danangwijaya commited on
Commit
e908a76
1 Parent(s): 0546cdb

End of training

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - liputan6
6
+ model-index:
7
+ - name: IndoRetNet-Liputan6
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # IndoRetNet-Liputan6
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the liputan6 dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.4936
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0006
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 32
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 10
46
+ - num_epochs: 3.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:-----:|:---------------:|
53
+ | 4.5053 | 0.17 | 1000 | 4.5145 |
54
+ | 4.1281 | 0.34 | 2000 | 4.1702 |
55
+ | 3.9452 | 0.52 | 3000 | 4.0094 |
56
+ | 3.8302 | 0.69 | 4000 | 3.8972 |
57
+ | 3.6955 | 0.86 | 5000 | 3.8144 |
58
+ | 3.589 | 1.03 | 6000 | 3.7600 |
59
+ | 3.5279 | 1.21 | 7000 | 3.7088 |
60
+ | 3.4598 | 1.38 | 8000 | 3.6670 |
61
+ | 3.4445 | 1.55 | 9000 | 3.6259 |
62
+ | 3.4098 | 1.72 | 10000 | 3.5904 |
63
+ | 3.3455 | 1.9 | 11000 | 3.5610 |
64
+ | 3.2306 | 2.07 | 12000 | 3.5406 |
65
+ | 3.261 | 2.24 | 13000 | 3.5216 |
66
+ | 3.2204 | 2.41 | 14000 | 3.5111 |
67
+ | 3.2321 | 2.59 | 15000 | 3.5001 |
68
+ | 3.2514 | 2.76 | 16000 | 3.4941 |
69
+ | 3.233 | 2.93 | 17000 | 3.4936 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.36.2
75
+ - Pytorch 2.1.0+cu121
76
+ - Datasets 2.16.1
77
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_fn": "swish",
4
+ "architectures": [
5
+ "RetNetForCausalLM"
6
+ ],
7
+ "decoder_embed_dim": 512,
8
+ "decoder_ffn_embed_dim": 864,
9
+ "decoder_layers": 6,
10
+ "decoder_normalize_before": true,
11
+ "decoder_retention_heads": 8,
12
+ "decoder_value_embed_dim": 864,
13
+ "deepnorm": false,
14
+ "drop_path_rate": 0.0,
15
+ "dropout": 0.1,
16
+ "eos_token_id": 0,
17
+ "forward_impl": "parallel",
18
+ "initializer_range": 0.02,
19
+ "is_decoder": true,
20
+ "layernorm_embedding": true,
21
+ "layernorm_eps": 1e-06,
22
+ "model_type": "retnet",
23
+ "no_scale_embedding": false,
24
+ "output_retentions": false,
25
+ "pad_token_id": 0,
26
+ "recurrent_chunk_size": 512,
27
+ "subln": true,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.2",
31
+ "use_cache": true,
32
+ "use_ffn_rms_norm": false,
33
+ "use_glu": true,
34
+ "use_lm_decay": false,
35
+ "vocab_size": 50257,
36
+ "z_loss_coeff": 0.0
37
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.36.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dfd1d4402f906514c3e0191309f57e2277578019f46fa4194fbe28605467d59
3
+ size 282172696
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2231034ab91c23466ddeabc12138856f6ac0e8d9878d66c1aeecc179e49811e6
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff