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
d455675
·
verified ·
1 Parent(s): 762591f

Training in progress, step 510, 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 sha256:222f354ce672e26e119a4df981d0a477189667641a94131f5247803c806632e2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f51b986027ff7494dfb7546218531e5858e86a0dfa8ce2826577c8e8e3a78c7
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c957d847f6a5729353e8d7d7eb25041514559e2b32562cb3d0b9ad19f3ecfc9d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21397d264e7d07c529b96a66539ab2c2b1c247dabedaf0abd2e532781211dea9
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d57511ac1749e127e707489114310b0a5924c2367e986c010bc6535bb404725
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ca667eca439ea4f0f9d63e63508ccbd5c8ec29349bd074b853825b3913ec98
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28ee2fe33536c5ce94544af34c4eb4758956d214568dce7ea91d805d4d22272e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04d0231a8a8b4aa513b3f93680ff4a5ac5a972259b2f97426cf017f89b6c2b7
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": 0.10666666666666667,
6
  "eval_steps": 500,
7
- "global_step": 500,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -518,6 +518,16 @@
518
  "mean_token_accuracy": 0.7319100961089134,
519
  "num_tokens": 2309133.0,
520
  "step": 500
 
 
 
 
 
 
 
 
 
 
521
  }
522
  ],
523
  "logging_steps": 10,
@@ -537,7 +547,7 @@
537
  "attributes": {}
538
  }
539
  },
540
- "total_flos": 1.0975518808154112e+16,
541
  "train_batch_size": 4,
542
  "trial_name": null,
543
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1088,
6
  "eval_steps": 500,
7
+ "global_step": 510,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
518
  "mean_token_accuracy": 0.7319100961089134,
519
  "num_tokens": 2309133.0,
520
  "step": 500
521
+ },
522
+ {
523
+ "entropy": 0.9629665195941925,
524
+ "epoch": 0.1088,
525
+ "grad_norm": 0.2432626485824585,
526
+ "learning_rate": 9.986921620596989e-05,
527
+ "loss": 1.038647174835205,
528
+ "mean_token_accuracy": 0.7657018698751926,
529
+ "num_tokens": 2352188.0,
530
+ "step": 510
531
  }
532
  ],
533
  "logging_steps": 10,
 
547
  "attributes": {}
548
  }
549
  },
550
+ "total_flos": 1.1188442229267456e+16,
551
  "train_batch_size": 4,
552
  "trial_name": null,
553
  "trial_params": null