Hugging Face's logo

osazuwa
/
causalLLM-prince

Transformers
PyTorch
bart
text2text-generation
Model card Files
xet
 Community
1
osazuwa commited on
Commit
eb07cde
·
1 Parent(s): 5185c5d

Initial update

Browse files
Files changed (7) hide show
  1. config.json +74 -0
  2. generation_config.json +13 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +70 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.31.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.31.0"
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1ea58a8cc701755a934f55119b6048257e0c83cf51d3d9b4df68d488cc7247a
3
+ size 1625541389
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f13ddf5256b8fece8a119c2d7ec91909e35ccd9da3f350159beb8d72b9c79e
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fe714afd93a500e9bffa11d97f82c71036be3f4afde899a2c3e4ce7ced2773
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9991823385118561,
5
+ "global_step": 4890,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.2,
12
+ "learning_rate": 3e-05,
13
+ "loss": 0.3074,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.41,
18
+ "learning_rate": 2.6584699453551913e-05,
19
+ "loss": 0.0499,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.61,
24
+ "learning_rate": 2.3169398907103826e-05,
25
+ "loss": 0.0496,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.82,
30
+ "learning_rate": 1.975409836065574e-05,
31
+ "loss": 0.0443,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.02,
36
+ "learning_rate": 1.633879781420765e-05,
37
+ "loss": 0.0433,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.23,
42
+ "learning_rate": 1.2923497267759564e-05,
43
+ "loss": 0.0411,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.43,
48
+ "learning_rate": 9.508196721311476e-06,
49
+ "loss": 0.0401,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.64,
54
+ "learning_rate": 6.092896174863388e-06,
55
+ "loss": 0.0395,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.84,
60
+ "learning_rate": 2.6775956284153005e-06,
61
+ "loss": 0.0388,
62
+ "step": 4500
63
+ }
64
+ ],
65
+ "max_steps": 4892,
66
+ "num_train_epochs": 2,
67
+ "total_flos": 4.238314825580544e+16,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec891222524c96f4a21bc6f75e3f3b25ebe5c708d1ba3ccbc320d31fbfed4d81
3
+ size 4155