Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +40 -0
- pytorch_model.bin +3 -0
- runs/Feb21_09-39-12_tardis/1676968762.0543756/events.out.tfevents.1676968762.tardis.2709587.1 +3 -0
- runs/Feb21_09-39-12_tardis/events.out.tfevents.1676968762.tardis.2709587.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +6 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "schreon/gpt2large-lhm-04",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"is_decoder": true,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 256,
|
16 |
+
"n_embd": 1280,
|
17 |
+
"n_head": 20,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 36,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.25.1",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 40000
|
40 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8972cb6f113d08c19207fc5911e87a4c930947a02e09a1a858cae709a27d6c3
|
3 |
+
size 3081519165
|
runs/Feb21_09-39-12_tardis/1676968762.0543756/events.out.tfevents.1676968762.tardis.2709587.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e65e68c7130382ae7551a02f4104e8bc0f0705ec7ab737bcdfe16ba7975747fb
|
3 |
+
size 5538
|
runs/Feb21_09-39-12_tardis/events.out.tfevents.1676968762.tardis.2709587.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e50f9461b92cbb4ac9e00f8aaf8f7e2c5315d1fad31cfb32d9cd62892f564e7f
|
3 |
+
size 4228
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<cls>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "</s>",
|
7 |
+
"sep_token": "<sep>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 1000000000000000019884624838656,
|
3 |
+
"name_or_path": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast",
|
4 |
+
"special_tokens_map_file": "/home/ma/s/schroederl/XNEXT/xnext/data/tokenizer_fast/special_tokens_map.json",
|
5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
6 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a09c99b0c1daeed33c4a7459178f758ca524e0263867875fac0356dc3ec4243
|
3 |
+
size 3451
|