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
12913ae
·
verified ·
1 Parent(s): e0cae4f

Training in progress, step 2250, 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:cbf8f35e02b47be1e56ca46ef473195ff9bd66be3066b8b56f63e7ee5fdcce16
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba6e2497236b1145ee0e78b4f2bbc1c11d33a3b77643e59f88f3d01a4970805
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd0fa2722f88764cd80539c3c5b906b8436dfcc9ac950d5e32dfa77ed4c7ee9d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d02b0eb3156392a7267ca9b91c8bac2001dc6268888c9d311759028001f807
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42e11840fa8572f47268c4bc4265601f3d257b8489303f069446375c7e013c53
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d475cb4dc00c25b48dcfcd87f69861b135a674dcb849b4fbe0e8df62dd6245de
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7191e8aec39dbfe02c73ac365799b6b127692ceda3fc10016619123797f49d7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939bba2fb6c84d79f44a1f88c0553fa3589d1a37451551a0adfee96fe284fc1f
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": 0.47786666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2240,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2258,6 +2258,16 @@
2258
  "mean_token_accuracy": 0.7383568711578846,
2259
  "num_tokens": 10412214.0,
2260
  "step": 2240
 
 
 
 
 
 
 
 
 
 
2261
  }
2262
  ],
2263
  "logging_steps": 10,
@@ -2277,7 +2287,7 @@
2277
  "attributes": {}
2278
  }
2279
  },
2280
- "total_flos": 4.938071462559744e+16,
2281
  "train_batch_size": 4,
2282
  "trial_name": null,
2283
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.48,
6
  "eval_steps": 500,
7
+ "global_step": 2250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2258
  "mean_token_accuracy": 0.7383568711578846,
2259
  "num_tokens": 10412214.0,
2260
  "step": 2240
2261
+ },
2262
+ {
2263
+ "entropy": 0.9707687653601169,
2264
+ "epoch": 0.48,
2265
+ "grad_norm": 0.2584036588668823,
2266
+ "learning_rate": 8.904682908831119e-05,
2267
+ "loss": 1.056828212738037,
2268
+ "mean_token_accuracy": 0.7611462950706482,
2269
+ "num_tokens": 10457804.0,
2270
+ "step": 2250
2271
  }
2272
  ],
2273
  "logging_steps": 10,
 
2287
  "attributes": {}
2288
  }
2289
  },
2290
+ "total_flos": 4.95945031861033e+16,
2291
  "train_batch_size": 4,
2292
  "trial_name": null,
2293
  "trial_params": null