mtzig commited on
Commit
cff83ff
·
verified ·
1 Parent(s): 2010cfc

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:e288bd840a16b2cbd8a3374bb949f1b1c187199eea64768875535052f81db099
3
  size 13934748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d6658706a2b1b22d02af67ed32e150daada045c6218fcbac8d61cdee6f387a
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 sha256:1d8f724ed2ba62d4ed4f7f457305a29c044fc92263fb4ca9b09038183d31aeaa
3
  size 13999412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a53a5f077427c1fb6c1be3beda662bcb3c55295e52e5aac6cdd521540645e78
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 sha256:62907865f8c9b9de147161436fec23e0a0a3205b827d496be6b915e2f6a61637
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4033bcd984ed883ee9f4753f5acd2a5f9698c3b391651526fe5836282d38a7
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:c32753acec9af4565f58dbc31cec7c0c6bc9ef2e62b6854c21d933b731258ac2
3
  size 13990904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abd615b881caa9b6b112faf16e7d3d92e8f14de7b312bdedd386f878060361e
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 sha256:697053a12f78e9cd0517de1cabfa72a579559630e95ed1aa433ad67c5646389b
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd4ac688667fed33dbac29dd54010210058743290dae20597420324bc4b12d61
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 sha256:48bcd48af5b6cfa380c1c36060fcb58077075241d5dca14ab2ed7b8d81477c9b
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c4e28b7b6c76dc1bee240fa0bb1bfba0d8ccb93833317aef937e1c66e8e56
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:f382917805c0880ea5c586f02898986f046f45ead5dbd892ad525b7d8a5b4e1a
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bc8d6adc4a8ca28639d5097e8d755b737723c2a73e02a639554d412e2af015c
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:b4597256259e5a2c7c475191a3bdd74624e158798e72d836b1a2749f70fc6048
3
  size 6966784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7adf139cb5be3fa94f558d2253b67614e8f5e40c792e0a5458dcecd0d865b5
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 sha256:855ee2eea26db19a2bc9cc5b04dadff41206d82e1c5a1fe77da238da76633816
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8846b74d96cda2078cccff557518227c163d02a7e2b4a593daa2acbfe4642d
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:b19f290e2b6e7e30a354c9cdd1a942b44ba05b3b706c4041390f3cbee2d59585
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075424ce87fff9c2e036af3f101cf627348425b5ff8402b4a0c190100ea3ad91
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 sha256:2828273a1308e661da21192f060469695aabbaeacbfc6389f33e773de694bc21
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ac8d82137e7b493f65b02fe60e742d00785831acde45a3e931ec88619a5dca
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 sha256:0185f9ac53f07ec0947948711d4dd961bdf47d4defc863468138a808e26e54b5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd75e3ece083256eebd1a793ba9c4d81a6d9e08a128d64453489d62e892f1f6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26db028a9049ea67225987ee1ccc2be42e4ecb5abdde128157d8fe80504b4a15
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7b277ba7269f25114908097aae9c5e108d3ce5eac98d48cc795839db8493c9
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": 0.7610993657505285,
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": 5.296,
4580
  "eval_steps_per_second": 0.172,
4581
  "step": 600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4582
  }
4583
  ],
4584
  "logging_steps": 1,
@@ -4598,7 +5358,7 @@
4598
  "attributes": {}
4599
  }
4600
  },
4601
- "total_flos": 2.2467637165634355e+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": 0.8879492600422833,
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": 5.296,
4580
  "eval_steps_per_second": 0.172,
4581
  "step": 600
4582
+ },
4583
+ {
4584
+ "epoch": 0.7623678646934461,
4585
+ "grad_norm": 3.266761064529419,
4586
+ "learning_rate": 3.2409224077012135e-06,
4587
+ "loss": 0.1771,
4588
+ "step": 601
4589
+ },
4590
+ {
4591
+ "epoch": 0.7636363636363637,
4592
+ "grad_norm": 4.591704368591309,
4593
+ "learning_rate": 3.2083328663766466e-06,
4594
+ "loss": 0.241,
4595
+ "step": 602
4596
+ },
4597
+ {
4598
+ "epoch": 0.7649048625792811,
4599
+ "grad_norm": 4.731637954711914,
4600
+ "learning_rate": 3.175876671962266e-06,
4601
+ "loss": 0.2559,
4602
+ "step": 603
4603
+ },
4604
+ {
4605
+ "epoch": 0.7661733615221987,
4606
+ "grad_norm": 9.054510116577148,
4607
+ "learning_rate": 3.1435544616997303e-06,
4608
+ "loss": 0.2459,
4609
+ "step": 604
4610
+ },
4611
+ {
4612
+ "epoch": 0.7674418604651163,
4613
+ "grad_norm": 5.0422821044921875,
4614
+ "learning_rate": 3.111366870200071e-06,
4615
+ "loss": 0.1812,
4616
+ "step": 605
4617
+ },
4618
+ {
4619
+ "epoch": 0.7687103594080338,
4620
+ "grad_norm": 5.838403701782227,
4621
+ "learning_rate": 3.0793145294312253e-06,
4622
+ "loss": 0.2237,
4623
+ "step": 606
4624
+ },
4625
+ {
4626
+ "epoch": 0.7699788583509514,
4627
+ "grad_norm": 3.5189685821533203,
4628
+ "learning_rate": 3.0473980687056314e-06,
4629
+ "loss": 0.1696,
4630
+ "step": 607
4631
+ },
4632
+ {
4633
+ "epoch": 0.771247357293869,
4634
+ "grad_norm": 3.204148530960083,
4635
+ "learning_rate": 3.015618114667873e-06,
4636
+ "loss": 0.1476,
4637
+ "step": 608
4638
+ },
4639
+ {
4640
+ "epoch": 0.7725158562367864,
4641
+ "grad_norm": 5.796388149261475,
4642
+ "learning_rate": 2.983975291282375e-06,
4643
+ "loss": 0.1914,
4644
+ "step": 609
4645
+ },
4646
+ {
4647
+ "epoch": 0.773784355179704,
4648
+ "grad_norm": 4.04534912109375,
4649
+ "learning_rate": 2.952470219821152e-06,
4650
+ "loss": 0.2216,
4651
+ "step": 610
4652
+ },
4653
+ {
4654
+ "epoch": 0.7750528541226216,
4655
+ "grad_norm": 3.9704835414886475,
4656
+ "learning_rate": 2.921103518851609e-06,
4657
+ "loss": 0.2576,
4658
+ "step": 611
4659
+ },
4660
+ {
4661
+ "epoch": 0.7763213530655391,
4662
+ "grad_norm": 3.9379115104675293,
4663
+ "learning_rate": 2.889875804224409e-06,
4664
+ "loss": 0.2255,
4665
+ "step": 612
4666
+ },
4667
+ {
4668
+ "epoch": 0.7775898520084567,
4669
+ "grad_norm": 4.200435161590576,
4670
+ "learning_rate": 2.8587876890613597e-06,
4671
+ "loss": 0.2399,
4672
+ "step": 613
4673
+ },
4674
+ {
4675
+ "epoch": 0.7788583509513742,
4676
+ "grad_norm": 3.6293070316314697,
4677
+ "learning_rate": 2.827839783743391e-06,
4678
+ "loss": 0.2346,
4679
+ "step": 614
4680
+ },
4681
+ {
4682
+ "epoch": 0.7801268498942917,
4683
+ "grad_norm": 4.450516700744629,
4684
+ "learning_rate": 2.7970326958985683e-06,
4685
+ "loss": 0.2134,
4686
+ "step": 615
4687
+ },
4688
+ {
4689
+ "epoch": 0.7813953488372093,
4690
+ "grad_norm": 3.8171873092651367,
4691
+ "learning_rate": 2.766367030390157e-06,
4692
+ "loss": 0.1628,
4693
+ "step": 616
4694
+ },
4695
+ {
4696
+ "epoch": 0.7826638477801269,
4697
+ "grad_norm": 4.238905906677246,
4698
+ "learning_rate": 2.7358433893047543e-06,
4699
+ "loss": 0.2054,
4700
+ "step": 617
4701
+ },
4702
+ {
4703
+ "epoch": 0.7839323467230443,
4704
+ "grad_norm": 3.8484349250793457,
4705
+ "learning_rate": 2.7054623719404617e-06,
4706
+ "loss": 0.1907,
4707
+ "step": 618
4708
+ },
4709
+ {
4710
+ "epoch": 0.7852008456659619,
4711
+ "grad_norm": 4.630876541137695,
4712
+ "learning_rate": 2.675224574795123e-06,
4713
+ "loss": 0.2193,
4714
+ "step": 619
4715
+ },
4716
+ {
4717
+ "epoch": 0.7864693446088795,
4718
+ "grad_norm": 5.129254341125488,
4719
+ "learning_rate": 2.645130591554609e-06,
4720
+ "loss": 0.2107,
4721
+ "step": 620
4722
+ },
4723
+ {
4724
+ "epoch": 0.7864693446088795,
4725
+ "eval_accuracy": 0.8642384105960265,
4726
+ "eval_f1": 0.7146171693735499,
4727
+ "eval_loss": 0.2954389750957489,
4728
+ "eval_precision": 0.8700564971751412,
4729
+ "eval_recall": 0.6062992125984252,
4730
+ "eval_runtime": 51.5152,
4731
+ "eval_samples_per_second": 5.377,
4732
+ "eval_steps_per_second": 0.175,
4733
+ "step": 620
4734
+ },
4735
+ {
4736
+ "epoch": 0.787737843551797,
4737
+ "grad_norm": 4.9152750968933105,
4738
+ "learning_rate": 2.615181013081164e-06,
4739
+ "loss": 0.1496,
4740
+ "step": 621
4741
+ },
4742
+ {
4743
+ "epoch": 0.7890063424947146,
4744
+ "grad_norm": 4.203990459442139,
4745
+ "learning_rate": 2.5853764274018024e-06,
4746
+ "loss": 0.1628,
4747
+ "step": 622
4748
+ },
4749
+ {
4750
+ "epoch": 0.7902748414376322,
4751
+ "grad_norm": 4.1775641441345215,
4752
+ "learning_rate": 2.555717419696764e-06,
4753
+ "loss": 0.1943,
4754
+ "step": 623
4755
+ },
4756
+ {
4757
+ "epoch": 0.7915433403805496,
4758
+ "grad_norm": 3.536635398864746,
4759
+ "learning_rate": 2.526204572288029e-06,
4760
+ "loss": 0.1927,
4761
+ "step": 624
4762
+ },
4763
+ {
4764
+ "epoch": 0.7928118393234672,
4765
+ "grad_norm": 3.426269769668579,
4766
+ "learning_rate": 2.4968384646278765e-06,
4767
+ "loss": 0.202,
4768
+ "step": 625
4769
+ },
4770
+ {
4771
+ "epoch": 0.7940803382663848,
4772
+ "grad_norm": 7.433694362640381,
4773
+ "learning_rate": 2.4676196732875147e-06,
4774
+ "loss": 0.2374,
4775
+ "step": 626
4776
+ },
4777
+ {
4778
+ "epoch": 0.7953488372093023,
4779
+ "grad_norm": 4.034791946411133,
4780
+ "learning_rate": 2.4385487719457568e-06,
4781
+ "loss": 0.2249,
4782
+ "step": 627
4783
+ },
4784
+ {
4785
+ "epoch": 0.7966173361522199,
4786
+ "grad_norm": 4.299747467041016,
4787
+ "learning_rate": 2.4096263313777603e-06,
4788
+ "loss": 0.1816,
4789
+ "step": 628
4790
+ },
4791
+ {
4792
+ "epoch": 0.7978858350951374,
4793
+ "grad_norm": 5.804561614990234,
4794
+ "learning_rate": 2.3808529194438156e-06,
4795
+ "loss": 0.3159,
4796
+ "step": 629
4797
+ },
4798
+ {
4799
+ "epoch": 0.7991543340380549,
4800
+ "grad_norm": 4.759912014007568,
4801
+ "learning_rate": 2.352229101078205e-06,
4802
+ "loss": 0.2168,
4803
+ "step": 630
4804
+ },
4805
+ {
4806
+ "epoch": 0.8004228329809725,
4807
+ "grad_norm": 4.604716777801514,
4808
+ "learning_rate": 2.3237554382781004e-06,
4809
+ "loss": 0.2306,
4810
+ "step": 631
4811
+ },
4812
+ {
4813
+ "epoch": 0.8016913319238901,
4814
+ "grad_norm": 4.394404411315918,
4815
+ "learning_rate": 2.2954324900925362e-06,
4816
+ "loss": 0.226,
4817
+ "step": 632
4818
+ },
4819
+ {
4820
+ "epoch": 0.8029598308668076,
4821
+ "grad_norm": 4.407333850860596,
4822
+ "learning_rate": 2.2672608126114337e-06,
4823
+ "loss": 0.2125,
4824
+ "step": 633
4825
+ },
4826
+ {
4827
+ "epoch": 0.8042283298097251,
4828
+ "grad_norm": 4.021424770355225,
4829
+ "learning_rate": 2.239240958954677e-06,
4830
+ "loss": 0.1941,
4831
+ "step": 634
4832
+ },
4833
+ {
4834
+ "epoch": 0.8054968287526427,
4835
+ "grad_norm": 5.0576066970825195,
4836
+ "learning_rate": 2.2113734792612586e-06,
4837
+ "loss": 0.1864,
4838
+ "step": 635
4839
+ },
4840
+ {
4841
+ "epoch": 0.8067653276955603,
4842
+ "grad_norm": 5.43579626083374,
4843
+ "learning_rate": 2.1836589206784742e-06,
4844
+ "loss": 0.2176,
4845
+ "step": 636
4846
+ },
4847
+ {
4848
+ "epoch": 0.8080338266384778,
4849
+ "grad_norm": 4.382997035980225,
4850
+ "learning_rate": 2.15609782735118e-06,
4851
+ "loss": 0.1978,
4852
+ "step": 637
4853
+ },
4854
+ {
4855
+ "epoch": 0.8093023255813954,
4856
+ "grad_norm": 3.2525434494018555,
4857
+ "learning_rate": 2.12869074041112e-06,
4858
+ "loss": 0.1882,
4859
+ "step": 638
4860
+ },
4861
+ {
4862
+ "epoch": 0.810570824524313,
4863
+ "grad_norm": 4.6330790519714355,
4864
+ "learning_rate": 2.1014381979662823e-06,
4865
+ "loss": 0.2146,
4866
+ "step": 639
4867
+ },
4868
+ {
4869
+ "epoch": 0.8118393234672304,
4870
+ "grad_norm": 4.439876079559326,
4871
+ "learning_rate": 2.0743407350903465e-06,
4872
+ "loss": 0.2562,
4873
+ "step": 640
4874
+ },
4875
+ {
4876
+ "epoch": 0.8118393234672304,
4877
+ "eval_accuracy": 0.8642384105960265,
4878
+ "eval_f1": 0.7210884353741497,
4879
+ "eval_loss": 0.293789803981781,
4880
+ "eval_precision": 0.8502673796791443,
4881
+ "eval_recall": 0.6259842519685039,
4882
+ "eval_runtime": 51.7868,
4883
+ "eval_samples_per_second": 5.349,
4884
+ "eval_steps_per_second": 0.174,
4885
+ "step": 640
4886
+ },
4887
+ {
4888
+ "epoch": 0.813107822410148,
4889
+ "grad_norm": 3.350806713104248,
4890
+ "learning_rate": 2.0473988838121783e-06,
4891
+ "loss": 0.1801,
4892
+ "step": 641
4893
+ },
4894
+ {
4895
+ "epoch": 0.8143763213530656,
4896
+ "grad_norm": 3.780141592025757,
4897
+ "learning_rate": 2.020613173105379e-06,
4898
+ "loss": 0.1665,
4899
+ "step": 642
4900
+ },
4901
+ {
4902
+ "epoch": 0.8156448202959831,
4903
+ "grad_norm": 3.851416826248169,
4904
+ "learning_rate": 1.9939841288778996e-06,
4905
+ "loss": 0.1559,
4906
+ "step": 643
4907
+ },
4908
+ {
4909
+ "epoch": 0.8169133192389006,
4910
+ "grad_norm": 3.916234254837036,
4911
+ "learning_rate": 1.96751227396172e-06,
4912
+ "loss": 0.2272,
4913
+ "step": 644
4914
+ },
4915
+ {
4916
+ "epoch": 0.8181818181818182,
4917
+ "grad_norm": 4.235809326171875,
4918
+ "learning_rate": 1.9411981281025818e-06,
4919
+ "loss": 0.2591,
4920
+ "step": 645
4921
+ },
4922
+ {
4923
+ "epoch": 0.8194503171247357,
4924
+ "grad_norm": 3.97944974899292,
4925
+ "learning_rate": 1.9150422079497787e-06,
4926
+ "loss": 0.1772,
4927
+ "step": 646
4928
+ },
4929
+ {
4930
+ "epoch": 0.8207188160676533,
4931
+ "grad_norm": 3.336775064468384,
4932
+ "learning_rate": 1.8890450270460204e-06,
4933
+ "loss": 0.1648,
4934
+ "step": 647
4935
+ },
4936
+ {
4937
+ "epoch": 0.8219873150105709,
4938
+ "grad_norm": 3.8211421966552734,
4939
+ "learning_rate": 1.8632070958173453e-06,
4940
+ "loss": 0.1483,
4941
+ "step": 648
4942
+ },
4943
+ {
4944
+ "epoch": 0.8232558139534883,
4945
+ "grad_norm": 4.630310535430908,
4946
+ "learning_rate": 1.8375289215630998e-06,
4947
+ "loss": 0.232,
4948
+ "step": 649
4949
+ },
4950
+ {
4951
+ "epoch": 0.8245243128964059,
4952
+ "grad_norm": 3.9007372856140137,
4953
+ "learning_rate": 1.8120110084459763e-06,
4954
+ "loss": 0.2163,
4955
+ "step": 650
4956
+ },
4957
+ {
4958
+ "epoch": 0.8257928118393235,
4959
+ "grad_norm": 4.006324291229248,
4960
+ "learning_rate": 1.786653857482118e-06,
4961
+ "loss": 0.2104,
4962
+ "step": 651
4963
+ },
4964
+ {
4965
+ "epoch": 0.827061310782241,
4966
+ "grad_norm": 4.888721942901611,
4967
+ "learning_rate": 1.7614579665312792e-06,
4968
+ "loss": 0.2257,
4969
+ "step": 652
4970
+ },
4971
+ {
4972
+ "epoch": 0.8283298097251586,
4973
+ "grad_norm": 5.345705032348633,
4974
+ "learning_rate": 1.7364238302870517e-06,
4975
+ "loss": 0.2251,
4976
+ "step": 653
4977
+ },
4978
+ {
4979
+ "epoch": 0.8295983086680762,
4980
+ "grad_norm": 3.589813709259033,
4981
+ "learning_rate": 1.711551940267151e-06,
4982
+ "loss": 0.1877,
4983
+ "step": 654
4984
+ },
4985
+ {
4986
+ "epoch": 0.8308668076109936,
4987
+ "grad_norm": 5.65714168548584,
4988
+ "learning_rate": 1.6868427848037672e-06,
4989
+ "loss": 0.2736,
4990
+ "step": 655
4991
+ },
4992
+ {
4993
+ "epoch": 0.8321353065539112,
4994
+ "grad_norm": 5.815731048583984,
4995
+ "learning_rate": 1.6622968490339775e-06,
4996
+ "loss": 0.2564,
4997
+ "step": 656
4998
+ },
4999
+ {
5000
+ "epoch": 0.8334038054968288,
5001
+ "grad_norm": 3.979933738708496,
5002
+ "learning_rate": 1.637914614890217e-06,
5003
+ "loss": 0.1795,
5004
+ "step": 657
5005
+ },
5006
+ {
5007
+ "epoch": 0.8346723044397463,
5008
+ "grad_norm": 4.708816051483154,
5009
+ "learning_rate": 1.613696561090823e-06,
5010
+ "loss": 0.2817,
5011
+ "step": 658
5012
+ },
5013
+ {
5014
+ "epoch": 0.8359408033826639,
5015
+ "grad_norm": 4.505849838256836,
5016
+ "learning_rate": 1.5896431631306298e-06,
5017
+ "loss": 0.2302,
5018
+ "step": 659
5019
+ },
5020
+ {
5021
+ "epoch": 0.8372093023255814,
5022
+ "grad_norm": 4.055660247802734,
5023
+ "learning_rate": 1.565754893271636e-06,
5024
+ "loss": 0.1054,
5025
+ "step": 660
5026
+ },
5027
+ {
5028
+ "epoch": 0.8372093023255814,
5029
+ "eval_accuracy": 0.8642384105960265,
5030
+ "eval_f1": 0.7210884353741497,
5031
+ "eval_loss": 0.29165971279144287,
5032
+ "eval_precision": 0.8502673796791443,
5033
+ "eval_recall": 0.6259842519685039,
5034
+ "eval_runtime": 52.8549,
5035
+ "eval_samples_per_second": 5.241,
5036
+ "eval_steps_per_second": 0.17,
5037
+ "step": 660
5038
+ },
5039
+ {
5040
+ "epoch": 0.8384778012684989,
5041
+ "grad_norm": 3.554976224899292,
5042
+ "learning_rate": 1.5420322205337335e-06,
5043
+ "loss": 0.2036,
5044
+ "step": 661
5045
+ },
5046
+ {
5047
+ "epoch": 0.8397463002114165,
5048
+ "grad_norm": 5.035533905029297,
5049
+ "learning_rate": 1.5184756106854925e-06,
5050
+ "loss": 0.1991,
5051
+ "step": 662
5052
+ },
5053
+ {
5054
+ "epoch": 0.8410147991543341,
5055
+ "grad_norm": 3.7902748584747314,
5056
+ "learning_rate": 1.4950855262350282e-06,
5057
+ "loss": 0.1813,
5058
+ "step": 663
5059
+ },
5060
+ {
5061
+ "epoch": 0.8422832980972516,
5062
+ "grad_norm": 3.7442333698272705,
5063
+ "learning_rate": 1.471862426420908e-06,
5064
+ "loss": 0.2316,
5065
+ "step": 664
5066
+ },
5067
+ {
5068
+ "epoch": 0.8435517970401691,
5069
+ "grad_norm": 3.83044171333313,
5070
+ "learning_rate": 1.4488067672031391e-06,
5071
+ "loss": 0.2185,
5072
+ "step": 665
5073
+ },
5074
+ {
5075
+ "epoch": 0.8448202959830867,
5076
+ "grad_norm": 3.863065719604492,
5077
+ "learning_rate": 1.425919001254219e-06,
5078
+ "loss": 0.2586,
5079
+ "step": 666
5080
+ },
5081
+ {
5082
+ "epoch": 0.8460887949260042,
5083
+ "grad_norm": 4.449268341064453,
5084
+ "learning_rate": 1.403199577950245e-06,
5085
+ "loss": 0.1982,
5086
+ "step": 667
5087
+ },
5088
+ {
5089
+ "epoch": 0.8473572938689218,
5090
+ "grad_norm": 4.1120123863220215,
5091
+ "learning_rate": 1.3806489433620917e-06,
5092
+ "loss": 0.2196,
5093
+ "step": 668
5094
+ },
5095
+ {
5096
+ "epoch": 0.8486257928118394,
5097
+ "grad_norm": 3.667243242263794,
5098
+ "learning_rate": 1.3582675402466538e-06,
5099
+ "loss": 0.1903,
5100
+ "step": 669
5101
+ },
5102
+ {
5103
+ "epoch": 0.8498942917547568,
5104
+ "grad_norm": 4.294753551483154,
5105
+ "learning_rate": 1.336055808038149e-06,
5106
+ "loss": 0.2223,
5107
+ "step": 670
5108
+ },
5109
+ {
5110
+ "epoch": 0.8511627906976744,
5111
+ "grad_norm": 3.5263938903808594,
5112
+ "learning_rate": 1.3140141828394993e-06,
5113
+ "loss": 0.1916,
5114
+ "step": 671
5115
+ },
5116
+ {
5117
+ "epoch": 0.852431289640592,
5118
+ "grad_norm": 4.649272918701172,
5119
+ "learning_rate": 1.2921430974137562e-06,
5120
+ "loss": 0.278,
5121
+ "step": 672
5122
+ },
5123
+ {
5124
+ "epoch": 0.8536997885835095,
5125
+ "grad_norm": 5.0053558349609375,
5126
+ "learning_rate": 1.270442981175617e-06,
5127
+ "loss": 0.2298,
5128
+ "step": 673
5129
+ },
5130
+ {
5131
+ "epoch": 0.8549682875264271,
5132
+ "grad_norm": 6.003551483154297,
5133
+ "learning_rate": 1.2489142601829819e-06,
5134
+ "loss": 0.3026,
5135
+ "step": 674
5136
+ },
5137
+ {
5138
+ "epoch": 0.8562367864693446,
5139
+ "grad_norm": 5.016626834869385,
5140
+ "learning_rate": 1.227557357128597e-06,
5141
+ "loss": 0.234,
5142
+ "step": 675
5143
+ },
5144
+ {
5145
+ "epoch": 0.8575052854122621,
5146
+ "grad_norm": 4.0852251052856445,
5147
+ "learning_rate": 1.2063726913317508e-06,
5148
+ "loss": 0.1984,
5149
+ "step": 676
5150
+ },
5151
+ {
5152
+ "epoch": 0.8587737843551797,
5153
+ "grad_norm": 3.9487900733947754,
5154
+ "learning_rate": 1.185360678730043e-06,
5155
+ "loss": 0.191,
5156
+ "step": 677
5157
+ },
5158
+ {
5159
+ "epoch": 0.8600422832980973,
5160
+ "grad_norm": 5.6874213218688965,
5161
+ "learning_rate": 1.1645217318712187e-06,
5162
+ "loss": 0.2541,
5163
+ "step": 678
5164
+ },
5165
+ {
5166
+ "epoch": 0.8613107822410148,
5167
+ "grad_norm": 4.008146286010742,
5168
+ "learning_rate": 1.1438562599050661e-06,
5169
+ "loss": 0.1698,
5170
+ "step": 679
5171
+ },
5172
+ {
5173
+ "epoch": 0.8625792811839323,
5174
+ "grad_norm": 5.791302680969238,
5175
+ "learning_rate": 1.1233646685753864e-06,
5176
+ "loss": 0.2837,
5177
+ "step": 680
5178
+ },
5179
+ {
5180
+ "epoch": 0.8625792811839323,
5181
+ "eval_accuracy": 0.8664459161147903,
5182
+ "eval_f1": 0.7317073170731707,
5183
+ "eval_loss": 0.2841557264328003,
5184
+ "eval_precision": 0.8375634517766497,
5185
+ "eval_recall": 0.6496062992125984,
5186
+ "eval_runtime": 51.6664,
5187
+ "eval_samples_per_second": 5.361,
5188
+ "eval_steps_per_second": 0.174,
5189
+ "step": 680
5190
+ },
5191
+ {
5192
+ "epoch": 0.8638477801268499,
5193
+ "grad_norm": 4.153045177459717,
5194
+ "learning_rate": 1.103047360212024e-06,
5195
+ "loss": 0.1929,
5196
+ "step": 681
5197
+ },
5198
+ {
5199
+ "epoch": 0.8651162790697674,
5200
+ "grad_norm": 6.1054511070251465,
5201
+ "learning_rate": 1.0829047337229714e-06,
5202
+ "loss": 0.2017,
5203
+ "step": 682
5204
+ },
5205
+ {
5206
+ "epoch": 0.866384778012685,
5207
+ "grad_norm": 4.814021110534668,
5208
+ "learning_rate": 1.0629371845865333e-06,
5209
+ "loss": 0.2109,
5210
+ "step": 683
5211
+ },
5212
+ {
5213
+ "epoch": 0.8676532769556026,
5214
+ "grad_norm": 3.665745258331299,
5215
+ "learning_rate": 1.0431451048435637e-06,
5216
+ "loss": 0.1851,
5217
+ "step": 684
5218
+ },
5219
+ {
5220
+ "epoch": 0.86892177589852,
5221
+ "grad_norm": 4.5687127113342285,
5222
+ "learning_rate": 1.023528883089766e-06,
5223
+ "loss": 0.2229,
5224
+ "step": 685
5225
+ },
5226
+ {
5227
+ "epoch": 0.8701902748414376,
5228
+ "grad_norm": 7.112755298614502,
5229
+ "learning_rate": 1.0040889044680702e-06,
5230
+ "loss": 0.2175,
5231
+ "step": 686
5232
+ },
5233
+ {
5234
+ "epoch": 0.8714587737843552,
5235
+ "grad_norm": 4.810848236083984,
5236
+ "learning_rate": 9.848255506610616e-07,
5237
+ "loss": 0.2445,
5238
+ "step": 687
5239
+ },
5240
+ {
5241
+ "epoch": 0.8727272727272727,
5242
+ "grad_norm": 3.9013190269470215,
5243
+ "learning_rate": 9.657391998834942e-07,
5244
+ "loss": 0.2054,
5245
+ "step": 688
5246
+ },
5247
+ {
5248
+ "epoch": 0.8739957716701903,
5249
+ "grad_norm": 4.112692832946777,
5250
+ "learning_rate": 9.468302268748608e-07,
5251
+ "loss": 0.2084,
5252
+ "step": 689
5253
+ },
5254
+ {
5255
+ "epoch": 0.8752642706131079,
5256
+ "grad_norm": 3.5854508876800537,
5257
+ "learning_rate": 9.2809900289204e-07,
5258
+ "loss": 0.1765,
5259
+ "step": 690
5260
+ },
5261
+ {
5262
+ "epoch": 0.8765327695560253,
5263
+ "grad_norm": 4.269070625305176,
5264
+ "learning_rate": 9.095458957019986e-07,
5265
+ "loss": 0.1872,
5266
+ "step": 691
5267
+ },
5268
+ {
5269
+ "epoch": 0.8778012684989429,
5270
+ "grad_norm": 6.264438152313232,
5271
+ "learning_rate": 8.911712695745823e-07,
5272
+ "loss": 0.1691,
5273
+ "step": 692
5274
+ },
5275
+ {
5276
+ "epoch": 0.8790697674418605,
5277
+ "grad_norm": 4.607624530792236,
5278
+ "learning_rate": 8.729754852753525e-07,
5279
+ "loss": 0.2539,
5280
+ "step": 693
5281
+ },
5282
+ {
5283
+ "epoch": 0.880338266384778,
5284
+ "grad_norm": 3.378829002380371,
5285
+ "learning_rate": 8.549589000585101e-07,
5286
+ "loss": 0.2015,
5287
+ "step": 694
5288
+ },
5289
+ {
5290
+ "epoch": 0.8816067653276956,
5291
+ "grad_norm": 4.111599922180176,
5292
+ "learning_rate": 8.371218676598814e-07,
5293
+ "loss": 0.212,
5294
+ "step": 695
5295
+ },
5296
+ {
5297
+ "epoch": 0.8828752642706131,
5298
+ "grad_norm": 7.777480125427246,
5299
+ "learning_rate": 8.194647382899657e-07,
5300
+ "loss": 0.2435,
5301
+ "step": 696
5302
+ },
5303
+ {
5304
+ "epoch": 0.8841437632135306,
5305
+ "grad_norm": 3.5605111122131348,
5306
+ "learning_rate": 8.019878586270691e-07,
5307
+ "loss": 0.2158,
5308
+ "step": 697
5309
+ },
5310
+ {
5311
+ "epoch": 0.8854122621564482,
5312
+ "grad_norm": 3.6146066188812256,
5313
+ "learning_rate": 7.846915718104897e-07,
5314
+ "loss": 0.2118,
5315
+ "step": 698
5316
+ },
5317
+ {
5318
+ "epoch": 0.8866807610993658,
5319
+ "grad_norm": 3.586723804473877,
5320
+ "learning_rate": 7.675762174337864e-07,
5321
+ "loss": 0.1818,
5322
+ "step": 699
5323
+ },
5324
+ {
5325
+ "epoch": 0.8879492600422833,
5326
+ "grad_norm": 4.1939167976379395,
5327
+ "learning_rate": 7.506421315381074e-07,
5328
+ "loss": 0.1779,
5329
+ "step": 700
5330
+ },
5331
+ {
5332
+ "epoch": 0.8879492600422833,
5333
+ "eval_accuracy": 0.8708609271523179,
5334
+ "eval_f1": 0.7405764966740577,
5335
+ "eval_loss": 0.28408411145210266,
5336
+ "eval_precision": 0.8477157360406091,
5337
+ "eval_recall": 0.65748031496063,
5338
+ "eval_runtime": 51.6724,
5339
+ "eval_samples_per_second": 5.361,
5340
+ "eval_steps_per_second": 0.174,
5341
+ "step": 700
5342
  }
5343
  ],
5344
  "logging_steps": 1,
 
5358
  "attributes": {}
5359
  }
5360
  },
5361
+ "total_flos": 2.6256102807044096e+17,
5362
  "train_batch_size": 6,
5363
  "trial_name": null,
5364
  "trial_params": null