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
7b2582f
·
verified ·
1 Parent(s): f3d796a

Training in progress, step 3960, 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:d7dd37205821e445b5a7d9e2489cc3194c006f75635a60f487a778d3b9383eed
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b670f420757979a9fb31c3ec4b43affcd500697d29af6d7dea401ba2f6a0eb
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c336382a56f6751ba11ea53a12c04fa71cf9bca3c3cbedcb2808039b558658
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400dfb5a127d1b0ec9abe90268cbac5c504b017c5d69a2aef46cd0ca1ff8cde0
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:ea2242d0015c6567e39a1276bd53269a1edfecf37f1f9ab4ddcc03a50fb889eb
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55c12345714d8be6d36a16c94ec51addf3d39f7b5901274ffa77fab857b746bc
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f61cfeac6c03c1de877322305f0fe5970af06ba8696c8712e459b3178cf37fa4
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd51a4d436504993959ae8f83f02774da2bae404bd162c6c5acf2e3f898b796a
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": 0.8426666666666667,
6
  "eval_steps": 500,
7
- "global_step": 3950,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3968,6 +3968,16 @@
3968
  "mean_token_accuracy": 0.7689836576581002,
3969
  "num_tokens": 18413756.0,
3970
  "step": 3950
 
 
 
 
 
 
 
 
 
 
3971
  }
3972
  ],
3973
  "logging_steps": 10,
@@ -3987,7 +3997,7 @@
3987
  "attributes": {}
3988
  }
3989
  },
3990
- "total_flos": 8.718232251499622e+16,
3991
  "train_batch_size": 4,
3992
  "trial_name": null,
3993
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8448,
6
  "eval_steps": 500,
7
+ "global_step": 3960,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3968
  "mean_token_accuracy": 0.7689836576581002,
3969
  "num_tokens": 18413756.0,
3970
  "step": 3950
3971
+ },
3972
+ {
3973
+ "entropy": 0.965121752768755,
3974
+ "epoch": 0.8448,
3975
+ "grad_norm": 0.23541757464408875,
3976
+ "learning_rate": 6.497934225067736e-05,
3977
+ "loss": 1.0639681816101074,
3978
+ "mean_token_accuracy": 0.7629014477133751,
3979
+ "num_tokens": 18459252.0,
3980
+ "step": 3960
3981
  }
3982
  ],
3983
  "logging_steps": 10,
 
3997
  "attributes": {}
3998
  }
3999
  },
4000
+ "total_flos": 8.741080943330611e+16,
4001
  "train_batch_size": 4,
4002
  "trial_name": null,
4003
  "trial_params": null