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
ebdd7bd
·
verified ·
1 Parent(s): e2338c9

Training in progress, step 2130, 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:e5088129c4003dad3b5017de7566e445b1a452d1131416c06159ea57021bf0d7
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaef5c4dbb1100be35184e3fb9dff618a4e0a29a04f80a6c2814268dd4dbd195
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aefe7b8a5249d7fe56d86787f9d56b78fd0d4fa465633ab1c8dba8e6fe92b5d9
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229718f8140e2af00da8af03c3e135e0d67e33e0bdcd4ee64fd84e2141485163
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:040b616c4d343a19d8ac7f4a94ee8608f91ce652a361d61caabcc8007973c965
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca714265660ffd42f6af4a029fea4229c61056348658f5bb4967fb06e6c2bcec
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebfe12db4af6f85a84ab2da0ea677dadec6d4b925c000eab4c3194b6835b4257
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e153808b7af9fc379c6f513ebe034ddbcbcea4e561a3c4dc5b7775bff6e3a3
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": 0.45226666666666665,
6
  "eval_steps": 500,
7
- "global_step": 2120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2138,6 +2138,16 @@
2138
  "mean_token_accuracy": 0.7480149149894715,
2139
  "num_tokens": 9821214.0,
2140
  "step": 2120
 
 
 
 
 
 
 
 
 
 
2141
  }
2142
  ],
2143
  "logging_steps": 10,
@@ -2157,7 +2167,7 @@
2157
  "attributes": {}
2158
  }
2159
  },
2160
- "total_flos": 4.659666001301914e+16,
2161
  "train_batch_size": 4,
2162
  "trial_name": null,
2163
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4544,
6
  "eval_steps": 500,
7
+ "global_step": 2130,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2138
  "mean_token_accuracy": 0.7480149149894715,
2139
  "num_tokens": 9821214.0,
2140
  "step": 2120
2141
+ },
2142
+ {
2143
+ "entropy": 1.002899456769228,
2144
+ "epoch": 0.4544,
2145
+ "grad_norm": 0.24397237598896027,
2146
+ "learning_rate": 9.031000296529336e-05,
2147
+ "loss": 1.0722038269042968,
2148
+ "mean_token_accuracy": 0.7499327704310417,
2149
+ "num_tokens": 9873482.0,
2150
+ "step": 2130
2151
  }
2152
  ],
2153
  "logging_steps": 10,
 
2167
  "attributes": {}
2168
  }
2169
  },
2170
+ "total_flos": 4.685941906788864e+16,
2171
  "train_batch_size": 4,
2172
  "trial_name": null,
2173
  "trial_params": null