floriangardin
commited on
Commit
•
4099e02
1
Parent(s):
c340281
musiclang/musiclang-v2-xl
Browse files- README.md +44 -52
- config.json +9 -8
- generation_config.json +3 -3
- model.safetensors +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
@@ -11,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# model
|
13 |
|
14 |
-
This model is a fine-tuned version of [
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 0.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -32,64 +33,55 @@ More information needed
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
-
- learning_rate:
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
-
- lr_scheduler_type:
|
41 |
-
- lr_scheduler_warmup_steps:
|
42 |
-
-
|
|
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
-
|
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.5884 | 4.59 | 12400 | 0.5704 |
|
79 |
-
| 0.588 | 4.74 | 12800 | 0.5690 |
|
80 |
-
| 0.5875 | 4.89 | 13200 | 0.5685 |
|
81 |
-
| 0.5848 | 5.04 | 13600 | 0.5679 |
|
82 |
-
| 0.5827 | 5.19 | 14000 | 0.5668 |
|
83 |
-
| 0.5827 | 5.34 | 14400 | 0.5663 |
|
84 |
-
| 0.5839 | 5.48 | 14800 | 0.5658 |
|
85 |
-
| 0.5806 | 5.63 | 15200 | 0.5650 |
|
86 |
-
| 0.5803 | 5.78 | 15600 | 0.5644 |
|
87 |
-
| 0.5796 | 5.93 | 16000 | 0.5640 |
|
88 |
|
89 |
|
90 |
### Framework versions
|
91 |
|
92 |
-
- Transformers 4.
|
93 |
-
- Pytorch 2.0
|
94 |
-
- Datasets 2.
|
95 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
base_model: musiclang/musiclang-v2-xl
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
|
|
12 |
|
13 |
# model
|
14 |
|
15 |
+
This model is a fine-tuned version of [musiclang/musiclang-v2-xl](https://huggingface.co/musiclang/musiclang-v2-xl) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.2930
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
33 |
### Training hyperparameters
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 24
|
38 |
+
- eval_batch_size: 24
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: cosine_with_restarts
|
42 |
+
- lr_scheduler_warmup_steps: 500
|
43 |
+
- training_steps: 0
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:-----:|:---------------:|
|
50 |
+
| 0.4098 | 0.03 | 2000 | 0.3828 |
|
51 |
+
| 0.3901 | 0.07 | 4000 | 0.3684 |
|
52 |
+
| 0.3737 | 0.1 | 6000 | 0.3569 |
|
53 |
+
| 0.3652 | 0.13 | 8000 | 0.3489 |
|
54 |
+
| 0.356 | 0.17 | 10000 | 0.3393 |
|
55 |
+
| 0.35 | 0.2 | 12000 | 0.3342 |
|
56 |
+
| 0.3443 | 0.23 | 14000 | 0.3282 |
|
57 |
+
| 0.3371 | 0.26 | 16000 | 0.3235 |
|
58 |
+
| 0.3361 | 0.3 | 18000 | 0.3201 |
|
59 |
+
| 0.3301 | 0.33 | 20000 | 0.3160 |
|
60 |
+
| 0.3253 | 0.36 | 22000 | 0.3131 |
|
61 |
+
| 0.327 | 0.4 | 24000 | 0.3109 |
|
62 |
+
| 0.3225 | 0.43 | 26000 | 0.3089 |
|
63 |
+
| 0.3156 | 0.46 | 28000 | 0.3066 |
|
64 |
+
| 0.3147 | 0.5 | 30000 | 0.3045 |
|
65 |
+
| 0.3182 | 0.53 | 32000 | 0.3026 |
|
66 |
+
| 0.3129 | 0.56 | 34000 | 0.3017 |
|
67 |
+
| 0.3132 | 0.59 | 36000 | 0.3008 |
|
68 |
+
| 0.3109 | 0.63 | 38000 | 0.2987 |
|
69 |
+
| 0.3092 | 0.66 | 40000 | 0.2972 |
|
70 |
+
| 0.3091 | 0.69 | 42000 | 0.2963 |
|
71 |
+
| 0.3034 | 0.73 | 44000 | 0.2960 |
|
72 |
+
| 0.3061 | 0.76 | 46000 | 0.2956 |
|
73 |
+
| 0.3044 | 0.79 | 48000 | 0.2946 |
|
74 |
+
| 0.3036 | 0.83 | 50000 | 0.2940 |
|
75 |
+
| 0.3003 | 0.86 | 52000 | 0.2939 |
|
76 |
+
| 0.303 | 0.89 | 54000 | 0.2934 |
|
77 |
+
| 0.3007 | 0.93 | 56000 | 0.2932 |
|
78 |
+
| 0.3009 | 0.96 | 58000 | 0.2930 |
|
79 |
+
| 0.3 | 0.99 | 60000 | 0.2930 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
|
82 |
### Framework versions
|
83 |
|
84 |
+
- Transformers 4.37.2
|
85 |
+
- Pytorch 2.2.0+cu121
|
86 |
+
- Datasets 2.17.0
|
87 |
+
- Tokenizers 0.15.1
|
config.json
CHANGED
@@ -1,21 +1,22 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
-
"bos_token_id":
|
9 |
"embd_pdrop": 0.1,
|
10 |
-
"eos_token_id":
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
"n_embd": 300,
|
15 |
-
"n_head":
|
16 |
"n_inner": null,
|
17 |
-
"n_layer":
|
18 |
-
"n_positions":
|
|
|
19 |
"reorder_and_upcast_attn": false,
|
20 |
"resid_pdrop": 0.1,
|
21 |
"scale_attn_by_inverse_layer_idx": false,
|
@@ -26,7 +27,7 @@
|
|
26 |
"summary_type": "cls_index",
|
27 |
"summary_use_proj": true,
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.
|
30 |
"use_cache": true,
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "musiclang/musiclang-v2-xl",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 5,
|
9 |
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 374,
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
"model_type": "gpt2",
|
14 |
"n_embd": 300,
|
15 |
+
"n_head": 10,
|
16 |
"n_inner": null,
|
17 |
+
"n_layer": 10,
|
18 |
+
"n_positions": 4096,
|
19 |
+
"padding_token_id": 3,
|
20 |
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
22 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
27 |
"summary_type": "cls_index",
|
28 |
"summary_use_proj": true,
|
29 |
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.37.2",
|
31 |
"use_cache": true,
|
32 |
+
"vocab_size": 374
|
33 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 5,
|
4 |
+
"eos_token_id": 374,
|
5 |
+
"transformers_version": "4.37.2"
|
6 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0edaec61be7b684821241f0871d5e8a7b48d865f5ad1aee2495c9dc9f54290a8
|
3 |
+
size 48734696
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ded85577c88c0610c6cc2a534d279f3cac2c97cc898df360f85bd6ae1a843d78
|
3 |
+
size 4664
|