eddieman78
commited on
Commit
•
d22341b
1
Parent(s):
a27330f
End
Browse files- README.md +4 -4
- config.json +7 -36
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
base_model: google/flan-t5-small
|
6 |
model-index:
|
7 |
- name: events-mem-large-test
|
8 |
results: []
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# events-mem-large-test
|
15 |
|
16 |
-
This model is a fine-tuned version of [google/flan-t5-
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:------:|:----:|:---------------:|
|
51 |
-
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: google/flan-t5-large
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: events-mem-large-test
|
8 |
results: []
|
|
|
13 |
|
14 |
# events-mem-large-test
|
15 |
|
16 |
+
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 35.1229
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:------:|:----:|:---------------:|
|
51 |
+
| 36.4164 | 0.0075 | 10 | 35.1229 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google/flan-t5-
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
@@ -18,45 +18,16 @@
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
28 |
-
"task_specific_params": {
|
29 |
-
"summarization": {
|
30 |
-
"early_stopping": true,
|
31 |
-
"length_penalty": 2.0,
|
32 |
-
"max_length": 200,
|
33 |
-
"min_length": 30,
|
34 |
-
"no_repeat_ngram_size": 3,
|
35 |
-
"num_beams": 4,
|
36 |
-
"prefix": "summarize: "
|
37 |
-
},
|
38 |
-
"translation_en_to_de": {
|
39 |
-
"early_stopping": true,
|
40 |
-
"max_length": 300,
|
41 |
-
"num_beams": 4,
|
42 |
-
"prefix": "translate English to German: "
|
43 |
-
},
|
44 |
-
"translation_en_to_fr": {
|
45 |
-
"early_stopping": true,
|
46 |
-
"max_length": 300,
|
47 |
-
"num_beams": 4,
|
48 |
-
"prefix": "translate English to French: "
|
49 |
-
},
|
50 |
-
"translation_en_to_ro": {
|
51 |
-
"early_stopping": true,
|
52 |
-
"max_length": 300,
|
53 |
-
"num_beams": 4,
|
54 |
-
"prefix": "translate English to Romanian: "
|
55 |
-
}
|
56 |
-
},
|
57 |
"tie_word_embeddings": false,
|
58 |
"torch_dtype": "float32",
|
59 |
"transformers_version": "4.40.1",
|
60 |
-
"use_cache":
|
61 |
"vocab_size": 32128
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "gelu_new",
|
12 |
"dropout_rate": 0.1,
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"tie_word_embeddings": false,
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.40.1",
|
31 |
+
"use_cache": true,
|
32 |
"vocab_size": 32128
|
33 |
}
|
model.safetensors
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:dbabeb033d9444f743a13730664c481c7cb15ddb2d7bd8a754dc872fa487e919
|
3 |
+
size 3132668808
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c53119d0ae0bf34028edf82979f3ebf159b1c4116545486b619b0d1da6442928
|
3 |
size 5112
|