Training in progress, step 80000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +303 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 100172997
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61757e92d02b06dda1da003da57fa0b18bc1cc2b413fc514841b017d0d63c3c8
|
| 3 |
size 100172997
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a90871ae24751a566fb99821bee5e29d062c303c164fcd6aeac08948cab240
|
| 3 |
size 146774203
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7978600af4170dc4592efcab1d33d1582d45b26dc998a10a280a81e23e422deb
|
| 3 |
size 14503
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246899880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7331ea7e49edb5d8c1485934eca953ca913987924fdd220c26d2fc895357dc9
|
| 3 |
size 246899880
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2106,11 +2106,311 @@
|
|
| 2106 |
"learning_rate": 0.00046983100340983056,
|
| 2107 |
"loss": 3.2461,
|
| 2108 |
"step": 70000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2109 |
}
|
| 2110 |
],
|
| 2111 |
"max_steps": 500000,
|
| 2112 |
"num_train_epochs": 3,
|
| 2113 |
-
"total_flos": 1.
|
| 2114 |
"trial_name": null,
|
| 2115 |
"trial_params": null
|
| 2116 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3437902879243661,
|
| 5 |
+
"global_step": 80000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2106 |
"learning_rate": 0.00046983100340983056,
|
| 2107 |
"loss": 3.2461,
|
| 2108 |
"step": 70000
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.3,
|
| 2112 |
+
"learning_rate": 0.00047183105799939297,
|
| 2113 |
+
"loss": 3.2495,
|
| 2114 |
+
"step": 70200
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 0.3,
|
| 2118 |
+
"learning_rate": 0.0004738319577694809,
|
| 2119 |
+
"loss": 3.2325,
|
| 2120 |
+
"step": 70400
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 0.3,
|
| 2124 |
+
"learning_rate": 0.0004758336676119636,
|
| 2125 |
+
"loss": 3.2335,
|
| 2126 |
+
"step": 70600
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 0.3,
|
| 2130 |
+
"learning_rate": 0.0004778361524044967,
|
| 2131 |
+
"loss": 3.2499,
|
| 2132 |
+
"step": 70800
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 0.31,
|
| 2136 |
+
"learning_rate": 0.00047983937701113794,
|
| 2137 |
+
"loss": 3.2323,
|
| 2138 |
+
"step": 71000
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.31,
|
| 2142 |
+
"learning_rate": 0.00048184330628296484,
|
| 2143 |
+
"loss": 3.221,
|
| 2144 |
+
"step": 71200
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.31,
|
| 2148 |
+
"learning_rate": 0.0004838479050586898,
|
| 2149 |
+
"loss": 3.2344,
|
| 2150 |
+
"step": 71400
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.31,
|
| 2154 |
+
"learning_rate": 0.0004858531381652792,
|
| 2155 |
+
"loss": 3.241,
|
| 2156 |
+
"step": 71600
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 0.31,
|
| 2160 |
+
"learning_rate": 0.0004878589704185682,
|
| 2161 |
+
"loss": 3.2434,
|
| 2162 |
+
"step": 71800
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 0.31,
|
| 2166 |
+
"learning_rate": 0.00048986536662388,
|
| 2167 |
+
"loss": 3.2375,
|
| 2168 |
+
"step": 72000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 0.31,
|
| 2172 |
+
"learning_rate": 0.0004918722915766426,
|
| 2173 |
+
"loss": 3.2237,
|
| 2174 |
+
"step": 72200
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 0.31,
|
| 2178 |
+
"learning_rate": 0.0004938797100630057,
|
| 2179 |
+
"loss": 3.2665,
|
| 2180 |
+
"step": 72400
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.31,
|
| 2184 |
+
"learning_rate": 0.0004958875868604602,
|
| 2185 |
+
"loss": 3.218,
|
| 2186 |
+
"step": 72600
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.31,
|
| 2190 |
+
"learning_rate": 0.0004978958867384551,
|
| 2191 |
+
"loss": 3.2474,
|
| 2192 |
+
"step": 72800
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 0.31,
|
| 2196 |
+
"learning_rate": 0.000499904574459016,
|
| 2197 |
+
"loss": 3.2423,
|
| 2198 |
+
"step": 73000
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 0.31,
|
| 2202 |
+
"learning_rate": 0.000501913614777363,
|
| 2203 |
+
"loss": 3.2288,
|
| 2204 |
+
"step": 73200
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 0.32,
|
| 2208 |
+
"learning_rate": 0.0005039229724425303,
|
| 2209 |
+
"loss": 3.2148,
|
| 2210 |
+
"step": 73400
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.32,
|
| 2214 |
+
"learning_rate": 0.0005059326121979831,
|
| 2215 |
+
"loss": 3.2383,
|
| 2216 |
+
"step": 73600
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.32,
|
| 2220 |
+
"learning_rate": 0.0005079424987822374,
|
| 2221 |
+
"loss": 3.236,
|
| 2222 |
+
"step": 73800
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.32,
|
| 2226 |
+
"learning_rate": 0.0005099525969294778,
|
| 2227 |
+
"loss": 3.2231,
|
| 2228 |
+
"step": 74000
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.32,
|
| 2232 |
+
"learning_rate": 0.0005119628713701773,
|
| 2233 |
+
"loss": 3.2215,
|
| 2234 |
+
"step": 74200
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.32,
|
| 2238 |
+
"learning_rate": 0.0005139732868317155,
|
| 2239 |
+
"loss": 3.227,
|
| 2240 |
+
"step": 74400
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 0.32,
|
| 2244 |
+
"learning_rate": 0.0005159838080389977,
|
| 2245 |
+
"loss": 3.2006,
|
| 2246 |
+
"step": 74600
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 0.32,
|
| 2250 |
+
"learning_rate": 0.0005179943997150736,
|
| 2251 |
+
"loss": 3.2426,
|
| 2252 |
+
"step": 74800
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.32,
|
| 2256 |
+
"learning_rate": 0.0005200050265817561,
|
| 2257 |
+
"loss": 3.2194,
|
| 2258 |
+
"step": 75000
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 0.32,
|
| 2262 |
+
"learning_rate": 0.0005220156533602416,
|
| 2263 |
+
"loss": 3.223,
|
| 2264 |
+
"step": 75200
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.32,
|
| 2268 |
+
"learning_rate": 0.0005240262447717271,
|
| 2269 |
+
"loss": 3.224,
|
| 2270 |
+
"step": 75400
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.32,
|
| 2274 |
+
"learning_rate": 0.0005260367655380307,
|
| 2275 |
+
"loss": 3.2138,
|
| 2276 |
+
"step": 75600
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.33,
|
| 2280 |
+
"learning_rate": 0.0005280471803822096,
|
| 2281 |
+
"loss": 3.2123,
|
| 2282 |
+
"step": 75800
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 0.33,
|
| 2286 |
+
"learning_rate": 0.0005300574540291803,
|
| 2287 |
+
"loss": 3.2208,
|
| 2288 |
+
"step": 76000
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.33,
|
| 2292 |
+
"learning_rate": 0.000532067551206336,
|
| 2293 |
+
"loss": 3.2199,
|
| 2294 |
+
"step": 76200
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.33,
|
| 2298 |
+
"learning_rate": 0.0005340774366441665,
|
| 2299 |
+
"loss": 3.2367,
|
| 2300 |
+
"step": 76400
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 0.33,
|
| 2304 |
+
"learning_rate": 0.0005360870750768769,
|
| 2305 |
+
"loss": 3.21,
|
| 2306 |
+
"step": 76600
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.33,
|
| 2310 |
+
"learning_rate": 0.0005380964312430063,
|
| 2311 |
+
"loss": 3.2221,
|
| 2312 |
+
"step": 76800
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.33,
|
| 2316 |
+
"learning_rate": 0.0005401054698860466,
|
| 2317 |
+
"loss": 3.2021,
|
| 2318 |
+
"step": 77000
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.33,
|
| 2322 |
+
"learning_rate": 0.0005421141557550603,
|
| 2323 |
+
"loss": 3.2352,
|
| 2324 |
+
"step": 77200
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 0.33,
|
| 2328 |
+
"learning_rate": 0.0005441224536053012,
|
| 2329 |
+
"loss": 3.1962,
|
| 2330 |
+
"step": 77400
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 0.33,
|
| 2334 |
+
"learning_rate": 0.0005461303281988298,
|
| 2335 |
+
"loss": 3.2127,
|
| 2336 |
+
"step": 77600
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.33,
|
| 2340 |
+
"learning_rate": 0.000548137744305134,
|
| 2341 |
+
"loss": 3.2307,
|
| 2342 |
+
"step": 77800
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 0.34,
|
| 2346 |
+
"learning_rate": 0.0005501446667017461,
|
| 2347 |
+
"loss": 3.2053,
|
| 2348 |
+
"step": 78000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.34,
|
| 2352 |
+
"learning_rate": 0.0005521510601748613,
|
| 2353 |
+
"loss": 3.1936,
|
| 2354 |
+
"step": 78200
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.34,
|
| 2358 |
+
"learning_rate": 0.0005541568895199552,
|
| 2359 |
+
"loss": 3.2019,
|
| 2360 |
+
"step": 78400
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.34,
|
| 2364 |
+
"learning_rate": 0.0005561621195424016,
|
| 2365 |
+
"loss": 3.203,
|
| 2366 |
+
"step": 78600
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.34,
|
| 2370 |
+
"learning_rate": 0.0005581667150580907,
|
| 2371 |
+
"loss": 3.2125,
|
| 2372 |
+
"step": 78800
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 0.34,
|
| 2376 |
+
"learning_rate": 0.0005601706408940451,
|
| 2377 |
+
"loss": 3.2205,
|
| 2378 |
+
"step": 79000
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.34,
|
| 2382 |
+
"learning_rate": 0.0005621738618890382,
|
| 2383 |
+
"loss": 3.2215,
|
| 2384 |
+
"step": 79200
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 0.34,
|
| 2388 |
+
"learning_rate": 0.0005641763428942106,
|
| 2389 |
+
"loss": 3.2052,
|
| 2390 |
+
"step": 79400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.34,
|
| 2394 |
+
"learning_rate": 0.0005661780487736866,
|
| 2395 |
+
"loss": 3.2249,
|
| 2396 |
+
"step": 79600
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.34,
|
| 2400 |
+
"learning_rate": 0.0005681789444051913,
|
| 2401 |
+
"loss": 3.1952,
|
| 2402 |
+
"step": 79800
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.34,
|
| 2406 |
+
"learning_rate": 0.0005701789946806666,
|
| 2407 |
+
"loss": 3.1995,
|
| 2408 |
+
"step": 80000
|
| 2409 |
}
|
| 2410 |
],
|
| 2411 |
"max_steps": 500000,
|
| 2412 |
"num_train_epochs": 3,
|
| 2413 |
+
"total_flos": 1.2750639857664e+17,
|
| 2414 |
"trial_name": null,
|
| 2415 |
"trial_params": null
|
| 2416 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 146774203
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a90871ae24751a566fb99821bee5e29d062c303c164fcd6aeac08948cab240
|
| 3 |
size 146774203
|