mtzig commited on
Commit
6e50ab1
·
verified ·
1 Parent(s): 1aff730

Training in progress, step 700, checkpoint

Browse files
last-checkpoint/optimizer_0/.metadata CHANGED
Binary files a/last-checkpoint/optimizer_0/.metadata and b/last-checkpoint/optimizer_0/.metadata differ
 
last-checkpoint/optimizer_0/__0_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c7ebbcad844382cb0827a7b1f134dbcd4d34137f17f88cff4f0916eb189ebf5
3
  size 13934748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7dc1d8e3e4567fe89f4044c634b8f92aedf608d5bdd3f24fc45d9218d18c608
3
  size 13934748
last-checkpoint/optimizer_0/__1_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7112a496d5fcae5f50cfea78f1f333eab9ed1e0c59313fd80a7a7bc132bf69da
3
  size 13999412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa097179e7a3cbf7bef3aa37244226bfd1640b93c7ba0b5dfaa41fa616ac02a
3
  size 13999412
last-checkpoint/optimizer_0/__2_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8017e33ea602d361b2a15d6086fc895939152bd60dd6cf18b54db9895e8fa4ab
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed962c5c5afe2495377b16a9858edd276c71d561e3acc283b688b0a7992d8b8
3
  size 13990904
last-checkpoint/optimizer_0/__3_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b44a3e9c1fc45b6852fc5241f9ff5cc13d8e2ff6074f9df68b4d097ed706134
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f176ea9f6443c51ec492b348b90b111f939183a5e003fcf58ccce5a48bed8
3
  size 13990904
last-checkpoint/pytorch_model_fsdp_0/.metadata CHANGED
Binary files a/last-checkpoint/pytorch_model_fsdp_0/.metadata and b/last-checkpoint/pytorch_model_fsdp_0/.metadata differ
 
last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecc2212000c5fe210e90809b2e44ab52cdbe049455449ffbb43a7aee4a0f7198
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1032191a70fdd167493a8a8fad09fb846d227558db21ec9589296a5451c68d
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e14dfa71bc73ec24ac571cc78cf5e1386575d6b3eadffbdf1fdb4f7ef2266da
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a2e4e249d34019134215ddaa4cc63e8644939816a9a88ec74d584e3f0992dc
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60546e3c3ddce8d7a69cf9166934de67859396cc08b7574b96d474577977c98
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dadeb199fe580ea06456c94dcbb2d45ed31e34770c0b224e435256b01449ac
3
  size 6966784
last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bae454cfbbeef253a90b9291e2fe802fd4eab12a25818000192a303e71359d4
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd840616de0e70d365cbe915046e9309ff83ea7be6461314be0447bd565a18fc
3
  size 6966784
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13cdfb0ba0b39344ffb7c51f008a9525a0099ba731e0b27df1e92d8952acacbf
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4b633cac6d9b72a3e5d722d9f2722a25aaa75c4863f524e50216508a581110
3
  size 14960
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:007a009d54f5cc96725c131dafb54cc883f16e2aa322b400a09312dd7b22f98b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328d400156bec7fe19b325dd69ca88353a35391b51331286aebee3364fe74ad0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.7425742574257426,
5
  "eval_steps": 20,
6
- "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -4579,6 +4579,766 @@
4579
  "eval_samples_per_second": 5.495,
4580
  "eval_steps_per_second": 0.179,
4581
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4582
  }
4583
  ],
4584
  "logging_steps": 1,
@@ -4598,7 +5358,7 @@
4598
  "attributes": {}
4599
  }
4600
  },
4601
- "total_flos": 1.8390793736473805e+17,
4602
  "train_batch_size": 8,
4603
  "trial_name": null,
4604
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8663366336633663,
5
  "eval_steps": 20,
6
+ "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
4579
  "eval_samples_per_second": 5.495,
4580
  "eval_steps_per_second": 0.179,
4581
  "step": 600
4582
+ },
4583
+ {
4584
+ "epoch": 0.7438118811881188,
4585
+ "grad_norm": 4.045815944671631,
4586
+ "learning_rate": 3.740999317291618e-06,
4587
+ "loss": 0.2221,
4588
+ "step": 601
4589
+ },
4590
+ {
4591
+ "epoch": 0.745049504950495,
4592
+ "grad_norm": 5.232572078704834,
4593
+ "learning_rate": 3.7073558206426673e-06,
4594
+ "loss": 0.2071,
4595
+ "step": 602
4596
+ },
4597
+ {
4598
+ "epoch": 0.7462871287128713,
4599
+ "grad_norm": 4.61077356338501,
4600
+ "learning_rate": 3.6738298309082665e-06,
4601
+ "loss": 0.1197,
4602
+ "step": 603
4603
+ },
4604
+ {
4605
+ "epoch": 0.7475247524752475,
4606
+ "grad_norm": 4.389346122741699,
4607
+ "learning_rate": 3.6404219741425084e-06,
4608
+ "loss": 0.153,
4609
+ "step": 604
4610
+ },
4611
+ {
4612
+ "epoch": 0.7487623762376238,
4613
+ "grad_norm": 6.2665791511535645,
4614
+ "learning_rate": 3.6071328741934985e-06,
4615
+ "loss": 0.2109,
4616
+ "step": 605
4617
+ },
4618
+ {
4619
+ "epoch": 0.75,
4620
+ "grad_norm": 2.8577771186828613,
4621
+ "learning_rate": 3.5739631526917152e-06,
4622
+ "loss": 0.1445,
4623
+ "step": 606
4624
+ },
4625
+ {
4626
+ "epoch": 0.7512376237623762,
4627
+ "grad_norm": 5.7536187171936035,
4628
+ "learning_rate": 3.540913429038407e-06,
4629
+ "loss": 0.1783,
4630
+ "step": 607
4631
+ },
4632
+ {
4633
+ "epoch": 0.7524752475247525,
4634
+ "grad_norm": 5.14769172668457,
4635
+ "learning_rate": 3.507984320394012e-06,
4636
+ "loss": 0.2198,
4637
+ "step": 608
4638
+ },
4639
+ {
4640
+ "epoch": 0.7537128712871287,
4641
+ "grad_norm": 6.156418323516846,
4642
+ "learning_rate": 3.47517644166664e-06,
4643
+ "loss": 0.1891,
4644
+ "step": 609
4645
+ },
4646
+ {
4647
+ "epoch": 0.754950495049505,
4648
+ "grad_norm": 3.9831583499908447,
4649
+ "learning_rate": 3.442490405500598e-06,
4650
+ "loss": 0.2457,
4651
+ "step": 610
4652
+ },
4653
+ {
4654
+ "epoch": 0.7561881188118812,
4655
+ "grad_norm": 5.4462056159973145,
4656
+ "learning_rate": 3.4099268222649373e-06,
4657
+ "loss": 0.2008,
4658
+ "step": 611
4659
+ },
4660
+ {
4661
+ "epoch": 0.7574257425742574,
4662
+ "grad_norm": 3.8568873405456543,
4663
+ "learning_rate": 3.3774863000420545e-06,
4664
+ "loss": 0.1695,
4665
+ "step": 612
4666
+ },
4667
+ {
4668
+ "epoch": 0.7586633663366337,
4669
+ "grad_norm": 5.273173809051514,
4670
+ "learning_rate": 3.3451694446163553e-06,
4671
+ "loss": 0.2127,
4672
+ "step": 613
4673
+ },
4674
+ {
4675
+ "epoch": 0.7599009900990099,
4676
+ "grad_norm": 5.92859411239624,
4677
+ "learning_rate": 3.3129768594629186e-06,
4678
+ "loss": 0.1385,
4679
+ "step": 614
4680
+ },
4681
+ {
4682
+ "epoch": 0.7611386138613861,
4683
+ "grad_norm": 5.471877574920654,
4684
+ "learning_rate": 3.2809091457362464e-06,
4685
+ "loss": 0.2105,
4686
+ "step": 615
4687
+ },
4688
+ {
4689
+ "epoch": 0.7623762376237624,
4690
+ "grad_norm": 3.4092907905578613,
4691
+ "learning_rate": 3.248966902259024e-06,
4692
+ "loss": 0.156,
4693
+ "step": 616
4694
+ },
4695
+ {
4696
+ "epoch": 0.7636138613861386,
4697
+ "grad_norm": 4.115101337432861,
4698
+ "learning_rate": 3.2171507255109457e-06,
4699
+ "loss": 0.2304,
4700
+ "step": 617
4701
+ },
4702
+ {
4703
+ "epoch": 0.7648514851485149,
4704
+ "grad_norm": 4.784317493438721,
4705
+ "learning_rate": 3.185461209617571e-06,
4706
+ "loss": 0.2025,
4707
+ "step": 618
4708
+ },
4709
+ {
4710
+ "epoch": 0.7660891089108911,
4711
+ "grad_norm": 4.379182815551758,
4712
+ "learning_rate": 3.153898946339241e-06,
4713
+ "loss": 0.1843,
4714
+ "step": 619
4715
+ },
4716
+ {
4717
+ "epoch": 0.7673267326732673,
4718
+ "grad_norm": 4.599033355712891,
4719
+ "learning_rate": 3.122464525060013e-06,
4720
+ "loss": 0.1743,
4721
+ "step": 620
4722
+ },
4723
+ {
4724
+ "epoch": 0.7673267326732673,
4725
+ "eval_accuracy": 0.8658536585365854,
4726
+ "eval_f1": 0.7256235827664399,
4727
+ "eval_loss": 0.29202917218208313,
4728
+ "eval_precision": 0.851063829787234,
4729
+ "eval_recall": 0.6324110671936759,
4730
+ "eval_runtime": 47.9364,
4731
+ "eval_samples_per_second": 5.758,
4732
+ "eval_steps_per_second": 0.188,
4733
+ "step": 620
4734
+ },
4735
+ {
4736
+ "epoch": 0.7685643564356436,
4737
+ "grad_norm": 4.76499605178833,
4738
+ "learning_rate": 3.0911585327766658e-06,
4739
+ "loss": 0.2115,
4740
+ "step": 621
4741
+ },
4742
+ {
4743
+ "epoch": 0.7698019801980198,
4744
+ "grad_norm": 3.3205549716949463,
4745
+ "learning_rate": 3.059981554087732e-06,
4746
+ "loss": 0.1956,
4747
+ "step": 622
4748
+ },
4749
+ {
4750
+ "epoch": 0.7710396039603961,
4751
+ "grad_norm": 5.28842306137085,
4752
+ "learning_rate": 3.0289341711825817e-06,
4753
+ "loss": 0.2971,
4754
+ "step": 623
4755
+ },
4756
+ {
4757
+ "epoch": 0.7722772277227723,
4758
+ "grad_norm": 5.2406182289123535,
4759
+ "learning_rate": 2.998016963830562e-06,
4760
+ "loss": 0.188,
4761
+ "step": 624
4762
+ },
4763
+ {
4764
+ "epoch": 0.7735148514851485,
4765
+ "grad_norm": 5.418379783630371,
4766
+ "learning_rate": 2.96723050937015e-06,
4767
+ "loss": 0.1859,
4768
+ "step": 625
4769
+ },
4770
+ {
4771
+ "epoch": 0.7747524752475248,
4772
+ "grad_norm": 3.3900177478790283,
4773
+ "learning_rate": 2.9365753826981947e-06,
4774
+ "loss": 0.1113,
4775
+ "step": 626
4776
+ },
4777
+ {
4778
+ "epoch": 0.775990099009901,
4779
+ "grad_norm": 7.410489082336426,
4780
+ "learning_rate": 2.9060521562591625e-06,
4781
+ "loss": 0.2426,
4782
+ "step": 627
4783
+ },
4784
+ {
4785
+ "epoch": 0.7772277227722773,
4786
+ "grad_norm": 4.490034580230713,
4787
+ "learning_rate": 2.875661400034452e-06,
4788
+ "loss": 0.1891,
4789
+ "step": 628
4790
+ },
4791
+ {
4792
+ "epoch": 0.7784653465346535,
4793
+ "grad_norm": 3.7824716567993164,
4794
+ "learning_rate": 2.8454036815317643e-06,
4795
+ "loss": 0.1712,
4796
+ "step": 629
4797
+ },
4798
+ {
4799
+ "epoch": 0.7797029702970297,
4800
+ "grad_norm": 6.608094215393066,
4801
+ "learning_rate": 2.8152795657744882e-06,
4802
+ "loss": 0.1994,
4803
+ "step": 630
4804
+ },
4805
+ {
4806
+ "epoch": 0.780940594059406,
4807
+ "grad_norm": 4.14816951751709,
4808
+ "learning_rate": 2.78528961529115e-06,
4809
+ "loss": 0.2238,
4810
+ "step": 631
4811
+ },
4812
+ {
4813
+ "epoch": 0.7821782178217822,
4814
+ "grad_norm": 4.3334760665893555,
4815
+ "learning_rate": 2.7554343901049295e-06,
4816
+ "loss": 0.256,
4817
+ "step": 632
4818
+ },
4819
+ {
4820
+ "epoch": 0.7834158415841584,
4821
+ "grad_norm": 4.515098571777344,
4822
+ "learning_rate": 2.7257144477231756e-06,
4823
+ "loss": 0.2338,
4824
+ "step": 633
4825
+ },
4826
+ {
4827
+ "epoch": 0.7846534653465347,
4828
+ "grad_norm": 4.144233703613281,
4829
+ "learning_rate": 2.696130343127007e-06,
4830
+ "loss": 0.1322,
4831
+ "step": 634
4832
+ },
4833
+ {
4834
+ "epoch": 0.7858910891089109,
4835
+ "grad_norm": 3.5474421977996826,
4836
+ "learning_rate": 2.666682628760958e-06,
4837
+ "loss": 0.1656,
4838
+ "step": 635
4839
+ },
4840
+ {
4841
+ "epoch": 0.7871287128712872,
4842
+ "grad_norm": 4.109697341918945,
4843
+ "learning_rate": 2.6373718545226444e-06,
4844
+ "loss": 0.2305,
4845
+ "step": 636
4846
+ },
4847
+ {
4848
+ "epoch": 0.7883663366336634,
4849
+ "grad_norm": 6.762195587158203,
4850
+ "learning_rate": 2.6081985677525124e-06,
4851
+ "loss": 0.2165,
4852
+ "step": 637
4853
+ },
4854
+ {
4855
+ "epoch": 0.7896039603960396,
4856
+ "grad_norm": 4.237494945526123,
4857
+ "learning_rate": 2.5791633132236027e-06,
4858
+ "loss": 0.2376,
4859
+ "step": 638
4860
+ },
4861
+ {
4862
+ "epoch": 0.7908415841584159,
4863
+ "grad_norm": 4.219669818878174,
4864
+ "learning_rate": 2.550266633131382e-06,
4865
+ "loss": 0.1932,
4866
+ "step": 639
4867
+ },
4868
+ {
4869
+ "epoch": 0.7920792079207921,
4870
+ "grad_norm": 3.1918282508850098,
4871
+ "learning_rate": 2.521509067083631e-06,
4872
+ "loss": 0.1281,
4873
+ "step": 640
4874
+ },
4875
+ {
4876
+ "epoch": 0.7920792079207921,
4877
+ "eval_accuracy": 0.8658536585365854,
4878
+ "eval_f1": 0.7268623024830699,
4879
+ "eval_loss": 0.29117584228515625,
4880
+ "eval_precision": 0.8473684210526315,
4881
+ "eval_recall": 0.6363636363636364,
4882
+ "eval_runtime": 48.65,
4883
+ "eval_samples_per_second": 5.673,
4884
+ "eval_steps_per_second": 0.185,
4885
+ "step": 640
4886
+ },
4887
+ {
4888
+ "epoch": 0.7933168316831684,
4889
+ "grad_norm": 3.6139471530914307,
4890
+ "learning_rate": 2.4928911520903466e-06,
4891
+ "loss": 0.1664,
4892
+ "step": 641
4893
+ },
4894
+ {
4895
+ "epoch": 0.7945544554455446,
4896
+ "grad_norm": 3.5790998935699463,
4897
+ "learning_rate": 2.4644134225537265e-06,
4898
+ "loss": 0.1926,
4899
+ "step": 642
4900
+ },
4901
+ {
4902
+ "epoch": 0.7957920792079208,
4903
+ "grad_norm": 6.101653575897217,
4904
+ "learning_rate": 2.4360764102581947e-06,
4905
+ "loss": 0.1896,
4906
+ "step": 643
4907
+ },
4908
+ {
4909
+ "epoch": 0.7970297029702971,
4910
+ "grad_norm": 4.154812335968018,
4911
+ "learning_rate": 2.4078806443604595e-06,
4912
+ "loss": 0.2341,
4913
+ "step": 644
4914
+ },
4915
+ {
4916
+ "epoch": 0.7982673267326733,
4917
+ "grad_norm": 4.5489630699157715,
4918
+ "learning_rate": 2.379826651379632e-06,
4919
+ "loss": 0.2022,
4920
+ "step": 645
4921
+ },
4922
+ {
4923
+ "epoch": 0.7995049504950495,
4924
+ "grad_norm": 4.680227756500244,
4925
+ "learning_rate": 2.351914955187412e-06,
4926
+ "loss": 0.2343,
4927
+ "step": 646
4928
+ },
4929
+ {
4930
+ "epoch": 0.8007425742574258,
4931
+ "grad_norm": 4.6964898109436035,
4932
+ "learning_rate": 2.3241460769982814e-06,
4933
+ "loss": 0.2174,
4934
+ "step": 647
4935
+ },
4936
+ {
4937
+ "epoch": 0.801980198019802,
4938
+ "grad_norm": 5.496919631958008,
4939
+ "learning_rate": 2.2965205353597866e-06,
4940
+ "loss": 0.2319,
4941
+ "step": 648
4942
+ },
4943
+ {
4944
+ "epoch": 0.8032178217821783,
4945
+ "grad_norm": 4.648072242736816,
4946
+ "learning_rate": 2.269038846142847e-06,
4947
+ "loss": 0.1666,
4948
+ "step": 649
4949
+ },
4950
+ {
4951
+ "epoch": 0.8044554455445545,
4952
+ "grad_norm": 3.861116409301758,
4953
+ "learning_rate": 2.241701522532136e-06,
4954
+ "loss": 0.1696,
4955
+ "step": 650
4956
+ },
4957
+ {
4958
+ "epoch": 0.8056930693069307,
4959
+ "grad_norm": 3.7325706481933594,
4960
+ "learning_rate": 2.214509075016478e-06,
4961
+ "loss": 0.168,
4962
+ "step": 651
4963
+ },
4964
+ {
4965
+ "epoch": 0.806930693069307,
4966
+ "grad_norm": 3.7055068016052246,
4967
+ "learning_rate": 2.1874620113793286e-06,
4968
+ "loss": 0.2214,
4969
+ "step": 652
4970
+ },
4971
+ {
4972
+ "epoch": 0.8081683168316832,
4973
+ "grad_norm": 3.3289315700531006,
4974
+ "learning_rate": 2.160560836689286e-06,
4975
+ "loss": 0.1643,
4976
+ "step": 653
4977
+ },
4978
+ {
4979
+ "epoch": 0.8094059405940595,
4980
+ "grad_norm": 3.24979567527771,
4981
+ "learning_rate": 2.1338060532906734e-06,
4982
+ "loss": 0.1478,
4983
+ "step": 654
4984
+ },
4985
+ {
4986
+ "epoch": 0.8106435643564357,
4987
+ "grad_norm": 6.499382972717285,
4988
+ "learning_rate": 2.107198160794136e-06,
4989
+ "loss": 0.1785,
4990
+ "step": 655
4991
+ },
4992
+ {
4993
+ "epoch": 0.8118811881188119,
4994
+ "grad_norm": 5.324498176574707,
4995
+ "learning_rate": 2.080737656067325e-06,
4996
+ "loss": 0.2121,
4997
+ "step": 656
4998
+ },
4999
+ {
5000
+ "epoch": 0.8131188118811881,
5001
+ "grad_norm": 3.2809088230133057,
5002
+ "learning_rate": 2.054425033225628e-06,
5003
+ "loss": 0.1683,
5004
+ "step": 657
5005
+ },
5006
+ {
5007
+ "epoch": 0.8143564356435643,
5008
+ "grad_norm": 4.163755416870117,
5009
+ "learning_rate": 2.028260783622914e-06,
5010
+ "loss": 0.1624,
5011
+ "step": 658
5012
+ },
5013
+ {
5014
+ "epoch": 0.8155940594059405,
5015
+ "grad_norm": 5.601637363433838,
5016
+ "learning_rate": 2.002245395842394e-06,
5017
+ "loss": 0.2025,
5018
+ "step": 659
5019
+ },
5020
+ {
5021
+ "epoch": 0.8168316831683168,
5022
+ "grad_norm": 6.822818756103516,
5023
+ "learning_rate": 1.9763793556874655e-06,
5024
+ "loss": 0.1879,
5025
+ "step": 660
5026
+ },
5027
+ {
5028
+ "epoch": 0.8168316831683168,
5029
+ "eval_accuracy": 0.8625277161862528,
5030
+ "eval_f1": 0.7181818181818181,
5031
+ "eval_loss": 0.293789803981781,
5032
+ "eval_precision": 0.8449197860962567,
5033
+ "eval_recall": 0.6245059288537549,
5034
+ "eval_runtime": 48.9901,
5035
+ "eval_samples_per_second": 5.634,
5036
+ "eval_steps_per_second": 0.184,
5037
+ "step": 660
5038
+ },
5039
+ {
5040
+ "epoch": 0.818069306930693,
5041
+ "grad_norm": 5.174654483795166,
5042
+ "learning_rate": 1.950663146172657e-06,
5043
+ "loss": 0.2161,
5044
+ "step": 661
5045
+ },
5046
+ {
5047
+ "epoch": 0.8193069306930693,
5048
+ "grad_norm": 7.8807692527771,
5049
+ "learning_rate": 1.9250972475146092e-06,
5050
+ "loss": 0.2391,
5051
+ "step": 662
5052
+ },
5053
+ {
5054
+ "epoch": 0.8205445544554455,
5055
+ "grad_norm": 4.177780628204346,
5056
+ "learning_rate": 1.8996821371231022e-06,
5057
+ "loss": 0.142,
5058
+ "step": 663
5059
+ },
5060
+ {
5061
+ "epoch": 0.8217821782178217,
5062
+ "grad_norm": 4.918459892272949,
5063
+ "learning_rate": 1.874418289592137e-06,
5064
+ "loss": 0.2504,
5065
+ "step": 664
5066
+ },
5067
+ {
5068
+ "epoch": 0.823019801980198,
5069
+ "grad_norm": 7.126182556152344,
5070
+ "learning_rate": 1.849306176691088e-06,
5071
+ "loss": 0.1987,
5072
+ "step": 665
5073
+ },
5074
+ {
5075
+ "epoch": 0.8242574257425742,
5076
+ "grad_norm": 5.940370082855225,
5077
+ "learning_rate": 1.8243462673558755e-06,
5078
+ "loss": 0.2805,
5079
+ "step": 666
5080
+ },
5081
+ {
5082
+ "epoch": 0.8254950495049505,
5083
+ "grad_norm": 3.46482515335083,
5084
+ "learning_rate": 1.799539027680216e-06,
5085
+ "loss": 0.1328,
5086
+ "step": 667
5087
+ },
5088
+ {
5089
+ "epoch": 0.8267326732673267,
5090
+ "grad_norm": 8.600014686584473,
5091
+ "learning_rate": 1.7748849209069286e-06,
5092
+ "loss": 0.2778,
5093
+ "step": 668
5094
+ },
5095
+ {
5096
+ "epoch": 0.8279702970297029,
5097
+ "grad_norm": 3.1640994548797607,
5098
+ "learning_rate": 1.7503844074192655e-06,
5099
+ "loss": 0.1474,
5100
+ "step": 669
5101
+ },
5102
+ {
5103
+ "epoch": 0.8292079207920792,
5104
+ "grad_norm": 5.749293327331543,
5105
+ "learning_rate": 1.7260379447323327e-06,
5106
+ "loss": 0.2154,
5107
+ "step": 670
5108
+ },
5109
+ {
5110
+ "epoch": 0.8304455445544554,
5111
+ "grad_norm": 6.068516731262207,
5112
+ "learning_rate": 1.7018459874845327e-06,
5113
+ "loss": 0.226,
5114
+ "step": 671
5115
+ },
5116
+ {
5117
+ "epoch": 0.8316831683168316,
5118
+ "grad_norm": 8.348623275756836,
5119
+ "learning_rate": 1.6778089874290793e-06,
5120
+ "loss": 0.29,
5121
+ "step": 672
5122
+ },
5123
+ {
5124
+ "epoch": 0.8329207920792079,
5125
+ "grad_norm": 6.485348701477051,
5126
+ "learning_rate": 1.6539273934255728e-06,
5127
+ "loss": 0.2041,
5128
+ "step": 673
5129
+ },
5130
+ {
5131
+ "epoch": 0.8341584158415841,
5132
+ "grad_norm": 4.267493724822998,
5133
+ "learning_rate": 1.6302016514316e-06,
5134
+ "loss": 0.1943,
5135
+ "step": 674
5136
+ },
5137
+ {
5138
+ "epoch": 0.8353960396039604,
5139
+ "grad_norm": 3.1872661113739014,
5140
+ "learning_rate": 1.6066322044944126e-06,
5141
+ "loss": 0.1807,
5142
+ "step": 675
5143
+ },
5144
+ {
5145
+ "epoch": 0.8366336633663366,
5146
+ "grad_norm": 5.531446933746338,
5147
+ "learning_rate": 1.583219492742667e-06,
5148
+ "loss": 0.244,
5149
+ "step": 676
5150
+ },
5151
+ {
5152
+ "epoch": 0.8378712871287128,
5153
+ "grad_norm": 4.929156303405762,
5154
+ "learning_rate": 1.5599639533781853e-06,
5155
+ "loss": 0.1353,
5156
+ "step": 677
5157
+ },
5158
+ {
5159
+ "epoch": 0.8391089108910891,
5160
+ "grad_norm": 4.086613655090332,
5161
+ "learning_rate": 1.5368660206678031e-06,
5162
+ "loss": 0.2356,
5163
+ "step": 678
5164
+ },
5165
+ {
5166
+ "epoch": 0.8403465346534653,
5167
+ "grad_norm": 4.462868690490723,
5168
+ "learning_rate": 1.5139261259352589e-06,
5169
+ "loss": 0.1682,
5170
+ "step": 679
5171
+ },
5172
+ {
5173
+ "epoch": 0.8415841584158416,
5174
+ "grad_norm": 3.685532808303833,
5175
+ "learning_rate": 1.4911446975531329e-06,
5176
+ "loss": 0.1741,
5177
+ "step": 680
5178
+ },
5179
+ {
5180
+ "epoch": 0.8415841584158416,
5181
+ "eval_accuracy": 0.8625277161862528,
5182
+ "eval_f1": 0.7168949771689498,
5183
+ "eval_loss": 0.2965390384197235,
5184
+ "eval_precision": 0.8486486486486486,
5185
+ "eval_recall": 0.6205533596837944,
5186
+ "eval_runtime": 49.6397,
5187
+ "eval_samples_per_second": 5.56,
5188
+ "eval_steps_per_second": 0.181,
5189
+ "step": 680
5190
+ },
5191
+ {
5192
+ "epoch": 0.8428217821782178,
5193
+ "grad_norm": 3.4863808155059814,
5194
+ "learning_rate": 1.4685221609348632e-06,
5195
+ "loss": 0.2203,
5196
+ "step": 681
5197
+ },
5198
+ {
5199
+ "epoch": 0.844059405940594,
5200
+ "grad_norm": 3.9294660091400146,
5201
+ "learning_rate": 1.4460589385267843e-06,
5202
+ "loss": 0.1609,
5203
+ "step": 682
5204
+ },
5205
+ {
5206
+ "epoch": 0.8452970297029703,
5207
+ "grad_norm": 3.837347984313965,
5208
+ "learning_rate": 1.4237554498002425e-06,
5209
+ "loss": 0.1866,
5210
+ "step": 683
5211
+ },
5212
+ {
5213
+ "epoch": 0.8465346534653465,
5214
+ "grad_norm": 5.066103458404541,
5215
+ "learning_rate": 1.4016121112437787e-06,
5216
+ "loss": 0.2101,
5217
+ "step": 684
5218
+ },
5219
+ {
5220
+ "epoch": 0.8477722772277227,
5221
+ "grad_norm": 4.614877700805664,
5222
+ "learning_rate": 1.3796293363553259e-06,
5223
+ "loss": 0.2043,
5224
+ "step": 685
5225
+ },
5226
+ {
5227
+ "epoch": 0.849009900990099,
5228
+ "grad_norm": 3.7771222591400146,
5229
+ "learning_rate": 1.3578075356345044e-06,
5230
+ "loss": 0.1599,
5231
+ "step": 686
5232
+ },
5233
+ {
5234
+ "epoch": 0.8502475247524752,
5235
+ "grad_norm": 2.7725830078125,
5236
+ "learning_rate": 1.3361471165749563e-06,
5237
+ "loss": 0.1179,
5238
+ "step": 687
5239
+ },
5240
+ {
5241
+ "epoch": 0.8514851485148515,
5242
+ "grad_norm": 4.316575527191162,
5243
+ "learning_rate": 1.3146484836567263e-06,
5244
+ "loss": 0.1996,
5245
+ "step": 688
5246
+ },
5247
+ {
5248
+ "epoch": 0.8527227722772277,
5249
+ "grad_norm": 3.446519374847412,
5250
+ "learning_rate": 1.2933120383387132e-06,
5251
+ "loss": 0.2208,
5252
+ "step": 689
5253
+ },
5254
+ {
5255
+ "epoch": 0.8539603960396039,
5256
+ "grad_norm": 4.64270544052124,
5257
+ "learning_rate": 1.2721381790511832e-06,
5258
+ "loss": 0.1745,
5259
+ "step": 690
5260
+ },
5261
+ {
5262
+ "epoch": 0.8551980198019802,
5263
+ "grad_norm": 5.920294761657715,
5264
+ "learning_rate": 1.2511273011883096e-06,
5265
+ "loss": 0.2257,
5266
+ "step": 691
5267
+ },
5268
+ {
5269
+ "epoch": 0.8564356435643564,
5270
+ "grad_norm": 5.84797477722168,
5271
+ "learning_rate": 1.2302797971008085e-06,
5272
+ "loss": 0.1741,
5273
+ "step": 692
5274
+ },
5275
+ {
5276
+ "epoch": 0.8576732673267327,
5277
+ "grad_norm": 4.7784223556518555,
5278
+ "learning_rate": 1.2095960560886e-06,
5279
+ "loss": 0.1844,
5280
+ "step": 693
5281
+ },
5282
+ {
5283
+ "epoch": 0.8589108910891089,
5284
+ "grad_norm": 4.6134161949157715,
5285
+ "learning_rate": 1.1890764643935393e-06,
5286
+ "loss": 0.26,
5287
+ "step": 694
5288
+ },
5289
+ {
5290
+ "epoch": 0.8601485148514851,
5291
+ "grad_norm": 3.6760635375976562,
5292
+ "learning_rate": 1.168721405192218e-06,
5293
+ "loss": 0.1946,
5294
+ "step": 695
5295
+ },
5296
+ {
5297
+ "epoch": 0.8613861386138614,
5298
+ "grad_norm": 5.395166873931885,
5299
+ "learning_rate": 1.1485312585887887e-06,
5300
+ "loss": 0.3086,
5301
+ "step": 696
5302
+ },
5303
+ {
5304
+ "epoch": 0.8626237623762376,
5305
+ "grad_norm": 3.1336684226989746,
5306
+ "learning_rate": 1.1285064016078784e-06,
5307
+ "loss": 0.1662,
5308
+ "step": 697
5309
+ },
5310
+ {
5311
+ "epoch": 0.8638613861386139,
5312
+ "grad_norm": 5.393222332000732,
5313
+ "learning_rate": 1.1086472081875488e-06,
5314
+ "loss": 0.2479,
5315
+ "step": 698
5316
+ },
5317
+ {
5318
+ "epoch": 0.8650990099009901,
5319
+ "grad_norm": 5.272143363952637,
5320
+ "learning_rate": 1.0889540491723106e-06,
5321
+ "loss": 0.1916,
5322
+ "step": 699
5323
+ },
5324
+ {
5325
+ "epoch": 0.8663366336633663,
5326
+ "grad_norm": 5.7492547035217285,
5327
+ "learning_rate": 1.0694272923061933e-06,
5328
+ "loss": 0.1429,
5329
+ "step": 700
5330
+ },
5331
+ {
5332
+ "epoch": 0.8663366336633663,
5333
+ "eval_accuracy": 0.8647450110864745,
5334
+ "eval_f1": 0.7276785714285714,
5335
+ "eval_loss": 0.2911153733730316,
5336
+ "eval_precision": 0.8358974358974359,
5337
+ "eval_recall": 0.6442687747035574,
5338
+ "eval_runtime": 48.2583,
5339
+ "eval_samples_per_second": 5.719,
5340
+ "eval_steps_per_second": 0.186,
5341
+ "step": 700
5342
  }
5343
  ],
5344
  "logging_steps": 1,
 
5358
  "attributes": {}
5359
  }
5360
  },
5361
+ "total_flos": 2.148551864918999e+17,
5362
  "train_batch_size": 8,
5363
  "trial_name": null,
5364
  "trial_params": null