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
5ac2de3
·
verified ·
1 Parent(s): 8c84ffb

Training in progress, step 1010, 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:fe49e42d2a302fdbcf09ea92f07fe293c8a2bb0395d8aa383cabbfd0daa5d35a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7801abd00974aaa08bac2050addd05582358ba8d6fba1fdffd081f457f7cbbd0
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84f336374c73eaa3e0cffed8db4372651cf36e031d49c3a3793598ee23bfe1cd
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f976700ee39917a70e7455594093124179a6b8219d40c681b879f6c2f647e3
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:d9df127ffff72d847710ffee4153c8826030d8229752a93a09e90ab015bde8e0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9391dd9f8ca951b26f2722de8cb55b8ef3514b03d49ff246c82d67b2b3a704
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12bcd1ca048dbaba0d04fdf16b335c31344751cacaba7e0f860e95741fdac905
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c940e54a0db6643b85375ae76e99b254a9a6e56275e3458b83592cf6e135219
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": 0.21333333333333335,
6
  "eval_steps": 500,
7
- "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1018,6 +1018,16 @@
1018
  "mean_token_accuracy": 0.762999877333641,
1019
  "num_tokens": 4670070.0,
1020
  "step": 1000
 
 
 
 
 
 
 
 
 
 
1021
  }
1022
  ],
1023
  "logging_steps": 10,
@@ -1037,7 +1047,7 @@
1037
  "attributes": {}
1038
  }
1039
  },
1040
- "total_flos": 2.2093569331224576e+16,
1041
  "train_batch_size": 4,
1042
  "trial_name": null,
1043
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.21546666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 1010,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1018
  "mean_token_accuracy": 0.762999877333641,
1019
  "num_tokens": 4670070.0,
1020
  "step": 1000
1021
+ },
1022
+ {
1023
+ "entropy": 0.9205634713172912,
1024
+ "epoch": 0.21546666666666667,
1025
+ "grad_norm": 0.2580691874027252,
1026
+ "learning_rate": 9.850182547917686e-05,
1027
+ "loss": 1.0361328125,
1028
+ "mean_token_accuracy": 0.77038114964962,
1029
+ "num_tokens": 4713754.0,
1030
+ "step": 1010
1031
  }
1032
  ],
1033
  "logging_steps": 10,
 
1047
  "attributes": {}
1048
  }
1049
  },
1050
+ "total_flos": 2.229555234377011e+16,
1051
  "train_batch_size": 4,
1052
  "trial_name": null,
1053
  "trial_params": null