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
03c8f6c
·
verified ·
1 Parent(s): 8353692

Training in progress, step 2370, 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 sha256:7fd7170591f5571b3bbcf9d603466417fc7136a3ac93e65d5337338d466eddf0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b3ab0129ba949aa72f8e2686df45a3377f47d5c44caf27a7f068745f2ab6e1
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc0e4d233e51d0716f11aa3c933ce7220053d5215cb79abc561196901c1ec7c5
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bcd64524d41ec137752e5b1d1f5189e1e8f11f17f5f7c5fb4da649c2a40f3f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7fdaec812b106b1310ee19a34a72066d9e146e7175dc3be750da56496929e0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce871eb31abb8d9b2981fa626b5498a52f470cafaa7083240383d0b137ec3d62
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38e6f7582b579bd50731564e68a4d878d6c62c900bebe47f92751e2d2be3afb6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d764aaca7e01285561aeb51436264e3411116198eba81bf4c226623726ed23b3
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": 0.5034666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2360,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2378,6 +2378,16 @@
2378
  "mean_token_accuracy": 0.7528289645910263,
2379
  "num_tokens": 10973794.0,
2380
  "step": 2360
 
 
 
 
 
 
 
 
 
 
2381
  }
2382
  ],
2383
  "logging_steps": 10,
@@ -2397,7 +2407,7 @@
2397
  "attributes": {}
2398
  }
2399
  },
2400
- "total_flos": 5.204525383584768e+16,
2401
  "train_batch_size": 4,
2402
  "trial_name": null,
2403
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5056,
6
  "eval_steps": 500,
7
+ "global_step": 2370,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2378
  "mean_token_accuracy": 0.7528289645910263,
2379
  "num_tokens": 10973794.0,
2380
  "step": 2360
2381
+ },
2382
+ {
2383
+ "entropy": 0.9620419174432755,
2384
+ "epoch": 0.5056,
2385
+ "grad_norm": 0.2626616656780243,
2386
+ "learning_rate": 8.771629606233314e-05,
2387
+ "loss": 1.0547003746032715,
2388
+ "mean_token_accuracy": 0.7652165532112122,
2389
+ "num_tokens": 11022983.0,
2390
+ "step": 2370
2391
  }
2392
  ],
2393
  "logging_steps": 10,
 
2407
  "attributes": {}
2408
  }
2409
  },
2410
+ "total_flos": 5.22816171273769e+16,
2411
  "train_batch_size": 4,
2412
  "trial_name": null,
2413
  "trial_params": null