Hugging Face's logo

Azrail
/
smallm_70

Text Generation
Transformers
Safetensors
English
smallm
transformer
language-model
experimental
conversational
custom_code
Model card Files
xet
 Community
Azrail commited on
Commit
005139b
·
verified ·
1 Parent(s): fa4cd76

Training in progress, step 28000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +182 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b55abcd2a89267e04c5dc4d6890be5cd51083ea26331bc0049c8cb798c0b2817
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6bfbf59e48ccbe1c689774152a90d74c704789cf0a24340e31d970e2ae2f82b
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e9ea5ffc99fb85ec5b642b4ddb430150759191b1ea5e8fb7a5392dcecaef6d1
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf459077dbfc45a1bef121401b69108c6a04f583daf68be560ffcfd374476dc
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c02dfe3855e4fc4d5677c85754decec4c9943b8de46688d5cac8a0ecd3c5105
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed11a30b4dd7817e80835c6ecf6fe24d8d86f18c493af4a03052d58b7baf6875
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5585e9833c9684d1dabff9cec651205ae9bf4f81ab2bb2b589702ce44919fbb3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d5fef101c9d39d51795e2426ebd97ece14c40eab5611cbd021ffd2d11b16ce
3
  size 1064
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": 0.1287906793708337,
6
  "eval_steps": 500,
7
- "global_step": 27000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4814,11 +4814,189 @@
4814
  "eval_steps_per_second": 24.907,
4815
  "num_input_tokens_seen": 7077888000,
4816
  "step": 27000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4817
  }
4818
  ],
4819
  "logging_steps": 50,
4820
  "max_steps": 70000,
4821
- "num_input_tokens_seen": 7077888000,
4822
  "num_train_epochs": 1,
4823
  "save_steps": 1000,
4824
  "stateful_callbacks": {
@@ -4833,7 +5011,7 @@
4833
  "attributes": {}
4834
  }
4835
  },
4836
- "total_flos": 1.89340412018688e+18,
4837
  "train_batch_size": 64,
4838
  "trial_name": null,
4839
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1335607045327164,
6
  "eval_steps": 500,
7
+ "global_step": 28000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4814
  "eval_steps_per_second": 24.907,
4815
  "num_input_tokens_seen": 7077888000,
4816
  "step": 27000
4817
+ },
4818
+ {
4819
+ "epoch": 0.12902918062892782,
4820
+ "grad_norm": 0.1790401190519333,
4821
+ "learning_rate": 0.001,
4822
+ "loss": 2.672,
4823
+ "num_input_tokens_seen": 7090995200,
4824
+ "step": 27050
4825
+ },
4826
+ {
4827
+ "epoch": 0.12926768188702195,
4828
+ "grad_norm": 0.18173836171627045,
4829
+ "learning_rate": 0.001,
4830
+ "loss": 2.6563,
4831
+ "num_input_tokens_seen": 7104102400,
4832
+ "step": 27100
4833
+ },
4834
+ {
4835
+ "epoch": 0.12950618314511608,
4836
+ "grad_norm": 0.1827983856201172,
4837
+ "learning_rate": 0.001,
4838
+ "loss": 2.665,
4839
+ "num_input_tokens_seen": 7117209600,
4840
+ "step": 27150
4841
+ },
4842
+ {
4843
+ "epoch": 0.12974468440321021,
4844
+ "grad_norm": 0.20252254605293274,
4845
+ "learning_rate": 0.001,
4846
+ "loss": 2.675,
4847
+ "num_input_tokens_seen": 7130316800,
4848
+ "step": 27200
4849
+ },
4850
+ {
4851
+ "epoch": 0.12998318566130437,
4852
+ "grad_norm": 0.18492095172405243,
4853
+ "learning_rate": 0.001,
4854
+ "loss": 2.6801,
4855
+ "num_input_tokens_seen": 7143424000,
4856
+ "step": 27250
4857
+ },
4858
+ {
4859
+ "epoch": 0.1302216869193985,
4860
+ "grad_norm": 0.1962280571460724,
4861
+ "learning_rate": 0.001,
4862
+ "loss": 2.6551,
4863
+ "num_input_tokens_seen": 7156531200,
4864
+ "step": 27300
4865
+ },
4866
+ {
4867
+ "epoch": 0.13046018817749264,
4868
+ "grad_norm": 0.18813727796077728,
4869
+ "learning_rate": 0.001,
4870
+ "loss": 2.6728,
4871
+ "num_input_tokens_seen": 7169638400,
4872
+ "step": 27350
4873
+ },
4874
+ {
4875
+ "epoch": 0.13069868943558677,
4876
+ "grad_norm": 0.18111565709114075,
4877
+ "learning_rate": 0.001,
4878
+ "loss": 2.6743,
4879
+ "num_input_tokens_seen": 7182745600,
4880
+ "step": 27400
4881
+ },
4882
+ {
4883
+ "epoch": 0.1309371906936809,
4884
+ "grad_norm": 0.1727459728717804,
4885
+ "learning_rate": 0.001,
4886
+ "loss": 2.6596,
4887
+ "num_input_tokens_seen": 7195852800,
4888
+ "step": 27450
4889
+ },
4890
+ {
4891
+ "epoch": 0.13117569195177506,
4892
+ "grad_norm": 0.20097768306732178,
4893
+ "learning_rate": 0.001,
4894
+ "loss": 2.6651,
4895
+ "num_input_tokens_seen": 7208960000,
4896
+ "step": 27500
4897
+ },
4898
+ {
4899
+ "epoch": 0.13117569195177506,
4900
+ "eval_loss": 2.5501132011413574,
4901
+ "eval_runtime": 50.3677,
4902
+ "eval_samples_per_second": 99.27,
4903
+ "eval_steps_per_second": 24.817,
4904
+ "num_input_tokens_seen": 7208960000,
4905
+ "step": 27500
4906
+ },
4907
+ {
4908
+ "epoch": 0.1314141932098692,
4909
+ "grad_norm": 0.17329637706279755,
4910
+ "learning_rate": 0.001,
4911
+ "loss": 2.663,
4912
+ "num_input_tokens_seen": 7222067200,
4913
+ "step": 27550
4914
+ },
4915
+ {
4916
+ "epoch": 0.13165269446796332,
4917
+ "grad_norm": 0.16942919790744781,
4918
+ "learning_rate": 0.001,
4919
+ "loss": 2.6609,
4920
+ "num_input_tokens_seen": 7235174400,
4921
+ "step": 27600
4922
+ },
4923
+ {
4924
+ "epoch": 0.13189119572605745,
4925
+ "grad_norm": 0.19828958809375763,
4926
+ "learning_rate": 0.001,
4927
+ "loss": 2.6625,
4928
+ "num_input_tokens_seen": 7248281600,
4929
+ "step": 27650
4930
+ },
4931
+ {
4932
+ "epoch": 0.13212969698415158,
4933
+ "grad_norm": 0.1928141862154007,
4934
+ "learning_rate": 0.001,
4935
+ "loss": 2.6597,
4936
+ "num_input_tokens_seen": 7261388800,
4937
+ "step": 27700
4938
+ },
4939
+ {
4940
+ "epoch": 0.13236819824224572,
4941
+ "grad_norm": 0.1870756894350052,
4942
+ "learning_rate": 0.001,
4943
+ "loss": 2.6718,
4944
+ "num_input_tokens_seen": 7274496000,
4945
+ "step": 27750
4946
+ },
4947
+ {
4948
+ "epoch": 0.13260669950033988,
4949
+ "grad_norm": 0.1786762923002243,
4950
+ "learning_rate": 0.001,
4951
+ "loss": 2.6631,
4952
+ "num_input_tokens_seen": 7287603200,
4953
+ "step": 27800
4954
+ },
4955
+ {
4956
+ "epoch": 0.132845200758434,
4957
+ "grad_norm": 0.1710624396800995,
4958
+ "learning_rate": 0.001,
4959
+ "loss": 2.6717,
4960
+ "num_input_tokens_seen": 7300710400,
4961
+ "step": 27850
4962
+ },
4963
+ {
4964
+ "epoch": 0.13308370201652814,
4965
+ "grad_norm": 0.1805214285850525,
4966
+ "learning_rate": 0.001,
4967
+ "loss": 2.6669,
4968
+ "num_input_tokens_seen": 7313817600,
4969
+ "step": 27900
4970
+ },
4971
+ {
4972
+ "epoch": 0.13332220327462227,
4973
+ "grad_norm": 0.18169906735420227,
4974
+ "learning_rate": 0.001,
4975
+ "loss": 2.6659,
4976
+ "num_input_tokens_seen": 7326924800,
4977
+ "step": 27950
4978
+ },
4979
+ {
4980
+ "epoch": 0.1335607045327164,
4981
+ "grad_norm": 0.16959500312805176,
4982
+ "learning_rate": 0.001,
4983
+ "loss": 2.6623,
4984
+ "num_input_tokens_seen": 7340032000,
4985
+ "step": 28000
4986
+ },
4987
+ {
4988
+ "epoch": 0.1335607045327164,
4989
+ "eval_loss": 2.548675060272217,
4990
+ "eval_runtime": 50.3022,
4991
+ "eval_samples_per_second": 99.399,
4992
+ "eval_steps_per_second": 24.85,
4993
+ "num_input_tokens_seen": 7340032000,
4994
+ "step": 28000
4995
  }
4996
  ],
4997
  "logging_steps": 50,
4998
  "max_steps": 70000,
4999
+ "num_input_tokens_seen": 7340032000,
5000
  "num_train_epochs": 1,
5001
  "save_steps": 1000,
5002
  "stateful_callbacks": {
 
5011
  "attributes": {}
5012
  }
5013
  },
5014
+ "total_flos": 1.96353019871232e+18,
5015
  "train_batch_size": 64,
5016
  "trial_name": null,
5017
  "trial_params": null