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
cf01876
·
verified ·
1 Parent(s): 34cf733

Training in progress, step 3750, 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:bbc1b89622751f053e7ff2346b133b3028758569564d88fe887d3e0eba781ce0
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13908de03ce552bb3101efbfa7154870835c3c882434bd41894cdcd4b5668712
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f40a889ff8bde7aa5f57989276fd833f13b31db95555cdd2efa4d8045ba54a8e
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fbc035d815655e1ebf380c8505c6ee8924d225e724b677fe5b699c60e5123a
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0565aab051b221c8329a27b9f3b009b32f3d27668dd77b90453c64515c758093
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5baf81fd4f5e1515efcd501efb3eb2191f05fe929ca9911a89ad5cc300fd7853
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:996645c7cd1b60a8b146fecd5fbe97bf4e16e497389a1e7205228f62963234f5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd9cd700e3b8f2fab4579116948124828e0c48e912d876c689b2a3ba68486b2
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": 0.7978666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3740,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3758,6 +3758,16 @@
3758
  "mean_token_accuracy": 0.7630825422704219,
3759
  "num_tokens": 17421511.0,
3760
  "step": 3740
 
 
 
 
 
 
 
 
 
 
3761
  }
3762
  ],
3763
  "logging_steps": 10,
@@ -3777,7 +3787,7 @@
3777
  "attributes": {}
3778
  }
3779
  },
3780
- "total_flos": 8.245690411748966e+16,
3781
  "train_batch_size": 4,
3782
  "trial_name": null,
3783
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8,
6
  "eval_steps": 500,
7
+ "global_step": 3750,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3758
  "mean_token_accuracy": 0.7630825422704219,
3759
  "num_tokens": 17421511.0,
3760
  "step": 3740
3761
+ },
3762
+ {
3763
+ "entropy": 1.0029884599149228,
3764
+ "epoch": 0.8,
3765
+ "grad_norm": 0.23356133699417114,
3766
+ "learning_rate": 6.840429660536953e-05,
3767
+ "loss": 1.0578575134277344,
3768
+ "mean_token_accuracy": 0.7524963855743408,
3769
+ "num_tokens": 17474234.0,
3770
+ "step": 3750
3771
  }
3772
  ],
3773
  "logging_steps": 10,
 
3787
  "attributes": {}
3788
  }
3789
  },
3790
+ "total_flos": 8.272621480088371e+16,
3791
  "train_batch_size": 4,
3792
  "trial_name": null,
3793
  "trial_params": null