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
a261e47
·
verified ·
1 Parent(s): f58e751

Training in progress, step 2450, 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 sha256:877256650b7a8ab456adddb51d08278cfbe43d4db2b3dc77bca7fcf30ed2fe4f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b1de31e6e2512039cefd883e4e8eb251c9673095441a50a44e9878c4186b6f
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c127466db4d213449c52bd6d68d5c64c89d6aa0c5b042d1daae6e98efaeb8b2
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9fb7d83cbe1d31db9dc18574ee6231afbaa8c5f3179fe68ddc8574422b1e0b
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:f0102bd114592cc21c21be0343e5e62d496f463a23a272dadff75312ffae918b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b120e3c5be2377cb28f7113ed22954876ef7593499d2822d8a83bc4583acf65
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb41a100db46242c18f39a26a42d3d0396b78dd79e428ab8473d72afa767aec9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ad3427c15ee9ff17c5a21099a4c9e2ef371efe1083da36290fe3c17e229858
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": 0.5205333333333333,
6
  "eval_steps": 500,
7
- "global_step": 2440,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2458,6 +2458,16 @@
2458
  "mean_token_accuracy": 0.7516932919621467,
2459
  "num_tokens": 11350668.0,
2460
  "step": 2440
 
 
 
 
 
 
 
 
 
 
2461
  }
2462
  ],
2463
  "logging_steps": 10,
@@ -2477,7 +2487,7 @@
2477
  "attributes": {}
2478
  }
2479
  },
2480
- "total_flos": 5.38359391765801e+16,
2481
  "train_batch_size": 4,
2482
  "trial_name": null,
2483
  "trial_params": null
 
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,
 
2458
  "mean_token_accuracy": 0.7516932919621467,
2459
  "num_tokens": 11350668.0,
2460
  "step": 2440
2461
+ },
2462
+ {
2463
+ "entropy": 1.0364744253456593,
2464
+ "epoch": 0.5226666666666666,
2465
+ "grad_norm": 0.24485838413238525,
2466
+ "learning_rate": 8.67929811055542e-05,
2467
+ "loss": 1.100508689880371,
2468
+ "mean_token_accuracy": 0.7447643153369427,
2469
+ "num_tokens": 11403181.0,
2470
+ "step": 2450
2471
  }
2472
  ],
2473
  "logging_steps": 10,
 
2487
  "attributes": {}
2488
  }
2489
  },
2490
+ "total_flos": 5.408470279940198e+16,
2491
  "train_batch_size": 4,
2492
  "trial_name": null,
2493
  "trial_params": null