MichaelDoron commited on
Commit
5b3389a
1 Parent(s): c931d56

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
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": 0,
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
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "type_vocab_size": 2,
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "vocab_size": 52000
82
+ },
83
+ "decoder_start_token_id": 0,
84
+ "encoder": {
85
+ "_name_or_path": "",
86
+ "add_cross_attention": false,
87
+ "architectures": null,
88
+ "attention_probs_dropout_prob": 0.1,
89
+ "bad_words_ids": null,
90
+ "begin_suppress_tokens": null,
91
+ "bos_token_id": null,
92
+ "chunk_size_feed_forward": 0,
93
+ "classifier_dropout": null,
94
+ "cross_attention_hidden_size": null,
95
+ "decoder_start_token_id": 0,
96
+ "diversity_penalty": 0.0,
97
+ "do_sample": false,
98
+ "early_stopping": false,
99
+ "encoder_no_repeat_ngram_size": 0,
100
+ "eos_token_id": null,
101
+ "exponential_decay_length_penalty": null,
102
+ "finetuning_task": null,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "hidden_act": "gelu",
106
+ "hidden_dropout_prob": 0.1,
107
+ "hidden_size": 768,
108
+ "id2label": {
109
+ "0": "LABEL_0",
110
+ "1": "LABEL_1"
111
+ },
112
+ "initializer_range": 0.02,
113
+ "intermediate_size": 3072,
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "label2id": {
117
+ "LABEL_0": 0,
118
+ "LABEL_1": 1
119
+ },
120
+ "layer_norm_eps": 1e-12,
121
+ "length_penalty": 1.0,
122
+ "max_length": 20,
123
+ "max_position_embeddings": 512,
124
+ "min_length": 0,
125
+ "model_type": "bert",
126
+ "no_repeat_ngram_size": 0,
127
+ "num_attention_heads": 12,
128
+ "num_beam_groups": 1,
129
+ "num_beams": 1,
130
+ "num_hidden_layers": 12,
131
+ "num_return_sequences": 1,
132
+ "output_attentions": false,
133
+ "output_hidden_states": false,
134
+ "output_scores": false,
135
+ "pad_token_id": 0,
136
+ "position_embedding_type": "absolute",
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "pruned_heads": {},
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "return_dict": true,
143
+ "return_dict_in_generate": false,
144
+ "sep_token_id": null,
145
+ "suppress_tokens": null,
146
+ "task_specific_params": null,
147
+ "temperature": 1.0,
148
+ "tf_legacy_loss": false,
149
+ "tie_encoder_decoder": false,
150
+ "tie_word_embeddings": true,
151
+ "tokenizer_class": null,
152
+ "top_k": 50,
153
+ "top_p": 1.0,
154
+ "torch_dtype": null,
155
+ "torchscript": false,
156
+ "type_vocab_size": 2,
157
+ "typical_p": 1.0,
158
+ "use_bfloat16": false,
159
+ "use_cache": true,
160
+ "vocab_size": 52000
161
+ },
162
+ "is_encoder_decoder": true,
163
+ "model_type": "encoder-decoder",
164
+ "pad_token_id": 1,
165
+ "torch_dtype": "float32",
166
+ "transformers_version": "4.36.2"
167
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3556c47156e448bbe00e4afff2324efd103bb324b01eb3af26fc7a5a90f03674
3
+ size 1121565672
runs/Jan22_10-19-55_gpu01-sensors-testing-0/events.out.tfevents.1705918832.gpu01-sensors-testing-0.228098.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21cef90a112ba702d81ed372e20d69844537963c93a3628ffd437804483083b1
3
+ size 8270
runs/Jan22_10-40-50_gpu01-sensors-testing-0/events.out.tfevents.1705920068.gpu01-sensors-testing-0.228098.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ecc7246b7903fa2f2d39dc7f53cef3a47984e9f53155de8d5029e2e9bdf211
3
+ size 8270
runs/Jan22_10-42-56_gpu01-sensors-testing-0/events.out.tfevents.1705920180.gpu01-sensors-testing-0.228098.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8a5c52c7848e5a1368d5c9259c1b5737ae80181a35961d46c1cd3a4ea8c2f48
3
+ size 8270
runs/Jan22_10-49-38_gpu01-sensors-testing-0/events.out.tfevents.1705920588.gpu01-sensors-testing-0.228098.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e0af3ed02765154a56599c1710d9ef010a66f85a6df37e6db92f537c1832a8
3
+ size 8270
runs/Jan22_10-53-09_gpu01-sensors-testing-0/events.out.tfevents.1705920792.gpu01-sensors-testing-0.228098.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03d65679eff5971347d8d72e567bdbaf83722b23c26eb58fdd2a4d8db385d10
3
+ size 8267
runs/Jan22_10-53-36_gpu01-sensors-testing-0/events.out.tfevents.1705920835.gpu01-sensors-testing-0.228098.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c2a015edaec2bf924bb18ab6bba20541b0cf8834a0af19484e2a23daa8e211
3
+ size 8264
runs/Jan22_10-55-27_gpu01-sensors-testing-0/events.out.tfevents.1705920930.gpu01-sensors-testing-0.228098.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2741fcbaebe296a017993da16435df1922d5b59a2577a08ae9ff7c248b7486cb
3
+ size 8316
runs/Jan22_11-00-18_gpu01-sensors-testing-0/events.out.tfevents.1705921225.gpu01-sensors-testing-0.229126.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f77e641303902b5dc1cf09e03bc8f2d115f2f602d0b0da038f766e9ca3bacc1
3
+ size 8312
runs/Jan22_11-04-09_gpu01-sensors-testing-0/events.out.tfevents.1705921450.gpu01-sensors-testing-0.229422.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af49fa5e935e53c4e7c065705c4794517804ee49453983a949a4a6ca84097ce
3
+ size 9027
runs/Jan22_11-04-56_gpu01-sensors-testing-0/events.out.tfevents.1705921500.gpu01-sensors-testing-0.229422.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e119bbe6c23df04fb3a6e252b1a36604bd2c3d3587f31b7dfd6238cc01d6e6bd
3
+ size 22102
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "pad_token": "[PAD]"
4
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "bos_token": "[BOS]",
4
+ "clean_up_tokenization_spaces": true,
5
+ "max_length": 512,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "stride": 0,
9
+ "tokenizer_class": "PreTrainedTokenizerFast",
10
+ "truncation_side": "right",
11
+ "truncation_strategy": "longest_first"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519ccf9d08aa9fe0f6cdb7f59ea53333b5aab4283fe70fedabf675b6c77c4190
3
+ size 4411