TensorBoard
Safetensors
English
llama
appvoid commited on
Commit
4fa173e
·
verified ·
1 Parent(s): 3ac631d

Deep35 continual checkpoint step 58000

Browse files
last-checkpoint/continual_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "global_step": 56000,
3
- "sequence_tokens_emitted": 8028405760,
4
  "mix": [
5
  0.8,
6
  0.09,
@@ -56,5 +56,5 @@
56
  "current_batch_size": 240,
57
  "current_gradient_accumulation": 1,
58
  "current_tokens_per_update": 245760,
59
- "cumulative_tokens_at_save": 8028160000
60
  }
 
1
  {
2
+ "global_step": 58000,
3
+ "sequence_tokens_emitted": 8519925760,
4
  "mix": [
5
  0.8,
6
  0.09,
 
56
  "current_batch_size": 240,
57
  "current_gradient_accumulation": 1,
58
  "current_tokens_per_update": 245760,
59
+ "cumulative_tokens_at_save": 8519680000
60
  }
last-checkpoint/data_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62f06b041dea7e0f485bdd3a9396d5c2580cb4e79bb840e464e7efadc470e182
3
- size 14079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35666478d5c7a5cafe2c95e8122313f853a3cb84bfd720a6e72512990c11b874
3
+ size 32255
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f638bbe213c2fea90734bd76f973b4c23733d0bb911eba574a86196d00d91eeb
3
  size 70326256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6f374e513e708e51aa48fc92f826c2b6701936e6d0ea77830a0bdc8f735ffb
3
  size 70326256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dbd3f08bf9bf03b3974c4a452278a0b8aa27665102e921c73eafc74e717e7be
3
  size 140740171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f589214fedf67891fb2a8576e676b306ceb43fa1b954f69dd7da6d0ea971187
3
  size 140740171
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c01dc452a9bd0a15de2bac056cb6dc8617697249cfc54e4f98ac6e420b3138e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb6a8c061da2fb25c00440949863d271e4f5fdaa06467eb7085f4ad7058ac909
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:627672765daef0438141a492dfc737f585010da61cd5218547a0089c830712ac
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f819fad73835a0fb350b07ad1ea3f3fbd2fdab0137086249074d87f9e276e82a
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": 3e-06,
6
  "eval_steps": 500,
7
- "global_step": 56000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -40202,6 +40202,1438 @@
40202
  "eval_samples_per_second": 519.813,
40203
  "eval_steps_per_second": 16.244,
40204
  "step": 56000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40205
  }
40206
  ],
40207
  "logging_steps": 10,
@@ -40221,7 +41653,7 @@
40221
  "attributes": {}
40222
  }
40223
  },
40224
- "total_flos": 1.10150773899264e+18,
40225
  "train_batch_size": 240,
40226
  "trial_name": null,
40227
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 4e-06,
6
  "eval_steps": 500,
7
+ "global_step": 58000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
40202
  "eval_samples_per_second": 519.813,
40203
  "eval_steps_per_second": 16.244,
40204
  "step": 56000
40205
+ },
40206
+ {
40207
+ "epoch": 3.005e-06,
40208
+ "grad_norm": 0.482421875,
40209
+ "learning_rate": 5.535110875818601e-05,
40210
+ "loss": 3.0393,
40211
+ "step": 56010
40212
+ },
40213
+ {
40214
+ "epoch": 3.01e-06,
40215
+ "grad_norm": 0.478515625,
40216
+ "learning_rate": 5.5289936901483165e-05,
40217
+ "loss": 3.0311,
40218
+ "step": 56020
40219
+ },
40220
+ {
40221
+ "epoch": 3.015e-06,
40222
+ "grad_norm": 0.5078125,
40223
+ "learning_rate": 5.522883130909399e-05,
40224
+ "loss": 3.0387,
40225
+ "step": 56030
40226
+ },
40227
+ {
40228
+ "epoch": 3.02e-06,
40229
+ "grad_norm": 0.474609375,
40230
+ "learning_rate": 5.516779201792605e-05,
40231
+ "loss": 3.0418,
40232
+ "step": 56040
40233
+ },
40234
+ {
40235
+ "epoch": 3.025e-06,
40236
+ "grad_norm": 0.447265625,
40237
+ "learning_rate": 5.510681906484666e-05,
40238
+ "loss": 3.0303,
40239
+ "step": 56050
40240
+ },
40241
+ {
40242
+ "epoch": 3.03e-06,
40243
+ "grad_norm": 0.5234375,
40244
+ "learning_rate": 5.504591248668322e-05,
40245
+ "loss": 3.0254,
40246
+ "step": 56060
40247
+ },
40248
+ {
40249
+ "epoch": 3.035e-06,
40250
+ "grad_norm": 0.462890625,
40251
+ "learning_rate": 5.4985072320223035e-05,
40252
+ "loss": 3.0246,
40253
+ "step": 56070
40254
+ },
40255
+ {
40256
+ "epoch": 3.04e-06,
40257
+ "grad_norm": 0.4765625,
40258
+ "learning_rate": 5.4924298602213124e-05,
40259
+ "loss": 3.0501,
40260
+ "step": 56080
40261
+ },
40262
+ {
40263
+ "epoch": 3.045e-06,
40264
+ "grad_norm": 0.4609375,
40265
+ "learning_rate": 5.48635913693606e-05,
40266
+ "loss": 3.03,
40267
+ "step": 56090
40268
+ },
40269
+ {
40270
+ "epoch": 3.05e-06,
40271
+ "grad_norm": 0.498046875,
40272
+ "learning_rate": 5.480295065833231e-05,
40273
+ "loss": 3.0406,
40274
+ "step": 56100
40275
+ },
40276
+ {
40277
+ "epoch": 3.055e-06,
40278
+ "grad_norm": 0.53125,
40279
+ "learning_rate": 5.4742376505754896e-05,
40280
+ "loss": 3.0288,
40281
+ "step": 56110
40282
+ },
40283
+ {
40284
+ "epoch": 3.06e-06,
40285
+ "grad_norm": 0.478515625,
40286
+ "learning_rate": 5.4681868948214876e-05,
40287
+ "loss": 3.0415,
40288
+ "step": 56120
40289
+ },
40290
+ {
40291
+ "epoch": 3.065e-06,
40292
+ "grad_norm": 0.48828125,
40293
+ "learning_rate": 5.4621428022258476e-05,
40294
+ "loss": 3.0557,
40295
+ "step": 56130
40296
+ },
40297
+ {
40298
+ "epoch": 3.07e-06,
40299
+ "grad_norm": 0.453125,
40300
+ "learning_rate": 5.456105376439167e-05,
40301
+ "loss": 3.049,
40302
+ "step": 56140
40303
+ },
40304
+ {
40305
+ "epoch": 3.075e-06,
40306
+ "grad_norm": 0.55078125,
40307
+ "learning_rate": 5.450074621108031e-05,
40308
+ "loss": 3.0445,
40309
+ "step": 56150
40310
+ },
40311
+ {
40312
+ "epoch": 3.08e-06,
40313
+ "grad_norm": 0.447265625,
40314
+ "learning_rate": 5.444050539874971e-05,
40315
+ "loss": 3.0246,
40316
+ "step": 56160
40317
+ },
40318
+ {
40319
+ "epoch": 3.085e-06,
40320
+ "grad_norm": 0.478515625,
40321
+ "learning_rate": 5.438033136378516e-05,
40322
+ "loss": 3.0429,
40323
+ "step": 56170
40324
+ },
40325
+ {
40326
+ "epoch": 3.09e-06,
40327
+ "grad_norm": 0.45703125,
40328
+ "learning_rate": 5.43202241425313e-05,
40329
+ "loss": 3.0454,
40330
+ "step": 56180
40331
+ },
40332
+ {
40333
+ "epoch": 3.095e-06,
40334
+ "grad_norm": 0.474609375,
40335
+ "learning_rate": 5.4260183771292704e-05,
40336
+ "loss": 3.0261,
40337
+ "step": 56190
40338
+ },
40339
+ {
40340
+ "epoch": 3.1e-06,
40341
+ "grad_norm": 0.490234375,
40342
+ "learning_rate": 5.420021028633342e-05,
40343
+ "loss": 3.039,
40344
+ "step": 56200
40345
+ },
40346
+ {
40347
+ "epoch": 3.105e-06,
40348
+ "grad_norm": 0.453125,
40349
+ "learning_rate": 5.414030372387711e-05,
40350
+ "loss": 3.0048,
40351
+ "step": 56210
40352
+ },
40353
+ {
40354
+ "epoch": 3.11e-06,
40355
+ "grad_norm": 0.53125,
40356
+ "learning_rate": 5.408046412010703e-05,
40357
+ "loss": 3.0254,
40358
+ "step": 56220
40359
+ },
40360
+ {
40361
+ "epoch": 3.115e-06,
40362
+ "grad_norm": 0.5625,
40363
+ "learning_rate": 5.402069151116601e-05,
40364
+ "loss": 3.0646,
40365
+ "step": 56230
40366
+ },
40367
+ {
40368
+ "epoch": 3.12e-06,
40369
+ "grad_norm": 0.470703125,
40370
+ "learning_rate": 5.396098593315635e-05,
40371
+ "loss": 3.0374,
40372
+ "step": 56240
40373
+ },
40374
+ {
40375
+ "epoch": 3.125e-06,
40376
+ "grad_norm": 0.462890625,
40377
+ "learning_rate": 5.390134742214002e-05,
40378
+ "loss": 3.0636,
40379
+ "step": 56250
40380
+ },
40381
+ {
40382
+ "epoch": 3.13e-06,
40383
+ "grad_norm": 0.5,
40384
+ "learning_rate": 5.384177601413823e-05,
40385
+ "loss": 3.0126,
40386
+ "step": 56260
40387
+ },
40388
+ {
40389
+ "epoch": 3.135e-06,
40390
+ "grad_norm": 0.53125,
40391
+ "learning_rate": 5.378227174513191e-05,
40392
+ "loss": 3.022,
40393
+ "step": 56270
40394
+ },
40395
+ {
40396
+ "epoch": 3.14e-06,
40397
+ "grad_norm": 0.46484375,
40398
+ "learning_rate": 5.3722834651061304e-05,
40399
+ "loss": 3.0478,
40400
+ "step": 56280
40401
+ },
40402
+ {
40403
+ "epoch": 3.145e-06,
40404
+ "grad_norm": 0.474609375,
40405
+ "learning_rate": 5.366346476782611e-05,
40406
+ "loss": 3.0544,
40407
+ "step": 56290
40408
+ },
40409
+ {
40410
+ "epoch": 3.15e-06,
40411
+ "grad_norm": 0.4765625,
40412
+ "learning_rate": 5.3604162131285404e-05,
40413
+ "loss": 3.0231,
40414
+ "step": 56300
40415
+ },
40416
+ {
40417
+ "epoch": 3.155e-06,
40418
+ "grad_norm": 0.498046875,
40419
+ "learning_rate": 5.354492677725772e-05,
40420
+ "loss": 3.0486,
40421
+ "step": 56310
40422
+ },
40423
+ {
40424
+ "epoch": 3.16e-06,
40425
+ "grad_norm": 0.4765625,
40426
+ "learning_rate": 5.3485758741520845e-05,
40427
+ "loss": 3.0163,
40428
+ "step": 56320
40429
+ },
40430
+ {
40431
+ "epoch": 3.165e-06,
40432
+ "grad_norm": 0.48828125,
40433
+ "learning_rate": 5.342665805981207e-05,
40434
+ "loss": 3.029,
40435
+ "step": 56330
40436
+ },
40437
+ {
40438
+ "epoch": 3.17e-06,
40439
+ "grad_norm": 0.49609375,
40440
+ "learning_rate": 5.3367624767827783e-05,
40441
+ "loss": 3.0407,
40442
+ "step": 56340
40443
+ },
40444
+ {
40445
+ "epoch": 3.175e-06,
40446
+ "grad_norm": 0.49609375,
40447
+ "learning_rate": 5.3308658901223864e-05,
40448
+ "loss": 3.0329,
40449
+ "step": 56350
40450
+ },
40451
+ {
40452
+ "epoch": 3.18e-06,
40453
+ "grad_norm": 0.486328125,
40454
+ "learning_rate": 5.3249760495615386e-05,
40455
+ "loss": 3.0116,
40456
+ "step": 56360
40457
+ },
40458
+ {
40459
+ "epoch": 3.185e-06,
40460
+ "grad_norm": 0.53125,
40461
+ "learning_rate": 5.319092958657668e-05,
40462
+ "loss": 3.0383,
40463
+ "step": 56370
40464
+ },
40465
+ {
40466
+ "epoch": 3.19e-06,
40467
+ "grad_norm": 0.458984375,
40468
+ "learning_rate": 5.3132166209641284e-05,
40469
+ "loss": 3.0493,
40470
+ "step": 56380
40471
+ },
40472
+ {
40473
+ "epoch": 3.195e-06,
40474
+ "grad_norm": 0.44140625,
40475
+ "learning_rate": 5.307347040030201e-05,
40476
+ "loss": 2.9958,
40477
+ "step": 56390
40478
+ },
40479
+ {
40480
+ "epoch": 3.2e-06,
40481
+ "grad_norm": 0.47265625,
40482
+ "learning_rate": 5.301484219401081e-05,
40483
+ "loss": 3.0409,
40484
+ "step": 56400
40485
+ },
40486
+ {
40487
+ "epoch": 3.205e-06,
40488
+ "grad_norm": 0.4921875,
40489
+ "learning_rate": 5.295628162617881e-05,
40490
+ "loss": 3.0473,
40491
+ "step": 56410
40492
+ },
40493
+ {
40494
+ "epoch": 3.21e-06,
40495
+ "grad_norm": 0.47265625,
40496
+ "learning_rate": 5.289778873217628e-05,
40497
+ "loss": 3.0385,
40498
+ "step": 56420
40499
+ },
40500
+ {
40501
+ "epoch": 3.215e-06,
40502
+ "grad_norm": 0.45703125,
40503
+ "learning_rate": 5.283936354733272e-05,
40504
+ "loss": 3.0433,
40505
+ "step": 56430
40506
+ },
40507
+ {
40508
+ "epoch": 3.22e-06,
40509
+ "grad_norm": 0.48046875,
40510
+ "learning_rate": 5.2781006106936485e-05,
40511
+ "loss": 3.0615,
40512
+ "step": 56440
40513
+ },
40514
+ {
40515
+ "epoch": 3.225e-06,
40516
+ "grad_norm": 0.4609375,
40517
+ "learning_rate": 5.2722716446235286e-05,
40518
+ "loss": 3.0456,
40519
+ "step": 56450
40520
+ },
40521
+ {
40522
+ "epoch": 3.23e-06,
40523
+ "grad_norm": 0.482421875,
40524
+ "learning_rate": 5.26644946004358e-05,
40525
+ "loss": 3.0323,
40526
+ "step": 56460
40527
+ },
40528
+ {
40529
+ "epoch": 3.235e-06,
40530
+ "grad_norm": 0.494140625,
40531
+ "learning_rate": 5.260634060470358e-05,
40532
+ "loss": 3.0368,
40533
+ "step": 56470
40534
+ },
40535
+ {
40536
+ "epoch": 3.24e-06,
40537
+ "grad_norm": 0.48046875,
40538
+ "learning_rate": 5.254825449416348e-05,
40539
+ "loss": 3.0267,
40540
+ "step": 56480
40541
+ },
40542
+ {
40543
+ "epoch": 3.245e-06,
40544
+ "grad_norm": 0.462890625,
40545
+ "learning_rate": 5.249023630389916e-05,
40546
+ "loss": 2.9978,
40547
+ "step": 56490
40548
+ },
40549
+ {
40550
+ "epoch": 3.25e-06,
40551
+ "grad_norm": 0.5234375,
40552
+ "learning_rate": 5.243228606895329e-05,
40553
+ "loss": 3.0386,
40554
+ "step": 56500
40555
+ },
40556
+ {
40557
+ "epoch": 3.25e-06,
40558
+ "eval_loss": 3.087893486022949,
40559
+ "eval_runtime": 0.0618,
40560
+ "eval_samples_per_second": 517.741,
40561
+ "eval_steps_per_second": 16.179,
40562
+ "step": 56500
40563
+ },
40564
+ {
40565
+ "epoch": 3.255e-06,
40566
+ "grad_norm": 0.486328125,
40567
+ "learning_rate": 5.2374403824327544e-05,
40568
+ "loss": 3.0251,
40569
+ "step": 56510
40570
+ },
40571
+ {
40572
+ "epoch": 3.26e-06,
40573
+ "grad_norm": 0.4609375,
40574
+ "learning_rate": 5.231658960498247e-05,
40575
+ "loss": 3.0412,
40576
+ "step": 56520
40577
+ },
40578
+ {
40579
+ "epoch": 3.265e-06,
40580
+ "grad_norm": 0.5078125,
40581
+ "learning_rate": 5.225884344583758e-05,
40582
+ "loss": 3.0285,
40583
+ "step": 56530
40584
+ },
40585
+ {
40586
+ "epoch": 3.27e-06,
40587
+ "grad_norm": 0.44140625,
40588
+ "learning_rate": 5.220116538177129e-05,
40589
+ "loss": 3.0349,
40590
+ "step": 56540
40591
+ },
40592
+ {
40593
+ "epoch": 3.275e-06,
40594
+ "grad_norm": 0.47265625,
40595
+ "learning_rate": 5.2143555447620765e-05,
40596
+ "loss": 3.0378,
40597
+ "step": 56550
40598
+ },
40599
+ {
40600
+ "epoch": 3.28e-06,
40601
+ "grad_norm": 0.466796875,
40602
+ "learning_rate": 5.20860136781822e-05,
40603
+ "loss": 3.0472,
40604
+ "step": 56560
40605
+ },
40606
+ {
40607
+ "epoch": 3.285e-06,
40608
+ "grad_norm": 0.45703125,
40609
+ "learning_rate": 5.2028540108210486e-05,
40610
+ "loss": 3.0287,
40611
+ "step": 56570
40612
+ },
40613
+ {
40614
+ "epoch": 3.29e-06,
40615
+ "grad_norm": 0.4609375,
40616
+ "learning_rate": 5.197113477241935e-05,
40617
+ "loss": 3.0381,
40618
+ "step": 56580
40619
+ },
40620
+ {
40621
+ "epoch": 3.295e-06,
40622
+ "grad_norm": 0.447265625,
40623
+ "learning_rate": 5.1913797705481364e-05,
40624
+ "loss": 3.0267,
40625
+ "step": 56590
40626
+ },
40627
+ {
40628
+ "epoch": 3.3e-06,
40629
+ "grad_norm": 0.4921875,
40630
+ "learning_rate": 5.185652894202779e-05,
40631
+ "loss": 3.0344,
40632
+ "step": 56600
40633
+ },
40634
+ {
40635
+ "epoch": 3.305e-06,
40636
+ "grad_norm": 0.470703125,
40637
+ "learning_rate": 5.179932851664866e-05,
40638
+ "loss": 3.0122,
40639
+ "step": 56610
40640
+ },
40641
+ {
40642
+ "epoch": 3.31e-06,
40643
+ "grad_norm": 0.44921875,
40644
+ "learning_rate": 5.174219646389274e-05,
40645
+ "loss": 3.0292,
40646
+ "step": 56620
40647
+ },
40648
+ {
40649
+ "epoch": 3.315e-06,
40650
+ "grad_norm": 0.4609375,
40651
+ "learning_rate": 5.16851328182675e-05,
40652
+ "loss": 3.0353,
40653
+ "step": 56630
40654
+ },
40655
+ {
40656
+ "epoch": 3.32e-06,
40657
+ "grad_norm": 0.46484375,
40658
+ "learning_rate": 5.162813761423913e-05,
40659
+ "loss": 3.0516,
40660
+ "step": 56640
40661
+ },
40662
+ {
40663
+ "epoch": 3.325e-06,
40664
+ "grad_norm": 0.45703125,
40665
+ "learning_rate": 5.157121088623235e-05,
40666
+ "loss": 3.0283,
40667
+ "step": 56650
40668
+ },
40669
+ {
40670
+ "epoch": 3.33e-06,
40671
+ "grad_norm": 0.466796875,
40672
+ "learning_rate": 5.151435266863069e-05,
40673
+ "loss": 3.0489,
40674
+ "step": 56660
40675
+ },
40676
+ {
40677
+ "epoch": 3.335e-06,
40678
+ "grad_norm": 0.474609375,
40679
+ "learning_rate": 5.145756299577619e-05,
40680
+ "loss": 3.0307,
40681
+ "step": 56670
40682
+ },
40683
+ {
40684
+ "epoch": 3.34e-06,
40685
+ "grad_norm": 0.466796875,
40686
+ "learning_rate": 5.1400841901969535e-05,
40687
+ "loss": 3.0096,
40688
+ "step": 56680
40689
+ },
40690
+ {
40691
+ "epoch": 3.345e-06,
40692
+ "grad_norm": 0.515625,
40693
+ "learning_rate": 5.1344189421469966e-05,
40694
+ "loss": 3.0348,
40695
+ "step": 56690
40696
+ },
40697
+ {
40698
+ "epoch": 3.35e-06,
40699
+ "grad_norm": 0.50390625,
40700
+ "learning_rate": 5.128760558849527e-05,
40701
+ "loss": 3.0201,
40702
+ "step": 56700
40703
+ },
40704
+ {
40705
+ "epoch": 3.355e-06,
40706
+ "grad_norm": 0.431640625,
40707
+ "learning_rate": 5.12310904372218e-05,
40708
+ "loss": 3.0465,
40709
+ "step": 56710
40710
+ },
40711
+ {
40712
+ "epoch": 3.36e-06,
40713
+ "grad_norm": 0.515625,
40714
+ "learning_rate": 5.1174644001784465e-05,
40715
+ "loss": 3.0555,
40716
+ "step": 56720
40717
+ },
40718
+ {
40719
+ "epoch": 3.365e-06,
40720
+ "grad_norm": 0.4609375,
40721
+ "learning_rate": 5.111826631627653e-05,
40722
+ "loss": 3.0203,
40723
+ "step": 56730
40724
+ },
40725
+ {
40726
+ "epoch": 3.37e-06,
40727
+ "grad_norm": 0.51171875,
40728
+ "learning_rate": 5.106195741474989e-05,
40729
+ "loss": 3.0128,
40730
+ "step": 56740
40731
+ },
40732
+ {
40733
+ "epoch": 3.375e-06,
40734
+ "grad_norm": 0.609375,
40735
+ "learning_rate": 5.100571733121484e-05,
40736
+ "loss": 3.0344,
40737
+ "step": 56750
40738
+ },
40739
+ {
40740
+ "epoch": 3.38e-06,
40741
+ "grad_norm": 0.46875,
40742
+ "learning_rate": 5.094954609964008e-05,
40743
+ "loss": 3.0237,
40744
+ "step": 56760
40745
+ },
40746
+ {
40747
+ "epoch": 3.385e-06,
40748
+ "grad_norm": 0.5703125,
40749
+ "learning_rate": 5.089344375395274e-05,
40750
+ "loss": 3.0247,
40751
+ "step": 56770
40752
+ },
40753
+ {
40754
+ "epoch": 3.39e-06,
40755
+ "grad_norm": 0.494140625,
40756
+ "learning_rate": 5.0837410328038354e-05,
40757
+ "loss": 3.038,
40758
+ "step": 56780
40759
+ },
40760
+ {
40761
+ "epoch": 3.395e-06,
40762
+ "grad_norm": 0.46484375,
40763
+ "learning_rate": 5.078144585574079e-05,
40764
+ "loss": 3.0339,
40765
+ "step": 56790
40766
+ },
40767
+ {
40768
+ "epoch": 3.4e-06,
40769
+ "grad_norm": 0.482421875,
40770
+ "learning_rate": 5.07255503708624e-05,
40771
+ "loss": 3.0661,
40772
+ "step": 56800
40773
+ },
40774
+ {
40775
+ "epoch": 3.405e-06,
40776
+ "grad_norm": 0.5,
40777
+ "learning_rate": 5.066972390716365e-05,
40778
+ "loss": 3.0529,
40779
+ "step": 56810
40780
+ },
40781
+ {
40782
+ "epoch": 3.41e-06,
40783
+ "grad_norm": 0.474609375,
40784
+ "learning_rate": 5.061396649836354e-05,
40785
+ "loss": 3.0566,
40786
+ "step": 56820
40787
+ },
40788
+ {
40789
+ "epoch": 3.415e-06,
40790
+ "grad_norm": 0.44921875,
40791
+ "learning_rate": 5.055827817813915e-05,
40792
+ "loss": 3.0318,
40793
+ "step": 56830
40794
+ },
40795
+ {
40796
+ "epoch": 3.42e-06,
40797
+ "grad_norm": 0.478515625,
40798
+ "learning_rate": 5.0502658980126033e-05,
40799
+ "loss": 3.0514,
40800
+ "step": 56840
40801
+ },
40802
+ {
40803
+ "epoch": 3.425e-06,
40804
+ "grad_norm": 0.51171875,
40805
+ "learning_rate": 5.044710893791786e-05,
40806
+ "loss": 3.032,
40807
+ "step": 56850
40808
+ },
40809
+ {
40810
+ "epoch": 3.43e-06,
40811
+ "grad_norm": 0.451171875,
40812
+ "learning_rate": 5.0391628085066574e-05,
40813
+ "loss": 3.0452,
40814
+ "step": 56860
40815
+ },
40816
+ {
40817
+ "epoch": 3.435e-06,
40818
+ "grad_norm": 0.44140625,
40819
+ "learning_rate": 5.033621645508233e-05,
40820
+ "loss": 3.0373,
40821
+ "step": 56870
40822
+ },
40823
+ {
40824
+ "epoch": 3.44e-06,
40825
+ "grad_norm": 0.439453125,
40826
+ "learning_rate": 5.0280874081433447e-05,
40827
+ "loss": 3.0321,
40828
+ "step": 56880
40829
+ },
40830
+ {
40831
+ "epoch": 3.445e-06,
40832
+ "grad_norm": 0.490234375,
40833
+ "learning_rate": 5.0225600997546456e-05,
40834
+ "loss": 3.0581,
40835
+ "step": 56890
40836
+ },
40837
+ {
40838
+ "epoch": 3.45e-06,
40839
+ "grad_norm": 0.46484375,
40840
+ "learning_rate": 5.017039723680601e-05,
40841
+ "loss": 3.0514,
40842
+ "step": 56900
40843
+ },
40844
+ {
40845
+ "epoch": 3.455e-06,
40846
+ "grad_norm": 0.451171875,
40847
+ "learning_rate": 5.01152628325549e-05,
40848
+ "loss": 3.0138,
40849
+ "step": 56910
40850
+ },
40851
+ {
40852
+ "epoch": 3.46e-06,
40853
+ "grad_norm": 0.46875,
40854
+ "learning_rate": 5.0060197818093976e-05,
40855
+ "loss": 3.0428,
40856
+ "step": 56920
40857
+ },
40858
+ {
40859
+ "epoch": 3.465e-06,
40860
+ "grad_norm": 0.4921875,
40861
+ "learning_rate": 5.000520222668233e-05,
40862
+ "loss": 3.0427,
40863
+ "step": 56930
40864
+ },
40865
+ {
40866
+ "epoch": 3.47e-06,
40867
+ "grad_norm": 0.451171875,
40868
+ "learning_rate": 4.995027609153691e-05,
40869
+ "loss": 3.0222,
40870
+ "step": 56940
40871
+ },
40872
+ {
40873
+ "epoch": 3.475e-06,
40874
+ "grad_norm": 0.52734375,
40875
+ "learning_rate": 4.989541944583286e-05,
40876
+ "loss": 3.0479,
40877
+ "step": 56950
40878
+ },
40879
+ {
40880
+ "epoch": 3.48e-06,
40881
+ "grad_norm": 0.482421875,
40882
+ "learning_rate": 4.9840632322703316e-05,
40883
+ "loss": 3.0479,
40884
+ "step": 56960
40885
+ },
40886
+ {
40887
+ "epoch": 3.485e-06,
40888
+ "grad_norm": 0.4609375,
40889
+ "learning_rate": 4.978591475523943e-05,
40890
+ "loss": 3.0424,
40891
+ "step": 56970
40892
+ },
40893
+ {
40894
+ "epoch": 3.49e-06,
40895
+ "grad_norm": 0.462890625,
40896
+ "learning_rate": 4.9731266776490305e-05,
40897
+ "loss": 3.0347,
40898
+ "step": 56980
40899
+ },
40900
+ {
40901
+ "epoch": 3.495e-06,
40902
+ "grad_norm": 0.45703125,
40903
+ "learning_rate": 4.967668841946305e-05,
40904
+ "loss": 3.0167,
40905
+ "step": 56990
40906
+ },
40907
+ {
40908
+ "epoch": 3.5e-06,
40909
+ "grad_norm": 0.50390625,
40910
+ "learning_rate": 4.962217971712269e-05,
40911
+ "loss": 3.0236,
40912
+ "step": 57000
40913
+ },
40914
+ {
40915
+ "epoch": 3.5e-06,
40916
+ "eval_loss": 3.0873687267303467,
40917
+ "eval_runtime": 0.0616,
40918
+ "eval_samples_per_second": 519.109,
40919
+ "eval_steps_per_second": 16.222,
40920
+ "step": 57000
40921
+ },
40922
+ {
40923
+ "epoch": 3.505e-06,
40924
+ "grad_norm": 0.484375,
40925
+ "learning_rate": 4.956774070239227e-05,
40926
+ "loss": 3.0128,
40927
+ "step": 57010
40928
+ },
40929
+ {
40930
+ "epoch": 3.51e-06,
40931
+ "grad_norm": 0.453125,
40932
+ "learning_rate": 4.951337140815256e-05,
40933
+ "loss": 3.0061,
40934
+ "step": 57020
40935
+ },
40936
+ {
40937
+ "epoch": 3.515e-06,
40938
+ "grad_norm": 0.44921875,
40939
+ "learning_rate": 4.945907186724246e-05,
40940
+ "loss": 3.0391,
40941
+ "step": 57030
40942
+ },
40943
+ {
40944
+ "epoch": 3.52e-06,
40945
+ "grad_norm": 0.484375,
40946
+ "learning_rate": 4.9404842112458525e-05,
40947
+ "loss": 3.0407,
40948
+ "step": 57040
40949
+ },
40950
+ {
40951
+ "epoch": 3.525e-06,
40952
+ "grad_norm": 0.53515625,
40953
+ "learning_rate": 4.93506821765553e-05,
40954
+ "loss": 3.0193,
40955
+ "step": 57050
40956
+ },
40957
+ {
40958
+ "epoch": 3.53e-06,
40959
+ "grad_norm": 0.474609375,
40960
+ "learning_rate": 4.929659209224508e-05,
40961
+ "loss": 3.0432,
40962
+ "step": 57060
40963
+ },
40964
+ {
40965
+ "epoch": 3.535e-06,
40966
+ "grad_norm": 0.451171875,
40967
+ "learning_rate": 4.924257189219799e-05,
40968
+ "loss": 2.9957,
40969
+ "step": 57070
40970
+ },
40971
+ {
40972
+ "epoch": 3.54e-06,
40973
+ "grad_norm": 0.458984375,
40974
+ "learning_rate": 4.918862160904198e-05,
40975
+ "loss": 3.0288,
40976
+ "step": 57080
40977
+ },
40978
+ {
40979
+ "epoch": 3.545e-06,
40980
+ "grad_norm": 0.4765625,
40981
+ "learning_rate": 4.9134741275362735e-05,
40982
+ "loss": 3.0417,
40983
+ "step": 57090
40984
+ },
40985
+ {
40986
+ "epoch": 3.55e-06,
40987
+ "grad_norm": 0.4453125,
40988
+ "learning_rate": 4.908093092370364e-05,
40989
+ "loss": 3.0475,
40990
+ "step": 57100
40991
+ },
40992
+ {
40993
+ "epoch": 3.555e-06,
40994
+ "grad_norm": 0.4609375,
40995
+ "learning_rate": 4.9027190586566e-05,
40996
+ "loss": 3.0488,
40997
+ "step": 57110
40998
+ },
40999
+ {
41000
+ "epoch": 3.56e-06,
41001
+ "grad_norm": 0.478515625,
41002
+ "learning_rate": 4.897352029640856e-05,
41003
+ "loss": 3.056,
41004
+ "step": 57120
41005
+ },
41006
+ {
41007
+ "epoch": 3.565e-06,
41008
+ "grad_norm": 0.4765625,
41009
+ "learning_rate": 4.8919920085648e-05,
41010
+ "loss": 3.0423,
41011
+ "step": 57130
41012
+ },
41013
+ {
41014
+ "epoch": 3.57e-06,
41015
+ "grad_norm": 0.48046875,
41016
+ "learning_rate": 4.886638998665855e-05,
41017
+ "loss": 3.0458,
41018
+ "step": 57140
41019
+ },
41020
+ {
41021
+ "epoch": 3.575e-06,
41022
+ "grad_norm": 0.482421875,
41023
+ "learning_rate": 4.8812930031772074e-05,
41024
+ "loss": 3.049,
41025
+ "step": 57150
41026
+ },
41027
+ {
41028
+ "epoch": 3.58e-06,
41029
+ "grad_norm": 0.44921875,
41030
+ "learning_rate": 4.875954025327816e-05,
41031
+ "loss": 3.0045,
41032
+ "step": 57160
41033
+ },
41034
+ {
41035
+ "epoch": 3.585e-06,
41036
+ "grad_norm": 0.4453125,
41037
+ "learning_rate": 4.870622068342391e-05,
41038
+ "loss": 3.0388,
41039
+ "step": 57170
41040
+ },
41041
+ {
41042
+ "epoch": 3.59e-06,
41043
+ "grad_norm": 0.470703125,
41044
+ "learning_rate": 4.8652971354414086e-05,
41045
+ "loss": 3.0488,
41046
+ "step": 57180
41047
+ },
41048
+ {
41049
+ "epoch": 3.595e-06,
41050
+ "grad_norm": 0.486328125,
41051
+ "learning_rate": 4.8599792298411076e-05,
41052
+ "loss": 3.0424,
41053
+ "step": 57190
41054
+ },
41055
+ {
41056
+ "epoch": 3.6e-06,
41057
+ "grad_norm": 0.52734375,
41058
+ "learning_rate": 4.8546683547534654e-05,
41059
+ "loss": 3.0623,
41060
+ "step": 57200
41061
+ },
41062
+ {
41063
+ "epoch": 3.605e-06,
41064
+ "grad_norm": 0.470703125,
41065
+ "learning_rate": 4.8493645133862284e-05,
41066
+ "loss": 3.0353,
41067
+ "step": 57210
41068
+ },
41069
+ {
41070
+ "epoch": 3.61e-06,
41071
+ "grad_norm": 0.486328125,
41072
+ "learning_rate": 4.84406770894289e-05,
41073
+ "loss": 3.0128,
41074
+ "step": 57220
41075
+ },
41076
+ {
41077
+ "epoch": 3.615e-06,
41078
+ "grad_norm": 0.49609375,
41079
+ "learning_rate": 4.838777944622691e-05,
41080
+ "loss": 3.0337,
41081
+ "step": 57230
41082
+ },
41083
+ {
41084
+ "epoch": 3.62e-06,
41085
+ "grad_norm": 0.47265625,
41086
+ "learning_rate": 4.833495223620624e-05,
41087
+ "loss": 3.0205,
41088
+ "step": 57240
41089
+ },
41090
+ {
41091
+ "epoch": 3.625e-06,
41092
+ "grad_norm": 0.470703125,
41093
+ "learning_rate": 4.828219549127422e-05,
41094
+ "loss": 3.0281,
41095
+ "step": 57250
41096
+ },
41097
+ {
41098
+ "epoch": 3.63e-06,
41099
+ "grad_norm": 0.439453125,
41100
+ "learning_rate": 4.822950924329565e-05,
41101
+ "loss": 3.0471,
41102
+ "step": 57260
41103
+ },
41104
+ {
41105
+ "epoch": 3.635e-06,
41106
+ "grad_norm": 0.451171875,
41107
+ "learning_rate": 4.8176893524092844e-05,
41108
+ "loss": 3.0169,
41109
+ "step": 57270
41110
+ },
41111
+ {
41112
+ "epoch": 3.64e-06,
41113
+ "grad_norm": 0.458984375,
41114
+ "learning_rate": 4.8124348365445325e-05,
41115
+ "loss": 3.0423,
41116
+ "step": 57280
41117
+ },
41118
+ {
41119
+ "epoch": 3.645e-06,
41120
+ "grad_norm": 0.4609375,
41121
+ "learning_rate": 4.807187379909011e-05,
41122
+ "loss": 3.0256,
41123
+ "step": 57290
41124
+ },
41125
+ {
41126
+ "epoch": 3.65e-06,
41127
+ "grad_norm": 0.451171875,
41128
+ "learning_rate": 4.801946985672161e-05,
41129
+ "loss": 3.0222,
41130
+ "step": 57300
41131
+ },
41132
+ {
41133
+ "epoch": 3.655e-06,
41134
+ "grad_norm": 0.484375,
41135
+ "learning_rate": 4.796713656999146e-05,
41136
+ "loss": 3.0559,
41137
+ "step": 57310
41138
+ },
41139
+ {
41140
+ "epoch": 3.66e-06,
41141
+ "grad_norm": 0.50390625,
41142
+ "learning_rate": 4.791487397050882e-05,
41143
+ "loss": 3.0485,
41144
+ "step": 57320
41145
+ },
41146
+ {
41147
+ "epoch": 3.665e-06,
41148
+ "grad_norm": 0.474609375,
41149
+ "learning_rate": 4.7862682089839895e-05,
41150
+ "loss": 3.0434,
41151
+ "step": 57330
41152
+ },
41153
+ {
41154
+ "epoch": 3.67e-06,
41155
+ "grad_norm": 0.49609375,
41156
+ "learning_rate": 4.781056095950841e-05,
41157
+ "loss": 3.0444,
41158
+ "step": 57340
41159
+ },
41160
+ {
41161
+ "epoch": 3.675e-06,
41162
+ "grad_norm": 0.51953125,
41163
+ "learning_rate": 4.7758510610995244e-05,
41164
+ "loss": 3.0176,
41165
+ "step": 57350
41166
+ },
41167
+ {
41168
+ "epoch": 3.68e-06,
41169
+ "grad_norm": 0.490234375,
41170
+ "learning_rate": 4.770653107573851e-05,
41171
+ "loss": 3.0333,
41172
+ "step": 57360
41173
+ },
41174
+ {
41175
+ "epoch": 3.685e-06,
41176
+ "grad_norm": 0.4609375,
41177
+ "learning_rate": 4.765462238513358e-05,
41178
+ "loss": 3.0264,
41179
+ "step": 57370
41180
+ },
41181
+ {
41182
+ "epoch": 3.69e-06,
41183
+ "grad_norm": 0.4609375,
41184
+ "learning_rate": 4.760278457053306e-05,
41185
+ "loss": 3.0358,
41186
+ "step": 57380
41187
+ },
41188
+ {
41189
+ "epoch": 3.695e-06,
41190
+ "grad_norm": 0.4765625,
41191
+ "learning_rate": 4.7551017663246685e-05,
41192
+ "loss": 3.0042,
41193
+ "step": 57390
41194
+ },
41195
+ {
41196
+ "epoch": 3.7e-06,
41197
+ "grad_norm": 0.4765625,
41198
+ "learning_rate": 4.7499321694541475e-05,
41199
+ "loss": 3.0172,
41200
+ "step": 57400
41201
+ },
41202
+ {
41203
+ "epoch": 3.705e-06,
41204
+ "grad_norm": 0.478515625,
41205
+ "learning_rate": 4.744769669564144e-05,
41206
+ "loss": 3.0453,
41207
+ "step": 57410
41208
+ },
41209
+ {
41210
+ "epoch": 3.71e-06,
41211
+ "grad_norm": 0.455078125,
41212
+ "learning_rate": 4.739614269772787e-05,
41213
+ "loss": 3.0138,
41214
+ "step": 57420
41215
+ },
41216
+ {
41217
+ "epoch": 3.715e-06,
41218
+ "grad_norm": 0.45703125,
41219
+ "learning_rate": 4.7344659731939115e-05,
41220
+ "loss": 3.0527,
41221
+ "step": 57430
41222
+ },
41223
+ {
41224
+ "epoch": 3.72e-06,
41225
+ "grad_norm": 0.4765625,
41226
+ "learning_rate": 4.729324782937059e-05,
41227
+ "loss": 3.0299,
41228
+ "step": 57440
41229
+ },
41230
+ {
41231
+ "epoch": 3.725e-06,
41232
+ "grad_norm": 0.5390625,
41233
+ "learning_rate": 4.724190702107485e-05,
41234
+ "loss": 3.0201,
41235
+ "step": 57450
41236
+ },
41237
+ {
41238
+ "epoch": 3.73e-06,
41239
+ "grad_norm": 0.4765625,
41240
+ "learning_rate": 4.7190637338061464e-05,
41241
+ "loss": 3.039,
41242
+ "step": 57460
41243
+ },
41244
+ {
41245
+ "epoch": 3.735e-06,
41246
+ "grad_norm": 0.4453125,
41247
+ "learning_rate": 4.713943881129701e-05,
41248
+ "loss": 3.0292,
41249
+ "step": 57470
41250
+ },
41251
+ {
41252
+ "epoch": 3.74e-06,
41253
+ "grad_norm": 0.462890625,
41254
+ "learning_rate": 4.708831147170527e-05,
41255
+ "loss": 3.0647,
41256
+ "step": 57480
41257
+ },
41258
+ {
41259
+ "epoch": 3.745e-06,
41260
+ "grad_norm": 0.46484375,
41261
+ "learning_rate": 4.7037255350166735e-05,
41262
+ "loss": 3.0109,
41263
+ "step": 57490
41264
+ },
41265
+ {
41266
+ "epoch": 3.75e-06,
41267
+ "grad_norm": 0.45703125,
41268
+ "learning_rate": 4.6986270477519167e-05,
41269
+ "loss": 3.0336,
41270
+ "step": 57500
41271
+ },
41272
+ {
41273
+ "epoch": 3.75e-06,
41274
+ "eval_loss": 3.0866641998291016,
41275
+ "eval_runtime": 0.0672,
41276
+ "eval_samples_per_second": 476.356,
41277
+ "eval_steps_per_second": 14.886,
41278
+ "step": 57500
41279
+ },
41280
+ {
41281
+ "epoch": 3.755e-06,
41282
+ "grad_norm": 0.48046875,
41283
+ "learning_rate": 4.693535688455706e-05,
41284
+ "loss": 3.0596,
41285
+ "step": 57510
41286
+ },
41287
+ {
41288
+ "epoch": 3.76e-06,
41289
+ "grad_norm": 0.435546875,
41290
+ "learning_rate": 4.688451460203204e-05,
41291
+ "loss": 3.0226,
41292
+ "step": 57520
41293
+ },
41294
+ {
41295
+ "epoch": 3.765e-06,
41296
+ "grad_norm": 0.455078125,
41297
+ "learning_rate": 4.683374366065256e-05,
41298
+ "loss": 3.0367,
41299
+ "step": 57530
41300
+ },
41301
+ {
41302
+ "epoch": 3.77e-06,
41303
+ "grad_norm": 0.486328125,
41304
+ "learning_rate": 4.678304409108399e-05,
41305
+ "loss": 3.0649,
41306
+ "step": 57540
41307
+ },
41308
+ {
41309
+ "epoch": 3.775e-06,
41310
+ "grad_norm": 0.458984375,
41311
+ "learning_rate": 4.673241592394864e-05,
41312
+ "loss": 3.0397,
41313
+ "step": 57550
41314
+ },
41315
+ {
41316
+ "epoch": 3.78e-06,
41317
+ "grad_norm": 0.49609375,
41318
+ "learning_rate": 4.6681859189825646e-05,
41319
+ "loss": 3.0128,
41320
+ "step": 57560
41321
+ },
41322
+ {
41323
+ "epoch": 3.785e-06,
41324
+ "grad_norm": 0.48828125,
41325
+ "learning_rate": 4.663137391925099e-05,
41326
+ "loss": 3.048,
41327
+ "step": 57570
41328
+ },
41329
+ {
41330
+ "epoch": 3.79e-06,
41331
+ "grad_norm": 0.48828125,
41332
+ "learning_rate": 4.65809601427176e-05,
41333
+ "loss": 3.0438,
41334
+ "step": 57580
41335
+ },
41336
+ {
41337
+ "epoch": 3.795e-06,
41338
+ "grad_norm": 0.474609375,
41339
+ "learning_rate": 4.653061789067502e-05,
41340
+ "loss": 3.0507,
41341
+ "step": 57590
41342
+ },
41343
+ {
41344
+ "epoch": 3.8e-06,
41345
+ "grad_norm": 0.486328125,
41346
+ "learning_rate": 4.64803471935298e-05,
41347
+ "loss": 3.0454,
41348
+ "step": 57600
41349
+ },
41350
+ {
41351
+ "epoch": 3.805e-06,
41352
+ "grad_norm": 0.5,
41353
+ "learning_rate": 4.643014808164516e-05,
41354
+ "loss": 3.0269,
41355
+ "step": 57610
41356
+ },
41357
+ {
41358
+ "epoch": 3.81e-06,
41359
+ "grad_norm": 0.5078125,
41360
+ "learning_rate": 4.638002058534108e-05,
41361
+ "loss": 3.0587,
41362
+ "step": 57620
41363
+ },
41364
+ {
41365
+ "epoch": 3.815e-06,
41366
+ "grad_norm": 0.4921875,
41367
+ "learning_rate": 4.632996473489434e-05,
41368
+ "loss": 3.0413,
41369
+ "step": 57630
41370
+ },
41371
+ {
41372
+ "epoch": 3.82e-06,
41373
+ "grad_norm": 0.5078125,
41374
+ "learning_rate": 4.627998056053841e-05,
41375
+ "loss": 3.0521,
41376
+ "step": 57640
41377
+ },
41378
+ {
41379
+ "epoch": 3.825e-06,
41380
+ "grad_norm": 0.51171875,
41381
+ "learning_rate": 4.6230068092463427e-05,
41382
+ "loss": 3.0244,
41383
+ "step": 57650
41384
+ },
41385
+ {
41386
+ "epoch": 3.83e-06,
41387
+ "grad_norm": 0.5234375,
41388
+ "learning_rate": 4.6180227360816373e-05,
41389
+ "loss": 3.0377,
41390
+ "step": 57660
41391
+ },
41392
+ {
41393
+ "epoch": 3.835e-06,
41394
+ "grad_norm": 0.466796875,
41395
+ "learning_rate": 4.613045839570068e-05,
41396
+ "loss": 3.031,
41397
+ "step": 57670
41398
+ },
41399
+ {
41400
+ "epoch": 3.84e-06,
41401
+ "grad_norm": 0.462890625,
41402
+ "learning_rate": 4.60807612271766e-05,
41403
+ "loss": 3.0441,
41404
+ "step": 57680
41405
+ },
41406
+ {
41407
+ "epoch": 3.845e-06,
41408
+ "grad_norm": 0.484375,
41409
+ "learning_rate": 4.6031135885261004e-05,
41410
+ "loss": 3.0159,
41411
+ "step": 57690
41412
+ },
41413
+ {
41414
+ "epoch": 3.85e-06,
41415
+ "grad_norm": 0.484375,
41416
+ "learning_rate": 4.5981582399927254e-05,
41417
+ "loss": 3.0318,
41418
+ "step": 57700
41419
+ },
41420
+ {
41421
+ "epoch": 3.855e-06,
41422
+ "grad_norm": 0.49609375,
41423
+ "learning_rate": 4.593210080110549e-05,
41424
+ "loss": 3.0609,
41425
+ "step": 57710
41426
+ },
41427
+ {
41428
+ "epoch": 3.86e-06,
41429
+ "grad_norm": 0.494140625,
41430
+ "learning_rate": 4.588269111868224e-05,
41431
+ "loss": 3.0359,
41432
+ "step": 57720
41433
+ },
41434
+ {
41435
+ "epoch": 3.865e-06,
41436
+ "grad_norm": 0.458984375,
41437
+ "learning_rate": 4.5833353382500786e-05,
41438
+ "loss": 3.0017,
41439
+ "step": 57730
41440
+ },
41441
+ {
41442
+ "epoch": 3.87e-06,
41443
+ "grad_norm": 0.4765625,
41444
+ "learning_rate": 4.5784087622360845e-05,
41445
+ "loss": 3.0226,
41446
+ "step": 57740
41447
+ },
41448
+ {
41449
+ "epoch": 3.875e-06,
41450
+ "grad_norm": 0.484375,
41451
+ "learning_rate": 4.5734893868018665e-05,
41452
+ "loss": 3.051,
41453
+ "step": 57750
41454
+ },
41455
+ {
41456
+ "epoch": 3.88e-06,
41457
+ "grad_norm": 0.451171875,
41458
+ "learning_rate": 4.568577214918706e-05,
41459
+ "loss": 3.0253,
41460
+ "step": 57760
41461
+ },
41462
+ {
41463
+ "epoch": 3.885e-06,
41464
+ "grad_norm": 0.466796875,
41465
+ "learning_rate": 4.563672249553525e-05,
41466
+ "loss": 3.0389,
41467
+ "step": 57770
41468
+ },
41469
+ {
41470
+ "epoch": 3.89e-06,
41471
+ "grad_norm": 0.48046875,
41472
+ "learning_rate": 4.558774493668896e-05,
41473
+ "loss": 3.0268,
41474
+ "step": 57780
41475
+ },
41476
+ {
41477
+ "epoch": 3.895e-06,
41478
+ "grad_norm": 0.45703125,
41479
+ "learning_rate": 4.553883950223047e-05,
41480
+ "loss": 3.0334,
41481
+ "step": 57790
41482
+ },
41483
+ {
41484
+ "epoch": 3.9e-06,
41485
+ "grad_norm": 0.466796875,
41486
+ "learning_rate": 4.549000622169831e-05,
41487
+ "loss": 3.0053,
41488
+ "step": 57800
41489
+ },
41490
+ {
41491
+ "epoch": 3.905e-06,
41492
+ "grad_norm": 0.490234375,
41493
+ "learning_rate": 4.5441245124587594e-05,
41494
+ "loss": 3.0351,
41495
+ "step": 57810
41496
+ },
41497
+ {
41498
+ "epoch": 3.91e-06,
41499
+ "grad_norm": 0.48046875,
41500
+ "learning_rate": 4.539255624034977e-05,
41501
+ "loss": 3.0549,
41502
+ "step": 57820
41503
+ },
41504
+ {
41505
+ "epoch": 3.915e-06,
41506
+ "grad_norm": 0.470703125,
41507
+ "learning_rate": 4.5343939598392644e-05,
41508
+ "loss": 3.0443,
41509
+ "step": 57830
41510
+ },
41511
+ {
41512
+ "epoch": 3.92e-06,
41513
+ "grad_norm": 0.50390625,
41514
+ "learning_rate": 4.5295395228080426e-05,
41515
+ "loss": 3.0512,
41516
+ "step": 57840
41517
+ },
41518
+ {
41519
+ "epoch": 3.925e-06,
41520
+ "grad_norm": 0.44921875,
41521
+ "learning_rate": 4.5246923158733695e-05,
41522
+ "loss": 3.0158,
41523
+ "step": 57850
41524
+ },
41525
+ {
41526
+ "epoch": 3.93e-06,
41527
+ "grad_norm": 0.4609375,
41528
+ "learning_rate": 4.5198523419629264e-05,
41529
+ "loss": 3.0327,
41530
+ "step": 57860
41531
+ },
41532
+ {
41533
+ "epoch": 3.935e-06,
41534
+ "grad_norm": 0.45703125,
41535
+ "learning_rate": 4.5150196040000436e-05,
41536
+ "loss": 3.0406,
41537
+ "step": 57870
41538
+ },
41539
+ {
41540
+ "epoch": 3.94e-06,
41541
+ "grad_norm": 0.482421875,
41542
+ "learning_rate": 4.5101941049036575e-05,
41543
+ "loss": 3.0524,
41544
+ "step": 57880
41545
+ },
41546
+ {
41547
+ "epoch": 3.945e-06,
41548
+ "grad_norm": 0.443359375,
41549
+ "learning_rate": 4.505375847588353e-05,
41550
+ "loss": 3.0266,
41551
+ "step": 57890
41552
+ },
41553
+ {
41554
+ "epoch": 3.95e-06,
41555
+ "grad_norm": 0.462890625,
41556
+ "learning_rate": 4.500564834964331e-05,
41557
+ "loss": 3.0524,
41558
+ "step": 57900
41559
+ },
41560
+ {
41561
+ "epoch": 3.955e-06,
41562
+ "grad_norm": 0.4609375,
41563
+ "learning_rate": 4.495761069937419e-05,
41564
+ "loss": 3.0356,
41565
+ "step": 57910
41566
+ },
41567
+ {
41568
+ "epoch": 3.96e-06,
41569
+ "grad_norm": 0.4921875,
41570
+ "learning_rate": 4.490964555409064e-05,
41571
+ "loss": 3.038,
41572
+ "step": 57920
41573
+ },
41574
+ {
41575
+ "epoch": 3.965e-06,
41576
+ "grad_norm": 0.474609375,
41577
+ "learning_rate": 4.486175294276337e-05,
41578
+ "loss": 3.0396,
41579
+ "step": 57930
41580
+ },
41581
+ {
41582
+ "epoch": 3.97e-06,
41583
+ "grad_norm": 0.482421875,
41584
+ "learning_rate": 4.481393289431929e-05,
41585
+ "loss": 3.0425,
41586
+ "step": 57940
41587
+ },
41588
+ {
41589
+ "epoch": 3.975e-06,
41590
+ "grad_norm": 0.46875,
41591
+ "learning_rate": 4.4766185437641437e-05,
41592
+ "loss": 3.0307,
41593
+ "step": 57950
41594
+ },
41595
+ {
41596
+ "epoch": 3.98e-06,
41597
+ "grad_norm": 0.43359375,
41598
+ "learning_rate": 4.4718510601569016e-05,
41599
+ "loss": 3.023,
41600
+ "step": 57960
41601
+ },
41602
+ {
41603
+ "epoch": 3.985e-06,
41604
+ "grad_norm": 0.466796875,
41605
+ "learning_rate": 4.4670908414897454e-05,
41606
+ "loss": 3.0441,
41607
+ "step": 57970
41608
+ },
41609
+ {
41610
+ "epoch": 3.99e-06,
41611
+ "grad_norm": 0.4921875,
41612
+ "learning_rate": 4.462337890637812e-05,
41613
+ "loss": 3.0096,
41614
+ "step": 57980
41615
+ },
41616
+ {
41617
+ "epoch": 3.995e-06,
41618
+ "grad_norm": 0.4765625,
41619
+ "learning_rate": 4.457592210471869e-05,
41620
+ "loss": 3.0315,
41621
+ "step": 57990
41622
+ },
41623
+ {
41624
+ "epoch": 4e-06,
41625
+ "grad_norm": 0.50390625,
41626
+ "learning_rate": 4.4528538038582794e-05,
41627
+ "loss": 3.0336,
41628
+ "step": 58000
41629
+ },
41630
+ {
41631
+ "epoch": 4e-06,
41632
+ "eval_loss": 3.087162971496582,
41633
+ "eval_runtime": 0.0617,
41634
+ "eval_samples_per_second": 518.477,
41635
+ "eval_steps_per_second": 16.202,
41636
+ "step": 58000
41637
  }
41638
  ],
41639
  "logging_steps": 10,
 
41653
  "attributes": {}
41654
  }
41655
  },
41656
+ "total_flos": 1.16894698831872e+18,
41657
  "train_batch_size": 240,
41658
  "trial_name": null,
41659
  "trial_params": null