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
4ec7352
·
verified ·
1 Parent(s): c656d96

Training in progress, step 830, 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 sha256:8b5700b8619200a633a3da7d7da99f201dba6d7c0fb71cf982d089608cd173b8
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eaf90d8cedec1ff12e3e7c4b352bab22257da6d241c9c9cce6def7e45c4e944
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bcba4099322e48aa173bc81b00571e6dbd53ec16301c6de3d79d78d8589f45b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d00d96532f14bdf7f0e2c9cb1dfcf7a97f78ede6c375da59043178fbbc28c436
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6192913e0d79f6b42d15c29949dbb5c38558770d20866a20c4955c216e1cbb06
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad3e5c5bedc41596a899e1b7ab60b0934c2bc3efe6a53966c7c66bd51d2b43e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e568151bce63cf2a47418ee600b11181a87b25acaab164421ab3d3363afa7a7a
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc403043ab056906986eef9421e72db598abb0832c8e1fb3f2ec3a4f9bbead3
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": 0.17493333333333333,
6
  "eval_steps": 500,
7
- "global_step": 820,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -838,6 +838,16 @@
838
  "mean_token_accuracy": 0.7301450505852699,
839
  "num_tokens": 3810938.0,
840
  "step": 820
 
 
 
 
 
 
 
 
 
 
841
  }
842
  ],
843
  "logging_steps": 10,
@@ -857,7 +867,7 @@
857
  "attributes": {}
858
  }
859
  },
860
- "total_flos": 1.805221484900352e+16,
861
  "train_batch_size": 4,
862
  "trial_name": null,
863
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.17706666666666668,
6
  "eval_steps": 500,
7
+ "global_step": 830,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
838
  "mean_token_accuracy": 0.7301450505852699,
839
  "num_tokens": 3810938.0,
840
  "step": 820
841
+ },
842
+ {
843
+ "entropy": 1.0070038817822933,
844
+ "epoch": 0.17706666666666668,
845
+ "grad_norm": 0.2899021506309509,
846
+ "learning_rate": 9.916411154823433e-05,
847
+ "loss": 1.146003818511963,
848
+ "mean_token_accuracy": 0.7569455504417419,
849
+ "num_tokens": 3857657.0,
850
+ "step": 830
851
  }
852
  ],
853
  "logging_steps": 10,
 
867
  "attributes": {}
868
  }
869
  },
870
+ "total_flos": 1.8272266658236416e+16,
871
  "train_batch_size": 4,
872
  "trial_name": null,
873
  "trial_params": null