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
d4aa5bd
·
verified ·
1 Parent(s): 7c3ef72

Training in progress, step 3150, 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 sha256:4325c83eeaaab353f576a0884a71791cc1d10d022f7ce5df9bc7909f2b326b7c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d560ff817dfac4f9147e1874151e30b83983e05ede84975e74ba4bd59966673a
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1ae5f00c354813d470dc5d2652f42b52bc5fd547433d7a4f128eb30bb49a691
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc352006581ccb9b03cc48447916af0800c6239bfc465ae0f03ff87136648083
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:e3dbf16553ca10ca422c033d8d9e4b9a17b9a6eb512c4a659d5e962c9f59e34a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bf9a57bf0fd474140b07d510b514e3540464b5559f1ada46e314a4d7c2e4fc
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5388f4e8040f2763e3ad91c567cc7c5a914c75d4a7373057013d5cb7818a95b7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111792031b33509ffa520007d27dc056f08f30da1f6b601c34c59facd57f4dc0
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": 0.6698666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3140,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3158,6 +3158,16 @@
3158
  "mean_token_accuracy": 0.7521986544132233,
3159
  "num_tokens": 14620140.0,
3160
  "step": 3140
 
 
 
 
 
 
 
 
 
 
3161
  }
3162
  ],
3163
  "logging_steps": 10,
@@ -3177,7 +3187,7 @@
3177
  "attributes": {}
3178
  }
3179
  },
3180
- "total_flos": 6.922965276734362e+16,
3181
  "train_batch_size": 4,
3182
  "trial_name": null,
3183
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.672,
6
  "eval_steps": 500,
7
+ "global_step": 3150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3158
  "mean_token_accuracy": 0.7521986544132233,
3159
  "num_tokens": 14620140.0,
3160
  "step": 3140
3161
+ },
3162
+ {
3163
+ "entropy": 0.8929514214396477,
3164
+ "epoch": 0.672,
3165
+ "grad_norm": 0.24498853087425232,
3166
+ "learning_rate": 7.759476458268165e-05,
3167
+ "loss": 0.9452738761901855,
3168
+ "mean_token_accuracy": 0.7730352610349656,
3169
+ "num_tokens": 14664132.0,
3170
+ "step": 3150
3171
  }
3172
  ],
3173
  "logging_steps": 10,
 
3187
  "attributes": {}
3188
  }
3189
  },
3190
+ "total_flos": 6.943624985664922e+16,
3191
  "train_batch_size": 4,
3192
  "trial_name": null,
3193
  "trial_params": null