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
2648b0c
·
verified ·
1 Parent(s): 668a01f

Training in progress, step 2310, 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 sha256:25777d4b1e19df6938f93a49ae4fd6a643a672eac4d577326d1235e09e721b8f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76022387961fc56a6a839cec6f747c514df94864ba9f2015e81fc31ac9fe420
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5916a8da5ddd576cc53de1bf016fda8ea98257e9143268097f444b9289e4abf5
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90dc3e65746e0994c06f35615e40ae962b97b713e6de0e6af7f3ed7234e7904e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85a542bdaa1414ef24dba57f4b2761bab55cae65a1369f43ae3040c3682ff5ce
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0d30be0107534f82e8019002d05672296d4f11499248f317d4f057228dd9ab
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:935c260d8d47f6c3b3e6dac00fe9f85351319b3b4cc067e993776e133bb21141
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89b3cfad524b8221ef5fd4a17e5c93b50f30ca3300e01485ea54ae56d2cd2f8
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": 0.49066666666666664,
6
  "eval_steps": 500,
7
- "global_step": 2300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2318,6 +2318,16 @@
2318
  "mean_token_accuracy": 0.7669046297669411,
2319
  "num_tokens": 10691324.0,
2320
  "step": 2300
 
 
 
 
 
 
 
 
 
 
2321
  }
2322
  ],
2323
  "logging_steps": 10,
@@ -2337,7 +2347,7 @@
2337
  "attributes": {}
2338
  }
2339
  },
2340
- "total_flos": 5.068992285879091e+16,
2341
  "train_batch_size": 4,
2342
  "trial_name": null,
2343
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4928,
6
  "eval_steps": 500,
7
+ "global_step": 2310,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2318
  "mean_token_accuracy": 0.7669046297669411,
2319
  "num_tokens": 10691324.0,
2320
  "step": 2300
2321
+ },
2322
+ {
2323
+ "entropy": 0.9109658055007458,
2324
+ "epoch": 0.4928,
2325
+ "grad_norm": 0.2615504264831543,
2326
+ "learning_rate": 8.838984169168708e-05,
2327
+ "loss": 0.9777699470520019,
2328
+ "mean_token_accuracy": 0.7721924617886543,
2329
+ "num_tokens": 10736949.0,
2330
+ "step": 2310
2331
  }
2332
  ],
2333
  "logging_steps": 10,
 
2347
  "attributes": {}
2348
  }
2349
  },
2350
+ "total_flos": 5.090651411045376e+16,
2351
  "train_batch_size": 4,
2352
  "trial_name": null,
2353
  "trial_params": null