mtzig commited on
Commit
7afe86e
·
verified ·
1 Parent(s): 0b06254

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 sha256:7454f5845a5f23b4913750fbc16c23c17c15de424259fe838f50365af1a6fc31
3
  size 13934748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5fb4d724032a1245dc6cde40f4e5188553186f46cc33db24ff9acace6d64996
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 sha256:85f7e2225ecc77b15d23f17a6bea4d6eff8126f32e4809d5fb9012178465eb09
3
  size 13999412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e385d511e036b931d8833bb9f18f12b276860005885c6db5883e2bb8ffb250
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:a00dd5beda4d499c230a9f8ca29e291ebb388ce836dab2a836a479101ade1b29
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c37b03fb2e32f372fe4bc5de8cfbfdcd80d4c5f02647d02082856a40cb7d81
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 sha256:3f93bf48e5d0d2bd9aeb51d2e8ded2cd18f7df64624a0dc6007c452f77b97c0b
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fc189980b81b63a0f5eb185c059a38e0e687a3da1cdbabb13632220bbd92f29
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 sha256:321edf67e47d0b4c67f8b27b7638c352cf813e649e5ee9996cca152fb9c75062
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22866ce89c0e7ab0cc0f664b14f5ba101d34c338fdb1a105f2b2815d715ca268
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:fed803da648fcbfb47d40579c66789c1b5813d1ca024980a285cc0b048653350
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba3c5c58c231743a3320074589c773530610636502758ac373fb041860f7629
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:c97e2f6d521cea150acde4f0539f7f18dddad1bc75aab9306523cb6a5047e1ae
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79b8891ee0d25a2be271a38d0ac5e556ce0257bf5123113c070352f99023ae9
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:f33f2493dd6209c0c885d7b0bc168e9eae2ef749d5250330e5bbff5e28b5a6d9
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcec9183c14a35cf480d0f7871398da31d6da2b44461bb7bdc738de5f51e523a
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 sha256:79f19fb56fbaf65a779ecd9cb3b30247bfd45158eafdcd105585ee87f1735d98
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d9fa53e4b694823856182f5d79606d713a9c38f7b0a474c8e8377b701cc4064
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afab5b50c52c688a707864652d6c5558ef69395b7a2375fa583b1b7139f6c609
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e467e256d1aeb5c59910c1df837a848b831bc8f1a437fc0b52c0ae7e6a47b29
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1755b69d438567bb52e96e1dc58c619fdbd9a694f1794f20010dff70a9f6c151
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a104e0586ff0fcc9930cb2ff4e524b78a6f6ffc91335870d99757828f52f1c
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd2c36f5a9cc648d59e856fb43df0193c9d5e0acbe931f548fb0ceebfba5c6a1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01842b4ecf9c63cb6983558b75f5223cbe340d5e106d6e47d3afec1652f1f03
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be9988adf605fcbeeb14de5bdc4b2db6b176f9774ef7818d04698d021a01fbf6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff7644a4cf9b613e830e53fbdb92eb21facf6604e16b66cdc1f7a045b886b1a7
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": 0.7531380753138075,
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": 5.341,
4580
  "eval_steps_per_second": 0.174,
4581
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4582
  }
4583
  ],
4584
  "logging_steps": 1,
@@ -4598,7 +5358,7 @@
4598
  "attributes": {}
4599
  }
4600
  },
4601
- "total_flos": 2.19779349803434e+17,
4602
  "train_batch_size": 6,
4603
  "trial_name": null,
4604
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8786610878661087,
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": 5.341,
4580
  "eval_steps_per_second": 0.174,
4581
  "step": 600
4582
+ },
4583
+ {
4584
+ "epoch": 0.7543933054393306,
4585
+ "grad_norm": 5.352249622344971,
4586
+ "learning_rate": 3.4423537100200068e-06,
4587
+ "loss": 0.2344,
4588
+ "step": 601
4589
+ },
4590
+ {
4591
+ "epoch": 0.7556485355648536,
4592
+ "grad_norm": 4.358277797698975,
4593
+ "learning_rate": 3.4092913288148254e-06,
4594
+ "loss": 0.2084,
4595
+ "step": 602
4596
+ },
4597
+ {
4598
+ "epoch": 0.7569037656903765,
4599
+ "grad_norm": 4.106777667999268,
4600
+ "learning_rate": 3.3763558311006207e-06,
4601
+ "loss": 0.2017,
4602
+ "step": 603
4603
+ },
4604
+ {
4605
+ "epoch": 0.7581589958158996,
4606
+ "grad_norm": 6.909910678863525,
4607
+ "learning_rate": 3.343547850947434e-06,
4608
+ "loss": 0.3994,
4609
+ "step": 604
4610
+ },
4611
+ {
4612
+ "epoch": 0.7594142259414226,
4613
+ "grad_norm": 4.24434757232666,
4614
+ "learning_rate": 3.310868019970356e-06,
4615
+ "loss": 0.2443,
4616
+ "step": 605
4617
+ },
4618
+ {
4619
+ "epoch": 0.7606694560669456,
4620
+ "grad_norm": 4.735110759735107,
4621
+ "learning_rate": 3.2783169673173666e-06,
4622
+ "loss": 0.2305,
4623
+ "step": 606
4624
+ },
4625
+ {
4626
+ "epoch": 0.7619246861924687,
4627
+ "grad_norm": 4.206883907318115,
4628
+ "learning_rate": 3.2458953196572194e-06,
4629
+ "loss": 0.2061,
4630
+ "step": 607
4631
+ },
4632
+ {
4633
+ "epoch": 0.7631799163179916,
4634
+ "grad_norm": 2.6777400970458984,
4635
+ "learning_rate": 3.2136037011673803e-06,
4636
+ "loss": 0.1777,
4637
+ "step": 608
4638
+ },
4639
+ {
4640
+ "epoch": 0.7644351464435146,
4641
+ "grad_norm": 3.7428863048553467,
4642
+ "learning_rate": 3.181442733522008e-06,
4643
+ "loss": 0.211,
4644
+ "step": 609
4645
+ },
4646
+ {
4647
+ "epoch": 0.7656903765690377,
4648
+ "grad_norm": 5.144768714904785,
4649
+ "learning_rate": 3.149413035879996e-06,
4650
+ "loss": 0.2571,
4651
+ "step": 610
4652
+ },
4653
+ {
4654
+ "epoch": 0.7669456066945607,
4655
+ "grad_norm": 6.341953754425049,
4656
+ "learning_rate": 3.1175152248730343e-06,
4657
+ "loss": 0.2649,
4658
+ "step": 611
4659
+ },
4660
+ {
4661
+ "epoch": 0.7682008368200837,
4662
+ "grad_norm": 4.261897563934326,
4663
+ "learning_rate": 3.085749914593752e-06,
4664
+ "loss": 0.2207,
4665
+ "step": 612
4666
+ },
4667
+ {
4668
+ "epoch": 0.7694560669456066,
4669
+ "grad_norm": 3.700777053833008,
4670
+ "learning_rate": 3.0541177165838954e-06,
4671
+ "loss": 0.2589,
4672
+ "step": 613
4673
+ },
4674
+ {
4675
+ "epoch": 0.7707112970711297,
4676
+ "grad_norm": 5.691616535186768,
4677
+ "learning_rate": 3.022619239822535e-06,
4678
+ "loss": 0.2042,
4679
+ "step": 614
4680
+ },
4681
+ {
4682
+ "epoch": 0.7719665271966527,
4683
+ "grad_norm": 2.532932996749878,
4684
+ "learning_rate": 2.9912550907143766e-06,
4685
+ "loss": 0.2177,
4686
+ "step": 615
4687
+ },
4688
+ {
4689
+ "epoch": 0.7732217573221757,
4690
+ "grad_norm": 6.345351219177246,
4691
+ "learning_rate": 2.9600258730780564e-06,
4692
+ "loss": 0.2141,
4693
+ "step": 616
4694
+ },
4695
+ {
4696
+ "epoch": 0.7744769874476988,
4697
+ "grad_norm": 4.4296793937683105,
4698
+ "learning_rate": 2.9289321881345257e-06,
4699
+ "loss": 0.2414,
4700
+ "step": 617
4701
+ },
4702
+ {
4703
+ "epoch": 0.7757322175732217,
4704
+ "grad_norm": 5.737855911254883,
4705
+ "learning_rate": 2.897974634495482e-06,
4706
+ "loss": 0.2163,
4707
+ "step": 618
4708
+ },
4709
+ {
4710
+ "epoch": 0.7769874476987447,
4711
+ "grad_norm": 3.722508430480957,
4712
+ "learning_rate": 2.867153808151837e-06,
4713
+ "loss": 0.2102,
4714
+ "step": 619
4715
+ },
4716
+ {
4717
+ "epoch": 0.7782426778242678,
4718
+ "grad_norm": 3.9203503131866455,
4719
+ "learning_rate": 2.8364703024622474e-06,
4720
+ "loss": 0.2049,
4721
+ "step": 620
4722
+ },
4723
+ {
4724
+ "epoch": 0.7782426778242678,
4725
+ "eval_accuracy": 0.8587196467991169,
4726
+ "eval_f1": 0.7117117117117117,
4727
+ "eval_loss": 0.28623539209365845,
4728
+ "eval_precision": 0.8315789473684211,
4729
+ "eval_recall": 0.6220472440944882,
4730
+ "eval_runtime": 51.4017,
4731
+ "eval_samples_per_second": 5.389,
4732
+ "eval_steps_per_second": 0.175,
4733
+ "step": 620
4734
+ },
4735
+ {
4736
+ "epoch": 0.7794979079497908,
4737
+ "grad_norm": 5.395325660705566,
4738
+ "learning_rate": 2.8059247081416887e-06,
4739
+ "loss": 0.2889,
4740
+ "step": 621
4741
+ },
4742
+ {
4743
+ "epoch": 0.7807531380753138,
4744
+ "grad_norm": 3.7470452785491943,
4745
+ "learning_rate": 2.7755176132500905e-06,
4746
+ "loss": 0.2567,
4747
+ "step": 622
4748
+ },
4749
+ {
4750
+ "epoch": 0.7820083682008369,
4751
+ "grad_norm": 3.5239267349243164,
4752
+ "learning_rate": 2.745249603180996e-06,
4753
+ "loss": 0.214,
4754
+ "step": 623
4755
+ },
4756
+ {
4757
+ "epoch": 0.7832635983263598,
4758
+ "grad_norm": 3.5487923622131348,
4759
+ "learning_rate": 2.7151212606503164e-06,
4760
+ "loss": 0.2062,
4761
+ "step": 624
4762
+ },
4763
+ {
4764
+ "epoch": 0.7845188284518828,
4765
+ "grad_norm": 3.3393709659576416,
4766
+ "learning_rate": 2.6851331656850966e-06,
4767
+ "loss": 0.1947,
4768
+ "step": 625
4769
+ },
4770
+ {
4771
+ "epoch": 0.7857740585774059,
4772
+ "grad_norm": 2.6931920051574707,
4773
+ "learning_rate": 2.6552858956123485e-06,
4774
+ "loss": 0.2918,
4775
+ "step": 626
4776
+ },
4777
+ {
4778
+ "epoch": 0.7870292887029289,
4779
+ "grad_norm": 3.748667001724243,
4780
+ "learning_rate": 2.625580025047956e-06,
4781
+ "loss": 0.2286,
4782
+ "step": 627
4783
+ },
4784
+ {
4785
+ "epoch": 0.7882845188284519,
4786
+ "grad_norm": 3.2201664447784424,
4787
+ "learning_rate": 2.5960161258855807e-06,
4788
+ "loss": 0.2037,
4789
+ "step": 628
4790
+ },
4791
+ {
4792
+ "epoch": 0.7895397489539749,
4793
+ "grad_norm": 3.861560821533203,
4794
+ "learning_rate": 2.5665947672856774e-06,
4795
+ "loss": 0.2023,
4796
+ "step": 629
4797
+ },
4798
+ {
4799
+ "epoch": 0.7907949790794979,
4800
+ "grad_norm": 2.7438437938690186,
4801
+ "learning_rate": 2.5373165156645263e-06,
4802
+ "loss": 0.2018,
4803
+ "step": 630
4804
+ },
4805
+ {
4806
+ "epoch": 0.7920502092050209,
4807
+ "grad_norm": 4.868431568145752,
4808
+ "learning_rate": 2.5081819346833293e-06,
4809
+ "loss": 0.2575,
4810
+ "step": 631
4811
+ },
4812
+ {
4813
+ "epoch": 0.793305439330544,
4814
+ "grad_norm": 4.836085796356201,
4815
+ "learning_rate": 2.4791915852373604e-06,
4816
+ "loss": 0.206,
4817
+ "step": 632
4818
+ },
4819
+ {
4820
+ "epoch": 0.794560669456067,
4821
+ "grad_norm": 3.095149278640747,
4822
+ "learning_rate": 2.450346025445165e-06,
4823
+ "loss": 0.173,
4824
+ "step": 633
4825
+ },
4826
+ {
4827
+ "epoch": 0.7958158995815899,
4828
+ "grad_norm": 3.0923187732696533,
4829
+ "learning_rate": 2.4216458106378194e-06,
4830
+ "loss": 0.2016,
4831
+ "step": 634
4832
+ },
4833
+ {
4834
+ "epoch": 0.797071129707113,
4835
+ "grad_norm": 5.667265892028809,
4836
+ "learning_rate": 2.3930914933482317e-06,
4837
+ "loss": 0.3038,
4838
+ "step": 635
4839
+ },
4840
+ {
4841
+ "epoch": 0.798326359832636,
4842
+ "grad_norm": 4.840297222137451,
4843
+ "learning_rate": 2.3646836233005133e-06,
4844
+ "loss": 0.2346,
4845
+ "step": 636
4846
+ },
4847
+ {
4848
+ "epoch": 0.799581589958159,
4849
+ "grad_norm": 3.6551482677459717,
4850
+ "learning_rate": 2.3364227473993885e-06,
4851
+ "loss": 0.2153,
4852
+ "step": 637
4853
+ },
4854
+ {
4855
+ "epoch": 0.800836820083682,
4856
+ "grad_norm": 6.236753940582275,
4857
+ "learning_rate": 2.3083094097196766e-06,
4858
+ "loss": 0.3236,
4859
+ "step": 638
4860
+ },
4861
+ {
4862
+ "epoch": 0.802092050209205,
4863
+ "grad_norm": 3.9249565601348877,
4864
+ "learning_rate": 2.280344151495799e-06,
4865
+ "loss": 0.1873,
4866
+ "step": 639
4867
+ },
4868
+ {
4869
+ "epoch": 0.803347280334728,
4870
+ "grad_norm": 5.489711284637451,
4871
+ "learning_rate": 2.252527511111381e-06,
4872
+ "loss": 0.2972,
4873
+ "step": 640
4874
+ },
4875
+ {
4876
+ "epoch": 0.803347280334728,
4877
+ "eval_accuracy": 0.8609271523178808,
4878
+ "eval_f1": 0.7149321266968326,
4879
+ "eval_loss": 0.2890259623527527,
4880
+ "eval_precision": 0.8404255319148937,
4881
+ "eval_recall": 0.6220472440944882,
4882
+ "eval_runtime": 52.9255,
4883
+ "eval_samples_per_second": 5.234,
4884
+ "eval_steps_per_second": 0.17,
4885
+ "step": 640
4886
+ },
4887
+ {
4888
+ "epoch": 0.804602510460251,
4889
+ "grad_norm": 4.235107421875,
4890
+ "learning_rate": 2.224860024088863e-06,
4891
+ "loss": 0.2522,
4892
+ "step": 641
4893
+ },
4894
+ {
4895
+ "epoch": 0.8058577405857741,
4896
+ "grad_norm": 5.042692184448242,
4897
+ "learning_rate": 2.197342223079212e-06,
4898
+ "loss": 0.2259,
4899
+ "step": 642
4900
+ },
4901
+ {
4902
+ "epoch": 0.8071129707112971,
4903
+ "grad_norm": 6.554571628570557,
4904
+ "learning_rate": 2.1699746378516618e-06,
4905
+ "loss": 0.3102,
4906
+ "step": 643
4907
+ },
4908
+ {
4909
+ "epoch": 0.80836820083682,
4910
+ "grad_norm": 5.590906143188477,
4911
+ "learning_rate": 2.1427577952835044e-06,
4912
+ "loss": 0.242,
4913
+ "step": 644
4914
+ },
4915
+ {
4916
+ "epoch": 0.8096234309623431,
4917
+ "grad_norm": 3.1682546138763428,
4918
+ "learning_rate": 2.1156922193499573e-06,
4919
+ "loss": 0.2016,
4920
+ "step": 645
4921
+ },
4922
+ {
4923
+ "epoch": 0.8108786610878661,
4924
+ "grad_norm": 5.03267765045166,
4925
+ "learning_rate": 2.088778431114068e-06,
4926
+ "loss": 0.3032,
4927
+ "step": 646
4928
+ },
4929
+ {
4930
+ "epoch": 0.8121338912133891,
4931
+ "grad_norm": 5.085690498352051,
4932
+ "learning_rate": 2.06201694871669e-06,
4933
+ "loss": 0.2572,
4934
+ "step": 647
4935
+ },
4936
+ {
4937
+ "epoch": 0.8133891213389122,
4938
+ "grad_norm": 6.410571098327637,
4939
+ "learning_rate": 2.0354082873665015e-06,
4940
+ "loss": 0.2776,
4941
+ "step": 648
4942
+ },
4943
+ {
4944
+ "epoch": 0.8146443514644351,
4945
+ "grad_norm": 2.672776699066162,
4946
+ "learning_rate": 2.0089529593300916e-06,
4947
+ "loss": 0.1729,
4948
+ "step": 649
4949
+ },
4950
+ {
4951
+ "epoch": 0.8158995815899581,
4952
+ "grad_norm": 4.959750175476074,
4953
+ "learning_rate": 1.9826514739220946e-06,
4954
+ "loss": 0.2254,
4955
+ "step": 650
4956
+ },
4957
+ {
4958
+ "epoch": 0.8171548117154812,
4959
+ "grad_norm": 4.0036725997924805,
4960
+ "learning_rate": 1.956504337495384e-06,
4961
+ "loss": 0.1674,
4962
+ "step": 651
4963
+ },
4964
+ {
4965
+ "epoch": 0.8184100418410042,
4966
+ "grad_norm": 4.883665561676025,
4967
+ "learning_rate": 1.9305120534313295e-06,
4968
+ "loss": 0.1647,
4969
+ "step": 652
4970
+ },
4971
+ {
4972
+ "epoch": 0.8196652719665272,
4973
+ "grad_norm": 5.845210075378418,
4974
+ "learning_rate": 1.9046751221301018e-06,
4975
+ "loss": 0.3202,
4976
+ "step": 653
4977
+ },
4978
+ {
4979
+ "epoch": 0.8209205020920503,
4980
+ "grad_norm": 5.12738037109375,
4981
+ "learning_rate": 1.8789940410010355e-06,
4982
+ "loss": 0.1829,
4983
+ "step": 654
4984
+ },
4985
+ {
4986
+ "epoch": 0.8221757322175732,
4987
+ "grad_norm": 3.904860019683838,
4988
+ "learning_rate": 1.853469304453066e-06,
4989
+ "loss": 0.2275,
4990
+ "step": 655
4991
+ },
4992
+ {
4993
+ "epoch": 0.8234309623430962,
4994
+ "grad_norm": 4.157991409301758,
4995
+ "learning_rate": 1.8281014038851963e-06,
4996
+ "loss": 0.2335,
4997
+ "step": 656
4998
+ },
4999
+ {
5000
+ "epoch": 0.8246861924686193,
5001
+ "grad_norm": 6.301884651184082,
5002
+ "learning_rate": 1.802890827677045e-06,
5003
+ "loss": 0.265,
5004
+ "step": 657
5005
+ },
5006
+ {
5007
+ "epoch": 0.8259414225941423,
5008
+ "grad_norm": 4.426259994506836,
5009
+ "learning_rate": 1.777838061179442e-06,
5010
+ "loss": 0.2346,
5011
+ "step": 658
5012
+ },
5013
+ {
5014
+ "epoch": 0.8271966527196652,
5015
+ "grad_norm": 3.300267457962036,
5016
+ "learning_rate": 1.7529435867050771e-06,
5017
+ "loss": 0.2312,
5018
+ "step": 659
5019
+ },
5020
+ {
5021
+ "epoch": 0.8284518828451883,
5022
+ "grad_norm": 3.5169765949249268,
5023
+ "learning_rate": 1.7282078835192362e-06,
5024
+ "loss": 0.1953,
5025
+ "step": 660
5026
+ },
5027
+ {
5028
+ "epoch": 0.8284518828451883,
5029
+ "eval_accuracy": 0.8609271523178808,
5030
+ "eval_f1": 0.7136363636363636,
5031
+ "eval_loss": 0.2910914123058319,
5032
+ "eval_precision": 0.8440860215053764,
5033
+ "eval_recall": 0.6181102362204725,
5034
+ "eval_runtime": 52.6057,
5035
+ "eval_samples_per_second": 5.266,
5036
+ "eval_steps_per_second": 0.171,
5037
+ "step": 660
5038
+ },
5039
+ {
5040
+ "epoch": 0.8297071129707113,
5041
+ "grad_norm": 3.4855308532714844,
5042
+ "learning_rate": 1.703631427830551e-06,
5043
+ "loss": 0.2036,
5044
+ "step": 661
5045
+ },
5046
+ {
5047
+ "epoch": 0.8309623430962343,
5048
+ "grad_norm": 4.0676493644714355,
5049
+ "learning_rate": 1.679214692781842e-06,
5050
+ "loss": 0.2412,
5051
+ "step": 662
5052
+ },
5053
+ {
5054
+ "epoch": 0.8322175732217573,
5055
+ "grad_norm": 4.750482559204102,
5056
+ "learning_rate": 1.6549581484410105e-06,
5057
+ "loss": 0.2193,
5058
+ "step": 663
5059
+ },
5060
+ {
5061
+ "epoch": 0.8334728033472804,
5062
+ "grad_norm": 7.349670886993408,
5063
+ "learning_rate": 1.6308622617919823e-06,
5064
+ "loss": 0.2712,
5065
+ "step": 664
5066
+ },
5067
+ {
5068
+ "epoch": 0.8347280334728033,
5069
+ "grad_norm": 3.89208984375,
5070
+ "learning_rate": 1.606927496725722e-06,
5071
+ "loss": 0.2761,
5072
+ "step": 665
5073
+ },
5074
+ {
5075
+ "epoch": 0.8359832635983263,
5076
+ "grad_norm": 3.2538020610809326,
5077
+ "learning_rate": 1.583154314031311e-06,
5078
+ "loss": 0.1974,
5079
+ "step": 666
5080
+ },
5081
+ {
5082
+ "epoch": 0.8372384937238494,
5083
+ "grad_norm": 4.290145397186279,
5084
+ "learning_rate": 1.5595431713870569e-06,
5085
+ "loss": 0.2562,
5086
+ "step": 667
5087
+ },
5088
+ {
5089
+ "epoch": 0.8384937238493724,
5090
+ "grad_norm": 5.561316013336182,
5091
+ "learning_rate": 1.5360945233516933e-06,
5092
+ "loss": 0.2707,
5093
+ "step": 668
5094
+ },
5095
+ {
5096
+ "epoch": 0.8397489539748954,
5097
+ "grad_norm": 4.019890308380127,
5098
+ "learning_rate": 1.5128088213556324e-06,
5099
+ "loss": 0.1786,
5100
+ "step": 669
5101
+ },
5102
+ {
5103
+ "epoch": 0.8410041841004184,
5104
+ "grad_norm": 4.0204758644104,
5105
+ "learning_rate": 1.489686513692269e-06,
5106
+ "loss": 0.2377,
5107
+ "step": 670
5108
+ },
5109
+ {
5110
+ "epoch": 0.8422594142259414,
5111
+ "grad_norm": 4.556098461151123,
5112
+ "learning_rate": 1.4667280455093468e-06,
5113
+ "loss": 0.2138,
5114
+ "step": 671
5115
+ },
5116
+ {
5117
+ "epoch": 0.8435146443514644,
5118
+ "grad_norm": 5.089337348937988,
5119
+ "learning_rate": 1.4439338588004005e-06,
5120
+ "loss": 0.2272,
5121
+ "step": 672
5122
+ },
5123
+ {
5124
+ "epoch": 0.8447698744769875,
5125
+ "grad_norm": 4.120019435882568,
5126
+ "learning_rate": 1.4213043923962322e-06,
5127
+ "loss": 0.2104,
5128
+ "step": 673
5129
+ },
5130
+ {
5131
+ "epoch": 0.8460251046025105,
5132
+ "grad_norm": 3.5715548992156982,
5133
+ "learning_rate": 1.3988400819564707e-06,
5134
+ "loss": 0.2013,
5135
+ "step": 674
5136
+ },
5137
+ {
5138
+ "epoch": 0.8472803347280334,
5139
+ "grad_norm": 4.313863277435303,
5140
+ "learning_rate": 1.3765413599611832e-06,
5141
+ "loss": 0.2265,
5142
+ "step": 675
5143
+ },
5144
+ {
5145
+ "epoch": 0.8485355648535565,
5146
+ "grad_norm": 5.553587436676025,
5147
+ "learning_rate": 1.3544086557025493e-06,
5148
+ "loss": 0.2667,
5149
+ "step": 676
5150
+ },
5151
+ {
5152
+ "epoch": 0.8497907949790795,
5153
+ "grad_norm": 4.209076404571533,
5154
+ "learning_rate": 1.3324423952765974e-06,
5155
+ "loss": 0.2375,
5156
+ "step": 677
5157
+ },
5158
+ {
5159
+ "epoch": 0.8510460251046025,
5160
+ "grad_norm": 4.849112033843994,
5161
+ "learning_rate": 1.3106430015749971e-06,
5162
+ "loss": 0.2268,
5163
+ "step": 678
5164
+ },
5165
+ {
5166
+ "epoch": 0.8523012552301256,
5167
+ "grad_norm": 4.489964485168457,
5168
+ "learning_rate": 1.2890108942769253e-06,
5169
+ "loss": 0.1934,
5170
+ "step": 679
5171
+ },
5172
+ {
5173
+ "epoch": 0.8535564853556485,
5174
+ "grad_norm": 3.962709665298462,
5175
+ "learning_rate": 1.2675464898409772e-06,
5176
+ "loss": 0.24,
5177
+ "step": 680
5178
+ },
5179
+ {
5180
+ "epoch": 0.8535564853556485,
5181
+ "eval_accuracy": 0.8653421633554084,
5182
+ "eval_f1": 0.7288888888888889,
5183
+ "eval_loss": 0.28242796659469604,
5184
+ "eval_precision": 0.8367346938775511,
5185
+ "eval_recall": 0.6456692913385826,
5186
+ "eval_runtime": 53.7633,
5187
+ "eval_samples_per_second": 5.152,
5188
+ "eval_steps_per_second": 0.167,
5189
+ "step": 680
5190
+ },
5191
+ {
5192
+ "epoch": 0.8548117154811715,
5193
+ "grad_norm": 4.079026699066162,
5194
+ "learning_rate": 1.2462502014971579e-06,
5195
+ "loss": 0.2389,
5196
+ "step": 681
5197
+ },
5198
+ {
5199
+ "epoch": 0.8560669456066946,
5200
+ "grad_norm": 5.030835151672363,
5201
+ "learning_rate": 1.2251224392389183e-06,
5202
+ "loss": 0.296,
5203
+ "step": 682
5204
+ },
5205
+ {
5206
+ "epoch": 0.8573221757322176,
5207
+ "grad_norm": 4.880098819732666,
5208
+ "learning_rate": 1.2041636098152742e-06,
5209
+ "loss": 0.2687,
5210
+ "step": 683
5211
+ },
5212
+ {
5213
+ "epoch": 0.8585774058577406,
5214
+ "grad_norm": 3.222585439682007,
5215
+ "learning_rate": 1.1833741167229584e-06,
5216
+ "loss": 0.2378,
5217
+ "step": 684
5218
+ },
5219
+ {
5220
+ "epoch": 0.8598326359832636,
5221
+ "grad_norm": 4.026751518249512,
5222
+ "learning_rate": 1.1627543601986702e-06,
5223
+ "loss": 0.1571,
5224
+ "step": 685
5225
+ },
5226
+ {
5227
+ "epoch": 0.8610878661087866,
5228
+ "grad_norm": 4.304843902587891,
5229
+ "learning_rate": 1.1423047372113538e-06,
5230
+ "loss": 0.2836,
5231
+ "step": 686
5232
+ },
5233
+ {
5234
+ "epoch": 0.8623430962343096,
5235
+ "grad_norm": 4.018265247344971,
5236
+ "learning_rate": 1.1220256414545682e-06,
5237
+ "loss": 0.2154,
5238
+ "step": 687
5239
+ },
5240
+ {
5241
+ "epoch": 0.8635983263598327,
5242
+ "grad_norm": 5.214784622192383,
5243
+ "learning_rate": 1.1019174633389073e-06,
5244
+ "loss": 0.235,
5245
+ "step": 688
5246
+ },
5247
+ {
5248
+ "epoch": 0.8648535564853557,
5249
+ "grad_norm": 3.2286956310272217,
5250
+ "learning_rate": 1.0819805899844748e-06,
5251
+ "loss": 0.1933,
5252
+ "step": 689
5253
+ },
5254
+ {
5255
+ "epoch": 0.8661087866108786,
5256
+ "grad_norm": 4.96722936630249,
5257
+ "learning_rate": 1.0622154052134392e-06,
5258
+ "loss": 0.2189,
5259
+ "step": 690
5260
+ },
5261
+ {
5262
+ "epoch": 0.8673640167364016,
5263
+ "grad_norm": 5.077961444854736,
5264
+ "learning_rate": 1.042622289542642e-06,
5265
+ "loss": 0.1864,
5266
+ "step": 691
5267
+ },
5268
+ {
5269
+ "epoch": 0.8686192468619247,
5270
+ "grad_norm": 4.23472785949707,
5271
+ "learning_rate": 1.0232016201762696e-06,
5272
+ "loss": 0.286,
5273
+ "step": 692
5274
+ },
5275
+ {
5276
+ "epoch": 0.8698744769874477,
5277
+ "grad_norm": 4.877628803253174,
5278
+ "learning_rate": 1.0039537709985968e-06,
5279
+ "loss": 0.23,
5280
+ "step": 693
5281
+ },
5282
+ {
5283
+ "epoch": 0.8711297071129707,
5284
+ "grad_norm": 5.60928201675415,
5285
+ "learning_rate": 9.848791125667867e-07,
5286
+ "loss": 0.2311,
5287
+ "step": 694
5288
+ },
5289
+ {
5290
+ "epoch": 0.8723849372384938,
5291
+ "grad_norm": 4.585776329040527,
5292
+ "learning_rate": 9.659780121037533e-07,
5293
+ "loss": 0.2079,
5294
+ "step": 695
5295
+ },
5296
+ {
5297
+ "epoch": 0.8736401673640167,
5298
+ "grad_norm": 4.836354732513428,
5299
+ "learning_rate": 9.472508334910946e-07,
5300
+ "loss": 0.1449,
5301
+ "step": 696
5302
+ },
5303
+ {
5304
+ "epoch": 0.8748953974895397,
5305
+ "grad_norm": 6.011707782745361,
5306
+ "learning_rate": 9.286979372620885e-07,
5307
+ "loss": 0.2135,
5308
+ "step": 697
5309
+ },
5310
+ {
5311
+ "epoch": 0.8761506276150628,
5312
+ "grad_norm": 5.969391822814941,
5313
+ "learning_rate": 9.103196805947522e-07,
5314
+ "loss": 0.2964,
5315
+ "step": 698
5316
+ },
5317
+ {
5318
+ "epoch": 0.8774058577405858,
5319
+ "grad_norm": 5.757129192352295,
5320
+ "learning_rate": 8.92116417304958e-07,
5321
+ "loss": 0.2444,
5322
+ "step": 699
5323
+ },
5324
+ {
5325
+ "epoch": 0.8786610878661087,
5326
+ "grad_norm": 4.445234298706055,
5327
+ "learning_rate": 8.740884978396358e-07,
5328
+ "loss": 0.282,
5329
+ "step": 700
5330
+ },
5331
+ {
5332
+ "epoch": 0.8786610878661087,
5333
+ "eval_accuracy": 0.8631346578366446,
5334
+ "eval_f1": 0.7219730941704036,
5335
+ "eval_loss": 0.2860436737537384,
5336
+ "eval_precision": 0.8385416666666666,
5337
+ "eval_recall": 0.6338582677165354,
5338
+ "eval_runtime": 51.8577,
5339
+ "eval_samples_per_second": 5.342,
5340
+ "eval_steps_per_second": 0.174,
5341
+ "step": 700
5342
  }
5343
  ],
5344
  "logging_steps": 1,
 
5358
  "attributes": {}
5359
  }
5360
  },
5361
+ "total_flos": 2.5677470361033114e+17,
5362
  "train_batch_size": 6,
5363
  "trial_name": null,
5364
  "trial_params": null