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
1df2e25
·
verified ·
1 Parent(s): 650c864

Training in progress, step 810, 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:bd2cda9c9230d2d0799a98d4cdf1dadae0585a355490e9c0c3a1041b4b0d60cc
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049743bfcb7f759734cbd629e6485aed0be4a34fa8ec7e7c7cc378b82b68bff1
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88805d5d925cc6ea67c7a661afd5da8cfb504bbdcccb54925a7884fd28adab48
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9b5e379d731b076e4482b67a806d92f720224e0087cf953a8eba2c68fd4aee
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dfadc0aadf8692780568210f6a28c96f4ccf2481b5f4cc7a3521dab721743a4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41f0c2e372afcf75476546e73c625079d8911a111dfbe4cceaa100a9a3d7fe3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf66822e6e71148b00e80d5a766aa265c0ba2c6ee19c08772affaaad1c0f1cde
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19dce1af1dc26cccf0df5a110280acf30d37386795f6a4e614ee2f72176a997
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": 0.17066666666666666,
6
  "eval_steps": 500,
7
- "global_step": 800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -818,6 +818,16 @@
818
  "mean_token_accuracy": 0.7589392751455307,
819
  "num_tokens": 3717893.0,
820
  "step": 800
 
 
 
 
 
 
 
 
 
 
821
  }
822
  ],
823
  "logging_steps": 10,
@@ -837,7 +847,7 @@
837
  "attributes": {}
838
  }
839
  },
840
- "total_flos": 1.7602666792169472e+16,
841
  "train_batch_size": 4,
842
  "trial_name": null,
843
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1728,
6
  "eval_steps": 500,
7
+ "global_step": 810,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
818
  "mean_token_accuracy": 0.7589392751455307,
819
  "num_tokens": 3717893.0,
820
  "step": 800
821
+ },
822
+ {
823
+ "entropy": 0.9766084000468254,
824
+ "epoch": 0.1728,
825
+ "grad_norm": 0.33309969305992126,
826
+ "learning_rate": 9.92259614070538e-05,
827
+ "loss": 1.0395455360412598,
828
+ "mean_token_accuracy": 0.7545588746666908,
829
+ "num_tokens": 3764739.0,
830
+ "step": 810
831
  }
832
  ],
833
  "logging_steps": 10,
 
847
  "attributes": {}
848
  }
849
  },
850
+ "total_flos": 1.7831135686742016e+16,
851
  "train_batch_size": 4,
852
  "trial_name": null,
853
  "trial_params": null