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
186d5d0
·
verified ·
1 Parent(s): 90af5c7

Training in progress, step 3240, 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:f5b6c49a89b818fae7e43099549ab78942ef74295d9f0164274bd532e97032ec
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd77f1b3f13538dff50a54bf48cb5033ae2636165fc65f96ba5652b40e228d67
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a64ab1c3fc005d0d2a54b385f20178137782cde6a1af8fd86b4df9afe71dc6f0
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c31708972f03cbbb12faff860abf54d12dc7a0a6f537ad6c897df2b4399f530
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:a9268c21752be987a94c355fcd6ae36d5c7bb827e224143b666e97ceab2a849e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7645ceb437a1bf47ff33880713453654d7140e1fb2063a51d9d8b6aaba4a8bb
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8818d19799a786ad326cffe909aba04c6116b03178ac87a8a92ddf5ce677c742
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7afa5750e2666b51da44554243ef6f97f2cf8352363ecb104ef1a19b20e6d3
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": 0.6890666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3230,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3248,6 +3248,16 @@
3248
  "mean_token_accuracy": 0.7634354814887047,
3249
  "num_tokens": 15031665.0,
3250
  "step": 3230
 
 
 
 
 
 
 
 
 
 
3251
  }
3252
  ],
3253
  "logging_steps": 10,
@@ -3267,7 +3277,7 @@
3267
  "attributes": {}
3268
  }
3269
  },
3270
- "total_flos": 7.118298431386829e+16,
3271
  "train_batch_size": 4,
3272
  "trial_name": null,
3273
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6912,
6
  "eval_steps": 500,
7
+ "global_step": 3240,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3248
  "mean_token_accuracy": 0.7634354814887047,
3249
  "num_tokens": 15031665.0,
3250
  "step": 3230
3251
+ },
3252
+ {
3253
+ "entropy": 0.930540493875742,
3254
+ "epoch": 0.6912,
3255
+ "grad_norm": 0.2832178473472595,
3256
+ "learning_rate": 7.628264608029277e-05,
3257
+ "loss": 1.0797764778137207,
3258
+ "mean_token_accuracy": 0.768897658586502,
3259
+ "num_tokens": 15075297.0,
3260
+ "step": 3240
3261
  }
3262
  ],
3263
  "logging_steps": 10,
 
3277
  "attributes": {}
3278
  }
3279
  },
3280
+ "total_flos": 7.139329429306675e+16,
3281
  "train_batch_size": 4,
3282
  "trial_name": null,
3283
  "trial_params": null