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
db9a7c2
·
verified ·
1 Parent(s): 5ec0688

Training in progress, step 770, 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:b61e639daf8257b450734dde575943cbb28c16807f6d54b412a9169cb98302b4
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad62e2b74554573c36e4e3440f7df6858d927c779bb32c2b00e20824529e7ee4
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46abcb12fceb1a18599d949d1f8176e0983d2cb632777d17c673f9c6db163c6e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e0c21fbd09091df69cd791b70a189dabb850f2ab31c6e5612663d577593b28
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:aaa5bf999af491adfda83a24f55a7a482c289639f30844801b5a09cef7e58eb1
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49f0bd33096188e4746ed896130bf2f1f38416a2ac5ac5c907d539f510ed389
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ee219d0f4408ed9b4286a66a6b9f33bf2c6758ea01303339bdb8d42db7c01de
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a094df716bc33e4f28da09e88cd908e7c42805aa24ce6e5025451d29a3900ce0
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": 0.16213333333333332,
6
  "eval_steps": 500,
7
- "global_step": 760,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -778,6 +778,16 @@
778
  "mean_token_accuracy": 0.7544152162969112,
779
  "num_tokens": 3528140.0,
780
  "step": 760
 
 
 
 
 
 
 
 
 
 
781
  }
782
  ],
783
  "logging_steps": 10,
@@ -797,7 +807,7 @@
797
  "attributes": {}
798
  }
799
  },
800
- "total_flos": 1.6687105994437632e+16,
801
  "train_batch_size": 4,
802
  "trial_name": null,
803
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.16426666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 770,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
778
  "mean_token_accuracy": 0.7544152162969112,
779
  "num_tokens": 3528140.0,
780
  "step": 760
781
+ },
782
+ {
783
+ "entropy": 0.9826410934329033,
784
+ "epoch": 0.16426666666666667,
785
+ "grad_norm": 0.20811501145362854,
786
+ "learning_rate": 9.934258069840765e-05,
787
+ "loss": 1.0858916282653808,
788
+ "mean_token_accuracy": 0.7535254985094071,
789
+ "num_tokens": 3578130.0,
790
+ "step": 770
791
  }
792
  ],
793
  "logging_steps": 10,
 
807
  "attributes": {}
808
  }
809
  },
810
+ "total_flos": 1.6928011267777536e+16,
811
  "train_batch_size": 4,
812
  "trial_name": null,
813
  "trial_params": null