Commit
•
3da861e
1
Parent(s):
903cdb7
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/bart-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- varun-v-rao/squad
|
8 |
+
model-index:
|
9 |
+
- name: bart-large-lora-2.36M-squad-model2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# bart-large-lora-2.36M-squad-model2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the squad dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 64
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.35.2
|
52 |
+
- Pytorch 2.1.1+cu121
|
53 |
+
- Datasets 2.15.0
|
54 |
+
- Tokenizers 0.15.0
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9465920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0a8b4fd96384c249df4f4227488a312b3a131cec31a9ddf208ac5f8fdacc39a
|
3 |
size 9465920
|
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForQuestionAnswering"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
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 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1024,
|
41 |
+
"model_type": "bart",
|
42 |
+
"no_repeat_ngram_size": 3,
|
43 |
+
"normalize_before": false,
|
44 |
+
"num_beams": 4,
|
45 |
+
"num_hidden_layers": 12,
|
46 |
+
"pad_token_id": 1,
|
47 |
+
"scale_embedding": false,
|
48 |
+
"task_specific_params": {
|
49 |
+
"summarization": {
|
50 |
+
"length_penalty": 1.0,
|
51 |
+
"max_length": 128,
|
52 |
+
"min_length": 12,
|
53 |
+
"num_beams": 4
|
54 |
+
},
|
55 |
+
"summarization_cnn": {
|
56 |
+
"length_penalty": 2.0,
|
57 |
+
"max_length": 142,
|
58 |
+
"min_length": 56,
|
59 |
+
"num_beams": 4
|
60 |
+
},
|
61 |
+
"summarization_xsum": {
|
62 |
+
"length_penalty": 1.0,
|
63 |
+
"max_length": 62,
|
64 |
+
"min_length": 11,
|
65 |
+
"num_beams": 6
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.35.2",
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 50265
|
72 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cfb604ca247bb2a51494ac5b79667159c39895325965e3cafe5561ee72ef1fa
|
3 |
+
size 1625234232
|
runs/Jun20_16-50-49_gl1509.arc-ts.umich.edu/events.out.tfevents.1718916662.gl1509.arc-ts.umich.edu.1452621.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2b4a41539dae03e5dfe3a165c7b37ed45825721c5285ca59e85a74b4726d0d0
|
3 |
+
size 10980
|