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
35da4b9
·
verified ·
1 Parent(s): 9b38704

Training in progress, step 3810, 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 sha256:1860091f6919f7735d38c70ff6a7843b1af1fc98d35d421517ebb72d27e35a8b
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c1ce9e1a04a4e94156e8ac42d0bd48ff84ba7e03c21682e54284c778cdbba2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3baddf5b574a25960405c4dfad82684c402c2fe9a1d6829f286d4a343034acae
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292da49218a254bdcca11769d6f4ec78035f17971565fea98ba017d49a415d4f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d887e8675b7564c41377da8b4aef48cfb83a5ecf6b9df33bf5c9bc0f1798223
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbc491c6954e3f7bb195bc86aee98fb85063edc4b42af22e4ea74a1fd46d728
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3adc0426eabe638b25789d83999511b320746a743905b8e6521fb7ada8e58d21
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd088300697d6b3e51ea0e890fdaa13b137c559ea6a9e7eaf72b56e9c624dd9
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": 0.8106666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3800,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3818,6 +3818,16 @@
3818
  "mean_token_accuracy": 0.7626087903976441,
3819
  "num_tokens": 17705375.0,
3820
  "step": 3800
 
 
 
 
 
 
 
 
 
 
3821
  }
3822
  ],
3823
  "logging_steps": 10,
@@ -3837,7 +3847,7 @@
3837
  "attributes": {}
3838
  }
3839
  },
3840
- "total_flos": 8.382420285614285e+16,
3841
  "train_batch_size": 4,
3842
  "trial_name": null,
3843
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8128,
6
  "eval_steps": 500,
7
+ "global_step": 3810,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3818
  "mean_token_accuracy": 0.7626087903976441,
3819
  "num_tokens": 17705375.0,
3820
  "step": 3800
3821
+ },
3822
+ {
3823
+ "entropy": 1.0885871052742004,
3824
+ "epoch": 0.8128,
3825
+ "grad_norm": 0.24882915616035461,
3826
+ "learning_rate": 6.743487459046971e-05,
3827
+ "loss": 1.1456743240356446,
3828
+ "mean_token_accuracy": 0.7413103066384792,
3829
+ "num_tokens": 17751890.0,
3830
+ "step": 3810
3831
  }
3832
  ],
3833
  "logging_steps": 10,
 
3847
  "attributes": {}
3848
  }
3849
  },
3850
+ "total_flos": 8.405295111864422e+16,
3851
  "train_batch_size": 4,
3852
  "trial_name": null,
3853
  "trial_params": null