End of training
Browse files- .gitignore +1 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Apr12_11-35-25_7eec58e665ce/1681299342.8705335/events.out.tfevents.1681299342.7eec58e665ce.23.1 +3 -0
- runs/Apr12_11-35-25_7eec58e665ce/events.out.tfevents.1681299342.7eec58e665ce.23.0 +3 -0
- runs/Apr12_11-40-27_7eec58e665ce/1681299637.5568898/events.out.tfevents.1681299637.7eec58e665ce.23.3 +3 -0
- runs/Apr12_11-40-27_7eec58e665ce/events.out.tfevents.1681299637.7eec58e665ce.23.2 +3 -0
- runs/Apr12_11-45-47_7eec58e665ce/1681299949.4890563/events.out.tfevents.1681299949.7eec58e665ce.23.5 +3 -0
- runs/Apr12_11-45-47_7eec58e665ce/events.out.tfevents.1681299949.7eec58e665ce.23.4 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 128,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.27.4",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50000
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.27.4"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c98cb89369999418b35b8236f480c56204f100ffcfd2a6951c288655ec095803
|
3 |
+
size 509608509
|
runs/Apr12_11-35-25_7eec58e665ce/1681299342.8705335/events.out.tfevents.1681299342.7eec58e665ce.23.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd85737142971f7c22200b858b742321523484d704ec4173b8ae52b069e79cc5
|
3 |
+
size 5773
|
runs/Apr12_11-35-25_7eec58e665ce/events.out.tfevents.1681299342.7eec58e665ce.23.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dd38d3fe08e3418833c94843c5957bffdf05053b975acb975cc50436354e0a6
|
3 |
+
size 4152
|
runs/Apr12_11-40-27_7eec58e665ce/1681299637.5568898/events.out.tfevents.1681299637.7eec58e665ce.23.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:189d440088713e90e66ef09dfadc44e152cc824a54e908916d5aa2c52f626fb0
|
3 |
+
size 5773
|
runs/Apr12_11-40-27_7eec58e665ce/events.out.tfevents.1681299637.7eec58e665ce.23.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:353d0d7357b5f62990d5c64a4b4731b64de7df0c6ac0f8047d7e44363ee00080
|
3 |
+
size 4153
|
runs/Apr12_11-45-47_7eec58e665ce/1681299949.4890563/events.out.tfevents.1681299949.7eec58e665ce.23.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7b7af49cb57878ac75aab2fde4dd42bd1179ce3a3c22ecdce0bcfefbe1c837
|
3 |
+
size 5773
|
runs/Apr12_11-45-47_7eec58e665ce/events.out.tfevents.1681299949.7eec58e665ce.23.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2701145130a99a92afff083ffb43cdb1171badb798e02646c00e83350d8ef25f
|
3 |
+
size 4935
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"special_tokens_map_file": null,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aed9ecfd3e22aea3553ba9f9876b7d9d6b98921acf034616256353a0f6b51f5a
|
3 |
+
size 3579
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|