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
5412649
·
verified ·
1 Parent(s): 8712138

Training in progress, step 2460, 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 sha256:89b1de31e6e2512039cefd883e4e8eb251c9673095441a50a44e9878c4186b6f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bbd98897007d5e0719a50c7763f7552d40805a4e0e93ef977ed80e95f6a5ac
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd9fb7d83cbe1d31db9dc18574ee6231afbaa8c5f3179fe68ddc8574422b1e0b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6e6db113fb2546f5fab8dfa629322b1b35d911af46a5e369c35b7e95ee1202b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b120e3c5be2377cb28f7113ed22954876ef7593499d2822d8a83bc4583acf65
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce863f92900b44410c3a7f85940b1ce75661822892c2c2c1d91f4b9948f78ed2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99ad3427c15ee9ff17c5a21099a4c9e2ef371efe1083da36290fe3c17e229858
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515429dd86eeba658ae7060a39c92746d8e0bf7ad7c444e90d685bef27a27db3
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": 0.5226666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2450,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2468,6 +2468,16 @@
2468
  "mean_token_accuracy": 0.7447643153369427,
2469
  "num_tokens": 11403181.0,
2470
  "step": 2450
 
 
 
 
 
 
 
 
 
 
2471
  }
2472
  ],
2473
  "logging_steps": 10,
@@ -2487,7 +2497,7 @@
2487
  "attributes": {}
2488
  }
2489
  },
2490
- "total_flos": 5.408470279940198e+16,
2491
  "train_batch_size": 4,
2492
  "trial_name": null,
2493
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5248,
6
  "eval_steps": 500,
7
+ "global_step": 2460,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2468
  "mean_token_accuracy": 0.7447643153369427,
2469
  "num_tokens": 11403181.0,
2470
  "step": 2450
2471
+ },
2472
+ {
2473
+ "entropy": 0.8236982800066471,
2474
+ "epoch": 0.5248,
2475
+ "grad_norm": 0.28031599521636963,
2476
+ "learning_rate": 8.667556834990211e-05,
2477
+ "loss": 0.9254312515258789,
2478
+ "mean_token_accuracy": 0.7904586613178253,
2479
+ "num_tokens": 11443565.0,
2480
+ "step": 2460
2481
  }
2482
  ],
2483
  "logging_steps": 10,
 
2497
  "attributes": {}
2498
  }
2499
  },
2500
+ "total_flos": 5.427367267358515e+16,
2501
  "train_batch_size": 4,
2502
  "trial_name": null,
2503
  "trial_params": null