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
470018e
·
verified ·
1 Parent(s): f6f622a

Training in progress, step 1110, 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 sha256:5d11c198de96d913ceb744ae87b53ac74dc6245baf78fcc2a8a89eda92fcaf3c
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc35203b5066f57c10ec28912e17ca7c2993c85147f5c6d9e968f6b9c083fdf
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b3e1e52fbce562e771a742f5ad6b2e697d3f0f09e728c7c268e58208f7ae300
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb267a645f0b9e467798a50121cfc90a60ac78850c44bddaa8430cf08de5882b
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0629240a7d81f4909c38b7f49a61ab2a8d41f48ac717724e08827e5ebfe5e4cc
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6049540202e3691d3cd2e092394351bff4b3df9ffce3cee9dc9fa33a88b4632
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fe12d5a15f606fb2e4985861955b0277bfa18a91815a68a3a508e2afb1758b0
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:792814134ab3636c6daba60a1bcb22ef4e22491c83bb44ed84495cf7562de8dd
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": 0.23466666666666666,
6
  "eval_steps": 500,
7
- "global_step": 1100,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1118,6 +1118,16 @@
1118
  "mean_token_accuracy": 0.7657159030437469,
1119
  "num_tokens": 5120632.0,
1120
  "step": 1100
 
 
 
 
 
 
 
 
 
 
1121
  }
1122
  ],
1123
  "logging_steps": 10,
@@ -1137,7 +1147,7 @@
1137
  "attributes": {}
1138
  }
1139
  },
1140
- "total_flos": 2.4204599567640576e+16,
1141
  "train_batch_size": 4,
1142
  "trial_name": null,
1143
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2368,
6
  "eval_steps": 500,
7
+ "global_step": 1110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1118
  "mean_token_accuracy": 0.7657159030437469,
1119
  "num_tokens": 5120632.0,
1120
  "step": 1100
1121
+ },
1122
+ {
1123
+ "entropy": 0.9960295349359513,
1124
+ "epoch": 0.2368,
1125
+ "grad_norm": 0.27676209807395935,
1126
+ "learning_rate": 9.805236318175672e-05,
1127
+ "loss": 1.0985889434814453,
1128
+ "mean_token_accuracy": 0.7565312668681144,
1129
+ "num_tokens": 5167690.0,
1130
+ "step": 1110
1131
  }
1132
  ],
1133
  "logging_steps": 10,
 
1147
  "attributes": {}
1148
  }
1149
  },
1150
+ "total_flos": 2.443419494579712e+16,
1151
  "train_batch_size": 4,
1152
  "trial_name": null,
1153
  "trial_params": null