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
c5a3c00
·
verified ·
1 Parent(s): 177d468

Training in progress, step 600, 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 sha256:2a0f84716d8cec074c95ed582a055c8f5d1f4b62732a4f4e906884dcdb5431b2
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61cb52070072e8afdec22ed12a2a6c0dcd897acc0f48fa5fb64af2ba786ab0de
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6b300e3ddf2612f0daf77e949a79296b8f6ea3973b76e83e594caad6a75fbb
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c721600da4eb90c4f49f8d37dbb1da796e5fbdf9c7643a9d8f761d2451dcc8b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e49732998a38b5707be22380a3b06b74ebddbc0c68379725cade23e827ead71
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d6cafb5e04141843b1a40b8ff83074c07b432b2b5a50df1e9f6d279b1eed92
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64e95c424288941f4f7d49c6fe841c41c1221a9e81e78aa0725573f3872f3f9d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e84e01eb9897f39a70561784520b1c3e4555338a3ed58b3ab5b08ab16be2ff2
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": 0.12586666666666665,
6
  "eval_steps": 500,
7
- "global_step": 590,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -608,6 +608,16 @@
608
  "mean_token_accuracy": 0.7749405071139336,
609
  "num_tokens": 2731814.0,
610
  "step": 590
 
 
 
 
 
 
 
 
 
 
611
  }
612
  ],
613
  "logging_steps": 10,
@@ -627,7 +637,7 @@
627
  "attributes": {}
628
  }
629
  },
630
- "total_flos": 1.2998476052038656e+16,
631
  "train_batch_size": 4,
632
  "trial_name": null,
633
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.128,
6
  "eval_steps": 500,
7
+ "global_step": 600,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
608
  "mean_token_accuracy": 0.7749405071139336,
609
  "num_tokens": 2731814.0,
610
  "step": 590
611
+ },
612
+ {
613
+ "entropy": 1.0139609590172767,
614
+ "epoch": 0.128,
615
+ "grad_norm": 0.26556891202926636,
616
+ "learning_rate": 9.973244969092282e-05,
617
+ "loss": 1.1074792861938476,
618
+ "mean_token_accuracy": 0.7530097424983978,
619
+ "num_tokens": 2780314.0,
620
+ "step": 600
621
  }
622
  ],
623
  "logging_steps": 10,
 
637
  "attributes": {}
638
  }
639
  },
640
+ "total_flos": 1.323906590997504e+16,
641
  "train_batch_size": 4,
642
  "trial_name": null,
643
  "trial_params": null