folflo commited on
Commit
d562602
1 Parent(s): 50b9535

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
7
+ "add_cross_attention": true,
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bad_words_ids": null,
11
+ "begin_suppress_tokens": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "classifier_dropout": null,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "gradient_checkpointing": false,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0.1,
29
+ "hidden_size": 768,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "min_length": 0,
47
+ "model_type": "bert",
48
+ "no_repeat_ngram_size": 0,
49
+ "num_attention_heads": 12,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_hidden_layers": 12,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "type_vocab_size": 2,
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "use_cache": true,
82
+ "vocab_size": 32001
83
+ },
84
+ "decoder_start_token_id": 2,
85
+ "early_stopping": true,
86
+ "encoder": {
87
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
88
+ "add_cross_attention": false,
89
+ "architectures": null,
90
+ "attention_probs_dropout_prob": 0.1,
91
+ "bad_words_ids": null,
92
+ "begin_suppress_tokens": null,
93
+ "bos_token_id": null,
94
+ "chunk_size_feed_forward": 0,
95
+ "classifier_dropout": null,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": null,
103
+ "exponential_decay_length_penalty": null,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "gradient_checkpointing": false,
108
+ "hidden_act": "gelu",
109
+ "hidden_dropout_prob": 0.1,
110
+ "hidden_size": 768,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 3072,
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "label2id": {
120
+ "LABEL_0": 0,
121
+ "LABEL_1": 1
122
+ },
123
+ "layer_norm_eps": 1e-12,
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "max_position_embeddings": 512,
127
+ "min_length": 0,
128
+ "model_type": "bert",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 12,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 12,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": 0,
139
+ "position_embedding_type": "absolute",
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "sep_token_id": null,
148
+ "suppress_tokens": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": null,
158
+ "torchscript": false,
159
+ "type_vocab_size": 2,
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false,
162
+ "use_cache": true,
163
+ "vocab_size": 32001
164
+ },
165
+ "eos_token_id": 3,
166
+ "is_encoder_decoder": true,
167
+ "length_penalty": 2.0,
168
+ "max_length": 142,
169
+ "min_length": 56,
170
+ "model_type": "encoder-decoder",
171
+ "no_repeat_ngram_size": 3,
172
+ "num_beams": 8,
173
+ "pad_token_id": 0,
174
+ "torch_dtype": "float32",
175
+ "transformers_version": "4.35.2",
176
+ "vocab_size": 32001
177
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba89f71ddc54f25cd8d8d4d7170bbd4c27ff553cf87906e562386bd30a0039b
3
+ size 998611676
runs/Dec06_22-24-15_TENSOR-FLOWER/events.out.tfevents.1701897858.TENSOR-FLOWER.9348.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de31f2efa6ada36ab84b1aff6d8ecb9cbd46ff32817837ffc7fc43d9cef5405d
3
+ size 8513
runs/Dec06_22-32-20_TENSOR-FLOWER/events.out.tfevents.1701898341.TENSOR-FLOWER.1076.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fa069a1c8cf98efb2c9a88654b9ad677465f36d97740ec990c519db5c2c733
3
+ size 8513
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab80c8726ff2b7b4e213402636cf673ebf3f088d79cc9afd4c904d2029d9d64
3
+ size 6264