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
586a5c0
·
verified ·
1 Parent(s): 7671904

Training in progress, step 3270, 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 sha256:2ceb84b623ea4d78dc2e4beb3d7672de0f0e5c8e936a1736b07631a92c841f7c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d5bfd726b6f899cd3a3211c32fd89ff31f4235943e76b6efb4bf3316bb8459
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9a464d9caf675edf8b54dd822c981016f50c5bbbc3d772937597812e5d1772e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a0ed048fabddf4df25803e3ff126e382b4dc8e649f9ae25cf12b29ae1ce16e
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46246c8e49d8f2613f3d43304f7e4c0dd732495aff5a0e5d355f2bc1027f637a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9c10f0f8645ada3914094d584a7f62f9fd4e4c786043e74cdec9161313442c
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:591c0e54afee71052c7df60f252065be39eb5d9debe3b0db8b4975811aaf703b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86817a07306c43bc0fce5e3853587c665aa9bf577be3c5b21acd76e5b416a1e5
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": 0.6954666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3260,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3278,6 +3278,16 @@
3278
  "mean_token_accuracy": 0.7648348346352577,
3279
  "num_tokens": 15164096.0,
3280
  "step": 3260
 
 
 
 
 
 
 
 
 
 
3281
  }
3282
  ],
3283
  "logging_steps": 10,
@@ -3297,7 +3307,7 @@
3297
  "attributes": {}
3298
  }
3299
  },
3300
- "total_flos": 7.18088856287447e+16,
3301
  "train_batch_size": 4,
3302
  "trial_name": null,
3303
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6976,
6
  "eval_steps": 500,
7
+ "global_step": 3270,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3278
  "mean_token_accuracy": 0.7648348346352577,
3279
  "num_tokens": 15164096.0,
3280
  "step": 3260
3281
+ },
3282
+ {
3283
+ "entropy": 1.0723001688718796,
3284
+ "epoch": 0.6976,
3285
+ "grad_norm": 0.3482857644557953,
3286
+ "learning_rate": 7.58395418062079e-05,
3287
+ "loss": 1.147115993499756,
3288
+ "mean_token_accuracy": 0.7382091999053955,
3289
+ "num_tokens": 15212178.0,
3290
+ "step": 3270
3291
  }
3292
  ],
3293
  "logging_steps": 10,
 
3307
  "attributes": {}
3308
  }
3309
  },
3310
+ "total_flos": 7.204931327304499e+16,
3311
  "train_batch_size": 4,
3312
  "trial_name": null,
3313
  "trial_params": null