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
75d2870
·
verified ·
1 Parent(s): 15c66d0

Training in progress, step 4110, 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 sha256:67abef3040ebedf604da50a24ed03285a45a9d7eb7ac8c410646fd74522733e4
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9e00f753bb1bbcfb5a5ddb4fd2666ab8f228d9591da3a11c6541456f9fdf45
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09eac62166d6bc29c4117a3983eef70a68dd7fba132d72e552169f93e3fef6dc
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d123a674a35d67ad00943ce1141096bd35bf0ab734b4de43d14e05f5eebc904
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:b2bc0e78b487ec09b26f5e38995aebc28bf2ea524c98bef42a35f5b7a2fa0585
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d010fa2a336c827a39930a13e22ca671772759564efcec24e06726aba01e59d
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be8178c5ebdaf6e1bce8cdbe0782794f33579fb4f40826cc2ecce542d68e0093
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0ef84f22e1a51f0501bdb9dd2984ff5a4709a4014a3b5bf10482092bf9db69
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": 0.8746666666666667,
6
  "eval_steps": 500,
7
- "global_step": 4100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4118,6 +4118,16 @@
4118
  "mean_token_accuracy": 0.7781016409397126,
4119
  "num_tokens": 19112840.0,
4120
  "step": 4100
 
 
 
 
 
 
 
 
 
 
4121
  }
4122
  ],
4123
  "logging_steps": 10,
@@ -4137,7 +4147,7 @@
4137
  "attributes": {}
4138
  }
4139
  },
4140
- "total_flos": 9.045065692627046e+16,
4141
  "train_batch_size": 4,
4142
  "trial_name": null,
4143
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8768,
6
  "eval_steps": 500,
7
+ "global_step": 4110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4118
  "mean_token_accuracy": 0.7781016409397126,
4119
  "num_tokens": 19112840.0,
4120
  "step": 4100
4121
+ },
4122
+ {
4123
+ "entropy": 0.8111571930348873,
4124
+ "epoch": 0.8768,
4125
+ "grad_norm": 0.24323873221874237,
4126
+ "learning_rate": 6.248343714855884e-05,
4127
+ "loss": 0.8503658294677734,
4128
+ "mean_token_accuracy": 0.7953767567873001,
4129
+ "num_tokens": 19155980.0,
4130
+ "step": 4110
4131
  }
4132
  ],
4133
  "logging_steps": 10,
 
4147
  "attributes": {}
4148
  }
4149
  },
4150
+ "total_flos": 9.064289810878157e+16,
4151
  "train_batch_size": 4,
4152
  "trial_name": null,
4153
  "trial_params": null