rorschach-40 commited on
Commit
958dbdf
1 Parent(s): 5953ea1

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-t5-large",
3
+ "architectures": [
4
+ "T5ForSequenceClassification"
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,
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": 24,
30
+ "num_heads": 16,
31
+ "num_layers": 24,
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
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.37.2",
40
+ "use_cache": true,
41
+ "vocab_size": 32128
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18de880f58d2fb84e2cced5586b3f1b0ab623174f10e844a703a5d390547c045
3
+ size 3005286112
runs/Mar20_17-12-07_thor/events.out.tfevents.1710951129.thor.697145.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f13ac437dfc809adca15441cf4a7479a845d1960e427e60ac334c29b89cc531
3
+ size 4711
runs/Mar20_17-13-33_thor/events.out.tfevents.1710951215.thor.697704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2228cf4ddfb692174012a4a3b839ef384ba21907dfc002c199643a15bd60649
3
+ size 5285
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69e1e468e89046a14343fc6127a289c945783ec6c7ca04ed8da6ede43394b2f
3
+ size 4792