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
eda77c0
·
verified ·
1 Parent(s): 59b0c19

Training in progress, step 950, 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:dbc2ee489f47ea596b321bd7995f2bac7a52945490c14f0a6880ce6475d80ec2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ba389655fb787a8530f6928885d73c045df0e160ac83ca56fbeca9c7f5df85
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:498c9374220fd4c1941619dd583dcc81dcf9e09c8a8c7c45e3d9c9a0492d40c8
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d84ffd8f3da9bc88deeb5e1e70716cb973af7c8848fb205649a545ebe5213ed
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:a8891a0f6c9651643dc673aa37b083ae9f9a5618485ed2fa5e42864224aba8ac
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef80415f80271c7045377d9cb212994ba16f0ef197b00ae6c42f30a5c4e2c5ea
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c75037f232440becd46b56e7118ddd0d9e982d54506ff3f4a917d7faef47618
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c54821fac94024aa599ca20bffff8456d09caf8bf8230e9279a1da43ab99b3
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": 0.20053333333333334,
6
  "eval_steps": 500,
7
- "global_step": 940,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -958,6 +958,16 @@
958
  "mean_token_accuracy": 0.780703829228878,
959
  "num_tokens": 4379939.0,
960
  "step": 940
 
 
 
 
 
 
 
 
 
 
961
  }
962
  ],
963
  "logging_steps": 10,
@@ -977,7 +987,7 @@
977
  "attributes": {}
978
  }
979
  },
980
- "total_flos": 2.0759848815243264e+16,
981
  "train_batch_size": 4,
982
  "trial_name": null,
983
  "trial_params": null
 
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,
 
958
  "mean_token_accuracy": 0.780703829228878,
959
  "num_tokens": 4379939.0,
960
  "step": 940
961
+ },
962
+ {
963
+ "entropy": 1.0914236083626747,
964
+ "epoch": 0.20266666666666666,
965
+ "grad_norm": 0.28582993149757385,
966
+ "learning_rate": 9.874364326083216e-05,
967
+ "loss": 1.1933195114135742,
968
+ "mean_token_accuracy": 0.7399712555110455,
969
+ "num_tokens": 4429828.0,
970
+ "step": 950
971
  }
972
  ],
973
  "logging_steps": 10,
 
987
  "attributes": {}
988
  }
989
  },
990
+ "total_flos": 2.0993301273191424e+16,
991
  "train_batch_size": 4,
992
  "trial_name": null,
993
  "trial_params": null