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
0f8bb66
·
verified ·
1 Parent(s): b5ab7de

Training in progress, step 2050, 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:e0865878ab8c84da9c28b5beeffc5d1ca448d0538c6a414a4c98f17773bd3041
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b9ebb7d0a4d9ba058b3b8554694658447acc65ca78331821e03c4bb71ef4f5
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ffcb646fe5e9bd792eaca38e55b80b62221173cee7784bced5245bb7ef86302
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66eb74738fb84d8442383b2e6539dfaee12bcb030b7b71e7b396f48ae1ca113c
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61c0f56c5d7a9ebe68efe0b2374595948fa35446985c60cf71092048ae4657e3
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3a9215814521eedf613c295d42129542ebe5c44e1f5bf54c74a569a258fb7a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:331c76566887bc46d0c9e202654ba3a432bd85731f1fc4302d3f95c92b195cb9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88387d21c5e510a789d0d790ff99b950be09036cfa7a0c5c786c5bf5cf53ad60
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": 0.4352,
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,
@@ -2058,6 +2058,16 @@
2058
  "mean_token_accuracy": 0.7496299520134926,
2059
  "num_tokens": 9449045.0,
2060
  "step": 2040
 
 
 
 
 
 
 
 
 
 
2061
  }
2062
  ],
2063
  "logging_steps": 10,
@@ -2077,7 +2087,7 @@
2077
  "attributes": {}
2078
  }
2079
  },
2080
- "total_flos": 4.483463241466368e+16,
2081
  "train_batch_size": 4,
2082
  "trial_name": null,
2083
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.43733333333333335,
6
  "eval_steps": 500,
7
+ "global_step": 2050,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2058
  "mean_token_accuracy": 0.7496299520134926,
2059
  "num_tokens": 9449045.0,
2060
  "step": 2040
2061
+ },
2062
+ {
2063
+ "entropy": 0.919689030200243,
2064
+ "epoch": 0.43733333333333335,
2065
+ "grad_norm": 0.33956724405288696,
2066
+ "learning_rate": 9.111361614629022e-05,
2067
+ "loss": 0.9860305786132812,
2068
+ "mean_token_accuracy": 0.7708889573812485,
2069
+ "num_tokens": 9498718.0,
2070
+ "step": 2050
2071
  }
2072
  ],
2073
  "logging_steps": 10,
 
2087
  "attributes": {}
2088
  }
2089
  },
2090
+ "total_flos": 4.507850259279667e+16,
2091
  "train_batch_size": 4,
2092
  "trial_name": null,
2093
  "trial_params": null