Training in progress, step 250
Browse files- .gitignore +1 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- runs/Dec31_17-29-56_n0004.savio3/1672538464.2712455/events.out.tfevents.1672538464.n0004.savio3.64291.1 +3 -0
- runs/Dec31_17-29-56_n0004.savio3/events.out.tfevents.1672538464.n0004.savio3.64291.0 +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"eos_token_id": 50256,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"layer_norm_epsilon": 1e-05,
|
12 |
+
"model_type": "gpt2",
|
13 |
+
"n_embd": 768,
|
14 |
+
"n_head": 12,
|
15 |
+
"n_inner": null,
|
16 |
+
"n_layer": 12,
|
17 |
+
"n_positions": 512,
|
18 |
+
"reorder_and_upcast_attn": false,
|
19 |
+
"resid_pdrop": 0.1,
|
20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
21 |
+
"scale_attn_weights": true,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "mean",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.24.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 4096
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e58b3ccebab689477bc7321e8e590e7f9e3e13577ba068d007c0ba99d5b5be27
|
3 |
+
size 357581373
|
runs/Dec31_17-29-56_n0004.savio3/1672538464.2712455/events.out.tfevents.1672538464.n0004.savio3.64291.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f1671b50c109df5d1ba175413f1a4fe9a05f143feb85d739ce3d1bd5d737e1b
|
3 |
+
size 5676
|
runs/Dec31_17-29-56_n0004.savio3/events.out.tfevents.1672538464.n0004.savio3.64291.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd1a9a36885598cc4e664a4e17a8e21d17fa8d5a4b89672d6b5f2acd739a5830
|
3 |
+
size 4516
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<BOS>",
|
3 |
+
"cls_token": "<CLS>",
|
4 |
+
"eos_token": "<EOS>",
|
5 |
+
"mask_token": "<MASK>",
|
6 |
+
"pad_token": "<PAD>",
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_max_length": 512,
|
3 |
+
"name_or_path": "/global/scratch/users/aniketh/PromoGen/SentencePieceUnigramTokenizer_4096_min_exp_2_fast",
|
4 |
+
"special_tokens": [
|
5 |
+
"<BOS>",
|
6 |
+
"<EOS>",
|
7 |
+
"<PAD>",
|
8 |
+
"<UNK>",
|
9 |
+
"<CLS>",
|
10 |
+
"<SEP>",
|
11 |
+
"<MASK>"
|
12 |
+
],
|
13 |
+
"special_tokens_map_file": "/global/scratch/users/aniketh/PromoGen/SentencePieceUnigramTokenizer_4096_min_exp_2_fast/special_tokens_map.json",
|
14 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d187c7796c31c77bc69371c0b68a7052eba69476c6bb7fb8edeea8ecf8f8f13
|
3 |
+
size 3515
|