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
83d123d
·
verified ·
1 Parent(s): d1eddfe

Training in progress, step 540, 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:f982b562a61d56ec88c927d94b2411635912f31e10481b36ab30b3cce791c977
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090462ef8f606075af048f85b7e046b41976430da4f96c31f29d19d3c0d99f97
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb30ea04c234d4ba96c9a55575da03e0537b8cd8d2ee0e07ce4471ccc4d4ddd7
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f080c3c3e9a8841d5f374bce88d1f132b493f39d9daa555483bb725580f05a3
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86db0c936b943210e7049764057f88776b6e2889685b63bc7fa74821938629ae
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba9e34cde3eeee92d5f00298627ddb43d984f163e0b84ea610723f9d6feda7e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:142dde52320342a8b723fdcf9bf6931bda898c4bb30385516c999713759acce6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcad7ace1953267f7e67920e5232af2f14d8f4d17fbdd7cef912bc890f95d17
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": 0.11306666666666666,
6
  "eval_steps": 500,
7
- "global_step": 530,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -548,6 +548,16 @@
548
  "mean_token_accuracy": 0.7418296962976456,
549
  "num_tokens": 2445609.0,
550
  "step": 530
 
 
 
 
 
 
 
 
 
 
551
  }
552
  ],
553
  "logging_steps": 10,
@@ -567,7 +577,7 @@
567
  "attributes": {}
568
  }
569
  },
570
- "total_flos": 1.1645244840382464e+16,
571
  "train_batch_size": 4,
572
  "trial_name": null,
573
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1152,
6
  "eval_steps": 500,
7
+ "global_step": 540,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
548
  "mean_token_accuracy": 0.7418296962976456,
549
  "num_tokens": 2445609.0,
550
  "step": 530
551
+ },
552
+ {
553
+ "entropy": 1.037429604679346,
554
+ "epoch": 0.1152,
555
+ "grad_norm": 0.29860854148864746,
556
+ "learning_rate": 9.982899891076973e-05,
557
+ "loss": 1.1256014823913574,
558
+ "mean_token_accuracy": 0.7413557574152947,
559
+ "num_tokens": 2490595.0,
560
+ "step": 540
561
  }
562
  ],
563
  "logging_steps": 10,
 
577
  "attributes": {}
578
  }
579
  },
580
+ "total_flos": 1.1864837044313088e+16,
581
  "train_batch_size": 4,
582
  "trial_name": null,
583
  "trial_params": null