Training in progress, step 342, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +306 -4
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1521616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:368e00a32e5e67904cdc68fad7b0d3ebbf6aa48a43908471978f2a2f044c71d6
|
| 3 |
size 1521616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3108666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13f99e35e1cd72dd67928139d82e8f270376e333cc058eeeca058766e79fd6da
|
| 3 |
size 3108666
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b725e55dc7e3cfcd2470e0b973a56ed83568003bb225faa55cd6d2bf9770b30b
|
| 3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3322560e39a902081358f17ff4055da3283ebe3e2fa1e6b657dab85c86236f7
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea66678ca299dd2b3d155e3c39e632e66dc28be0c18e9664e7c6b137c3f76689
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f314b3eeeb0bd949fe539d551bea83f6ef4f1ddb092c681433bf0279c6b7fe91
|
| 3 |
size 15024
|
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 sha256:0aa55a29e9da8bc1ccf97b1a76ccd03130ba0539481d5a33300527a24e5c40c2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 6.472244739532471,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-300",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2211,6 +2211,308 @@
|
|
| 2211 |
"eval_samples_per_second": 249.929,
|
| 2212 |
"eval_steps_per_second": 64.982,
|
| 2213 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2214 |
}
|
| 2215 |
],
|
| 2216 |
"logging_steps": 1,
|
|
@@ -2234,12 +2536,12 @@
|
|
| 2234 |
"should_evaluate": false,
|
| 2235 |
"should_log": false,
|
| 2236 |
"should_save": true,
|
| 2237 |
-
"should_training_stop":
|
| 2238 |
},
|
| 2239 |
"attributes": {}
|
| 2240 |
}
|
| 2241 |
},
|
| 2242 |
-
"total_flos":
|
| 2243 |
"train_batch_size": 1,
|
| 2244 |
"trial_name": null,
|
| 2245 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 6.472244739532471,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-300",
|
| 4 |
+
"epoch": 0.08817202568461421,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 342,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2211 |
"eval_samples_per_second": 249.929,
|
| 2212 |
"eval_steps_per_second": 64.982,
|
| 2213 |
"step": 300
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 0.07760169512008443,
|
| 2217 |
+
"grad_norm": 1.2554875612258911,
|
| 2218 |
+
"learning_rate": 1.3404895720259053e-05,
|
| 2219 |
+
"loss": 7.3701,
|
| 2220 |
+
"step": 301
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 0.07785950806068272,
|
| 2224 |
+
"grad_norm": 0.8463560342788696,
|
| 2225 |
+
"learning_rate": 1.3242829026768597e-05,
|
| 2226 |
+
"loss": 6.4277,
|
| 2227 |
+
"step": 302
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 0.078117321001281,
|
| 2231 |
+
"grad_norm": 0.644782304763794,
|
| 2232 |
+
"learning_rate": 1.3084569796502682e-05,
|
| 2233 |
+
"loss": 6.356,
|
| 2234 |
+
"step": 303
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 0.0783751339418793,
|
| 2238 |
+
"grad_norm": 0.7398347854614258,
|
| 2239 |
+
"learning_rate": 1.293013245970609e-05,
|
| 2240 |
+
"loss": 6.2324,
|
| 2241 |
+
"step": 304
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.07863294688247759,
|
| 2245 |
+
"grad_norm": 0.5900807976722717,
|
| 2246 |
+
"learning_rate": 1.2779531098139333e-05,
|
| 2247 |
+
"loss": 6.1167,
|
| 2248 |
+
"step": 305
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 0.07889075982307588,
|
| 2252 |
+
"grad_norm": 0.6693830490112305,
|
| 2253 |
+
"learning_rate": 1.263277944379459e-05,
|
| 2254 |
+
"loss": 6.2377,
|
| 2255 |
+
"step": 306
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.07914857276367415,
|
| 2259 |
+
"grad_norm": 0.6465635895729065,
|
| 2260 |
+
"learning_rate": 1.248989087764366e-05,
|
| 2261 |
+
"loss": 6.1853,
|
| 2262 |
+
"step": 307
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 0.07940638570427244,
|
| 2266 |
+
"grad_norm": 0.6336793303489685,
|
| 2267 |
+
"learning_rate": 1.2350878428417839e-05,
|
| 2268 |
+
"loss": 5.9979,
|
| 2269 |
+
"step": 308
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.07966419864487073,
|
| 2273 |
+
"grad_norm": 0.6897872090339661,
|
| 2274 |
+
"learning_rate": 1.2215754771419997e-05,
|
| 2275 |
+
"loss": 6.0263,
|
| 2276 |
+
"step": 309
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 0.07992201158546902,
|
| 2280 |
+
"grad_norm": 0.7997320294380188,
|
| 2281 |
+
"learning_rate": 1.2084532227368761e-05,
|
| 2282 |
+
"loss": 6.3959,
|
| 2283 |
+
"step": 310
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 0.08017982452606731,
|
| 2287 |
+
"grad_norm": 1.0460010766983032,
|
| 2288 |
+
"learning_rate": 1.1957222761275149e-05,
|
| 2289 |
+
"loss": 6.7064,
|
| 2290 |
+
"step": 311
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 0.08043763746666559,
|
| 2294 |
+
"grad_norm": 1.4831907749176025,
|
| 2295 |
+
"learning_rate": 1.183383798135157e-05,
|
| 2296 |
+
"loss": 6.8091,
|
| 2297 |
+
"step": 312
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.08069545040726388,
|
| 2301 |
+
"grad_norm": 2.0493836402893066,
|
| 2302 |
+
"learning_rate": 1.171438913795338e-05,
|
| 2303 |
+
"loss": 7.5173,
|
| 2304 |
+
"step": 313
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 0.08095326334786217,
|
| 2308 |
+
"grad_norm": 1.0544261932373047,
|
| 2309 |
+
"learning_rate": 1.1598887122553061e-05,
|
| 2310 |
+
"loss": 6.7366,
|
| 2311 |
+
"step": 314
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.08121107628846046,
|
| 2315 |
+
"grad_norm": 0.7413960099220276,
|
| 2316 |
+
"learning_rate": 1.1487342466747112e-05,
|
| 2317 |
+
"loss": 6.2798,
|
| 2318 |
+
"step": 315
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 0.08146888922905875,
|
| 2322 |
+
"grad_norm": 0.6017177700996399,
|
| 2323 |
+
"learning_rate": 1.137976534129579e-05,
|
| 2324 |
+
"loss": 6.3163,
|
| 2325 |
+
"step": 316
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.08172670216965702,
|
| 2329 |
+
"grad_norm": 0.6235430240631104,
|
| 2330 |
+
"learning_rate": 1.127616555519573e-05,
|
| 2331 |
+
"loss": 6.2398,
|
| 2332 |
+
"step": 317
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 0.08198451511025531,
|
| 2336 |
+
"grad_norm": 0.6497268676757812,
|
| 2337 |
+
"learning_rate": 1.1176552554785504e-05,
|
| 2338 |
+
"loss": 6.2297,
|
| 2339 |
+
"step": 318
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 0.0822423280508536,
|
| 2343 |
+
"grad_norm": 0.6185296177864075,
|
| 2344 |
+
"learning_rate": 1.1080935422884358e-05,
|
| 2345 |
+
"loss": 6.0099,
|
| 2346 |
+
"step": 319
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 0.08250014099145189,
|
| 2350 |
+
"grad_norm": 0.7389028668403625,
|
| 2351 |
+
"learning_rate": 1.0989322877963985e-05,
|
| 2352 |
+
"loss": 5.8818,
|
| 2353 |
+
"step": 320
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 0.08275795393205018,
|
| 2357 |
+
"grad_norm": 0.7540916204452515,
|
| 2358 |
+
"learning_rate": 1.0901723273353597e-05,
|
| 2359 |
+
"loss": 6.1902,
|
| 2360 |
+
"step": 321
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 0.08301576687264846,
|
| 2364 |
+
"grad_norm": 0.7044777274131775,
|
| 2365 |
+
"learning_rate": 1.0818144596478224e-05,
|
| 2366 |
+
"loss": 6.1747,
|
| 2367 |
+
"step": 322
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 0.08327357981324675,
|
| 2371 |
+
"grad_norm": 0.9389222264289856,
|
| 2372 |
+
"learning_rate": 1.0738594468130452e-05,
|
| 2373 |
+
"loss": 6.479,
|
| 2374 |
+
"step": 323
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.08353139275384504,
|
| 2378 |
+
"grad_norm": 1.1994636058807373,
|
| 2379 |
+
"learning_rate": 1.0663080141775504e-05,
|
| 2380 |
+
"loss": 6.6693,
|
| 2381 |
+
"step": 324
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.08378920569444333,
|
| 2385 |
+
"grad_norm": 3.2903223037719727,
|
| 2386 |
+
"learning_rate": 1.0591608502889928e-05,
|
| 2387 |
+
"loss": 6.1876,
|
| 2388 |
+
"step": 325
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.08378920569444333,
|
| 2392 |
+
"eval_loss": 6.461916446685791,
|
| 2393 |
+
"eval_runtime": 0.1956,
|
| 2394 |
+
"eval_samples_per_second": 255.68,
|
| 2395 |
+
"eval_steps_per_second": 66.477,
|
| 2396 |
+
"step": 325
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.08404701863504162,
|
| 2400 |
+
"grad_norm": 1.2868388891220093,
|
| 2401 |
+
"learning_rate": 1.0524186068333692e-05,
|
| 2402 |
+
"loss": 7.4553,
|
| 2403 |
+
"step": 326
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.0843048315756399,
|
| 2407 |
+
"grad_norm": 0.8954585194587708,
|
| 2408 |
+
"learning_rate": 1.046081898575604e-05,
|
| 2409 |
+
"loss": 6.399,
|
| 2410 |
+
"step": 327
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.08456264451623818,
|
| 2414 |
+
"grad_norm": 0.612129807472229,
|
| 2415 |
+
"learning_rate": 1.04015130330349e-05,
|
| 2416 |
+
"loss": 6.4022,
|
| 2417 |
+
"step": 328
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.08482045745683647,
|
| 2421 |
+
"grad_norm": 0.6739881634712219,
|
| 2422 |
+
"learning_rate": 1.0346273617750057e-05,
|
| 2423 |
+
"loss": 6.0706,
|
| 2424 |
+
"step": 329
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.08507827039743476,
|
| 2428 |
+
"grad_norm": 0.7707552909851074,
|
| 2429 |
+
"learning_rate": 1.0295105776690108e-05,
|
| 2430 |
+
"loss": 6.0031,
|
| 2431 |
+
"step": 330
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.08533608333803305,
|
| 2435 |
+
"grad_norm": 0.7329960465431213,
|
| 2436 |
+
"learning_rate": 1.0248014175393177e-05,
|
| 2437 |
+
"loss": 6.1073,
|
| 2438 |
+
"step": 331
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.08559389627863133,
|
| 2442 |
+
"grad_norm": 0.7465705275535583,
|
| 2443 |
+
"learning_rate": 1.0205003107721506e-05,
|
| 2444 |
+
"loss": 6.0385,
|
| 2445 |
+
"step": 332
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.08585170921922962,
|
| 2449 |
+
"grad_norm": 0.6375886797904968,
|
| 2450 |
+
"learning_rate": 1.0166076495469963e-05,
|
| 2451 |
+
"loss": 6.0305,
|
| 2452 |
+
"step": 333
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.08610952215982791,
|
| 2456 |
+
"grad_norm": 0.7056543231010437,
|
| 2457 |
+
"learning_rate": 1.0131237888008412e-05,
|
| 2458 |
+
"loss": 6.1335,
|
| 2459 |
+
"step": 334
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.0863673351004262,
|
| 2463 |
+
"grad_norm": 0.8683858513832092,
|
| 2464 |
+
"learning_rate": 1.0100490461958109e-05,
|
| 2465 |
+
"loss": 6.3272,
|
| 2466 |
+
"step": 335
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.08662514804102449,
|
| 2470 |
+
"grad_norm": 0.9683743119239807,
|
| 2471 |
+
"learning_rate": 1.0073837020902033e-05,
|
| 2472 |
+
"loss": 6.5318,
|
| 2473 |
+
"step": 336
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.08688296098162278,
|
| 2477 |
+
"grad_norm": 1.4957187175750732,
|
| 2478 |
+
"learning_rate": 1.0051279995129273e-05,
|
| 2479 |
+
"loss": 6.8366,
|
| 2480 |
+
"step": 337
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.08714077392222105,
|
| 2484 |
+
"grad_norm": 1.5700278282165527,
|
| 2485 |
+
"learning_rate": 1.0032821441413394e-05,
|
| 2486 |
+
"loss": 7.7112,
|
| 2487 |
+
"step": 338
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.08739858686281934,
|
| 2491 |
+
"grad_norm": 1.0813219547271729,
|
| 2492 |
+
"learning_rate": 1.0018463042824957e-05,
|
| 2493 |
+
"loss": 6.923,
|
| 2494 |
+
"step": 339
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.08765639980341763,
|
| 2498 |
+
"grad_norm": 0.6960993409156799,
|
| 2499 |
+
"learning_rate": 1.0008206108577992e-05,
|
| 2500 |
+
"loss": 6.4607,
|
| 2501 |
+
"step": 340
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.08791421274401592,
|
| 2505 |
+
"grad_norm": 0.6256797313690186,
|
| 2506 |
+
"learning_rate": 1.0002051573910671e-05,
|
| 2507 |
+
"loss": 6.3162,
|
| 2508 |
+
"step": 341
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.08817202568461421,
|
| 2512 |
+
"grad_norm": 0.5889110565185547,
|
| 2513 |
+
"learning_rate": 1e-05,
|
| 2514 |
+
"loss": 6.0812,
|
| 2515 |
+
"step": 342
|
| 2516 |
}
|
| 2517 |
],
|
| 2518 |
"logging_steps": 1,
|
|
|
|
| 2536 |
"should_evaluate": false,
|
| 2537 |
"should_log": false,
|
| 2538 |
"should_save": true,
|
| 2539 |
+
"should_training_stop": true
|
| 2540 |
},
|
| 2541 |
"attributes": {}
|
| 2542 |
}
|
| 2543 |
},
|
| 2544 |
+
"total_flos": 3177646474133504.0,
|
| 2545 |
"train_batch_size": 1,
|
| 2546 |
"trial_name": null,
|
| 2547 |
"trial_params": null
|