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
9a07325
·
verified ·
1 Parent(s): 0d6b20b

Training in progress, step 1180, 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 sha256:0ad5feee574fc9cf82f3a18445fae9dac753f73aa3e331196d1848b487ff5ce8
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602b9d65ddf098f785d3b23ec5e8cb63648396cd5ff54d7a4d6d20461daace36
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86b55f892a18476ed97b10955fe7b490a80c7dc10027c8fe73a816dca9cda332
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa138315154c92fbbf5a282c238cbf6211c7f92f73b5bf1acc3b208ce071c75c
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eda22a1d85d7cda0418d7dc4be938dd0c1311708873716f2b00441cf7520246
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122da5a58172c5a85b774cafef86e893c98ce66e0880748444961acd1fcd5317
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe490c6010e0c0d8c317fef7f6184fb6f5c74dee78d88daba0e96c3f7f353e3b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57c38ca293e8349258dc47df7ce5a1ed5e78a718a03a0f6e7bfe992a6651616
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": 0.2496,
6
  "eval_steps": 500,
7
- "global_step": 1170,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1188,6 +1188,16 @@
1188
  "mean_token_accuracy": 0.7444046661257744,
1189
  "num_tokens": 5443639.0,
1190
  "step": 1170
 
 
 
 
 
 
 
 
 
 
1191
  }
1192
  ],
1193
  "logging_steps": 10,
@@ -1207,7 +1217,7 @@
1207
  "attributes": {}
1208
  }
1209
  },
1210
- "total_flos": 2.577578282312909e+16,
1211
  "train_batch_size": 4,
1212
  "trial_name": null,
1213
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2517333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 1180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1188
  "mean_token_accuracy": 0.7444046661257744,
1189
  "num_tokens": 5443639.0,
1190
  "step": 1170
1191
+ },
1192
+ {
1193
+ "entropy": 0.9544263079762458,
1194
+ "epoch": 0.2517333333333333,
1195
+ "grad_norm": 0.28337323665618896,
1196
+ "learning_rate": 9.770345171721929e-05,
1197
+ "loss": 1.0133567810058595,
1198
+ "mean_token_accuracy": 0.7597964540123939,
1199
+ "num_tokens": 5494552.0,
1200
+ "step": 1180
1201
  }
1202
  ],
1203
  "logging_steps": 10,
 
1217
  "attributes": {}
1218
  }
1219
  },
1220
+ "total_flos": 2.6006738993455104e+16,
1221
  "train_batch_size": 4,
1222
  "trial_name": null,
1223
  "trial_params": null