rorschach-40 commited on
Commit
400663a
1 Parent(s): 32535cb

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/sasha/adp/flan-t5-text-classifier/classifier/AutoModelForSequenceClassification/flan-t5-small-window_5000_batch_7-classification/checkpoint-242",
3
+ "architectures": [
4
+ "T5ForSequenceClassification"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": "P",
17
+ "1": "S"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": true,
22
+ "label2id": {
23
+ "P": 0,
24
+ "S": 1
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "model_type": "t5",
28
+ "n_positions": 512,
29
+ "num_decoder_layers": 8,
30
+ "num_heads": 6,
31
+ "num_layers": 8,
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": "4.37.2",
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 sha256:3b75b75d4b9c5248bca2fe0a8d957403aa604f9f023446def153078e9ad5d23e
3
+ size 243126200
runs/Mar24_11-42-25_thor/events.out.tfevents.1711276946.thor.1334250.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31e47c262a0139c308e0ddfded5956a8654c16ed525f804048b3b9c21a7548a
3
+ size 6195
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca00a501f29ac927c99d3e3eac435c3b65e73e76f8dc26bcd76bd50634f06e83
3
+ size 4792