Hugging Face's logo

AlignmentResearch
/
robust_llm_pythia-70m_mz-131_IMDB

Text Classification
Transformers
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
michalzajac commited on
Commit
e6dda24
•
1 Parent(s): dcaa233

End of training

Browse files
Files changed (37) hide show
  1. README.md +52 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713946758.rllm-mz-131-adv-train-4-6k2nc.66.0 +3 -0
  5. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713949432.rllm-mz-131-adv-train-4-6k2nc.66.1 +3 -0
  6. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713952101.rllm-mz-131-adv-train-4-6k2nc.66.2 +3 -0
  7. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713954784.rllm-mz-131-adv-train-4-6k2nc.66.3 +3 -0
  8. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713957497.rllm-mz-131-adv-train-4-6k2nc.66.4 +3 -0
  9. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713960228.rllm-mz-131-adv-train-4-6k2nc.66.5 +3 -0
  10. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713962880.rllm-mz-131-adv-train-4-6k2nc.66.6 +3 -0
  11. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713965528.rllm-mz-131-adv-train-4-6k2nc.66.7 +3 -0
  12. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713968185.rllm-mz-131-adv-train-4-6k2nc.66.8 +3 -0
  13. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713970856.rllm-mz-131-adv-train-4-6k2nc.66.9 +3 -0
  14. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713973587.rllm-mz-131-adv-train-4-6k2nc.66.10 +3 -0
  15. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713976315.rllm-mz-131-adv-train-4-6k2nc.66.11 +3 -0
  16. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713978979.rllm-mz-131-adv-train-4-6k2nc.66.12 +3 -0
  17. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713981637.rllm-mz-131-adv-train-4-6k2nc.66.13 +3 -0
  18. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713984299.rllm-mz-131-adv-train-4-6k2nc.66.14 +3 -0
  19. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713986990.rllm-mz-131-adv-train-4-6k2nc.66.15 +3 -0
  20. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713989712.rllm-mz-131-adv-train-4-6k2nc.66.16 +3 -0
  21. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713992453.rllm-mz-131-adv-train-4-6k2nc.66.17 +3 -0
  22. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713995211.rllm-mz-131-adv-train-4-6k2nc.66.18 +3 -0
  23. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713997958.rllm-mz-131-adv-train-4-6k2nc.66.19 +3 -0
  24. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714000677.rllm-mz-131-adv-train-4-6k2nc.66.20 +3 -0
  25. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714003399.rllm-mz-131-adv-train-4-6k2nc.66.21 +3 -0
  26. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714006165.rllm-mz-131-adv-train-4-6k2nc.66.22 +3 -0
  27. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714008906.rllm-mz-131-adv-train-4-6k2nc.66.23 +3 -0
  28. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714011678.rllm-mz-131-adv-train-4-6k2nc.66.24 +3 -0
  29. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714014421.rllm-mz-131-adv-train-4-6k2nc.66.25 +3 -0
  30. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714017174.rllm-mz-131-adv-train-4-6k2nc.66.26 +3 -0
  31. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714019909.rllm-mz-131-adv-train-4-6k2nc.66.27 +3 -0
  32. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714022692.rllm-mz-131-adv-train-4-6k2nc.66.28 +3 -0
  33. runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714025480.rllm-mz-131-adv-train-4-6k2nc.66.29 +3 -0
  34. special_tokens_map.json +24 -0
  35. tokenizer.json +0 -0
  36. tokenizer_config.json +213 -0
  37. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: EleutherAI/pythia-70m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: robust_llm_pythia-70m_mz-131_IMDB
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-70m_mz-131_IMDB
15
+
16
+ This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) 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-70m",
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": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
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 sha256:913d4c05a19b5e81d771ec693a263fd726e0d7931a3d7ab95dc6379f3d9d5c02
3
+ size 178696672
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713946758.rllm-mz-131-adv-train-4-6k2nc.66.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e042162f7ee8f84f5db6b60ae0cbd069719ed0ab7a7316b600ff4bdc23a00347
3
+ size 6799
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713949432.rllm-mz-131-adv-train-4-6k2nc.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfadd570896d3bfec7ae6ab57033a3c3c58a71fca3279e4eb2e6814c52cfbcfa
3
+ size 6848
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713952101.rllm-mz-131-adv-train-4-6k2nc.66.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856db67e367745d5740e937935e0cb2aad4cc55df81a13d646940ef9170192cc
3
+ size 7619
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713954784.rllm-mz-131-adv-train-4-6k2nc.66.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df2789918d26c998a677e7384941e4046e44dd62811e771e16b7405d384cb5a
3
+ size 7619
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713957497.rllm-mz-131-adv-train-4-6k2nc.66.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673df319f79c7a03db11609ff2dc8abb89901dbee335c7bbca823ae27ead07a7
3
+ size 7619
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713960228.rllm-mz-131-adv-train-4-6k2nc.66.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695d954a35233e7a659128e0bfaa09f64b0541a26c17c4648d434ba48788d237
3
+ size 7619
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713962880.rllm-mz-131-adv-train-4-6k2nc.66.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa4c4ffdc810ee16d3f4ee06f1621db8d5bafedc45e72ab77b003bee697d323
3
+ size 8390
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713965528.rllm-mz-131-adv-train-4-6k2nc.66.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae564082c828bc0e97f5fd85ac2257aa78a05653bd75190fd62cc0c2da981bf
3
+ size 8390
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713968185.rllm-mz-131-adv-train-4-6k2nc.66.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b64a80f0dec2e0f97573a2c07d69cb89f384f6fd8f7969a51c1137f53d7e0c9
3
+ size 8390
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713970856.rllm-mz-131-adv-train-4-6k2nc.66.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:570529d47dc1fb921b7026397ee9b094a0071a1ab22a617cd46d36c96c878f3a
3
+ size 8390
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713973587.rllm-mz-131-adv-train-4-6k2nc.66.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4dcd5e05912c600eac3d1600244c5a75c4965223f31c3763e12ceee2aede162
3
+ size 9161
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713976315.rllm-mz-131-adv-train-4-6k2nc.66.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff900e0f837603ab34335de6605984f08aebc0a391c36977684f2563d781096
3
+ size 9161
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713978979.rllm-mz-131-adv-train-4-6k2nc.66.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a000646ab49545ed4f3a4bd337f041b63cb4ef2a9ee5e0f988320142ca140ab
3
+ size 9161
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713981637.rllm-mz-131-adv-train-4-6k2nc.66.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8149e6f5e57c498d601d2da461a2bf868b5955cc96725a48943221dfee1590d
3
+ size 9161
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713984299.rllm-mz-131-adv-train-4-6k2nc.66.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b4bd074ff49e290b96d31d98fdc1904d870a0701c2ff118d1eea14aaab4790
3
+ size 9932
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713986990.rllm-mz-131-adv-train-4-6k2nc.66.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e2fff8885d3a93037043d9d489fc288fb25f1b2ce706d994bfb0d610a14f96
3
+ size 9932
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713989712.rllm-mz-131-adv-train-4-6k2nc.66.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f3b94df349371758a31777a1eb2f837fcf9bad04c3affa17e0983e6cf5c3f5
3
+ size 9932
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713992453.rllm-mz-131-adv-train-4-6k2nc.66.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0f00cf98218680ff89f8148d8599a01fa5876ea2e3605e77292c845d87a306
3
+ size 9932
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713995211.rllm-mz-131-adv-train-4-6k2nc.66.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f3b52d60aaeb0838f4727e439b8dcf240c38f3a44e995c859a8ab2c3a0e097
3
+ size 10703
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1713997958.rllm-mz-131-adv-train-4-6k2nc.66.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db10ee65906d144be86d94b212a6ac14683e906f8454b1e8b7306c4957a5526b
3
+ size 10703
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714000677.rllm-mz-131-adv-train-4-6k2nc.66.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afffcd22c3bf2cdca3e6cdc36142d8f9dc15ac9b79783b78d3d6f5411cc16cd
3
+ size 10703
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714003399.rllm-mz-131-adv-train-4-6k2nc.66.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:078af7636abddb52a1135073714f017b064a44f97cf7c1c98f3b87b62d46d86c
3
+ size 10703
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714006165.rllm-mz-131-adv-train-4-6k2nc.66.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17115f7803e764558e7beafa46713c9bf83a5e88b6222293360a3ced4522949e
3
+ size 11474
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714008906.rllm-mz-131-adv-train-4-6k2nc.66.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3706e5f3f5fc7d31417dfa60d958c5295722d634bc0a8a73456ebe7b9e6ace96
3
+ size 11474
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714011678.rllm-mz-131-adv-train-4-6k2nc.66.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c950ab64a136ec7aa76694903eb9e34ac25a3a7b7e01e891447d561e51d5e01
3
+ size 11474
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714014421.rllm-mz-131-adv-train-4-6k2nc.66.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43a759f8615c4029d6ce65e8a1e16ada105a37b897eafc4e0567a0e871b0088
3
+ size 11474
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714017174.rllm-mz-131-adv-train-4-6k2nc.66.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d30f865d16b16c019bef030dec12251f629984cf1f90659576c61448e1ed5f9
3
+ size 12245
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714019909.rllm-mz-131-adv-train-4-6k2nc.66.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54a09a1cb892fd5a0132dfd73a0fdef0947fed7560767ced1306f86fc3b732c
3
+ size 12245
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714022692.rllm-mz-131-adv-train-4-6k2nc.66.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5985b12ee416031895b994fd88474c15d9a5bd71263a594b283eb5df4c56b52
3
+ size 12245
runs/Apr24_08-19-09_rllm-mz-131-adv-train-4-6k2nc/events.out.tfevents.1714025480.rllm-mz-131-adv-train-4-6k2nc.66.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5bae8f1b483a55de81ba40a2c6cbfad3c23f1425548d02bdcdf7c1b0b64e2b
3
+ size 12245
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 sha256:602689bba614c94d6b41208db3085683c90df6705144dca12d316edd59ae66a3
3
+ size 5048