Hugging Face's logo

nnheui
/
zephyr-7b-kto-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
nnheui commited on
Commit
1f448bc
•
1 Parent(s): b0b7528

Model save

Browse files
Files changed (9) hide show
  1. README.md +2 -2
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. all_results.json +5 -5
  5. runs/Apr18_13-12-45_104-171-203-159/events.out.tfevents.1713446020.104-171-203-159.3711193.0 +3 -0
  6. runs/Apr18_13-14-37_104-171-203-159/events.out.tfevents.1713446111.104-171-203-159.3712827.0 +3 -0
  7. train_results.json +5 -5
  8. trainer_state.json +14 -14
  9. training_args.bin +1 -1
README.md CHANGED
@@ -40,8 +40,8 @@ The following hyperparameters were used during training:
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - distributed_type: multi-GPU
43
- - gradient_accumulation_steps: 4
44
- - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
 
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - distributed_type: multi-GPU
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: cosine
47
  - lr_scheduler_warmup_ratio: 0.1
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
- "o_proj",
24
- "down_proj",
25
- "q_proj",
26
  "gate_proj",
 
27
  "v_proj",
28
- "up_proj"
 
 
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
 
 
22
  "gate_proj",
23
+ "k_proj",
24
  "v_proj",
25
+ "q_proj",
26
+ "up_proj",
27
+ "down_proj",
28
+ "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:504cc70457d6aa2f64390f990c709688fd864a890f3aab7ed9e12586a2460d9f
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccf2aa6da043eaa987dcf38cf34fb3f402099f156d9fff0bf96e7d5fb411bf4
3
  size 671150064
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5023353099822998,
4
- "train_runtime": 47.6763,
5
- "train_samples": 30,
6
- "train_samples_per_second": 0.629,
7
- "train_steps_per_second": 0.042
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.5000961124897003,
4
+ "train_runtime": 87.0205,
5
+ "train_samples": 61,
6
+ "train_samples_per_second": 0.701,
7
+ "train_steps_per_second": 0.023
8
  }
runs/Apr18_13-12-45_104-171-203-159/events.out.tfevents.1713446020.104-171-203-159.3711193.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f683042e3a9dadac21d72be8a531f2f3f25cb8be0187be37127a1557957d6780
3
+ size 5278
runs/Apr18_13-14-37_104-171-203-159/events.out.tfevents.1713446111.104-171-203-159.3712827.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486ce07a04a64dde103b0947104165f83f3f4c8d2b961a6dd60467a29c64e55d
3
+ size 6302
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.5023353099822998,
4
- "train_runtime": 47.6763,
5
- "train_samples": 30,
6
- "train_samples_per_second": 0.629,
7
- "train_steps_per_second": 0.042
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.5000961124897003,
4
+ "train_runtime": 87.0205,
5
+ "train_samples": 61,
6
+ "train_samples_per_second": 0.701,
7
+ "train_steps_per_second": 0.023
8
  }
trainer_state.json CHANGED
@@ -10,27 +10,27 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.5,
13
- "grad_norm": 0.546875,
14
  "learning_rate": 5e-06,
15
- "logits/chosen": -3.2339999675750732,
16
- "logits/rejected": -3.2524003982543945,
17
- "logps/chosen": -330.6106262207031,
18
- "logps/rejected": -271.2039794921875,
19
- "loss": 0.5011,
20
- "rewards/accuracies": 0.4375,
21
- "rewards/chosen": -0.037355951964855194,
22
- "rewards/margins": -0.008914755657315254,
23
- "rewards/rejected": -0.02844119817018509,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 1.0,
28
  "step": 2,
29
  "total_flos": 0.0,
30
- "train_loss": 0.5023353099822998,
31
- "train_runtime": 47.6763,
32
- "train_samples_per_second": 0.629,
33
- "train_steps_per_second": 0.042
34
  }
35
  ],
36
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.5,
13
+ "grad_norm": 0.58984375,
14
  "learning_rate": 5e-06,
15
+ "logits/chosen": -3.1927170753479004,
16
+ "logits/rejected": -3.1942551136016846,
17
+ "logps/chosen": -293.9735107421875,
18
+ "logps/rejected": -260.54400634765625,
19
+ "loss": 0.5,
20
+ "rewards/accuracies": 0.34375,
21
+ "rewards/chosen": -0.0009545064531266689,
22
+ "rewards/margins": -0.0002557558473199606,
23
+ "rewards/rejected": -0.0006987505475990474,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 1.0,
28
  "step": 2,
29
  "total_flos": 0.0,
30
+ "train_loss": 0.5000961124897003,
31
+ "train_runtime": 87.0205,
32
+ "train_samples_per_second": 0.701,
33
+ "train_steps_per_second": 0.023
34
  }
35
  ],
36
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31ac445b754ae67bed5d7eeb0fe377d42820f5a6b19ee75b2727260bfe2e6ab2
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95677d0a8de9f9657c1c54ac2f6b2e70e6d9c418f6241dfcd95c3a94d606312
3
  size 5112