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
67d0d1a
·
verified ·
1 Parent(s): 4ec274a

Training in progress, step 920, 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 sha256:044cf7bf03a83a1284032c251edc991976e172eee726149453d68149c900667c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00af1438a0f904c703b2a0a9b91360fc9cf02a1afd861f7ac653278d5f692e1
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57020216701ba285d7744225001c8d3129ec84fee5bd0354316de2439e8d52cb
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744d3d74d3e89764ef707a6d808aff55cdd0c082b466e82063591be566be397f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6099696e5efa68a4c7a2bb1a82a249d91c626ec7f203b8f6b838381539a28861
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7793f67a5ffc7c73f9bd638ac902d3a52494a9eb54bc6a053bd4759db7dadd1b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79c9349aa9c1938ff5bb9677d6cbc53c39492b7ed82b6c3d05e5d4d84802ba85
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60462611dbafa72b0e44e437a106336f8704064ce3123087a96fe9be72c4580f
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": 0.19413333333333332,
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,
@@ -928,6 +928,16 @@
928
  "mean_token_accuracy": 0.7455965608358384,
929
  "num_tokens": 4243300.0,
930
  "step": 910
 
 
 
 
 
 
 
 
 
 
931
  }
932
  ],
933
  "logging_steps": 10,
@@ -947,7 +957,7 @@
947
  "attributes": {}
948
  }
949
  },
950
- "total_flos": 2.0122349225385984e+16,
951
  "train_batch_size": 4,
952
  "trial_name": null,
953
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.19626666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 920,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
928
  "mean_token_accuracy": 0.7455965608358384,
929
  "num_tokens": 4243300.0,
930
  "step": 910
931
+ },
932
+ {
933
+ "entropy": 0.9650195389986038,
934
+ "epoch": 0.19626666666666667,
935
+ "grad_norm": 0.3590649366378784,
936
+ "learning_rate": 9.885667431126824e-05,
937
+ "loss": 1.0054343223571778,
938
+ "mean_token_accuracy": 0.7639905765652657,
939
+ "num_tokens": 4291788.0,
940
+ "step": 920
941
  }
942
  ],
943
  "logging_steps": 10,
 
957
  "attributes": {}
958
  }
959
  },
960
+ "total_flos": 2.036894999972659e+16,
961
  "train_batch_size": 4,
962
  "trial_name": null,
963
  "trial_params": null