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 541154336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fea0a0b88a8852aec2382a6400435ae84bbfcb52cd14372fe08dab6f5a9b181
|
| 3 |
size 541154336
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1082379659
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bbb61cfa227633b44a69a3c624c1b0dbf80db3ba79898d7b764dc31de1163ee
|
| 3 |
size 1082379659
|
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 sha256:428aed83766f09a6a2d9ccfb86972eeda646225b3b0cd6accec4a90e4f900161
|
| 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 sha256:35deceb007dc05c0a67e4f7d57b32921e37176fa5a3cb5bba0983b1b73cb3efc
|
| 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": 36.109,
|
| 2193 |
"eval_steps_per_second": 9.027,
|
| 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": 0.4155844155844156,
|
| 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": 36.109,
|
| 2193 |
"eval_steps_per_second": 9.027,
|
| 2194 |
"step": 28000
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.36493506493506495,
|
| 2198 |
+
"grad_norm": 0.20181582868099213,
|
| 2199 |
+
"learning_rate": 0.00085546987355325,
|
| 2200 |
+
"loss": 2.835,
|
| 2201 |
+
"step": 28100
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.36623376623376624,
|
| 2205 |
+
"grad_norm": 0.1909325122833252,
|
| 2206 |
+
"learning_rate": 0.0008544544759847112,
|
| 2207 |
+
"loss": 2.8291,
|
| 2208 |
+
"step": 28200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.36753246753246754,
|
| 2212 |
+
"grad_norm": 0.21319599449634552,
|
| 2213 |
+
"learning_rate": 0.000853436131244459,
|
| 2214 |
+
"loss": 2.8536,
|
| 2215 |
+
"step": 28300
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.36883116883116884,
|
| 2219 |
+
"grad_norm": 0.200112447142601,
|
| 2220 |
+
"learning_rate": 0.0008524148477996933,
|
| 2221 |
+
"loss": 2.8732,
|
| 2222 |
+
"step": 28400
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.37012987012987014,
|
| 2226 |
+
"grad_norm": 0.19826772809028625,
|
| 2227 |
+
"learning_rate": 0.0008513906341420478,
|
| 2228 |
+
"loss": 2.8208,
|
| 2229 |
+
"step": 28500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.37142857142857144,
|
| 2233 |
+
"grad_norm": 0.21064135432243347,
|
| 2234 |
+
"learning_rate": 0.0008503634987875206,
|
| 2235 |
+
"loss": 2.805,
|
| 2236 |
+
"step": 28600
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.37272727272727274,
|
| 2240 |
+
"grad_norm": 0.2014266848564148,
|
| 2241 |
+
"learning_rate": 0.0008493334502764021,
|
| 2242 |
+
"loss": 2.8257,
|
| 2243 |
+
"step": 28700
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.37402597402597404,
|
| 2247 |
+
"grad_norm": 0.21088480949401855,
|
| 2248 |
+
"learning_rate": 0.0008483004971732049,
|
| 2249 |
+
"loss": 2.8261,
|
| 2250 |
+
"step": 28800
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.37532467532467534,
|
| 2254 |
+
"grad_norm": 0.20050457119941711,
|
| 2255 |
+
"learning_rate": 0.0008472646480665924,
|
| 2256 |
+
"loss": 2.8694,
|
| 2257 |
+
"step": 28900
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.37662337662337664,
|
| 2261 |
+
"grad_norm": 0.21420925855636597,
|
| 2262 |
+
"learning_rate": 0.0008462259115693076,
|
| 2263 |
+
"loss": 2.8473,
|
| 2264 |
+
"step": 29000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.37662337662337664,
|
| 2268 |
+
"eval_loss": 3.195821523666382,
|
| 2269 |
+
"eval_runtime": 15.2121,
|
| 2270 |
+
"eval_samples_per_second": 37.865,
|
| 2271 |
+
"eval_steps_per_second": 9.466,
|
| 2272 |
+
"step": 29000
|
| 2273 |
+
},
|
| 2274 |
+
{
|
| 2275 |
+
"epoch": 0.37792207792207794,
|
| 2276 |
+
"grad_norm": 0.2159246951341629,
|
| 2277 |
+
"learning_rate": 0.0008451842963181003,
|
| 2278 |
+
"loss": 2.8032,
|
| 2279 |
+
"step": 29100
|
| 2280 |
+
},
|
| 2281 |
+
{
|
| 2282 |
+
"epoch": 0.37922077922077924,
|
| 2283 |
+
"grad_norm": 0.19643986225128174,
|
| 2284 |
+
"learning_rate": 0.0008441398109736571,
|
| 2285 |
+
"loss": 2.847,
|
| 2286 |
+
"step": 29200
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 0.38051948051948054,
|
| 2290 |
+
"grad_norm": 0.1965179294347763,
|
| 2291 |
+
"learning_rate": 0.0008430924642205279,
|
| 2292 |
+
"loss": 2.8529,
|
| 2293 |
+
"step": 29300
|
| 2294 |
+
},
|
| 2295 |
+
{
|
| 2296 |
+
"epoch": 0.38181818181818183,
|
| 2297 |
+
"grad_norm": 0.21244043111801147,
|
| 2298 |
+
"learning_rate": 0.0008420422647670548,
|
| 2299 |
+
"loss": 2.8067,
|
| 2300 |
+
"step": 29400
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.38311688311688313,
|
| 2304 |
+
"grad_norm": 0.20399615168571472,
|
| 2305 |
+
"learning_rate": 0.0008409892213452987,
|
| 2306 |
+
"loss": 2.8176,
|
| 2307 |
+
"step": 29500
|
| 2308 |
+
},
|
| 2309 |
+
{
|
| 2310 |
+
"epoch": 0.38441558441558443,
|
| 2311 |
+
"grad_norm": 0.20329082012176514,
|
| 2312 |
+
"learning_rate": 0.0008399333427109672,
|
| 2313 |
+
"loss": 2.8316,
|
| 2314 |
+
"step": 29600
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 0.38571428571428573,
|
| 2318 |
+
"grad_norm": 0.19244763255119324,
|
| 2319 |
+
"learning_rate": 0.0008388746376433419,
|
| 2320 |
+
"loss": 2.8367,
|
| 2321 |
+
"step": 29700
|
| 2322 |
+
},
|
| 2323 |
+
{
|
| 2324 |
+
"epoch": 0.38701298701298703,
|
| 2325 |
+
"grad_norm": 0.18999354541301727,
|
| 2326 |
+
"learning_rate": 0.0008378131149452053,
|
| 2327 |
+
"loss": 2.8212,
|
| 2328 |
+
"step": 29800
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 0.38831168831168833,
|
| 2332 |
+
"grad_norm": 0.20788761973381042,
|
| 2333 |
+
"learning_rate": 0.0008367487834427674,
|
| 2334 |
+
"loss": 2.7999,
|
| 2335 |
+
"step": 29900
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 0.38961038961038963,
|
| 2339 |
+
"grad_norm": 0.21678058803081512,
|
| 2340 |
+
"learning_rate": 0.0008356816519855926,
|
| 2341 |
+
"loss": 2.81,
|
| 2342 |
+
"step": 30000
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.38961038961038963,
|
| 2346 |
+
"eval_loss": 3.1891965866088867,
|
| 2347 |
+
"eval_runtime": 15.5166,
|
| 2348 |
+
"eval_samples_per_second": 37.122,
|
| 2349 |
+
"eval_steps_per_second": 9.28,
|
| 2350 |
+
"step": 30000
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.39090909090909093,
|
| 2354 |
+
"grad_norm": 0.25863537192344666,
|
| 2355 |
+
"learning_rate": 0.0008346117294465258,
|
| 2356 |
+
"loss": 2.7919,
|
| 2357 |
+
"step": 30100
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.3922077922077922,
|
| 2361 |
+
"grad_norm": 0.2082231491804123,
|
| 2362 |
+
"learning_rate": 0.0008335390247216193,
|
| 2363 |
+
"loss": 2.8058,
|
| 2364 |
+
"step": 30200
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.3935064935064935,
|
| 2368 |
+
"grad_norm": 0.2484658658504486,
|
| 2369 |
+
"learning_rate": 0.0008324635467300578,
|
| 2370 |
+
"loss": 2.7913,
|
| 2371 |
+
"step": 30300
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.3948051948051948,
|
| 2375 |
+
"grad_norm": 0.19809049367904663,
|
| 2376 |
+
"learning_rate": 0.000831385304414085,
|
| 2377 |
+
"loss": 2.8392,
|
| 2378 |
+
"step": 30400
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.3961038961038961,
|
| 2382 |
+
"grad_norm": 0.19220763444900513,
|
| 2383 |
+
"learning_rate": 0.0008303043067389293,
|
| 2384 |
+
"loss": 2.8326,
|
| 2385 |
+
"step": 30500
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.3974025974025974,
|
| 2389 |
+
"grad_norm": 0.19120201468467712,
|
| 2390 |
+
"learning_rate": 0.0008292205626927285,
|
| 2391 |
+
"loss": 2.8008,
|
| 2392 |
+
"step": 30600
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.3987012987012987,
|
| 2396 |
+
"grad_norm": 0.2093675136566162,
|
| 2397 |
+
"learning_rate": 0.000828134081286456,
|
| 2398 |
+
"loss": 2.8228,
|
| 2399 |
+
"step": 30700
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.4,
|
| 2403 |
+
"grad_norm": 0.2077227681875229,
|
| 2404 |
+
"learning_rate": 0.0008270448715538452,
|
| 2405 |
+
"loss": 2.8263,
|
| 2406 |
+
"step": 30800
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.4012987012987013,
|
| 2410 |
+
"grad_norm": 0.2050541490316391,
|
| 2411 |
+
"learning_rate": 0.0008259529425513148,
|
| 2412 |
+
"loss": 2.8289,
|
| 2413 |
+
"step": 30900
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.4025974025974026,
|
| 2417 |
+
"grad_norm": 0.19998504221439362,
|
| 2418 |
+
"learning_rate": 0.0008248583033578932,
|
| 2419 |
+
"loss": 2.8068,
|
| 2420 |
+
"step": 31000
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.4025974025974026,
|
| 2424 |
+
"eval_loss": 3.1833224296569824,
|
| 2425 |
+
"eval_runtime": 11.0521,
|
| 2426 |
+
"eval_samples_per_second": 52.117,
|
| 2427 |
+
"eval_steps_per_second": 13.029,
|
| 2428 |
+
"step": 31000
|
| 2429 |
+
},
|
| 2430 |
+
{
|
| 2431 |
+
"epoch": 0.4038961038961039,
|
| 2432 |
+
"grad_norm": 0.20032985508441925,
|
| 2433 |
+
"learning_rate": 0.0008237609630751433,
|
| 2434 |
+
"loss": 2.8321,
|
| 2435 |
+
"step": 31100
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 0.4051948051948052,
|
| 2439 |
+
"grad_norm": 0.2228243052959442,
|
| 2440 |
+
"learning_rate": 0.0008226609308270862,
|
| 2441 |
+
"loss": 2.8323,
|
| 2442 |
+
"step": 31200
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 0.4064935064935065,
|
| 2446 |
+
"grad_norm": 0.22431324422359467,
|
| 2447 |
+
"learning_rate": 0.0008215582157601267,
|
| 2448 |
+
"loss": 2.8489,
|
| 2449 |
+
"step": 31300
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 0.4077922077922078,
|
| 2453 |
+
"grad_norm": 0.20516513288021088,
|
| 2454 |
+
"learning_rate": 0.0008204528270429752,
|
| 2455 |
+
"loss": 2.8001,
|
| 2456 |
+
"step": 31400
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 0.4090909090909091,
|
| 2460 |
+
"grad_norm": 0.20168229937553406,
|
| 2461 |
+
"learning_rate": 0.0008193447738665735,
|
| 2462 |
+
"loss": 2.8463,
|
| 2463 |
+
"step": 31500
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 0.4103896103896104,
|
| 2467 |
+
"grad_norm": 0.20102174580097198,
|
| 2468 |
+
"learning_rate": 0.0008182340654440173,
|
| 2469 |
+
"loss": 2.8226,
|
| 2470 |
+
"step": 31600
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 0.4116883116883117,
|
| 2474 |
+
"grad_norm": 0.2369510680437088,
|
| 2475 |
+
"learning_rate": 0.0008171207110104797,
|
| 2476 |
+
"loss": 2.8284,
|
| 2477 |
+
"step": 31700
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 0.412987012987013,
|
| 2481 |
+
"grad_norm": 0.18998616933822632,
|
| 2482 |
+
"learning_rate": 0.0008160047198231344,
|
| 2483 |
+
"loss": 2.8506,
|
| 2484 |
+
"step": 31800
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 0.4142857142857143,
|
| 2488 |
+
"grad_norm": 0.21406228840351105,
|
| 2489 |
+
"learning_rate": 0.000814886101161079,
|
| 2490 |
+
"loss": 2.81,
|
| 2491 |
+
"step": 31900
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 0.4155844155844156,
|
| 2495 |
+
"grad_norm": 0.20903189480304718,
|
| 2496 |
+
"learning_rate": 0.0008137648643252575,
|
| 2497 |
+
"loss": 2.7976,
|
| 2498 |
+
"step": 32000
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 0.4155844155844156,
|
| 2502 |
+
"eval_loss": 3.1785833835601807,
|
| 2503 |
+
"eval_runtime": 15.2674,
|
| 2504 |
+
"eval_samples_per_second": 37.727,
|
| 2505 |
+
"eval_steps_per_second": 9.432,
|
| 2506 |
+
"step": 32000
|
| 2507 |
}
|
| 2508 |
],
|
| 2509 |
"logging_steps": 100,
|
|
|
|
| 2523 |
"attributes": {}
|
| 2524 |
}
|
| 2525 |
},
|
| 2526 |
+
"total_flos": 9.5261804199936e+17,
|
| 2527 |
"train_batch_size": 22,
|
| 2528 |
"trial_name": null,
|
| 2529 |
"trial_params": null
|