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
7b777d1
·
verified ·
1 Parent(s): dee6e7b

Training in progress, step 2350, 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:d480df01085fda8e13898dcd02006b3a08c9d4f450c7947f0b536f4ba4218d23
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79f8bb9d5f7dc15c04fa86ab72d4b1d25c7f112febc4658c22f8f3fae5a8034
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b24fa3a485109dd9aa3a79a39bcf9655c86072536e74917dbb45ac4544b7d65e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51af2c09efe30f822ec7955da569a14d92bc67173a2ad6375838b7d2a18fde9a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:447ffe73e3b0b4023df1f0ea9045a31fdc44e7e7c474029cf8a4e5e354703254
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf2f0f561cb542533e93676afd9598125fe0373b36b6381b7d48a9e8d03bca97
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4cd9ad4146890a32a97263ee3577f249bc631d6cdfc423e198c1ac66a39a570
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632011de483a2102d4f0d1947c4329c3cd8dce410c54d596291881aacfbc03d9
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": 0.4992,
6
  "eval_steps": 500,
7
- "global_step": 2340,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2358,6 +2358,16 @@
2358
  "mean_token_accuracy": 0.7492594376206398,
2359
  "num_tokens": 10876689.0,
2360
  "step": 2340
 
 
 
 
 
 
 
 
 
 
2361
  }
2362
  ],
2363
  "logging_steps": 10,
@@ -2377,7 +2387,7 @@
2377
  "attributes": {}
2378
  }
2379
  },
2380
- "total_flos": 5.157450085202842e+16,
2381
  "train_batch_size": 4,
2382
  "trial_name": null,
2383
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5013333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 2350,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2358
  "mean_token_accuracy": 0.7492594376206398,
2359
  "num_tokens": 10876689.0,
2360
  "step": 2340
2361
+ },
2362
+ {
2363
+ "entropy": 1.0402933657169342,
2364
+ "epoch": 0.5013333333333333,
2365
+ "grad_norm": 0.2032317966222763,
2366
+ "learning_rate": 8.794263328847975e-05,
2367
+ "loss": 1.1533799171447754,
2368
+ "mean_token_accuracy": 0.7475039146840572,
2369
+ "num_tokens": 10925395.0,
2370
+ "step": 2350
2371
  }
2372
  ],
2373
  "logging_steps": 10,
 
2387
  "attributes": {}
2388
  }
2389
  },
2390
+ "total_flos": 5.181426161804698e+16,
2391
  "train_batch_size": 4,
2392
  "trial_name": null,
2393
  "trial_params": null