Hugging Face's logo

KaixuanJi
/
zephyr-7b-dpo-lora

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Model card Files Metrics Community
Jerry Ji commited on
Commit
e7a8b93
·
1 Parent(s): 95ee68d

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. adapter_config.json +4 -4
  2. adapter_model.safetensors +2 -2
  3. all_results.json +5 -18
  4. train_results.json +5 -5
  5. trainer_state.json +0 -0
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "q_proj",
20
- "k_proj",
21
  "v_proj",
22
- "o_proj"
 
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "v_proj",
20
+ "o_proj",
21
+ "k_proj",
22
+ "q_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df7c66b2ac34303827d857d3d4c0b6dffe70d61b1d97fa62cb2a93d5af147460
3
- size 218138576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8871811ad1829b0923b3045a3284f49bcafa69b38137e8e095f39d13b1e437b1
3
+ size 109086672
all_results.json CHANGED
@@ -1,21 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_logits/chosen": -2.0662753582000732,
4
- "eval_logits/rejected": -1.9411602020263672,
5
- "eval_logps/chosen": -266.15380859375,
6
- "eval_logps/rejected": -228.28196716308594,
7
- "eval_loss": 0.5263338685035706,
8
- "eval_rewards/accuracies": 0.7480000257492065,
9
- "eval_rewards/chosen": -0.14929771423339844,
10
- "eval_rewards/margins": 0.7504671812057495,
11
- "eval_rewards/rejected": -0.899764895439148,
12
- "eval_runtime": 443.1683,
13
- "eval_samples": 2000,
14
- "eval_samples_per_second": 4.513,
15
- "eval_steps_per_second": 0.282,
16
- "train_loss": 0.5640471254170105,
17
- "train_runtime": 84492.9354,
18
  "train_samples": 61966,
19
- "train_samples_per_second": 2.2,
20
- "train_steps_per_second": 0.034
21
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6731863415930882,
4
+ "train_runtime": 27311.2139,
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "train_samples": 61966,
6
+ "train_samples_per_second": 2.269,
7
+ "train_steps_per_second": 0.035
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 3.0,
3
- "train_loss": 0.5640471254170105,
4
- "train_runtime": 84492.9354,
5
  "train_samples": 61966,
6
- "train_samples_per_second": 2.2,
7
- "train_steps_per_second": 0.034
8
  }
 
1
  {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6731863415930882,
4
+ "train_runtime": 27311.2139,
5
  "train_samples": 61966,
6
+ "train_samples_per_second": 2.269,
7
+ "train_steps_per_second": 0.035
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fc66c772c0a45fc2b3937369ccc3768508ec3d91869b201909e9cda99c3c455
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdefb077695dcf29ef41f5fe1cec41780efc249a1ae6388bcd274fd33ef9945
3
  size 4792