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
39a964d
·
verified ·
1 Parent(s): 4d15551

Training in progress, step 2390, 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 sha256:3cfc94df1948867d085e105e320b2b8c6a0b046ddc60086e8e828c5ef65d8091
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f6c4fba22cc3ffa68c73da8a65e6ac0292a8494736ebd9cf01fa275521ba15
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d80edb3dc59cf7129b1025d5afc6331bbbf1ef729a98c0f8de3864e318e2e08b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8985561580e2a3a135e83bff5598977e85d195297db16c1cf76c514be2eeb2b0
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:bd45251763048e57f61324cd3793c9364158d2cf969dd6a4eac12b56f3101007
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6396f47afe3aa623c294a866435dbc7a9bb028716704d2f2f48e0b2b87a290f
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c6eec566df00974ba222ba4aead107902646903b39998420f3f73fc62064416
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4392e26fd215c89319acad5af1671eb7abce7b3a173715912a2f15034a0d89b
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": 0.5077333333333334,
6
  "eval_steps": 500,
7
- "global_step": 2380,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2398,6 +2398,16 @@
2398
  "mean_token_accuracy": 0.7643568038940429,
2399
  "num_tokens": 11065494.0,
2400
  "step": 2380
 
 
 
 
 
 
 
 
 
 
2401
  }
2402
  ],
2403
  "logging_steps": 10,
@@ -2417,7 +2427,7 @@
2417
  "attributes": {}
2418
  }
2419
  },
2420
- "total_flos": 5.248290622603469e+16,
2421
  "train_batch_size": 4,
2422
  "trial_name": null,
2423
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5098666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 2390,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2398
  "mean_token_accuracy": 0.7643568038940429,
2399
  "num_tokens": 11065494.0,
2400
  "step": 2380
2401
+ },
2402
+ {
2403
+ "entropy": 1.0124794401228427,
2404
+ "epoch": 0.5098666666666667,
2405
+ "grad_norm": 0.2306586503982544,
2406
+ "learning_rate": 8.74881512539534e-05,
2407
+ "loss": 1.159686279296875,
2408
+ "mean_token_accuracy": 0.7495349571108818,
2409
+ "num_tokens": 11117249.0,
2410
+ "step": 2390
2411
  }
2412
  ],
2413
  "logging_steps": 10,
 
2427
  "attributes": {}
2428
  }
2429
  },
2430
+ "total_flos": 5.271640374332621e+16,
2431
  "train_batch_size": 4,
2432
  "trial_name": null,
2433
  "trial_params": null