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
f91e82c
·
verified ·
1 Parent(s): 5138ca7

Training in progress, step 1950, 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 sha256:5b0f651dd2390787ccc654779331c7efcf4a41676fe84918fe06f53baf66c597
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fe39fff458d6b62846442523528cce378f798e09f1e67c0b4568c2d3f592d4b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b74a028f8d5d4158861ae111bf1223362eabef881272e6b876250870a5d325eb
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbd7b4dd42466221bba71411da9f586fd88a167e9e8a901f7cd5049747da468
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7689f5a1f02390c85238d6479425461f19fb98f89c3806536dc670f98d7b55eb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5a6c67f9781c4e91ddafe3e118cf0facdb785f4abb89cd52f5fc13e9252a6b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14432b7129e77fe387e9dcc1ce58477852a16b33e4ab9ce60c922269768d96ac
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9566af3e319364a3808e69e353e8c1787eec78598708372beecd198ce7557b
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": 0.41386666666666666,
6
  "eval_steps": 500,
7
- "global_step": 1940,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1958,6 +1958,16 @@
1958
  "mean_token_accuracy": 0.7712534263730049,
1959
  "num_tokens": 8990326.0,
1960
  "step": 1940
 
 
 
 
 
 
 
 
 
 
1961
  }
1962
  ],
1963
  "logging_steps": 10,
@@ -1977,7 +1987,7 @@
1977
  "attributes": {}
1978
  }
1979
  },
1980
- "total_flos": 4.266892717101466e+16,
1981
  "train_batch_size": 4,
1982
  "trial_name": null,
1983
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.416,
6
  "eval_steps": 500,
7
+ "global_step": 1950,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1958
  "mean_token_accuracy": 0.7712534263730049,
1959
  "num_tokens": 8990326.0,
1960
  "step": 1940
1961
+ },
1962
+ {
1963
+ "entropy": 1.0142885446548462,
1964
+ "epoch": 0.416,
1965
+ "grad_norm": 0.25167402625083923,
1966
+ "learning_rate": 9.20737313331655e-05,
1967
+ "loss": 1.0986696243286134,
1968
+ "mean_token_accuracy": 0.7525161564350128,
1969
+ "num_tokens": 9037859.0,
1970
+ "step": 1950
1971
  }
1972
  ],
1973
  "logging_steps": 10,
 
1987
  "attributes": {}
1988
  }
1989
  },
1990
+ "total_flos": 4.290455148931277e+16,
1991
  "train_batch_size": 4,
1992
  "trial_name": null,
1993
  "trial_params": null