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
207aeb3
·
verified ·
1 Parent(s): 0aa9a28

Training in progress, step 960, 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 sha256:13ba389655fb787a8530f6928885d73c045df0e160ac83ca56fbeca9c7f5df85
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564e891558dbee48aaabad64385e525ca07f69d70f6780eac526b7227fb0e4d7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d84ffd8f3da9bc88deeb5e1e70716cb973af7c8848fb205649a545ebe5213ed
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f756146704b821da6d38eae88e48b9c6e19d4ba23d13be975d5302eda8f7b3b7
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:ef80415f80271c7045377d9cb212994ba16f0ef197b00ae6c42f30a5c4e2c5ea
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea58ffab763eb2832ec247dd6950bb9f06c3eba9a785871c428cff34de2202c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2c54821fac94024aa599ca20bffff8456d09caf8bf8230e9279a1da43ab99b3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97633a098e7ad4dd3b61fe26d82257e5d244df4a98bccfd3b80c0d03883af5fc
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": 0.20266666666666666,
6
  "eval_steps": 500,
7
- "global_step": 950,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -968,6 +968,16 @@
968
  "mean_token_accuracy": 0.7399712555110455,
969
  "num_tokens": 4429828.0,
970
  "step": 950
 
 
 
 
 
 
 
 
 
 
971
  }
972
  ],
973
  "logging_steps": 10,
@@ -987,7 +997,7 @@
987
  "attributes": {}
988
  }
989
  },
990
- "total_flos": 2.0993301273191424e+16,
991
  "train_batch_size": 4,
992
  "trial_name": null,
993
  "trial_params": null
 
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,
 
968
  "mean_token_accuracy": 0.7399712555110455,
969
  "num_tokens": 4429828.0,
970
  "step": 950
971
+ },
972
+ {
973
+ "entropy": 0.9969653740525246,
974
+ "epoch": 0.2048,
975
+ "grad_norm": 0.23508235812187195,
976
+ "learning_rate": 9.87047975934885e-05,
977
+ "loss": 1.080200481414795,
978
+ "mean_token_accuracy": 0.7547310657799244,
979
+ "num_tokens": 4478207.0,
980
+ "step": 960
981
  }
982
  ],
983
  "logging_steps": 10,
 
997
  "attributes": {}
998
  }
999
  },
1000
+ "total_flos": 2.121952621246464e+16,
1001
  "train_batch_size": 4,
1002
  "trial_name": null,
1003
  "trial_params": null