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
a8a5630
·
verified ·
1 Parent(s): 7f9a7b8

Training in progress, step 2520, 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:dbe67794af50642f182b9ea8c384905c650abf9cc8b329428898500972747400
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eef7ebe66a4d39b9b733071b25bb0943f0273d15e8d4985631af916ef647e55
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5619a0f072aab8b47dd7d30c4ada88d0753ce4862a2d555516994d2a847ef155
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac23e094bdff1ee533bbedad7b5556dc4cfd187f669554e72b85031dab7e8a3a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13bb58902d7911f6b8185a6ef12bf6396763797af9152cc44e85896cb9480a07
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9c1ed3f1de6d5c5f42062a74c12db4948e298c880f316a70486fa97b159992
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e0e6092e19618a2ff351245c56be6866db27a4f7763b7af3f3d7624941a3665
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ad73a9cf554b3393b6a0365c57cf35ca0d09d89785e25b59f37505835ce5b9
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": 0.5354666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2510,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2528,6 +2528,16 @@
2528
  "mean_token_accuracy": 0.7692675769329071,
2529
  "num_tokens": 11666713.0,
2530
  "step": 2510
 
 
 
 
 
 
 
 
 
 
2531
  }
2532
  ],
2533
  "logging_steps": 10,
@@ -2547,7 +2557,7 @@
2547
  "attributes": {}
2548
  }
2549
  },
2550
- "total_flos": 5.535017643393024e+16,
2551
  "train_batch_size": 4,
2552
  "trial_name": null,
2553
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5376,
6
  "eval_steps": 500,
7
+ "global_step": 2520,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2528
  "mean_token_accuracy": 0.7692675769329071,
2529
  "num_tokens": 11666713.0,
2530
  "step": 2510
2531
+ },
2532
+ {
2533
+ "entropy": 0.995804300904274,
2534
+ "epoch": 0.5376,
2535
+ "grad_norm": 0.3097708821296692,
2536
+ "learning_rate": 8.596191344422144e-05,
2537
+ "loss": 1.072645664215088,
2538
+ "mean_token_accuracy": 0.7509198278188706,
2539
+ "num_tokens": 11710341.0,
2540
+ "step": 2520
2541
  }
2542
  ],
2543
  "logging_steps": 10,
 
2557
  "attributes": {}
2558
  }
2559
  },
2560
+ "total_flos": 5.557611299340595e+16,
2561
  "train_batch_size": 4,
2562
  "trial_name": null,
2563
  "trial_params": null