Training in progress, epoch 1
Browse files- config.json +71 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2048,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"id2label": {
|
16 |
+
"0": "not funny",
|
17 |
+
"1": "funny"
|
18 |
+
},
|
19 |
+
"initializer_factor": 1.0,
|
20 |
+
"is_encoder_decoder": true,
|
21 |
+
"is_gated_act": true,
|
22 |
+
"label2id": {
|
23 |
+
"funny": 1,
|
24 |
+
"not funny": 0
|
25 |
+
},
|
26 |
+
"layer_norm_epsilon": 1e-06,
|
27 |
+
"model_type": "t5",
|
28 |
+
"n_positions": 512,
|
29 |
+
"num_decoder_layers": 12,
|
30 |
+
"num_heads": 12,
|
31 |
+
"num_layers": 12,
|
32 |
+
"output_past": true,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"relative_attention_max_distance": 128,
|
36 |
+
"relative_attention_num_buckets": 32,
|
37 |
+
"task_specific_params": {
|
38 |
+
"summarization": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"length_penalty": 2.0,
|
41 |
+
"max_length": 200,
|
42 |
+
"min_length": 30,
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"num_beams": 4,
|
45 |
+
"prefix": "summarize: "
|
46 |
+
},
|
47 |
+
"translation_en_to_de": {
|
48 |
+
"early_stopping": true,
|
49 |
+
"max_length": 300,
|
50 |
+
"num_beams": 4,
|
51 |
+
"prefix": "translate English to German: "
|
52 |
+
},
|
53 |
+
"translation_en_to_fr": {
|
54 |
+
"early_stopping": true,
|
55 |
+
"max_length": 300,
|
56 |
+
"num_beams": 4,
|
57 |
+
"prefix": "translate English to French: "
|
58 |
+
},
|
59 |
+
"translation_en_to_ro": {
|
60 |
+
"early_stopping": true,
|
61 |
+
"max_length": 300,
|
62 |
+
"num_beams": 4,
|
63 |
+
"prefix": "translate English to Romanian: "
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"tie_word_embeddings": false,
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.39.2",
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 32128
|
71 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02a656bf3a21e974665a1c18f2384a8df5ccfd9af09908400444dd52781060fc
|
3 |
+
size 894020048
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aceedb9544511807a408fb8cefe73e7eda9f5eda764660ef178bc26eabeeccb5
|
3 |
+
size 5112
|