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
abbafd8
·
verified ·
1 Parent(s): 22e1b25

Training in progress, step 2700, 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:d5eb2ee973879112097d1758432b9b2e61786fee31e6bd869380647709b83ef3
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d26b6d4e8857a241279a673f1c2e62300163c947b92176bc79abbbb2cd574f98
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53b11da829c5f5458da3adbc60f1c036d0dde99453994139b78ffe2e40ce6886
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653fd3d1560e6ed55196a4b59f47188184d66e2be2bda7d4c31010e1c729538e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c2f4f1b1d31d7a26a28599e389b397c7f30000aa564ac18d3b8159b626b2933
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dffb3dd30fdb978ab869b0050adff160719c68d4feea033c48128d7566af5c9
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d31de6314a1235f5b5377eb57bfa8665def9dea6396aa59075ea46f0656add58
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2150a0e3242c02623edce45b81d60969b212a524cc98cbdacfe85d8a97935109
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": 0.5738666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2690,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2708,6 +2708,16 @@
2708
  "mean_token_accuracy": 0.7823046505451202,
2709
  "num_tokens": 12496420.0,
2710
  "step": 2690
 
 
 
 
 
 
 
 
 
 
2711
  }
2712
  ],
2713
  "logging_steps": 10,
@@ -2727,7 +2737,7 @@
2727
  "attributes": {}
2728
  }
2729
  },
2730
- "total_flos": 5.922995712273101e+16,
2731
  "train_batch_size": 4,
2732
  "trial_name": null,
2733
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.576,
6
  "eval_steps": 500,
7
+ "global_step": 2700,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2708
  "mean_token_accuracy": 0.7823046505451202,
2709
  "num_tokens": 12496420.0,
2710
  "step": 2690
2711
+ },
2712
+ {
2713
+ "entropy": 0.9863057106733322,
2714
+ "epoch": 0.576,
2715
+ "grad_norm": 0.2574012279510498,
2716
+ "learning_rate": 8.372914715119269e-05,
2717
+ "loss": 1.0647315979003906,
2718
+ "mean_token_accuracy": 0.7581366948783398,
2719
+ "num_tokens": 12541298.0,
2720
+ "step": 2700
2721
  }
2722
  ],
2723
  "logging_steps": 10,
 
2737
  "attributes": {}
2738
  }
2739
  },
2740
+ "total_flos": 5.946095835240038e+16,
2741
  "train_batch_size": 4,
2742
  "trial_name": null,
2743
  "trial_params": null