Training in progress, step 3000, 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 2384234968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a49264be75b7765ea678b9b59b3a697ee1aafcfc6ba700a2bb5029482f8d7bf
|
| 3 |
size 2384234968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4768663315
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f742f053229dbe9bb02cee7d2b024a0b812cecc2ca49ca71a2d415a2c2912a70
|
| 3 |
size 4768663315
|
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 sha256:29f59d5835f9b632408ae6ab68738905e125bd09ad3ec01adcf60d2207ea126d
|
| 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": 2.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2258,6 +2258,456 @@
|
|
| 2258 |
"mean_token_accuracy": 0.8223948117345572,
|
| 2259 |
"num_tokens": 20475904.0,
|
| 2260 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2261 |
}
|
| 2262 |
],
|
| 2263 |
"logging_steps": 10,
|
|
@@ -2277,7 +2727,7 @@
|
|
| 2277 |
"attributes": {}
|
| 2278 |
}
|
| 2279 |
},
|
| 2280 |
-
"total_flos":
|
| 2281 |
"train_batch_size": 2,
|
| 2282 |
"trial_name": null,
|
| 2283 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.88482808367396,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2258 |
"mean_token_accuracy": 0.8223948117345572,
|
| 2259 |
"num_tokens": 20475904.0,
|
| 2260 |
"step": 2500
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 2.4135609521519594,
|
| 2264 |
+
"grad_norm": 1.350571870803833,
|
| 2265 |
+
"learning_rate": 2.175925925925926e-06,
|
| 2266 |
+
"loss": 0.1403,
|
| 2267 |
+
"mean_token_accuracy": 0.829684441536665,
|
| 2268 |
+
"num_tokens": 20557824.0,
|
| 2269 |
+
"step": 2510
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 2.423178648713633,
|
| 2273 |
+
"grad_norm": 1.4614524841308594,
|
| 2274 |
+
"learning_rate": 2.1403133903133905e-06,
|
| 2275 |
+
"loss": 0.1627,
|
| 2276 |
+
"mean_token_accuracy": 0.8001100782305002,
|
| 2277 |
+
"num_tokens": 20639744.0,
|
| 2278 |
+
"step": 2520
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.4327963452753067,
|
| 2282 |
+
"grad_norm": 1.424734115600586,
|
| 2283 |
+
"learning_rate": 2.104700854700855e-06,
|
| 2284 |
+
"loss": 0.1476,
|
| 2285 |
+
"mean_token_accuracy": 0.8220401186496019,
|
| 2286 |
+
"num_tokens": 20721664.0,
|
| 2287 |
+
"step": 2530
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 2.44241404183698,
|
| 2291 |
+
"grad_norm": 1.10490882396698,
|
| 2292 |
+
"learning_rate": 2.069088319088319e-06,
|
| 2293 |
+
"loss": 0.1294,
|
| 2294 |
+
"mean_token_accuracy": 0.83066291436553,
|
| 2295 |
+
"num_tokens": 20803584.0,
|
| 2296 |
+
"step": 2540
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 2.4520317383986536,
|
| 2300 |
+
"grad_norm": 1.5091724395751953,
|
| 2301 |
+
"learning_rate": 2.033475783475784e-06,
|
| 2302 |
+
"loss": 0.122,
|
| 2303 |
+
"mean_token_accuracy": 0.8367049902677536,
|
| 2304 |
+
"num_tokens": 20885504.0,
|
| 2305 |
+
"step": 2550
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 2.461649434960327,
|
| 2309 |
+
"grad_norm": 1.088440179824829,
|
| 2310 |
+
"learning_rate": 1.9978632478632483e-06,
|
| 2311 |
+
"loss": 0.1233,
|
| 2312 |
+
"mean_token_accuracy": 0.8360934432595968,
|
| 2313 |
+
"num_tokens": 20967424.0,
|
| 2314 |
+
"step": 2560
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 2.4712671315220005,
|
| 2318 |
+
"grad_norm": 1.1838353872299194,
|
| 2319 |
+
"learning_rate": 1.962250712250712e-06,
|
| 2320 |
+
"loss": 0.1428,
|
| 2321 |
+
"mean_token_accuracy": 0.8347969647496939,
|
| 2322 |
+
"num_tokens": 21049344.0,
|
| 2323 |
+
"step": 2570
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 2.480884828083674,
|
| 2327 |
+
"grad_norm": 1.687991738319397,
|
| 2328 |
+
"learning_rate": 1.9266381766381765e-06,
|
| 2329 |
+
"loss": 0.1543,
|
| 2330 |
+
"mean_token_accuracy": 0.808084636554122,
|
| 2331 |
+
"num_tokens": 21131264.0,
|
| 2332 |
+
"step": 2580
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 2.4905025246453474,
|
| 2336 |
+
"grad_norm": 0.9223553538322449,
|
| 2337 |
+
"learning_rate": 1.891025641025641e-06,
|
| 2338 |
+
"loss": 0.1155,
|
| 2339 |
+
"mean_token_accuracy": 0.8487157512456178,
|
| 2340 |
+
"num_tokens": 21213184.0,
|
| 2341 |
+
"step": 2590
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.500120221207021,
|
| 2345 |
+
"grad_norm": 1.4413843154907227,
|
| 2346 |
+
"learning_rate": 1.8554131054131056e-06,
|
| 2347 |
+
"loss": 0.135,
|
| 2348 |
+
"mean_token_accuracy": 0.8379280813038349,
|
| 2349 |
+
"num_tokens": 21295104.0,
|
| 2350 |
+
"step": 2600
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 2.5097379177686943,
|
| 2354 |
+
"grad_norm": 1.0525134801864624,
|
| 2355 |
+
"learning_rate": 1.81980056980057e-06,
|
| 2356 |
+
"loss": 0.14,
|
| 2357 |
+
"mean_token_accuracy": 0.8360812149941921,
|
| 2358 |
+
"num_tokens": 21377024.0,
|
| 2359 |
+
"step": 2610
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 2.519355614330368,
|
| 2363 |
+
"grad_norm": 1.246717095375061,
|
| 2364 |
+
"learning_rate": 1.7841880341880343e-06,
|
| 2365 |
+
"loss": 0.1511,
|
| 2366 |
+
"mean_token_accuracy": 0.827531798556447,
|
| 2367 |
+
"num_tokens": 21458944.0,
|
| 2368 |
+
"step": 2620
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 2.5289733108920416,
|
| 2372 |
+
"grad_norm": 1.5476717948913574,
|
| 2373 |
+
"learning_rate": 1.7485754985754989e-06,
|
| 2374 |
+
"loss": 0.1471,
|
| 2375 |
+
"mean_token_accuracy": 0.8342710375785828,
|
| 2376 |
+
"num_tokens": 21540864.0,
|
| 2377 |
+
"step": 2630
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 2.538591007453715,
|
| 2381 |
+
"grad_norm": 0.9907192587852478,
|
| 2382 |
+
"learning_rate": 1.7129629629629632e-06,
|
| 2383 |
+
"loss": 0.1281,
|
| 2384 |
+
"mean_token_accuracy": 0.8439823880791664,
|
| 2385 |
+
"num_tokens": 21622784.0,
|
| 2386 |
+
"step": 2640
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 2.5482087040153885,
|
| 2390 |
+
"grad_norm": 1.137152910232544,
|
| 2391 |
+
"learning_rate": 1.6773504273504274e-06,
|
| 2392 |
+
"loss": 0.1273,
|
| 2393 |
+
"mean_token_accuracy": 0.8406555730849504,
|
| 2394 |
+
"num_tokens": 21704704.0,
|
| 2395 |
+
"step": 2650
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 2.5578264005770617,
|
| 2399 |
+
"grad_norm": 1.1246287822723389,
|
| 2400 |
+
"learning_rate": 1.6417378917378917e-06,
|
| 2401 |
+
"loss": 0.1161,
|
| 2402 |
+
"mean_token_accuracy": 0.8306873764842748,
|
| 2403 |
+
"num_tokens": 21786624.0,
|
| 2404 |
+
"step": 2660
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.5674440971387353,
|
| 2408 |
+
"grad_norm": 1.2270443439483643,
|
| 2409 |
+
"learning_rate": 1.6061253561253563e-06,
|
| 2410 |
+
"loss": 0.1478,
|
| 2411 |
+
"mean_token_accuracy": 0.8372553810477257,
|
| 2412 |
+
"num_tokens": 21868544.0,
|
| 2413 |
+
"step": 2670
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 2.577061793700409,
|
| 2417 |
+
"grad_norm": 1.3623789548873901,
|
| 2418 |
+
"learning_rate": 1.5705128205128206e-06,
|
| 2419 |
+
"loss": 0.1489,
|
| 2420 |
+
"mean_token_accuracy": 0.8291340474039316,
|
| 2421 |
+
"num_tokens": 21950464.0,
|
| 2422 |
+
"step": 2680
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"epoch": 2.586679490262082,
|
| 2426 |
+
"grad_norm": 0.8751484751701355,
|
| 2427 |
+
"learning_rate": 1.534900284900285e-06,
|
| 2428 |
+
"loss": 0.1659,
|
| 2429 |
+
"mean_token_accuracy": 0.8064823867753148,
|
| 2430 |
+
"num_tokens": 22032384.0,
|
| 2431 |
+
"step": 2690
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 2.596297186823756,
|
| 2435 |
+
"grad_norm": 1.0951944589614868,
|
| 2436 |
+
"learning_rate": 1.4992877492877495e-06,
|
| 2437 |
+
"loss": 0.1433,
|
| 2438 |
+
"mean_token_accuracy": 0.828779349476099,
|
| 2439 |
+
"num_tokens": 22114304.0,
|
| 2440 |
+
"step": 2700
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 2.605914883385429,
|
| 2444 |
+
"grad_norm": 1.2346906661987305,
|
| 2445 |
+
"learning_rate": 1.4636752136752138e-06,
|
| 2446 |
+
"loss": 0.1502,
|
| 2447 |
+
"mean_token_accuracy": 0.8060298431664705,
|
| 2448 |
+
"num_tokens": 22196224.0,
|
| 2449 |
+
"step": 2710
|
| 2450 |
+
},
|
| 2451 |
+
{
|
| 2452 |
+
"epoch": 2.6155325799471028,
|
| 2453 |
+
"grad_norm": 1.6823463439941406,
|
| 2454 |
+
"learning_rate": 1.4280626780626784e-06,
|
| 2455 |
+
"loss": 0.1778,
|
| 2456 |
+
"mean_token_accuracy": 0.7855185937136412,
|
| 2457 |
+
"num_tokens": 22278144.0,
|
| 2458 |
+
"step": 2720
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.6251502765087764,
|
| 2462 |
+
"grad_norm": 1.1732553243637085,
|
| 2463 |
+
"learning_rate": 1.3924501424501425e-06,
|
| 2464 |
+
"loss": 0.1529,
|
| 2465 |
+
"mean_token_accuracy": 0.8153375726193189,
|
| 2466 |
+
"num_tokens": 22360064.0,
|
| 2467 |
+
"step": 2730
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.6347679730704496,
|
| 2471 |
+
"grad_norm": 0.921587347984314,
|
| 2472 |
+
"learning_rate": 1.3568376068376069e-06,
|
| 2473 |
+
"loss": 0.135,
|
| 2474 |
+
"mean_token_accuracy": 0.8219545006752014,
|
| 2475 |
+
"num_tokens": 22441984.0,
|
| 2476 |
+
"step": 2740
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 2.644385669632123,
|
| 2480 |
+
"grad_norm": 1.4507887363433838,
|
| 2481 |
+
"learning_rate": 1.3212250712250712e-06,
|
| 2482 |
+
"loss": 0.1432,
|
| 2483 |
+
"mean_token_accuracy": 0.8294031292200088,
|
| 2484 |
+
"num_tokens": 22523904.0,
|
| 2485 |
+
"step": 2750
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 2.6540033661937965,
|
| 2489 |
+
"grad_norm": 1.614626169204712,
|
| 2490 |
+
"learning_rate": 1.2856125356125358e-06,
|
| 2491 |
+
"loss": 0.1658,
|
| 2492 |
+
"mean_token_accuracy": 0.8020303327590227,
|
| 2493 |
+
"num_tokens": 22605824.0,
|
| 2494 |
+
"step": 2760
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 2.66362106275547,
|
| 2498 |
+
"grad_norm": 0.9506202340126038,
|
| 2499 |
+
"learning_rate": 1.25e-06,
|
| 2500 |
+
"loss": 0.1229,
|
| 2501 |
+
"mean_token_accuracy": 0.8390044014900923,
|
| 2502 |
+
"num_tokens": 22687744.0,
|
| 2503 |
+
"step": 2770
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 2.6732387593171434,
|
| 2507 |
+
"grad_norm": 1.1267729997634888,
|
| 2508 |
+
"learning_rate": 1.2143874643874644e-06,
|
| 2509 |
+
"loss": 0.1409,
|
| 2510 |
+
"mean_token_accuracy": 0.8417808238416911,
|
| 2511 |
+
"num_tokens": 22769664.0,
|
| 2512 |
+
"step": 2780
|
| 2513 |
+
},
|
| 2514 |
+
{
|
| 2515 |
+
"epoch": 2.682856455878817,
|
| 2516 |
+
"grad_norm": 0.9731321930885315,
|
| 2517 |
+
"learning_rate": 1.178774928774929e-06,
|
| 2518 |
+
"loss": 0.1481,
|
| 2519 |
+
"mean_token_accuracy": 0.8307118374854326,
|
| 2520 |
+
"num_tokens": 22851584.0,
|
| 2521 |
+
"step": 2790
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 2.6924741524404903,
|
| 2525 |
+
"grad_norm": 1.5113604068756104,
|
| 2526 |
+
"learning_rate": 1.1431623931623931e-06,
|
| 2527 |
+
"loss": 0.1493,
|
| 2528 |
+
"mean_token_accuracy": 0.8170865952968598,
|
| 2529 |
+
"num_tokens": 22933504.0,
|
| 2530 |
+
"step": 2800
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.702091849002164,
|
| 2534 |
+
"grad_norm": 1.5031578540802002,
|
| 2535 |
+
"learning_rate": 1.1075498575498577e-06,
|
| 2536 |
+
"loss": 0.1333,
|
| 2537 |
+
"mean_token_accuracy": 0.8457436379045248,
|
| 2538 |
+
"num_tokens": 23015424.0,
|
| 2539 |
+
"step": 2810
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 2.7117095455638376,
|
| 2543 |
+
"grad_norm": 0.9475900530815125,
|
| 2544 |
+
"learning_rate": 1.071937321937322e-06,
|
| 2545 |
+
"loss": 0.1533,
|
| 2546 |
+
"mean_token_accuracy": 0.8175391405820847,
|
| 2547 |
+
"num_tokens": 23097344.0,
|
| 2548 |
+
"step": 2820
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"epoch": 2.721327242125511,
|
| 2552 |
+
"grad_norm": 1.1415244340896606,
|
| 2553 |
+
"learning_rate": 1.0363247863247866e-06,
|
| 2554 |
+
"loss": 0.1325,
|
| 2555 |
+
"mean_token_accuracy": 0.8296232886612416,
|
| 2556 |
+
"num_tokens": 23179264.0,
|
| 2557 |
+
"step": 2830
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 2.7309449386871845,
|
| 2561 |
+
"grad_norm": 1.2204571962356567,
|
| 2562 |
+
"learning_rate": 1.0007122507122507e-06,
|
| 2563 |
+
"loss": 0.1314,
|
| 2564 |
+
"mean_token_accuracy": 0.8463918767869473,
|
| 2565 |
+
"num_tokens": 23261184.0,
|
| 2566 |
+
"step": 2840
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 2.7405626352488577,
|
| 2570 |
+
"grad_norm": 1.4655503034591675,
|
| 2571 |
+
"learning_rate": 9.650997150997153e-07,
|
| 2572 |
+
"loss": 0.1492,
|
| 2573 |
+
"mean_token_accuracy": 0.8253546953201294,
|
| 2574 |
+
"num_tokens": 23343104.0,
|
| 2575 |
+
"step": 2850
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 2.7501803318105313,
|
| 2579 |
+
"grad_norm": 1.8217484951019287,
|
| 2580 |
+
"learning_rate": 9.294871794871796e-07,
|
| 2581 |
+
"loss": 0.148,
|
| 2582 |
+
"mean_token_accuracy": 0.8358488243073225,
|
| 2583 |
+
"num_tokens": 23425024.0,
|
| 2584 |
+
"step": 2860
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 2.759798028372205,
|
| 2588 |
+
"grad_norm": 1.4163944721221924,
|
| 2589 |
+
"learning_rate": 8.938746438746441e-07,
|
| 2590 |
+
"loss": 0.1626,
|
| 2591 |
+
"mean_token_accuracy": 0.8236545998603105,
|
| 2592 |
+
"num_tokens": 23506944.0,
|
| 2593 |
+
"step": 2870
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.769415724933878,
|
| 2597 |
+
"grad_norm": 1.2180320024490356,
|
| 2598 |
+
"learning_rate": 8.582621082621083e-07,
|
| 2599 |
+
"loss": 0.1444,
|
| 2600 |
+
"mean_token_accuracy": 0.817331212759018,
|
| 2601 |
+
"num_tokens": 23588864.0,
|
| 2602 |
+
"step": 2880
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 2.779033421495552,
|
| 2606 |
+
"grad_norm": 1.457688808441162,
|
| 2607 |
+
"learning_rate": 8.226495726495727e-07,
|
| 2608 |
+
"loss": 0.1272,
|
| 2609 |
+
"mean_token_accuracy": 0.8441291574388743,
|
| 2610 |
+
"num_tokens": 23670784.0,
|
| 2611 |
+
"step": 2890
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"epoch": 2.788651118057225,
|
| 2615 |
+
"grad_norm": 1.5352418422698975,
|
| 2616 |
+
"learning_rate": 7.870370370370371e-07,
|
| 2617 |
+
"loss": 0.1599,
|
| 2618 |
+
"mean_token_accuracy": 0.8156800389289856,
|
| 2619 |
+
"num_tokens": 23752704.0,
|
| 2620 |
+
"step": 2900
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 2.7982688146188988,
|
| 2624 |
+
"grad_norm": 1.1528174877166748,
|
| 2625 |
+
"learning_rate": 7.514245014245015e-07,
|
| 2626 |
+
"loss": 0.142,
|
| 2627 |
+
"mean_token_accuracy": 0.8310543041676283,
|
| 2628 |
+
"num_tokens": 23834624.0,
|
| 2629 |
+
"step": 2910
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 2.8078865111805724,
|
| 2633 |
+
"grad_norm": 0.9919131994247437,
|
| 2634 |
+
"learning_rate": 7.158119658119659e-07,
|
| 2635 |
+
"loss": 0.1517,
|
| 2636 |
+
"mean_token_accuracy": 0.8280088048428297,
|
| 2637 |
+
"num_tokens": 23916544.0,
|
| 2638 |
+
"step": 2920
|
| 2639 |
+
},
|
| 2640 |
+
{
|
| 2641 |
+
"epoch": 2.8175042077422456,
|
| 2642 |
+
"grad_norm": 1.1298660039901733,
|
| 2643 |
+
"learning_rate": 6.801994301994302e-07,
|
| 2644 |
+
"loss": 0.1282,
|
| 2645 |
+
"mean_token_accuracy": 0.8396893307566643,
|
| 2646 |
+
"num_tokens": 23998464.0,
|
| 2647 |
+
"step": 2930
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 2.8271219043039193,
|
| 2651 |
+
"grad_norm": 1.4493669271469116,
|
| 2652 |
+
"learning_rate": 6.445868945868947e-07,
|
| 2653 |
+
"loss": 0.1474,
|
| 2654 |
+
"mean_token_accuracy": 0.8369129169732332,
|
| 2655 |
+
"num_tokens": 24080384.0,
|
| 2656 |
+
"step": 2940
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.8367396008655925,
|
| 2660 |
+
"grad_norm": 1.313490390777588,
|
| 2661 |
+
"learning_rate": 6.08974358974359e-07,
|
| 2662 |
+
"loss": 0.1356,
|
| 2663 |
+
"mean_token_accuracy": 0.8197651654481888,
|
| 2664 |
+
"num_tokens": 24162304.0,
|
| 2665 |
+
"step": 2950
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.846357297427266,
|
| 2669 |
+
"grad_norm": 1.632154107093811,
|
| 2670 |
+
"learning_rate": 5.733618233618235e-07,
|
| 2671 |
+
"loss": 0.1636,
|
| 2672 |
+
"mean_token_accuracy": 0.8243272993713617,
|
| 2673 |
+
"num_tokens": 24244224.0,
|
| 2674 |
+
"step": 2960
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 2.85597499398894,
|
| 2678 |
+
"grad_norm": 1.3894017934799194,
|
| 2679 |
+
"learning_rate": 5.377492877492878e-07,
|
| 2680 |
+
"loss": 0.16,
|
| 2681 |
+
"mean_token_accuracy": 0.8183586075901985,
|
| 2682 |
+
"num_tokens": 24326144.0,
|
| 2683 |
+
"step": 2970
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 2.865592690550613,
|
| 2687 |
+
"grad_norm": 1.0274466276168823,
|
| 2688 |
+
"learning_rate": 5.021367521367522e-07,
|
| 2689 |
+
"loss": 0.1246,
|
| 2690 |
+
"mean_token_accuracy": 0.8431629177182913,
|
| 2691 |
+
"num_tokens": 24408064.0,
|
| 2692 |
+
"step": 2980
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 2.8752103871122867,
|
| 2696 |
+
"grad_norm": 1.2301019430160522,
|
| 2697 |
+
"learning_rate": 4.6652421652421653e-07,
|
| 2698 |
+
"loss": 0.1283,
|
| 2699 |
+
"mean_token_accuracy": 0.8367906074970961,
|
| 2700 |
+
"num_tokens": 24489984.0,
|
| 2701 |
+
"step": 2990
|
| 2702 |
+
},
|
| 2703 |
+
{
|
| 2704 |
+
"epoch": 2.88482808367396,
|
| 2705 |
+
"grad_norm": 1.6906356811523438,
|
| 2706 |
+
"learning_rate": 4.30911680911681e-07,
|
| 2707 |
+
"loss": 0.1407,
|
| 2708 |
+
"mean_token_accuracy": 0.8170743655413389,
|
| 2709 |
+
"num_tokens": 24571904.0,
|
| 2710 |
+
"step": 3000
|
| 2711 |
}
|
| 2712 |
],
|
| 2713 |
"logging_steps": 10,
|
|
|
|
| 2727 |
"attributes": {}
|
| 2728 |
}
|
| 2729 |
},
|
| 2730 |
+
"total_flos": 6.493874426373734e+16,
|
| 2731 |
"train_batch_size": 2,
|
| 2732 |
"trial_name": null,
|
| 2733 |
"trial_params": null
|