Training in progress, step 350, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281587880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40f2cf472b8c7e6ccdc86217290eb8d7dc33e3ab80f71ee367c67e02d39e1fe3
|
| 3 |
size 281587880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 143366164
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6e64630ea125e1b76094f0464fb8369e95526b154858cc41fd58814081e1a20
|
| 3 |
size 143366164
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbaea94c24565bdc57de5411d2276eefbc226e76b091640d4f584c6a6fdc009
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc4359ecb90a50bbea116b9a12b6a99effac889cc2d40f6093f2c443d61fb593
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.0175247173756361,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2163,6 +2163,364 @@
|
|
| 2163 |
"eval_samples_per_second": 15.434,
|
| 2164 |
"eval_steps_per_second": 15.434,
|
| 2165 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2166 |
}
|
| 2167 |
],
|
| 2168 |
"logging_steps": 1,
|
|
@@ -2177,7 +2535,7 @@
|
|
| 2177 |
"early_stopping_threshold": 0.0
|
| 2178 |
},
|
| 2179 |
"attributes": {
|
| 2180 |
-
"early_stopping_patience_counter":
|
| 2181 |
}
|
| 2182 |
},
|
| 2183 |
"TrainerControl": {
|
|
@@ -2186,12 +2544,12 @@
|
|
| 2186 |
"should_evaluate": false,
|
| 2187 |
"should_log": false,
|
| 2188 |
"should_save": true,
|
| 2189 |
-
"should_training_stop":
|
| 2190 |
},
|
| 2191 |
"attributes": {}
|
| 2192 |
}
|
| 2193 |
},
|
| 2194 |
-
"total_flos":
|
| 2195 |
"train_batch_size": 1,
|
| 2196 |
"trial_name": null,
|
| 2197 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.0175247173756361,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.025881232871014407,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 350,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2163 |
"eval_samples_per_second": 15.434,
|
| 2164 |
"eval_steps_per_second": 15.434,
|
| 2165 |
"step": 300
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.02225786026907239,
|
| 2169 |
+
"grad_norm": 0.3705998659133911,
|
| 2170 |
+
"learning_rate": 0.0002404622145698234,
|
| 2171 |
+
"loss": 0.0342,
|
| 2172 |
+
"step": 301
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.022331806648703857,
|
| 2176 |
+
"grad_norm": 0.3507665693759918,
|
| 2177 |
+
"learning_rate": 0.00024008206511550044,
|
| 2178 |
+
"loss": 0.021,
|
| 2179 |
+
"step": 302
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.022405753028335328,
|
| 2183 |
+
"grad_norm": 0.2580109238624573,
|
| 2184 |
+
"learning_rate": 0.00023970100853578185,
|
| 2185 |
+
"loss": 0.0366,
|
| 2186 |
+
"step": 303
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.022479699407966798,
|
| 2190 |
+
"grad_norm": 0.2751363217830658,
|
| 2191 |
+
"learning_rate": 0.00023931904866790317,
|
| 2192 |
+
"loss": 0.0383,
|
| 2193 |
+
"step": 304
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.02255364578759827,
|
| 2197 |
+
"grad_norm": 0.1519552618265152,
|
| 2198 |
+
"learning_rate": 0.00023893618935819607,
|
| 2199 |
+
"loss": 0.0114,
|
| 2200 |
+
"step": 305
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.02262759216722974,
|
| 2204 |
+
"grad_norm": 0.4399930536746979,
|
| 2205 |
+
"learning_rate": 0.00023855243446204946,
|
| 2206 |
+
"loss": 0.1788,
|
| 2207 |
+
"step": 306
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.022701538546861206,
|
| 2211 |
+
"grad_norm": 0.3781653046607971,
|
| 2212 |
+
"learning_rate": 0.00023816778784387094,
|
| 2213 |
+
"loss": 0.0413,
|
| 2214 |
+
"step": 307
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.022775484926492676,
|
| 2218 |
+
"grad_norm": 0.2434411644935608,
|
| 2219 |
+
"learning_rate": 0.00023778225337704772,
|
| 2220 |
+
"loss": 0.002,
|
| 2221 |
+
"step": 308
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.022849431306124147,
|
| 2225 |
+
"grad_norm": 0.06450709700584412,
|
| 2226 |
+
"learning_rate": 0.00023739583494390752,
|
| 2227 |
+
"loss": 0.0019,
|
| 2228 |
+
"step": 309
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.022923377685755617,
|
| 2232 |
+
"grad_norm": 0.3262978494167328,
|
| 2233 |
+
"learning_rate": 0.0002370085364356797,
|
| 2234 |
+
"loss": 0.0118,
|
| 2235 |
+
"step": 310
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.022997324065387088,
|
| 2239 |
+
"grad_norm": 0.22701017558574677,
|
| 2240 |
+
"learning_rate": 0.00023662036175245595,
|
| 2241 |
+
"loss": 0.0297,
|
| 2242 |
+
"step": 311
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.023071270445018555,
|
| 2246 |
+
"grad_norm": 0.14085568487644196,
|
| 2247 |
+
"learning_rate": 0.00023623131480315107,
|
| 2248 |
+
"loss": 0.0104,
|
| 2249 |
+
"step": 312
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.023145216824650025,
|
| 2253 |
+
"grad_norm": 0.2725294232368469,
|
| 2254 |
+
"learning_rate": 0.00023584139950546344,
|
| 2255 |
+
"loss": 0.0214,
|
| 2256 |
+
"step": 313
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.023219163204281495,
|
| 2260 |
+
"grad_norm": 0.27837783098220825,
|
| 2261 |
+
"learning_rate": 0.0002354506197858358,
|
| 2262 |
+
"loss": 0.0054,
|
| 2263 |
+
"step": 314
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.023293109583912966,
|
| 2267 |
+
"grad_norm": 0.4964681565761566,
|
| 2268 |
+
"learning_rate": 0.00023505897957941556,
|
| 2269 |
+
"loss": 0.0053,
|
| 2270 |
+
"step": 315
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.023367055963544436,
|
| 2274 |
+
"grad_norm": 0.19499018788337708,
|
| 2275 |
+
"learning_rate": 0.00023466648283001538,
|
| 2276 |
+
"loss": 0.0111,
|
| 2277 |
+
"step": 316
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.023441002343175903,
|
| 2281 |
+
"grad_norm": 0.11361473798751831,
|
| 2282 |
+
"learning_rate": 0.000234273133490073,
|
| 2283 |
+
"loss": 0.0189,
|
| 2284 |
+
"step": 317
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.023514948722807374,
|
| 2288 |
+
"grad_norm": 0.1209384948015213,
|
| 2289 |
+
"learning_rate": 0.00023387893552061199,
|
| 2290 |
+
"loss": 0.0048,
|
| 2291 |
+
"step": 318
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.023588895102438844,
|
| 2295 |
+
"grad_norm": 0.3064891993999481,
|
| 2296 |
+
"learning_rate": 0.00023348389289120158,
|
| 2297 |
+
"loss": 0.0043,
|
| 2298 |
+
"step": 319
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.023662841482070315,
|
| 2302 |
+
"grad_norm": 0.04545588046312332,
|
| 2303 |
+
"learning_rate": 0.00023308800957991653,
|
| 2304 |
+
"loss": 0.0012,
|
| 2305 |
+
"step": 320
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.023736787861701785,
|
| 2309 |
+
"grad_norm": 0.16587400436401367,
|
| 2310 |
+
"learning_rate": 0.00023269128957329748,
|
| 2311 |
+
"loss": 0.0077,
|
| 2312 |
+
"step": 321
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.023810734241333252,
|
| 2316 |
+
"grad_norm": 0.03504616394639015,
|
| 2317 |
+
"learning_rate": 0.0002322937368663105,
|
| 2318 |
+
"loss": 0.0009,
|
| 2319 |
+
"step": 322
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.023884680620964722,
|
| 2323 |
+
"grad_norm": 0.3943489193916321,
|
| 2324 |
+
"learning_rate": 0.00023189535546230683,
|
| 2325 |
+
"loss": 0.0193,
|
| 2326 |
+
"step": 323
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.023958627000596193,
|
| 2330 |
+
"grad_norm": 4.359734058380127,
|
| 2331 |
+
"learning_rate": 0.00023149614937298296,
|
| 2332 |
+
"loss": 0.3536,
|
| 2333 |
+
"step": 324
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.024032573380227663,
|
| 2337 |
+
"grad_norm": 0.07727823406457901,
|
| 2338 |
+
"learning_rate": 0.00023109612261833963,
|
| 2339 |
+
"loss": 0.0029,
|
| 2340 |
+
"step": 325
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.024106519759859134,
|
| 2344 |
+
"grad_norm": 0.23159946501255035,
|
| 2345 |
+
"learning_rate": 0.00023069527922664186,
|
| 2346 |
+
"loss": 0.0352,
|
| 2347 |
+
"step": 326
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.0241804661394906,
|
| 2351 |
+
"grad_norm": 0.07464925199747086,
|
| 2352 |
+
"learning_rate": 0.00023029362323437818,
|
| 2353 |
+
"loss": 0.0012,
|
| 2354 |
+
"step": 327
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.02425441251912207,
|
| 2358 |
+
"grad_norm": 0.4283057749271393,
|
| 2359 |
+
"learning_rate": 0.00022989115868621995,
|
| 2360 |
+
"loss": 0.0076,
|
| 2361 |
+
"step": 328
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.02432835889875354,
|
| 2365 |
+
"grad_norm": 0.3561228811740875,
|
| 2366 |
+
"learning_rate": 0.0002294878896349807,
|
| 2367 |
+
"loss": 0.0053,
|
| 2368 |
+
"step": 329
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.024402305278385012,
|
| 2372 |
+
"grad_norm": 0.5599501132965088,
|
| 2373 |
+
"learning_rate": 0.00022908382014157533,
|
| 2374 |
+
"loss": 0.0079,
|
| 2375 |
+
"step": 330
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.024476251658016483,
|
| 2379 |
+
"grad_norm": 0.8999078869819641,
|
| 2380 |
+
"learning_rate": 0.00022867895427497914,
|
| 2381 |
+
"loss": 0.1989,
|
| 2382 |
+
"step": 331
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.02455019803764795,
|
| 2386 |
+
"grad_norm": 0.6236395239830017,
|
| 2387 |
+
"learning_rate": 0.00022827329611218688,
|
| 2388 |
+
"loss": 0.0226,
|
| 2389 |
+
"step": 332
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.02462414441727942,
|
| 2393 |
+
"grad_norm": 0.292870432138443,
|
| 2394 |
+
"learning_rate": 0.0002278668497381718,
|
| 2395 |
+
"loss": 0.06,
|
| 2396 |
+
"step": 333
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.02469809079691089,
|
| 2400 |
+
"grad_norm": 0.14794032275676727,
|
| 2401 |
+
"learning_rate": 0.00022745961924584428,
|
| 2402 |
+
"loss": 0.0028,
|
| 2403 |
+
"step": 334
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.02477203717654236,
|
| 2407 |
+
"grad_norm": 0.013083276338875294,
|
| 2408 |
+
"learning_rate": 0.00022705160873601096,
|
| 2409 |
+
"loss": 0.0005,
|
| 2410 |
+
"step": 335
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.024845983556173828,
|
| 2414 |
+
"grad_norm": 0.21283191442489624,
|
| 2415 |
+
"learning_rate": 0.00022664282231733309,
|
| 2416 |
+
"loss": 0.0248,
|
| 2417 |
+
"step": 336
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.024919929935805298,
|
| 2421 |
+
"grad_norm": 0.444803923368454,
|
| 2422 |
+
"learning_rate": 0.00022623326410628534,
|
| 2423 |
+
"loss": 0.0026,
|
| 2424 |
+
"step": 337
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.02499387631543677,
|
| 2428 |
+
"grad_norm": 1.0099908113479614,
|
| 2429 |
+
"learning_rate": 0.00022582293822711444,
|
| 2430 |
+
"loss": 0.0088,
|
| 2431 |
+
"step": 338
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.02506782269506824,
|
| 2435 |
+
"grad_norm": 0.45318788290023804,
|
| 2436 |
+
"learning_rate": 0.00022541184881179737,
|
| 2437 |
+
"loss": 0.1016,
|
| 2438 |
+
"step": 339
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.02514176907469971,
|
| 2442 |
+
"grad_norm": 0.5700947046279907,
|
| 2443 |
+
"learning_rate": 0.000225,
|
| 2444 |
+
"loss": 0.0194,
|
| 2445 |
+
"step": 340
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.025215715454331177,
|
| 2449 |
+
"grad_norm": 0.12225595116615295,
|
| 2450 |
+
"learning_rate": 0.0002245873959390353,
|
| 2451 |
+
"loss": 0.0016,
|
| 2452 |
+
"step": 341
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.025289661833962647,
|
| 2456 |
+
"grad_norm": 0.21263572573661804,
|
| 2457 |
+
"learning_rate": 0.00022417404078382152,
|
| 2458 |
+
"loss": 0.0088,
|
| 2459 |
+
"step": 342
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.025363608213594117,
|
| 2463 |
+
"grad_norm": 0.7097033262252808,
|
| 2464 |
+
"learning_rate": 0.00022375993869684058,
|
| 2465 |
+
"loss": 0.0065,
|
| 2466 |
+
"step": 343
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.025437554593225588,
|
| 2470 |
+
"grad_norm": 0.3727460205554962,
|
| 2471 |
+
"learning_rate": 0.00022334509384809584,
|
| 2472 |
+
"loss": 0.0088,
|
| 2473 |
+
"step": 344
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.025511500972857058,
|
| 2477 |
+
"grad_norm": 3.5641732215881348,
|
| 2478 |
+
"learning_rate": 0.00022292951041507028,
|
| 2479 |
+
"loss": 0.0075,
|
| 2480 |
+
"step": 345
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.025585447352488525,
|
| 2484 |
+
"grad_norm": 0.12729483842849731,
|
| 2485 |
+
"learning_rate": 0.00022251319258268453,
|
| 2486 |
+
"loss": 0.0027,
|
| 2487 |
+
"step": 346
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.025659393732119996,
|
| 2491 |
+
"grad_norm": 0.2512650787830353,
|
| 2492 |
+
"learning_rate": 0.00022209614454325459,
|
| 2493 |
+
"loss": 0.0099,
|
| 2494 |
+
"step": 347
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.025733340111751466,
|
| 2498 |
+
"grad_norm": 0.754295825958252,
|
| 2499 |
+
"learning_rate": 0.00022167837049644947,
|
| 2500 |
+
"loss": 0.0754,
|
| 2501 |
+
"step": 348
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.025807286491382937,
|
| 2505 |
+
"grad_norm": 0.0925987958908081,
|
| 2506 |
+
"learning_rate": 0.00022125987464924926,
|
| 2507 |
+
"loss": 0.0022,
|
| 2508 |
+
"step": 349
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.025881232871014407,
|
| 2512 |
+
"grad_norm": 1.8068702220916748,
|
| 2513 |
+
"learning_rate": 0.0002208406612159024,
|
| 2514 |
+
"loss": 0.0575,
|
| 2515 |
+
"step": 350
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.025881232871014407,
|
| 2519 |
+
"eval_loss": 0.019101565703749657,
|
| 2520 |
+
"eval_runtime": 28.2195,
|
| 2521 |
+
"eval_samples_per_second": 15.379,
|
| 2522 |
+
"eval_steps_per_second": 15.379,
|
| 2523 |
+
"step": 350
|
| 2524 |
}
|
| 2525 |
],
|
| 2526 |
"logging_steps": 1,
|
|
|
|
| 2535 |
"early_stopping_threshold": 0.0
|
| 2536 |
},
|
| 2537 |
"attributes": {
|
| 2538 |
+
"early_stopping_patience_counter": 3
|
| 2539 |
}
|
| 2540 |
},
|
| 2541 |
"TrainerControl": {
|
|
|
|
| 2544 |
"should_evaluate": false,
|
| 2545 |
"should_log": false,
|
| 2546 |
"should_save": true,
|
| 2547 |
+
"should_training_stop": true
|
| 2548 |
},
|
| 2549 |
"attributes": {}
|
| 2550 |
}
|
| 2551 |
},
|
| 2552 |
+
"total_flos": 1.0126848687734784e+16,
|
| 2553 |
"train_batch_size": 1,
|
| 2554 |
"trial_name": null,
|
| 2555 |
"trial_params": null
|