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
daa115e
·
verified ·
1 Parent(s): 27cd429

Training in progress, step 3180, 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 sha256:938f3aaa4d0a1a0f0d622f0f8a936da0c90d397c7d1b537480cd001d01294881
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f53e4a57c845b1b622d95deae45627683b3ed0feac3d195486cc323ff652afb
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4261fa0f35f36fcd8e5b9376580bb171ee48c5330fc2bf5157abb1ab166dddac
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbde89fc98026e710d3c42ce9650526f864b36a8f7f48758f725e07262ccd0cd
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:c5d4f55f44de93efe61c27fd488807e1910d727472c23376d68b9657202aa821
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e18d9e496a69d4a6c252aa121f9e8b2e06d97fd9b33e8310a0a29d63b66303
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d5820fa9451eaa8db6c9330845956e020f49e5d7d79491d1a89fd111892d4e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdafe2974e974f9386672d4bb7069924b0998118deff9bc4807913c7eba6a703
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": 0.6762666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3170,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3188,6 +3188,16 @@
3188
  "mean_token_accuracy": 0.7616261839866638,
3189
  "num_tokens": 14759139.0,
3190
  "step": 3170
 
 
 
 
 
 
 
 
 
 
3191
  }
3192
  ],
3193
  "logging_steps": 10,
@@ -3207,7 +3217,7 @@
3207
  "attributes": {}
3208
  }
3209
  },
3210
- "total_flos": 6.988322953091174e+16,
3211
  "train_batch_size": 4,
3212
  "trial_name": null,
3213
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6784,
6
  "eval_steps": 500,
7
+ "global_step": 3180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3188
  "mean_token_accuracy": 0.7616261839866638,
3189
  "num_tokens": 14759139.0,
3190
  "step": 3170
3191
+ },
3192
+ {
3193
+ "entropy": 0.9082593686878682,
3194
+ "epoch": 0.6784,
3195
+ "grad_norm": 0.23811033368110657,
3196
+ "learning_rate": 7.71603047885637e-05,
3197
+ "loss": 1.0061087608337402,
3198
+ "mean_token_accuracy": 0.7741461530327797,
3199
+ "num_tokens": 14803777.0,
3200
+ "step": 3180
3201
  }
3202
  ],
3203
  "logging_steps": 10,
 
3217
  "attributes": {}
3218
  }
3219
  },
3220
+ "total_flos": 7.01061921737257e+16,
3221
  "train_batch_size": 4,
3222
  "trial_name": null,
3223
  "trial_params": null