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
e7e3d52
·
verified ·
1 Parent(s): 0a363e0

Training in progress, step 110, 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:eb454717f18f3a4368d7c3040ee8cc9208602f5fcab68e9b67e853914f25bb11
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624f7058064d76847152a7aff03ccc76f9687853b2fe9892d721cbe8fffcd2c4
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1e6b83be3aaeeec6eb14808af346bd67cffb95129b57d9698d96e413b331d93
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065f308e48674fbaead7fbe7336d030bb7aff58e7b4632d7a51e4ace7e66a063
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:c20d77fd0f8ca8e0d959a35902916d9113e4094ff6f70fdce68809f2cc07e7d7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503c8a7590e7af91329256ad3aad149e4b5fc6f9829d279e0510c95425b510ab
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d40d7ee4cb3750a04a94c1e6c33db3b3326535948996cc27f9d31f301ea90e48
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255c2565ea9ef2b84420f28b6a4b847239969551451003011398fa9bc80fd20c
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": 0.021333333333333333,
6
  "eval_steps": 500,
7
- "global_step": 100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -118,6 +118,16 @@
118
  "mean_token_accuracy": 0.6885988213121891,
119
  "num_tokens": 462284.0,
120
  "step": 100
 
 
 
 
 
 
 
 
 
 
121
  }
122
  ],
123
  "logging_steps": 10,
@@ -137,7 +147,7 @@
137
  "attributes": {}
138
  }
139
  },
140
- "total_flos": 2246830085434368.0,
141
  "train_batch_size": 4,
142
  "trial_name": null,
143
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.023466666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
118
  "mean_token_accuracy": 0.6885988213121891,
119
  "num_tokens": 462284.0,
120
  "step": 100
121
+ },
122
+ {
123
+ "entropy": 1.3056970939040184,
124
+ "epoch": 0.023466666666666667,
125
+ "grad_norm": 0.4493468701839447,
126
+ "learning_rate": 3.633333333333333e-05,
127
+ "loss": 1.2876591682434082,
128
+ "mean_token_accuracy": 0.7173117578029633,
129
+ "num_tokens": 508883.0,
130
+ "step": 110
131
  }
132
  ],
133
  "logging_steps": 10,
 
147
  "attributes": {}
148
  }
149
  },
150
+ "total_flos": 2463835883056128.0,
151
  "train_batch_size": 4,
152
  "trial_name": null,
153
  "trial_params": null