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
f367155
·
verified ·
1 Parent(s): 8034401

Training in progress, step 4180, 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 sha256:9ccaeb804f9b6339376a0d6f74d6c334b6eb36fd1892507c3b34e94f66c1e1bf
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2114c8dcd45ec33a775a5a4a697a58657507a16b2a8175b54c74eeec7acbde21
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:276e770cc5b71982215faa4f50ea14c6a98017924c5feafb7578312276f64ad1
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ac86085fe63dc55718775aeefd05456a3af744a9347f5b65128becf2457502
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a4261614ec2769b75eb3eb8096c701bfd0727fa3236b57ffd43416a9c8e5839
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976c1aa93153db4d76a2109bdb54936f079dcd39ed97e5f392f47382120bde9e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c401033d069a80d943c5965c82f0efeea7af48655a969c8737a463bf9c11013
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ea95aee2e57549cdc344d0b62fe336b0c6bcde2640b7a55e4e0c10cbd7f52e
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": 0.8896,
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,
@@ -4188,6 +4188,16 @@
4188
  "mean_token_accuracy": 0.7722298249602317,
4189
  "num_tokens": 19431392.0,
4190
  "step": 4170
 
 
 
 
 
 
 
 
 
 
4191
  }
4192
  ],
4193
  "logging_steps": 10,
@@ -4207,7 +4217,7 @@
4207
  "attributes": {}
4208
  }
4209
  },
4210
- "total_flos": 9.1941886882901e+16,
4211
  "train_batch_size": 4,
4212
  "trial_name": null,
4213
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8917333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 4180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4188
  "mean_token_accuracy": 0.7722298249602317,
4189
  "num_tokens": 19431392.0,
4190
  "step": 4170
4191
+ },
4192
+ {
4193
+ "entropy": 0.874677724391222,
4194
+ "epoch": 0.8917333333333334,
4195
+ "grad_norm": 0.3088259994983673,
4196
+ "learning_rate": 6.130675423706191e-05,
4197
+ "loss": 0.9541938781738282,
4198
+ "mean_token_accuracy": 0.780048543214798,
4199
+ "num_tokens": 19476928.0,
4200
+ "step": 4180
4201
  }
4202
  ],
4203
  "logging_steps": 10,
 
4217
  "attributes": {}
4218
  }
4219
  },
4220
+ "total_flos": 9.215352160679424e+16,
4221
  "train_batch_size": 4,
4222
  "trial_name": null,
4223
  "trial_params": null