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
fa6b52d
·
verified ·
1 Parent(s): c378f19

Training in progress, step 3210, 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 sha256:4a6194decd5c41b1d392f5b6a5526c862c4e03d75a2dd8c8d3496b537164c924
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4608fe69037e476aa864f7ed6f95bd2a736c2c081654228aba09dce283587c2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73e03c1bb5699997b82591d17eabfada95cbe056a96727cf2d2ad69cbfdf5bd7
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8191f78b55b3d9a0bb3fd6543fca84d2db9122c8a5636c8bf5a3b3013ec286b8
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:df60d642c5b261118910ad500cd47166ae3633ef9d95665fc8d6f01f0fcabd33
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa04534c1113a9f50eecadd2111ba75ec2bed9781b19da4285b5c1ab4d0e7c3e
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98f6aafd392baebf728bf16476f3c3f7a41f8a1d6e44904a5322e138fe82b0a6
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be70e4db37452226ebb82c1877b1c54bc5ac13da8cc45dd7064c1e97d5607de6
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": 0.6826666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3218,6 +3218,16 @@
3218
  "mean_token_accuracy": 0.8022488832473755,
3219
  "num_tokens": 14891820.0,
3220
  "step": 3200
 
 
 
 
 
 
 
 
 
 
3221
  }
3222
  ],
3223
  "logging_steps": 10,
@@ -3237,7 +3247,7 @@
3237
  "attributes": {}
3238
  }
3239
  },
3240
- "total_flos": 7.052555948237722e+16,
3241
  "train_batch_size": 4,
3242
  "trial_name": null,
3243
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.6848,
6
  "eval_steps": 500,
7
+ "global_step": 3210,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3218
  "mean_token_accuracy": 0.8022488832473755,
3219
  "num_tokens": 14891820.0,
3220
  "step": 3200
3221
+ },
3222
+ {
3223
+ "entropy": 1.0069321602582932,
3224
+ "epoch": 0.6848,
3225
+ "grad_norm": 0.27509671449661255,
3226
+ "learning_rate": 7.672291623287766e-05,
3227
+ "loss": 1.1010238647460937,
3228
+ "mean_token_accuracy": 0.754035946726799,
3229
+ "num_tokens": 14942310.0,
3230
+ "step": 3210
3231
  }
3232
  ],
3233
  "logging_steps": 10,
 
3247
  "attributes": {}
3248
  }
3249
  },
3250
+ "total_flos": 7.076161637037158e+16,
3251
  "train_batch_size": 4,
3252
  "trial_name": null,
3253
  "trial_params": null