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
36d977e
·
verified ·
1 Parent(s): 456e422

Training in progress, step 2340, 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:e3082fb894dbd61eebf0ce8e1e0178955754520e516c02e6d4de3d6929e7e021
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d480df01085fda8e13898dcd02006b3a08c9d4f450c7947f0b536f4ba4218d23
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a766541713bb5cb997e2d6a26f04a7fb9f56a20c1d508ecbbc0e6180d6addcb
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24fa3a485109dd9aa3a79a39bcf9655c86072536e74917dbb45ac4544b7d65e
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:bcdbf33be2e859933ffe1b4d6cf7b3a3cebb6e75037e3ceecd09032fe2f44d39
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447ffe73e3b0b4023df1f0ea9045a31fdc44e7e7c474029cf8a4e5e354703254
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5defde01bc6738c098494a3315f8e057dccd48f0861e19102cb32c194b34b83c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cd9ad4146890a32a97263ee3577f249bc631d6cdfc423e198c1ac66a39a570
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": 0.49706666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2330,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2348,6 +2348,16 @@
2348
  "mean_token_accuracy": 0.7838068321347237,
2349
  "num_tokens": 10830340.0,
2350
  "step": 2330
 
 
 
 
 
 
 
 
 
 
2351
  }
2352
  ],
2353
  "logging_steps": 10,
@@ -2367,7 +2377,7 @@
2367
  "attributes": {}
2368
  }
2369
  },
2370
- "total_flos": 5.134250831680512e+16,
2371
  "train_batch_size": 4,
2372
  "trial_name": null,
2373
  "trial_params": null
 
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,
 
2348
  "mean_token_accuracy": 0.7838068321347237,
2349
  "num_tokens": 10830340.0,
2350
  "step": 2330
2351
+ },
2352
+ {
2353
+ "entropy": 0.985354783385992,
2354
+ "epoch": 0.4992,
2355
+ "grad_norm": 0.2665145695209503,
2356
+ "learning_rate": 8.805512066500992e-05,
2357
+ "loss": 1.0852888107299805,
2358
+ "mean_token_accuracy": 0.7492594376206398,
2359
+ "num_tokens": 10876689.0,
2360
+ "step": 2340
2361
  }
2362
  ],
2363
  "logging_steps": 10,
 
2377
  "attributes": {}
2378
  }
2379
  },
2380
+ "total_flos": 5.157450085202842e+16,
2381
  "train_batch_size": 4,
2382
  "trial_name": null,
2383
  "trial_params": null