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
1443e45
·
verified ·
1 Parent(s): b24d94b

Training in progress, step 1060, 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:e6ad9d4121458f767533edfdc993a25e94121f6db3ce90446eb882661c48cc1c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e56181fd4f1ddb4dbe5e13e162041ad21bbf09a083dc51c53c025f643c9bdf
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ed1ce51e87f0a8d2a2d62bf93516ea5a884b530e7bc871f3368b39235952d4
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad3b52df1cee3f690b86804abba0dd6de17f5c88dc2e05b97208d5d7b5c0683
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19468c0e1756e3077097eb2dc7d2dd2e6a8672a7daab66fbe812d41a50dfa0d7
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3e9df45817b517928d1682908960aeee387f74ba460bae3aff8f936fb59264
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da7380d5cf110b7d9db786bae99f249fd7994ec4cd093646cfbe6add9b059d77
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2357f740163bde0b35f3740cb6e06619b381392e88bb967d59c384f7d1397e
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": 0.224,
6
  "eval_steps": 500,
7
- "global_step": 1050,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1068,6 +1068,16 @@
1068
  "mean_token_accuracy": 0.7473610386252403,
1069
  "num_tokens": 4889983.0,
1070
  "step": 1050
 
 
 
 
 
 
 
 
 
 
1071
  }
1072
  ],
1073
  "logging_steps": 10,
@@ -1087,7 +1097,7 @@
1087
  "attributes": {}
1088
  }
1089
  },
1090
- "total_flos": 2.3115371048730624e+16,
1091
  "train_batch_size": 4,
1092
  "trial_name": null,
1093
  "trial_params": null
 
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,
 
1068
  "mean_token_accuracy": 0.7473610386252403,
1069
  "num_tokens": 4889983.0,
1070
  "step": 1050
1071
+ },
1072
+ {
1073
+ "entropy": 0.9305486619472504,
1074
+ "epoch": 0.22613333333333333,
1075
+ "grad_norm": 0.3190745413303375,
1076
+ "learning_rate": 9.828432562604197e-05,
1077
+ "loss": 1.0010540008544921,
1078
+ "mean_token_accuracy": 0.7654982030391693,
1079
+ "num_tokens": 4935048.0,
1080
+ "step": 1060
1081
  }
1082
  ],
1083
  "logging_steps": 10,
 
1097
  "attributes": {}
1098
  }
1099
  },
1100
+ "total_flos": 2.332162568702669e+16,
1101
  "train_batch_size": 4,
1102
  "trial_name": null,
1103
  "trial_params": null