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
60b7579
·
verified ·
1 Parent(s): 42e2dc7

Training in progress, step 910, 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 sha256:6e47026d8d9e9eef5dd43f037c38456cb4a4bc33d85f2d287262deffe130fa55
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:044cf7bf03a83a1284032c251edc991976e172eee726149453d68149c900667c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e897f7b6640776d1fc68c4336c64070fb82f4f46526d5483b99ec9d7b682506
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57020216701ba285d7744225001c8d3129ec84fee5bd0354316de2439e8d52cb
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a86a51f646cf00fb8db1ac2a7e1d9dd446604af03dd319a668c4c6e0bdc8af0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6099696e5efa68a4c7a2bb1a82a249d91c626ec7f203b8f6b838381539a28861
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2404255a94204789d141502b69632ccd1d8ecf1615874d47ddc39e1a4515f7ac
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c9349aa9c1938ff5bb9677d6cbc53c39492b7ed82b6c3d05e5d4d84802ba85
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": 0.192,
6
  "eval_steps": 500,
7
- "global_step": 900,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -918,6 +918,16 @@
918
  "mean_token_accuracy": 0.7614006102085114,
919
  "num_tokens": 4194087.0,
920
  "step": 900
 
 
 
 
 
 
 
 
 
 
921
  }
922
  ],
923
  "logging_steps": 10,
@@ -937,7 +947,7 @@
937
  "attributes": {}
938
  }
939
  },
940
- "total_flos": 1.9883003005326336e+16,
941
  "train_batch_size": 4,
942
  "trial_name": null,
943
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.19413333333333332,
6
  "eval_steps": 500,
7
+ "global_step": 910,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
918
  "mean_token_accuracy": 0.7614006102085114,
919
  "num_tokens": 4194087.0,
920
  "step": 900
921
+ },
922
+ {
923
+ "entropy": 1.0538529880344867,
924
+ "epoch": 0.19413333333333332,
925
+ "grad_norm": 0.23789124190807343,
926
+ "learning_rate": 9.889318117279373e-05,
927
+ "loss": 1.196424674987793,
928
+ "mean_token_accuracy": 0.7455965608358384,
929
+ "num_tokens": 4243300.0,
930
+ "step": 910
931
  }
932
  ],
933
  "logging_steps": 10,
 
947
  "attributes": {}
948
  }
949
  },
950
+ "total_flos": 2.0122349225385984e+16,
951
  "train_batch_size": 4,
952
  "trial_name": null,
953
  "trial_params": null