Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +44 -0
- pytorch_model.bin +3 -0
- runs/Jan14_05-57-58_b7a73a5d9060/1642139916.8957107/events.out.tfevents.1642139916.b7a73a5d9060.72.1 +3 -0
- runs/Jan14_05-57-58_b7a73a5d9060/events.out.tfevents.1642139916.b7a73a5d9060.72.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlnet-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"XLNetForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attn_type": "bi",
|
7 |
+
"bi_data": false,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"clamp_len": -1,
|
10 |
+
"d_head": 64,
|
11 |
+
"d_inner": 3072,
|
12 |
+
"d_model": 768,
|
13 |
+
"dropout": 0.1,
|
14 |
+
"end_n_top": 5,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"ff_activation": "gelu",
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"layer_norm_eps": 1e-12,
|
19 |
+
"mem_len": null,
|
20 |
+
"model_type": "xlnet",
|
21 |
+
"n_head": 12,
|
22 |
+
"n_layer": 12,
|
23 |
+
"pad_token_id": 5,
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"reuse_len": null,
|
26 |
+
"same_length": false,
|
27 |
+
"start_n_top": 5,
|
28 |
+
"summary_activation": "tanh",
|
29 |
+
"summary_last_dropout": 0.1,
|
30 |
+
"summary_type": "last",
|
31 |
+
"summary_use_proj": true,
|
32 |
+
"task_specific_params": {
|
33 |
+
"text-generation": {
|
34 |
+
"do_sample": true,
|
35 |
+
"max_length": 250
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.15.0",
|
40 |
+
"untie_r": true,
|
41 |
+
"use_mems_eval": true,
|
42 |
+
"use_mems_train": false,
|
43 |
+
"vocab_size": 32000
|
44 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2489ee71f00fe763f50e7d24c616a43e3ac4d7538655792768025c22b2550c12
|
3 |
+
size 469316765
|
runs/Jan14_05-57-58_b7a73a5d9060/1642139916.8957107/events.out.tfevents.1642139916.b7a73a5d9060.72.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9132d8ea59edcdb9f9b70919e00e9712bc89d4e33b25761f73f9b81ac30699a2
|
3 |
+
size 4774
|
runs/Jan14_05-57-58_b7a73a5d9060/events.out.tfevents.1642139916.b7a73a5d9060.72.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c34defa32961b8a167b2184c180f5d3e3e14c7754b0ade8a86a035910152637
|
3 |
+
size 3890
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<eop>", "<eod>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<sep>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<eop>", "<eod>"], "special_tokens_map_file": null, "name_or_path": "xlnet-base-cased", "tokenizer_class": "XLNetTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70ebd70d9ddc40d100bb54d9f6a248cc5e05e315873fdc2ef43d8130c4edd9a
|
3 |
+
size 2991
|