 3209 |
+
"learning_rate": 7.876190476190477e-05,
|
| 3210 |
+
"loss": 2.1494,
|
| 3211 |
+
"step": 446
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 10.397660818713451,
|
| 3215 |
+
"grad_norm": 3.057953357696533,
|
| 3216 |
+
"learning_rate": 7.871428571428572e-05,
|
| 3217 |
+
"loss": 2.1407,
|
| 3218 |
+
"step": 447
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 10.421052631578947,
|
| 3222 |
+
"grad_norm": 5.560679912567139,
|
| 3223 |
+
"learning_rate": 7.866666666666666e-05,
|
| 3224 |
+
"loss": 2.133,
|
| 3225 |
+
"step": 448
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 10.444444444444445,
|
| 3229 |
+
"grad_norm": 3.6114635467529297,
|
| 3230 |
+
"learning_rate": 7.861904761904762e-05,
|
| 3231 |
+
"loss": 2.177,
|
| 3232 |
+
"step": 449
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 10.46783625730994,
|
| 3236 |
+
"grad_norm": 4.344070911407471,
|
| 3237 |
+
"learning_rate": 7.857142857142858e-05,
|
| 3238 |
+
"loss": 2.15,
|
| 3239 |
+
"step": 450
|
| 3240 |
+
},
|
| 3241 |
+
{
|
| 3242 |
+
"epoch": 10.491228070175438,
|
| 3243 |
+
"grad_norm": 5.889255046844482,
|
| 3244 |
+
"learning_rate": 7.852380952380954e-05,
|
| 3245 |
+
"loss": 2.1536,
|
| 3246 |
+
"step": 451
|
| 3247 |
+
},
|
| 3248 |
+
{
|
| 3249 |
+
"epoch": 10.514619883040936,
|
| 3250 |
+
"grad_norm": 2.920121192932129,
|
| 3251 |
+
"learning_rate": 7.847619047619048e-05,
|
| 3252 |
+
"loss": 2.1646,
|
| 3253 |
+
"step": 452
|
| 3254 |
+
},
|
| 3255 |
+
{
|
| 3256 |
+
"epoch": 10.538011695906432,
|
| 3257 |
+
"grad_norm": 4.948288440704346,
|
| 3258 |
+
"learning_rate": 7.842857142857143e-05,
|
| 3259 |
+
"loss": 2.1893,
|
| 3260 |
+
"step": 453
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 10.56140350877193,
|
| 3264 |
+
"grad_norm": 3.4220526218414307,
|
| 3265 |
+
"learning_rate": 7.838095238095239e-05,
|
| 3266 |
+
"loss": 2.1845,
|
| 3267 |
+
"step": 454
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"epoch": 10.584795321637428,
|
| 3271 |
+
"grad_norm": 5.378625869750977,
|
| 3272 |
+
"learning_rate": 7.833333333333333e-05,
|
| 3273 |
+
"loss": 2.1713,
|
| 3274 |
+
"step": 455
|
| 3275 |
+
},
|
| 3276 |
+
{
|
| 3277 |
+
"epoch": 10.608187134502923,
|
| 3278 |
+
"grad_norm": 6.9921159744262695,
|
| 3279 |
+
"learning_rate": 7.828571428571429e-05,
|
| 3280 |
+
"loss": 2.1645,
|
| 3281 |
+
"step": 456
|
| 3282 |
+
},
|
| 3283 |
+
{
|
| 3284 |
+
"epoch": 10.631578947368421,
|
| 3285 |
+
"grad_norm": 3.1062328815460205,
|
| 3286 |
+
"learning_rate": 7.823809523809525e-05,
|
| 3287 |
+
"loss": 2.1829,
|
| 3288 |
+
"step": 457
|
| 3289 |
+
},
|
| 3290 |
+
{
|
| 3291 |
+
"epoch": 10.654970760233919,
|
| 3292 |
+
"grad_norm": 3.9356822967529297,
|
| 3293 |
+
"learning_rate": 7.819047619047619e-05,
|
| 3294 |
+
"loss": 2.1961,
|
| 3295 |
+
"step": 458
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 10.678362573099415,
|
| 3299 |
+
"grad_norm": 2.3222548961639404,
|
| 3300 |
+
"learning_rate": 7.814285714285715e-05,
|
| 3301 |
+
"loss": 2.1581,
|
| 3302 |
+
"step": 459
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 10.701754385964913,
|
| 3306 |
+
"grad_norm": 5.491628646850586,
|
| 3307 |
+
"learning_rate": 7.80952380952381e-05,
|
| 3308 |
+
"loss": 2.1506,
|
| 3309 |
+
"step": 460
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 10.725146198830409,
|
| 3313 |
+
"grad_norm": 3.369358777999878,
|
| 3314 |
+
"learning_rate": 7.804761904761905e-05,
|
| 3315 |
+
"loss": 2.1679,
|
| 3316 |
+
"step": 461
|
| 3317 |
+
},
|
| 3318 |
+
{
|
| 3319 |
+
"epoch": 10.748538011695906,
|
| 3320 |
+
"grad_norm": 6.5891523361206055,
|
| 3321 |
+
"learning_rate": 7.800000000000001e-05,
|
| 3322 |
+
"loss": 2.1454,
|
| 3323 |
+
"step": 462
|
| 3324 |
+
},
|
| 3325 |
+
{
|
| 3326 |
+
"epoch": 10.771929824561404,
|
| 3327 |
+
"grad_norm": 7.308892726898193,
|
| 3328 |
+
"learning_rate": 7.795238095238096e-05,
|
| 3329 |
+
"loss": 2.2065,
|
| 3330 |
+
"step": 463
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"epoch": 10.7953216374269,
|
| 3334 |
+
"grad_norm": 3.553459882736206,
|
| 3335 |
+
"learning_rate": 7.790476190476192e-05,
|
| 3336 |
+
"loss": 2.1726,
|
| 3337 |
+
"step": 464
|
| 3338 |
+
},
|
| 3339 |
+
{
|
| 3340 |
+
"epoch": 10.818713450292398,
|
| 3341 |
+
"grad_norm": 7.7826642990112305,
|
| 3342 |
+
"learning_rate": 7.785714285714286e-05,
|
| 3343 |
+
"loss": 2.1967,
|
| 3344 |
+
"step": 465
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 10.842105263157894,
|
| 3348 |
+
"grad_norm": 10.483582496643066,
|
| 3349 |
+
"learning_rate": 7.78095238095238e-05,
|
| 3350 |
+
"loss": 2.2286,
|
| 3351 |
+
"step": 466
|
| 3352 |
+
},
|
| 3353 |
+
{
|
| 3354 |
+
"epoch": 10.865497076023392,
|
| 3355 |
+
"grad_norm": 4.64753532409668,
|
| 3356 |
+
"learning_rate": 7.776190476190476e-05,
|
| 3357 |
+
"loss": 2.1643,
|
| 3358 |
+
"step": 467
|
| 3359 |
+
},
|
| 3360 |
+
{
|
| 3361 |
+
"epoch": 10.88888888888889,
|
| 3362 |
+
"grad_norm": 4.482329845428467,
|
| 3363 |
+
"learning_rate": 7.771428571428572e-05,
|
| 3364 |
+
"loss": 2.1681,
|
| 3365 |
+
"step": 468
|
| 3366 |
+
},
|
| 3367 |
+
{
|
| 3368 |
+
"epoch": 10.912280701754385,
|
| 3369 |
+
"grad_norm": 8.45293140411377,
|
| 3370 |
+
"learning_rate": 7.766666666666667e-05,
|
| 3371 |
+
"loss": 2.1633,
|
| 3372 |
+
"step": 469
|
| 3373 |
+
},
|
| 3374 |
+
{
|
| 3375 |
+
"epoch": 10.935672514619883,
|
| 3376 |
+
"grad_norm": 5.571048736572266,
|
| 3377 |
+
"learning_rate": 7.761904761904762e-05,
|
| 3378 |
+
"loss": 2.2138,
|
| 3379 |
+
"step": 470
|
| 3380 |
+
},
|
| 3381 |
+
{
|
| 3382 |
+
"epoch": 10.95906432748538,
|
| 3383 |
+
"grad_norm": 3.7479379177093506,
|
| 3384 |
+
"learning_rate": 7.757142857142857e-05,
|
| 3385 |
+
"loss": 2.1603,
|
| 3386 |
+
"step": 471
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 10.982456140350877,
|
| 3390 |
+
"grad_norm": 6.011244297027588,
|
| 3391 |
+
"learning_rate": 7.752380952380953e-05,
|
| 3392 |
+
"loss": 2.22,
|
| 3393 |
+
"step": 472
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"epoch": 11.0,
|
| 3397 |
+
"grad_norm": 4.298096179962158,
|
| 3398 |
+
"learning_rate": 7.747619047619049e-05,
|
| 3399 |
+
"loss": 1.6397,
|
| 3400 |
+
"step": 473
|
| 3401 |
+
},
|
| 3402 |
+
{
|
| 3403 |
+
"epoch": 11.0,
|
| 3404 |
+
"eval_loss": 0.3189237415790558,
|
| 3405 |
+
"eval_runtime": 3.4973,
|
| 3406 |
+
"eval_samples_per_second": 61.762,
|
| 3407 |
+
"eval_steps_per_second": 15.441,
|
| 3408 |
+
"step": 473
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 11.023391812865498,
|
| 3412 |
+
"grad_norm": 3.59027361869812,
|
| 3413 |
+
"learning_rate": 7.742857142857143e-05,
|
| 3414 |
+
"loss": 2.0829,
|
| 3415 |
+
"step": 474
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 11.046783625730994,
|
| 3419 |
+
"grad_norm": 4.3692851066589355,
|
| 3420 |
+
"learning_rate": 7.738095238095239e-05,
|
| 3421 |
+
"loss": 2.0586,
|
| 3422 |
+
"step": 475
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 11.070175438596491,
|
| 3426 |
+
"grad_norm": 4.701996803283691,
|
| 3427 |
+
"learning_rate": 7.733333333333333e-05,
|
| 3428 |
+
"loss": 2.1107,
|
| 3429 |
+
"step": 476
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 11.093567251461987,
|
| 3433 |
+
"grad_norm": 3.7033441066741943,
|
| 3434 |
+
"learning_rate": 7.728571428571429e-05,
|
| 3435 |
+
"loss": 2.0621,
|
| 3436 |
+
"step": 477
|
| 3437 |
+
},
|
| 3438 |
+
{
|
| 3439 |
+
"epoch": 11.116959064327485,
|
| 3440 |
+
"grad_norm": 5.6654887199401855,
|
| 3441 |
+
"learning_rate": 7.723809523809524e-05,
|
| 3442 |
+
"loss": 2.0648,
|
| 3443 |
+
"step": 478
|
| 3444 |
+
},
|
| 3445 |
+
{
|
| 3446 |
+
"epoch": 11.140350877192983,
|
| 3447 |
+
"grad_norm": 3.5010275840759277,
|
| 3448 |
+
"learning_rate": 7.71904761904762e-05,
|
| 3449 |
+
"loss": 2.0696,
|
| 3450 |
+
"step": 479
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 11.163742690058479,
|
| 3454 |
+
"grad_norm": 5.883917808532715,
|
| 3455 |
+
"learning_rate": 7.714285714285715e-05,
|
| 3456 |
+
"loss": 2.0749,
|
| 3457 |
+
"step": 480
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 11.187134502923977,
|
| 3461 |
+
"grad_norm": 5.297660827636719,
|
| 3462 |
+
"learning_rate": 7.70952380952381e-05,
|
| 3463 |
+
"loss": 2.0188,
|
| 3464 |
+
"step": 481
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 11.210526315789474,
|
| 3468 |
+
"grad_norm": 3.6153805255889893,
|
| 3469 |
+
"learning_rate": 7.704761904761904e-05,
|
| 3470 |
+
"loss": 2.0778,
|
| 3471 |
+
"step": 482
|
| 3472 |
+
},
|
| 3473 |
+
{
|
| 3474 |
+
"epoch": 11.23391812865497,
|
| 3475 |
+
"grad_norm": 5.116675853729248,
|
| 3476 |
+
"learning_rate": 7.7e-05,
|
| 3477 |
+
"loss": 2.0994,
|
| 3478 |
+
"step": 483
|
| 3479 |
+
},
|
| 3480 |
+
{
|
| 3481 |
+
"epoch": 11.257309941520468,
|
| 3482 |
+
"grad_norm": 2.987740993499756,
|
| 3483 |
+
"learning_rate": 7.695238095238096e-05,
|
| 3484 |
+
"loss": 2.0525,
|
| 3485 |
+
"step": 484
|
| 3486 |
+
},
|
| 3487 |
+
{
|
| 3488 |
+
"epoch": 11.280701754385966,
|
| 3489 |
+
"grad_norm": 4.422389984130859,
|
| 3490 |
+
"learning_rate": 7.690476190476192e-05,
|
| 3491 |
+
"loss": 2.0637,
|
| 3492 |
+
"step": 485
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"epoch": 11.304093567251462,
|
| 3496 |
+
"grad_norm": 3.5934934616088867,
|
| 3497 |
+
"learning_rate": 7.685714285714286e-05,
|
| 3498 |
+
"loss": 2.1044,
|
| 3499 |
+
"step": 486
|
| 3500 |
+
},
|
| 3501 |
+
{
|
| 3502 |
+
"epoch": 11.32748538011696,
|
| 3503 |
+
"grad_norm": 5.785375118255615,
|
| 3504 |
+
"learning_rate": 7.680952380952381e-05,
|
| 3505 |
+
"loss": 2.0194,
|
| 3506 |
+
"step": 487
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 11.350877192982455,
|
| 3510 |
+
"grad_norm": 4.386531352996826,
|
| 3511 |
+
"learning_rate": 7.676190476190477e-05,
|
| 3512 |
+
"loss": 2.0181,
|
| 3513 |
+
"step": 488
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 11.374269005847953,
|
| 3517 |
+
"grad_norm": 3.4447247982025146,
|
| 3518 |
+
"learning_rate": 7.671428571428571e-05,
|
| 3519 |
+
"loss": 2.0698,
|
| 3520 |
+
"step": 489
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 11.397660818713451,
|
| 3524 |
+
"grad_norm": 5.470218658447266,
|
| 3525 |
+
"learning_rate": 7.666666666666667e-05,
|
| 3526 |
+
"loss": 2.0635,
|
| 3527 |
+
"step": 490
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 11.421052631578947,
|
| 3531 |
+
"grad_norm": 3.2394590377807617,
|
| 3532 |
+
"learning_rate": 7.661904761904763e-05,
|
| 3533 |
+
"loss": 2.0613,
|
| 3534 |
+
"step": 491
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 11.444444444444445,
|
| 3538 |
+
"grad_norm": 7.506831169128418,
|
| 3539 |
+
"learning_rate": 7.657142857142857e-05,
|
| 3540 |
+
"loss": 2.0938,
|
| 3541 |
+
"step": 492
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 11.46783625730994,
|
| 3545 |
+
"grad_norm": 8.396202087402344,
|
| 3546 |
+
"learning_rate": 7.652380952380953e-05,
|
| 3547 |
+
"loss": 2.0775,
|
| 3548 |
+
"step": 493
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 11.491228070175438,
|
| 3552 |
+
"grad_norm": 3.5975074768066406,
|
| 3553 |
+
"learning_rate": 7.647619047619048e-05,
|
| 3554 |
+
"loss": 2.1297,
|
| 3555 |
+
"step": 494
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 11.514619883040936,
|
| 3559 |
+
"grad_norm": 7.446574687957764,
|
| 3560 |
+
"learning_rate": 7.642857142857143e-05,
|
| 3561 |
+
"loss": 2.1108,
|
| 3562 |
+
"step": 495
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 11.538011695906432,
|
| 3566 |
+
"grad_norm": 9.395698547363281,
|
| 3567 |
+
"learning_rate": 7.638095238095239e-05,
|
| 3568 |
+
"loss": 2.1134,
|
| 3569 |
+
"step": 496
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 11.56140350877193,
|
| 3573 |
+
"grad_norm": 4.919811725616455,
|
| 3574 |
+
"learning_rate": 7.633333333333334e-05,
|
| 3575 |
+
"loss": 2.0989,
|
| 3576 |
+
"step": 497
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 11.584795321637428,
|
| 3580 |
+
"grad_norm": 5.478214740753174,
|
| 3581 |
+
"learning_rate": 7.62857142857143e-05,
|
| 3582 |
+
"loss": 2.1026,
|
| 3583 |
+
"step": 498
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 11.608187134502923,
|
| 3587 |
+
"grad_norm": 7.014881134033203,
|
| 3588 |
+
"learning_rate": 7.623809523809524e-05,
|
| 3589 |
+
"loss": 2.0747,
|
| 3590 |
+
"step": 499
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 11.631578947368421,
|
| 3594 |
+
"grad_norm": 3.6512677669525146,
|
| 3595 |
+
"learning_rate": 7.619047619047618e-05,
|
| 3596 |
+
"loss": 2.1082,
|
| 3597 |
+
"step": 500
|
| 3598 |
+
},
|
| 3599 |
+
{
|
| 3600 |
+
"epoch": 11.654970760233919,
|
| 3601 |
+
"grad_norm": 5.103152751922607,
|
| 3602 |
+
"learning_rate": 7.614285714285714e-05,
|
| 3603 |
+
"loss": 2.0812,
|
| 3604 |
+
"step": 501
|
| 3605 |
+
},
|
| 3606 |
+
{
|
| 3607 |
+
"epoch": 11.678362573099415,
|
| 3608 |
+
"grad_norm": 5.7634477615356445,
|
| 3609 |
+
"learning_rate": 7.60952380952381e-05,
|
| 3610 |
+
"loss": 2.0911,
|
| 3611 |
+
"step": 502
|
| 3612 |
+
},
|
| 3613 |
+
{
|
| 3614 |
+
"epoch": 11.701754385964913,
|
| 3615 |
+
"grad_norm": 3.540539264678955,
|
| 3616 |
+
"learning_rate": 7.604761904761906e-05,
|
| 3617 |
+
"loss": 2.0894,
|
| 3618 |
+
"step": 503
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 11.725146198830409,
|
| 3622 |
+
"grad_norm": 3.773231267929077,
|
| 3623 |
+
"learning_rate": 7.6e-05,
|
| 3624 |
+
"loss": 2.0756,
|
| 3625 |
+
"step": 504
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 11.748538011695906,
|
| 3629 |
+
"grad_norm": 4.254147052764893,
|
| 3630 |
+
"learning_rate": 7.595238095238095e-05,
|
| 3631 |
+
"loss": 2.0937,
|
| 3632 |
+
"step": 505
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 11.771929824561404,
|
| 3636 |
+
"grad_norm": 3.7697649002075195,
|
| 3637 |
+
"learning_rate": 7.590476190476191e-05,
|
| 3638 |
+
"loss": 2.1034,
|
| 3639 |
+
"step": 506
|
| 3640 |
+
},
|
| 3641 |
+
{
|
| 3642 |
+
"epoch": 11.7953216374269,
|
| 3643 |
+
"grad_norm": 4.8648295402526855,
|
| 3644 |
+
"learning_rate": 7.585714285714287e-05,
|
| 3645 |
+
"loss": 2.106,
|
| 3646 |
+
"step": 507
|
| 3647 |
+
},
|
| 3648 |
+
{
|
| 3649 |
+
"epoch": 11.818713450292398,
|
| 3650 |
+
"grad_norm": 4.606119155883789,
|
| 3651 |
+
"learning_rate": 7.580952380952381e-05,
|
| 3652 |
+
"loss": 2.1035,
|
| 3653 |
+
"step": 508
|
| 3654 |
+
},
|
| 3655 |
+
{
|
| 3656 |
+
"epoch": 11.842105263157894,
|
| 3657 |
+
"grad_norm": 3.0035810470581055,
|
| 3658 |
+
"learning_rate": 7.576190476190477e-05,
|
| 3659 |
+
"loss": 2.0961,
|
| 3660 |
+
"step": 509
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"epoch": 11.865497076023392,
|
| 3664 |
+
"grad_norm": 5.411649227142334,
|
| 3665 |
+
"learning_rate": 7.571428571428571e-05,
|
| 3666 |
+
"loss": 2.0972,
|
| 3667 |
+
"step": 510
|
| 3668 |
+
},
|
| 3669 |
+
{
|
| 3670 |
+
"epoch": 11.88888888888889,
|
| 3671 |
+
"grad_norm": 5.5969157218933105,
|
| 3672 |
+
"learning_rate": 7.566666666666667e-05,
|
| 3673 |
+
"loss": 2.1224,
|
| 3674 |
+
"step": 511
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 11.912280701754385,
|
| 3678 |
+
"grad_norm": 3.6775734424591064,
|
| 3679 |
+
"learning_rate": 7.561904761904762e-05,
|
| 3680 |
+
"loss": 2.0929,
|
| 3681 |
+
"step": 512
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"epoch": 11.935672514619883,
|
| 3685 |
+
"grad_norm": 4.247641563415527,
|
| 3686 |
+
"learning_rate": 7.557142857142857e-05,
|
| 3687 |
+
"loss": 2.1077,
|
| 3688 |
+
"step": 513
|
| 3689 |
+
},
|
| 3690 |
+
{
|
| 3691 |
+
"epoch": 11.95906432748538,
|
| 3692 |
+
"grad_norm": 3.0920655727386475,
|
| 3693 |
+
"learning_rate": 7.552380952380953e-05,
|
| 3694 |
+
"loss": 2.0521,
|
| 3695 |
+
"step": 514
|
| 3696 |
+
},
|
| 3697 |
+
{
|
| 3698 |
+
"epoch": 11.982456140350877,
|
| 3699 |
+
"grad_norm": 3.7392711639404297,
|
| 3700 |
+
"learning_rate": 7.547619047619048e-05,
|
| 3701 |
+
"loss": 2.1152,
|
| 3702 |
+
"step": 515
|
| 3703 |
+
},
|
| 3704 |
+
{
|
| 3705 |
+
"epoch": 12.0,
|
| 3706 |
+
"grad_norm": 2.820730209350586,
|
| 3707 |
+
"learning_rate": 7.542857142857144e-05,
|
| 3708 |
+
"loss": 1.5974,
|
| 3709 |
+
"step": 516
|
| 3710 |
+
},
|
| 3711 |
+
{
|
| 3712 |
+
"epoch": 12.0,
|
| 3713 |
+
"eval_loss": 0.32489120960235596,
|
| 3714 |
+
"eval_runtime": 3.4774,
|
| 3715 |
+
"eval_samples_per_second": 62.116,
|
| 3716 |
+
"eval_steps_per_second": 15.529,
|
| 3717 |
+
"step": 516
|
| 3718 |
}
|
| 3719 |
],
|
| 3720 |
"logging_steps": 1,
|
|
|
|
| 3734 |
"attributes": {}
|
| 3735 |
}
|
| 3736 |
},
|
| 3737 |
+
"total_flos": 2.581592674192589e+16,
|
| 3738 |
"train_batch_size": 12,
|
| 3739 |
"trial_name": null,
|
| 3740 |
"trial_params": null
|