michalzajac commited on
Commit
c1c6dfc
1 Parent(s): 0f1393b

End of training

Browse files
Files changed (37) hide show
  1. README.md +51 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713946683.rllm-mz-131-adv-train-0-gs26k.66.0 +3 -0
  5. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713949112.rllm-mz-131-adv-train-0-gs26k.66.1 +3 -0
  6. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713951554.rllm-mz-131-adv-train-0-gs26k.66.2 +3 -0
  7. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713954003.rllm-mz-131-adv-train-0-gs26k.66.3 +3 -0
  8. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713956474.rllm-mz-131-adv-train-0-gs26k.66.4 +3 -0
  9. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713958940.rllm-mz-131-adv-train-0-gs26k.66.5 +3 -0
  10. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713961411.rllm-mz-131-adv-train-0-gs26k.66.6 +3 -0
  11. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713963883.rllm-mz-131-adv-train-0-gs26k.66.7 +3 -0
  12. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713966354.rllm-mz-131-adv-train-0-gs26k.66.8 +3 -0
  13. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713968838.rllm-mz-131-adv-train-0-gs26k.66.9 +3 -0
  14. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713971338.rllm-mz-131-adv-train-0-gs26k.66.10 +3 -0
  15. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713973845.rllm-mz-131-adv-train-0-gs26k.66.11 +3 -0
  16. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713976355.rllm-mz-131-adv-train-0-gs26k.66.12 +3 -0
  17. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713978804.rllm-mz-131-adv-train-0-gs26k.66.13 +3 -0
  18. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713981233.rllm-mz-131-adv-train-0-gs26k.66.14 +3 -0
  19. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713983654.rllm-mz-131-adv-train-0-gs26k.66.15 +3 -0
  20. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713986045.rllm-mz-131-adv-train-0-gs26k.66.16 +3 -0
  21. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713988468.rllm-mz-131-adv-train-0-gs26k.66.17 +3 -0
  22. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713990941.rllm-mz-131-adv-train-0-gs26k.66.18 +3 -0
  23. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713993438.rllm-mz-131-adv-train-0-gs26k.66.19 +3 -0
  24. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713995924.rllm-mz-131-adv-train-0-gs26k.66.20 +3 -0
  25. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713998400.rllm-mz-131-adv-train-0-gs26k.66.21 +3 -0
  26. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714000906.rllm-mz-131-adv-train-0-gs26k.66.22 +3 -0
  27. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714003409.rllm-mz-131-adv-train-0-gs26k.66.23 +3 -0
  28. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714005927.rllm-mz-131-adv-train-0-gs26k.66.24 +3 -0
  29. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714008424.rllm-mz-131-adv-train-0-gs26k.66.25 +3 -0
  30. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714010906.rllm-mz-131-adv-train-0-gs26k.66.26 +3 -0
  31. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714013401.rllm-mz-131-adv-train-0-gs26k.66.27 +3 -0
  32. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714015914.rllm-mz-131-adv-train-0-gs26k.66.28 +3 -0
  33. runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714018401.rllm-mz-131-adv-train-0-gs26k.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 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: EleutherAI/pythia-14m
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: robust_llm_pythia-14m_mz-131_IMDB
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # robust_llm_pythia-14m_mz-131_IMDB
14
+
15
+ This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 1e-05
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 64
37
+ - seed: 0
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 1
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.39.3
49
+ - Pytorch 2.2.1
50
+ - Datasets 2.18.0
51
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-14m",
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": 128,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 512,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 4,
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:b11b4265f6941bca81105642e237eac37e25f932cc81dbe35901a162f34855ea
3
+ size 30524712
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713946683.rllm-mz-131-adv-train-0-gs26k.66.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f19600c510b84237391d331c4685229100b5b5efb0420ea2148a40f48b9e00
3
+ size 6798
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713949112.rllm-mz-131-adv-train-0-gs26k.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75ade00031ed22f100575d9396304794588a14afb6f0b7c26e6ee2316252011b
3
+ size 6847
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713951554.rllm-mz-131-adv-train-0-gs26k.66.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0222e0b499260c881cb303f4693185ad72363e5850fb1c57ccf3c77c8548762
3
+ size 7618
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713954003.rllm-mz-131-adv-train-0-gs26k.66.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e7d6166b830e86d8f940984114a95a011d55035783db66de7cc9f49e6c78ef
3
+ size 7618
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713956474.rllm-mz-131-adv-train-0-gs26k.66.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a422e21dc2b396b3272b6704a531506c16e1f950484567ebb2e9a45249845d7f
3
+ size 7618
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713958940.rllm-mz-131-adv-train-0-gs26k.66.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df934e58309d71a35d5b61383257e886a614d694afdee6a49d1fb0a277abf978
3
+ size 7618
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713961411.rllm-mz-131-adv-train-0-gs26k.66.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1325dc25623c3286cfe81c26158657f26a006c337190f4ab7298e5373cf5d586
3
+ size 8389
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713963883.rllm-mz-131-adv-train-0-gs26k.66.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66716f6f8226f9795af55d97f00464538870b99672a50de243a3d4c0030f2e34
3
+ size 8389
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713966354.rllm-mz-131-adv-train-0-gs26k.66.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5cbdc6dacd9fe39d7eb3244f01c067dca19ad2bc868188d2a04c9ef57b6bd3
3
+ size 8389
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713968838.rllm-mz-131-adv-train-0-gs26k.66.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93de5c6f236a4247cea303f797da18a7e818b6a93ebf4a450c021a25691ddc0
3
+ size 8389
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713971338.rllm-mz-131-adv-train-0-gs26k.66.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1efe1d46164839bb500bc6f92d087ac39471da71e1e2c4e46efc51accf18e3a
3
+ size 9160
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713973845.rllm-mz-131-adv-train-0-gs26k.66.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c3c77b257e0fe2fdc39c604c260e1d314c5b72ff546f9a1d2c18ea5474b176
3
+ size 9160
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713976355.rllm-mz-131-adv-train-0-gs26k.66.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cca2d9877f3d93ab906ecd464e8e04d00af5dd6de60606b1cd2243785d5913
3
+ size 9160
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713978804.rllm-mz-131-adv-train-0-gs26k.66.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34f3b12f2dacf1eef7843753ec5468b3c9f4d5598e9f806427e534e7bf16ff3
3
+ size 9160
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713981233.rllm-mz-131-adv-train-0-gs26k.66.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0848a0d9510018d74679e5bc89254af6b9939f46d1ee71ce1e76903ba82e3db5
3
+ size 9931
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713983654.rllm-mz-131-adv-train-0-gs26k.66.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2bd623a496fca781bd8506ed5b497402fde1889ebbc679fbfeeb4f1777325f2
3
+ size 9931
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713986045.rllm-mz-131-adv-train-0-gs26k.66.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2064cc01ae74f9d710ce8e38a14b585fbdb4c82f6280e56618e358caae97c9a
3
+ size 9931
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713988468.rllm-mz-131-adv-train-0-gs26k.66.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f5c599529a8cf2a42ea531f0d6d1267fde69f9aac9e0a42bf0f821ebb9ea7b5
3
+ size 9931
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713990941.rllm-mz-131-adv-train-0-gs26k.66.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d66934d84511937c7c980e43a6a2cc70b1f7a5ec1acd45f872c2b3ceaefb71
3
+ size 10702
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713993438.rllm-mz-131-adv-train-0-gs26k.66.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb5656b19ab7bf46c2f1662c001db4f0c016300348f9b81adff41f5abcaf79d5
3
+ size 10702
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713995924.rllm-mz-131-adv-train-0-gs26k.66.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef9ff633b2e165cf14aff7793710636138f9ba5cfd7aa11a4ecc396eb79f51e
3
+ size 10702
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1713998400.rllm-mz-131-adv-train-0-gs26k.66.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ef8fa2432e4f4e41e40966f2d3ac42994dbfffda8d8c3adf7bf22cd01455d9
3
+ size 10702
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714000906.rllm-mz-131-adv-train-0-gs26k.66.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3006861d728e3d20d68be86308ebdbcfdb569e3a99e5d8a6bcd86a8c1b20e44
3
+ size 11473
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714003409.rllm-mz-131-adv-train-0-gs26k.66.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad2f4da8eb63aaa78a004cb97e4c25ef9f8d9bde2544c648c8470433a100164
3
+ size 11473
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714005927.rllm-mz-131-adv-train-0-gs26k.66.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc12719d8a751585795a962a4daafa5b6b715409fd4161287064e1af830ff7f
3
+ size 11473
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714008424.rllm-mz-131-adv-train-0-gs26k.66.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f5b0e7b8e0874da96b98b0010c9a1943876dea730061aef1131c65a31a9745
3
+ size 11473
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714010906.rllm-mz-131-adv-train-0-gs26k.66.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdee128f78948f09631778501ca843fbe6bf7a569aa46b7c07eaa1f129898477
3
+ size 12244
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714013401.rllm-mz-131-adv-train-0-gs26k.66.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511fba9d9fd19970bbed84f96440ff6e0d178ca88226e2ce074be04c5ec22b11
3
+ size 12244
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714015914.rllm-mz-131-adv-train-0-gs26k.66.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb92ad9338e73b455790f20cd5a5ebc5474d9bba20ce01aa32f1c4f1d86ffc77
3
+ size 12244
runs/Apr24_08-17-54_rllm-mz-131-adv-train-0-gs26k/events.out.tfevents.1714018401.rllm-mz-131-adv-train-0-gs26k.66.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d6d6830444336baf969880676a95a48de4c20ebdaefce17634dcce50423176
3
+ size 12244
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:ec377cb06eb9b83493e9e39f8c1d378d90d1269f50d31e50b0a3f9a55759e66c
3
+ size 5048