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
f720203
·
verified ·
1 Parent(s): c789289

Training in progress, step 2120, 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:b776ced8c78aac80a4abe39b2298c457d422f9401db961bed3834b94ac88542b
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5088129c4003dad3b5017de7566e445b1a452d1131416c06159ea57021bf0d7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebd54b659d3eaa86c63d2e93a80b846e3e9732481a6ddc8a08199e259cf99cde
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aefe7b8a5249d7fe56d86787f9d56b78fd0d4fa465633ab1c8dba8e6fe92b5d9
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c984125d6b74470d240a0b60f0c9979b54ec8a305937f59b6901ed64861f64d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:040b616c4d343a19d8ac7f4a94ee8608f91ce652a361d61caabcc8007973c965
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91f73b3e4e2bd57599755af9d2abc683e515e4a1bbc0214b088b1d7601c53afa
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebfe12db4af6f85a84ab2da0ea677dadec6d4b925c000eab4c3194b6835b4257
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": 0.45013333333333333,
6
  "eval_steps": 500,
7
- "global_step": 2110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2128,6 +2128,16 @@
2128
  "mean_token_accuracy": 0.7496985673904419,
2129
  "num_tokens": 9766859.0,
2130
  "step": 2110
 
 
 
 
 
 
 
 
 
 
2131
  }
2132
  ],
2133
  "logging_steps": 10,
@@ -2147,7 +2157,7 @@
2147
  "attributes": {}
2148
  }
2149
  },
2150
- "total_flos": 4.633604578289357e+16,
2151
  "train_batch_size": 4,
2152
  "trial_name": null,
2153
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.45226666666666665,
6
  "eval_steps": 500,
7
+ "global_step": 2120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2128
  "mean_token_accuracy": 0.7496985673904419,
2129
  "num_tokens": 9766859.0,
2130
  "step": 2110
2131
+ },
2132
+ {
2133
+ "entropy": 1.0453794084489345,
2134
+ "epoch": 0.45226666666666665,
2135
+ "grad_norm": 0.21886104345321655,
2136
+ "learning_rate": 9.041215777967945e-05,
2137
+ "loss": 1.128882598876953,
2138
+ "mean_token_accuracy": 0.7480149149894715,
2139
+ "num_tokens": 9821214.0,
2140
+ "step": 2120
2141
  }
2142
  ],
2143
  "logging_steps": 10,
 
2157
  "attributes": {}
2158
  }
2159
  },
2160
+ "total_flos": 4.659666001301914e+16,
2161
  "train_batch_size": 4,
2162
  "trial_name": null,
2163
  "trial_params": null