Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
e742c52
·
verified ·
1 Parent(s): 1f893fb

Training in progress, step 860, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_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 +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fddc345ae6d2b73ee57370372630cb3799ae0d04076c953daffa116187dbab07
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8b6a1ae563c2a6072db187fe4f04086a0bc9de8975e495b407323cb2ab8d9f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e30b59ca469485cb4d3c1b1fd41cc3176cfa57e591993c804843ddbcebf765dd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8503e14e439fb940f132eaf9f9f6416b6e02914ab8db8f998e789d3238f4c79e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed7c9da09ac2e2da4726d998155ab319bdce74dc5490db2a8af114c66f110360
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f877b1343eb539e4b139e6ffe314a2159804af1cd639148ba0b50465516d07e5
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4228f8bcc0f777dd374525c5543b7fd9d59767e59fc71edf11fc0a4c8e676b49
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdf5892a3b4b72d817da6c694339f4c1f62b87ad44cc3b2ed51616035415123
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": 0.18133333333333335,
6
  "eval_steps": 500,
7
- "global_step": 850,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -868,6 +868,16 @@
868
  "mean_token_accuracy": 0.7678412273526192,
869
  "num_tokens": 3948812.0,
870
  "step": 850
 
 
 
 
 
 
 
 
 
 
871
  }
872
  ],
873
  "logging_steps": 10,
@@ -887,7 +897,7 @@
887
  "attributes": {}
888
  }
889
  },
890
- "total_flos": 1.870809865095168e+16,
891
  "train_batch_size": 4,
892
  "trial_name": null,
893
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.18346666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 860,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
868
  "mean_token_accuracy": 0.7678412273526192,
869
  "num_tokens": 3948812.0,
870
  "step": 850
871
+ },
872
+ {
873
+ "entropy": 0.8651109091937542,
874
+ "epoch": 0.18346666666666667,
875
+ "grad_norm": 0.2479069083929062,
876
+ "learning_rate": 9.906691979060943e-05,
877
+ "loss": 0.9216291427612304,
878
+ "mean_token_accuracy": 0.7761695921421051,
879
+ "num_tokens": 3991940.0,
880
+ "step": 860
881
  }
882
  ],
883
  "logging_steps": 10,
 
897
  "attributes": {}
898
  }
899
  },
900
+ "total_flos": 1.891983250540032e+16,
901
  "train_batch_size": 4,
902
  "trial_name": null,
903
  "trial_params": null