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
05a6928
·
verified ·
1 Parent(s): 17f3fcb

Training in progress, step 1140, 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 sha256:624ca27ec31cd718988ae2e701c34d2a5c37c24af396b4f01cc7ebd4dffd90f5
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e421356a08ab52e140026da65d5861223082140ba24ee78b3fe86949d0ea4236
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:147b98cbe08fb1ca714092fd5f88aaca8f659f61afa679247d23ed23534e325f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebc9a1960eca13fadd941b073064cf7560b80d545e6159964841e0fad286a4c
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5903a6fcc85ab2e812cf0c76cb692bc37ddaa8a934113db0d28af03dac18b56a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e85b5465fe52973a7bd51b7c785181b8b382ea41c86dc79168d0eca8972a904
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa3baabbd2c84ed44d6dc28874c23c6480fd913a22e79e566a7473e47b6a3dc5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e58f741bd504af13f9a07922da1601be73c5c9e500ed2ea57a5d3024618328c
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": 0.24106666666666668,
6
  "eval_steps": 500,
7
- "global_step": 1130,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1148,6 +1148,16 @@
1148
  "mean_token_accuracy": 0.7670834749937058,
1149
  "num_tokens": 5257491.0,
1150
  "step": 1130
 
 
 
 
 
 
 
 
 
 
1151
  }
1152
  ],
1153
  "logging_steps": 10,
@@ -1167,7 +1177,7 @@
1167
  "attributes": {}
1168
  }
1169
  },
1170
- "total_flos": 2.486159182943539e+16,
1171
  "train_batch_size": 4,
1172
  "trial_name": null,
1173
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2432,
6
  "eval_steps": 500,
7
+ "global_step": 1140,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1148
  "mean_token_accuracy": 0.7670834749937058,
1149
  "num_tokens": 5257491.0,
1150
  "step": 1130
1151
+ },
1152
+ {
1153
+ "entropy": 1.0790555529296397,
1154
+ "epoch": 0.2432,
1155
+ "grad_norm": 0.2658112645149231,
1156
+ "learning_rate": 9.790627239537144e-05,
1157
+ "loss": 1.2411640167236329,
1158
+ "mean_token_accuracy": 0.7390920028090477,
1159
+ "num_tokens": 5302986.0,
1160
+ "step": 1140
1161
  }
1162
  ],
1163
  "logging_steps": 10,
 
1177
  "attributes": {}
1178
  }
1179
  },
1180
+ "total_flos": 2.50703427553536e+16,
1181
  "train_batch_size": 4,
1182
  "trial_name": null,
1183
  "trial_params": null