Hugging Face's logo

YL95
/
copa_v_wright_CPT_mistral_file_folder_path_checkpoint

Transformers
Safetensors
English
text-generation-inference
unsloth
mistral
trl
Model card Files
xet
 Community
YL95 commited on
Commit
2b28f4e
·
verified ·
1 Parent(s): fd2b4aa

training state at step 80

Browse files
Files changed (1) hide show
  1. trainer_state.json +78 -3
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0344827586206897,
5
  "eval_steps": 1,
6
- "global_step": 75,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1087,6 +1087,81 @@
1087
  "eval_samples_per_second": 1.097,
1088
  "eval_steps_per_second": 0.549,
1089
  "step": 74
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1090
  }
1091
  ],
1092
  "logging_steps": 1,
@@ -1106,7 +1181,7 @@
1106
  "attributes": {}
1107
  }
1108
  },
1109
- "total_flos": 9.437537876803584e+16,
1110
  "train_batch_size": 2,
1111
  "trial_name": null,
1112
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.103448275862069,
5
  "eval_steps": 1,
6
+ "global_step": 80,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1087
  "eval_samples_per_second": 1.097,
1088
  "eval_steps_per_second": 0.549,
1089
  "step": 74
1090
+ },
1091
+ {
1092
+ "epoch": 1.0344827586206897,
1093
+ "grad_norm": 2.0641109943389893,
1094
+ "learning_rate": 4.545454545454546e-05,
1095
+ "loss": 1.0793,
1096
+ "step": 75
1097
+ },
1098
+ {
1099
+ "epoch": 1.0344827586206897,
1100
+ "eval_loss": 0.7307212948799133,
1101
+ "eval_runtime": 18.5348,
1102
+ "eval_samples_per_second": 1.079,
1103
+ "eval_steps_per_second": 0.54,
1104
+ "step": 75
1105
+ },
1106
+ {
1107
+ "epoch": 1.0482758620689656,
1108
+ "grad_norm": 1.918042778968811,
1109
+ "learning_rate": 4.772727272727273e-05,
1110
+ "loss": 1.0897,
1111
+ "step": 76
1112
+ },
1113
+ {
1114
+ "epoch": 1.0482758620689656,
1115
+ "eval_loss": 0.7253277897834778,
1116
+ "eval_runtime": 18.4554,
1117
+ "eval_samples_per_second": 1.084,
1118
+ "eval_steps_per_second": 0.542,
1119
+ "step": 76
1120
+ },
1121
+ {
1122
+ "epoch": 1.0620689655172413,
1123
+ "grad_norm": 2.216691493988037,
1124
+ "learning_rate": 5e-05,
1125
+ "loss": 1.2309,
1126
+ "step": 77
1127
+ },
1128
+ {
1129
+ "epoch": 1.0620689655172413,
1130
+ "eval_loss": 0.7224608659744263,
1131
+ "eval_runtime": 18.0728,
1132
+ "eval_samples_per_second": 1.107,
1133
+ "eval_steps_per_second": 0.553,
1134
+ "step": 77
1135
+ },
1136
+ {
1137
+ "epoch": 1.0758620689655172,
1138
+ "grad_norm": 2.304621934890747,
1139
+ "learning_rate": 4.999672209164081e-05,
1140
+ "loss": 1.1722,
1141
+ "step": 78
1142
+ },
1143
+ {
1144
+ "epoch": 1.0758620689655172,
1145
+ "eval_loss": 0.7266848683357239,
1146
+ "eval_runtime": 18.2053,
1147
+ "eval_samples_per_second": 1.099,
1148
+ "eval_steps_per_second": 0.549,
1149
+ "step": 78
1150
+ },
1151
+ {
1152
+ "epoch": 1.089655172413793,
1153
+ "grad_norm": 2.0087103843688965,
1154
+ "learning_rate": 4.998688922613788e-05,
1155
+ "loss": 1.105,
1156
+ "step": 79
1157
+ },
1158
+ {
1159
+ "epoch": 1.089655172413793,
1160
+ "eval_loss": 0.7276325225830078,
1161
+ "eval_runtime": 18.0661,
1162
+ "eval_samples_per_second": 1.107,
1163
+ "eval_steps_per_second": 0.554,
1164
+ "step": 79
1165
  }
1166
  ],
1167
  "logging_steps": 1,
 
1181
  "attributes": {}
1182
  }
1183
  },
1184
+ "total_flos": 1.0083257447114342e+17,
1185
  "train_batch_size": 2,
1186
  "trial_name": null,
1187
  "trial_params": null