Commit
•
311485d
1
Parent(s):
8de7203
Training in progress, step 3500
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 +363 -3
- pytorch_model.bin +1 -1
- runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920384.2f481ea0b382.229.4 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4115013
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dee4476ab05abceb3ef157f762adb7b7ff2d24c295242ef85bdc7aa9baf339c
|
| 3 |
size 4115013
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c224c2d13e7b12f967f2ff294e904f86dfd319b281de69e29b4ca2a309522ccf
|
| 3 |
size 2329702453
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ace5200ce81b04d30bdcefc552d51b2d31acee8aa24f561db0693af839dd1d4
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cb02ae445517d5b6d8cceafc80181af9dac20207d12d240d963ba9d73872898
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -2166,11 +2166,371 @@
|
|
| 2166 |
"eval_samples_per_second": 0.213,
|
| 2167 |
"eval_steps_per_second": 0.213,
|
| 2168 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2169 |
}
|
| 2170 |
],
|
| 2171 |
"max_steps": 3542,
|
| 2172 |
"num_train_epochs": 7,
|
| 2173 |
-
"total_flos":
|
| 2174 |
"trial_name": null,
|
| 2175 |
"trial_params": null
|
| 2176 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.915300209591912,
|
| 5 |
+
"global_step": 3500,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 2166 |
"eval_samples_per_second": 0.213,
|
| 2167 |
"eval_steps_per_second": 0.213,
|
| 2168 |
"step": 3000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 5.95,
|
| 2172 |
+
"learning_rate": 7.705677867902664e-05,
|
| 2173 |
+
"loss": 0.0824,
|
| 2174 |
+
"step": 3010
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 5.97,
|
| 2178 |
+
"learning_rate": 7.560834298957127e-05,
|
| 2179 |
+
"loss": 0.1048,
|
| 2180 |
+
"step": 3020
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 5.99,
|
| 2184 |
+
"learning_rate": 7.415990730011588e-05,
|
| 2185 |
+
"loss": 0.1295,
|
| 2186 |
+
"step": 3030
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 6.01,
|
| 2190 |
+
"learning_rate": 7.271147161066048e-05,
|
| 2191 |
+
"loss": 0.1296,
|
| 2192 |
+
"step": 3040
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 6.03,
|
| 2196 |
+
"learning_rate": 7.12630359212051e-05,
|
| 2197 |
+
"loss": 0.1146,
|
| 2198 |
+
"step": 3050
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 6.05,
|
| 2202 |
+
"learning_rate": 6.981460023174971e-05,
|
| 2203 |
+
"loss": 0.1158,
|
| 2204 |
+
"step": 3060
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 6.07,
|
| 2208 |
+
"learning_rate": 6.836616454229433e-05,
|
| 2209 |
+
"loss": 0.094,
|
| 2210 |
+
"step": 3070
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 6.09,
|
| 2214 |
+
"learning_rate": 6.691772885283893e-05,
|
| 2215 |
+
"loss": 0.1141,
|
| 2216 |
+
"step": 3080
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 6.11,
|
| 2220 |
+
"learning_rate": 6.546929316338354e-05,
|
| 2221 |
+
"loss": 0.1025,
|
| 2222 |
+
"step": 3090
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 6.13,
|
| 2226 |
+
"learning_rate": 6.402085747392817e-05,
|
| 2227 |
+
"loss": 0.1474,
|
| 2228 |
+
"step": 3100
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 6.13,
|
| 2232 |
+
"eval_loss": 0.9422538876533508,
|
| 2233 |
+
"eval_rouge1": 0.20069541569541566,
|
| 2234 |
+
"eval_rouge2": 0.10303030303030303,
|
| 2235 |
+
"eval_rougeL": 0.19625097125097124,
|
| 2236 |
+
"eval_rougeLsum": 0.19848096348096347,
|
| 2237 |
+
"eval_runtime": 94.7246,
|
| 2238 |
+
"eval_samples_per_second": 0.211,
|
| 2239 |
+
"eval_steps_per_second": 0.211,
|
| 2240 |
+
"step": 3100
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 6.15,
|
| 2244 |
+
"learning_rate": 6.257242178447277e-05,
|
| 2245 |
+
"loss": 0.09,
|
| 2246 |
+
"step": 3110
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 6.17,
|
| 2250 |
+
"learning_rate": 6.112398609501739e-05,
|
| 2251 |
+
"loss": 0.1235,
|
| 2252 |
+
"step": 3120
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 6.19,
|
| 2256 |
+
"learning_rate": 5.9675550405561996e-05,
|
| 2257 |
+
"loss": 0.0733,
|
| 2258 |
+
"step": 3130
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 6.21,
|
| 2262 |
+
"learning_rate": 5.822711471610661e-05,
|
| 2263 |
+
"loss": 0.1035,
|
| 2264 |
+
"step": 3140
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 6.22,
|
| 2268 |
+
"learning_rate": 5.6778679026651216e-05,
|
| 2269 |
+
"loss": 0.1027,
|
| 2270 |
+
"step": 3150
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 6.24,
|
| 2274 |
+
"learning_rate": 5.533024333719583e-05,
|
| 2275 |
+
"loss": 0.0863,
|
| 2276 |
+
"step": 3160
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 6.26,
|
| 2280 |
+
"learning_rate": 5.388180764774044e-05,
|
| 2281 |
+
"loss": 0.095,
|
| 2282 |
+
"step": 3170
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 6.28,
|
| 2286 |
+
"learning_rate": 5.243337195828506e-05,
|
| 2287 |
+
"loss": 0.1103,
|
| 2288 |
+
"step": 3180
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 6.3,
|
| 2292 |
+
"learning_rate": 5.098493626882966e-05,
|
| 2293 |
+
"loss": 0.1325,
|
| 2294 |
+
"step": 3190
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 6.32,
|
| 2298 |
+
"learning_rate": 4.953650057937428e-05,
|
| 2299 |
+
"loss": 0.1052,
|
| 2300 |
+
"step": 3200
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 6.32,
|
| 2304 |
+
"eval_loss": 0.9328528642654419,
|
| 2305 |
+
"eval_rouge1": 0.2023076923076923,
|
| 2306 |
+
"eval_rouge2": 0.1102272727272727,
|
| 2307 |
+
"eval_rougeL": 0.19999999999999998,
|
| 2308 |
+
"eval_rougeLsum": 0.2,
|
| 2309 |
+
"eval_runtime": 92.8302,
|
| 2310 |
+
"eval_samples_per_second": 0.215,
|
| 2311 |
+
"eval_steps_per_second": 0.215,
|
| 2312 |
+
"step": 3200
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 6.34,
|
| 2316 |
+
"learning_rate": 4.808806488991889e-05,
|
| 2317 |
+
"loss": 0.1293,
|
| 2318 |
+
"step": 3210
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 6.36,
|
| 2322 |
+
"learning_rate": 4.6639629200463506e-05,
|
| 2323 |
+
"loss": 0.1301,
|
| 2324 |
+
"step": 3220
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 6.38,
|
| 2328 |
+
"learning_rate": 4.519119351100811e-05,
|
| 2329 |
+
"loss": 0.0873,
|
| 2330 |
+
"step": 3230
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 6.4,
|
| 2334 |
+
"learning_rate": 4.3742757821552725e-05,
|
| 2335 |
+
"loss": 0.1017,
|
| 2336 |
+
"step": 3240
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 6.42,
|
| 2340 |
+
"learning_rate": 4.2294322132097335e-05,
|
| 2341 |
+
"loss": 0.0846,
|
| 2342 |
+
"step": 3250
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 6.44,
|
| 2346 |
+
"learning_rate": 4.084588644264195e-05,
|
| 2347 |
+
"loss": 0.0898,
|
| 2348 |
+
"step": 3260
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 6.46,
|
| 2352 |
+
"learning_rate": 3.9397450753186555e-05,
|
| 2353 |
+
"loss": 0.1494,
|
| 2354 |
+
"step": 3270
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 6.48,
|
| 2358 |
+
"learning_rate": 3.794901506373117e-05,
|
| 2359 |
+
"loss": 0.0742,
|
| 2360 |
+
"step": 3280
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 6.5,
|
| 2364 |
+
"learning_rate": 3.650057937427578e-05,
|
| 2365 |
+
"loss": 0.0793,
|
| 2366 |
+
"step": 3290
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 6.52,
|
| 2370 |
+
"learning_rate": 3.50521436848204e-05,
|
| 2371 |
+
"loss": 0.1203,
|
| 2372 |
+
"step": 3300
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 6.52,
|
| 2376 |
+
"eval_loss": 0.9380243420600891,
|
| 2377 |
+
"eval_rouge1": 0.2023076923076923,
|
| 2378 |
+
"eval_rouge2": 0.1102272727272727,
|
| 2379 |
+
"eval_rougeL": 0.19999999999999998,
|
| 2380 |
+
"eval_rougeLsum": 0.2,
|
| 2381 |
+
"eval_runtime": 94.5066,
|
| 2382 |
+
"eval_samples_per_second": 0.212,
|
| 2383 |
+
"eval_steps_per_second": 0.212,
|
| 2384 |
+
"step": 3300
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 6.54,
|
| 2388 |
+
"learning_rate": 3.360370799536501e-05,
|
| 2389 |
+
"loss": 0.1257,
|
| 2390 |
+
"step": 3310
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 6.56,
|
| 2394 |
+
"learning_rate": 3.215527230590962e-05,
|
| 2395 |
+
"loss": 0.1177,
|
| 2396 |
+
"step": 3320
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 6.58,
|
| 2400 |
+
"learning_rate": 3.070683661645423e-05,
|
| 2401 |
+
"loss": 0.1359,
|
| 2402 |
+
"step": 3330
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 6.6,
|
| 2406 |
+
"learning_rate": 2.9258400926998842e-05,
|
| 2407 |
+
"loss": 0.1303,
|
| 2408 |
+
"step": 3340
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 6.62,
|
| 2412 |
+
"learning_rate": 2.7809965237543452e-05,
|
| 2413 |
+
"loss": 0.0968,
|
| 2414 |
+
"step": 3350
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 6.64,
|
| 2418 |
+
"learning_rate": 2.6361529548088065e-05,
|
| 2419 |
+
"loss": 0.1061,
|
| 2420 |
+
"step": 3360
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 6.66,
|
| 2424 |
+
"learning_rate": 2.4913093858632675e-05,
|
| 2425 |
+
"loss": 0.1307,
|
| 2426 |
+
"step": 3370
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 6.68,
|
| 2430 |
+
"learning_rate": 2.346465816917729e-05,
|
| 2431 |
+
"loss": 0.0981,
|
| 2432 |
+
"step": 3380
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 6.7,
|
| 2436 |
+
"learning_rate": 2.20162224797219e-05,
|
| 2437 |
+
"loss": 0.0901,
|
| 2438 |
+
"step": 3390
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 6.72,
|
| 2442 |
+
"learning_rate": 2.0567786790266515e-05,
|
| 2443 |
+
"loss": 0.1125,
|
| 2444 |
+
"step": 3400
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 6.72,
|
| 2448 |
+
"eval_loss": 0.9421626925468445,
|
| 2449 |
+
"eval_rouge1": 0.18958041958041955,
|
| 2450 |
+
"eval_rouge2": 0.0977272727272727,
|
| 2451 |
+
"eval_rougeL": 0.18615384615384614,
|
| 2452 |
+
"eval_rougeLsum": 0.19,
|
| 2453 |
+
"eval_runtime": 96.4239,
|
| 2454 |
+
"eval_samples_per_second": 0.207,
|
| 2455 |
+
"eval_steps_per_second": 0.207,
|
| 2456 |
+
"step": 3400
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 6.74,
|
| 2460 |
+
"learning_rate": 1.9119351100811125e-05,
|
| 2461 |
+
"loss": 0.0823,
|
| 2462 |
+
"step": 3410
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 6.76,
|
| 2466 |
+
"learning_rate": 1.767091541135574e-05,
|
| 2467 |
+
"loss": 0.1016,
|
| 2468 |
+
"step": 3420
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 6.78,
|
| 2472 |
+
"learning_rate": 1.6222479721900348e-05,
|
| 2473 |
+
"loss": 0.1172,
|
| 2474 |
+
"step": 3430
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 6.8,
|
| 2478 |
+
"learning_rate": 1.477404403244496e-05,
|
| 2479 |
+
"loss": 0.0959,
|
| 2480 |
+
"step": 3440
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 6.82,
|
| 2484 |
+
"learning_rate": 1.3325608342989572e-05,
|
| 2485 |
+
"loss": 0.1534,
|
| 2486 |
+
"step": 3450
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 6.84,
|
| 2490 |
+
"learning_rate": 1.1877172653534183e-05,
|
| 2491 |
+
"loss": 0.125,
|
| 2492 |
+
"step": 3460
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 6.86,
|
| 2496 |
+
"learning_rate": 1.0428736964078795e-05,
|
| 2497 |
+
"loss": 0.1221,
|
| 2498 |
+
"step": 3470
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 6.88,
|
| 2502 |
+
"learning_rate": 8.980301274623406e-06,
|
| 2503 |
+
"loss": 0.1391,
|
| 2504 |
+
"step": 3480
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 6.9,
|
| 2508 |
+
"learning_rate": 7.531865585168019e-06,
|
| 2509 |
+
"loss": 0.0986,
|
| 2510 |
+
"step": 3490
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 6.92,
|
| 2514 |
+
"learning_rate": 6.083429895712631e-06,
|
| 2515 |
+
"loss": 0.1323,
|
| 2516 |
+
"step": 3500
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 6.92,
|
| 2520 |
+
"eval_loss": 0.9433181881904602,
|
| 2521 |
+
"eval_rouge1": 0.19,
|
| 2522 |
+
"eval_rouge2": 0.0977272727272727,
|
| 2523 |
+
"eval_rougeL": 0.18615384615384617,
|
| 2524 |
+
"eval_rougeLsum": 0.19,
|
| 2525 |
+
"eval_runtime": 94.6833,
|
| 2526 |
+
"eval_samples_per_second": 0.211,
|
| 2527 |
+
"eval_steps_per_second": 0.211,
|
| 2528 |
+
"step": 3500
|
| 2529 |
}
|
| 2530 |
],
|
| 2531 |
"max_steps": 3542,
|
| 2532 |
"num_train_epochs": 7,
|
| 2533 |
+
"total_flos": 8.516307584906035e+16,
|
| 2534 |
"trial_name": null,
|
| 2535 |
"trial_params": null
|
| 2536 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2329702453
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c224c2d13e7b12f967f2ff294e904f86dfd319b281de69e29b4ca2a309522ccf
|
| 3 |
size 2329702453
|
runs/Feb09_05-19-49_2f481ea0b382/events.out.tfevents.1675920384.2f481ea0b382.229.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6b509b0a8c5d255f18347ea36ef5ec5e33b87ce49dd65c62b7d4e64b70e8b5a
|
| 3 |
+
size 24646
|