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
e940b62
·
verified ·
1 Parent(s): 0a6cad9

Training in progress, step 2760, 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:ce94a5b1e3b400b149d2ecf3ee1b3dd4aa14f31896bc979121978907fffc6905
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7c7b11bf4af22833a30bca65afaaba79466bcb38e6ef88ccb1f32aefce0eef
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8664e7824d8b3bba40659baf27145335ca033b25b9896ed5512f2a1eabe9df23
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b105f6fb327ecc7d00721fe2e2478c9eb4640cd475c5d6a8bad802527512e7
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b4620901f2758e01da843da2db128a11d9df79e7a18131b8f46a15775daebc4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d298977f46940ce930a1610734fdbd09ff3ff7d8a1f64dff4330d9526aec19
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a7f63523305b465edcf4a901415b1488702abd4e2aa16500e27bb14080a8b45
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7657da79e8e0597c4348d0d623a98f036b4edefab04eefd8b1bf7b9cbe9182
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": 0.5866666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2768,6 +2768,16 @@
2768
  "mean_token_accuracy": 0.7488874278962612,
2769
  "num_tokens": 12776988.0,
2770
  "step": 2750
 
 
 
 
 
 
 
 
 
 
2771
  }
2772
  ],
2773
  "logging_steps": 10,
@@ -2787,7 +2797,7 @@
2787
  "attributes": {}
2788
  }
2789
  },
2790
- "total_flos": 6.057115748971008e+16,
2791
  "train_batch_size": 4,
2792
  "trial_name": null,
2793
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5888,
6
  "eval_steps": 500,
7
+ "global_step": 2760,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2768
  "mean_token_accuracy": 0.7488874278962612,
2769
  "num_tokens": 12776988.0,
2770
  "step": 2750
2771
+ },
2772
+ {
2773
+ "entropy": 0.8518887549638748,
2774
+ "epoch": 0.5888,
2775
+ "grad_norm": 0.2686164677143097,
2776
+ "learning_rate": 8.295536124631385e-05,
2777
+ "loss": 0.9314091682434082,
2778
+ "mean_token_accuracy": 0.7844551488757133,
2779
+ "num_tokens": 12821354.0,
2780
+ "step": 2760
2781
  }
2782
  ],
2783
  "logging_steps": 10,
 
2797
  "attributes": {}
2798
  }
2799
  },
2800
+ "total_flos": 6.07747536267479e+16,
2801
  "train_batch_size": 4,
2802
  "trial_name": null,
2803
  "trial_params": null