dalyaff commited on
Commit
beb841a
1 Parent(s): 6e35162

fine-tuned adapter

Browse files
README.md CHANGED
@@ -36,15 +36,21 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
- - train_batch_size: 1
40
  - eval_batch_size: 8
41
  - seed: 42
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 100
45
- - training_steps: 100
46
  - mixed_precision_training: Native AMP
47
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - PEFT 0.7.1
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
+ - train_batch_size: 5
40
  - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 24
43
+ - total_train_batch_size: 120
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 1000
48
  - mixed_precision_training: Native AMP
49
 
50
+ ### Training results
51
+
52
+
53
+
54
  ### Framework versions
55
 
56
  - PEFT 0.7.1
adapter_config.json CHANGED
@@ -19,9 +19,9 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "Wqkv",
23
  "fc1",
24
- "fc2"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "fc1",
23
+ "fc2",
24
+ "Wqkv"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e937f840c99e31817cf862c3b659de1b8994217aa851493c65ff95f3141a512d
3
- size 52444936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ef9d4778218c696aefab9a29ec361e73a50171d24b2a5102fbed53857f2d2e
3
+ size 73424880
runs/Jan14_18-45-15_ebccfba642b4/events.out.tfevents.1705258104.ebccfba642b4.5211.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7894d602f6a58b90994343df40d36e42023acde07f2ea59b85b79614a3413e1d
3
+ size 11482
special_tokens_map.json CHANGED
@@ -13,6 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
16
  "unk_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "50256": {
@@ -317,7 +318,9 @@
317
  "bos_token": "<|endoftext|>",
318
  "clean_up_tokenization_spaces": true,
319
  "eos_token": "<|endoftext|>",
 
320
  "model_max_length": 2048,
 
321
  "tokenizer_class": "CodeGenTokenizer",
322
  "unk_token": "<|endoftext|>"
323
  }
 
1
  {
2
+ "add_eos_token": true,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "50256": {
 
318
  "bos_token": "<|endoftext|>",
319
  "clean_up_tokenization_spaces": true,
320
  "eos_token": "<|endoftext|>",
321
+ "max_length": 250,
322
  "model_max_length": 2048,
323
+ "pad_token": "<|endoftext|>",
324
  "tokenizer_class": "CodeGenTokenizer",
325
  "unk_token": "<|endoftext|>"
326
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b24019b9f8b59c573402aec5817119ab811a3d22607e204bde8250664615a26
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c90cf5baa8591012894ab2332ec839b4a13568b610ec2a8277b9d78d0a3ba0
3
  size 4664