Hugging Face's logo

koshirowada
/
pythia_160m_sft

Text Generation
Transformers
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
koshirowada commited on
Commit
ae7ff39
•
1 Parent(s): e0d1fe2

Initial model upload

Browse files
Files changed (5) hide show
  1. README.md +36 -38
  2. logs/events.out.tfevents.1731925396.05fd0bfb43a8.1118.1 +3 -0
  3. model.safetensors +1 -1
  4. tokenizer.json +2 -16
  5. training_args.bin +1 -1
README.md CHANGED
@@ -7,8 +7,6 @@ tags:
7
  model-index:
8
  - name: pythia_160m_sft
9
  results: []
10
- datasets:
11
- - tatsu-lab/alpaca_farm
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.1033
22
 
23
  ## Model description
24
 
@@ -37,7 +35,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 2e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
@@ -50,39 +48,39 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 2.3332 | 0.0889 | 100 | 2.2776 |
54
- | 2.3071 | 0.1778 | 200 | 2.2564 |
55
- | 2.2941 | 0.2667 | 300 | 2.2301 |
56
- | 2.2548 | 0.3556 | 400 | 2.2094 |
57
- | 2.2246 | 0.4444 | 500 | 2.1973 |
58
- | 2.2189 | 0.5333 | 600 | 2.1705 |
59
- | 2.181 | 0.6222 | 700 | 2.1498 |
60
- | 2.1515 | 0.7111 | 800 | 2.1399 |
61
- | 2.1333 | 0.8 | 900 | 2.1212 |
62
- | 2.1139 | 0.8889 | 1000 | 2.1050 |
63
- | 2.0778 | 0.9778 | 1100 | 2.0970 |
64
- | 1.8312 | 1.0667 | 1200 | 2.1071 |
65
- | 1.7405 | 1.1556 | 1300 | 2.1022 |
66
- | 1.7284 | 1.2444 | 1400 | 2.1049 |
67
- | 1.7554 | 1.3333 | 1500 | 2.1023 |
68
- | 1.732 | 1.4222 | 1600 | 2.0934 |
69
- | 1.7474 | 1.5111 | 1700 | 2.0917 |
70
- | 1.7495 | 1.6 | 1800 | 2.0820 |
71
- | 1.7449 | 1.6889 | 1900 | 2.0770 |
72
- | 1.7474 | 1.7778 | 2000 | 2.0708 |
73
- | 1.7447 | 1.8667 | 2100 | 2.0643 |
74
- | 1.7138 | 1.9556 | 2200 | 2.0550 |
75
- | 1.5662 | 2.0444 | 2300 | 2.1122 |
76
- | 1.4506 | 2.1333 | 2400 | 2.1203 |
77
- | 1.4282 | 2.2222 | 2500 | 2.1225 |
78
- | 1.4302 | 2.3111 | 2600 | 2.1173 |
79
- | 1.4471 | 2.4 | 2700 | 2.1156 |
80
- | 1.4217 | 2.4889 | 2800 | 2.1168 |
81
- | 1.428 | 2.5778 | 2900 | 2.1126 |
82
- | 1.4206 | 2.6667 | 3000 | 2.1059 |
83
- | 1.4315 | 2.7556 | 3100 | 2.1068 |
84
- | 1.4345 | 2.8444 | 3200 | 2.1037 |
85
- | 1.4034 | 2.9333 | 3300 | 2.1033 |
86
 
87
 
88
  ### Framework versions
@@ -90,4 +88,4 @@ The following hyperparameters were used during training:
90
  - Transformers 4.46.2
91
  - Pytorch 2.5.1+cu121
92
  - Datasets 3.1.0
93
- - Tokenizers 0.20.3
 
7
  model-index:
8
  - name: pythia_160m_sft
9
  results: []
 
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.9831
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 2e-06
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
+ | 2.2935 | 0.0889 | 100 | 2.1426 |
52
+ | 2.153 | 0.1778 | 200 | 2.0977 |
53
+ | 2.1432 | 0.2667 | 300 | 2.0771 |
54
+ | 2.1131 | 0.3556 | 400 | 2.0633 |
55
+ | 2.0885 | 0.4444 | 500 | 2.0510 |
56
+ | 2.0956 | 0.5333 | 600 | 2.0403 |
57
+ | 2.0647 | 0.6222 | 700 | 2.0354 |
58
+ | 2.0498 | 0.7111 | 800 | 2.0273 |
59
+ | 2.0317 | 0.8 | 900 | 2.0202 |
60
+ | 2.0226 | 0.8889 | 1000 | 2.0150 |
61
+ | 1.992 | 0.9778 | 1100 | 2.0114 |
62
+ | 1.9639 | 1.0667 | 1200 | 2.0088 |
63
+ | 1.9302 | 1.1556 | 1300 | 2.0051 |
64
+ | 1.9381 | 1.2444 | 1400 | 2.0028 |
65
+ | 1.9595 | 1.3333 | 1500 | 2.0009 |
66
+ | 1.9325 | 1.4222 | 1600 | 1.9998 |
67
+ | 1.9481 | 1.5111 | 1700 | 1.9981 |
68
+ | 1.9572 | 1.6 | 1800 | 1.9956 |
69
+ | 1.9456 | 1.6889 | 1900 | 1.9944 |
70
+ | 1.9565 | 1.7778 | 2000 | 1.9922 |
71
+ | 1.9507 | 1.8667 | 2100 | 1.9905 |
72
+ | 1.9247 | 1.9556 | 2200 | 1.9881 |
73
+ | 1.8998 | 2.0444 | 2300 | 1.9874 |
74
+ | 1.9102 | 2.1333 | 2400 | 1.9873 |
75
+ | 1.8842 | 2.2222 | 2500 | 1.9876 |
76
+ | 1.876 | 2.3111 | 2600 | 1.9863 |
77
+ | 1.9001 | 2.4 | 2700 | 1.9856 |
78
+ | 1.8725 | 2.4889 | 2800 | 1.9859 |
79
+ | 1.868 | 2.5778 | 2900 | 1.9845 |
80
+ | 1.8803 | 2.6667 | 3000 | 1.9844 |
81
+ | 1.9002 | 2.7556 | 3100 | 1.9838 |
82
+ | 1.8941 | 2.8444 | 3200 | 1.9839 |
83
+ | 1.8548 | 2.9333 | 3300 | 1.9831 |
84
 
85
 
86
  ### Framework versions
 
88
  - Transformers 4.46.2
89
  - Pytorch 2.5.1+cu121
90
  - Datasets 3.1.0
91
+ - Tokenizers 0.20.3
logs/events.out.tfevents.1731925396.05fd0bfb43a8.1118.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf7485b9b2815e9a1d2a4fdbbb5b20b745cda81a8a88da56e9aed9d73315d75
3
+ size 21431
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22b159c840b2d0d830eb19dafbd2cba433d820d7cdb45dfc0d811c0c80ee9e5c
3
  size 649308728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16010f6fd8175f9600a0d54e1a8ffc3ac56d6a3f94c4f9f1f09a105106b9c8c
3
  size 649308728
tokenizer.json CHANGED
@@ -1,21 +1,7 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
- "padding": {
10
- "strategy": {
11
- "Fixed": 512
12
- },
13
- "direction": "Right",
14
- "pad_to_multiple_of": null,
15
- "pad_id": 0,
16
- "pad_type_id": 0,
17
- "pad_token": "<|endoftext|>"
18
- },
19
  "added_tokens": [
20
  {
21
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a25a53601ab9c07d6da59917595cc80b6bdb83ae8c0bbbe5dddfc9052d7ad4d
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c05d15220df0d64e6af2e9e631e0c6bb6cedad273a907d2ae742da96528a778
3
  size 5240