michalzajac commited on
Commit
fffee4e
·
verified ·
1 Parent(s): dd03be6

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_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713961821.rllm-mz-131-adv-train-8-9cckf.66.0 +3 -0
  5. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713971207.rllm-mz-131-adv-train-8-9cckf.66.1 +3 -0
  6. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713980426.rllm-mz-131-adv-train-8-9cckf.66.2 +3 -0
  7. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713989714.rllm-mz-131-adv-train-8-9cckf.66.3 +3 -0
  8. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713999204.rllm-mz-131-adv-train-8-9cckf.66.4 +3 -0
  9. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714008874.rllm-mz-131-adv-train-8-9cckf.66.5 +3 -0
  10. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714017930.rllm-mz-131-adv-train-8-9cckf.66.6 +3 -0
  11. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714027088.rllm-mz-131-adv-train-8-9cckf.66.7 +3 -0
  12. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714036271.rllm-mz-131-adv-train-8-9cckf.66.8 +3 -0
  13. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714045526.rllm-mz-131-adv-train-8-9cckf.66.9 +3 -0
  14. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714055265.rllm-mz-131-adv-train-8-9cckf.66.10 +3 -0
  15. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714064891.rllm-mz-131-adv-train-8-9cckf.66.11 +3 -0
  16. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714074421.rllm-mz-131-adv-train-8-9cckf.66.12 +3 -0
  17. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714083940.rllm-mz-131-adv-train-8-9cckf.66.13 +3 -0
  18. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714093676.rllm-mz-131-adv-train-8-9cckf.66.14 +3 -0
  19. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714103164.rllm-mz-131-adv-train-8-9cckf.66.15 +3 -0
  20. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714112804.rllm-mz-131-adv-train-8-9cckf.66.16 +3 -0
  21. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714122566.rllm-mz-131-adv-train-8-9cckf.66.17 +3 -0
  22. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714132539.rllm-mz-131-adv-train-8-9cckf.66.18 +3 -0
  23. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714142432.rllm-mz-131-adv-train-8-9cckf.66.19 +3 -0
  24. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714151948.rllm-mz-131-adv-train-8-9cckf.66.20 +3 -0
  25. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714161501.rllm-mz-131-adv-train-8-9cckf.66.21 +3 -0
  26. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714171491.rllm-mz-131-adv-train-8-9cckf.66.22 +3 -0
  27. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714181367.rllm-mz-131-adv-train-8-9cckf.66.23 +3 -0
  28. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714191490.rllm-mz-131-adv-train-8-9cckf.66.24 +3 -0
  29. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714201414.rllm-mz-131-adv-train-8-9cckf.66.25 +3 -0
  30. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714211394.rllm-mz-131-adv-train-8-9cckf.66.26 +3 -0
  31. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714221396.rllm-mz-131-adv-train-8-9cckf.66.27 +3 -0
  32. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714231505.rllm-mz-131-adv-train-8-9cckf.66.28 +3 -0
  33. runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714241581.rllm-mz-131-adv-train-8-9cckf.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-410m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: robust_llm_pythia-410m_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-410m_mz-131_IMDB
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 sha256:5b2b9898938f3a63dfa9c0b735aac50d370e31ee66e90c823daee1de5e5b647f
3
+ size 1415333128
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713961821.rllm-mz-131-adv-train-8-9cckf.66.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500603976d2f2ed3c7c89e411fab875efec725769a0db22efad9719f9f59a3fa
3
+ size 6807
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713971207.rllm-mz-131-adv-train-8-9cckf.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df623416b437b105f0c71f557cda3f2c14f6e5df3c707c2d7a230d09ce88db9b
3
+ size 6856
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713980426.rllm-mz-131-adv-train-8-9cckf.66.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595157a74584933a10327b6ea57da2eb282b0514120271fe5b87847aea193237
3
+ size 7627
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713989714.rllm-mz-131-adv-train-8-9cckf.66.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e026f9d0a2eacad8b3be6c3593e82c904821d6c00535224bf03eb7ccae38ed2c
3
+ size 7627
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1713999204.rllm-mz-131-adv-train-8-9cckf.66.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e95b3d20d80513e8ed12954438dc660375b58298333369ad0b45215ced5f3fa
3
+ size 7627
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714008874.rllm-mz-131-adv-train-8-9cckf.66.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06429be333d7f31b2fe202067ae5c911d1134d6f8aeba7658f84601c4ec0b552
3
+ size 7627
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714017930.rllm-mz-131-adv-train-8-9cckf.66.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea95386ab385e7547c9867555d65a4c2ea71f0f8ac068a2eaf4980d19e2bfe4
3
+ size 8398
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714027088.rllm-mz-131-adv-train-8-9cckf.66.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d49e1e110890a2720f8d3656605fac534806f4a89d73beb7dd4420fa0365d2
3
+ size 8398
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714036271.rllm-mz-131-adv-train-8-9cckf.66.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ceca502470c0c1c69e782f37615facb6b315c71af528b7d498ecbb4d592504
3
+ size 8398
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714045526.rllm-mz-131-adv-train-8-9cckf.66.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523ab0b23ac261fe69200c3ab928b6e669d05f8c08e3194a2143d283a1a607a6
3
+ size 8398
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714055265.rllm-mz-131-adv-train-8-9cckf.66.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be668260e19e8da3e122e592b2097e2a0c57de24cc0816032032d19f307f40de
3
+ size 9169
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714064891.rllm-mz-131-adv-train-8-9cckf.66.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e465429fe0498ac76f31986cdd7d3ecf5c7bf5480b56a8a79fe1612a9d1111a9
3
+ size 9169
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714074421.rllm-mz-131-adv-train-8-9cckf.66.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:826e592f06cc3d372bad6aaf3f91202184366ffaccb465228bf0220bf41e60cb
3
+ size 9169
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714083940.rllm-mz-131-adv-train-8-9cckf.66.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c298d8a7c338be9d2d758a7ea882092c0407af03dab74890ece6622529f4d4c
3
+ size 9169
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714093676.rllm-mz-131-adv-train-8-9cckf.66.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22de279531da6dff6cfb6de8f68957e392fa706d507038dcdcf5407bf798b884
3
+ size 9940
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714103164.rllm-mz-131-adv-train-8-9cckf.66.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff19c2c483e68f02ca91f78e574ba9d1e7a754bb5e354cf6819d480b16796e4a
3
+ size 9940
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714112804.rllm-mz-131-adv-train-8-9cckf.66.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07debfdb64e021a2b0eb245aecacc8982f1b23c056e2ae0e77c86745d3d1e0f5
3
+ size 9940
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714122566.rllm-mz-131-adv-train-8-9cckf.66.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6fe223b265a6a1d92cf8a1acde04310c803665fa2211a916df241602f65d2e
3
+ size 9940
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714132539.rllm-mz-131-adv-train-8-9cckf.66.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3eac3989ad2c693729e4a0fc5e086b47eb1e985307fe16ebed4315a939f375
3
+ size 10711
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714142432.rllm-mz-131-adv-train-8-9cckf.66.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec34fa74dd40db8585d4f993628032f17c14dc0144c27baf350d68dab453006
3
+ size 10711
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714151948.rllm-mz-131-adv-train-8-9cckf.66.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608bb810de12cf807fe0e9fd3885fb9542d4cdaccd77ef0cac6115635e003a44
3
+ size 10711
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714161501.rllm-mz-131-adv-train-8-9cckf.66.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2111f9e5dd0f4809233328c2794b3cb9d12ca250fe3c938f8604d7231f81a359
3
+ size 10711
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714171491.rllm-mz-131-adv-train-8-9cckf.66.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9676c13fb40dad3047ec91aeb5763cf2b6ddbd370050a33eb5d2bb14aee4084
3
+ size 11482
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714181367.rllm-mz-131-adv-train-8-9cckf.66.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbecb8c276f292418452695c0249417fde440e81392eaddbc095ae56000a3da
3
+ size 11482
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714191490.rllm-mz-131-adv-train-8-9cckf.66.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c22baa03ec952172d3e848229a3631cd94d654e95756bc6a6368da0430f043a
3
+ size 11482
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714201414.rllm-mz-131-adv-train-8-9cckf.66.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009c500ae37d673ed6f71ac98173483cd4f35ecf14e87659323ca347b09c20a3
3
+ size 11482
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714211394.rllm-mz-131-adv-train-8-9cckf.66.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82e32de29b8f35df87249148146038bbc771ce0f17836e2fd556845aa7c65c3
3
+ size 12253
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714221396.rllm-mz-131-adv-train-8-9cckf.66.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbd36ab29d365c477f9196de8c3517c3acb4a05ab42b8474b54aa9b804c433de
3
+ size 12253
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714231505.rllm-mz-131-adv-train-8-9cckf.66.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a374f71fcc441789534e9e86f849c7b103e7ff7daee7c82d909a9eb0b5c79ab6
3
+ size 12253
runs/Apr24_12-30-12_rllm-mz-131-adv-train-8-9cckf/events.out.tfevents.1714241581.rllm-mz-131-adv-train-8-9cckf.66.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59cffce09a5ab0c4f18fa6703dcb2d261b16ea62f7103a27b46d43d4338e554f
3
+ size 12253
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 sha256:84fc8e6bc9ae7ac21b678abd48835c672b29afd37781aa4f3fa6ef732c09f38f
3
+ size 5112