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
45c72bf
·
verified ·
1 Parent(s): 24f59c3

Training in progress, step 2580, 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:b644e512c89843d97d997f8a9c53bf1ce6be1554e3802234674d774f8014328a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06757b49024a03e7630cb05ba37129db6bc65c98594eb983f02577d3e7da46d9
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:244ef5d25a5a82e09cea12d17f1b198217012526842ef2c65441d505fac6635b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54b137324384195daf0391deb928749cbf916ab6bc40e59e81e3d2b5564b74a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48d4ff4c1ac80a437a2b457e1a9cb435b917049919abfd5a51eb188115254ac8
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cbb2cd8dd18a8a6f0c55360f79fa08a12f2361a727becc4f7ce3ae74ce1c55
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a541264643bd1ce7de970e9b47b3a04a702c2dd2cd8a9962cc93dd00e4370124
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a3ccafdbc42a79e9731e173c41d7c224b70bbc4f38fffb55184fb0eb09993c
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": 0.5482666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2570,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2588,6 +2588,16 @@
2588
  "mean_token_accuracy": 0.7793566673994065,
2589
  "num_tokens": 11940774.0,
2590
  "step": 2570
 
 
 
 
 
 
 
 
 
 
2591
  }
2592
  ],
2593
  "logging_steps": 10,
@@ -2607,7 +2617,7 @@
2607
  "attributes": {}
2608
  }
2609
  },
2610
- "total_flos": 5.662076880986419e+16,
2611
  "train_batch_size": 4,
2612
  "trial_name": null,
2613
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5504,
6
  "eval_steps": 500,
7
+ "global_step": 2580,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2588
  "mean_token_accuracy": 0.7793566673994065,
2589
  "num_tokens": 11940774.0,
2590
  "step": 2570
2591
+ },
2592
+ {
2593
+ "entropy": 0.941501996666193,
2594
+ "epoch": 0.5504,
2595
+ "grad_norm": 0.2179393619298935,
2596
+ "learning_rate": 8.523274751515595e-05,
2597
+ "loss": 0.9954432487487793,
2598
+ "mean_token_accuracy": 0.7663334146142006,
2599
+ "num_tokens": 11987918.0,
2600
+ "step": 2580
2601
  }
2602
  ],
2603
  "logging_steps": 10,
 
2617
  "attributes": {}
2618
  }
2619
  },
2620
+ "total_flos": 5.68461286097449e+16,
2621
  "train_batch_size": 4,
2622
  "trial_name": null,
2623
  "trial_params": null