Hugging Face's logo

jikaixuan
/
zephyr-ds

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jikaixuan commited on
Commit
c8462f6
•
1 Parent(s): 1d936e9

Model save

Browse files
Files changed (5) hide show
  1. adapter_model.safetensors +1 -1
  2. all_results.json +5 -5
  3. eval_results.json +3 -3
  4. train_results.json +2 -2
  5. trainer_state.json +6 -6
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4d27920bc2b739a86b45b5d78876cde77b5ebbfffbcd54acbedb78aceb29bdb
3
  size 109086672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00939d9330e0ca755ea426cd1027d9495c60be5fc0f3709bd197a1640cb76326
3
  size 109086672
all_results.json CHANGED
@@ -10,14 +10,14 @@
10
  "eval_rewards/chosen": 0.03307868540287018,
11
  "eval_rewards/margins": 0.06870328634977341,
12
  "eval_rewards/rejected": -0.03562460467219353,
13
- "eval_runtime": 441.6525,
14
  "eval_samples": 2000,
15
- "eval_samples_per_second": 4.528,
16
- "eval_steps_per_second": 0.283,
17
  "eval_use_label": 9174.8564453125,
18
  "train_loss": 0.6567496789063458,
19
- "train_runtime": 24439.922,
20
  "train_samples": 61135,
21
- "train_samples_per_second": 2.501,
22
  "train_steps_per_second": 0.039
23
  }
 
10
  "eval_rewards/chosen": 0.03307868540287018,
11
  "eval_rewards/margins": 0.06870328634977341,
12
  "eval_rewards/rejected": -0.03562460467219353,
13
+ "eval_runtime": 469.8823,
14
  "eval_samples": 2000,
15
+ "eval_samples_per_second": 4.256,
16
+ "eval_steps_per_second": 0.266,
17
  "eval_use_label": 9174.8564453125,
18
  "train_loss": 0.6567496789063458,
19
+ "train_runtime": 24286.6837,
20
  "train_samples": 61135,
21
+ "train_samples_per_second": 2.517,
22
  "train_steps_per_second": 0.039
23
  }
eval_results.json CHANGED
@@ -10,9 +10,9 @@
10
  "eval_rewards/chosen": 0.03307868540287018,
11
  "eval_rewards/margins": 0.06870328634977341,
12
  "eval_rewards/rejected": -0.03562460467219353,
13
- "eval_runtime": 441.6525,
14
  "eval_samples": 2000,
15
- "eval_samples_per_second": 4.528,
16
- "eval_steps_per_second": 0.283,
17
  "eval_use_label": 9174.8564453125
18
  }
 
10
  "eval_rewards/chosen": 0.03307868540287018,
11
  "eval_rewards/margins": 0.06870328634977341,
12
  "eval_rewards/rejected": -0.03562460467219353,
13
+ "eval_runtime": 469.8823,
14
  "eval_samples": 2000,
15
+ "eval_samples_per_second": 4.256,
16
+ "eval_steps_per_second": 0.266,
17
  "eval_use_label": 9174.8564453125
18
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6567496789063458,
4
- "train_runtime": 24439.922,
5
  "train_samples": 61135,
6
- "train_samples_per_second": 2.501,
7
  "train_steps_per_second": 0.039
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.6567496789063458,
4
+ "train_runtime": 24286.6837,
5
  "train_samples": 61135,
6
+ "train_samples_per_second": 2.517,
7
  "train_steps_per_second": 0.039
8
  }
trainer_state.json CHANGED
@@ -180,9 +180,9 @@
180
  "eval_rewards/chosen": 0.03307868540287018,
181
  "eval_rewards/margins": 0.06870328634977341,
182
  "eval_rewards/rejected": -0.03562460467219353,
183
- "eval_runtime": 443.034,
184
- "eval_samples_per_second": 4.514,
185
- "eval_steps_per_second": 0.282,
186
  "eval_use_label": 8966.8564453125,
187
  "step": 955
188
  },
@@ -191,15 +191,15 @@
191
  "step": 955,
192
  "total_flos": 0.0,
193
  "train_loss": 0.6567496789063458,
194
- "train_runtime": 24439.922,
195
- "train_samples_per_second": 2.501,
196
  "train_steps_per_second": 0.039
197
  }
198
  ],
199
  "logging_steps": 100,
200
  "max_steps": 955,
201
  "num_train_epochs": 1,
202
- "save_steps": 500,
203
  "total_flos": 0.0,
204
  "trial_name": null,
205
  "trial_params": null
 
180
  "eval_rewards/chosen": 0.03307868540287018,
181
  "eval_rewards/margins": 0.06870328634977341,
182
  "eval_rewards/rejected": -0.03562460467219353,
183
+ "eval_runtime": 474.2549,
184
+ "eval_samples_per_second": 4.217,
185
+ "eval_steps_per_second": 0.264,
186
  "eval_use_label": 8966.8564453125,
187
  "step": 955
188
  },
 
191
  "step": 955,
192
  "total_flos": 0.0,
193
  "train_loss": 0.6567496789063458,
194
+ "train_runtime": 24286.6837,
195
+ "train_samples_per_second": 2.517,
196
  "train_steps_per_second": 0.039
197
  }
198
  ],
199
  "logging_steps": 100,
200
  "max_steps": 955,
201
  "num_train_epochs": 1,
202
+ "save_steps": 10,
203
  "total_flos": 0.0,
204
  "trial_name": null,
205
  "trial_params": null