sam-paech commited on
Commit
e2d2b8d
·
verified ·
1 Parent(s): eb2d0b2

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/muppet-roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "roberta",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.45.2",
35
+ "type_vocab_size": 1,
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6860272da4c6bd537aa64a8423e33bbd4be152d31b430db61b65a239f29c88f9
3
+ size 498615900
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31b400bd2e51dcbebfea23a5ccaa8a0ca5d5679f01bc94896178971b1a86b45
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f555dd259b487dd62dd1d4d4135cb9243ab657edfb020284161ae93958d3771
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9029529506581548,
3
+ "best_model_checkpoint": "muppet_base_divergence_classifier_v1.0/checkpoint-4800",
4
+ "epoch": 2.1248339973439574,
5
+ "eval_steps": 480,
6
+ "global_step": 4800,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.21248339973439576,
13
+ "eval_accuracy": 0.8745519713261649,
14
+ "eval_f1": 0.874329560354496,
15
+ "eval_loss": 0.4335894286632538,
16
+ "eval_runtime": 3.9801,
17
+ "eval_samples_per_second": 140.196,
18
+ "eval_steps_per_second": 17.587,
19
+ "step": 480
20
+ },
21
+ {
22
+ "epoch": 0.4249667994687915,
23
+ "eval_accuracy": 0.8835125448028673,
24
+ "eval_f1": 0.8827759092141159,
25
+ "eval_loss": 0.37165558338165283,
26
+ "eval_runtime": 4.0199,
27
+ "eval_samples_per_second": 138.809,
28
+ "eval_steps_per_second": 17.413,
29
+ "step": 960
30
+ },
31
+ {
32
+ "epoch": 0.6374501992031872,
33
+ "eval_accuracy": 0.8853046594982079,
34
+ "eval_f1": 0.8848186914136107,
35
+ "eval_loss": 0.37070879340171814,
36
+ "eval_runtime": 3.9732,
37
+ "eval_samples_per_second": 140.44,
38
+ "eval_steps_per_second": 17.618,
39
+ "step": 1440
40
+ },
41
+ {
42
+ "epoch": 0.849933598937583,
43
+ "eval_accuracy": 0.8888888888888888,
44
+ "eval_f1": 0.8877338353414772,
45
+ "eval_loss": 0.43106743693351746,
46
+ "eval_runtime": 4.0177,
47
+ "eval_samples_per_second": 138.885,
48
+ "eval_steps_per_second": 17.423,
49
+ "step": 1920
50
+ },
51
+ {
52
+ "epoch": 0.9065958388667552,
53
+ "grad_norm": 0.671415388584137,
54
+ "learning_rate": 1.804100815434448e-05,
55
+ "loss": 0.5386,
56
+ "step": 2048
57
+ },
58
+ {
59
+ "epoch": 1.0624169986719787,
60
+ "eval_accuracy": 0.8548387096774194,
61
+ "eval_f1": 0.8556637971147828,
62
+ "eval_loss": 0.6500999927520752,
63
+ "eval_runtime": 4.0038,
64
+ "eval_samples_per_second": 139.368,
65
+ "eval_steps_per_second": 17.483,
66
+ "step": 2400
67
+ },
68
+ {
69
+ "epoch": 1.2749003984063745,
70
+ "eval_accuracy": 0.8888888888888888,
71
+ "eval_f1": 0.888992318806512,
72
+ "eval_loss": 0.5748390555381775,
73
+ "eval_runtime": 4.0052,
74
+ "eval_samples_per_second": 139.319,
75
+ "eval_steps_per_second": 17.477,
76
+ "step": 2880
77
+ },
78
+ {
79
+ "epoch": 1.4873837981407703,
80
+ "eval_accuracy": 0.8924731182795699,
81
+ "eval_f1": 0.8920627439279448,
82
+ "eval_loss": 0.5230178236961365,
83
+ "eval_runtime": 4.0216,
84
+ "eval_samples_per_second": 138.749,
85
+ "eval_steps_per_second": 17.406,
86
+ "step": 3360
87
+ },
88
+ {
89
+ "epoch": 1.699867197875166,
90
+ "eval_accuracy": 0.8942652329749103,
91
+ "eval_f1": 0.894461310705129,
92
+ "eval_loss": 0.555411159992218,
93
+ "eval_runtime": 3.9433,
94
+ "eval_samples_per_second": 141.506,
95
+ "eval_steps_per_second": 17.752,
96
+ "step": 3840
97
+ },
98
+ {
99
+ "epoch": 1.8131916777335104,
100
+ "grad_norm": 8.14060115814209,
101
+ "learning_rate": 1.1986926694634988e-05,
102
+ "loss": 0.4507,
103
+ "step": 4096
104
+ },
105
+ {
106
+ "epoch": 1.9123505976095618,
107
+ "eval_accuracy": 0.8906810035842294,
108
+ "eval_f1": 0.8906975831458821,
109
+ "eval_loss": 0.5315648317337036,
110
+ "eval_runtime": 3.9793,
111
+ "eval_samples_per_second": 140.227,
112
+ "eval_steps_per_second": 17.591,
113
+ "step": 4320
114
+ },
115
+ {
116
+ "epoch": 2.1248339973439574,
117
+ "eval_accuracy": 0.9032258064516129,
118
+ "eval_f1": 0.9029529506581548,
119
+ "eval_loss": 0.5185472369194031,
120
+ "eval_runtime": 4.0159,
121
+ "eval_samples_per_second": 138.949,
122
+ "eval_steps_per_second": 17.431,
123
+ "step": 4800
124
+ }
125
+ ],
126
+ "logging_steps": 2048,
127
+ "max_steps": 9036,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 4,
130
+ "save_steps": 480,
131
+ "stateful_callbacks": {
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": true,
138
+ "should_training_stop": false
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 9462403342238616.0,
144
+ "train_batch_size": 8,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5f8b9010f8db32fe897d01175f35a5129879aa44e33b2d9bf5700dd6417928
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff