Training in progress, step 32000, 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 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc3c5b4f1c32d282710a153ae5bf5ca6bd7cbd3f4f67f12a3907a6cd19d2d279
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:605c9b21acde75c1394f97c25a318d3192f035d829b96871f4ced0b57206ec1c
|
| 3 |
size 938825803
|
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 sha256:6177091d3805fe7255fbeea64136d688b15629fc946401f1853fbd6e6a2f18ad
|
| 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 sha256:30eae1c116a1408bbe4aec95a1368b13c0bf69d349ca373bf4a8fd3a1e9fc110
|
| 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": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2192,6 +2192,318 @@
|
|
| 2192 |
"eval_samples_per_second": 84.778,
|
| 2193 |
"eval_steps_per_second": 21.195,
|
| 2194 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2195 |
}
|
| 2196 |
],
|
| 2197 |
"logging_steps": 100,
|
|
@@ -2211,7 +2523,7 @@
|
|
| 2211 |
"attributes": {}
|
| 2212 |
}
|
| 2213 |
},
|
| 2214 |
-
"total_flos":
|
| 2215 |
"train_batch_size": 22,
|
| 2216 |
"trial_name": null,
|
| 2217 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.2909090909090909,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 32000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2192 |
"eval_samples_per_second": 84.778,
|
| 2193 |
"eval_steps_per_second": 21.195,
|
| 2194 |
"step": 28000
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.25545454545454543,
|
| 2198 |
+
"grad_norm": 0.1713736206293106,
|
| 2199 |
+
"learning_rate": 0.0008486002062601203,
|
| 2200 |
+
"loss": 2.8171258544921876,
|
| 2201 |
+
"step": 28100
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.25636363636363635,
|
| 2205 |
+
"grad_norm": 0.18038378655910492,
|
| 2206 |
+
"learning_rate": 0.000847573687285321,
|
| 2207 |
+
"loss": 2.8066680908203123,
|
| 2208 |
+
"step": 28200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.25727272727272726,
|
| 2212 |
+
"grad_norm": 0.1601206362247467,
|
| 2213 |
+
"learning_rate": 0.0008465443255111025,
|
| 2214 |
+
"loss": 2.8091595458984373,
|
| 2215 |
+
"step": 28300
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.2581818181818182,
|
| 2219 |
+
"grad_norm": 0.15122343599796295,
|
| 2220 |
+
"learning_rate": 0.0008455121293565974,
|
| 2221 |
+
"loss": 2.8354150390625,
|
| 2222 |
+
"step": 28400
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.2590909090909091,
|
| 2226 |
+
"grad_norm": 0.1411023885011673,
|
| 2227 |
+
"learning_rate": 0.000844477107264121,
|
| 2228 |
+
"loss": 2.805926513671875,
|
| 2229 |
+
"step": 28500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.26,
|
| 2233 |
+
"grad_norm": 0.1714688241481781,
|
| 2234 |
+
"learning_rate": 0.0008434392676991018,
|
| 2235 |
+
"loss": 2.774625244140625,
|
| 2236 |
+
"step": 28600
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.2609090909090909,
|
| 2240 |
+
"grad_norm": 0.14336396753787994,
|
| 2241 |
+
"learning_rate": 0.0008423986191500126,
|
| 2242 |
+
"loss": 2.806527099609375,
|
| 2243 |
+
"step": 28700
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.26181818181818184,
|
| 2247 |
+
"grad_norm": 0.14724823832511902,
|
| 2248 |
+
"learning_rate": 0.0008413551701283003,
|
| 2249 |
+
"loss": 2.7858685302734374,
|
| 2250 |
+
"step": 28800
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.26272727272727275,
|
| 2254 |
+
"grad_norm": 0.1667833775281906,
|
| 2255 |
+
"learning_rate": 0.0008403089291683173,
|
| 2256 |
+
"loss": 2.788014221191406,
|
| 2257 |
+
"step": 28900
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.2636363636363636,
|
| 2261 |
+
"grad_norm": 0.13815470039844513,
|
| 2262 |
+
"learning_rate": 0.0008392599048272509,
|
| 2263 |
+
"loss": 2.7937637329101563,
|
| 2264 |
+
"step": 29000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.2636363636363636,
|
| 2268 |
+
"eval_loss": 3.1548070907592773,
|
| 2269 |
+
"eval_runtime": 6.8019,
|
| 2270 |
+
"eval_samples_per_second": 84.682,
|
| 2271 |
+
"eval_steps_per_second": 21.171,
|
| 2272 |
+
"step": 29000
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 0.26454545454545453,
|
| 2276 |
+
"grad_norm": 0.1442345827817917,
|
| 2277 |
+
"learning_rate": 0.0008382081056850541,
|
| 2278 |
+
"loss": 2.77263671875,
|
| 2279 |
+
"step": 29100
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 0.26545454545454544,
|
| 2283 |
+
"grad_norm": 0.14780735969543457,
|
| 2284 |
+
"learning_rate": 0.0008371535403443743,
|
| 2285 |
+
"loss": 2.8082760620117186,
|
| 2286 |
+
"step": 29200
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.26636363636363636,
|
| 2290 |
+
"grad_norm": 0.13575103878974915,
|
| 2291 |
+
"learning_rate": 0.000836096217430484,
|
| 2292 |
+
"loss": 2.7685586547851564,
|
| 2293 |
+
"step": 29300
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 0.2672727272727273,
|
| 2297 |
+
"grad_norm": 0.131728395819664,
|
| 2298 |
+
"learning_rate": 0.0008350361455912099,
|
| 2299 |
+
"loss": 2.771170349121094,
|
| 2300 |
+
"step": 29400
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.2681818181818182,
|
| 2304 |
+
"grad_norm": 0.18209482729434967,
|
| 2305 |
+
"learning_rate": 0.0008339733334968619,
|
| 2306 |
+
"loss": 2.7749264526367186,
|
| 2307 |
+
"step": 29500
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.2690909090909091,
|
| 2311 |
+
"grad_norm": 0.14567936956882477,
|
| 2312 |
+
"learning_rate": 0.0008329077898401624,
|
| 2313 |
+
"loss": 2.8004241943359376,
|
| 2314 |
+
"step": 29600
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.27,
|
| 2318 |
+
"grad_norm": 0.1705045998096466,
|
| 2319 |
+
"learning_rate": 0.0008318395233361753,
|
| 2320 |
+
"loss": 2.8070437622070314,
|
| 2321 |
+
"step": 29700
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.27090909090909093,
|
| 2325 |
+
"grad_norm": 0.1700645238161087,
|
| 2326 |
+
"learning_rate": 0.0008307685427222345,
|
| 2327 |
+
"loss": 2.769403991699219,
|
| 2328 |
+
"step": 29800
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.2718181818181818,
|
| 2332 |
+
"grad_norm": 0.2213045209646225,
|
| 2333 |
+
"learning_rate": 0.000829694856757873,
|
| 2334 |
+
"loss": 2.75067138671875,
|
| 2335 |
+
"step": 29900
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.2727272727272727,
|
| 2339 |
+
"grad_norm": 0.1627679318189621,
|
| 2340 |
+
"learning_rate": 0.0008286184742247502,
|
| 2341 |
+
"loss": 2.782334899902344,
|
| 2342 |
+
"step": 30000
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.2727272727272727,
|
| 2346 |
+
"eval_loss": 3.1495797634124756,
|
| 2347 |
+
"eval_runtime": 6.8699,
|
| 2348 |
+
"eval_samples_per_second": 83.844,
|
| 2349 |
+
"eval_steps_per_second": 20.961,
|
| 2350 |
+
"step": 30000
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.2736363636363636,
|
| 2354 |
+
"grad_norm": 0.1445474475622177,
|
| 2355 |
+
"learning_rate": 0.0008275394039265813,
|
| 2356 |
+
"loss": 2.80556396484375,
|
| 2357 |
+
"step": 30100
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.27454545454545454,
|
| 2361 |
+
"grad_norm": 0.14685708284378052,
|
| 2362 |
+
"learning_rate": 0.0008264576546890639,
|
| 2363 |
+
"loss": 2.776888732910156,
|
| 2364 |
+
"step": 30200
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.27545454545454545,
|
| 2368 |
+
"grad_norm": 0.1347658634185791,
|
| 2369 |
+
"learning_rate": 0.0008253732353598072,
|
| 2370 |
+
"loss": 2.7627569580078126,
|
| 2371 |
+
"step": 30300
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.27636363636363637,
|
| 2375 |
+
"grad_norm": 0.13901016116142273,
|
| 2376 |
+
"learning_rate": 0.0008242861548082591,
|
| 2377 |
+
"loss": 2.780741882324219,
|
| 2378 |
+
"step": 30400
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.2772727272727273,
|
| 2382 |
+
"grad_norm": 0.13585121929645538,
|
| 2383 |
+
"learning_rate": 0.0008231964219256331,
|
| 2384 |
+
"loss": 2.804005432128906,
|
| 2385 |
+
"step": 30500
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.2781818181818182,
|
| 2389 |
+
"grad_norm": 0.15015123784542084,
|
| 2390 |
+
"learning_rate": 0.0008221040456248367,
|
| 2391 |
+
"loss": 2.7642987060546873,
|
| 2392 |
+
"step": 30600
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.2790909090909091,
|
| 2396 |
+
"grad_norm": 0.13883176445960999,
|
| 2397 |
+
"learning_rate": 0.0008210090348403973,
|
| 2398 |
+
"loss": 2.79775146484375,
|
| 2399 |
+
"step": 30700
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.28,
|
| 2403 |
+
"grad_norm": 0.1524442732334137,
|
| 2404 |
+
"learning_rate": 0.0008199113985283902,
|
| 2405 |
+
"loss": 2.7866134643554688,
|
| 2406 |
+
"step": 30800
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.2809090909090909,
|
| 2410 |
+
"grad_norm": 0.14497579634189606,
|
| 2411 |
+
"learning_rate": 0.0008188111456663641,
|
| 2412 |
+
"loss": 2.770282897949219,
|
| 2413 |
+
"step": 30900
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.2818181818181818,
|
| 2417 |
+
"grad_norm": 0.1663127839565277,
|
| 2418 |
+
"learning_rate": 0.0008177082852532691,
|
| 2419 |
+
"loss": 2.7479037475585937,
|
| 2420 |
+
"step": 31000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.2818181818181818,
|
| 2424 |
+
"eval_loss": 3.1455507278442383,
|
| 2425 |
+
"eval_runtime": 6.8464,
|
| 2426 |
+
"eval_samples_per_second": 84.131,
|
| 2427 |
+
"eval_steps_per_second": 21.033,
|
| 2428 |
+
"step": 31000
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 0.2827272727272727,
|
| 2432 |
+
"grad_norm": 0.3059700131416321,
|
| 2433 |
+
"learning_rate": 0.0008166028263093825,
|
| 2434 |
+
"loss": 2.786407775878906,
|
| 2435 |
+
"step": 31100
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.28363636363636363,
|
| 2439 |
+
"grad_norm": 0.1757507622241974,
|
| 2440 |
+
"learning_rate": 0.0008154947778762343,
|
| 2441 |
+
"loss": 2.7669387817382813,
|
| 2442 |
+
"step": 31200
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.28454545454545455,
|
| 2446 |
+
"grad_norm": 0.1763867884874344,
|
| 2447 |
+
"learning_rate": 0.0008143841490165344,
|
| 2448 |
+
"loss": 2.763365478515625,
|
| 2449 |
+
"step": 31300
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.28545454545454546,
|
| 2453 |
+
"grad_norm": 0.1497093141078949,
|
| 2454 |
+
"learning_rate": 0.0008132709488140977,
|
| 2455 |
+
"loss": 2.7558905029296876,
|
| 2456 |
+
"step": 31400
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.2863636363636364,
|
| 2460 |
+
"grad_norm": 0.15906350314617157,
|
| 2461 |
+
"learning_rate": 0.0008121551863737704,
|
| 2462 |
+
"loss": 2.7421307373046875,
|
| 2463 |
+
"step": 31500
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 0.2872727272727273,
|
| 2467 |
+
"grad_norm": 0.14353445172309875,
|
| 2468 |
+
"learning_rate": 0.0008110368708213548,
|
| 2469 |
+
"loss": 2.7798092651367186,
|
| 2470 |
+
"step": 31600
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 0.2881818181818182,
|
| 2474 |
+
"grad_norm": 0.1670762598514557,
|
| 2475 |
+
"learning_rate": 0.0008099160113035353,
|
| 2476 |
+
"loss": 2.764653625488281,
|
| 2477 |
+
"step": 31700
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 0.28909090909090907,
|
| 2481 |
+
"grad_norm": 0.15554283559322357,
|
| 2482 |
+
"learning_rate": 0.000808792616987803,
|
| 2483 |
+
"loss": 2.76354736328125,
|
| 2484 |
+
"step": 31800
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.29,
|
| 2488 |
+
"grad_norm": 0.14061635732650757,
|
| 2489 |
+
"learning_rate": 0.0008076666970623821,
|
| 2490 |
+
"loss": 2.764184875488281,
|
| 2491 |
+
"step": 31900
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.2909090909090909,
|
| 2495 |
+
"grad_norm": 0.18086077272891998,
|
| 2496 |
+
"learning_rate": 0.0008065382607361523,
|
| 2497 |
+
"loss": 2.7778125,
|
| 2498 |
+
"step": 32000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.2909090909090909,
|
| 2502 |
+
"eval_loss": 3.1462559700012207,
|
| 2503 |
+
"eval_runtime": 6.8321,
|
| 2504 |
+
"eval_samples_per_second": 84.308,
|
| 2505 |
+
"eval_steps_per_second": 21.077,
|
| 2506 |
+
"step": 32000
|
| 2507 |
}
|
| 2508 |
],
|
| 2509 |
"logging_steps": 100,
|
|
|
|
| 2523 |
"attributes": {}
|
| 2524 |
}
|
| 2525 |
},
|
| 2526 |
+
"total_flos": 7.97266591875072e+17,
|
| 2527 |
"train_batch_size": 22,
|
| 2528 |
"trial_name": null,
|
| 2529 |
"trial_params": null
|