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
f1517c7
·
verified ·
1 Parent(s): 1b4eccc

Training in progress, step 1620, 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 sha256:18628fff5888b391bc6d563651a70135cf360160b9e4b8c54a931c505add45cb
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986a5524833904be4f85327276cbfed0d29c1b1dc1f6b84bc1e293043990a953
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:565117ea44dd9d3c592e4adacb279e4ff3cbcab209baeac22bb40b1d188fb170
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04ba6ece78fe5204a7ad68c5705eedc9ac7aea1d78b39c6510b69216d950858
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:334bc8ec02e58e4ba446fec4b8806a7cb93f1b5dce895a4a76fdea72b35e04c7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392635ad4fd5ad7587c3b5f69ebc5215a0bcf1764ac9342829ece6a1eacb5ba3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e4a19270e2b79c7632a330b85d9c8b414e7539580876dbcc408ebf95a863643
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cf0e9d5987591210144464ea7f678fcc231d36808fd9149fbbcc5ce5a883bd
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": 0.34346666666666664,
6
  "eval_steps": 500,
7
- "global_step": 1610,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1628,6 +1628,16 @@
1628
  "mean_token_accuracy": 0.7388298735022545,
1629
  "num_tokens": 7485267.0,
1630
  "step": 1610
 
 
 
 
 
 
 
 
 
 
1631
  }
1632
  ],
1633
  "logging_steps": 10,
@@ -1647,7 +1657,7 @@
1647
  "attributes": {}
1648
  }
1649
  },
1650
- "total_flos": 3.5487369026297856e+16,
1651
  "train_batch_size": 4,
1652
  "trial_name": null,
1653
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.3456,
6
  "eval_steps": 500,
7
+ "global_step": 1620,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1628
  "mean_token_accuracy": 0.7388298735022545,
1629
  "num_tokens": 7485267.0,
1630
  "step": 1610
1631
+ },
1632
+ {
1633
+ "entropy": 0.8908423334360123,
1634
+ "epoch": 0.3456,
1635
+ "grad_norm": 0.3009212613105774,
1636
+ "learning_rate": 9.487866491545554e-05,
1637
+ "loss": 0.9948520660400391,
1638
+ "mean_token_accuracy": 0.7739639699459075,
1639
+ "num_tokens": 7527918.0,
1640
+ "step": 1620
1641
  }
1642
  ],
1643
  "logging_steps": 10,
 
1657
  "attributes": {}
1658
  }
1659
  },
1660
+ "total_flos": 3.568690081056461e+16,
1661
  "train_batch_size": 4,
1662
  "trial_name": null,
1663
  "trial_params": null