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
9341561
·
verified ·
1 Parent(s): 6ede16b

Training in progress, step 970, 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 sha256:564e891558dbee48aaabad64385e525ca07f69d70f6780eac526b7227fb0e4d7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25ef14d544a86261a8303ea4d09fe51a9afbbbe2131ea2b01201b585d541998
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f756146704b821da6d38eae88e48b9c6e19d4ba23d13be975d5302eda8f7b3b7
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdfdb3d6508fa69e14210a096f5358eab840da3193e2990e0ff2493741a36488
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:bea58ffab763eb2832ec247dd6950bb9f06c3eba9a785871c428cff34de2202c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0d18ed158a4b4d641ed44d7bc0652113a71069ac47b6a6b9b881008433d282
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97633a098e7ad4dd3b61fe26d82257e5d244df4a98bccfd3b80c0d03883af5fc
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ed72dba72c3a00ae79b076236883de329c07dacf5137a49edae1986175bb16
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": 0.2048,
6
  "eval_steps": 500,
7
- "global_step": 960,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -978,6 +978,16 @@
978
  "mean_token_accuracy": 0.7547310657799244,
979
  "num_tokens": 4478207.0,
980
  "step": 960
 
 
 
 
 
 
 
 
 
 
981
  }
982
  ],
983
  "logging_steps": 10,
@@ -997,7 +1007,7 @@
997
  "attributes": {}
998
  }
999
  },
1000
- "total_flos": 2.121952621246464e+16,
1001
  "train_batch_size": 4,
1002
  "trial_name": null,
1003
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.20693333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 970,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
978
  "mean_token_accuracy": 0.7547310657799244,
979
  "num_tokens": 4478207.0,
980
  "step": 960
981
+ },
982
+ {
983
+ "entropy": 0.9463694766163826,
984
+ "epoch": 0.20693333333333333,
985
+ "grad_norm": 0.28800663352012634,
986
+ "learning_rate": 9.866536837076098e-05,
987
+ "loss": 1.0770373344421387,
988
+ "mean_token_accuracy": 0.7622694931924343,
989
+ "num_tokens": 4523626.0,
990
+ "step": 970
991
  }
992
  ],
993
  "logging_steps": 10,
 
1007
  "attributes": {}
1008
  }
1009
  },
1010
+ "total_flos": 2.1420878394203136e+16,
1011
  "train_batch_size": 4,
1012
  "trial_name": null,
1013
  "trial_params": null