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
c9b93de
·
verified ·
1 Parent(s): 848338a

Training in progress, step 990, 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 sha256:4f634f9369074472a2e31f37db9850b242418fa532f43fb64cff4d43ef4439cd
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848e02636e0046033d9d268b11b8866792f016fe069218d56b1760048f69279b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc695542096599de55f0b5fcd2b2a385ef2345628b4ebd642ca809fc52d1c22f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8389e1882d08a021929d18a6409fa4d36586fdf03bbacdac2f205afc288a52d
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:b2f8c970e66b7de8d3227575da95e6238c27e97b698e58fdbf57e5c81e2daf3a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3989d47215da2bcc5045af1a18f7c3a86c0f88e6c255f680417c43a9ee431231
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b2724ce615aaf3d4c61df0be59b979f77e4cf27ed07d6f1feddad50f287959
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8f9c9d73e107a6fe9aa154fef44fffd34f66bdb9b1ffbe5b54066724b10b13
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": 0.20906666666666668,
6
  "eval_steps": 500,
7
- "global_step": 980,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -998,6 +998,16 @@
998
  "mean_token_accuracy": 0.7514706686139107,
999
  "num_tokens": 4575636.0,
1000
  "step": 980
 
 
 
 
 
 
 
 
 
 
1001
  }
1002
  ],
1003
  "logging_steps": 10,
@@ -1017,7 +1027,7 @@
1017
  "attributes": {}
1018
  }
1019
  },
1020
- "total_flos": 2.1652970059981824e+16,
1021
  "train_batch_size": 4,
1022
  "trial_name": null,
1023
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2112,
6
  "eval_steps": 500,
7
+ "global_step": 990,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
998
  "mean_token_accuracy": 0.7514706686139107,
999
  "num_tokens": 4575636.0,
1000
  "step": 980
1001
+ },
1002
+ {
1003
+ "entropy": 0.9148829184472561,
1004
+ "epoch": 0.2112,
1005
+ "grad_norm": 0.44951871037483215,
1006
+ "learning_rate": 9.85847611558218e-05,
1007
+ "loss": 1.0038617134094239,
1008
+ "mean_token_accuracy": 0.7708485037088394,
1009
+ "num_tokens": 4623275.0,
1010
+ "step": 990
1011
  }
1012
  ],
1013
  "logging_steps": 10,
 
1027
  "attributes": {}
1028
  }
1029
  },
1030
+ "total_flos": 2.1869624394725376e+16,
1031
  "train_batch_size": 4,
1032
  "trial_name": null,
1033
  "trial_params": null