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
58a103e
·
verified ·
1 Parent(s): 9be668c

Training in progress, step 2470, 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:e9bbd98897007d5e0719a50c7763f7552d40805a4e0e93ef977ed80e95f6a5ac
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5daec94ab4c7edf0afd64141e9d20d9ba0bf5fd0a82b42a4c0db7494730b45
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6e6db113fb2546f5fab8dfa629322b1b35d911af46a5e369c35b7e95ee1202b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4313d1913f6e103ac08baef3aa1800e41b60704df552757850abe9d49b845397
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:ce863f92900b44410c3a7f85940b1ce75661822892c2c2c1d91f4b9948f78ed2
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff866723734e0adc58fb40ffcb7a3dd3a12e3cb3db94522b26c14c356f6f5633
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:515429dd86eeba658ae7060a39c92746d8e0bf7ad7c444e90d685bef27a27db3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca256463bf3b81d496ab75a5c499f745901944fba869752239bcb2cd2c46f99
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": 0.5248,
6
  "eval_steps": 500,
7
- "global_step": 2460,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2478,6 +2478,16 @@
2478
  "mean_token_accuracy": 0.7904586613178253,
2479
  "num_tokens": 11443565.0,
2480
  "step": 2460
 
 
 
 
 
 
 
 
 
 
2481
  }
2482
  ],
2483
  "logging_steps": 10,
@@ -2497,7 +2507,7 @@
2497
  "attributes": {}
2498
  }
2499
  },
2500
- "total_flos": 5.427367267358515e+16,
2501
  "train_batch_size": 4,
2502
  "trial_name": null,
2503
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5269333333333334,
6
  "eval_steps": 500,
7
+ "global_step": 2470,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2478
  "mean_token_accuracy": 0.7904586613178253,
2479
  "num_tokens": 11443565.0,
2480
  "step": 2460
2481
+ },
2482
+ {
2483
+ "entropy": 0.9475759953260422,
2484
+ "epoch": 0.5269333333333334,
2485
+ "grad_norm": 0.2664242088794708,
2486
+ "learning_rate": 8.65577161667927e-05,
2487
+ "loss": 1.0038702011108398,
2488
+ "mean_token_accuracy": 0.7648072987794876,
2489
+ "num_tokens": 11484816.0,
2490
+ "step": 2470
2491
  }
2492
  ],
2493
  "logging_steps": 10,
 
2507
  "attributes": {}
2508
  }
2509
  },
2510
+ "total_flos": 5.448449632929792e+16,
2511
  "train_batch_size": 4,
2512
  "trial_name": null,
2513
  "trial_params": null