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
0d449d5
·
verified ·
1 Parent(s): f19068d

Training in progress, step 4080, 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 sha256:93ef1f07c11a6b90609b8645142cc53829e92b3caff7920e5d03b8d02384b1b0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830be9a07eeafe0ab736f51f9d923c01e8b37b358d73134dae0b3cec1098ad9d
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2813a9854b37407768cfc611a6fce15a56bfa23a08144ae15296c551f230a0d7
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510a7ee570e02627014358f303f763f2d4294457065c18a4e40297de45b2d217
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:ab8c3cb4f9d852761b66d2cf9068feaf1e95c33532bc68ce82647b882e9fdf10
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e933d19456df795187f1211e6c9b85bac0330ea6505919982a6b62414c6317
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869bc43bd5ce66a990e097b9d9594cc766e3ea51ea3aa0b58c8fd4323f1ef782
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad51a949fc3ea36e34b6413b1ad65f923f9470c8a3a1e973509bf815584c7d26
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": 0.8682666666666666,
6
  "eval_steps": 500,
7
- "global_step": 4070,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4088,6 +4088,16 @@
4088
  "mean_token_accuracy": 0.7691247522830963,
4089
  "num_tokens": 18984144.0,
4090
  "step": 4070
 
 
 
 
 
 
 
 
 
 
4091
  }
4092
  ],
4093
  "logging_steps": 10,
@@ -4107,7 +4117,7 @@
4107
  "attributes": {}
4108
  }
4109
  },
4110
- "total_flos": 8.98662282310226e+16,
4111
  "train_batch_size": 4,
4112
  "trial_name": null,
4113
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8704,
6
  "eval_steps": 500,
7
+ "global_step": 4080,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4088
  "mean_token_accuracy": 0.7691247522830963,
4089
  "num_tokens": 18984144.0,
4090
  "step": 4070
4091
+ },
4092
+ {
4093
+ "entropy": 0.9895228892564774,
4094
+ "epoch": 0.8704,
4095
+ "grad_norm": 0.2775322198867798,
4096
+ "learning_rate": 6.298552651371316e-05,
4097
+ "loss": 1.10516300201416,
4098
+ "mean_token_accuracy": 0.7543898217380047,
4099
+ "num_tokens": 19027278.0,
4100
+ "step": 4080
4101
  }
4102
  ],
4103
  "logging_steps": 10,
 
4117
  "attributes": {}
4118
  }
4119
  },
4120
+ "total_flos": 9.007989062536704e+16,
4121
  "train_batch_size": 4,
4122
  "trial_name": null,
4123
  "trial_params": null