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
4d1cb88
·
verified ·
1 Parent(s): 7529a1e

Training in progress, step 4130, 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 sha256:39809768485ed7213e828aa1117fd3373192ee5e1f52a62dbc39b3e8fa1c7689
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f1c00d9372003130f22f1f23e2744616a02ce07a866c6d9985deb5d6c3b503
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cec767c800e79c2547e666d75f382fe2a0e9abfc0a25112d17400a6e617b7d1
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a42f47b816e3c139ffb2db53fa673e3220b6ab6c7b610775c575fdb56c88571b
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:ace53224d1b1577125a09e63208f2a3f1330c86b6aaaeb0e29e16558f332ddf3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415e51d16dd002639e05a523a0c081c328b5254d670a017854a475492baa20d0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6aeb1f52232f9bd405c486e9d1290975d5ffe513e4aeabd2f1d6ee03a1a7d41
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f007c0fe31b3e32b6b457d9b437311bf3e7a5975656ae4adc10dd087e0ebbdd1
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": 0.8789333333333333,
6
  "eval_steps": 500,
7
- "global_step": 4120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4138,6 +4138,16 @@
4138
  "mean_token_accuracy": 0.7424666874110699,
4139
  "num_tokens": 19206121.0,
4140
  "step": 4120
 
 
 
 
 
 
 
 
 
 
4141
  }
4142
  ],
4143
  "logging_steps": 10,
@@ -4157,7 +4167,7 @@
4157
  "attributes": {}
4158
  }
4159
  },
4160
- "total_flos": 9.08747825015808e+16,
4161
  "train_batch_size": 4,
4162
  "trial_name": null,
4163
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8810666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4130,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4138
  "mean_token_accuracy": 0.7424666874110699,
4139
  "num_tokens": 19206121.0,
4140
  "step": 4120
4141
+ },
4142
+ {
4143
+ "entropy": 0.9243351340293884,
4144
+ "epoch": 0.8810666666666667,
4145
+ "grad_norm": 0.29001903533935547,
4146
+ "learning_rate": 6.214795971295063e-05,
4147
+ "loss": 0.9857352256774903,
4148
+ "mean_token_accuracy": 0.771124804764986,
4149
+ "num_tokens": 19252396.0,
4150
+ "step": 4130
4151
  }
4152
  ],
4153
  "logging_steps": 10,
 
4167
  "attributes": {}
4168
  }
4169
  },
4170
+ "total_flos": 9.109545612975206e+16,
4171
  "train_batch_size": 4,
4172
  "trial_name": null,
4173
  "trial_params": null