End of training
Browse files- README.md +51 -0
- config.json +32 -0
- model.safetensors +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714380205.rllm-mz-134-adv-train-0-1-hcxpv.66.0 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714380205.rllm-mz-134-adv-train-0-1-hcxpv.67.0 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714381877.rllm-mz-134-adv-train-0-1-hcxpv.66.1 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714381893.rllm-mz-134-adv-train-0-1-hcxpv.67.1 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714383583.rllm-mz-134-adv-train-0-1-hcxpv.66.2 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714383621.rllm-mz-134-adv-train-0-1-hcxpv.67.2 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714385301.rllm-mz-134-adv-train-0-1-hcxpv.66.3 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714385357.rllm-mz-134-adv-train-0-1-hcxpv.67.3 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714387056.rllm-mz-134-adv-train-0-1-hcxpv.66.4 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714387132.rllm-mz-134-adv-train-0-1-hcxpv.67.4 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714388813.rllm-mz-134-adv-train-0-1-hcxpv.66.5 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714388908.rllm-mz-134-adv-train-0-1-hcxpv.67.5 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714390567.rllm-mz-134-adv-train-0-1-hcxpv.66.6 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714390679.rllm-mz-134-adv-train-0-1-hcxpv.67.6 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714392313.rllm-mz-134-adv-train-0-1-hcxpv.66.7 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714392444.rllm-mz-134-adv-train-0-1-hcxpv.67.7 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714394042.rllm-mz-134-adv-train-0-1-hcxpv.66.8 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714394195.rllm-mz-134-adv-train-0-1-hcxpv.67.8 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714395768.rllm-mz-134-adv-train-0-1-hcxpv.66.9 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714395941.rllm-mz-134-adv-train-0-1-hcxpv.67.9 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714397526.rllm-mz-134-adv-train-0-1-hcxpv.66.10 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714397720.rllm-mz-134-adv-train-0-1-hcxpv.67.10 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714399281.rllm-mz-134-adv-train-0-1-hcxpv.66.11 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714399497.rllm-mz-134-adv-train-0-1-hcxpv.67.11 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714401025.rllm-mz-134-adv-train-0-1-hcxpv.66.12 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714401263.rllm-mz-134-adv-train-0-1-hcxpv.67.12 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714402771.rllm-mz-134-adv-train-0-1-hcxpv.66.13 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714403029.rllm-mz-134-adv-train-0-1-hcxpv.67.13 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714404512.rllm-mz-134-adv-train-0-1-hcxpv.66.14 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714404795.rllm-mz-134-adv-train-0-1-hcxpv.67.14 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714406246.rllm-mz-134-adv-train-0-1-hcxpv.66.15 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714406543.rllm-mz-134-adv-train-0-1-hcxpv.67.15 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714407971.rllm-mz-134-adv-train-0-1-hcxpv.66.16 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714408295.rllm-mz-134-adv-train-0-1-hcxpv.67.16 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714409723.rllm-mz-134-adv-train-0-1-hcxpv.66.17 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714410070.rllm-mz-134-adv-train-0-1-hcxpv.67.17 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714411493.rllm-mz-134-adv-train-0-1-hcxpv.66.18 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714411864.rllm-mz-134-adv-train-0-1-hcxpv.67.18 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714413253.rllm-mz-134-adv-train-0-1-hcxpv.66.19 +3 -0
- runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714413642.rllm-mz-134-adv-train-0-1-hcxpv.67.19 +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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: EleutherAI/pythia-14m
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: robust_llm_pythia-14m_mz-134_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-134_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: 3e-06
|
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 sha256:5b99ef8d1eee09404310ba1dde414af3514f3304fff19d847c01b917adefb15f
|
3 |
+
size 30524712
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714380205.rllm-mz-134-adv-train-0-1-hcxpv.66.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4e0c7304ea6d9e8e4815d69f4fdab611288450d6d8000032ece95089e018771
|
3 |
+
size 6800
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714380205.rllm-mz-134-adv-train-0-1-hcxpv.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f81f618f31f769fde7e0af97e1549186857dcb8858057c9f86349d78be15412
|
3 |
+
size 6800
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714381877.rllm-mz-134-adv-train-0-1-hcxpv.66.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7437fd044b127749e215608330b2c759a8715ac5965cfc3bd12f85ee8e96c25
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714381893.rllm-mz-134-adv-train-0-1-hcxpv.67.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b72bfc2faf635dc0b0f465cf8ecf5c038418169b50935f8551e6fe06c2a381f
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714383583.rllm-mz-134-adv-train-0-1-hcxpv.66.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc5ebaf6ec5083fd44edb1edc7db98b48b8ceda51d6983542be63e7d057ff1a3
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714383621.rllm-mz-134-adv-train-0-1-hcxpv.67.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd672e3372b60f066fb32c7d62000497a4b6f539ac8d34b67a947d32c58e4790
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714385301.rllm-mz-134-adv-train-0-1-hcxpv.66.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:261ab194df83b0c0ba9f365fb6f81f61773296b6ccc7cd35a5472fe0c75ef6b3
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714385357.rllm-mz-134-adv-train-0-1-hcxpv.67.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfe41e17bf61ce1c64735d4c57bf006af08f80563e74269e1bc4b6f49863965c
|
3 |
+
size 6849
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714387056.rllm-mz-134-adv-train-0-1-hcxpv.66.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c47353af31cdad15cfcce46ddaef4293c4039f76a84c276bdf3561fea484d41c
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714387132.rllm-mz-134-adv-train-0-1-hcxpv.67.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1683e501dd1072e920d73bb34a0ffce0b855ec3ae6a8fd22a6eaef3abdd6d645
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714388813.rllm-mz-134-adv-train-0-1-hcxpv.66.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc2f3ea0c48f7464426b2c13cb3dce26b581b233b0bede82a0f39b73ce54cbcf
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714388908.rllm-mz-134-adv-train-0-1-hcxpv.67.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78e29733c3d31d7811892fd422ed07c6395830057dfec72ef4af06e8b4ffb67d
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714390567.rllm-mz-134-adv-train-0-1-hcxpv.66.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa4e5dd8a73f4f6ce45a81c4260cbd0d4237b47300355b730e6419cd47506a5
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714390679.rllm-mz-134-adv-train-0-1-hcxpv.67.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca7177d17ba7ca1effbcbd22b2319ec15c65d8035a12b333b9452ae63b027c73
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714392313.rllm-mz-134-adv-train-0-1-hcxpv.66.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19d13e7cff801cbc8795b10b13ed58db3e54790e76b66ad13f10321947a133b
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714392444.rllm-mz-134-adv-train-0-1-hcxpv.67.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5da50f1286319651422272c7e2dc8db8cae4eb437581fa2c72567df236512714
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714394042.rllm-mz-134-adv-train-0-1-hcxpv.66.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41e81ffdf0b3df6ab7b06f4c4fbe7671765afbd14409566c1f5b855874f92207
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714394195.rllm-mz-134-adv-train-0-1-hcxpv.67.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86dc2a5c88ca1178d59a34ec33ab7a506eee21a5ee5aab2040bf81b9a43d90b8
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714395768.rllm-mz-134-adv-train-0-1-hcxpv.66.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df43c623103fa2d7adde788f2ed5e987d5ae19dd5e7de04f910d46317fddcde0
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714395941.rllm-mz-134-adv-train-0-1-hcxpv.67.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd44de0d3d75c42fe1fdb0e9513d8a2da6bc6b38fa9fe4dee1ed0d853250cee2
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714397526.rllm-mz-134-adv-train-0-1-hcxpv.66.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e21df1687bf2af32b5f9bc97cf855eff2423ea23fa71a8215f2b41798ab01f2
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714397720.rllm-mz-134-adv-train-0-1-hcxpv.67.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ccb4f97b1f61aa300070e1acc8bf729c2509234948bde11477385a089632a398
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714399281.rllm-mz-134-adv-train-0-1-hcxpv.66.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bff8c20201e9e56579d783b9a5bdc503ac84fbd656c8f9259798659b1ce8c0f2
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714399497.rllm-mz-134-adv-train-0-1-hcxpv.67.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee0ae7783eaf6f205678bcc1240f48c8fbd3e8657cd34099af9ff70b10e7127b
|
3 |
+
size 7620
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714401025.rllm-mz-134-adv-train-0-1-hcxpv.66.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b23892ea6a8afb5f1bae932ab7a9083238d7911b8db29be118f2fc5a3f44928
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714401263.rllm-mz-134-adv-train-0-1-hcxpv.67.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b57b40e7143a4cdcf5283da5efd17e693040909805274cf3073d0978e7fa21e
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714402771.rllm-mz-134-adv-train-0-1-hcxpv.66.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e543945507a11858f8ab8a183636e742e78b01a7bdcfead6268d984ce53774
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714403029.rllm-mz-134-adv-train-0-1-hcxpv.67.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c37c23304e411bc2dc9172edc8ff99960aa189330906b4a970f1f65ac27e410d
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714404512.rllm-mz-134-adv-train-0-1-hcxpv.66.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68654043aaac6f721e18a4a7f08e7dd29fa75ec7e0d7f9ffe9f970c3b8c27068
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714404795.rllm-mz-134-adv-train-0-1-hcxpv.67.14
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:676e363c8a62a4a577932ca2a2b139368fd42287aa9fff7db665c13a49feb347
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714406246.rllm-mz-134-adv-train-0-1-hcxpv.66.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3efe2df296904a3377ba864086260189b498482897a958399601e57f3e66895
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714406543.rllm-mz-134-adv-train-0-1-hcxpv.67.15
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:493a01e1974b64fc8137ed90beda6255ea7f3b7b5a4b528646789973ca734a84
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714407971.rllm-mz-134-adv-train-0-1-hcxpv.66.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9292bdb5e52fb409fa9500ccef043797fe86f95feb0360c670200c9e6b06894
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714408295.rllm-mz-134-adv-train-0-1-hcxpv.67.16
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fee65c46dc433b4b866761dcab9639e1a8e95bbc9948d1a8ea4e079eab74d8c
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714409723.rllm-mz-134-adv-train-0-1-hcxpv.66.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:281fd758ccbd9fc58b66577bfff831c8ff768f447e720af2caefe86b0a318db0
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714410070.rllm-mz-134-adv-train-0-1-hcxpv.67.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c77c591054292670df8d7b8df69bfb54da46c73b35072d7faa560964a847925
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714411493.rllm-mz-134-adv-train-0-1-hcxpv.66.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb30f83cd492adef490b08df0ec0c0fd413812dce349303aad0285d99960219c
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714411864.rllm-mz-134-adv-train-0-1-hcxpv.67.18
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a1467c05cfa7e4d94918e6faa0992ec00096bedcfc2e734cab07ebd25a61c6c
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714413253.rllm-mz-134-adv-train-0-1-hcxpv.66.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fdd15234a3152d0fe23e11ac95ade1d59add1a3ccb5f030c4c7208809fe2db6
|
3 |
+
size 8391
|
runs/Apr29_08-43-16_rllm-mz-134-adv-train-0-1-hcxpv/events.out.tfevents.1714413642.rllm-mz-134-adv-train-0-1-hcxpv.67.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbce88190b94c953a963fa468b12d9f1d05b7952634960b506c6e616ec81fda3
|
3 |
+
size 8391
|
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 sha256:2aa3523fe71b1c63e5794d40ec89746d03012f8b9b94c70715a9e8e7756cb1dd
|
3 |
+
size 5048
|