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
ea5da5a
·
verified ·
1 Parent(s): 6463052

Training in progress, step 3470, 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 sha256:7812b22f640f6779046a94850c20d8130cbef98868c1bd6d52482119d9e468a1
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0171d7e649dd6a8b49c1eb9e6ff3b75eec6fdb119e7d4cedd98ec382bd1091f0
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89c24ca5067abc3c4007746375351b1234f6bbad64851d6d65632b67cf10a941
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2656cd5f9de0d774c6d5ee5f7e4cf62b75accb683056c6c71a0fc1220c9462db
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74630eab6c20ceb20051c7c99754c46602da37a1b83de2c58239d9a9bdd22c26
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e52ad55e4ab3d1623b5249d385041cd2a1a01b912d2cf106d89b8ec45a29f86
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:696dc354a288c906f25e166278fb460fd9fcaa4eafb9cbcfe466a3bb12d630e8
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85ea2a402e38c6f2ba689f525ad2de306dc03983ba992d937a5c92396d49fd36
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": 0.7381333333333333,
6
  "eval_steps": 500,
7
- "global_step": 3460,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3478,6 +3478,16 @@
3478
  "mean_token_accuracy": 0.7672612771391869,
3479
  "num_tokens": 16128753.0,
3480
  "step": 3460
 
 
 
 
 
 
 
 
 
 
3481
  }
3482
  ],
3483
  "logging_steps": 10,
@@ -3497,7 +3507,7 @@
3497
  "attributes": {}
3498
  }
3499
  },
3500
- "total_flos": 7.63869779972014e+16,
3501
  "train_batch_size": 4,
3502
  "trial_name": null,
3503
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7402666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 3470,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3478
  "mean_token_accuracy": 0.7672612771391869,
3479
  "num_tokens": 16128753.0,
3480
  "step": 3460
3481
+ },
3482
+ {
3483
+ "entropy": 0.9178998105227947,
3484
+ "epoch": 0.7402666666666666,
3485
+ "grad_norm": 0.24847134947776794,
3486
+ "learning_rate": 7.281664421551684e-05,
3487
+ "loss": 1.0369275093078614,
3488
+ "mean_token_accuracy": 0.7686163082718849,
3489
+ "num_tokens": 16169199.0,
3490
+ "step": 3470
3491
  }
3492
  ],
3493
  "logging_steps": 10,
 
3507
  "attributes": {}
3508
  }
3509
  },
3510
+ "total_flos": 7.657711040244326e+16,
3511
  "train_batch_size": 4,
3512
  "trial_name": null,
3513
  "trial_params": null