TensorBoard
Safetensors
English
llama
appvoid commited on
Commit
ef5d11c
·
verified ·
1 Parent(s): c925933

Deep35 continual checkpoint step 70000

Browse files
last-checkpoint/continual_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "global_step": 68000,
3
- "sequence_tokens_emitted": 10977525760,
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": 10977280000
60
  }
 
1
  {
2
+ "global_step": 70000,
3
+ "sequence_tokens_emitted": 11469045760,
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": 11468800000
60
  }
last-checkpoint/data_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83839bb4a1a1dd1bdb13ae46419226765e1f4932d23409118ae48682e4b81711
3
- size 25087
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d13c20a890cf0a56a4a6834ddba384231d2683b12c4714ba5556ca6860862f7
3
+ size 17087
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dbe9733d86e444acf76351bdc0d01c90c9ebfadaa415e128566c836b0e34d58
3
  size 70326256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc103916873e1262bfc23d1dd8a92eca53f4f15831f4c6dd913e7f11322b220
3
  size 70326256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:506921a66c8e8d24363c844357c33b51d81726d4f2505352e43c93b354f7b1ad
3
  size 140740171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8768888097feaefcaad79f2a16904510e60e37b0d2337a03b7068541bb69fe4
3
  size 140740171
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d24c706aabd9e13c1509b36523f7b9ba4d813be3ac7bd6766eb3b55a97ca216
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d335be81226cd81ea46d3fcf1cf9d04777f156b67e1b9d884c93a8f05103a457
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83683208050f46041252eea4909d760c7161c0633154e96362abc1e12795e57e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b588cc85f85bfe2402983dbceaa921b14c6b5565bd198e73f3b0979bcf40551
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": 9e-06,
6
  "eval_steps": 500,
7
- "global_step": 68000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -48794,6 +48794,1438 @@
48794
  "eval_samples_per_second": 520.008,
48795
  "eval_steps_per_second": 16.25,
48796
  "step": 68000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48797
  }
48798
  ],
48799
  "logging_steps": 10,
@@ -48813,7 +50245,7 @@
48813
  "attributes": {}
48814
  }
48815
  },
48816
- "total_flos": 1.50614323494912e+18,
48817
  "train_batch_size": 240,
48818
  "trial_name": null,
48819
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1e-05,
6
  "eval_steps": 500,
7
+ "global_step": 70000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
48794
  "eval_samples_per_second": 520.008,
48795
  "eval_steps_per_second": 16.25,
48796
  "step": 68000
48797
+ },
48798
+ {
48799
+ "epoch": 9.005e-06,
48800
+ "grad_norm": 0.470703125,
48801
+ "learning_rate": 2.9999999999999997e-05,
48802
+ "loss": 3.0451,
48803
+ "step": 68010
48804
+ },
48805
+ {
48806
+ "epoch": 9.01e-06,
48807
+ "grad_norm": 0.4609375,
48808
+ "learning_rate": 2.9999999999999997e-05,
48809
+ "loss": 3.0444,
48810
+ "step": 68020
48811
+ },
48812
+ {
48813
+ "epoch": 9.015e-06,
48814
+ "grad_norm": 0.470703125,
48815
+ "learning_rate": 2.9999999999999997e-05,
48816
+ "loss": 3.0592,
48817
+ "step": 68030
48818
+ },
48819
+ {
48820
+ "epoch": 9.02e-06,
48821
+ "grad_norm": 0.447265625,
48822
+ "learning_rate": 2.9999999999999997e-05,
48823
+ "loss": 3.0288,
48824
+ "step": 68040
48825
+ },
48826
+ {
48827
+ "epoch": 9.025e-06,
48828
+ "grad_norm": 0.451171875,
48829
+ "learning_rate": 2.9999999999999997e-05,
48830
+ "loss": 3.0585,
48831
+ "step": 68050
48832
+ },
48833
+ {
48834
+ "epoch": 9.03e-06,
48835
+ "grad_norm": 0.455078125,
48836
+ "learning_rate": 2.9999999999999997e-05,
48837
+ "loss": 3.0547,
48838
+ "step": 68060
48839
+ },
48840
+ {
48841
+ "epoch": 9.035e-06,
48842
+ "grad_norm": 0.451171875,
48843
+ "learning_rate": 2.9999999999999997e-05,
48844
+ "loss": 3.0539,
48845
+ "step": 68070
48846
+ },
48847
+ {
48848
+ "epoch": 9.04e-06,
48849
+ "grad_norm": 0.4609375,
48850
+ "learning_rate": 2.9999999999999997e-05,
48851
+ "loss": 3.0554,
48852
+ "step": 68080
48853
+ },
48854
+ {
48855
+ "epoch": 9.045e-06,
48856
+ "grad_norm": 0.5078125,
48857
+ "learning_rate": 2.9999999999999997e-05,
48858
+ "loss": 3.0259,
48859
+ "step": 68090
48860
+ },
48861
+ {
48862
+ "epoch": 9.05e-06,
48863
+ "grad_norm": 0.50390625,
48864
+ "learning_rate": 2.9999999999999997e-05,
48865
+ "loss": 3.0393,
48866
+ "step": 68100
48867
+ },
48868
+ {
48869
+ "epoch": 9.055e-06,
48870
+ "grad_norm": 0.4453125,
48871
+ "learning_rate": 2.9999999999999997e-05,
48872
+ "loss": 3.031,
48873
+ "step": 68110
48874
+ },
48875
+ {
48876
+ "epoch": 9.06e-06,
48877
+ "grad_norm": 0.47265625,
48878
+ "learning_rate": 2.9999999999999997e-05,
48879
+ "loss": 3.0485,
48880
+ "step": 68120
48881
+ },
48882
+ {
48883
+ "epoch": 9.065e-06,
48884
+ "grad_norm": 0.482421875,
48885
+ "learning_rate": 2.9999999999999997e-05,
48886
+ "loss": 3.037,
48887
+ "step": 68130
48888
+ },
48889
+ {
48890
+ "epoch": 9.07e-06,
48891
+ "grad_norm": 0.462890625,
48892
+ "learning_rate": 2.9999999999999997e-05,
48893
+ "loss": 3.0359,
48894
+ "step": 68140
48895
+ },
48896
+ {
48897
+ "epoch": 9.075e-06,
48898
+ "grad_norm": 0.4609375,
48899
+ "learning_rate": 2.9999999999999997e-05,
48900
+ "loss": 3.039,
48901
+ "step": 68150
48902
+ },
48903
+ {
48904
+ "epoch": 9.08e-06,
48905
+ "grad_norm": 0.47265625,
48906
+ "learning_rate": 2.9999999999999997e-05,
48907
+ "loss": 3.0519,
48908
+ "step": 68160
48909
+ },
48910
+ {
48911
+ "epoch": 9.085e-06,
48912
+ "grad_norm": 0.4921875,
48913
+ "learning_rate": 2.9999999999999997e-05,
48914
+ "loss": 3.0182,
48915
+ "step": 68170
48916
+ },
48917
+ {
48918
+ "epoch": 9.09e-06,
48919
+ "grad_norm": 0.453125,
48920
+ "learning_rate": 2.9999999999999997e-05,
48921
+ "loss": 3.0604,
48922
+ "step": 68180
48923
+ },
48924
+ {
48925
+ "epoch": 9.095e-06,
48926
+ "grad_norm": 0.451171875,
48927
+ "learning_rate": 2.9999999999999997e-05,
48928
+ "loss": 3.0318,
48929
+ "step": 68190
48930
+ },
48931
+ {
48932
+ "epoch": 9.1e-06,
48933
+ "grad_norm": 0.44921875,
48934
+ "learning_rate": 2.9999999999999997e-05,
48935
+ "loss": 3.0592,
48936
+ "step": 68200
48937
+ },
48938
+ {
48939
+ "epoch": 9.105e-06,
48940
+ "grad_norm": 0.46875,
48941
+ "learning_rate": 2.9999999999999997e-05,
48942
+ "loss": 3.0451,
48943
+ "step": 68210
48944
+ },
48945
+ {
48946
+ "epoch": 9.11e-06,
48947
+ "grad_norm": 0.453125,
48948
+ "learning_rate": 2.9999999999999997e-05,
48949
+ "loss": 3.0467,
48950
+ "step": 68220
48951
+ },
48952
+ {
48953
+ "epoch": 9.115e-06,
48954
+ "grad_norm": 0.462890625,
48955
+ "learning_rate": 2.9999999999999997e-05,
48956
+ "loss": 3.0359,
48957
+ "step": 68230
48958
+ },
48959
+ {
48960
+ "epoch": 9.12e-06,
48961
+ "grad_norm": 0.4453125,
48962
+ "learning_rate": 2.9999999999999997e-05,
48963
+ "loss": 3.0402,
48964
+ "step": 68240
48965
+ },
48966
+ {
48967
+ "epoch": 9.125e-06,
48968
+ "grad_norm": 0.44921875,
48969
+ "learning_rate": 2.9999999999999997e-05,
48970
+ "loss": 3.059,
48971
+ "step": 68250
48972
+ },
48973
+ {
48974
+ "epoch": 9.13e-06,
48975
+ "grad_norm": 0.4375,
48976
+ "learning_rate": 2.9999999999999997e-05,
48977
+ "loss": 3.0156,
48978
+ "step": 68260
48979
+ },
48980
+ {
48981
+ "epoch": 9.135e-06,
48982
+ "grad_norm": 0.4375,
48983
+ "learning_rate": 2.9999999999999997e-05,
48984
+ "loss": 3.037,
48985
+ "step": 68270
48986
+ },
48987
+ {
48988
+ "epoch": 9.14e-06,
48989
+ "grad_norm": 0.44140625,
48990
+ "learning_rate": 2.9999999999999997e-05,
48991
+ "loss": 3.0382,
48992
+ "step": 68280
48993
+ },
48994
+ {
48995
+ "epoch": 9.145e-06,
48996
+ "grad_norm": 0.451171875,
48997
+ "learning_rate": 2.9999999999999997e-05,
48998
+ "loss": 3.0143,
48999
+ "step": 68290
49000
+ },
49001
+ {
49002
+ "epoch": 9.15e-06,
49003
+ "grad_norm": 0.46484375,
49004
+ "learning_rate": 2.9999999999999997e-05,
49005
+ "loss": 3.0337,
49006
+ "step": 68300
49007
+ },
49008
+ {
49009
+ "epoch": 9.155e-06,
49010
+ "grad_norm": 0.46484375,
49011
+ "learning_rate": 2.9999999999999997e-05,
49012
+ "loss": 3.0244,
49013
+ "step": 68310
49014
+ },
49015
+ {
49016
+ "epoch": 9.16e-06,
49017
+ "grad_norm": 0.443359375,
49018
+ "learning_rate": 2.9999999999999997e-05,
49019
+ "loss": 3.0256,
49020
+ "step": 68320
49021
+ },
49022
+ {
49023
+ "epoch": 9.165e-06,
49024
+ "grad_norm": 0.44140625,
49025
+ "learning_rate": 2.9999999999999997e-05,
49026
+ "loss": 3.0293,
49027
+ "step": 68330
49028
+ },
49029
+ {
49030
+ "epoch": 9.17e-06,
49031
+ "grad_norm": 0.51171875,
49032
+ "learning_rate": 2.9999999999999997e-05,
49033
+ "loss": 3.0486,
49034
+ "step": 68340
49035
+ },
49036
+ {
49037
+ "epoch": 9.175e-06,
49038
+ "grad_norm": 0.455078125,
49039
+ "learning_rate": 2.9999999999999997e-05,
49040
+ "loss": 3.0348,
49041
+ "step": 68350
49042
+ },
49043
+ {
49044
+ "epoch": 9.18e-06,
49045
+ "grad_norm": 0.44140625,
49046
+ "learning_rate": 2.9999999999999997e-05,
49047
+ "loss": 3.0506,
49048
+ "step": 68360
49049
+ },
49050
+ {
49051
+ "epoch": 9.185e-06,
49052
+ "grad_norm": 0.515625,
49053
+ "learning_rate": 2.9999999999999997e-05,
49054
+ "loss": 3.0462,
49055
+ "step": 68370
49056
+ },
49057
+ {
49058
+ "epoch": 9.19e-06,
49059
+ "grad_norm": 0.455078125,
49060
+ "learning_rate": 2.9999999999999997e-05,
49061
+ "loss": 3.0454,
49062
+ "step": 68380
49063
+ },
49064
+ {
49065
+ "epoch": 9.195e-06,
49066
+ "grad_norm": 0.55078125,
49067
+ "learning_rate": 2.9999999999999997e-05,
49068
+ "loss": 3.0605,
49069
+ "step": 68390
49070
+ },
49071
+ {
49072
+ "epoch": 9.2e-06,
49073
+ "grad_norm": 0.47265625,
49074
+ "learning_rate": 2.9999999999999997e-05,
49075
+ "loss": 3.06,
49076
+ "step": 68400
49077
+ },
49078
+ {
49079
+ "epoch": 9.205e-06,
49080
+ "grad_norm": 0.45703125,
49081
+ "learning_rate": 2.9999999999999997e-05,
49082
+ "loss": 3.0545,
49083
+ "step": 68410
49084
+ },
49085
+ {
49086
+ "epoch": 9.21e-06,
49087
+ "grad_norm": 0.470703125,
49088
+ "learning_rate": 2.9999999999999997e-05,
49089
+ "loss": 3.0176,
49090
+ "step": 68420
49091
+ },
49092
+ {
49093
+ "epoch": 9.215e-06,
49094
+ "grad_norm": 0.4453125,
49095
+ "learning_rate": 2.9999999999999997e-05,
49096
+ "loss": 3.0582,
49097
+ "step": 68430
49098
+ },
49099
+ {
49100
+ "epoch": 9.22e-06,
49101
+ "grad_norm": 0.59375,
49102
+ "learning_rate": 2.9999999999999997e-05,
49103
+ "loss": 3.0499,
49104
+ "step": 68440
49105
+ },
49106
+ {
49107
+ "epoch": 9.225e-06,
49108
+ "grad_norm": 0.451171875,
49109
+ "learning_rate": 2.9999999999999997e-05,
49110
+ "loss": 3.0459,
49111
+ "step": 68450
49112
+ },
49113
+ {
49114
+ "epoch": 9.23e-06,
49115
+ "grad_norm": 0.453125,
49116
+ "learning_rate": 2.9999999999999997e-05,
49117
+ "loss": 3.0453,
49118
+ "step": 68460
49119
+ },
49120
+ {
49121
+ "epoch": 9.235e-06,
49122
+ "grad_norm": 0.443359375,
49123
+ "learning_rate": 2.9999999999999997e-05,
49124
+ "loss": 3.0428,
49125
+ "step": 68470
49126
+ },
49127
+ {
49128
+ "epoch": 9.24e-06,
49129
+ "grad_norm": 0.46875,
49130
+ "learning_rate": 2.9999999999999997e-05,
49131
+ "loss": 3.0526,
49132
+ "step": 68480
49133
+ },
49134
+ {
49135
+ "epoch": 9.245e-06,
49136
+ "grad_norm": 0.453125,
49137
+ "learning_rate": 2.9999999999999997e-05,
49138
+ "loss": 3.0117,
49139
+ "step": 68490
49140
+ },
49141
+ {
49142
+ "epoch": 9.25e-06,
49143
+ "grad_norm": 0.447265625,
49144
+ "learning_rate": 2.9999999999999997e-05,
49145
+ "loss": 3.0232,
49146
+ "step": 68500
49147
+ },
49148
+ {
49149
+ "epoch": 9.25e-06,
49150
+ "eval_loss": 3.0828802585601807,
49151
+ "eval_runtime": 0.0653,
49152
+ "eval_samples_per_second": 490.316,
49153
+ "eval_steps_per_second": 15.322,
49154
+ "step": 68500
49155
+ },
49156
+ {
49157
+ "epoch": 9.255e-06,
49158
+ "grad_norm": 0.671875,
49159
+ "learning_rate": 2.9999999999999997e-05,
49160
+ "loss": 3.0604,
49161
+ "step": 68510
49162
+ },
49163
+ {
49164
+ "epoch": 9.26e-06,
49165
+ "grad_norm": 0.546875,
49166
+ "learning_rate": 2.9999999999999997e-05,
49167
+ "loss": 3.0111,
49168
+ "step": 68520
49169
+ },
49170
+ {
49171
+ "epoch": 9.265e-06,
49172
+ "grad_norm": 0.458984375,
49173
+ "learning_rate": 2.9999999999999997e-05,
49174
+ "loss": 3.043,
49175
+ "step": 68530
49176
+ },
49177
+ {
49178
+ "epoch": 9.27e-06,
49179
+ "grad_norm": 0.451171875,
49180
+ "learning_rate": 2.9999999999999997e-05,
49181
+ "loss": 3.051,
49182
+ "step": 68540
49183
+ },
49184
+ {
49185
+ "epoch": 9.275e-06,
49186
+ "grad_norm": 0.46484375,
49187
+ "learning_rate": 2.9999999999999997e-05,
49188
+ "loss": 3.028,
49189
+ "step": 68550
49190
+ },
49191
+ {
49192
+ "epoch": 9.28e-06,
49193
+ "grad_norm": 0.474609375,
49194
+ "learning_rate": 2.9999999999999997e-05,
49195
+ "loss": 3.0423,
49196
+ "step": 68560
49197
+ },
49198
+ {
49199
+ "epoch": 9.285e-06,
49200
+ "grad_norm": 0.4609375,
49201
+ "learning_rate": 2.9999999999999997e-05,
49202
+ "loss": 3.0444,
49203
+ "step": 68570
49204
+ },
49205
+ {
49206
+ "epoch": 9.29e-06,
49207
+ "grad_norm": 0.447265625,
49208
+ "learning_rate": 2.9999999999999997e-05,
49209
+ "loss": 3.0581,
49210
+ "step": 68580
49211
+ },
49212
+ {
49213
+ "epoch": 9.295e-06,
49214
+ "grad_norm": 0.46875,
49215
+ "learning_rate": 2.9999999999999997e-05,
49216
+ "loss": 3.0312,
49217
+ "step": 68590
49218
+ },
49219
+ {
49220
+ "epoch": 9.3e-06,
49221
+ "grad_norm": 0.439453125,
49222
+ "learning_rate": 2.9999999999999997e-05,
49223
+ "loss": 3.0238,
49224
+ "step": 68600
49225
+ },
49226
+ {
49227
+ "epoch": 9.305e-06,
49228
+ "grad_norm": 0.453125,
49229
+ "learning_rate": 2.9999999999999997e-05,
49230
+ "loss": 3.0517,
49231
+ "step": 68610
49232
+ },
49233
+ {
49234
+ "epoch": 9.31e-06,
49235
+ "grad_norm": 0.5703125,
49236
+ "learning_rate": 2.9999999999999997e-05,
49237
+ "loss": 3.0625,
49238
+ "step": 68620
49239
+ },
49240
+ {
49241
+ "epoch": 9.315e-06,
49242
+ "grad_norm": 0.466796875,
49243
+ "learning_rate": 2.9999999999999997e-05,
49244
+ "loss": 3.0378,
49245
+ "step": 68630
49246
+ },
49247
+ {
49248
+ "epoch": 9.32e-06,
49249
+ "grad_norm": 0.443359375,
49250
+ "learning_rate": 2.9999999999999997e-05,
49251
+ "loss": 3.0311,
49252
+ "step": 68640
49253
+ },
49254
+ {
49255
+ "epoch": 9.325e-06,
49256
+ "grad_norm": 0.466796875,
49257
+ "learning_rate": 2.9999999999999997e-05,
49258
+ "loss": 3.036,
49259
+ "step": 68650
49260
+ },
49261
+ {
49262
+ "epoch": 9.33e-06,
49263
+ "grad_norm": 0.44140625,
49264
+ "learning_rate": 2.9999999999999997e-05,
49265
+ "loss": 3.0264,
49266
+ "step": 68660
49267
+ },
49268
+ {
49269
+ "epoch": 9.335e-06,
49270
+ "grad_norm": 0.44921875,
49271
+ "learning_rate": 2.9999999999999997e-05,
49272
+ "loss": 3.0273,
49273
+ "step": 68670
49274
+ },
49275
+ {
49276
+ "epoch": 9.34e-06,
49277
+ "grad_norm": 0.466796875,
49278
+ "learning_rate": 2.9999999999999997e-05,
49279
+ "loss": 3.0309,
49280
+ "step": 68680
49281
+ },
49282
+ {
49283
+ "epoch": 9.345e-06,
49284
+ "grad_norm": 0.482421875,
49285
+ "learning_rate": 2.9999999999999997e-05,
49286
+ "loss": 3.0353,
49287
+ "step": 68690
49288
+ },
49289
+ {
49290
+ "epoch": 9.35e-06,
49291
+ "grad_norm": 0.48828125,
49292
+ "learning_rate": 2.9999999999999997e-05,
49293
+ "loss": 3.0108,
49294
+ "step": 68700
49295
+ },
49296
+ {
49297
+ "epoch": 9.355e-06,
49298
+ "grad_norm": 0.458984375,
49299
+ "learning_rate": 2.9999999999999997e-05,
49300
+ "loss": 3.0369,
49301
+ "step": 68710
49302
+ },
49303
+ {
49304
+ "epoch": 9.36e-06,
49305
+ "grad_norm": 0.466796875,
49306
+ "learning_rate": 2.9999999999999997e-05,
49307
+ "loss": 3.0463,
49308
+ "step": 68720
49309
+ },
49310
+ {
49311
+ "epoch": 9.365e-06,
49312
+ "grad_norm": 0.486328125,
49313
+ "learning_rate": 2.9999999999999997e-05,
49314
+ "loss": 3.0464,
49315
+ "step": 68730
49316
+ },
49317
+ {
49318
+ "epoch": 9.37e-06,
49319
+ "grad_norm": 0.4765625,
49320
+ "learning_rate": 2.9999999999999997e-05,
49321
+ "loss": 3.0536,
49322
+ "step": 68740
49323
+ },
49324
+ {
49325
+ "epoch": 9.375e-06,
49326
+ "grad_norm": 0.49609375,
49327
+ "learning_rate": 2.9999999999999997e-05,
49328
+ "loss": 3.0404,
49329
+ "step": 68750
49330
+ },
49331
+ {
49332
+ "epoch": 9.38e-06,
49333
+ "grad_norm": 0.4765625,
49334
+ "learning_rate": 2.9999999999999997e-05,
49335
+ "loss": 3.0392,
49336
+ "step": 68760
49337
+ },
49338
+ {
49339
+ "epoch": 9.385e-06,
49340
+ "grad_norm": 0.44921875,
49341
+ "learning_rate": 2.9999999999999997e-05,
49342
+ "loss": 3.0276,
49343
+ "step": 68770
49344
+ },
49345
+ {
49346
+ "epoch": 9.39e-06,
49347
+ "grad_norm": 0.451171875,
49348
+ "learning_rate": 2.9999999999999997e-05,
49349
+ "loss": 3.0424,
49350
+ "step": 68780
49351
+ },
49352
+ {
49353
+ "epoch": 9.395e-06,
49354
+ "grad_norm": 0.4609375,
49355
+ "learning_rate": 2.9999999999999997e-05,
49356
+ "loss": 3.0378,
49357
+ "step": 68790
49358
+ },
49359
+ {
49360
+ "epoch": 9.4e-06,
49361
+ "grad_norm": 0.478515625,
49362
+ "learning_rate": 2.9999999999999997e-05,
49363
+ "loss": 3.0609,
49364
+ "step": 68800
49365
+ },
49366
+ {
49367
+ "epoch": 9.405e-06,
49368
+ "grad_norm": 0.490234375,
49369
+ "learning_rate": 2.9999999999999997e-05,
49370
+ "loss": 3.0275,
49371
+ "step": 68810
49372
+ },
49373
+ {
49374
+ "epoch": 9.41e-06,
49375
+ "grad_norm": 0.4609375,
49376
+ "learning_rate": 2.9999999999999997e-05,
49377
+ "loss": 3.0371,
49378
+ "step": 68820
49379
+ },
49380
+ {
49381
+ "epoch": 9.415e-06,
49382
+ "grad_norm": 0.447265625,
49383
+ "learning_rate": 2.9999999999999997e-05,
49384
+ "loss": 3.0314,
49385
+ "step": 68830
49386
+ },
49387
+ {
49388
+ "epoch": 9.42e-06,
49389
+ "grad_norm": 0.462890625,
49390
+ "learning_rate": 2.9999999999999997e-05,
49391
+ "loss": 3.0273,
49392
+ "step": 68840
49393
+ },
49394
+ {
49395
+ "epoch": 9.425e-06,
49396
+ "grad_norm": 0.4375,
49397
+ "learning_rate": 2.9999999999999997e-05,
49398
+ "loss": 3.018,
49399
+ "step": 68850
49400
+ },
49401
+ {
49402
+ "epoch": 9.43e-06,
49403
+ "grad_norm": 0.4765625,
49404
+ "learning_rate": 2.9999999999999997e-05,
49405
+ "loss": 3.0344,
49406
+ "step": 68860
49407
+ },
49408
+ {
49409
+ "epoch": 9.435e-06,
49410
+ "grad_norm": 0.490234375,
49411
+ "learning_rate": 2.9999999999999997e-05,
49412
+ "loss": 3.0649,
49413
+ "step": 68870
49414
+ },
49415
+ {
49416
+ "epoch": 9.44e-06,
49417
+ "grad_norm": 0.458984375,
49418
+ "learning_rate": 2.9999999999999997e-05,
49419
+ "loss": 3.0442,
49420
+ "step": 68880
49421
+ },
49422
+ {
49423
+ "epoch": 9.445e-06,
49424
+ "grad_norm": 0.474609375,
49425
+ "learning_rate": 2.9999999999999997e-05,
49426
+ "loss": 3.0283,
49427
+ "step": 68890
49428
+ },
49429
+ {
49430
+ "epoch": 9.45e-06,
49431
+ "grad_norm": 0.43359375,
49432
+ "learning_rate": 2.9999999999999997e-05,
49433
+ "loss": 3.0419,
49434
+ "step": 68900
49435
+ },
49436
+ {
49437
+ "epoch": 9.455e-06,
49438
+ "grad_norm": 0.458984375,
49439
+ "learning_rate": 2.9999999999999997e-05,
49440
+ "loss": 3.0686,
49441
+ "step": 68910
49442
+ },
49443
+ {
49444
+ "epoch": 9.46e-06,
49445
+ "grad_norm": 0.4765625,
49446
+ "learning_rate": 2.9999999999999997e-05,
49447
+ "loss": 3.0588,
49448
+ "step": 68920
49449
+ },
49450
+ {
49451
+ "epoch": 9.465e-06,
49452
+ "grad_norm": 0.4375,
49453
+ "learning_rate": 2.9999999999999997e-05,
49454
+ "loss": 3.0435,
49455
+ "step": 68930
49456
+ },
49457
+ {
49458
+ "epoch": 9.47e-06,
49459
+ "grad_norm": 0.466796875,
49460
+ "learning_rate": 2.9999999999999997e-05,
49461
+ "loss": 3.0343,
49462
+ "step": 68940
49463
+ },
49464
+ {
49465
+ "epoch": 9.475e-06,
49466
+ "grad_norm": 0.451171875,
49467
+ "learning_rate": 2.9999999999999997e-05,
49468
+ "loss": 3.0368,
49469
+ "step": 68950
49470
+ },
49471
+ {
49472
+ "epoch": 9.48e-06,
49473
+ "grad_norm": 0.44921875,
49474
+ "learning_rate": 2.9999999999999997e-05,
49475
+ "loss": 3.0272,
49476
+ "step": 68960
49477
+ },
49478
+ {
49479
+ "epoch": 9.485e-06,
49480
+ "grad_norm": 0.4765625,
49481
+ "learning_rate": 2.9999999999999997e-05,
49482
+ "loss": 3.0359,
49483
+ "step": 68970
49484
+ },
49485
+ {
49486
+ "epoch": 9.49e-06,
49487
+ "grad_norm": 0.47265625,
49488
+ "learning_rate": 2.9999999999999997e-05,
49489
+ "loss": 3.0642,
49490
+ "step": 68980
49491
+ },
49492
+ {
49493
+ "epoch": 9.495e-06,
49494
+ "grad_norm": 0.455078125,
49495
+ "learning_rate": 2.9999999999999997e-05,
49496
+ "loss": 3.0518,
49497
+ "step": 68990
49498
+ },
49499
+ {
49500
+ "epoch": 9.5e-06,
49501
+ "grad_norm": 0.46484375,
49502
+ "learning_rate": 2.9999999999999997e-05,
49503
+ "loss": 3.0262,
49504
+ "step": 69000
49505
+ },
49506
+ {
49507
+ "epoch": 9.5e-06,
49508
+ "eval_loss": 3.0823965072631836,
49509
+ "eval_runtime": 0.0619,
49510
+ "eval_samples_per_second": 517.085,
49511
+ "eval_steps_per_second": 16.159,
49512
+ "step": 69000
49513
+ },
49514
+ {
49515
+ "epoch": 9.505e-06,
49516
+ "grad_norm": 0.484375,
49517
+ "learning_rate": 2.9999999999999997e-05,
49518
+ "loss": 3.0395,
49519
+ "step": 69010
49520
+ },
49521
+ {
49522
+ "epoch": 9.51e-06,
49523
+ "grad_norm": 0.50390625,
49524
+ "learning_rate": 2.9999999999999997e-05,
49525
+ "loss": 3.0714,
49526
+ "step": 69020
49527
+ },
49528
+ {
49529
+ "epoch": 9.515e-06,
49530
+ "grad_norm": 0.427734375,
49531
+ "learning_rate": 2.9999999999999997e-05,
49532
+ "loss": 2.9955,
49533
+ "step": 69030
49534
+ },
49535
+ {
49536
+ "epoch": 9.52e-06,
49537
+ "grad_norm": 0.453125,
49538
+ "learning_rate": 2.9999999999999997e-05,
49539
+ "loss": 3.0481,
49540
+ "step": 69040
49541
+ },
49542
+ {
49543
+ "epoch": 9.525e-06,
49544
+ "grad_norm": 0.482421875,
49545
+ "learning_rate": 2.9999999999999997e-05,
49546
+ "loss": 3.0602,
49547
+ "step": 69050
49548
+ },
49549
+ {
49550
+ "epoch": 9.53e-06,
49551
+ "grad_norm": 0.494140625,
49552
+ "learning_rate": 2.9999999999999997e-05,
49553
+ "loss": 3.0226,
49554
+ "step": 69060
49555
+ },
49556
+ {
49557
+ "epoch": 9.535e-06,
49558
+ "grad_norm": 0.5546875,
49559
+ "learning_rate": 2.9999999999999997e-05,
49560
+ "loss": 3.0469,
49561
+ "step": 69070
49562
+ },
49563
+ {
49564
+ "epoch": 9.54e-06,
49565
+ "grad_norm": 0.443359375,
49566
+ "learning_rate": 2.9999999999999997e-05,
49567
+ "loss": 3.0322,
49568
+ "step": 69080
49569
+ },
49570
+ {
49571
+ "epoch": 9.545e-06,
49572
+ "grad_norm": 0.46875,
49573
+ "learning_rate": 2.9999999999999997e-05,
49574
+ "loss": 3.0518,
49575
+ "step": 69090
49576
+ },
49577
+ {
49578
+ "epoch": 9.55e-06,
49579
+ "grad_norm": 0.5078125,
49580
+ "learning_rate": 2.9999999999999997e-05,
49581
+ "loss": 3.0512,
49582
+ "step": 69100
49583
+ },
49584
+ {
49585
+ "epoch": 9.555e-06,
49586
+ "grad_norm": 0.47265625,
49587
+ "learning_rate": 2.9999999999999997e-05,
49588
+ "loss": 3.049,
49589
+ "step": 69110
49590
+ },
49591
+ {
49592
+ "epoch": 9.56e-06,
49593
+ "grad_norm": 0.455078125,
49594
+ "learning_rate": 2.9999999999999997e-05,
49595
+ "loss": 3.0239,
49596
+ "step": 69120
49597
+ },
49598
+ {
49599
+ "epoch": 9.565e-06,
49600
+ "grad_norm": 0.462890625,
49601
+ "learning_rate": 2.9999999999999997e-05,
49602
+ "loss": 3.051,
49603
+ "step": 69130
49604
+ },
49605
+ {
49606
+ "epoch": 9.57e-06,
49607
+ "grad_norm": 0.494140625,
49608
+ "learning_rate": 2.9999999999999997e-05,
49609
+ "loss": 3.0255,
49610
+ "step": 69140
49611
+ },
49612
+ {
49613
+ "epoch": 9.575e-06,
49614
+ "grad_norm": 0.453125,
49615
+ "learning_rate": 2.9999999999999997e-05,
49616
+ "loss": 3.0192,
49617
+ "step": 69150
49618
+ },
49619
+ {
49620
+ "epoch": 9.58e-06,
49621
+ "grad_norm": 0.462890625,
49622
+ "learning_rate": 2.9999999999999997e-05,
49623
+ "loss": 3.0343,
49624
+ "step": 69160
49625
+ },
49626
+ {
49627
+ "epoch": 9.585e-06,
49628
+ "grad_norm": 0.4921875,
49629
+ "learning_rate": 2.9999999999999997e-05,
49630
+ "loss": 3.0403,
49631
+ "step": 69170
49632
+ },
49633
+ {
49634
+ "epoch": 9.59e-06,
49635
+ "grad_norm": 0.4453125,
49636
+ "learning_rate": 2.9999999999999997e-05,
49637
+ "loss": 3.047,
49638
+ "step": 69180
49639
+ },
49640
+ {
49641
+ "epoch": 9.595e-06,
49642
+ "grad_norm": 0.43359375,
49643
+ "learning_rate": 2.9999999999999997e-05,
49644
+ "loss": 3.0326,
49645
+ "step": 69190
49646
+ },
49647
+ {
49648
+ "epoch": 9.6e-06,
49649
+ "grad_norm": 0.498046875,
49650
+ "learning_rate": 2.9999999999999997e-05,
49651
+ "loss": 3.0503,
49652
+ "step": 69200
49653
+ },
49654
+ {
49655
+ "epoch": 9.605e-06,
49656
+ "grad_norm": 0.4609375,
49657
+ "learning_rate": 2.9999999999999997e-05,
49658
+ "loss": 3.0517,
49659
+ "step": 69210
49660
+ },
49661
+ {
49662
+ "epoch": 9.61e-06,
49663
+ "grad_norm": 0.447265625,
49664
+ "learning_rate": 2.9999999999999997e-05,
49665
+ "loss": 3.0413,
49666
+ "step": 69220
49667
+ },
49668
+ {
49669
+ "epoch": 9.615e-06,
49670
+ "grad_norm": 0.4609375,
49671
+ "learning_rate": 2.9999999999999997e-05,
49672
+ "loss": 3.0598,
49673
+ "step": 69230
49674
+ },
49675
+ {
49676
+ "epoch": 9.62e-06,
49677
+ "grad_norm": 0.486328125,
49678
+ "learning_rate": 2.9999999999999997e-05,
49679
+ "loss": 3.0452,
49680
+ "step": 69240
49681
+ },
49682
+ {
49683
+ "epoch": 9.625e-06,
49684
+ "grad_norm": 0.474609375,
49685
+ "learning_rate": 2.9999999999999997e-05,
49686
+ "loss": 3.0536,
49687
+ "step": 69250
49688
+ },
49689
+ {
49690
+ "epoch": 9.63e-06,
49691
+ "grad_norm": 0.45703125,
49692
+ "learning_rate": 2.9999999999999997e-05,
49693
+ "loss": 3.0473,
49694
+ "step": 69260
49695
+ },
49696
+ {
49697
+ "epoch": 9.635e-06,
49698
+ "grad_norm": 0.439453125,
49699
+ "learning_rate": 2.9999999999999997e-05,
49700
+ "loss": 3.0351,
49701
+ "step": 69270
49702
+ },
49703
+ {
49704
+ "epoch": 9.64e-06,
49705
+ "grad_norm": 0.5078125,
49706
+ "learning_rate": 2.9999999999999997e-05,
49707
+ "loss": 3.0561,
49708
+ "step": 69280
49709
+ },
49710
+ {
49711
+ "epoch": 9.645e-06,
49712
+ "grad_norm": 0.5,
49713
+ "learning_rate": 2.9999999999999997e-05,
49714
+ "loss": 3.0493,
49715
+ "step": 69290
49716
+ },
49717
+ {
49718
+ "epoch": 9.65e-06,
49719
+ "grad_norm": 0.51171875,
49720
+ "learning_rate": 2.9999999999999997e-05,
49721
+ "loss": 3.026,
49722
+ "step": 69300
49723
+ },
49724
+ {
49725
+ "epoch": 9.655e-06,
49726
+ "grad_norm": 0.49609375,
49727
+ "learning_rate": 2.9999999999999997e-05,
49728
+ "loss": 3.0658,
49729
+ "step": 69310
49730
+ },
49731
+ {
49732
+ "epoch": 9.66e-06,
49733
+ "grad_norm": 0.478515625,
49734
+ "learning_rate": 2.9999999999999997e-05,
49735
+ "loss": 3.0109,
49736
+ "step": 69320
49737
+ },
49738
+ {
49739
+ "epoch": 9.665e-06,
49740
+ "grad_norm": 0.515625,
49741
+ "learning_rate": 2.9999999999999997e-05,
49742
+ "loss": 3.0594,
49743
+ "step": 69330
49744
+ },
49745
+ {
49746
+ "epoch": 9.67e-06,
49747
+ "grad_norm": 0.46484375,
49748
+ "learning_rate": 2.9999999999999997e-05,
49749
+ "loss": 3.0377,
49750
+ "step": 69340
49751
+ },
49752
+ {
49753
+ "epoch": 9.675e-06,
49754
+ "grad_norm": 0.494140625,
49755
+ "learning_rate": 2.9999999999999997e-05,
49756
+ "loss": 3.047,
49757
+ "step": 69350
49758
+ },
49759
+ {
49760
+ "epoch": 9.68e-06,
49761
+ "grad_norm": 0.4609375,
49762
+ "learning_rate": 2.9999999999999997e-05,
49763
+ "loss": 3.035,
49764
+ "step": 69360
49765
+ },
49766
+ {
49767
+ "epoch": 9.685e-06,
49768
+ "grad_norm": 0.447265625,
49769
+ "learning_rate": 2.9999999999999997e-05,
49770
+ "loss": 3.0478,
49771
+ "step": 69370
49772
+ },
49773
+ {
49774
+ "epoch": 9.69e-06,
49775
+ "grad_norm": 0.490234375,
49776
+ "learning_rate": 2.9999999999999997e-05,
49777
+ "loss": 3.0446,
49778
+ "step": 69380
49779
+ },
49780
+ {
49781
+ "epoch": 9.695e-06,
49782
+ "grad_norm": 0.48828125,
49783
+ "learning_rate": 2.9999999999999997e-05,
49784
+ "loss": 3.0558,
49785
+ "step": 69390
49786
+ },
49787
+ {
49788
+ "epoch": 9.7e-06,
49789
+ "grad_norm": 0.46875,
49790
+ "learning_rate": 2.9999999999999997e-05,
49791
+ "loss": 3.0527,
49792
+ "step": 69400
49793
+ },
49794
+ {
49795
+ "epoch": 9.705e-06,
49796
+ "grad_norm": 0.447265625,
49797
+ "learning_rate": 2.9999999999999997e-05,
49798
+ "loss": 3.0341,
49799
+ "step": 69410
49800
+ },
49801
+ {
49802
+ "epoch": 9.71e-06,
49803
+ "grad_norm": 0.453125,
49804
+ "learning_rate": 2.9999999999999997e-05,
49805
+ "loss": 3.0493,
49806
+ "step": 69420
49807
+ },
49808
+ {
49809
+ "epoch": 9.715e-06,
49810
+ "grad_norm": 0.478515625,
49811
+ "learning_rate": 2.9999999999999997e-05,
49812
+ "loss": 3.0506,
49813
+ "step": 69430
49814
+ },
49815
+ {
49816
+ "epoch": 9.72e-06,
49817
+ "grad_norm": 0.474609375,
49818
+ "learning_rate": 2.9999999999999997e-05,
49819
+ "loss": 3.039,
49820
+ "step": 69440
49821
+ },
49822
+ {
49823
+ "epoch": 9.725e-06,
49824
+ "grad_norm": 0.44921875,
49825
+ "learning_rate": 2.9999999999999997e-05,
49826
+ "loss": 3.0187,
49827
+ "step": 69450
49828
+ },
49829
+ {
49830
+ "epoch": 9.73e-06,
49831
+ "grad_norm": 0.466796875,
49832
+ "learning_rate": 2.9999999999999997e-05,
49833
+ "loss": 3.0177,
49834
+ "step": 69460
49835
+ },
49836
+ {
49837
+ "epoch": 9.735e-06,
49838
+ "grad_norm": 0.44140625,
49839
+ "learning_rate": 2.9999999999999997e-05,
49840
+ "loss": 3.0063,
49841
+ "step": 69470
49842
+ },
49843
+ {
49844
+ "epoch": 9.74e-06,
49845
+ "grad_norm": 0.4765625,
49846
+ "learning_rate": 2.9999999999999997e-05,
49847
+ "loss": 3.0459,
49848
+ "step": 69480
49849
+ },
49850
+ {
49851
+ "epoch": 9.745e-06,
49852
+ "grad_norm": 0.4453125,
49853
+ "learning_rate": 2.9999999999999997e-05,
49854
+ "loss": 3.043,
49855
+ "step": 69490
49856
+ },
49857
+ {
49858
+ "epoch": 9.75e-06,
49859
+ "grad_norm": 0.435546875,
49860
+ "learning_rate": 2.9999999999999997e-05,
49861
+ "loss": 3.0777,
49862
+ "step": 69500
49863
+ },
49864
+ {
49865
+ "epoch": 9.75e-06,
49866
+ "eval_loss": 3.082871913909912,
49867
+ "eval_runtime": 0.0636,
49868
+ "eval_samples_per_second": 503.384,
49869
+ "eval_steps_per_second": 15.731,
49870
+ "step": 69500
49871
+ },
49872
+ {
49873
+ "epoch": 9.755e-06,
49874
+ "grad_norm": 0.44140625,
49875
+ "learning_rate": 2.9999999999999997e-05,
49876
+ "loss": 3.0507,
49877
+ "step": 69510
49878
+ },
49879
+ {
49880
+ "epoch": 9.76e-06,
49881
+ "grad_norm": 0.49609375,
49882
+ "learning_rate": 2.9999999999999997e-05,
49883
+ "loss": 3.0286,
49884
+ "step": 69520
49885
+ },
49886
+ {
49887
+ "epoch": 9.765e-06,
49888
+ "grad_norm": 0.5,
49889
+ "learning_rate": 2.9999999999999997e-05,
49890
+ "loss": 3.0301,
49891
+ "step": 69530
49892
+ },
49893
+ {
49894
+ "epoch": 9.77e-06,
49895
+ "grad_norm": 0.451171875,
49896
+ "learning_rate": 2.9999999999999997e-05,
49897
+ "loss": 3.0609,
49898
+ "step": 69540
49899
+ },
49900
+ {
49901
+ "epoch": 9.775e-06,
49902
+ "grad_norm": 0.486328125,
49903
+ "learning_rate": 2.9999999999999997e-05,
49904
+ "loss": 3.0646,
49905
+ "step": 69550
49906
+ },
49907
+ {
49908
+ "epoch": 9.78e-06,
49909
+ "grad_norm": 0.546875,
49910
+ "learning_rate": 2.9999999999999997e-05,
49911
+ "loss": 3.0599,
49912
+ "step": 69560
49913
+ },
49914
+ {
49915
+ "epoch": 9.785e-06,
49916
+ "grad_norm": 0.490234375,
49917
+ "learning_rate": 2.9999999999999997e-05,
49918
+ "loss": 3.0421,
49919
+ "step": 69570
49920
+ },
49921
+ {
49922
+ "epoch": 9.79e-06,
49923
+ "grad_norm": 0.4609375,
49924
+ "learning_rate": 2.9999999999999997e-05,
49925
+ "loss": 3.0307,
49926
+ "step": 69580
49927
+ },
49928
+ {
49929
+ "epoch": 9.795e-06,
49930
+ "grad_norm": 0.478515625,
49931
+ "learning_rate": 2.9999999999999997e-05,
49932
+ "loss": 3.0187,
49933
+ "step": 69590
49934
+ },
49935
+ {
49936
+ "epoch": 9.8e-06,
49937
+ "grad_norm": 0.45703125,
49938
+ "learning_rate": 2.9999999999999997e-05,
49939
+ "loss": 3.0622,
49940
+ "step": 69600
49941
+ },
49942
+ {
49943
+ "epoch": 9.805e-06,
49944
+ "grad_norm": 0.45703125,
49945
+ "learning_rate": 2.9999999999999997e-05,
49946
+ "loss": 3.0186,
49947
+ "step": 69610
49948
+ },
49949
+ {
49950
+ "epoch": 9.81e-06,
49951
+ "grad_norm": 0.51953125,
49952
+ "learning_rate": 2.9999999999999997e-05,
49953
+ "loss": 3.0356,
49954
+ "step": 69620
49955
+ },
49956
+ {
49957
+ "epoch": 9.815e-06,
49958
+ "grad_norm": 0.451171875,
49959
+ "learning_rate": 2.9999999999999997e-05,
49960
+ "loss": 3.0355,
49961
+ "step": 69630
49962
+ },
49963
+ {
49964
+ "epoch": 9.82e-06,
49965
+ "grad_norm": 0.455078125,
49966
+ "learning_rate": 2.9999999999999997e-05,
49967
+ "loss": 3.0386,
49968
+ "step": 69640
49969
+ },
49970
+ {
49971
+ "epoch": 9.825e-06,
49972
+ "grad_norm": 0.44140625,
49973
+ "learning_rate": 2.9999999999999997e-05,
49974
+ "loss": 3.048,
49975
+ "step": 69650
49976
+ },
49977
+ {
49978
+ "epoch": 9.83e-06,
49979
+ "grad_norm": 0.46484375,
49980
+ "learning_rate": 2.9999999999999997e-05,
49981
+ "loss": 3.0209,
49982
+ "step": 69660
49983
+ },
49984
+ {
49985
+ "epoch": 9.835e-06,
49986
+ "grad_norm": 0.44921875,
49987
+ "learning_rate": 2.9999999999999997e-05,
49988
+ "loss": 3.0096,
49989
+ "step": 69670
49990
+ },
49991
+ {
49992
+ "epoch": 9.84e-06,
49993
+ "grad_norm": 0.48046875,
49994
+ "learning_rate": 2.9999999999999997e-05,
49995
+ "loss": 3.0265,
49996
+ "step": 69680
49997
+ },
49998
+ {
49999
+ "epoch": 9.845e-06,
50000
+ "grad_norm": 0.45703125,
50001
+ "learning_rate": 2.9999999999999997e-05,
50002
+ "loss": 3.0422,
50003
+ "step": 69690
50004
+ },
50005
+ {
50006
+ "epoch": 9.85e-06,
50007
+ "grad_norm": 0.451171875,
50008
+ "learning_rate": 2.9999999999999997e-05,
50009
+ "loss": 3.0192,
50010
+ "step": 69700
50011
+ },
50012
+ {
50013
+ "epoch": 9.855e-06,
50014
+ "grad_norm": 0.46484375,
50015
+ "learning_rate": 2.9999999999999997e-05,
50016
+ "loss": 3.0285,
50017
+ "step": 69710
50018
+ },
50019
+ {
50020
+ "epoch": 9.86e-06,
50021
+ "grad_norm": 0.462890625,
50022
+ "learning_rate": 2.9999999999999997e-05,
50023
+ "loss": 3.0295,
50024
+ "step": 69720
50025
+ },
50026
+ {
50027
+ "epoch": 9.865e-06,
50028
+ "grad_norm": 0.4609375,
50029
+ "learning_rate": 2.9999999999999997e-05,
50030
+ "loss": 3.0217,
50031
+ "step": 69730
50032
+ },
50033
+ {
50034
+ "epoch": 9.87e-06,
50035
+ "grad_norm": 0.46484375,
50036
+ "learning_rate": 2.9999999999999997e-05,
50037
+ "loss": 3.0344,
50038
+ "step": 69740
50039
+ },
50040
+ {
50041
+ "epoch": 9.875e-06,
50042
+ "grad_norm": 0.43359375,
50043
+ "learning_rate": 2.9999999999999997e-05,
50044
+ "loss": 3.0269,
50045
+ "step": 69750
50046
+ },
50047
+ {
50048
+ "epoch": 9.88e-06,
50049
+ "grad_norm": 0.474609375,
50050
+ "learning_rate": 2.9999999999999997e-05,
50051
+ "loss": 3.0206,
50052
+ "step": 69760
50053
+ },
50054
+ {
50055
+ "epoch": 9.885e-06,
50056
+ "grad_norm": 0.5,
50057
+ "learning_rate": 2.9999999999999997e-05,
50058
+ "loss": 3.035,
50059
+ "step": 69770
50060
+ },
50061
+ {
50062
+ "epoch": 9.89e-06,
50063
+ "grad_norm": 0.494140625,
50064
+ "learning_rate": 2.9999999999999997e-05,
50065
+ "loss": 3.027,
50066
+ "step": 69780
50067
+ },
50068
+ {
50069
+ "epoch": 9.895e-06,
50070
+ "grad_norm": 0.470703125,
50071
+ "learning_rate": 2.9999999999999997e-05,
50072
+ "loss": 3.0153,
50073
+ "step": 69790
50074
+ },
50075
+ {
50076
+ "epoch": 9.9e-06,
50077
+ "grad_norm": 0.45703125,
50078
+ "learning_rate": 2.9999999999999997e-05,
50079
+ "loss": 3.0281,
50080
+ "step": 69800
50081
+ },
50082
+ {
50083
+ "epoch": 9.905e-06,
50084
+ "grad_norm": 0.439453125,
50085
+ "learning_rate": 2.9999999999999997e-05,
50086
+ "loss": 3.0556,
50087
+ "step": 69810
50088
+ },
50089
+ {
50090
+ "epoch": 9.91e-06,
50091
+ "grad_norm": 0.484375,
50092
+ "learning_rate": 2.9999999999999997e-05,
50093
+ "loss": 3.056,
50094
+ "step": 69820
50095
+ },
50096
+ {
50097
+ "epoch": 9.915e-06,
50098
+ "grad_norm": 0.5078125,
50099
+ "learning_rate": 2.9999999999999997e-05,
50100
+ "loss": 3.0744,
50101
+ "step": 69830
50102
+ },
50103
+ {
50104
+ "epoch": 9.92e-06,
50105
+ "grad_norm": 0.484375,
50106
+ "learning_rate": 2.9999999999999997e-05,
50107
+ "loss": 3.0246,
50108
+ "step": 69840
50109
+ },
50110
+ {
50111
+ "epoch": 9.925e-06,
50112
+ "grad_norm": 0.4765625,
50113
+ "learning_rate": 2.9999999999999997e-05,
50114
+ "loss": 3.0199,
50115
+ "step": 69850
50116
+ },
50117
+ {
50118
+ "epoch": 9.93e-06,
50119
+ "grad_norm": 0.47265625,
50120
+ "learning_rate": 2.9999999999999997e-05,
50121
+ "loss": 3.0537,
50122
+ "step": 69860
50123
+ },
50124
+ {
50125
+ "epoch": 9.935e-06,
50126
+ "grad_norm": 0.466796875,
50127
+ "learning_rate": 2.9999999999999997e-05,
50128
+ "loss": 3.0239,
50129
+ "step": 69870
50130
+ },
50131
+ {
50132
+ "epoch": 9.94e-06,
50133
+ "grad_norm": 0.50390625,
50134
+ "learning_rate": 2.9999999999999997e-05,
50135
+ "loss": 3.0518,
50136
+ "step": 69880
50137
+ },
50138
+ {
50139
+ "epoch": 9.945e-06,
50140
+ "grad_norm": 0.443359375,
50141
+ "learning_rate": 2.9999999999999997e-05,
50142
+ "loss": 3.0183,
50143
+ "step": 69890
50144
+ },
50145
+ {
50146
+ "epoch": 9.95e-06,
50147
+ "grad_norm": 0.439453125,
50148
+ "learning_rate": 2.9999999999999997e-05,
50149
+ "loss": 3.0489,
50150
+ "step": 69900
50151
+ },
50152
+ {
50153
+ "epoch": 9.955e-06,
50154
+ "grad_norm": 0.5546875,
50155
+ "learning_rate": 2.9999999999999997e-05,
50156
+ "loss": 3.0386,
50157
+ "step": 69910
50158
+ },
50159
+ {
50160
+ "epoch": 9.96e-06,
50161
+ "grad_norm": 0.443359375,
50162
+ "learning_rate": 2.9999999999999997e-05,
50163
+ "loss": 3.0299,
50164
+ "step": 69920
50165
+ },
50166
+ {
50167
+ "epoch": 9.965e-06,
50168
+ "grad_norm": 0.46875,
50169
+ "learning_rate": 2.9999999999999997e-05,
50170
+ "loss": 3.0745,
50171
+ "step": 69930
50172
+ },
50173
+ {
50174
+ "epoch": 9.97e-06,
50175
+ "grad_norm": 0.5078125,
50176
+ "learning_rate": 2.9999999999999997e-05,
50177
+ "loss": 3.0528,
50178
+ "step": 69940
50179
+ },
50180
+ {
50181
+ "epoch": 9.975e-06,
50182
+ "grad_norm": 0.443359375,
50183
+ "learning_rate": 2.9999999999999997e-05,
50184
+ "loss": 3.063,
50185
+ "step": 69950
50186
+ },
50187
+ {
50188
+ "epoch": 9.98e-06,
50189
+ "grad_norm": 0.462890625,
50190
+ "learning_rate": 2.9999999999999997e-05,
50191
+ "loss": 3.0478,
50192
+ "step": 69960
50193
+ },
50194
+ {
50195
+ "epoch": 9.985e-06,
50196
+ "grad_norm": 0.447265625,
50197
+ "learning_rate": 2.9999999999999997e-05,
50198
+ "loss": 3.0393,
50199
+ "step": 69970
50200
+ },
50201
+ {
50202
+ "epoch": 9.99e-06,
50203
+ "grad_norm": 0.46875,
50204
+ "learning_rate": 2.9999999999999997e-05,
50205
+ "loss": 3.0326,
50206
+ "step": 69980
50207
+ },
50208
+ {
50209
+ "epoch": 9.995e-06,
50210
+ "grad_norm": 0.470703125,
50211
+ "learning_rate": 2.9999999999999997e-05,
50212
+ "loss": 3.017,
50213
+ "step": 69990
50214
+ },
50215
+ {
50216
+ "epoch": 1e-05,
50217
+ "grad_norm": 0.4453125,
50218
+ "learning_rate": 2.9999999999999997e-05,
50219
+ "loss": 3.0427,
50220
+ "step": 70000
50221
+ },
50222
+ {
50223
+ "epoch": 1e-05,
50224
+ "eval_loss": 3.082289218902588,
50225
+ "eval_runtime": 0.0664,
50226
+ "eval_samples_per_second": 481.893,
50227
+ "eval_steps_per_second": 15.059,
50228
+ "step": 70000
50229
  }
50230
  ],
50231
  "logging_steps": 10,
 
50245
  "attributes": {}
50246
  }
50247
  },
50248
+ "total_flos": 1.5735824842752e+18,
50249
  "train_batch_size": 240,
50250
  "trial_name": null,
50251
  "trial_params": null