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
dcfc23a
·
verified ·
1 Parent(s): ca10af5

Training in progress, step 4140, 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 sha256:12f1c00d9372003130f22f1f23e2744616a02ce07a866c6d9985deb5d6c3b503
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb595e9ab46f8844e76dc2223d7e417f10d61514c8ddb395d18fcab0d6529c7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a42f47b816e3c139ffb2db53fa673e3220b6ab6c7b610775c575fdb56c88571b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4cbbe6f556a8ceec38300907866c7096b5b27483853975010214da431563f9
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:415e51d16dd002639e05a523a0c081c328b5254d670a017854a475492baa20d0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e023260c085d30f4021e31e42e94de09bfaef7d945f6bf9bced4689d040186
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f007c0fe31b3e32b6b457d9b437311bf3e7a5975656ae4adc10dd087e0ebbdd1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d0cf6f19aeeede8ba18176abd7dd337c6db3f56cdb76cb87eeaaacde41b53e
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": 0.8810666666666667,
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,
@@ -4148,6 +4148,16 @@
4148
  "mean_token_accuracy": 0.771124804764986,
4149
  "num_tokens": 19252396.0,
4150
  "step": 4130
 
 
 
 
 
 
 
 
 
 
4151
  }
4152
  ],
4153
  "logging_steps": 10,
@@ -4167,7 +4177,7 @@
4167
  "attributes": {}
4168
  }
4169
  },
4170
- "total_flos": 9.109545612975206e+16,
4171
  "train_batch_size": 4,
4172
  "trial_name": null,
4173
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8832,
6
  "eval_steps": 500,
7
+ "global_step": 4140,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4148
  "mean_token_accuracy": 0.771124804764986,
4149
  "num_tokens": 19252396.0,
4150
  "step": 4130
4151
+ },
4152
+ {
4153
+ "entropy": 0.7921540692448616,
4154
+ "epoch": 0.8832,
4155
+ "grad_norm": 0.3147003650665283,
4156
+ "learning_rate": 6.198000166408651e-05,
4157
+ "loss": 0.8609647750854492,
4158
+ "mean_token_accuracy": 0.7940000563859939,
4159
+ "num_tokens": 19293212.0,
4160
+ "step": 4140
4161
  }
4162
  ],
4163
  "logging_steps": 10,
 
4177
  "attributes": {}
4178
  }
4179
  },
4180
+ "total_flos": 9.128628244888166e+16,
4181
  "train_batch_size": 4,
4182
  "trial_name": null,
4183
  "trial_params": null