eightynine01
commited on
Commit
•
3d82d51
1
Parent(s):
2a77756
End of training
Browse files- README.md +66 -0
- config.json +48 -0
- model.safetensors +3 -0
- runs/May30_18-03-06_one/events.out.tfevents.1717059786.one.682896.14 +3 -0
- runs/May30_18-03-06_one/events.out.tfevents.1717060072.one.682896.15 +3 -0
- runs/May30_18-39-39_one/events.out.tfevents.1717061980.one.682896.19 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: ibm/TTM
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: fewshot_10
|
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 |
+
# fewshot_10
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [ibm/TTM](https://huggingface.co/ibm/TTM) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.0405
|
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: 0.001
|
38 |
+
- train_batch_size: 512
|
39 |
+
- eval_batch_size: 512
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 10
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 0.1341 | 1.0 | 48 | 0.0386 |
|
50 |
+
| 0.1293 | 2.0 | 96 | 0.0383 |
|
51 |
+
| 0.1268 | 3.0 | 144 | 0.0382 |
|
52 |
+
| 0.1245 | 4.0 | 192 | 0.0382 |
|
53 |
+
| 0.1218 | 5.0 | 240 | 0.0383 |
|
54 |
+
| 0.1188 | 6.0 | 288 | 0.0389 |
|
55 |
+
| 0.1159 | 7.0 | 336 | 0.0395 |
|
56 |
+
| 0.1124 | 8.0 | 384 | 0.0399 |
|
57 |
+
| 0.1088 | 9.0 | 432 | 0.0402 |
|
58 |
+
| 0.105 | 10.0 | 480 | 0.0405 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.41.1
|
64 |
+
- Pytorch 2.3.0+cu121
|
65 |
+
- Datasets 2.19.1
|
66 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ibm/TTM",
|
3 |
+
"adaptive_patching_levels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"TinyTimeMixerForPrediction"
|
6 |
+
],
|
7 |
+
"context_length": 1024,
|
8 |
+
"d_model": 192,
|
9 |
+
"d_model_scale": 3,
|
10 |
+
"decoder_adaptive_patching_levels": 0,
|
11 |
+
"decoder_d_model": 128,
|
12 |
+
"decoder_d_model_scale": 2,
|
13 |
+
"decoder_mode": "common_channel",
|
14 |
+
"decoder_num_layers": 2,
|
15 |
+
"decoder_raw_residual": false,
|
16 |
+
"dropout": 0.2,
|
17 |
+
"expansion_factor": 2,
|
18 |
+
"frequency_token_vocab_size": 5,
|
19 |
+
"gated_attn": true,
|
20 |
+
"head_dropout": 0.2,
|
21 |
+
"init_processing": true,
|
22 |
+
"init_std": 0.02,
|
23 |
+
"loss": "mse",
|
24 |
+
"mode": "common_channel",
|
25 |
+
"model_type": "tinytimemixer",
|
26 |
+
"norm_eps": 1e-05,
|
27 |
+
"norm_mlp": "LayerNorm",
|
28 |
+
"num_input_channels": 1,
|
29 |
+
"num_layers": 2,
|
30 |
+
"num_patches": 16,
|
31 |
+
"patch_last": true,
|
32 |
+
"patch_length": 64,
|
33 |
+
"patch_stride": 64,
|
34 |
+
"positional_encoding_type": "sincos",
|
35 |
+
"post_init": false,
|
36 |
+
"prediction_channel_indices": null,
|
37 |
+
"prediction_filter_length": null,
|
38 |
+
"prediction_length": 96,
|
39 |
+
"resolution_prefix_tuning": false,
|
40 |
+
"scaling": "std",
|
41 |
+
"self_attn": false,
|
42 |
+
"self_attn_heads": 1,
|
43 |
+
"stride_ratio": 1,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.41.1",
|
46 |
+
"use_decoder": true,
|
47 |
+
"use_positional_encoding": false
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa22459b56fa87cf69e94b7d280c97582a76096d3a4658e1331d2a5c54d3379a
|
3 |
+
size 3804872
|
runs/May30_18-03-06_one/events.out.tfevents.1717059786.one.682896.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fe3c6f3f63706cd6dc3d3c349d83990b76b7ac9af6ba21ed137f6cf8c8f8e7d
|
3 |
+
size 12932
|
runs/May30_18-03-06_one/events.out.tfevents.1717060072.one.682896.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cb88f2d0463ec79835120cb246057e289fe1b3b00dde250225ef50956cff31d
|
3 |
+
size 359
|
runs/May30_18-39-39_one/events.out.tfevents.1717061980.one.682896.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:330a9d06583aca1e0fdf7235c99b7eb40d5c8f2af779a7d648660bb40f876606
|
3 |
+
size 10522
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:672ffb824bcbf81435d9c4bc302b7f87aa44e25357c55d24606e67c9b82340f7
|
3 |
+
size 5048
|