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
02ae960
·
verified ·
1 Parent(s): 8ce2fc3

Training in progress, step 1190, 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 sha256:602b9d65ddf098f785d3b23ec5e8cb63648396cd5ff54d7a4d6d20461daace36
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b200680d038211860ba584c2f28a63092bedbb52e5d90f6546bd5a10d09e06a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa138315154c92fbbf5a282c238cbf6211c7f92f73b5bf1acc3b208ce071c75c
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88dd34cdf02f6c0060ce2effba9c422499547a777556c6fa4324624714c519ba
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:122da5a58172c5a85b774cafef86e893c98ce66e0880748444961acd1fcd5317
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6099819e8294a8fc5af7ae38f658d01ef30baab7a41ad4ede6b3e0c5a669d1f0
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57c38ca293e8349258dc47df7ce5a1ed5e78a718a03a0f6e7bfe992a6651616
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc341169ddfbf9f200256314bab44f65cd4b1a53f8b3614ed0e563731aee7ac
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": 0.2517333333333333,
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,
@@ -1198,6 +1198,16 @@
1198
  "mean_token_accuracy": 0.7597964540123939,
1199
  "num_tokens": 5494552.0,
1200
  "step": 1180
 
 
 
 
 
 
 
 
 
 
1201
  }
1202
  ],
1203
  "logging_steps": 10,
@@ -1217,7 +1227,7 @@
1217
  "attributes": {}
1218
  }
1219
  },
1220
- "total_flos": 2.6006738993455104e+16,
1221
  "train_batch_size": 4,
1222
  "trial_name": null,
1223
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2538666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 1190,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1198
  "mean_token_accuracy": 0.7597964540123939,
1199
  "num_tokens": 5494552.0,
1200
  "step": 1180
1201
+ },
1202
+ {
1203
+ "entropy": 0.9211089439690113,
1204
+ "epoch": 0.2538666666666667,
1205
+ "grad_norm": 0.23862819373607635,
1206
+ "learning_rate": 9.765131611726446e-05,
1207
+ "loss": 0.9742342948913574,
1208
+ "mean_token_accuracy": 0.7758729934692383,
1209
+ "num_tokens": 5540743.0,
1210
+ "step": 1190
1211
  }
1212
  ],
1213
  "logging_steps": 10,
 
1227
  "attributes": {}
1228
  }
1229
  },
1230
+ "total_flos": 2.6230647882479616e+16,
1231
  "train_batch_size": 4,
1232
  "trial_name": null,
1233
  "trial_params": null