oliverguhr
commited on
Commit
•
370b45c
1
Parent(s):
f9a54ca
deleted old model
Browse files- all_results.json +0 -14
- config.json +0 -75
- eval_results.json +0 -9
- merges.txt +0 -0
- model.safetensors +0 -3
- pytorch_model.bin +0 -3
- runs/May23_22-15-11_redrod/1653336920.7642183/events.out.tfevents.1653336920.redrod.73588.1 +0 -3
- runs/May23_22-15-11_redrod/events.out.tfevents.1653336920.redrod.73588.0 +0 -3
- runs/May23_22-15-11_redrod/events.out.tfevents.1653359540.redrod.73588.2 +0 -3
- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
- train_results.json +0 -8
- trainer_state.json +0 -0
- training_args.bin +0 -3
- vocab.json +0 -0
all_results.json
DELETED
@@ -1,14 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 2.0,
|
3 |
-
"eval_cer": 0.20216230110383845,
|
4 |
-
"eval_loss": 0.10652155429124832,
|
5 |
-
"eval_runtime": 981.2095,
|
6 |
-
"eval_samples": 1000,
|
7 |
-
"eval_samples_per_second": 1.019,
|
8 |
-
"eval_steps_per_second": 0.255,
|
9 |
-
"train_loss": 0.16492035415392825,
|
10 |
-
"train_runtime": 21638.3485,
|
11 |
-
"train_samples": 298969,
|
12 |
-
"train_samples_per_second": 27.633,
|
13 |
-
"train_steps_per_second": 0.863
|
14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
DELETED
@@ -1,75 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "facebook/bart-base",
|
3 |
-
"activation_dropout": 0.1,
|
4 |
-
"activation_function": "gelu",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": false,
|
7 |
-
"architectures": [
|
8 |
-
"BartForConditionalGeneration"
|
9 |
-
],
|
10 |
-
"attention_dropout": 0.1,
|
11 |
-
"bos_token_id": 0,
|
12 |
-
"classif_dropout": 0.1,
|
13 |
-
"classifier_dropout": 0.0,
|
14 |
-
"d_model": 768,
|
15 |
-
"decoder_attention_heads": 12,
|
16 |
-
"decoder_ffn_dim": 3072,
|
17 |
-
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers": 6,
|
19 |
-
"decoder_start_token_id": 2,
|
20 |
-
"dropout": 0.1,
|
21 |
-
"early_stopping": true,
|
22 |
-
"encoder_attention_heads": 12,
|
23 |
-
"encoder_ffn_dim": 3072,
|
24 |
-
"encoder_layerdrop": 0.0,
|
25 |
-
"encoder_layers": 6,
|
26 |
-
"eos_token_id": 2,
|
27 |
-
"forced_bos_token_id": 0,
|
28 |
-
"forced_eos_token_id": 2,
|
29 |
-
"gradient_checkpointing": false,
|
30 |
-
"id2label": {
|
31 |
-
"0": "LABEL_0",
|
32 |
-
"1": "LABEL_1",
|
33 |
-
"2": "LABEL_2"
|
34 |
-
},
|
35 |
-
"init_std": 0.02,
|
36 |
-
"is_encoder_decoder": true,
|
37 |
-
"label2id": {
|
38 |
-
"LABEL_0": 0,
|
39 |
-
"LABEL_1": 1,
|
40 |
-
"LABEL_2": 2
|
41 |
-
},
|
42 |
-
"max_position_embeddings": 1024,
|
43 |
-
"model_type": "bart",
|
44 |
-
"no_repeat_ngram_size": 3,
|
45 |
-
"normalize_before": false,
|
46 |
-
"normalize_embedding": true,
|
47 |
-
"num_beams": 4,
|
48 |
-
"num_hidden_layers": 6,
|
49 |
-
"pad_token_id": 1,
|
50 |
-
"scale_embedding": false,
|
51 |
-
"task_specific_params": {
|
52 |
-
"summarization": {
|
53 |
-
"length_penalty": 1.0,
|
54 |
-
"max_length": 128,
|
55 |
-
"min_length": 12,
|
56 |
-
"num_beams": 4
|
57 |
-
},
|
58 |
-
"summarization_cnn": {
|
59 |
-
"length_penalty": 2.0,
|
60 |
-
"max_length": 142,
|
61 |
-
"min_length": 56,
|
62 |
-
"num_beams": 4
|
63 |
-
},
|
64 |
-
"summarization_xsum": {
|
65 |
-
"length_penalty": 1.0,
|
66 |
-
"max_length": 62,
|
67 |
-
"min_length": 11,
|
68 |
-
"num_beams": 6
|
69 |
-
}
|
70 |
-
},
|
71 |
-
"torch_dtype": "float32",
|
72 |
-
"transformers_version": "4.19.0.dev0",
|
73 |
-
"use_cache": true,
|
74 |
-
"vocab_size": 50265
|
75 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
eval_results.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 2.0,
|
3 |
-
"eval_cer": 0.20216230110383845,
|
4 |
-
"eval_loss": 0.10652155429124832,
|
5 |
-
"eval_runtime": 981.2095,
|
6 |
-
"eval_samples": 1000,
|
7 |
-
"eval_samples_per_second": 1.019,
|
8 |
-
"eval_steps_per_second": 0.255
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:030e468aa6f6df38adebed6971806a773f786904ab811d274f0af6423a2cc16d
|
3 |
-
size 557912616
|
|
|
|
|
|
|
|
pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8fafd7324572f453b2f6bbb76fae25b68a38925abefc7c36e7d107d1729d7bbf
|
3 |
-
size 557969145
|
|
|
|
|
|
|
|
runs/May23_22-15-11_redrod/1653336920.7642183/events.out.tfevents.1653336920.redrod.73588.1
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:cd5745bc0a83afd042d29ac6b6e31ec45457d8165cfa35f612448575c097f986
|
3 |
-
size 5381
|
|
|
|
|
|
|
|
runs/May23_22-15-11_redrod/events.out.tfevents.1653336920.redrod.73588.0
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a78553872f86b85f91efa5cd7976d85682af10bd1ad771e15c85936022208d44
|
3 |
-
size 304749
|
|
|
|
|
|
|
|
runs/May23_22-15-11_redrod/events.out.tfevents.1653359540.redrod.73588.2
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d7c4603dab81d2ad2a758a6dbc983c52c3433fec1f722d29331e12b29a112a0f
|
3 |
-
size 364
|
|
|
|
|
|
|
|
special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
|
|
|
tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
|
|
|
|
train_results.json
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 2.0,
|
3 |
-
"train_loss": 0.16492035415392825,
|
4 |
-
"train_runtime": 21638.3485,
|
5 |
-
"train_samples": 298969,
|
6 |
-
"train_samples_per_second": 27.633,
|
7 |
-
"train_steps_per_second": 0.863
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:86db7474590e0d9fb8ea0e8be89b19710348e2b8b5efbd7f2dad410f64876127
|
3 |
-
size 3311
|
|
|
|
|
|
|
|
vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|