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
000eaf5
·
verified ·
1 Parent(s): c6759e3

Training in progress, step 2560, 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 sha256:4a7397b1813b8f8212bef99779310a1f431833e1b1e3988acb861b9fd9379033
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33bb84a80d6102dd7d4f044f378dcefdea3d115107fb87b8c1f80a67d238faec
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcbefccd35763118e3b705932a37bfb88b4cd8cfd3bab48c581733431394ee56
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff9917a66c9118c7f2ffaa8fa676ea6489c4ec095f0bd064ff0e16c54b67ffc
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d5fa4c0df4659fb420e7780836b47a9622b8a5149fd210efcc998d7302ba3d3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb54d46b1e27cf8f8b88e5c7edb0dcd5859cf8467f70a7ed5ca65363e3a057a8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1246307382e43171b8de79290a2c836f7e18bb028472b3c3ce4ae92e84622dc3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00104bbfecd1f30a0d96466205b66aa9e741272468e0fd680c03668919e603af
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": 0.544,
6
  "eval_steps": 500,
7
- "global_step": 2550,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2568,6 +2568,16 @@
2568
  "mean_token_accuracy": 0.7507105216383934,
2569
  "num_tokens": 11847802.0,
2570
  "step": 2550
 
 
 
 
 
 
 
 
 
 
2571
  }
2572
  ],
2573
  "logging_steps": 10,
@@ -2587,7 +2597,7 @@
2587
  "attributes": {}
2588
  }
2589
  },
2590
- "total_flos": 5.619448038607258e+16,
2591
  "train_batch_size": 4,
2592
  "trial_name": null,
2593
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5461333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 2560,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2568
  "mean_token_accuracy": 0.7507105216383934,
2569
  "num_tokens": 11847802.0,
2570
  "step": 2550
2571
+ },
2572
+ {
2573
+ "entropy": 0.9052864700555802,
2574
+ "epoch": 0.5461333333333334,
2575
+ "grad_norm": 0.21368557214736938,
2576
+ "learning_rate": 8.54775069943376e-05,
2577
+ "loss": 0.9432812690734863,
2578
+ "mean_token_accuracy": 0.7738461554050445,
2579
+ "num_tokens": 11895685.0,
2580
+ "step": 2560
2581
  }
2582
  ],
2583
  "logging_steps": 10,
 
2597
  "attributes": {}
2598
  }
2599
  },
2600
+ "total_flos": 5.642576098367078e+16,
2601
  "train_batch_size": 4,
2602
  "trial_name": null,
2603
  "trial_params": null