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
c3fb38f
·
verified ·
1 Parent(s): fd346fb

Training in progress, step 4280, 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:f89da48a68fcc55e3d138692cbeb28e6b4f96d3f71a659a578517d55144d4d3a
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e5e7810249347584d9bdd94cfe666abf722f51e9df64f9e4e89965e567f91e
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1cbe1676c2ef867fa5de11325371bf92dda3e274c31cf8003b52d3620847b0d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649a9f8a6a315d0647c96260afc243265f8f934b787d51a3af7df5929ffe8603
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e4681240597c52c68411aa0b9a3792bc73cc13d2ccca7e73b8fbee2aaa4429e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3abc0160f5702ba37704b671272e8df84374a3f82121ad3ead0c93e557a6a3e6
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61b3d2f18fddb8935455b715f83e0fd5895fd8d87e763702cffb720f2517cd02
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889b168a77b23f5e0cf66dcf46600d99e2463a955f249138701d219515ba8859
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": 0.9109333333333334,
6
  "eval_steps": 500,
7
- "global_step": 4270,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4288,6 +4288,16 @@
4288
  "mean_token_accuracy": 0.7536325603723526,
4289
  "num_tokens": 19888786.0,
4290
  "step": 4270
 
 
 
 
 
 
 
 
 
 
4291
  }
4292
  ],
4293
  "logging_steps": 10,
@@ -4307,7 +4317,7 @@
4307
  "attributes": {}
4308
  }
4309
  },
4310
- "total_flos": 9.412431815480525e+16,
4311
  "train_batch_size": 4,
4312
  "trial_name": null,
4313
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.9130666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4280,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4288
  "mean_token_accuracy": 0.7536325603723526,
4289
  "num_tokens": 19888786.0,
4290
  "step": 4270
4291
+ },
4292
+ {
4293
+ "entropy": 0.8563631072640419,
4294
+ "epoch": 0.9130666666666667,
4295
+ "grad_norm": 0.2725948393344879,
4296
+ "learning_rate": 5.961443613853157e-05,
4297
+ "loss": 0.9641815185546875,
4298
+ "mean_token_accuracy": 0.7762529909610748,
4299
+ "num_tokens": 19931094.0,
4300
+ "step": 4280
4301
  }
4302
  ],
4303
  "logging_steps": 10,
 
4317
  "attributes": {}
4318
  }
4319
  },
4320
+ "total_flos": 9.432187633983283e+16,
4321
  "train_batch_size": 4,
4322
  "trial_name": null,
4323
  "trial_params": null