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
21de28c
·
verified ·
1 Parent(s): 272ba5c

Training in progress, step 4690, 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 sha256:6a6492ef322d5597fea48d081cb22f028e55d23c7221c1f5d2c0d52b36383977
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9891707facbf59cb701e4e90396bb1b791554a7e357f79370284f032e8b2514
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c9b537d59fc8f54ed6f9bc67a07461d112b9d35e7bdba97c29c8aeae6b9c47d
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27201866dc283b390acb05f52c519567dd9a07cf765880dcaf0b0d9c6fbe32a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:627c156134610fd8bc9611a809d7d0e96a5b62384327d5b22ed21fa23dd24cb0
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:effd1a63ea106f1c978690dd1bfdc7e9c430740a23dccf7aad02d01b79cb685a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7021d506222316729103157c09f6bde2051538c7c9b802480f486047db26ae
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be13bfa65e548520ace5cebaf073676c6f5dc87bc0a9c77183829a44f1ae3b98
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": 0.9984,
6
  "eval_steps": 500,
7
- "global_step": 4680,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4698,6 +4698,16 @@
4698
  "mean_token_accuracy": 0.7623668745160103,
4699
  "num_tokens": 21747104.0,
4700
  "step": 4680
 
 
 
 
 
 
 
 
 
 
4701
  }
4702
  ],
4703
  "logging_steps": 10,
@@ -4717,7 +4727,7 @@
4717
  "attributes": {}
4718
  }
4719
  },
4720
- "total_flos": 1.0298188561140326e+17,
4721
  "train_batch_size": 4,
4722
  "trial_name": null,
4723
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.0004266666666666,
6
  "eval_steps": 500,
7
+ "global_step": 4690,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4698
  "mean_token_accuracy": 0.7623668745160103,
4699
  "num_tokens": 21747104.0,
4700
  "step": 4680
4701
+ },
4702
+ {
4703
+ "entropy": 0.9629100082736266,
4704
+ "epoch": 1.0004266666666666,
4705
+ "grad_norm": 0.3171702027320862,
4706
+ "learning_rate": 5.257762124860431e-05,
4707
+ "loss": 1.0939340591430664,
4708
+ "mean_token_accuracy": 0.7673146160025346,
4709
+ "num_tokens": 21789348.0,
4710
+ "step": 4690
4711
  }
4712
  ],
4713
  "logging_steps": 10,
 
4727
  "attributes": {}
4728
  }
4729
  },
4730
+ "total_flos": 1.0316783650958131e+17,
4731
  "train_batch_size": 4,
4732
  "trial_name": null,
4733
  "trial_params": null