error577 commited on
Commit
491bcaa
·
verified ·
1 Parent(s): 8d9ce71

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:a380c2863c79af247d96d6850191d235a6db52061a5724a076c0dd239c9f504c
3
  size 1279323952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552e477a98c0768adcd4647d633d95db645032bd3f24e1fbfae67c6bab7019be
3
  size 1279323952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bf5c79e2d4caba6d6b955ef8f298c069c385488cd86f05df41634db3f2abc48
3
  size 650153044
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398600ed212b3e574407dad7720c69a44d8b3f066be917bd7839a180244a2e8b
3
  size 650153044
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91556d821de6d4edd57a622971805ecea7b0d8d7ba486bacda72e26999bdf356
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c974a18173c5b253003de5cec0751303a41dda5f56e281ac6e5b3f9dfe4eec8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a29bcee20d4efb76c3fc52ec9e4c8bd30e6af1b1acd2ceb28a084d03e0ab190
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef796d1416c59d81a908d0d533ec75f7cbfbe54b55c3fcdeb18a69501c216c1e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.4393945932388306,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
- "epoch": 0.06552990484511734,
5
  "eval_steps": 50,
6
- "global_step": 300,
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": 4.645,
2164
  "eval_steps_per_second": 4.645,
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": 2
2181
  }
2182
  },
2183
  "TrainerControl": {
@@ -2186,12 +2544,12 @@
2186
  "should_evaluate": false,
2187
  "should_log": false,
2188
  "should_save": true,
2189
- "should_training_stop": false
2190
  },
2191
  "attributes": {}
2192
  }
2193
  },
2194
- "total_flos": 1.0216640034845491e+17,
2195
  "train_batch_size": 1,
2196
  "trial_name": null,
2197
  "trial_params": null
 
1
  {
2
  "best_metric": 1.4393945932388306,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.0764515556526369,
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": 4.645,
2164
  "eval_steps_per_second": 4.645,
2165
  "step": 300
2166
+ },
2167
+ {
2168
+ "epoch": 0.06574833786126773,
2169
+ "grad_norm": 1.63740873336792,
2170
+ "learning_rate": 0.0002996673213206589,
2171
+ "loss": 1.9815,
2172
+ "step": 301
2173
+ },
2174
+ {
2175
+ "epoch": 0.06596677087741812,
2176
+ "grad_norm": 1.046769380569458,
2177
+ "learning_rate": 0.000299665031793473,
2178
+ "loss": 1.6878,
2179
+ "step": 302
2180
+ },
2181
+ {
2182
+ "epoch": 0.06618520389356851,
2183
+ "grad_norm": 0.513561487197876,
2184
+ "learning_rate": 0.0002996627344237122,
2185
+ "loss": 1.5141,
2186
+ "step": 303
2187
+ },
2188
+ {
2189
+ "epoch": 0.0664036369097189,
2190
+ "grad_norm": 0.38992562890052795,
2191
+ "learning_rate": 0.0002996604292114971,
2192
+ "loss": 1.1818,
2193
+ "step": 304
2194
+ },
2195
+ {
2196
+ "epoch": 0.06662206992586929,
2197
+ "grad_norm": 0.4074482023715973,
2198
+ "learning_rate": 0.00029965811615694844,
2199
+ "loss": 1.4627,
2200
+ "step": 305
2201
+ },
2202
+ {
2203
+ "epoch": 0.06684050294201968,
2204
+ "grad_norm": 0.41403788328170776,
2205
+ "learning_rate": 0.0002996557952601874,
2206
+ "loss": 1.5682,
2207
+ "step": 306
2208
+ },
2209
+ {
2210
+ "epoch": 0.06705893595817007,
2211
+ "grad_norm": 0.4047700762748718,
2212
+ "learning_rate": 0.00029965346652133565,
2213
+ "loss": 1.0902,
2214
+ "step": 307
2215
+ },
2216
+ {
2217
+ "epoch": 0.06727736897432046,
2218
+ "grad_norm": 0.4367327094078064,
2219
+ "learning_rate": 0.0002996511299405151,
2220
+ "loss": 1.3241,
2221
+ "step": 308
2222
+ },
2223
+ {
2224
+ "epoch": 0.06749580199047087,
2225
+ "grad_norm": 0.40244677662849426,
2226
+ "learning_rate": 0.0002996487855178483,
2227
+ "loss": 1.2218,
2228
+ "step": 309
2229
+ },
2230
+ {
2231
+ "epoch": 0.06771423500662126,
2232
+ "grad_norm": 0.42241427302360535,
2233
+ "learning_rate": 0.0002996464332534581,
2234
+ "loss": 1.0742,
2235
+ "step": 310
2236
+ },
2237
+ {
2238
+ "epoch": 0.06793266802277165,
2239
+ "grad_norm": 0.4748789966106415,
2240
+ "learning_rate": 0.00029964407314746764,
2241
+ "loss": 1.3064,
2242
+ "step": 311
2243
+ },
2244
+ {
2245
+ "epoch": 0.06815110103892204,
2246
+ "grad_norm": 0.4514020085334778,
2247
+ "learning_rate": 0.00029964170520000073,
2248
+ "loss": 1.1954,
2249
+ "step": 312
2250
+ },
2251
+ {
2252
+ "epoch": 0.06836953405507243,
2253
+ "grad_norm": 0.5442508459091187,
2254
+ "learning_rate": 0.0002996393294111814,
2255
+ "loss": 1.2674,
2256
+ "step": 313
2257
+ },
2258
+ {
2259
+ "epoch": 0.06858796707122282,
2260
+ "grad_norm": 0.4211152195930481,
2261
+ "learning_rate": 0.00029963694578113417,
2262
+ "loss": 0.9404,
2263
+ "step": 314
2264
+ },
2265
+ {
2266
+ "epoch": 0.06880640008737321,
2267
+ "grad_norm": 0.44201675057411194,
2268
+ "learning_rate": 0.0002996345543099839,
2269
+ "loss": 1.363,
2270
+ "step": 315
2271
+ },
2272
+ {
2273
+ "epoch": 0.0690248331035236,
2274
+ "grad_norm": 0.4818100333213806,
2275
+ "learning_rate": 0.0002996321549978559,
2276
+ "loss": 1.1752,
2277
+ "step": 316
2278
+ },
2279
+ {
2280
+ "epoch": 0.06924326611967399,
2281
+ "grad_norm": 0.5382769107818604,
2282
+ "learning_rate": 0.0002996297478448759,
2283
+ "loss": 1.3113,
2284
+ "step": 317
2285
+ },
2286
+ {
2287
+ "epoch": 0.06946169913582438,
2288
+ "grad_norm": 0.44174817204475403,
2289
+ "learning_rate": 0.0002996273328511701,
2290
+ "loss": 1.4191,
2291
+ "step": 318
2292
+ },
2293
+ {
2294
+ "epoch": 0.06968013215197477,
2295
+ "grad_norm": 0.5009336471557617,
2296
+ "learning_rate": 0.000299624910016865,
2297
+ "loss": 1.1101,
2298
+ "step": 319
2299
+ },
2300
+ {
2301
+ "epoch": 0.06989856516812516,
2302
+ "grad_norm": 0.4469683766365051,
2303
+ "learning_rate": 0.0002996224793420875,
2304
+ "loss": 1.2823,
2305
+ "step": 320
2306
+ },
2307
+ {
2308
+ "epoch": 0.07011699818427555,
2309
+ "grad_norm": 0.4948316216468811,
2310
+ "learning_rate": 0.0002996200408269651,
2311
+ "loss": 1.3302,
2312
+ "step": 321
2313
+ },
2314
+ {
2315
+ "epoch": 0.07033543120042594,
2316
+ "grad_norm": 0.5020711421966553,
2317
+ "learning_rate": 0.0002996175944716255,
2318
+ "loss": 1.0552,
2319
+ "step": 322
2320
+ },
2321
+ {
2322
+ "epoch": 0.07055386421657633,
2323
+ "grad_norm": 0.528529703617096,
2324
+ "learning_rate": 0.0002996151402761969,
2325
+ "loss": 1.2313,
2326
+ "step": 323
2327
+ },
2328
+ {
2329
+ "epoch": 0.07077229723272672,
2330
+ "grad_norm": 0.48190081119537354,
2331
+ "learning_rate": 0.00029961267824080785,
2332
+ "loss": 1.2774,
2333
+ "step": 324
2334
+ },
2335
+ {
2336
+ "epoch": 0.07099073024887712,
2337
+ "grad_norm": 0.43585675954818726,
2338
+ "learning_rate": 0.0002996102083655875,
2339
+ "loss": 0.8383,
2340
+ "step": 325
2341
+ },
2342
+ {
2343
+ "epoch": 0.0712091632650275,
2344
+ "grad_norm": 0.4349531829357147,
2345
+ "learning_rate": 0.00029960773065066515,
2346
+ "loss": 1.0135,
2347
+ "step": 326
2348
+ },
2349
+ {
2350
+ "epoch": 0.0714275962811779,
2351
+ "grad_norm": 0.45253872871398926,
2352
+ "learning_rate": 0.00029960524509617067,
2353
+ "loss": 1.0758,
2354
+ "step": 327
2355
+ },
2356
+ {
2357
+ "epoch": 0.07164602929732829,
2358
+ "grad_norm": 0.48265528678894043,
2359
+ "learning_rate": 0.0002996027517022343,
2360
+ "loss": 1.0895,
2361
+ "step": 328
2362
+ },
2363
+ {
2364
+ "epoch": 0.07186446231347868,
2365
+ "grad_norm": 0.4599095582962036,
2366
+ "learning_rate": 0.0002996002504689867,
2367
+ "loss": 0.9751,
2368
+ "step": 329
2369
+ },
2370
+ {
2371
+ "epoch": 0.07208289532962907,
2372
+ "grad_norm": 0.4035511016845703,
2373
+ "learning_rate": 0.000299597741396559,
2374
+ "loss": 0.9046,
2375
+ "step": 330
2376
+ },
2377
+ {
2378
+ "epoch": 0.07230132834577946,
2379
+ "grad_norm": 0.44477182626724243,
2380
+ "learning_rate": 0.0002995952244850826,
2381
+ "loss": 0.8351,
2382
+ "step": 331
2383
+ },
2384
+ {
2385
+ "epoch": 0.07251976136192985,
2386
+ "grad_norm": 0.49605095386505127,
2387
+ "learning_rate": 0.00029959269973468935,
2388
+ "loss": 1.1617,
2389
+ "step": 332
2390
+ },
2391
+ {
2392
+ "epoch": 0.07273819437808025,
2393
+ "grad_norm": 0.4683946967124939,
2394
+ "learning_rate": 0.00029959016714551165,
2395
+ "loss": 0.815,
2396
+ "step": 333
2397
+ },
2398
+ {
2399
+ "epoch": 0.07295662739423064,
2400
+ "grad_norm": 0.5074111223220825,
2401
+ "learning_rate": 0.00029958762671768223,
2402
+ "loss": 1.08,
2403
+ "step": 334
2404
+ },
2405
+ {
2406
+ "epoch": 0.07317506041038103,
2407
+ "grad_norm": 0.4522974491119385,
2408
+ "learning_rate": 0.000299585078451334,
2409
+ "loss": 1.0445,
2410
+ "step": 335
2411
+ },
2412
+ {
2413
+ "epoch": 0.07339349342653143,
2414
+ "grad_norm": 0.49050214886665344,
2415
+ "learning_rate": 0.00029958252234660077,
2416
+ "loss": 1.023,
2417
+ "step": 336
2418
+ },
2419
+ {
2420
+ "epoch": 0.07361192644268182,
2421
+ "grad_norm": 0.5193130373954773,
2422
+ "learning_rate": 0.0002995799584036163,
2423
+ "loss": 0.9875,
2424
+ "step": 337
2425
+ },
2426
+ {
2427
+ "epoch": 0.0738303594588322,
2428
+ "grad_norm": 0.4777398109436035,
2429
+ "learning_rate": 0.000299577386622515,
2430
+ "loss": 1.0041,
2431
+ "step": 338
2432
+ },
2433
+ {
2434
+ "epoch": 0.0740487924749826,
2435
+ "grad_norm": 0.5704786777496338,
2436
+ "learning_rate": 0.0002995748070034317,
2437
+ "loss": 1.2806,
2438
+ "step": 339
2439
+ },
2440
+ {
2441
+ "epoch": 0.07426722549113299,
2442
+ "grad_norm": 0.5965543985366821,
2443
+ "learning_rate": 0.0002995722195465013,
2444
+ "loss": 1.2449,
2445
+ "step": 340
2446
+ },
2447
+ {
2448
+ "epoch": 0.07448565850728338,
2449
+ "grad_norm": 0.5655717849731445,
2450
+ "learning_rate": 0.0002995696242518598,
2451
+ "loss": 1.492,
2452
+ "step": 341
2453
+ },
2454
+ {
2455
+ "epoch": 0.07470409152343377,
2456
+ "grad_norm": 0.8123418092727661,
2457
+ "learning_rate": 0.0002995670211196429,
2458
+ "loss": 1.2705,
2459
+ "step": 342
2460
+ },
2461
+ {
2462
+ "epoch": 0.07492252453958416,
2463
+ "grad_norm": 0.6008387804031372,
2464
+ "learning_rate": 0.0002995644101499871,
2465
+ "loss": 1.2037,
2466
+ "step": 343
2467
+ },
2468
+ {
2469
+ "epoch": 0.07514095755573455,
2470
+ "grad_norm": 0.601810872554779,
2471
+ "learning_rate": 0.0002995617913430292,
2472
+ "loss": 1.2099,
2473
+ "step": 344
2474
+ },
2475
+ {
2476
+ "epoch": 0.07535939057188494,
2477
+ "grad_norm": 0.589198887348175,
2478
+ "learning_rate": 0.0002995591646989064,
2479
+ "loss": 1.4846,
2480
+ "step": 345
2481
+ },
2482
+ {
2483
+ "epoch": 0.07557782358803533,
2484
+ "grad_norm": 0.6595737338066101,
2485
+ "learning_rate": 0.00029955653021775634,
2486
+ "loss": 1.356,
2487
+ "step": 346
2488
+ },
2489
+ {
2490
+ "epoch": 0.07579625660418572,
2491
+ "grad_norm": 0.5962746739387512,
2492
+ "learning_rate": 0.00029955388789971717,
2493
+ "loss": 1.1548,
2494
+ "step": 347
2495
+ },
2496
+ {
2497
+ "epoch": 0.07601468962033611,
2498
+ "grad_norm": 0.6426790952682495,
2499
+ "learning_rate": 0.0002995512377449273,
2500
+ "loss": 1.16,
2501
+ "step": 348
2502
+ },
2503
+ {
2504
+ "epoch": 0.0762331226364865,
2505
+ "grad_norm": 0.6003267765045166,
2506
+ "learning_rate": 0.00029954857975352553,
2507
+ "loss": 1.1259,
2508
+ "step": 349
2509
+ },
2510
+ {
2511
+ "epoch": 0.0764515556526369,
2512
+ "grad_norm": 0.8509035110473633,
2513
+ "learning_rate": 0.0002995459139256512,
2514
+ "loss": 1.0266,
2515
+ "step": 350
2516
+ },
2517
+ {
2518
+ "epoch": 0.0764515556526369,
2519
+ "eval_loss": 1.4707661867141724,
2520
+ "eval_runtime": 79.3549,
2521
+ "eval_samples_per_second": 4.65,
2522
+ "eval_steps_per_second": 4.65,
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": 1.1919058703430451e+17,
2553
  "train_batch_size": 1,
2554
  "trial_name": null,
2555
  "trial_params": null