Seynro commited on
Commit
cd415b2
·
verified ·
1 Parent(s): 07bf0d0

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. config.json +35 -6
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,12 +1,12 @@
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,
@@ -18,13 +18,42 @@
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": "4.49.0",
 
1
  {
2
+ "_name_or_path": "google/flan-t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
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,
 
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
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": "4.49.0",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
3
- size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
3
+ size 990345064
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e199b472559e751d0a2c1f2a93cbdadbf1689a5b0ab06b8ee95ec9cb709ac8c0
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a01da3f911c7391e39c82e7e7d3942ae9762ad4614907a5211f63df84cf891
3
  size 5496