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
718b59b
·
verified ·
1 Parent(s): 696ae4d

Training in progress, step 1070, 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 sha256:25e56181fd4f1ddb4dbe5e13e162041ad21bbf09a083dc51c53c025f643c9bdf
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaee39d3429fd04041eb97153c8ed2416c794f3ca1cd3b719028844572f773ae
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ad3b52df1cee3f690b86804abba0dd6de17f5c88dc2e05b97208d5d7b5c0683
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc505ffa7602ca9c31cb380c978f30c74e6f330c07bf9c826a553e4d5d75731f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f3e9df45817b517928d1682908960aeee387f74ba460bae3aff8f936fb59264
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ead786d67611b1bc6ea0b189c9fe6c35148f3fbf50d8caf39ac88f12063c33
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b2357f740163bde0b35f3740cb6e06619b381392e88bb967d59c384f7d1397e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd0335654ff33fc2ef31d0d1183d257249034b8a39cd5e36172e39810b6cddd
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": 0.22613333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1060,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1078,6 +1078,16 @@
1078
  "mean_token_accuracy": 0.7654982030391693,
1079
  "num_tokens": 4935048.0,
1080
  "step": 1060
 
 
 
 
 
 
 
 
 
 
1081
  }
1082
  ],
1083
  "logging_steps": 10,
@@ -1097,7 +1107,7 @@
1097
  "attributes": {}
1098
  }
1099
  },
1100
- "total_flos": 2.332162568702669e+16,
1101
  "train_batch_size": 4,
1102
  "trial_name": null,
1103
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.22826666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 1070,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1078
  "mean_token_accuracy": 0.7654982030391693,
1079
  "num_tokens": 4935048.0,
1080
  "step": 1060
1081
+ },
1082
+ {
1083
+ "entropy": 0.8807580441236496,
1084
+ "epoch": 0.22826666666666667,
1085
+ "grad_norm": 0.25836268067359924,
1086
+ "learning_rate": 9.823908798338061e-05,
1087
+ "loss": 0.9626541137695312,
1088
+ "mean_token_accuracy": 0.7766690820455551,
1089
+ "num_tokens": 4974286.0,
1090
+ "step": 1070
1091
  }
1092
  ],
1093
  "logging_steps": 10,
 
1107
  "attributes": {}
1108
  }
1109
  },
1110
+ "total_flos": 2.3502881401626624e+16,
1111
  "train_batch_size": 4,
1112
  "trial_name": null,
1113
  "trial_params": null