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
07d43fe
·
verified ·
1 Parent(s): 980bd42

Training in progress, step 2590, 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 sha256:06757b49024a03e7630cb05ba37129db6bc65c98594eb983f02577d3e7da46d9
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9c8820ea9f00124d2e6c2a545182018cc25bd060816910c6300f17ccbff455
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a54b137324384195daf0391deb928749cbf916ab6bc40e59e81e3d2b5564b74a
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93a578b7efdc530c1435c64ead73387a4818b9bbcd4ca0151b9996be401bd36
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:a5cbb2cd8dd18a8a6f0c55360f79fa08a12f2361a727becc4f7ce3ae74ce1c55
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234daeb512cc98cf6cd6f20334cf2cc2d5c1695848f1f6c77dc965106332cb08
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27a3ccafdbc42a79e9731e173c41d7c224b70bbc4f38fffb55184fb0eb09993c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc2717ac5bbee249ccef8c4d225963e7b44bfb26a9658a9a26de152929b3606
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": 0.5504,
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,
@@ -2598,6 +2598,16 @@
2598
  "mean_token_accuracy": 0.7663334146142006,
2599
  "num_tokens": 11987918.0,
2600
  "step": 2580
 
 
 
 
 
 
 
 
 
 
2601
  }
2602
  ],
2603
  "logging_steps": 10,
@@ -2617,7 +2627,7 @@
2617
  "attributes": {}
2618
  }
2619
  },
2620
- "total_flos": 5.68461286097449e+16,
2621
  "train_batch_size": 4,
2622
  "trial_name": null,
2623
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5525333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 2590,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2598
  "mean_token_accuracy": 0.7663334146142006,
2599
  "num_tokens": 11987918.0,
2600
  "step": 2580
2601
+ },
2602
+ {
2603
+ "entropy": 0.8678958520293236,
2604
+ "epoch": 0.5525333333333333,
2605
+ "grad_norm": 0.28909558057785034,
2606
+ "learning_rate": 8.510973383065099e-05,
2607
+ "loss": 0.9430976867675781,
2608
+ "mean_token_accuracy": 0.7832803040742874,
2609
+ "num_tokens": 12032447.0,
2610
+ "step": 2590
2611
  }
2612
  ],
2613
  "logging_steps": 10,
 
2627
  "attributes": {}
2628
  }
2629
  },
2630
+ "total_flos": 5.705449202531021e+16,
2631
  "train_batch_size": 4,
2632
  "trial_name": null,
2633
  "trial_params": null