Hugging Face's logo

Denm
/
output

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Denm commited on
Commit
7e8cdf4
•
1 Parent(s): 90e5a54

End of training

Browse files
Files changed (17) hide show
  1. README.md +67 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. merges.txt +0 -0
  5. runs/Dec13_09-25-33_312614f68533/events.out.tfevents.1702459644.312614f68533.264.0 +3 -0
  6. runs/Dec13_09-28-31_312614f68533/events.out.tfevents.1702459733.312614f68533.264.1 +3 -0
  7. runs/Dec13_09-31-47_312614f68533/events.out.tfevents.1702459925.312614f68533.264.2 +3 -0
  8. runs/Dec13_09-36-23_312614f68533/events.out.tfevents.1702460200.312614f68533.264.3 +3 -0
  9. runs/Dec13_09-38-04_312614f68533/events.out.tfevents.1702460301.312614f68533.264.4 +3 -0
  10. runs/Dec13_09-43-22_312614f68533/events.out.tfevents.1702460624.312614f68533.10155.0 +3 -0
  11. runs/Dec13_09-45-11_312614f68533/events.out.tfevents.1702460733.312614f68533.10155.1 +3 -0
  12. runs/Dec13_09-46-12_312614f68533/events.out.tfevents.1702460794.312614f68533.10155.2 +3 -0
  13. special_tokens_map.json +37 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +58 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ai-forever/rugpt3small_based_on_gpt2
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: output
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # output
16
+
17
+ This model is a fine-tuned version of [ai-forever/rugpt3small_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3small_based_on_gpt2) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.7083
20
+ - Accuracy: 0.5209
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1.41e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 24
44
+ - total_train_batch_size: 192
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.7676 | 0.13 | 50 | 0.7502 | 0.4717 |
54
+ | 0.7482 | 0.25 | 100 | 0.7369 | 0.4830 |
55
+ | 0.7414 | 0.38 | 150 | 0.7276 | 0.4915 |
56
+ | 0.7261 | 0.5 | 200 | 0.7205 | 0.5062 |
57
+ | 0.7272 | 0.63 | 250 | 0.7143 | 0.5132 |
58
+ | 0.7209 | 0.76 | 300 | 0.7106 | 0.5148 |
59
+ | 0.7218 | 0.88 | 350 | 0.7083 | 0.5209 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.35.2
65
+ - Pytorch 2.1.0+cu118
66
+ - Datasets 2.15.0
67
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ai-forever/rugpt3small_based_on_gpt2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "scores"
18
+ ],
19
+ "peft_type": "LORA",
20
+ "r": 16,
21
+ "rank_pattern": {},
22
+ "revision": null,
23
+ "target_modules": [
24
+ "c_attn"
25
+ ],
26
+ "task_type": "SEQ_CLS"
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4cd192bbad3969e699811a06044a90a663d95f75a02349c00e7d2f6f137207
3
+ size 2365536
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec13_09-25-33_312614f68533/events.out.tfevents.1702459644.312614f68533.264.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75086698ad612ee7a71c97b9bf0f35538a130b1ae2e97782faeb5dd426274d39
3
+ size 4981
runs/Dec13_09-28-31_312614f68533/events.out.tfevents.1702459733.312614f68533.264.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c565c1a8598bc6eb8082ab7d3eee656bc10db920bccf18879bc60f89b6a07473
3
+ size 4970
runs/Dec13_09-31-47_312614f68533/events.out.tfevents.1702459925.312614f68533.264.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957bffebd59b083b2c31e8096fa22177374c93a60c5a54e93975097cdf8d899f
3
+ size 4971
runs/Dec13_09-36-23_312614f68533/events.out.tfevents.1702460200.312614f68533.264.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3dd40269c617025fd41c134eee3ea8c3997a12d56a4951c8ce1b1921ab5aab
3
+ size 4932
runs/Dec13_09-38-04_312614f68533/events.out.tfevents.1702460301.312614f68533.264.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d3e4f8a1a31c186015054f9688b8527612f307337852cbb872912017f0035c
3
+ size 4899
runs/Dec13_09-43-22_312614f68533/events.out.tfevents.1702460624.312614f68533.10155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:299a91562441a44eb58b5a64a73a0d45b65790ff361eec1205d343ff5b8a6d85
3
+ size 4899
runs/Dec13_09-45-11_312614f68533/events.out.tfevents.1702460733.312614f68533.10155.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116d5d28cd2cba917aaa5cce9548c328263f9d4eca0e2a877fd18132cea2a82a
3
+ size 4899
runs/Dec13_09-46-12_312614f68533/events.out.tfevents.1702460794.312614f68533.10155.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca1e00da6ce7f088d5735ac4e9eb65192db4c4906a97d0bb69077fbfec71233
3
+ size 8593
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 2048,
52
+ "pad_token": "<pad>",
53
+ "padding_side": "left",
54
+ "tokenizer_class": "GPT2Tokenizer",
55
+ "truncation_side": "left",
56
+ "trust_remote_code": false,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c947bbd976ea86248669099ec12e879c39992f6cabca37316c00985076f8b94a
3
+ size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff