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
76466c9
·
verified ·
1 Parent(s): 3108a85

Training in progress, step 3720, 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 sha256:8c19cebfd097c52d8252201564a90baf66afce410053d4622b9f9203cd5b323a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a97bc565a5767bf486b326fb87539c2b73753b86934a4ddb313cf730feb54b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad92e45bed68c79521d82d462764b3510cfe038d13ab9c3f853804df03fff512
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f45d3bc13da5779b0fe33e99b0340bc6896ded59993e9ae554de77288bdedce
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:bb26e6ee02aadc7d8c0b2d9ff753d338ee61b3002b03febd1669b67b4ac88115
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5bc8d22a0076e75cd0cfd0dd59bae5e3a04a47d7ee2d978b5c11ccecdeefd8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:112424dfe1d0ba6b6bb7340e2d1c9d55d7aa639fe09b2e797e34b9a13e889a5f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2add9630f63e65a41e9aced9f0fc658b410e16228e2d7cf80cbb7266d64ee8
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": 0.7914666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3710,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3728,6 +3728,16 @@
3728
  "mean_token_accuracy": 0.7794149458408356,
3729
  "num_tokens": 17280617.0,
3730
  "step": 3710
 
 
 
 
 
 
 
 
 
 
3731
  }
3732
  ],
3733
  "logging_steps": 10,
@@ -3747,7 +3757,7 @@
3747
  "attributes": {}
3748
  }
3749
  },
3750
- "total_flos": 8.182288310893978e+16,
3751
  "train_batch_size": 4,
3752
  "trial_name": null,
3753
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7936,
6
  "eval_steps": 500,
7
+ "global_step": 3720,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3728
  "mean_token_accuracy": 0.7794149458408356,
3729
  "num_tokens": 17280617.0,
3730
  "step": 3710
3731
+ },
3732
+ {
3733
+ "entropy": 0.8956944331526756,
3734
+ "epoch": 0.7936,
3735
+ "grad_norm": 0.23321297764778137,
3736
+ "learning_rate": 6.888605682456746e-05,
3737
+ "loss": 1.0033020973205566,
3738
+ "mean_token_accuracy": 0.7758402660489082,
3739
+ "num_tokens": 17326396.0,
3740
+ "step": 3720
3741
  }
3742
  ],
3743
  "logging_steps": 10,
 
3757
  "attributes": {}
3758
  }
3759
  },
3760
+ "total_flos": 8.202966944748749e+16,
3761
  "train_batch_size": 4,
3762
  "trial_name": null,
3763
  "trial_params": null