Training in progress, step 10
Browse files- README.md +66 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: dummy_fict-full-lstm-42
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# dummy_fict-full-lstm-42
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 7.8141
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 8
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 1
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 10.813 | 0.08 | 10 | 10.8032 |
|
48 |
+
| 10.793 | 0.16 | 20 | 10.7786 |
|
49 |
+
| 10.7565 | 0.24 | 30 | 10.7117 |
|
50 |
+
| 10.5835 | 0.32 | 40 | 10.2088 |
|
51 |
+
| 9.8124 | 0.4 | 50 | 9.1973 |
|
52 |
+
| 9.0079 | 0.48 | 60 | 8.6022 |
|
53 |
+
| 8.5534 | 0.56 | 70 | 8.2718 |
|
54 |
+
| 8.3394 | 0.64 | 80 | 8.0790 |
|
55 |
+
| 8.2026 | 0.72 | 90 | 7.9587 |
|
56 |
+
| 8.0804 | 0.8 | 100 | 7.8829 |
|
57 |
+
| 8.0245 | 0.88 | 110 | 7.8368 |
|
58 |
+
| 8.0949 | 0.96 | 120 | 7.8141 |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- Transformers 4.33.3
|
64 |
+
- Pytorch 2.0.1
|
65 |
+
- Datasets 2.12.0
|
66 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RNNForLanguageModeling"
|
4 |
+
],
|
5 |
+
"bidirectional": false,
|
6 |
+
"dropout_p": 0.1,
|
7 |
+
"emb_init_range": 0.1,
|
8 |
+
"embedding_dim": 1024,
|
9 |
+
"embedding_kwargs": {},
|
10 |
+
"hidden_dim": 1024,
|
11 |
+
"lin_init_range": 0.03125,
|
12 |
+
"lm_in_features": 1024,
|
13 |
+
"model_type": "rnn",
|
14 |
+
"num_layers": 2,
|
15 |
+
"output_last_state": false,
|
16 |
+
"output_recurrent_outputs": false,
|
17 |
+
"recur_init_range": 0.03125,
|
18 |
+
"rnn_kwargs": {},
|
19 |
+
"rnn_type": "LSTM",
|
20 |
+
"tie_weights": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.3",
|
23 |
+
"vocab_size": 50002
|
24 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f2e753e9641f49bbe7947e96053c7ef99ad8f2c25ffa2bb571bd68904280acd
|
3 |
+
size 272184705
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<eos>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"max_length": null,
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_to_multiple_of": null,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"pad_token_type_id": 0,
|
9 |
+
"padding_side": "right",
|
10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca94376b560130659aac7fc1141fac166f9e87d222e6f51cda86dacf6c253994
|
3 |
+
size 4155
|