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
cfe656a
·
verified ·
1 Parent(s): 1e5e471

Training in progress, step 2540, 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:bb88d925858e94344d7f87fe677e32165eb8e3252e76d7f0da0e73d8b1d32ce3
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44bc77c6565271feab7e3c7b4dcf6309ff4407c21e6ee1c8bee91da083bfa41e
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b45818ae8407cc67d7bfd50a7787c613a72f2379e40affdd12142c829450fc81
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668ba5cce3c84a65e433cf033a6e5b75c109903f41b4f8b35717ca47a06cab54
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:a34422028f7ff9fe4ff4ee216ad704753af7fb1e625c31db00d387461d736940
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6062a8762014575d040a3bcc196b9278a1f33f78579fc863d474a54c89e88e0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f957b3cff70835bb9ada1b9a20d676302da81eb94bd5937f10ed4e15a62423e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a192b1ac6e4741adc1d8201252f5b9e6d728173683d919e5e81f11d58e77175d
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": 0.5397333333333333,
6
  "eval_steps": 500,
7
- "global_step": 2530,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2548,6 +2548,16 @@
2548
  "mean_token_accuracy": 0.789941257238388,
2549
  "num_tokens": 11753282.0,
2550
  "step": 2530
 
 
 
 
 
 
 
 
 
 
2551
  }
2552
  ],
2553
  "logging_steps": 10,
@@ -2567,7 +2577,7 @@
2567
  "attributes": {}
2568
  }
2569
  },
2570
- "total_flos": 5.576751607213056e+16,
2571
  "train_batch_size": 4,
2572
  "trial_name": null,
2573
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5418666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 2540,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2548
  "mean_token_accuracy": 0.789941257238388,
2549
  "num_tokens": 11753282.0,
2550
  "step": 2530
2551
+ },
2552
+ {
2553
+ "entropy": 1.0006135009229182,
2554
+ "epoch": 0.5418666666666667,
2555
+ "grad_norm": 0.2360389232635498,
2556
+ "learning_rate": 8.572056618695845e-05,
2557
+ "loss": 1.1389695167541505,
2558
+ "mean_token_accuracy": 0.7522218823432922,
2559
+ "num_tokens": 11801605.0,
2560
+ "step": 2540
2561
  }
2562
  ],
2563
  "logging_steps": 10,
 
2577
  "attributes": {}
2578
  }
2579
  },
2580
+ "total_flos": 5.599219096999219e+16,
2581
  "train_batch_size": 4,
2582
  "trial_name": null,
2583
  "trial_params": null