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
749353f
·
verified ·
1 Parent(s): 19e3848

Training in progress, step 1170, 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:e7ec8210e40ef9bff7e21844dc5c54cfc672dd5f0b6d383b889b06d63ce78bed
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad5feee574fc9cf82f3a18445fae9dac753f73aa3e331196d1848b487ff5ce8
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:719a92384cc6dd51403e415afc1f6ae48115fe7a4d0fe5c872ac52233e2ef05b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b55f892a18476ed97b10955fe7b490a80c7dc10027c8fe73a816dca9cda332
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83fea4ca6fbd27b9f9af6bebd465d4341515a1fa3bcab48235135fa1dcf1954a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eda22a1d85d7cda0418d7dc4be938dd0c1311708873716f2b00441cf7520246
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58294efefbc57d410c163650ffb40daaa45a57196d92d68ade97704bb31c1ec1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe490c6010e0c0d8c317fef7f6184fb6f5c74dee78d88daba0e96c3f7f353e3b
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": 0.24746666666666667,
6
  "eval_steps": 500,
7
- "global_step": 1160,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1178,6 +1178,16 @@
1178
  "mean_token_accuracy": 0.7714703544974327,
1179
  "num_tokens": 5393421.0,
1180
  "step": 1160
 
 
 
 
 
 
 
 
 
 
1181
  }
1182
  ],
1183
  "logging_steps": 10,
@@ -1197,7 +1207,7 @@
1197
  "attributes": {}
1198
  }
1199
  },
1200
- "total_flos": 2.551277143593677e+16,
1201
  "train_batch_size": 4,
1202
  "trial_name": null,
1203
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2496,
6
  "eval_steps": 500,
7
+ "global_step": 1170,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1178
  "mean_token_accuracy": 0.7714703544974327,
1179
  "num_tokens": 5393421.0,
1180
  "step": 1160
1181
+ },
1182
+ {
1183
+ "entropy": 1.0325972460210324,
1184
+ "epoch": 0.2496,
1185
+ "grad_norm": 0.26943519711494446,
1186
+ "learning_rate": 9.775501575939227e-05,
1187
+ "loss": 1.0748598098754882,
1188
+ "mean_token_accuracy": 0.7444046661257744,
1189
+ "num_tokens": 5443639.0,
1190
+ "step": 1170
1191
  }
1192
  ],
1193
  "logging_steps": 10,
 
1207
  "attributes": {}
1208
  }
1209
  },
1210
+ "total_flos": 2.577578282312909e+16,
1211
  "train_batch_size": 4,
1212
  "trial_name": null,
1213
  "trial_params": null