Alexa067 commited on
Commit
57f8206
1 Parent(s): b90b427

End of training

Browse files
Files changed (16) hide show
  1. README.md +59 -0
  2. config.json +43 -0
  3. model.safetensors +3 -0
  4. runs/Mar07_17-07-09_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849229.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2145.0 +3 -0
  5. runs/Mar07_17-08-25_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849306.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2186.0 +3 -0
  6. runs/Mar07_17-10-23_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849423.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2229.0 +3 -0
  7. runs/Mar07_17-19-57_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849997.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2301.0 +3 -0
  8. runs/Mar07_17-21-01_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850062.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2321.0 +3 -0
  9. runs/Mar07_17-28-26_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850506.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2367.0 +3 -0
  10. runs/Mar07_17-31-06_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850667.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2403.0 +3 -0
  11. runs/Mar07_17-33-03_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850783.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2421.0 +3 -0
  12. runs/Mar07_17-35-25_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850926.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2446.0 +3 -0
  13. special_tokens_map.json +19 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +93 -0
  16. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlnet-base-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: my_awesome_qa_model
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
+ # my_awesome_qa_model
15
+
16
+ This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 6.0138
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: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 1 | 5.9660 |
50
+ | No log | 2.0 | 2 | 5.9563 |
51
+ | No log | 3.0 | 3 | 6.0138 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.38.2
57
+ - Pytorch 2.2.1
58
+ - Datasets 2.18.0
59
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-base-cased",
3
+ "architectures": [
4
+ "XLNetForQuestionAnswering"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "initializer_range": 0.02,
18
+ "layer_norm_eps": 1e-12,
19
+ "mem_len": null,
20
+ "model_type": "xlnet",
21
+ "n_head": 12,
22
+ "n_layer": 12,
23
+ "pad_token_id": 5,
24
+ "reuse_len": null,
25
+ "same_length": false,
26
+ "start_n_top": 5,
27
+ "summary_activation": "tanh",
28
+ "summary_last_dropout": 0.1,
29
+ "summary_type": "last",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 250
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.38.2",
39
+ "untie_r": true,
40
+ "use_mems_eval": true,
41
+ "use_mems_train": false,
42
+ "vocab_size": 32000
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723db6c03bbab70ecb26bee817ec7f062272dd731fe7551a57e9d41aef27eb6d
3
+ size 476355440
runs/Mar07_17-07-09_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849229.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2145.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f79106fa9530f0c119d15bd18826f4d2823f9a52f9db4dfced6bc39e049b7b2
3
+ size 5996
runs/Mar07_17-08-25_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849306.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2186.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504f429452dd5307fe5b38815f9a3aa0858ffd36a1234e0f52d73ad5600cfadf
3
+ size 5996
runs/Mar07_17-10-23_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849423.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2229.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e4453943e6d1fe9ceb78f14e3b6ab685b58f80954edd1923515d68ab578a6e
3
+ size 5996
runs/Mar07_17-19-57_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709849997.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2301.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea07e758faaca9224b0bd0c954948a42e7dd42fdcb4c4df853474e4ef5ff32c5
3
+ size 5996
runs/Mar07_17-21-01_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850062.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2321.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbaf2e376e1b4c4656c844d87c61f975c8c4344c52b0054ee8065edf558ceb9c
3
+ size 5996
runs/Mar07_17-28-26_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850506.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2367.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a44ae0b0962a405e802f42673bb964c027daf4a13041a7acd7e7a49aa48936
3
+ size 5996
runs/Mar07_17-31-06_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850667.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2403.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b7914da13655da47d3242d5a1889af8f4029210002a55955f5519919052cb8
3
+ size 5996
runs/Mar07_17-33-03_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850783.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2421.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b43d0d24846fc6f1f0595a03346d4f4b4ce0bb04c3b9e782d515a7a6872fd1
3
+ size 5996
runs/Mar07_17-35-25_sireeshas-mbp.notrust.clients.wireless.pfw.edu/events.out.tfevents.1709850926.sireeshas-mbp.notrust.clients.wireless.pfw.edu.2446.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5027f15be18196d67fbad97b7a34a47d6ebfeaee960bbecf8e94f7e2754dfbf
3
+ size 5996
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<cls>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<eod>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<eop>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<eop>",
78
+ "<eod>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": true,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "eos_token": "</s>",
85
+ "keep_accents": false,
86
+ "mask_token": "<mask>",
87
+ "model_max_length": 1000000000000000019884624838656,
88
+ "pad_token": "<pad>",
89
+ "remove_space": true,
90
+ "sep_token": "<sep>",
91
+ "tokenizer_class": "XLNetTokenizer",
92
+ "unk_token": "<unk>"
93
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562349fcedfe6777aadc33e5644126aa5e75225ae365fc397c7ded47a5e2d872
3
+ size 4920