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
7c85822
·
verified ·
1 Parent(s): 4387c35

Training in progress, step 880, 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:ddb73b24f7c24360f86d65b2aae05a3ca8d784fd150ca6942d5aa861f92a3940
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a89201e2981c3443e4690a2b08cdbb901b7cbf35b56a2251f389bdca44adfb9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:036591dbbb25389e3e01d287cccfbe6918a85cccfcf7c4483d9a8e91c3447de5
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4fd8a0f4ce699737bf6a62e9fae62ede5d935346488525d3b70889f69e3be62
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:bd521810c87442802b38d9ddb25a7dac561287aff02c46dc14fcbc8a24272fb9
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a5b399ec19b0ca4e18f925ddb3741df1a49a5fa34b3dca1198ca2d343e4cf0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:addf757fbcba66917f74ece6118fc7351d4fc2adf0697c9d475ff88757237430
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c456df62378afb46dea59259d93eb8a7b5767c6590640903dc8ecd47bb7fb3
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": 0.1856,
6
  "eval_steps": 500,
7
- "global_step": 870,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -888,6 +888,16 @@
888
  "mean_token_accuracy": 0.7244490720331669,
889
  "num_tokens": 4050343.0,
890
  "step": 870
 
 
 
 
 
 
 
 
 
 
891
  }
892
  ],
893
  "logging_steps": 10,
@@ -907,7 +917,7 @@
907
  "attributes": {}
908
  }
909
  },
910
- "total_flos": 1.9197380036760576e+16,
911
  "train_batch_size": 4,
912
  "trial_name": null,
913
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.18773333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 880,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
888
  "mean_token_accuracy": 0.7244490720331669,
889
  "num_tokens": 4050343.0,
890
  "step": 870
891
+ },
892
+ {
893
+ "entropy": 1.0595085561275481,
894
+ "epoch": 0.18773333333333334,
895
+ "grad_norm": 0.294251948595047,
896
+ "learning_rate": 9.89991851678619e-05,
897
+ "loss": 1.1476259231567383,
898
+ "mean_token_accuracy": 0.7438870698213578,
899
+ "num_tokens": 4099181.0,
900
+ "step": 880
901
  }
902
  ],
903
  "logging_steps": 10,
 
917
  "attributes": {}
918
  }
919
  },
920
+ "total_flos": 1.9434887835611136e+16,
921
  "train_batch_size": 4,
922
  "trial_name": null,
923
  "trial_params": null