Training in progress, step 4500, 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 234681136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f76e1c71a592d741fdd40918c6891542d3837ccabc9fa8cbe1831ad73bed3377
|
| 3 |
size 234681136
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469516363
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79b075c21268b2a7ca8b93698d0da84575f538e338132fe643c3c6880a8693db
|
| 3 |
size 469516363
|
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:e9bbfe0b3b83ac16896ad88a72baf7b907818b1deab71bce85f11ea4f6347d4c
|
| 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:cfc4607d0eab509f8bd12c06c7cf681bedc18d3448143992c224d019b4cd4e30
|
| 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": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3128,6 +3128,396 @@
|
|
| 3128 |
"eval_samples_per_second": 66.73,
|
| 3129 |
"eval_steps_per_second": 3.807,
|
| 3130 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3131 |
}
|
| 3132 |
],
|
| 3133 |
"logging_steps": 10,
|
|
@@ -3147,7 +3537,7 @@
|
|
| 3147 |
"attributes": {}
|
| 3148 |
}
|
| 3149 |
},
|
| 3150 |
-
"total_flos": 1.
|
| 3151 |
"train_batch_size": 18,
|
| 3152 |
"trial_name": null,
|
| 3153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3128 |
"eval_samples_per_second": 66.73,
|
| 3129 |
"eval_steps_per_second": 3.807,
|
| 3130 |
"step": 4000
|
| 3131 |
+
},
|
| 3132 |
+
{
|
| 3133 |
+
"epoch": 0.802,
|
| 3134 |
+
"grad_norm": 0.054931640625,
|
| 3135 |
+
"learning_rate": 0.0003,
|
| 3136 |
+
"loss": 2.5756288528442384,
|
| 3137 |
+
"step": 4010
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 0.804,
|
| 3141 |
+
"grad_norm": 0.5546875,
|
| 3142 |
+
"learning_rate": 0.0003,
|
| 3143 |
+
"loss": 2.591953468322754,
|
| 3144 |
+
"step": 4020
|
| 3145 |
+
},
|
| 3146 |
+
{
|
| 3147 |
+
"epoch": 0.806,
|
| 3148 |
+
"grad_norm": 0.05029296875,
|
| 3149 |
+
"learning_rate": 0.0003,
|
| 3150 |
+
"loss": 2.5956727981567385,
|
| 3151 |
+
"step": 4030
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.808,
|
| 3155 |
+
"grad_norm": 0.05224609375,
|
| 3156 |
+
"learning_rate": 0.0003,
|
| 3157 |
+
"loss": 2.60211067199707,
|
| 3158 |
+
"step": 4040
|
| 3159 |
+
},
|
| 3160 |
+
{
|
| 3161 |
+
"epoch": 0.81,
|
| 3162 |
+
"grad_norm": 0.049072265625,
|
| 3163 |
+
"learning_rate": 0.0003,
|
| 3164 |
+
"loss": 2.5871608734130858,
|
| 3165 |
+
"step": 4050
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 0.812,
|
| 3169 |
+
"grad_norm": 0.10693359375,
|
| 3170 |
+
"learning_rate": 0.0003,
|
| 3171 |
+
"loss": 2.5698373794555662,
|
| 3172 |
+
"step": 4060
|
| 3173 |
+
},
|
| 3174 |
+
{
|
| 3175 |
+
"epoch": 0.814,
|
| 3176 |
+
"grad_norm": 0.05810546875,
|
| 3177 |
+
"learning_rate": 0.0003,
|
| 3178 |
+
"loss": 2.6126802444458006,
|
| 3179 |
+
"step": 4070
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 0.816,
|
| 3183 |
+
"grad_norm": 0.05029296875,
|
| 3184 |
+
"learning_rate": 0.0003,
|
| 3185 |
+
"loss": 2.5981868743896483,
|
| 3186 |
+
"step": 4080
|
| 3187 |
+
},
|
| 3188 |
+
{
|
| 3189 |
+
"epoch": 0.818,
|
| 3190 |
+
"grad_norm": 0.052978515625,
|
| 3191 |
+
"learning_rate": 0.0003,
|
| 3192 |
+
"loss": 2.580386161804199,
|
| 3193 |
+
"step": 4090
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 0.82,
|
| 3197 |
+
"grad_norm": 0.07080078125,
|
| 3198 |
+
"learning_rate": 0.0003,
|
| 3199 |
+
"loss": 2.5840375900268553,
|
| 3200 |
+
"step": 4100
|
| 3201 |
+
},
|
| 3202 |
+
{
|
| 3203 |
+
"epoch": 0.82,
|
| 3204 |
+
"eval_loss": 3.0312201976776123,
|
| 3205 |
+
"eval_runtime": 4.4429,
|
| 3206 |
+
"eval_samples_per_second": 67.074,
|
| 3207 |
+
"eval_steps_per_second": 3.826,
|
| 3208 |
+
"step": 4100
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.822,
|
| 3212 |
+
"grad_norm": 0.052978515625,
|
| 3213 |
+
"learning_rate": 0.0003,
|
| 3214 |
+
"loss": 2.6040040969848635,
|
| 3215 |
+
"step": 4110
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.824,
|
| 3219 |
+
"grad_norm": 0.05224609375,
|
| 3220 |
+
"learning_rate": 0.0003,
|
| 3221 |
+
"loss": 2.5784271240234373,
|
| 3222 |
+
"step": 4120
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.826,
|
| 3226 |
+
"grad_norm": 0.05078125,
|
| 3227 |
+
"learning_rate": 0.0003,
|
| 3228 |
+
"loss": 2.5992313385009767,
|
| 3229 |
+
"step": 4130
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.828,
|
| 3233 |
+
"grad_norm": 0.62109375,
|
| 3234 |
+
"learning_rate": 0.0003,
|
| 3235 |
+
"loss": 2.607274055480957,
|
| 3236 |
+
"step": 4140
|
| 3237 |
+
},
|
| 3238 |
+
{
|
| 3239 |
+
"epoch": 0.83,
|
| 3240 |
+
"grad_norm": 0.05126953125,
|
| 3241 |
+
"learning_rate": 0.0003,
|
| 3242 |
+
"loss": 2.5900325775146484,
|
| 3243 |
+
"step": 4150
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.832,
|
| 3247 |
+
"grad_norm": 0.0556640625,
|
| 3248 |
+
"learning_rate": 0.0003,
|
| 3249 |
+
"loss": 2.584280586242676,
|
| 3250 |
+
"step": 4160
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 0.834,
|
| 3254 |
+
"grad_norm": 0.06103515625,
|
| 3255 |
+
"learning_rate": 0.0003,
|
| 3256 |
+
"loss": 2.578823471069336,
|
| 3257 |
+
"step": 4170
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.836,
|
| 3261 |
+
"grad_norm": 0.05908203125,
|
| 3262 |
+
"learning_rate": 0.0003,
|
| 3263 |
+
"loss": 2.600706672668457,
|
| 3264 |
+
"step": 4180
|
| 3265 |
+
},
|
| 3266 |
+
{
|
| 3267 |
+
"epoch": 0.838,
|
| 3268 |
+
"grad_norm": 0.054931640625,
|
| 3269 |
+
"learning_rate": 0.0003,
|
| 3270 |
+
"loss": 2.5908893585205077,
|
| 3271 |
+
"step": 4190
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.84,
|
| 3275 |
+
"grad_norm": 0.08740234375,
|
| 3276 |
+
"learning_rate": 0.0003,
|
| 3277 |
+
"loss": 2.6078845977783205,
|
| 3278 |
+
"step": 4200
|
| 3279 |
+
},
|
| 3280 |
+
{
|
| 3281 |
+
"epoch": 0.84,
|
| 3282 |
+
"eval_loss": 3.0311102867126465,
|
| 3283 |
+
"eval_runtime": 4.4714,
|
| 3284 |
+
"eval_samples_per_second": 66.645,
|
| 3285 |
+
"eval_steps_per_second": 3.802,
|
| 3286 |
+
"step": 4200
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 0.842,
|
| 3290 |
+
"grad_norm": 0.0556640625,
|
| 3291 |
+
"learning_rate": 0.0003,
|
| 3292 |
+
"loss": 2.630947303771973,
|
| 3293 |
+
"step": 4210
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 0.844,
|
| 3297 |
+
"grad_norm": 0.09423828125,
|
| 3298 |
+
"learning_rate": 0.0003,
|
| 3299 |
+
"loss": 2.623428726196289,
|
| 3300 |
+
"step": 4220
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 0.846,
|
| 3304 |
+
"grad_norm": 0.111328125,
|
| 3305 |
+
"learning_rate": 0.0003,
|
| 3306 |
+
"loss": 2.5977907180786133,
|
| 3307 |
+
"step": 4230
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 0.848,
|
| 3311 |
+
"grad_norm": 0.455078125,
|
| 3312 |
+
"learning_rate": 0.0003,
|
| 3313 |
+
"loss": 2.6008005142211914,
|
| 3314 |
+
"step": 4240
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 0.85,
|
| 3318 |
+
"grad_norm": 1.6015625,
|
| 3319 |
+
"learning_rate": 0.0003,
|
| 3320 |
+
"loss": 2.5678030014038087,
|
| 3321 |
+
"step": 4250
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 0.852,
|
| 3325 |
+
"grad_norm": 0.052490234375,
|
| 3326 |
+
"learning_rate": 0.0003,
|
| 3327 |
+
"loss": 2.613857650756836,
|
| 3328 |
+
"step": 4260
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 0.854,
|
| 3332 |
+
"grad_norm": 0.08349609375,
|
| 3333 |
+
"learning_rate": 0.0003,
|
| 3334 |
+
"loss": 2.579903221130371,
|
| 3335 |
+
"step": 4270
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 0.856,
|
| 3339 |
+
"grad_norm": 0.049560546875,
|
| 3340 |
+
"learning_rate": 0.0003,
|
| 3341 |
+
"loss": 2.579732131958008,
|
| 3342 |
+
"step": 4280
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 0.858,
|
| 3346 |
+
"grad_norm": 0.181640625,
|
| 3347 |
+
"learning_rate": 0.0003,
|
| 3348 |
+
"loss": 2.5955440521240236,
|
| 3349 |
+
"step": 4290
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 0.86,
|
| 3353 |
+
"grad_norm": 0.05712890625,
|
| 3354 |
+
"learning_rate": 0.0003,
|
| 3355 |
+
"loss": 2.592930793762207,
|
| 3356 |
+
"step": 4300
|
| 3357 |
+
},
|
| 3358 |
+
{
|
| 3359 |
+
"epoch": 0.86,
|
| 3360 |
+
"eval_loss": 3.031736373901367,
|
| 3361 |
+
"eval_runtime": 4.4299,
|
| 3362 |
+
"eval_samples_per_second": 67.27,
|
| 3363 |
+
"eval_steps_per_second": 3.838,
|
| 3364 |
+
"step": 4300
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 0.862,
|
| 3368 |
+
"grad_norm": 0.05419921875,
|
| 3369 |
+
"learning_rate": 0.0003,
|
| 3370 |
+
"loss": 2.592413902282715,
|
| 3371 |
+
"step": 4310
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 0.864,
|
| 3375 |
+
"grad_norm": 0.10986328125,
|
| 3376 |
+
"learning_rate": 0.0003,
|
| 3377 |
+
"loss": 2.569998931884766,
|
| 3378 |
+
"step": 4320
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 0.866,
|
| 3382 |
+
"grad_norm": 0.048583984375,
|
| 3383 |
+
"learning_rate": 0.0003,
|
| 3384 |
+
"loss": 2.5922664642333983,
|
| 3385 |
+
"step": 4330
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 0.868,
|
| 3389 |
+
"grad_norm": 0.052734375,
|
| 3390 |
+
"learning_rate": 0.0003,
|
| 3391 |
+
"loss": 2.6012556076049806,
|
| 3392 |
+
"step": 4340
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 0.87,
|
| 3396 |
+
"grad_norm": 0.07177734375,
|
| 3397 |
+
"learning_rate": 0.0003,
|
| 3398 |
+
"loss": 2.6031923294067383,
|
| 3399 |
+
"step": 4350
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 0.872,
|
| 3403 |
+
"grad_norm": 0.07763671875,
|
| 3404 |
+
"learning_rate": 0.0003,
|
| 3405 |
+
"loss": 2.59698543548584,
|
| 3406 |
+
"step": 4360
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 0.874,
|
| 3410 |
+
"grad_norm": 0.051513671875,
|
| 3411 |
+
"learning_rate": 0.0003,
|
| 3412 |
+
"loss": 2.6096282958984376,
|
| 3413 |
+
"step": 4370
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 0.876,
|
| 3417 |
+
"grad_norm": 0.052734375,
|
| 3418 |
+
"learning_rate": 0.0003,
|
| 3419 |
+
"loss": 2.6013412475585938,
|
| 3420 |
+
"step": 4380
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 0.878,
|
| 3424 |
+
"grad_norm": 0.051025390625,
|
| 3425 |
+
"learning_rate": 0.0003,
|
| 3426 |
+
"loss": 2.570247268676758,
|
| 3427 |
+
"step": 4390
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 0.88,
|
| 3431 |
+
"grad_norm": 0.19140625,
|
| 3432 |
+
"learning_rate": 0.0003,
|
| 3433 |
+
"loss": 2.6004173278808596,
|
| 3434 |
+
"step": 4400
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.88,
|
| 3438 |
+
"eval_loss": 3.032118320465088,
|
| 3439 |
+
"eval_runtime": 4.4552,
|
| 3440 |
+
"eval_samples_per_second": 66.887,
|
| 3441 |
+
"eval_steps_per_second": 3.816,
|
| 3442 |
+
"step": 4400
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 0.882,
|
| 3446 |
+
"grad_norm": 0.050048828125,
|
| 3447 |
+
"learning_rate": 0.0003,
|
| 3448 |
+
"loss": 2.60999755859375,
|
| 3449 |
+
"step": 4410
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 0.884,
|
| 3453 |
+
"grad_norm": 0.1044921875,
|
| 3454 |
+
"learning_rate": 0.0003,
|
| 3455 |
+
"loss": 2.5999217987060548,
|
| 3456 |
+
"step": 4420
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 0.886,
|
| 3460 |
+
"grad_norm": 0.255859375,
|
| 3461 |
+
"learning_rate": 0.0003,
|
| 3462 |
+
"loss": 2.57828369140625,
|
| 3463 |
+
"step": 4430
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 0.888,
|
| 3467 |
+
"grad_norm": 0.0556640625,
|
| 3468 |
+
"learning_rate": 0.0003,
|
| 3469 |
+
"loss": 2.5876300811767576,
|
| 3470 |
+
"step": 4440
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 0.89,
|
| 3474 |
+
"grad_norm": 0.052490234375,
|
| 3475 |
+
"learning_rate": 0.0003,
|
| 3476 |
+
"loss": 2.5927480697631835,
|
| 3477 |
+
"step": 4450
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 0.892,
|
| 3481 |
+
"grad_norm": 0.076171875,
|
| 3482 |
+
"learning_rate": 0.0003,
|
| 3483 |
+
"loss": 2.6045318603515626,
|
| 3484 |
+
"step": 4460
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 0.894,
|
| 3488 |
+
"grad_norm": 0.06201171875,
|
| 3489 |
+
"learning_rate": 0.0003,
|
| 3490 |
+
"loss": 2.585988235473633,
|
| 3491 |
+
"step": 4470
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 0.896,
|
| 3495 |
+
"grad_norm": 0.050048828125,
|
| 3496 |
+
"learning_rate": 0.0003,
|
| 3497 |
+
"loss": 2.613155555725098,
|
| 3498 |
+
"step": 4480
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 0.898,
|
| 3502 |
+
"grad_norm": 4.125,
|
| 3503 |
+
"learning_rate": 0.0003,
|
| 3504 |
+
"loss": 2.592078971862793,
|
| 3505 |
+
"step": 4490
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 0.9,
|
| 3509 |
+
"grad_norm": 0.048095703125,
|
| 3510 |
+
"learning_rate": 0.0003,
|
| 3511 |
+
"loss": 2.591631317138672,
|
| 3512 |
+
"step": 4500
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.9,
|
| 3516 |
+
"eval_loss": 3.028334617614746,
|
| 3517 |
+
"eval_runtime": 4.4441,
|
| 3518 |
+
"eval_samples_per_second": 67.055,
|
| 3519 |
+
"eval_steps_per_second": 3.825,
|
| 3520 |
+
"step": 4500
|
| 3521 |
}
|
| 3522 |
],
|
| 3523 |
"logging_steps": 10,
|
|
|
|
| 3537 |
"attributes": {}
|
| 3538 |
}
|
| 3539 |
},
|
| 3540 |
+
"total_flos": 1.467695316860928e+18,
|
| 3541 |
"train_batch_size": 18,
|
| 3542 |
"trial_name": null,
|
| 3543 |
"trial_params": null
|