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
e7170be
·
verified ·
1 Parent(s): e06f56e

Training in progress, step 1210, 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:ace55a11230d780c73ad3972a954e4d11272264f349fe01c8e407e0c23c8989f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fcad317f9dc0279c2bdfe2776581fe1e9ded6c6b456e1df675c7d5f9b7ab4c
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:872d4d72444b5de1cc08ad181c9790f46118072a5396e08c0f8471ef620fc0ab
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a0fdb8bb12f98e024e4e681c21868d90f54ee8cb87fd85bedfcae773d8ae33
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a1632b2e2a3ea7078bbcddab1cf01b7157f2874045a58a01a68284bf195ec13
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118e54e4238fbac6d96a3f5db54dfaa2da72293ef9253831a39b22d03a7082d9
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d44244312cb5c2d760059d356bc53d068bf179be10b7607667de831e91a7da74
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f70b2baed2af61db86c660a4d5947a9d3c73e1e277ed144c6224b03af39ae7
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": 0.256,
6
  "eval_steps": 500,
7
- "global_step": 1200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1218,6 +1218,16 @@
1218
  "mean_token_accuracy": 0.7419089064002037,
1219
  "num_tokens": 5592981.0,
1220
  "step": 1200
 
 
 
 
 
 
 
 
 
 
1221
  }
1222
  ],
1223
  "logging_steps": 10,
@@ -1237,7 +1247,7 @@
1237
  "attributes": {}
1238
  }
1239
  },
1240
- "total_flos": 2.647411252652237e+16,
1241
  "train_batch_size": 4,
1242
  "trial_name": null,
1243
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2581333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 1210,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1218
  "mean_token_accuracy": 0.7419089064002037,
1219
  "num_tokens": 5592981.0,
1220
  "step": 1200
1221
+ },
1222
+ {
1223
+ "entropy": 1.115493653714657,
1224
+ "epoch": 0.2581333333333333,
1225
+ "grad_norm": 0.2895198464393616,
1226
+ "learning_rate": 9.754533274949575e-05,
1227
+ "loss": 1.2449783325195312,
1228
+ "mean_token_accuracy": 0.7372826255857945,
1229
+ "num_tokens": 5637868.0,
1230
+ "step": 1210
1231
  }
1232
  ],
1233
  "logging_steps": 10,
 
1247
  "attributes": {}
1248
  }
1249
  },
1250
+ "total_flos": 2.670758300820787e+16,
1251
  "train_batch_size": 4,
1252
  "trial_name": null,
1253
  "trial_params": null