End of training
Browse files- README.md +52 -0
- config.json +32 -0
- model.safetensors +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088499.rllm-niki-044-long-ad-14-rrssn.66.0 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088534.rllm-niki-044-long-ad-14-rrssn.66.1 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088620.rllm-niki-044-long-ad-14-rrssn.66.2 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715089002.rllm-niki-044-long-ad-14-rrssn.66.3 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715089717.rllm-niki-044-long-ad-14-rrssn.66.4 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715090516.rllm-niki-044-long-ad-14-rrssn.66.5 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715091418.rllm-niki-044-long-ad-14-rrssn.66.6 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715092324.rllm-niki-044-long-ad-14-rrssn.66.7 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715093217.rllm-niki-044-long-ad-14-rrssn.66.8 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715094143.rllm-niki-044-long-ad-14-rrssn.66.9 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715095075.rllm-niki-044-long-ad-14-rrssn.66.10 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715096015.rllm-niki-044-long-ad-14-rrssn.66.11 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715096987.rllm-niki-044-long-ad-14-rrssn.66.12 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715097974.rllm-niki-044-long-ad-14-rrssn.66.13 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715098963.rllm-niki-044-long-ad-14-rrssn.66.14 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715100000.rllm-niki-044-long-ad-14-rrssn.66.15 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715101010.rllm-niki-044-long-ad-14-rrssn.66.16 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715102047.rllm-niki-044-long-ad-14-rrssn.66.17 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715103129.rllm-niki-044-long-ad-14-rrssn.66.18 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715104226.rllm-niki-044-long-ad-14-rrssn.66.19 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715105297.rllm-niki-044-long-ad-14-rrssn.66.20 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715106340.rllm-niki-044-long-ad-14-rrssn.66.21 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715107374.rllm-niki-044-long-ad-14-rrssn.66.22 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715108482.rllm-niki-044-long-ad-14-rrssn.66.23 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715109565.rllm-niki-044-long-ad-14-rrssn.66.24 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715110602.rllm-niki-044-long-ad-14-rrssn.66.25 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715111647.rllm-niki-044-long-ad-14-rrssn.66.26 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715112747.rllm-niki-044-long-ad-14-rrssn.66.27 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715113858.rllm-niki-044-long-ad-14-rrssn.66.28 +3 -0
- runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715114925.rllm-niki-044-long-ad-14-rrssn.66.29 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +213 -0
- 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_niki-044_imdb_random-token-1280_30-rounds_seed-4
|
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_niki-044_imdb_random-token-1280_30-rounds_seed-4
|
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: 8
|
38 |
+
- seed: 4
|
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 sha256:547c48daeb7836e3a34ce6fafed0b2f358e74fbdccc8f2d19d46d9df96e34113
|
3 |
+
size 178696672
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088499.rllm-niki-044-long-ad-14-rrssn.66.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd893cc6df620d1e9dd16a1763728b84a6aa3eea60e21e9608f0699131c0bfd3
|
3 |
+
size 6947
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088534.rllm-niki-044-long-ad-14-rrssn.66.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6f2cf9aed528e13150b686fde8c3031975edd9d2ec87da2b227d1bb5aa17296
|
3 |
+
size 6996
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715088620.rllm-niki-044-long-ad-14-rrssn.66.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a45701ef3f8ba80e4e16816c4c0bf24a93b8fdd12e6b696992d3e974486d38f8
|
3 |
+
size 7767
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715089002.rllm-niki-044-long-ad-14-rrssn.66.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd96a92a73d118f19af1d617e97497a59a0965b95d7a47975461b1ab575fac63
|
3 |
+
size 7767
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715089717.rllm-niki-044-long-ad-14-rrssn.66.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4ce881ddde247709a891f501ef6f24afcb365597495124438113340af2a8ae9
|
3 |
+
size 7767
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715090516.rllm-niki-044-long-ad-14-rrssn.66.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6c988d678e98ef711f53aaf525092ffdf4df8392a5575bb190e8a0367a58dc4
|
3 |
+
size 7767
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715091418.rllm-niki-044-long-ad-14-rrssn.66.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f00c46d2c11c3ac70294c462b59bb7febd0d8dbe3e10534f6da0b6408fd869
|
3 |
+
size 8538
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715092324.rllm-niki-044-long-ad-14-rrssn.66.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e11d4fcffb4f607af2e272e6d1d4db8e23cac76b7d838fbf0ebf50979d9c422f
|
3 |
+
size 8538
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715093217.rllm-niki-044-long-ad-14-rrssn.66.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c4c7c401a807bdc21750addd928852d2ae801c769d4f2ef5a78f43da8383815
|
3 |
+
size 8538
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715094143.rllm-niki-044-long-ad-14-rrssn.66.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb712ba79078dc7b533f245e52600574dd148795a95d048c396cd37fc13ec2fe
|
3 |
+
size 8538
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715095075.rllm-niki-044-long-ad-14-rrssn.66.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7979e5e3459a80d9576ce9f386a625053a3bd8f15a803d9b4a7b8627029ccff3
|
3 |
+
size 9309
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715096015.rllm-niki-044-long-ad-14-rrssn.66.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:787ab8134bdbcd18db61467a341501e80051cdad367634e53cd2fd32e3a496e5
|
3 |
+
size 9309
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715096987.rllm-niki-044-long-ad-14-rrssn.66.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe3b0c1e89e3fb4e38ba53f8856ce3ff0b68810d103f0259b6155715b96284e
|
3 |
+
size 9309
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715097974.rllm-niki-044-long-ad-14-rrssn.66.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:039430807a7543dbe5723e47315d5632e568cbd0e6f3697789fcfb379061db2f
|
3 |
+
size 9309
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715098963.rllm-niki-044-long-ad-14-rrssn.66.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d0aacedcc518dae6b391f6ce2420734d48ba5b357e9c9442a9bdd31ad647c83
|
3 |
+
size 10080
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715100000.rllm-niki-044-long-ad-14-rrssn.66.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2784a7343d283d5d8ca6276a1e7948ad797d03769e203e1a64ee4205702f8def
|
3 |
+
size 10080
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715101010.rllm-niki-044-long-ad-14-rrssn.66.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ada27edfdc9c9eeb4d0a7b1d845c27cbbc3cc4438b1c17b549d00076747f49
|
3 |
+
size 10080
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715102047.rllm-niki-044-long-ad-14-rrssn.66.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef5b1dad45f5ff0cee79a9d11576e7360c3a08eac72c27aebbc0b55ab232fe98
|
3 |
+
size 10080
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715103129.rllm-niki-044-long-ad-14-rrssn.66.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:635b959bc3042acbea9e2dd2a25a5b91722bdfc677b3e2d1cda521377ba0f9b9
|
3 |
+
size 10851
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715104226.rllm-niki-044-long-ad-14-rrssn.66.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7620a4eaf60be2e5ed276b76e7b18f789e1d71a9ecad286299e6ace3e74cfaf
|
3 |
+
size 10851
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715105297.rllm-niki-044-long-ad-14-rrssn.66.20
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90a522ce2261e1331547b5f4a6b2d13fc018b41bc67ffde90968b0a1286f0713
|
3 |
+
size 10851
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715106340.rllm-niki-044-long-ad-14-rrssn.66.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5409420a82bdfcc4f84ed9c2152a6244dd7e075515f472c7dce2778f1de2c941
|
3 |
+
size 10851
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715107374.rllm-niki-044-long-ad-14-rrssn.66.22
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b91b449378073489f3150a9d3b450ac4e2c343a03ef4277a36a1f3e8459612e
|
3 |
+
size 11622
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715108482.rllm-niki-044-long-ad-14-rrssn.66.23
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24554809888938feed375d2ea7986fd91eb890cf18e87552f67febe54ea64253
|
3 |
+
size 11622
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715109565.rllm-niki-044-long-ad-14-rrssn.66.24
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8171e2448848f5e3b72b7027b5db152eb195e561e23361b232e8dc7d9ec88f69
|
3 |
+
size 11622
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715110602.rllm-niki-044-long-ad-14-rrssn.66.25
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08f15d13b2bd2ab9acb386be8f74a10fdd44f7442ebb3e2e16d256d50363d07c
|
3 |
+
size 11622
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715111647.rllm-niki-044-long-ad-14-rrssn.66.26
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0989fadb30c4ff73b81e1bbcd148c9db2853cbe54b5c733996d94535306986d8
|
3 |
+
size 12393
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715112747.rllm-niki-044-long-ad-14-rrssn.66.27
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13cc3cc36a50a7ec6a2f40448840c883e038b711e68e21f41d37d513471590d3
|
3 |
+
size 12393
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715113858.rllm-niki-044-long-ad-14-rrssn.66.28
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d4fcb28e6de8229666a3b82096e8ea8b833a00d4535f9b89de3492c064581ff
|
3 |
+
size 12393
|
runs/May07_13-28-09_rllm-niki-044-long-ad-14-rrssn/events.out.tfevents.1715114925.rllm-niki-044-long-ad-14-rrssn.66.29
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac271acaad8d3368a9358130d8a3d62dd86aaa6cf3a3386dba69b2bf261bb6d0
|
3 |
+
size 12393
|
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 sha256:6bd897d1b2ff40819d27dfca75c5283474bad8f65a8fb40c468b21babfed1a0f
|
3 |
+
size 5176
|