Hugging Face's logo

floriangardin
/
chord_model

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
floriangardin commited on
Commit
7df6472
•
1 Parent(s): f4cc7f4

musiclang/musiclang-chord-v2-4k

Browse files
Files changed (7) hide show
  1. README.md +5 -3
  2. config.json +3 -3
  3. model.safetensors +2 -2
  4. runs/Jan30_17-13-27_cd32c414008c/events.out.tfevents.1706634807.cd32c414008c.2129.3 +3 -0
  5. runs/Jan30_17-14-26_cd32c414008c/events.out.tfevents.1706634867.cd32c414008c.2129.4 +3 -0
  6. runs/Jan30_17-20-40_cd32c414008c/events.out.tfevents.1706635241.cd32c414008c.2129.5 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.5901
17
 
18
  ## Model description
19
 
@@ -46,8 +46,10 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 0.7385 | 1.71 | 1000 | 0.6878 |
50
- | 0.6582 | 3.42 | 2000 | 0.5901 |
 
 
51
 
52
 
53
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.5575
17
 
18
  ## Model description
19
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.8224 | 0.85 | 500 | 0.7821 |
50
+ | 0.696 | 1.71 | 1000 | 0.6441 |
51
+ | 0.6373 | 2.56 | 1500 | 0.5845 |
52
+ | 0.6171 | 3.42 | 2000 | 0.5575 |
53
 
54
 
55
  ### Framework versions
config.json CHANGED
@@ -10,10 +10,10 @@
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
13
- "n_embd": 256,
14
- "n_head": 4,
15
  "n_inner": null,
16
- "n_layer": 4,
17
  "n_positions": 512,
18
  "padding_token_id": 3,
19
  "reorder_and_upcast_attn": false,
 
10
  "initializer_range": 0.02,
11
  "layer_norm_epsilon": 1e-05,
12
  "model_type": "gpt2",
13
+ "n_embd": 300,
14
+ "n_head": 5,
15
  "n_inner": null,
16
+ "n_layer": 5,
17
  "n_positions": 512,
18
  "padding_token_id": 3,
19
  "reorder_and_upcast_attn": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72965e9478bb4bb4b01766cd667aa4c063b1fc11e9d3360fb4ffcbce66db6cf3
3
- size 13217768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebf15034aa16bb986fdc50477a7644621a1be4d669a43e1248ad7d85d00d640
3
+ size 22359920
runs/Jan30_17-13-27_cd32c414008c/events.out.tfevents.1706634807.cd32c414008c.2129.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6890eeff93c9f12038dce578e214235c4825b814e5f3de20effe208a637517ad
3
+ size 4880
runs/Jan30_17-14-26_cd32c414008c/events.out.tfevents.1706634867.cd32c414008c.2129.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9934a852e05731bf39cd78deb15cb13a56a0324d6ad59fe2efb661e95469c3
3
+ size 6824
runs/Jan30_17-20-40_cd32c414008c/events.out.tfevents.1706635241.cd32c414008c.2129.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccc3720546e9fa1b1e7fa18643c377c3580de1da906d309f9b3290932857724
3
+ size 24051
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef5b7876ecdfda74427c1a92db98e65d22d7aa281e6d4898c7723ba7758f73aa
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b5d88586d0ada9a6ff897f9f3ddb35f33e5971ab1de235a8340a474996afe3
3
  size 4536