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
45ccb69
·
verified ·
1 Parent(s): f01f790

Training in progress, step 3480, 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 sha256:0171d7e649dd6a8b49c1eb9e6ff3b75eec6fdb119e7d4cedd98ec382bd1091f0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b6ad1fecdf9421f9c00f50b37e7e192fe08a902047a90352ac7868856b7db2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2656cd5f9de0d774c6d5ee5f7e4cf62b75accb683056c6c71a0fc1220c9462db
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec08ee9cc02ada0966475e4765e516a60ab63fb6e5fc6cf1b35435a6be755156
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e52ad55e4ab3d1623b5249d385041cd2a1a01b912d2cf106d89b8ec45a29f86
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d301cace1c0586a0af4b283d8676432196b785f2b113ed068ccc25d3287a59fe
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85ea2a402e38c6f2ba689f525ad2de306dc03983ba992d937a5c92396d49fd36
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ef7510762ea03eddd238a753e92d652e1336d4c108e4f7cfc5dc319bb901b5
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": 0.7402666666666666,
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,
@@ -3488,6 +3488,16 @@
3488
  "mean_token_accuracy": 0.7686163082718849,
3489
  "num_tokens": 16169199.0,
3490
  "step": 3470
 
 
 
 
 
 
 
 
 
 
3491
  }
3492
  ],
3493
  "logging_steps": 10,
@@ -3507,7 +3517,7 @@
3507
  "attributes": {}
3508
  }
3509
  },
3510
- "total_flos": 7.657711040244326e+16,
3511
  "train_batch_size": 4,
3512
  "trial_name": null,
3513
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7424,
6
  "eval_steps": 500,
7
+ "global_step": 3480,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3488
  "mean_token_accuracy": 0.7686163082718849,
3489
  "num_tokens": 16169199.0,
3490
  "step": 3470
3491
+ },
3492
+ {
3493
+ "entropy": 1.089708861708641,
3494
+ "epoch": 0.7424,
3495
+ "grad_norm": 0.2787526547908783,
3496
+ "learning_rate": 7.266250729213105e-05,
3497
+ "loss": 1.177119255065918,
3498
+ "mean_token_accuracy": 0.7344872549176216,
3499
+ "num_tokens": 16218140.0,
3500
+ "step": 3480
3501
  }
3502
  ],
3503
  "logging_steps": 10,
 
3517
  "attributes": {}
3518
  }
3519
  },
3520
+ "total_flos": 7.682752319723213e+16,
3521
  "train_batch_size": 4,
3522
  "trial_name": null,
3523
  "trial_params": null