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
fc57bb8
·
verified ·
1 Parent(s): 7fadad3

Training in progress, step 2110, 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 sha256:88baf6e130dd025d7367cb6b2041757d6dc5dfe0d5a0cfc07c9f0512ceb465ae
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b776ced8c78aac80a4abe39b2298c457d422f9401db961bed3834b94ac88542b
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:398b68cb0514ab9cd4b8a6c865ebd1420b3064a4513ce0a5c01b5651f4a71b8b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd54b659d3eaa86c63d2e93a80b846e3e9732481a6ddc8a08199e259cf99cde
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:e4749d1b30a709b110e23e61415e2016f4ebf4ae472d68dd081fec452584be44
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c984125d6b74470d240a0b60f0c9979b54ec8a305937f59b6901ed64861f64d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:621e2d22465ecb33c8f957578230e4a8d20454e49cf74c74c56a5af8e4cf8969
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f73b3e4e2bd57599755af9d2abc683e515e4a1bbc0214b088b1d7601c53afa
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": 0.448,
6
  "eval_steps": 500,
7
- "global_step": 2100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2118,6 +2118,16 @@
2118
  "mean_token_accuracy": 0.7796914517879486,
2119
  "num_tokens": 9717399.0,
2120
  "step": 2100
 
 
 
 
 
 
 
 
 
 
2121
  }
2122
  ],
2123
  "logging_steps": 10,
@@ -2137,7 +2147,7 @@
2137
  "attributes": {}
2138
  }
2139
  },
2140
- "total_flos": 4.609600564894618e+16,
2141
  "train_batch_size": 4,
2142
  "trial_name": null,
2143
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.45013333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 2110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2118
  "mean_token_accuracy": 0.7796914517879486,
2119
  "num_tokens": 9717399.0,
2120
  "step": 2100
2121
+ },
2122
+ {
2123
+ "entropy": 1.0308616764843463,
2124
+ "epoch": 0.45013333333333333,
2125
+ "grad_norm": 0.2896214723587036,
2126
+ "learning_rate": 9.051382839675005e-05,
2127
+ "loss": 1.1293525695800781,
2128
+ "mean_token_accuracy": 0.7496985673904419,
2129
+ "num_tokens": 9766859.0,
2130
+ "step": 2110
2131
  }
2132
  ],
2133
  "logging_steps": 10,
 
2147
  "attributes": {}
2148
  }
2149
  },
2150
+ "total_flos": 4.633604578289357e+16,
2151
  "train_batch_size": 4,
2152
  "trial_name": null,
2153
  "trial_params": null