osazuwa commited on
Commit
64ad6f7
1 Parent(s): 3ac3688

Add model checkpoint

Browse files
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": "4.35.2",
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": "4.35.2"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2ec1788f9c8e48243dbf85ae52c3d108b9da07d395ee05f99a5e4c773e6a55
3
+ size 1625426996
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8165a2708d97b42db31640048781dbdd4dac5c129cfd341f2880cc0b7c7bc555
3
+ size 3250759951
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe8e0e44b4c13ab05326c6c60eca19733d46ff21431ad7dd2087077d271d063
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da07f4bc6a42da189cc0168c278eeb6c954af047743c7cc8ef9379424d71370
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.857142857142857,
5
+ "eval_steps": 500,
6
+ "global_step": 8000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "learning_rate": 5e-05,
14
+ "loss": 0.0898,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.36,
19
+ "learning_rate": 4.683544303797468e-05,
20
+ "loss": 0.0637,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.54,
25
+ "learning_rate": 4.367088607594937e-05,
26
+ "loss": 0.0706,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.71,
31
+ "learning_rate": 4.050632911392405e-05,
32
+ "loss": 0.0894,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.89,
37
+ "learning_rate": 3.7341772151898736e-05,
38
+ "loss": 0.1138,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 1.07,
43
+ "learning_rate": 3.4177215189873416e-05,
44
+ "loss": 0.1484,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 1.25,
49
+ "learning_rate": 3.10126582278481e-05,
50
+ "loss": 0.1201,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 1.43,
55
+ "learning_rate": 2.7848101265822786e-05,
56
+ "loss": 0.1216,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.61,
61
+ "learning_rate": 2.468354430379747e-05,
62
+ "loss": 0.1238,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 1.79,
67
+ "learning_rate": 2.1518987341772153e-05,
68
+ "loss": 0.1255,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 1.96,
73
+ "learning_rate": 1.8354430379746836e-05,
74
+ "loss": 0.1305,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 2.14,
79
+ "learning_rate": 1.5189873417721521e-05,
80
+ "loss": 0.1012,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 2.32,
85
+ "learning_rate": 1.2025316455696203e-05,
86
+ "loss": 0.0969,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 2.5,
91
+ "learning_rate": 8.860759493670886e-06,
92
+ "loss": 0.1036,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 2.68,
97
+ "learning_rate": 5.69620253164557e-06,
98
+ "loss": 0.1146,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 2.86,
103
+ "learning_rate": 2.531645569620253e-06,
104
+ "loss": 0.1198,
105
+ "step": 8000
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 8400,
110
+ "num_train_epochs": 3,
111
+ "save_steps": 500,
112
+ "total_flos": 3.4673673633792e+16,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747828469188eed9e710be3490b8946d03d6473ac83e16c89b65d7577a9ea3a7
3
+ size 4728