Training in progress, step 3500, 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 328277848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:738c2de85f0e51539b3b28ef14af7af58903d06b8cb198594333ab46070e708c
|
| 3 |
size 328277848
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 318646859
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:024ddd20febf80999241a3aa205a823795a590616e197f4bf659cd2cd012b820
|
| 3 |
size 318646859
|
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 sha256:28f4baaa7c055b0898b0ca303ea04e20e5e8e6d3ba1fd3140d755b6a404cb08b
|
| 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 sha256:78485ac70c57dc668ae0e88817673f3f048988e00a751f9337313c02c006f1eb
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2163,6 +2163,364 @@
|
|
| 2163 |
"eval_samples_per_second": 273.24,
|
| 2164 |
"eval_steps_per_second": 5.738,
|
| 2165 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2166 |
}
|
| 2167 |
],
|
| 2168 |
"logging_steps": 10,
|
|
@@ -2182,7 +2540,7 @@
|
|
| 2182 |
"attributes": {}
|
| 2183 |
}
|
| 2184 |
},
|
| 2185 |
-
"total_flos": 1.
|
| 2186 |
"train_batch_size": 48,
|
| 2187 |
"trial_name": null,
|
| 2188 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5913161006926846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2163 |
"eval_samples_per_second": 273.24,
|
| 2164 |
"eval_steps_per_second": 5.738,
|
| 2165 |
"step": 3000
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.5085318465957087,
|
| 2169 |
+
"grad_norm": 0.5907111167907715,
|
| 2170 |
+
"learning_rate": 0.00029228085521948167,
|
| 2171 |
+
"loss": 4.962014770507812,
|
| 2172 |
+
"step": 3010
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.5102213211691164,
|
| 2176 |
+
"grad_norm": 0.6199477314949036,
|
| 2177 |
+
"learning_rate": 0.000292128450206336,
|
| 2178 |
+
"loss": 4.9626415252685545,
|
| 2179 |
+
"step": 3020
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.5119107957425241,
|
| 2183 |
+
"grad_norm": 0.6104288697242737,
|
| 2184 |
+
"learning_rate": 0.00029197459586493077,
|
| 2185 |
+
"loss": 4.9658355712890625,
|
| 2186 |
+
"step": 3030
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.5136002703159317,
|
| 2190 |
+
"grad_norm": 0.6005300879478455,
|
| 2191 |
+
"learning_rate": 0.0002918192937641668,
|
| 2192 |
+
"loss": 4.934582138061524,
|
| 2193 |
+
"step": 3040
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.5152897448893394,
|
| 2197 |
+
"grad_norm": 0.6632323265075684,
|
| 2198 |
+
"learning_rate": 0.00029166254548770827,
|
| 2199 |
+
"loss": 4.954456329345703,
|
| 2200 |
+
"step": 3050
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.516979219462747,
|
| 2204 |
+
"grad_norm": 0.6572689414024353,
|
| 2205 |
+
"learning_rate": 0.0002915043526339663,
|
| 2206 |
+
"loss": 4.949708557128906,
|
| 2207 |
+
"step": 3060
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.5186686940361548,
|
| 2211 |
+
"grad_norm": 0.5921790599822998,
|
| 2212 |
+
"learning_rate": 0.00029134471681608286,
|
| 2213 |
+
"loss": 4.954426956176758,
|
| 2214 |
+
"step": 3070
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.5203581686095624,
|
| 2218 |
+
"grad_norm": 0.5966045260429382,
|
| 2219 |
+
"learning_rate": 0.00029118363966191445,
|
| 2220 |
+
"loss": 4.942135620117187,
|
| 2221 |
+
"step": 3080
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.5220476431829701,
|
| 2225 |
+
"grad_norm": 0.6385965943336487,
|
| 2226 |
+
"learning_rate": 0.00029102112281401507,
|
| 2227 |
+
"loss": 4.943619155883789,
|
| 2228 |
+
"step": 3090
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.5237371177563778,
|
| 2232 |
+
"grad_norm": 0.5503054261207581,
|
| 2233 |
+
"learning_rate": 0.0002908571679296199,
|
| 2234 |
+
"loss": 4.951112747192383,
|
| 2235 |
+
"step": 3100
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.5254265923297854,
|
| 2239 |
+
"grad_norm": 0.6213752031326294,
|
| 2240 |
+
"learning_rate": 0.00029069177668062816,
|
| 2241 |
+
"loss": 4.945027542114258,
|
| 2242 |
+
"step": 3110
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.5271160669031931,
|
| 2246 |
+
"grad_norm": 0.6044753193855286,
|
| 2247 |
+
"learning_rate": 0.00029052495075358617,
|
| 2248 |
+
"loss": 4.938185119628907,
|
| 2249 |
+
"step": 3120
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.5288055414766007,
|
| 2253 |
+
"grad_norm": 0.6271653175354004,
|
| 2254 |
+
"learning_rate": 0.0002903566918496701,
|
| 2255 |
+
"loss": 4.923495101928711,
|
| 2256 |
+
"step": 3130
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.5304950160500085,
|
| 2260 |
+
"grad_norm": 0.6465984582901001,
|
| 2261 |
+
"learning_rate": 0.0002901870016846685,
|
| 2262 |
+
"loss": 4.891114807128906,
|
| 2263 |
+
"step": 3140
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.5321844906234161,
|
| 2267 |
+
"grad_norm": 0.620452880859375,
|
| 2268 |
+
"learning_rate": 0.00029001588198896523,
|
| 2269 |
+
"loss": 4.925071716308594,
|
| 2270 |
+
"step": 3150
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.5338739651968238,
|
| 2274 |
+
"grad_norm": 0.6565406918525696,
|
| 2275 |
+
"learning_rate": 0.0002898433345075212,
|
| 2276 |
+
"loss": 4.935154724121094,
|
| 2277 |
+
"step": 3160
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.5355634397702315,
|
| 2281 |
+
"grad_norm": 0.6409232020378113,
|
| 2282 |
+
"learning_rate": 0.0002896693609998571,
|
| 2283 |
+
"loss": 4.912665939331054,
|
| 2284 |
+
"step": 3170
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.5372529143436391,
|
| 2288 |
+
"grad_norm": 0.6292628049850464,
|
| 2289 |
+
"learning_rate": 0.0002894939632400352,
|
| 2290 |
+
"loss": 4.893975448608399,
|
| 2291 |
+
"step": 3180
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.5389423889170468,
|
| 2295 |
+
"grad_norm": 0.662747323513031,
|
| 2296 |
+
"learning_rate": 0.0002893171430166413,
|
| 2297 |
+
"loss": 4.919517898559571,
|
| 2298 |
+
"step": 3190
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.5406318634904544,
|
| 2302 |
+
"grad_norm": 0.6002474427223206,
|
| 2303 |
+
"learning_rate": 0.00028913890213276664,
|
| 2304 |
+
"loss": 4.877264785766601,
|
| 2305 |
+
"step": 3200
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.5423213380638622,
|
| 2309 |
+
"grad_norm": 0.624601423740387,
|
| 2310 |
+
"learning_rate": 0.0002889592424059891,
|
| 2311 |
+
"loss": 4.865252304077148,
|
| 2312 |
+
"step": 3210
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.5440108126372698,
|
| 2316 |
+
"grad_norm": 0.6517230272293091,
|
| 2317 |
+
"learning_rate": 0.0002887781656683551,
|
| 2318 |
+
"loss": 4.910610198974609,
|
| 2319 |
+
"step": 3220
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.5457002872106774,
|
| 2323 |
+
"grad_norm": 0.5979717373847961,
|
| 2324 |
+
"learning_rate": 0.0002885956737663609,
|
| 2325 |
+
"loss": 4.881752014160156,
|
| 2326 |
+
"step": 3230
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.5473897617840852,
|
| 2330 |
+
"grad_norm": 0.612158477306366,
|
| 2331 |
+
"learning_rate": 0.00028841176856093346,
|
| 2332 |
+
"loss": 4.865722274780273,
|
| 2333 |
+
"step": 3240
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.5490792363574928,
|
| 2337 |
+
"grad_norm": 0.5829477906227112,
|
| 2338 |
+
"learning_rate": 0.0002882264519274116,
|
| 2339 |
+
"loss": 4.901315689086914,
|
| 2340 |
+
"step": 3250
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.5507687109309005,
|
| 2344 |
+
"grad_norm": 0.555895209312439,
|
| 2345 |
+
"learning_rate": 0.0002880397257555271,
|
| 2346 |
+
"loss": 4.875097274780273,
|
| 2347 |
+
"step": 3260
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.5524581855043081,
|
| 2351 |
+
"grad_norm": 0.558150589466095,
|
| 2352 |
+
"learning_rate": 0.000287851591949385,
|
| 2353 |
+
"loss": 4.87982063293457,
|
| 2354 |
+
"step": 3270
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.5541476600777159,
|
| 2358 |
+
"grad_norm": 0.6409489512443542,
|
| 2359 |
+
"learning_rate": 0.0002876620524274447,
|
| 2360 |
+
"loss": 4.872901535034179,
|
| 2361 |
+
"step": 3280
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.5558371346511235,
|
| 2365 |
+
"grad_norm": 0.5831784009933472,
|
| 2366 |
+
"learning_rate": 0.0002874711091224999,
|
| 2367 |
+
"loss": 4.875904846191406,
|
| 2368 |
+
"step": 3290
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.5575266092245311,
|
| 2372 |
+
"grad_norm": 0.6392360329627991,
|
| 2373 |
+
"learning_rate": 0.0002872787639816593,
|
| 2374 |
+
"loss": 4.889061737060547,
|
| 2375 |
+
"step": 3300
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.5592160837979389,
|
| 2379 |
+
"grad_norm": 0.5464599132537842,
|
| 2380 |
+
"learning_rate": 0.00028708501896632636,
|
| 2381 |
+
"loss": 4.861515045166016,
|
| 2382 |
+
"step": 3310
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.5609055583713465,
|
| 2386 |
+
"grad_norm": 0.5729095935821533,
|
| 2387 |
+
"learning_rate": 0.0002868898760521796,
|
| 2388 |
+
"loss": 4.874145889282227,
|
| 2389 |
+
"step": 3320
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.5625950329447542,
|
| 2393 |
+
"grad_norm": 0.5853311419487,
|
| 2394 |
+
"learning_rate": 0.00028669333722915245,
|
| 2395 |
+
"loss": 4.873168182373047,
|
| 2396 |
+
"step": 3330
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.5642845075181618,
|
| 2400 |
+
"grad_norm": 0.6287094950675964,
|
| 2401 |
+
"learning_rate": 0.0002864954045014126,
|
| 2402 |
+
"loss": 4.851799774169922,
|
| 2403 |
+
"step": 3340
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.5659739820915696,
|
| 2407 |
+
"grad_norm": 0.6342536807060242,
|
| 2408 |
+
"learning_rate": 0.00028629607988734214,
|
| 2409 |
+
"loss": 4.875107955932617,
|
| 2410 |
+
"step": 3350
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.5676634566649772,
|
| 2414 |
+
"grad_norm": 0.614021360874176,
|
| 2415 |
+
"learning_rate": 0.00028609536541951636,
|
| 2416 |
+
"loss": 4.858898544311524,
|
| 2417 |
+
"step": 3360
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.5693529312383848,
|
| 2421 |
+
"grad_norm": 0.6052382588386536,
|
| 2422 |
+
"learning_rate": 0.00028589326314468357,
|
| 2423 |
+
"loss": 4.861991882324219,
|
| 2424 |
+
"step": 3370
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.5710424058117926,
|
| 2428 |
+
"grad_norm": 0.6074774861335754,
|
| 2429 |
+
"learning_rate": 0.0002856897751237439,
|
| 2430 |
+
"loss": 4.841437911987304,
|
| 2431 |
+
"step": 3380
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.5727318803852002,
|
| 2435 |
+
"grad_norm": 0.570922315120697,
|
| 2436 |
+
"learning_rate": 0.0002854849034317282,
|
| 2437 |
+
"loss": 4.846294403076172,
|
| 2438 |
+
"step": 3390
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.5744213549586079,
|
| 2442 |
+
"grad_norm": 0.5668649673461914,
|
| 2443 |
+
"learning_rate": 0.0002852786501577773,
|
| 2444 |
+
"loss": 4.829824829101563,
|
| 2445 |
+
"step": 3400
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.5761108295320155,
|
| 2449 |
+
"grad_norm": 0.5982180833816528,
|
| 2450 |
+
"learning_rate": 0.0002850710174051204,
|
| 2451 |
+
"loss": 4.869507598876953,
|
| 2452 |
+
"step": 3410
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.5778003041054233,
|
| 2456 |
+
"grad_norm": 0.6077879071235657,
|
| 2457 |
+
"learning_rate": 0.0002848620072910535,
|
| 2458 |
+
"loss": 4.834074020385742,
|
| 2459 |
+
"step": 3420
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.5794897786788309,
|
| 2463 |
+
"grad_norm": 0.5370880961418152,
|
| 2464 |
+
"learning_rate": 0.0002846516219469181,
|
| 2465 |
+
"loss": 4.8527587890625,
|
| 2466 |
+
"step": 3430
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.5811792532522385,
|
| 2470 |
+
"grad_norm": 0.558279275894165,
|
| 2471 |
+
"learning_rate": 0.0002844398635180794,
|
| 2472 |
+
"loss": 4.853738403320312,
|
| 2473 |
+
"step": 3440
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.5828687278256462,
|
| 2477 |
+
"grad_norm": 0.563609778881073,
|
| 2478 |
+
"learning_rate": 0.00028422673416390437,
|
| 2479 |
+
"loss": 4.860172271728516,
|
| 2480 |
+
"step": 3450
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.5845582023990539,
|
| 2484 |
+
"grad_norm": 0.5331059694290161,
|
| 2485 |
+
"learning_rate": 0.00028401223605773964,
|
| 2486 |
+
"loss": 4.843973159790039,
|
| 2487 |
+
"step": 3460
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.5862476769724616,
|
| 2491 |
+
"grad_norm": 0.6446515321731567,
|
| 2492 |
+
"learning_rate": 0.00028379637138688945,
|
| 2493 |
+
"loss": 4.827552032470703,
|
| 2494 |
+
"step": 3470
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.5879371515458692,
|
| 2498 |
+
"grad_norm": 0.6347187161445618,
|
| 2499 |
+
"learning_rate": 0.0002835791423525935,
|
| 2500 |
+
"loss": 4.821343231201172,
|
| 2501 |
+
"step": 3480
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.5896266261192769,
|
| 2505 |
+
"grad_norm": 0.6264333724975586,
|
| 2506 |
+
"learning_rate": 0.00028336055117000403,
|
| 2507 |
+
"loss": 4.83858642578125,
|
| 2508 |
+
"step": 3490
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.5913161006926846,
|
| 2512 |
+
"grad_norm": 0.5439333915710449,
|
| 2513 |
+
"learning_rate": 0.0002831406000681638,
|
| 2514 |
+
"loss": 4.8269500732421875,
|
| 2515 |
+
"step": 3500
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.5913161006926846,
|
| 2519 |
+
"eval_loss": 4.798425674438477,
|
| 2520 |
+
"eval_runtime": 3.5865,
|
| 2521 |
+
"eval_samples_per_second": 278.824,
|
| 2522 |
+
"eval_steps_per_second": 5.855,
|
| 2523 |
+
"step": 3500
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 10,
|
|
|
|
| 2540 |
"attributes": {}
|
| 2541 |
}
|
| 2542 |
},
|
| 2543 |
+
"total_flos": 1.17059887300608e+17,
|
| 2544 |
"train_batch_size": 48,
|
| 2545 |
"trial_name": null,
|
| 2546 |
"trial_params": null
|