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
9ddcf18
·
verified ·
1 Parent(s): 72583cf

Training in progress, step 4170, 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:aaa1aff895909357c44b573ec0398e815d0c193c67f6bfa729c43cef731a961f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccaeb804f9b6339376a0d6f74d6c334b6eb36fd1892507c3b34e94f66c1e1bf
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0814b042d85845cd3e60cea5526bc76ccfce20863f8155bc29ec1425745fb36
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276e770cc5b71982215faa4f50ea14c6a98017924c5feafb7578312276f64ad1
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86b0fb6ec03bb62ad28e8db71f76e05ff97d321967538f6fbb900f70e388757a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4261614ec2769b75eb3eb8096c701bfd0727fa3236b57ffd43416a9c8e5839
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f52c47069f2ea2fa68023d25c01778c684b9f67ab4160ebd0ff0b45183ef6e5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c401033d069a80d943c5965c82f0efeea7af48655a969c8737a463bf9c11013
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": 0.8874666666666666,
6
  "eval_steps": 500,
7
- "global_step": 4160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4178,6 +4178,16 @@
4178
  "mean_token_accuracy": 0.7473259434103966,
4179
  "num_tokens": 19389016.0,
4180
  "step": 4160
 
 
 
 
 
 
 
 
 
 
4181
  }
4182
  ],
4183
  "logging_steps": 10,
@@ -4197,7 +4207,7 @@
4197
  "attributes": {}
4198
  }
4199
  },
4200
- "total_flos": 9.172663839967027e+16,
4201
  "train_batch_size": 4,
4202
  "trial_name": null,
4203
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8896,
6
  "eval_steps": 500,
7
+ "global_step": 4170,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4178
  "mean_token_accuracy": 0.7473259434103966,
4179
  "num_tokens": 19389016.0,
4180
  "step": 4160
4181
+ },
4182
+ {
4183
+ "entropy": 0.913795480877161,
4184
+ "epoch": 0.8896,
4185
+ "grad_norm": 0.27178287506103516,
4186
+ "learning_rate": 6.147527434696606e-05,
4187
+ "loss": 0.976069450378418,
4188
+ "mean_token_accuracy": 0.7722298249602317,
4189
+ "num_tokens": 19431392.0,
4190
+ "step": 4170
4191
  }
4192
  ],
4193
  "logging_steps": 10,
 
4207
  "attributes": {}
4208
  }
4209
  },
4210
+ "total_flos": 9.1941886882901e+16,
4211
  "train_batch_size": 4,
4212
  "trial_name": null,
4213
  "trial_params": null