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
e0bbde0
·
verified ·
1 Parent(s): 4f66cd1

Training in progress, step 870, 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 sha256:5b8b6a1ae563c2a6072db187fe4f04086a0bc9de8975e495b407323cb2ab8d9f
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb73b24f7c24360f86d65b2aae05a3ca8d784fd150ca6942d5aa861f92a3940
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8503e14e439fb940f132eaf9f9f6416b6e02914ab8db8f998e789d3238f4c79e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:036591dbbb25389e3e01d287cccfbe6918a85cccfcf7c4483d9a8e91c3447de5
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:f877b1343eb539e4b139e6ffe314a2159804af1cd639148ba0b50465516d07e5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd521810c87442802b38d9ddb25a7dac561287aff02c46dc14fcbc8a24272fb9
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fdf5892a3b4b72d817da6c694339f4c1f62b87ad44cc3b2ed51616035415123
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:addf757fbcba66917f74ece6118fc7351d4fc2adf0697c9d475ff88757237430
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": 0.18346666666666667,
6
  "eval_steps": 500,
7
- "global_step": 860,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -878,6 +878,16 @@
878
  "mean_token_accuracy": 0.7761695921421051,
879
  "num_tokens": 3991940.0,
880
  "step": 860
 
 
 
 
 
 
 
 
 
 
881
  }
882
  ],
883
  "logging_steps": 10,
@@ -897,7 +907,7 @@
897
  "attributes": {}
898
  }
899
  },
900
- "total_flos": 1.891983250540032e+16,
901
  "train_batch_size": 4,
902
  "trial_name": null,
903
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1856,
6
  "eval_steps": 500,
7
+ "global_step": 870,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
878
  "mean_token_accuracy": 0.7761695921421051,
879
  "num_tokens": 3991940.0,
880
  "step": 860
881
+ },
882
+ {
883
+ "entropy": 1.1529859654605388,
884
+ "epoch": 0.1856,
885
+ "grad_norm": 0.26249563694000244,
886
+ "learning_rate": 9.903334622517643e-05,
887
+ "loss": 1.2724492073059082,
888
+ "mean_token_accuracy": 0.7244490720331669,
889
+ "num_tokens": 4050343.0,
890
+ "step": 870
891
  }
892
  ],
893
  "logging_steps": 10,
 
907
  "attributes": {}
908
  }
909
  },
910
+ "total_flos": 1.9197380036760576e+16,
911
  "train_batch_size": 4,
912
  "trial_name": null,
913
  "trial_params": null