Hugging Face's logo

eskayML
/
outputs

PEFT
Safetensors
trl
sft
unsloth
Generated from Trainer
Model card Files
xet
 Community
eskayML commited on
Commit
f14466d
·
verified ·
1 Parent(s): 1b9c858

eskayML/mistral-7b-plaba-with-context

Browse files
Files changed (4) hide show
  1. README.md +4 -4
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -37,15 +37,15 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0002
40
- - train_batch_size: 1
41
  - eval_batch_size: 8
42
  - seed: 3407
43
- - gradient_accumulation_steps: 2
44
- - total_train_batch_size: 2
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 5
48
- - training_steps: 50
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0002
40
+ - train_batch_size: 2
41
  - eval_batch_size: 8
42
  - seed: 3407
43
+ - gradient_accumulation_steps: 8
44
+ - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 5
48
+ - training_steps: 70
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "o_proj",
25
  "down_proj",
26
- "gate_proj",
27
  "up_proj",
28
- "v_proj",
 
29
  "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
 
24
  "down_proj",
25
+ "o_proj",
26
  "up_proj",
27
+ "k_proj",
28
+ "gate_proj",
29
  "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d4ef93822fa31d6279f91dace055f3a17cf3610aa87577349b99b8774ef56e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a69ed07c45f1b0e775ba3377eeb2af2c0ac3809205895543f4da2597e0696cc
3
  size 167832240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98ac43cfdbf19556a93042c8dea609ab8236bbb906076a8cde6df7f9748ad3d7
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7927bdab41cadc85a03f2e9644c66f4365ac234737b13515387f90d84705a084
3
  size 5368