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
4a88c4d
·
verified ·
1 Parent(s): dc43ec3

Training in progress, step 1130, 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:e52628a0c7aae39af49a19bc026383eb668cf1ee77f536f8c5265988e4a89521
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624ca27ec31cd718988ae2e701c34d2a5c37c24af396b4f01cc7ebd4dffd90f5
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bebc472578678417f863749ba663c136aa45b4ed02bddb3b2d4dd2a080abec45
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147b98cbe08fb1ca714092fd5f88aaca8f659f61afa679247d23ed23534e325f
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cac05f14d800772ea9ca17de810c8b6ad818100db3a04e7de62285443c3fa04
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5903a6fcc85ab2e812cf0c76cb692bc37ddaa8a934113db0d28af03dac18b56a
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8180f29921749336731381af4512d6a7af639725681bd9e8dbf49efe4382b618
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3baabbd2c84ed44d6dc28874c23c6480fd913a22e79e566a7473e47b6a3dc5
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": 0.23893333333333333,
6
  "eval_steps": 500,
7
- "global_step": 1120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1138,6 +1138,16 @@
1138
  "mean_token_accuracy": 0.7664023399353027,
1139
  "num_tokens": 5209976.0,
1140
  "step": 1120
 
 
 
 
 
 
 
 
 
 
1141
  }
1142
  ],
1143
  "logging_steps": 10,
@@ -1157,7 +1167,7 @@
1157
  "attributes": {}
1158
  }
1159
  },
1160
- "total_flos": 2.463681780101837e+16,
1161
  "train_batch_size": 4,
1162
  "trial_name": null,
1163
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.24106666666666668,
6
  "eval_steps": 500,
7
+ "global_step": 1130,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1138
  "mean_token_accuracy": 0.7664023399353027,
1139
  "num_tokens": 5209976.0,
1140
  "step": 1120
1141
+ },
1142
+ {
1143
+ "entropy": 0.960879421979189,
1144
+ "epoch": 0.24106666666666668,
1145
+ "grad_norm": 0.2650390565395355,
1146
+ "learning_rate": 9.79555440968751e-05,
1147
+ "loss": 1.0518557548522949,
1148
+ "mean_token_accuracy": 0.7670834749937058,
1149
+ "num_tokens": 5257491.0,
1150
+ "step": 1130
1151
  }
1152
  ],
1153
  "logging_steps": 10,
 
1167
  "attributes": {}
1168
  }
1169
  },
1170
+ "total_flos": 2.486159182943539e+16,
1171
  "train_batch_size": 4,
1172
  "trial_name": null,
1173
  "trial_params": null