Wilsonwin commited on
Commit
bd764ff
·
verified ·
1 Parent(s): 0780efd

Training in progress, step 3500, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70a1b4253dbb29f8e4b115ce512099e2a0de49bca6fe4f046bc1138470767710
3
  size 328277848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae40666b5d8548b4d9d44d04450474f6ec13fb66ce89d797f3570b713fd7b0f
3
  size 328277848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3921f59e58371b75b46766a5952ebd13a4560da6484caf2bb03abc77b5e6c05
3
  size 318646859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ba5a0db1a0c5043a6579a04b471b8428c571ae1a5d3be6e5ebd94a2fd1cedf
3
  size 318646859
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef678004bfc53268aeb4845a442c0327144244832e571a2be41a7160145765eb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012c45d165b3369856a4591817420a71a07d3d2cd37f890b655313517015a2fd
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69dd724b4433a1f1a09f5e5486cf5f9b72f5c8cfac628d8213b1ad6d68ac0c2b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78485ac70c57dc668ae0e88817673f3f048988e00a751f9337313c02c006f1eb
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": 0.5068423720223011,
6
  "eval_steps": 500,
7
- "global_step": 3000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2163,6 +2163,364 @@
2163
  "eval_samples_per_second": 277.146,
2164
  "eval_steps_per_second": 5.82,
2165
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2166
  }
2167
  ],
2168
  "logging_steps": 10,
@@ -2182,7 +2540,7 @@
2182
  "attributes": {}
2183
  }
2184
  },
2185
- "total_flos": 1.00337046257664e+17,
2186
  "train_batch_size": 48,
2187
  "trial_name": null,
2188
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5913161006926846,
6
  "eval_steps": 500,
7
+ "global_step": 3500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2163
  "eval_samples_per_second": 277.146,
2164
  "eval_steps_per_second": 5.82,
2165
  "step": 3000
2166
+ },
2167
+ {
2168
+ "epoch": 0.5085318465957087,
2169
+ "grad_norm": 0.6639596819877625,
2170
+ "learning_rate": 0.00029228085521948167,
2171
+ "loss": 4.964737319946289,
2172
+ "step": 3010
2173
+ },
2174
+ {
2175
+ "epoch": 0.5102213211691164,
2176
+ "grad_norm": 0.6372225284576416,
2177
+ "learning_rate": 0.000292128450206336,
2178
+ "loss": 4.964575576782226,
2179
+ "step": 3020
2180
+ },
2181
+ {
2182
+ "epoch": 0.5119107957425241,
2183
+ "grad_norm": 0.6287721991539001,
2184
+ "learning_rate": 0.00029197459586493077,
2185
+ "loss": 4.968457794189453,
2186
+ "step": 3030
2187
+ },
2188
+ {
2189
+ "epoch": 0.5136002703159317,
2190
+ "grad_norm": 0.596134603023529,
2191
+ "learning_rate": 0.0002918192937641668,
2192
+ "loss": 4.937327194213867,
2193
+ "step": 3040
2194
+ },
2195
+ {
2196
+ "epoch": 0.5152897448893394,
2197
+ "grad_norm": 0.6308782696723938,
2198
+ "learning_rate": 0.00029166254548770827,
2199
+ "loss": 4.955413055419922,
2200
+ "step": 3050
2201
+ },
2202
+ {
2203
+ "epoch": 0.516979219462747,
2204
+ "grad_norm": 0.6965638399124146,
2205
+ "learning_rate": 0.0002915043526339663,
2206
+ "loss": 4.951367568969727,
2207
+ "step": 3060
2208
+ },
2209
+ {
2210
+ "epoch": 0.5186686940361548,
2211
+ "grad_norm": 0.5890870690345764,
2212
+ "learning_rate": 0.00029134471681608286,
2213
+ "loss": 4.956174087524414,
2214
+ "step": 3070
2215
+ },
2216
+ {
2217
+ "epoch": 0.5203581686095624,
2218
+ "grad_norm": 0.6104860901832581,
2219
+ "learning_rate": 0.00029118363966191445,
2220
+ "loss": 4.943370056152344,
2221
+ "step": 3080
2222
+ },
2223
+ {
2224
+ "epoch": 0.5220476431829701,
2225
+ "grad_norm": 0.5911648869514465,
2226
+ "learning_rate": 0.00029102112281401507,
2227
+ "loss": 4.944694900512696,
2228
+ "step": 3090
2229
+ },
2230
+ {
2231
+ "epoch": 0.5237371177563778,
2232
+ "grad_norm": 0.565938413143158,
2233
+ "learning_rate": 0.0002908571679296199,
2234
+ "loss": 4.952177047729492,
2235
+ "step": 3100
2236
+ },
2237
+ {
2238
+ "epoch": 0.5254265923297854,
2239
+ "grad_norm": 0.5907305479049683,
2240
+ "learning_rate": 0.00029069177668062816,
2241
+ "loss": 4.945420837402343,
2242
+ "step": 3110
2243
+ },
2244
+ {
2245
+ "epoch": 0.5271160669031931,
2246
+ "grad_norm": 0.6035214066505432,
2247
+ "learning_rate": 0.00029052495075358617,
2248
+ "loss": 4.937542343139649,
2249
+ "step": 3120
2250
+ },
2251
+ {
2252
+ "epoch": 0.5288055414766007,
2253
+ "grad_norm": 0.6489094495773315,
2254
+ "learning_rate": 0.0002903566918496701,
2255
+ "loss": 4.9244636535644535,
2256
+ "step": 3130
2257
+ },
2258
+ {
2259
+ "epoch": 0.5304950160500085,
2260
+ "grad_norm": 0.6260411739349365,
2261
+ "learning_rate": 0.0002901870016846685,
2262
+ "loss": 4.8926746368408205,
2263
+ "step": 3140
2264
+ },
2265
+ {
2266
+ "epoch": 0.5321844906234161,
2267
+ "grad_norm": 0.6731085777282715,
2268
+ "learning_rate": 0.00029001588198896523,
2269
+ "loss": 4.926407241821289,
2270
+ "step": 3150
2271
+ },
2272
+ {
2273
+ "epoch": 0.5338739651968238,
2274
+ "grad_norm": 0.7428810596466064,
2275
+ "learning_rate": 0.0002898433345075212,
2276
+ "loss": 4.938412857055664,
2277
+ "step": 3160
2278
+ },
2279
+ {
2280
+ "epoch": 0.5355634397702315,
2281
+ "grad_norm": 0.6765902042388916,
2282
+ "learning_rate": 0.0002896693609998571,
2283
+ "loss": 4.913272094726563,
2284
+ "step": 3170
2285
+ },
2286
+ {
2287
+ "epoch": 0.5372529143436391,
2288
+ "grad_norm": 0.7018482089042664,
2289
+ "learning_rate": 0.0002894939632400352,
2290
+ "loss": 4.8967021942138675,
2291
+ "step": 3180
2292
+ },
2293
+ {
2294
+ "epoch": 0.5389423889170468,
2295
+ "grad_norm": 0.6272666454315186,
2296
+ "learning_rate": 0.0002893171430166413,
2297
+ "loss": 4.921631622314453,
2298
+ "step": 3190
2299
+ },
2300
+ {
2301
+ "epoch": 0.5406318634904544,
2302
+ "grad_norm": 0.6220508217811584,
2303
+ "learning_rate": 0.00028913890213276664,
2304
+ "loss": 4.878177642822266,
2305
+ "step": 3200
2306
+ },
2307
+ {
2308
+ "epoch": 0.5423213380638622,
2309
+ "grad_norm": 0.6996421813964844,
2310
+ "learning_rate": 0.0002889592424059891,
2311
+ "loss": 4.867180633544922,
2312
+ "step": 3210
2313
+ },
2314
+ {
2315
+ "epoch": 0.5440108126372698,
2316
+ "grad_norm": 0.6159099340438843,
2317
+ "learning_rate": 0.0002887781656683551,
2318
+ "loss": 4.913734436035156,
2319
+ "step": 3220
2320
+ },
2321
+ {
2322
+ "epoch": 0.5457002872106774,
2323
+ "grad_norm": 0.6269960403442383,
2324
+ "learning_rate": 0.0002885956737663609,
2325
+ "loss": 4.884205627441406,
2326
+ "step": 3230
2327
+ },
2328
+ {
2329
+ "epoch": 0.5473897617840852,
2330
+ "grad_norm": 0.6038281321525574,
2331
+ "learning_rate": 0.00028841176856093346,
2332
+ "loss": 4.866396713256836,
2333
+ "step": 3240
2334
+ },
2335
+ {
2336
+ "epoch": 0.5490792363574928,
2337
+ "grad_norm": 0.587129533290863,
2338
+ "learning_rate": 0.0002882264519274116,
2339
+ "loss": 4.902432632446289,
2340
+ "step": 3250
2341
+ },
2342
+ {
2343
+ "epoch": 0.5507687109309005,
2344
+ "grad_norm": 0.58821040391922,
2345
+ "learning_rate": 0.0002880397257555271,
2346
+ "loss": 4.8774364471435545,
2347
+ "step": 3260
2348
+ },
2349
+ {
2350
+ "epoch": 0.5524581855043081,
2351
+ "grad_norm": 0.5894278287887573,
2352
+ "learning_rate": 0.000287851591949385,
2353
+ "loss": 4.882402038574218,
2354
+ "step": 3270
2355
+ },
2356
+ {
2357
+ "epoch": 0.5541476600777159,
2358
+ "grad_norm": 0.6682536005973816,
2359
+ "learning_rate": 0.0002876620524274447,
2360
+ "loss": 4.875947570800781,
2361
+ "step": 3280
2362
+ },
2363
+ {
2364
+ "epoch": 0.5558371346511235,
2365
+ "grad_norm": 0.56892329454422,
2366
+ "learning_rate": 0.0002874711091224999,
2367
+ "loss": 4.8791545867919925,
2368
+ "step": 3290
2369
+ },
2370
+ {
2371
+ "epoch": 0.5575266092245311,
2372
+ "grad_norm": 0.6786117553710938,
2373
+ "learning_rate": 0.0002872787639816593,
2374
+ "loss": 4.891143417358398,
2375
+ "step": 3300
2376
+ },
2377
+ {
2378
+ "epoch": 0.5592160837979389,
2379
+ "grad_norm": 0.5622825622558594,
2380
+ "learning_rate": 0.00028708501896632636,
2381
+ "loss": 4.864010620117187,
2382
+ "step": 3310
2383
+ },
2384
+ {
2385
+ "epoch": 0.5609055583713465,
2386
+ "grad_norm": 0.5666744709014893,
2387
+ "learning_rate": 0.0002868898760521796,
2388
+ "loss": 4.874967956542969,
2389
+ "step": 3320
2390
+ },
2391
+ {
2392
+ "epoch": 0.5625950329447542,
2393
+ "grad_norm": 0.5970442295074463,
2394
+ "learning_rate": 0.00028669333722915245,
2395
+ "loss": 4.873799514770508,
2396
+ "step": 3330
2397
+ },
2398
+ {
2399
+ "epoch": 0.5642845075181618,
2400
+ "grad_norm": 0.6412243843078613,
2401
+ "learning_rate": 0.0002864954045014126,
2402
+ "loss": 4.852934646606445,
2403
+ "step": 3340
2404
+ },
2405
+ {
2406
+ "epoch": 0.5659739820915696,
2407
+ "grad_norm": 0.6244974732398987,
2408
+ "learning_rate": 0.00028629607988734214,
2409
+ "loss": 4.876249694824219,
2410
+ "step": 3350
2411
+ },
2412
+ {
2413
+ "epoch": 0.5676634566649772,
2414
+ "grad_norm": 0.6246965527534485,
2415
+ "learning_rate": 0.00028609536541951636,
2416
+ "loss": 4.86097412109375,
2417
+ "step": 3360
2418
+ },
2419
+ {
2420
+ "epoch": 0.5693529312383848,
2421
+ "grad_norm": 0.6178351044654846,
2422
+ "learning_rate": 0.00028589326314468357,
2423
+ "loss": 4.864706420898438,
2424
+ "step": 3370
2425
+ },
2426
+ {
2427
+ "epoch": 0.5710424058117926,
2428
+ "grad_norm": 0.5810765624046326,
2429
+ "learning_rate": 0.0002856897751237439,
2430
+ "loss": 4.842799377441406,
2431
+ "step": 3380
2432
+ },
2433
+ {
2434
+ "epoch": 0.5727318803852002,
2435
+ "grad_norm": 0.5823137760162354,
2436
+ "learning_rate": 0.0002854849034317282,
2437
+ "loss": 4.846402740478515,
2438
+ "step": 3390
2439
+ },
2440
+ {
2441
+ "epoch": 0.5744213549586079,
2442
+ "grad_norm": 0.5997573137283325,
2443
+ "learning_rate": 0.0002852786501577773,
2444
+ "loss": 4.83245849609375,
2445
+ "step": 3400
2446
+ },
2447
+ {
2448
+ "epoch": 0.5761108295320155,
2449
+ "grad_norm": 0.587899386882782,
2450
+ "learning_rate": 0.0002850710174051204,
2451
+ "loss": 4.871646118164063,
2452
+ "step": 3410
2453
+ },
2454
+ {
2455
+ "epoch": 0.5778003041054233,
2456
+ "grad_norm": 0.6415139436721802,
2457
+ "learning_rate": 0.0002848620072910535,
2458
+ "loss": 4.83592414855957,
2459
+ "step": 3420
2460
+ },
2461
+ {
2462
+ "epoch": 0.5794897786788309,
2463
+ "grad_norm": 0.5660437345504761,
2464
+ "learning_rate": 0.0002846516219469181,
2465
+ "loss": 4.855052947998047,
2466
+ "step": 3430
2467
+ },
2468
+ {
2469
+ "epoch": 0.5811792532522385,
2470
+ "grad_norm": 0.5609036087989807,
2471
+ "learning_rate": 0.0002844398635180794,
2472
+ "loss": 4.856648254394531,
2473
+ "step": 3440
2474
+ },
2475
+ {
2476
+ "epoch": 0.5828687278256462,
2477
+ "grad_norm": 0.5897738933563232,
2478
+ "learning_rate": 0.00028422673416390437,
2479
+ "loss": 4.862053298950196,
2480
+ "step": 3450
2481
+ },
2482
+ {
2483
+ "epoch": 0.5845582023990539,
2484
+ "grad_norm": 0.5655834674835205,
2485
+ "learning_rate": 0.00028401223605773964,
2486
+ "loss": 4.845742416381836,
2487
+ "step": 3460
2488
+ },
2489
+ {
2490
+ "epoch": 0.5862476769724616,
2491
+ "grad_norm": 0.604269802570343,
2492
+ "learning_rate": 0.00028379637138688945,
2493
+ "loss": 4.828603363037109,
2494
+ "step": 3470
2495
+ },
2496
+ {
2497
+ "epoch": 0.5879371515458692,
2498
+ "grad_norm": 0.5728313326835632,
2499
+ "learning_rate": 0.0002835791423525935,
2500
+ "loss": 4.821448516845703,
2501
+ "step": 3480
2502
+ },
2503
+ {
2504
+ "epoch": 0.5896266261192769,
2505
+ "grad_norm": 0.6384554505348206,
2506
+ "learning_rate": 0.00028336055117000403,
2507
+ "loss": 4.838501358032227,
2508
+ "step": 3490
2509
+ },
2510
+ {
2511
+ "epoch": 0.5913161006926846,
2512
+ "grad_norm": 0.5678889155387878,
2513
+ "learning_rate": 0.0002831406000681638,
2514
+ "loss": 4.827870178222656,
2515
+ "step": 3500
2516
+ },
2517
+ {
2518
+ "epoch": 0.5913161006926846,
2519
+ "eval_loss": 4.812247276306152,
2520
+ "eval_runtime": 3.7454,
2521
+ "eval_samples_per_second": 266.992,
2522
+ "eval_steps_per_second": 5.607,
2523
+ "step": 3500
2524
  }
2525
  ],
2526
  "logging_steps": 10,
 
2540
  "attributes": {}
2541
  }
2542
  },
2543
+ "total_flos": 1.17059887300608e+17,
2544
  "train_batch_size": 48,
2545
  "trial_name": null,
2546
  "trial_params": null