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
2d84328
·
verified ·
1 Parent(s): 7fdc67c

Training in progress, step 3390, 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:bd3163ea4ecda2dd3295cc8084688e97c54a9b66618650e065018637b5623acb
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d4592d676f09e52407436dbde7f3210bd40876daf20e121a9e622fd85a4db0b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf86301750b1b5da2090cbb265bbc1fa9ec01099b683cb6f301cd75225067363
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9ab14bce1bc5045ab7da6fa980d4cddc8688989d148bfd07cd5482a597dc64
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22c9f8513070c222196bbd9fb5737c7f860237d83ffb0525bd5ab7f8561ae027
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9157204a896e954a18befa1d2242e3ee9b6a0d6242abcd6b713adffb5a82dabc
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82112089131b59c9c09e5311962aa5585309e7ce7360243d8a501733bc00b65c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3514931ba26a784b8df45c0d5696df81ebd8cf3276f8361aea2d5af4942ead14
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": 0.7210666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3380,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3398,6 +3398,16 @@
3398
  "mean_token_accuracy": 0.7620216578245163,
3399
  "num_tokens": 15736780.0,
3400
  "step": 3380
 
 
 
 
 
 
 
 
 
 
3401
  }
3402
  ],
3403
  "logging_steps": 10,
@@ -3417,7 +3427,7 @@
3417
  "attributes": {}
3418
  }
3419
  },
3420
- "total_flos": 7.454063535555072e+16,
3421
  "train_batch_size": 4,
3422
  "trial_name": null,
3423
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.7232,
6
  "eval_steps": 500,
7
+ "global_step": 3390,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3398
  "mean_token_accuracy": 0.7620216578245163,
3399
  "num_tokens": 15736780.0,
3400
  "step": 3380
3401
+ },
3402
+ {
3403
+ "entropy": 1.0298451118171215,
3404
+ "epoch": 0.7232,
3405
+ "grad_norm": 0.24461258947849274,
3406
+ "learning_rate": 7.403974359077664e-05,
3407
+ "loss": 1.080700397491455,
3408
+ "mean_token_accuracy": 0.7475218966603279,
3409
+ "num_tokens": 15789887.0,
3410
+ "step": 3390
3411
  }
3412
  ],
3413
  "logging_steps": 10,
 
3427
  "attributes": {}
3428
  }
3429
  },
3430
+ "total_flos": 7.480277259148186e+16,
3431
  "train_batch_size": 4,
3432
  "trial_name": null,
3433
  "trial_params": null