Hugging Face's logo

AlignmentResearch
/
robust_llm_pythia-410m_mz-132_WordLength_n-its-10

Text Classification
Transformers
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
michalzajac commited on
Commit
544e9a0
•
1 Parent(s): 824c791

End of training

Browse files
Files changed (17) hide show
  1. README.md +52 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713962258.rllm-mz-132-adv-train-9-dkbdb.66.0 +3 -0
  5. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713968228.rllm-mz-132-adv-train-9-dkbdb.66.1 +3 -0
  6. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713974248.rllm-mz-132-adv-train-9-dkbdb.66.2 +3 -0
  7. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713980210.rllm-mz-132-adv-train-9-dkbdb.66.3 +3 -0
  8. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713986152.rllm-mz-132-adv-train-9-dkbdb.66.4 +3 -0
  9. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713992188.rllm-mz-132-adv-train-9-dkbdb.66.5 +3 -0
  10. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713998218.rllm-mz-132-adv-train-9-dkbdb.66.6 +3 -0
  11. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714004281.rllm-mz-132-adv-train-9-dkbdb.66.7 +3 -0
  12. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714010351.rllm-mz-132-adv-train-9-dkbdb.66.8 +3 -0
  13. runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714016420.rllm-mz-132-adv-train-9-dkbdb.66.9 +3 -0
  14. special_tokens_map.json +24 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +213 -0
  17. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: EleutherAI/pythia-410m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: robust_llm_pythia-410m_mz-132_WordLength_n-its-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
+ # robust_llm_pythia-410m_mz-132_WordLength_n-its-10
15
+
16
+ This model is a fine-tuned version of [EleutherAI/pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 1e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 64
38
+ - seed: 0
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 1
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.39.3
50
+ - Pytorch 2.2.1
51
+ - Datasets 2.18.0
52
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-410m",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 4096,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "pad_token_id": 0,
22
+ "problem_type": "single_label_classification",
23
+ "rope_scaling": null,
24
+ "rotary_emb_base": 10000,
25
+ "rotary_pct": 0.25,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.39.3",
29
+ "use_cache": false,
30
+ "use_parallel_residual": true,
31
+ "vocab_size": 50304
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9d6337ab80c75a5055fa7547eb3d3183a2a08f8f3e983434da5a9f48ed4e22
3
+ size 1415333128
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713962258.rllm-mz-132-adv-train-9-dkbdb.66.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd91eb600add1aa59d71c23fb9c2c3eed02a2aab9360d8f5ce793ce9a9aac54
3
+ size 6867
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713968228.rllm-mz-132-adv-train-9-dkbdb.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bfe77097369668865b0818ced750c855d3c87c08096ec1d512a67063eccc3f
3
+ size 7687
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713974248.rllm-mz-132-adv-train-9-dkbdb.66.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:554011ab1dd13a62745651c70a81f9b1dd4a5d8de567a35b170e8eccd0224491
3
+ size 7687
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713980210.rllm-mz-132-adv-train-9-dkbdb.66.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cd1d726d958b41793028dd731568db85b17fd60c627d11744b383c96b37bb80
3
+ size 8458
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713986152.rllm-mz-132-adv-train-9-dkbdb.66.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f89e2f1a170572192b2df8419fb158706c1e8c23f224defe85e9199b439b63
3
+ size 9229
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713992188.rllm-mz-132-adv-train-9-dkbdb.66.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645bb87892e987b787736d8043d17fc89077debf849c9aa66284d9738cd9762c
3
+ size 9229
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1713998218.rllm-mz-132-adv-train-9-dkbdb.66.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d7e642d5ce3a42b7380725459e2674543c3ee74ea90d71ced5d9df4f72f558
3
+ size 10000
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714004281.rllm-mz-132-adv-train-9-dkbdb.66.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e1574765231ba336e74abb76dda03ba34de0ee3ed64bd1b2db4740af81405c
3
+ size 10000
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714010351.rllm-mz-132-adv-train-9-dkbdb.66.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7fa9a99031d62233a0241c9fd0b241ab3cda29a419b16f6b0e58d470d3c618
3
+ size 10771
runs/Apr24_12-37-29_rllm-mz-132-adv-train-9-dkbdb/events.out.tfevents.1714016420.rllm-mz-132-adv-train-9-dkbdb.66.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398316c646eb8fe75cb9bd6a7c35c6131c580b325e45e1077107f70d9856c935
3
+ size 11542
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,213 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": false,
207
+ "eos_token": "<|endoftext|>",
208
+ "model_max_length": 2048,
209
+ "pad_token": "<|endoftext|>",
210
+ "padding_side": "right",
211
+ "tokenizer_class": "GPTNeoXTokenizer",
212
+ "unk_token": "<|endoftext|>"
213
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ddeb570b15e7143e7294d652a866c909ca6f921f2b54d7da67f291260de9f6d
3
+ size 5112