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
f0176c8
·
verified ·
1 Parent(s): a8e921c

Training in progress, step 1890, 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:b2b21bd8936658e5150f3047874ba691c8a210aa08bfd77a81bb9312a0abc347
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05e308a2c5af8f4a69099ac2de9cce1395313d8791bfa1b42b74df3fbbdac04
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd452283deb362d747a69acc15373134cb96b3763aac10c459ff7a5dc9a0a56f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37661b6d815425fc48061352f7f41c6088b99503d71e872d4dcaaa11c4f2a3ae
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab15fa9541989393212b46b5e35cbaaeb3e1e8b00877f3c0e40b3538467f916
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fadf706c8631bc79645621556fd45511580e2a05bccb6929c4101949cb9bf9fa
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5c87f4c2ffbbf44382d4689760dcb3c3df4a1b19df9759f1fb08863cfbe3ff6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f860aca640e106bfe1fa8cc2600c1667f6b24fe1566f5e575c7ab9acedbccf47
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": 0.4010666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1880,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1898,6 +1898,16 @@
1898
  "mean_token_accuracy": 0.7662092931568623,
1899
  "num_tokens": 8707004.0,
1900
  "step": 1880
 
 
 
 
 
 
 
 
 
 
1901
  }
1902
  ],
1903
  "logging_steps": 10,
@@ -1917,7 +1927,7 @@
1917
  "attributes": {}
1918
  }
1919
  },
1920
- "total_flos": 4.134666975198413e+16,
1921
  "train_batch_size": 4,
1922
  "trial_name": null,
1923
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4032,
6
  "eval_steps": 500,
7
+ "global_step": 1890,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1898
  "mean_token_accuracy": 0.7662092931568623,
1899
  "num_tokens": 8707004.0,
1900
  "step": 1880
1901
+ },
1902
+ {
1903
+ "entropy": 1.0146782457828523,
1904
+ "epoch": 0.4032,
1905
+ "grad_norm": 0.2506401240825653,
1906
+ "learning_rate": 9.262567689604195e-05,
1907
+ "loss": 1.124861240386963,
1908
+ "mean_token_accuracy": 0.7566848322749138,
1909
+ "num_tokens": 8753713.0,
1910
+ "step": 1890
1911
  }
1912
  ],
1913
  "logging_steps": 10,
 
1927
  "attributes": {}
1928
  }
1929
  },
1930
+ "total_flos": 4.157858118038938e+16,
1931
  "train_batch_size": 4,
1932
  "trial_name": null,
1933
  "trial_params": null