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
f761996
·
verified ·
1 Parent(s): d8d63c5

Training in progress, step 3770, 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 sha256:35cbb294ca131bf71e08da9541046263bc6cf9c0cded313a47a61d42609b7d66
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c1a161977e9ae31c5e7068aa29473c8a56d1e4487ac3f26b676df25a23cf6a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3008f9a48d2b37d474060de2dad5c0aca2cda94e9e3b59cbb5699f6e0eedec4
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d110d205e7820b84308ba24c1b34260b2fc80a37fe7d91d947d9f51077ecbb74
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:cf42325a1cd17968c48d9389be187faf9cddbbb4ca6e358455bb5548a8f7fb0c
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36ee8ffd6e236e454a94766e95e7bbeff897da092727caafc81f8a4d30246d6
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf8dc1d66d843e6daf41e0f9a415fde2893c0bdb3049573e320e768417beee06
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e0ba4e5eaa10dc017da6a4a30c7d09ec7aae6a3438aa93ce0f4d5ab71016c7e
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": 0.8021333333333334,
6
  "eval_steps": 500,
7
- "global_step": 3760,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3778,6 +3778,16 @@
3778
  "mean_token_accuracy": 0.7684256717562675,
3779
  "num_tokens": 17519106.0,
3780
  "step": 3760
 
 
 
 
 
 
 
 
 
 
3781
  }
3782
  ],
3783
  "logging_steps": 10,
@@ -3797,7 +3807,7 @@
3797
  "attributes": {}
3798
  }
3799
  },
3800
- "total_flos": 8.29500696186962e+16,
3801
  "train_batch_size": 4,
3802
  "trial_name": null,
3803
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8042666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 3770,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3778
  "mean_token_accuracy": 0.7684256717562675,
3779
  "num_tokens": 17519106.0,
3780
  "step": 3760
3781
+ },
3782
+ {
3783
+ "entropy": 0.9076099701225757,
3784
+ "epoch": 0.8042666666666667,
3785
+ "grad_norm": 0.28303810954093933,
3786
+ "learning_rate": 6.80820173658624e-05,
3787
+ "loss": 1.0061184883117675,
3788
+ "mean_token_accuracy": 0.774385878443718,
3789
+ "num_tokens": 17563524.0,
3790
+ "step": 3770
3791
  }
3792
  ],
3793
  "logging_steps": 10,
 
3807
  "attributes": {}
3808
  }
3809
  },
3810
+ "total_flos": 8.315729753880883e+16,
3811
  "train_batch_size": 4,
3812
  "trial_name": null,
3813
  "trial_params": null