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
bb22221
·
verified ·
1 Parent(s): b9eeeb4

Training in progress, step 2040, 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:b905651374eb2e59d0098ec78dfa8fd628bebad699c69be6259081f8ca6eed83
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0865878ab8c84da9c28b5beeffc5d1ca448d0538c6a414a4c98f17773bd3041
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00f2dda045580becfc005e53e68449b8bb0898dc88d89856d32ed14d13b1d111
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffcb646fe5e9bd792eaca38e55b80b62221173cee7784bced5245bb7ef86302
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69278b4a3681b01d8f701e80b23385d7d42b83b4d66e68ecd0a5a2973bcf8f5b
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c0f56c5d7a9ebe68efe0b2374595948fa35446985c60cf71092048ae4657e3
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d5461865fd39a6a349b4cd5c7ceb6252061309c8a68ee111d9578fa57092966
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331c76566887bc46d0c9e202654ba3a432bd85731f1fc4302d3f95c92b195cb9
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": 0.43306666666666666,
6
  "eval_steps": 500,
7
- "global_step": 2030,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2048,6 +2048,16 @@
2048
  "mean_token_accuracy": 0.7726532012224198,
2049
  "num_tokens": 9396928.0,
2050
  "step": 2030
 
 
 
 
 
 
 
 
 
 
2051
  }
2052
  ],
2053
  "logging_steps": 10,
@@ -2067,7 +2077,7 @@
2067
  "attributes": {}
2068
  }
2069
  },
2070
- "total_flos": 4.459659291556147e+16,
2071
  "train_batch_size": 4,
2072
  "trial_name": null,
2073
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4352,
6
  "eval_steps": 500,
7
+ "global_step": 2040,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2048
  "mean_token_accuracy": 0.7726532012224198,
2049
  "num_tokens": 9396928.0,
2050
  "step": 2030
2051
+ },
2052
+ {
2053
+ "entropy": 1.0050749816000462,
2054
+ "epoch": 0.4352,
2055
+ "grad_norm": 0.30352818965911865,
2056
+ "learning_rate": 9.121186360026625e-05,
2057
+ "loss": 1.0613908767700195,
2058
+ "mean_token_accuracy": 0.7496299520134926,
2059
+ "num_tokens": 9449045.0,
2060
+ "step": 2040
2061
  }
2062
  ],
2063
  "logging_steps": 10,
 
2077
  "attributes": {}
2078
  }
2079
  },
2080
+ "total_flos": 4.483463241466368e+16,
2081
  "train_batch_size": 4,
2082
  "trial_name": null,
2083
  "trial_params": null