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
1c8b9fd
·
verified ·
1 Parent(s): 4d39397

Training in progress, step 2550, 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 sha256:44bc77c6565271feab7e3c7b4dcf6309ff4407c21e6ee1c8bee91da083bfa41e
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7397b1813b8f8212bef99779310a1f431833e1b1e3988acb861b9fd9379033
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:668ba5cce3c84a65e433cf033a6e5b75c109903f41b4f8b35717ca47a06cab54
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcbefccd35763118e3b705932a37bfb88b4cd8cfd3bab48c581733431394ee56
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:a6062a8762014575d040a3bcc196b9278a1f33f78579fc863d474a54c89e88e0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5fa4c0df4659fb420e7780836b47a9622b8a5149fd210efcc998d7302ba3d3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a192b1ac6e4741adc1d8201252f5b9e6d728173683d919e5e81f11d58e77175d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1246307382e43171b8de79290a2c836f7e18bb028472b3c3ce4ae92e84622dc3
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": 0.5418666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2540,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2558,6 +2558,16 @@
2558
  "mean_token_accuracy": 0.7522218823432922,
2559
  "num_tokens": 11801605.0,
2560
  "step": 2540
 
 
 
 
 
 
 
 
 
 
2561
  }
2562
  ],
2563
  "logging_steps": 10,
@@ -2577,7 +2587,7 @@
2577
  "attributes": {}
2578
  }
2579
  },
2580
- "total_flos": 5.599219096999219e+16,
2581
  "train_batch_size": 4,
2582
  "trial_name": null,
2583
  "trial_params": null
 
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,
 
2558
  "mean_token_accuracy": 0.7522218823432922,
2559
  "num_tokens": 11801605.0,
2560
  "step": 2540
2561
+ },
2562
+ {
2563
+ "entropy": 1.0214832991361618,
2564
+ "epoch": 0.544,
2565
+ "grad_norm": 0.265127569437027,
2566
+ "learning_rate": 8.559924985643436e-05,
2567
+ "loss": 1.1042506217956543,
2568
+ "mean_token_accuracy": 0.7507105216383934,
2569
+ "num_tokens": 11847802.0,
2570
+ "step": 2550
2571
  }
2572
  ],
2573
  "logging_steps": 10,
 
2587
  "attributes": {}
2588
  }
2589
  },
2590
+ "total_flos": 5.619448038607258e+16,
2591
  "train_batch_size": 4,
2592
  "trial_name": null,
2593
  "trial_params": null