Training in progress, step 350, 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 59933632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1c35ae538f4b13ed118009e42d3af5ce35d02974649d677dcae751fa109040d
|
| 3 |
size 59933632
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31823460
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b4af661d5dbc2e4ded19c017724e4032b3e4ebda32ac08442406a113fb81189
|
| 3 |
size 31823460
|
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:e5cd4d6f1a56868495de31ebab839ccdff6500d945e21b9b50d123a2662f6221
|
| 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:b881a4283fbf9ae4dd8073fe406895e163eb2a9281e2f7a0b2ffcfdeea673f59
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5701812505722046,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
-
"epoch": 2.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2163,6 +2163,364 @@
|
|
| 2163 |
"eval_samples_per_second": 7.449,
|
| 2164 |
"eval_steps_per_second": 7.449,
|
| 2165 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2166 |
}
|
| 2167 |
],
|
| 2168 |
"logging_steps": 1,
|
|
@@ -2177,7 +2535,7 @@
|
|
| 2177 |
"early_stopping_threshold": 0.0
|
| 2178 |
},
|
| 2179 |
"attributes": {
|
| 2180 |
-
"early_stopping_patience_counter":
|
| 2181 |
}
|
| 2182 |
},
|
| 2183 |
"TrainerControl": {
|
|
@@ -2191,7 +2549,7 @@
|
|
| 2191 |
"attributes": {}
|
| 2192 |
}
|
| 2193 |
},
|
| 2194 |
-
"total_flos": 4.
|
| 2195 |
"train_batch_size": 1,
|
| 2196 |
"trial_name": null,
|
| 2197 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5701812505722046,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-250",
|
| 4 |
+
"epoch": 2.564102564102564,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 350,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2163 |
"eval_samples_per_second": 7.449,
|
| 2164 |
"eval_steps_per_second": 7.449,
|
| 2165 |
"step": 300
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 2.2051282051282053,
|
| 2169 |
+
"grad_norm": 0.599308431148529,
|
| 2170 |
+
"learning_rate": 5.039532853343533e-05,
|
| 2171 |
+
"loss": 0.249,
|
| 2172 |
+
"step": 301
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 2.2124542124542126,
|
| 2176 |
+
"grad_norm": 0.7922989130020142,
|
| 2177 |
+
"learning_rate": 4.951314514232175e-05,
|
| 2178 |
+
"loss": 0.2308,
|
| 2179 |
+
"step": 302
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 2.21978021978022,
|
| 2183 |
+
"grad_norm": 0.8403403162956238,
|
| 2184 |
+
"learning_rate": 4.863722270645869e-05,
|
| 2185 |
+
"loss": 0.2293,
|
| 2186 |
+
"step": 303
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 2.227106227106227,
|
| 2190 |
+
"grad_norm": 0.8893972039222717,
|
| 2191 |
+
"learning_rate": 4.776761580125495e-05,
|
| 2192 |
+
"loss": 0.2041,
|
| 2193 |
+
"step": 304
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 2.2344322344322345,
|
| 2197 |
+
"grad_norm": 0.6155855059623718,
|
| 2198 |
+
"learning_rate": 4.690437860862234e-05,
|
| 2199 |
+
"loss": 0.1374,
|
| 2200 |
+
"step": 305
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 2.241758241758242,
|
| 2204 |
+
"grad_norm": 0.7354236245155334,
|
| 2205 |
+
"learning_rate": 4.6047564913600234e-05,
|
| 2206 |
+
"loss": 0.1482,
|
| 2207 |
+
"step": 306
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 2.249084249084249,
|
| 2211 |
+
"grad_norm": 2.1080105304718018,
|
| 2212 |
+
"learning_rate": 4.519722810100403e-05,
|
| 2213 |
+
"loss": 0.1127,
|
| 2214 |
+
"step": 307
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 2.2564102564102564,
|
| 2218 |
+
"grad_norm": 0.4302568733692169,
|
| 2219 |
+
"learning_rate": 4.435342115209916e-05,
|
| 2220 |
+
"loss": 0.5135,
|
| 2221 |
+
"step": 308
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 2.2637362637362637,
|
| 2225 |
+
"grad_norm": 0.8538389205932617,
|
| 2226 |
+
"learning_rate": 4.35161966413001e-05,
|
| 2227 |
+
"loss": 0.6252,
|
| 2228 |
+
"step": 309
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.271062271062271,
|
| 2232 |
+
"grad_norm": 0.7556006908416748,
|
| 2233 |
+
"learning_rate": 4.2685606732894316e-05,
|
| 2234 |
+
"loss": 0.4975,
|
| 2235 |
+
"step": 310
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 2.2783882783882783,
|
| 2239 |
+
"grad_norm": 0.58868408203125,
|
| 2240 |
+
"learning_rate": 4.186170317779257e-05,
|
| 2241 |
+
"loss": 0.4612,
|
| 2242 |
+
"step": 311
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 2.2857142857142856,
|
| 2246 |
+
"grad_norm": 0.7426422238349915,
|
| 2247 |
+
"learning_rate": 4.1044537310304135e-05,
|
| 2248 |
+
"loss": 0.458,
|
| 2249 |
+
"step": 312
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 2.293040293040293,
|
| 2253 |
+
"grad_norm": 0.6092411279678345,
|
| 2254 |
+
"learning_rate": 4.023416004493849e-05,
|
| 2255 |
+
"loss": 0.5098,
|
| 2256 |
+
"step": 313
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 2.3003663003663,
|
| 2260 |
+
"grad_norm": 0.6772862076759338,
|
| 2261 |
+
"learning_rate": 3.943062187323317e-05,
|
| 2262 |
+
"loss": 0.5537,
|
| 2263 |
+
"step": 314
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.3076923076923075,
|
| 2267 |
+
"grad_norm": 0.5766953229904175,
|
| 2268 |
+
"learning_rate": 3.863397286060752e-05,
|
| 2269 |
+
"loss": 0.4449,
|
| 2270 |
+
"step": 315
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.315018315018315,
|
| 2274 |
+
"grad_norm": 0.5632515549659729,
|
| 2275 |
+
"learning_rate": 3.784426264324364e-05,
|
| 2276 |
+
"loss": 0.4455,
|
| 2277 |
+
"step": 316
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 2.3223443223443225,
|
| 2281 |
+
"grad_norm": 0.4638958275318146,
|
| 2282 |
+
"learning_rate": 3.7061540424993455e-05,
|
| 2283 |
+
"loss": 0.3575,
|
| 2284 |
+
"step": 317
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 2.32967032967033,
|
| 2288 |
+
"grad_norm": 0.5185256004333496,
|
| 2289 |
+
"learning_rate": 3.628585497431319e-05,
|
| 2290 |
+
"loss": 0.4092,
|
| 2291 |
+
"step": 318
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 2.336996336996337,
|
| 2295 |
+
"grad_norm": 0.4830188751220703,
|
| 2296 |
+
"learning_rate": 3.551725462122475e-05,
|
| 2297 |
+
"loss": 0.4283,
|
| 2298 |
+
"step": 319
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 2.3443223443223444,
|
| 2302 |
+
"grad_norm": 0.5283904075622559,
|
| 2303 |
+
"learning_rate": 3.47557872543044e-05,
|
| 2304 |
+
"loss": 0.4279,
|
| 2305 |
+
"step": 320
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.3516483516483517,
|
| 2309 |
+
"grad_norm": 0.48210349678993225,
|
| 2310 |
+
"learning_rate": 3.400150031769916e-05,
|
| 2311 |
+
"loss": 0.3868,
|
| 2312 |
+
"step": 321
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.358974358974359,
|
| 2316 |
+
"grad_norm": 0.49750009179115295,
|
| 2317 |
+
"learning_rate": 3.325444080817054e-05,
|
| 2318 |
+
"loss": 0.4265,
|
| 2319 |
+
"step": 322
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 2.3663003663003663,
|
| 2323 |
+
"grad_norm": 0.5228102803230286,
|
| 2324 |
+
"learning_rate": 3.251465527216644e-05,
|
| 2325 |
+
"loss": 0.3988,
|
| 2326 |
+
"step": 323
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 2.3736263736263736,
|
| 2330 |
+
"grad_norm": 0.4787524938583374,
|
| 2331 |
+
"learning_rate": 3.178218980292116e-05,
|
| 2332 |
+
"loss": 0.4338,
|
| 2333 |
+
"step": 324
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 2.380952380952381,
|
| 2337 |
+
"grad_norm": 0.5247374773025513,
|
| 2338 |
+
"learning_rate": 3.1057090037583195e-05,
|
| 2339 |
+
"loss": 0.457,
|
| 2340 |
+
"step": 325
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 2.3882783882783882,
|
| 2344 |
+
"grad_norm": 0.49824175238609314,
|
| 2345 |
+
"learning_rate": 3.03394011543721e-05,
|
| 2346 |
+
"loss": 0.3382,
|
| 2347 |
+
"step": 326
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 2.3956043956043955,
|
| 2351 |
+
"grad_norm": 0.5834226012229919,
|
| 2352 |
+
"learning_rate": 2.9629167869763314e-05,
|
| 2353 |
+
"loss": 0.4105,
|
| 2354 |
+
"step": 327
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.402930402930403,
|
| 2358 |
+
"grad_norm": 0.5177899599075317,
|
| 2359 |
+
"learning_rate": 2.8926434435702213e-05,
|
| 2360 |
+
"loss": 0.3676,
|
| 2361 |
+
"step": 328
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.41025641025641,
|
| 2365 |
+
"grad_norm": 0.5421662926673889,
|
| 2366 |
+
"learning_rate": 2.823124463684692e-05,
|
| 2367 |
+
"loss": 0.3891,
|
| 2368 |
+
"step": 329
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.4175824175824174,
|
| 2372 |
+
"grad_norm": 0.6656437516212463,
|
| 2373 |
+
"learning_rate": 2.7543641787840137e-05,
|
| 2374 |
+
"loss": 0.4003,
|
| 2375 |
+
"step": 330
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 2.4249084249084247,
|
| 2379 |
+
"grad_norm": 0.5354308485984802,
|
| 2380 |
+
"learning_rate": 2.6863668730610628e-05,
|
| 2381 |
+
"loss": 0.334,
|
| 2382 |
+
"step": 331
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 2.4322344322344325,
|
| 2386 |
+
"grad_norm": 0.5242961049079895,
|
| 2387 |
+
"learning_rate": 2.6191367831703597e-05,
|
| 2388 |
+
"loss": 0.3575,
|
| 2389 |
+
"step": 332
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 2.4395604395604398,
|
| 2393 |
+
"grad_norm": 0.5668814182281494,
|
| 2394 |
+
"learning_rate": 2.5526780979641132e-05,
|
| 2395 |
+
"loss": 0.251,
|
| 2396 |
+
"step": 333
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.446886446886447,
|
| 2400 |
+
"grad_norm": 0.6647098064422607,
|
| 2401 |
+
"learning_rate": 2.486994958231238e-05,
|
| 2402 |
+
"loss": 0.3012,
|
| 2403 |
+
"step": 334
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 2.4542124542124544,
|
| 2407 |
+
"grad_norm": 0.590238630771637,
|
| 2408 |
+
"learning_rate": 2.422091456439338e-05,
|
| 2409 |
+
"loss": 0.2125,
|
| 2410 |
+
"step": 335
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 2.4615384615384617,
|
| 2414 |
+
"grad_norm": 0.6544525027275085,
|
| 2415 |
+
"learning_rate": 2.3579716364797406e-05,
|
| 2416 |
+
"loss": 0.2345,
|
| 2417 |
+
"step": 336
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 2.468864468864469,
|
| 2421 |
+
"grad_norm": 0.6543833017349243,
|
| 2422 |
+
"learning_rate": 2.294639493415517e-05,
|
| 2423 |
+
"loss": 0.2455,
|
| 2424 |
+
"step": 337
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 2.4761904761904763,
|
| 2428 |
+
"grad_norm": 0.8714612126350403,
|
| 2429 |
+
"learning_rate": 2.2320989732325816e-05,
|
| 2430 |
+
"loss": 0.2462,
|
| 2431 |
+
"step": 338
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.4835164835164836,
|
| 2435 |
+
"grad_norm": 0.8587841391563416,
|
| 2436 |
+
"learning_rate": 2.170353972593825e-05,
|
| 2437 |
+
"loss": 0.1519,
|
| 2438 |
+
"step": 339
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.490842490842491,
|
| 2442 |
+
"grad_norm": 0.6549997329711914,
|
| 2443 |
+
"learning_rate": 2.1094083385963202e-05,
|
| 2444 |
+
"loss": 0.1206,
|
| 2445 |
+
"step": 340
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.498168498168498,
|
| 2449 |
+
"grad_norm": 0.5828280448913574,
|
| 2450 |
+
"learning_rate": 2.049265868531651e-05,
|
| 2451 |
+
"loss": 0.0964,
|
| 2452 |
+
"step": 341
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.5054945054945055,
|
| 2456 |
+
"grad_norm": 0.29954391717910767,
|
| 2457 |
+
"learning_rate": 1.989930309649282e-05,
|
| 2458 |
+
"loss": 0.4719,
|
| 2459 |
+
"step": 342
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 2.5128205128205128,
|
| 2463 |
+
"grad_norm": 0.41014474630355835,
|
| 2464 |
+
"learning_rate": 1.9314053589231067e-05,
|
| 2465 |
+
"loss": 0.5926,
|
| 2466 |
+
"step": 343
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 2.52014652014652,
|
| 2470 |
+
"grad_norm": 0.42200765013694763,
|
| 2471 |
+
"learning_rate": 1.873694662821096e-05,
|
| 2472 |
+
"loss": 0.5305,
|
| 2473 |
+
"step": 344
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 2.5274725274725274,
|
| 2477 |
+
"grad_norm": 0.4672837257385254,
|
| 2478 |
+
"learning_rate": 1.816801817078093e-05,
|
| 2479 |
+
"loss": 0.5177,
|
| 2480 |
+
"step": 345
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.5347985347985347,
|
| 2484 |
+
"grad_norm": 0.45549672842025757,
|
| 2485 |
+
"learning_rate": 1.760730366471796e-05,
|
| 2486 |
+
"loss": 0.4906,
|
| 2487 |
+
"step": 346
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 2.542124542124542,
|
| 2491 |
+
"grad_norm": 0.42634275555610657,
|
| 2492 |
+
"learning_rate": 1.705483804601871e-05,
|
| 2493 |
+
"loss": 0.4466,
|
| 2494 |
+
"step": 347
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.5494505494505493,
|
| 2498 |
+
"grad_norm": 0.5157731175422668,
|
| 2499 |
+
"learning_rate": 1.6510655736722967e-05,
|
| 2500 |
+
"loss": 0.5153,
|
| 2501 |
+
"step": 348
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 2.5567765567765566,
|
| 2505 |
+
"grad_norm": 0.6015162467956543,
|
| 2506 |
+
"learning_rate": 1.5974790642768903e-05,
|
| 2507 |
+
"loss": 0.4401,
|
| 2508 |
+
"step": 349
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 2.564102564102564,
|
| 2512 |
+
"grad_norm": 0.5981739163398743,
|
| 2513 |
+
"learning_rate": 1.5447276151880473e-05,
|
| 2514 |
+
"loss": 0.5157,
|
| 2515 |
+
"step": 350
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 2.564102564102564,
|
| 2519 |
+
"eval_loss": 0.6206538081169128,
|
| 2520 |
+
"eval_runtime": 73.5137,
|
| 2521 |
+
"eval_samples_per_second": 7.441,
|
| 2522 |
+
"eval_steps_per_second": 7.441,
|
| 2523 |
+
"step": 350
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 1,
|
|
|
|
| 2535 |
"early_stopping_threshold": 0.0
|
| 2536 |
},
|
| 2537 |
"attributes": {
|
| 2538 |
+
"early_stopping_patience_counter": 2
|
| 2539 |
}
|
| 2540 |
},
|
| 2541 |
"TrainerControl": {
|
|
|
|
| 2549 |
"attributes": {}
|
| 2550 |
}
|
| 2551 |
},
|
| 2552 |
+
"total_flos": 4.957792987250688e+16,
|
| 2553 |
"train_batch_size": 1,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|