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
16bd6c8
·
verified ·
1 Parent(s): df7b06e

Training in progress, step 780, 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:ad62e2b74554573c36e4e3440f7df6858d927c779bb32c2b00e20824529e7ee4
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea577c1e1cb2ab96b4187304e772b7c0c62b214515b98c634e0447d1397314e5
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52e0c21fbd09091df69cd791b70a189dabb850f2ab31c6e5612663d577593b28
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da1d94d2bd26b542776b6d5ae7061491c3beab87ea6a56fc99eec9b32e1e4e7
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:d49f0bd33096188e4746ed896130bf2f1f38416a2ac5ac5c907d539f510ed389
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c303dc67477d1cf76a046a76e0eb8fe002589b994e9d9341cca80061c4966e4e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a094df716bc33e4f28da09e88cd908e7c42805aa24ce6e5025451d29a3900ce0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3a6f8ed8cf049ad4e1776aa7ec88aa3130e1b2d34600187b9f9290f4bae1d4
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": 0.16426666666666667,
6
  "eval_steps": 500,
7
- "global_step": 770,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -788,6 +788,16 @@
788
  "mean_token_accuracy": 0.7535254985094071,
789
  "num_tokens": 3578130.0,
790
  "step": 770
 
 
 
 
 
 
 
 
 
 
791
  }
792
  ],
793
  "logging_steps": 10,
@@ -807,7 +817,7 @@
807
  "attributes": {}
808
  }
809
  },
810
- "total_flos": 1.6928011267777536e+16,
811
  "train_batch_size": 4,
812
  "trial_name": null,
813
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1664,
6
  "eval_steps": 500,
7
+ "global_step": 780,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
788
  "mean_token_accuracy": 0.7535254985094071,
789
  "num_tokens": 3578130.0,
790
  "step": 770
791
+ },
792
+ {
793
+ "entropy": 0.9679107010364533,
794
+ "epoch": 0.1664,
795
+ "grad_norm": 0.3156932294368744,
796
+ "learning_rate": 9.931431181541426e-05,
797
+ "loss": 1.0209306716918944,
798
+ "mean_token_accuracy": 0.7623399093747139,
799
+ "num_tokens": 3625602.0,
800
+ "step": 780
801
  }
802
  ],
803
  "logging_steps": 10,
 
817
  "attributes": {}
818
  }
819
  },
820
+ "total_flos": 1.7155506880533504e+16,
821
  "train_batch_size": 4,
822
  "trial_name": null,
823
  "trial_params": null