Ayham commited on
Commit
21f342d
1 Parent(s): eada704

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "gpt2",
7
+ "activation_function": "gelu_new",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "GPT2LMHeadModel"
11
+ ],
12
+ "attn_pdrop": 0.1,
13
+ "bad_words_ids": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "embd_pdrop": 0.1,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 50256,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layer_norm_epsilon": 1e-05,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_type": "gpt2",
43
+ "n_ctx": 1024,
44
+ "n_embd": 768,
45
+ "n_head": 12,
46
+ "n_inner": null,
47
+ "n_layer": 12,
48
+ "n_positions": 1024,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": null,
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "reorder_and_upcast_attn": false,
62
+ "repetition_penalty": 1.0,
63
+ "resid_pdrop": 0.1,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "scale_attn_by_inverse_layer_idx": false,
67
+ "scale_attn_weights": true,
68
+ "sep_token_id": null,
69
+ "summary_activation": null,
70
+ "summary_first_dropout": 0.1,
71
+ "summary_proj_to_labels": true,
72
+ "summary_type": "cls_index",
73
+ "summary_use_proj": true,
74
+ "task_specific_params": {
75
+ "text-generation": {
76
+ "do_sample": true,
77
+ "max_length": 50
78
+ }
79
+ },
80
+ "temperature": 1.0,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "transformers_version": "4.12.0.dev0",
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "vocab_size": 50257
92
+ },
93
+ "decoder_start_token_id": 50256,
94
+ "early_stopping": true,
95
+ "encoder": {
96
+ "_name_or_path": "roberta-base",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "RobertaForMaskedLM"
100
+ ],
101
+ "attention_probs_dropout_prob": 0.1,
102
+ "bad_words_ids": null,
103
+ "bos_token_id": 0,
104
+ "chunk_size_feed_forward": 0,
105
+ "classifier_dropout": null,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": 2,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "gelu",
117
+ "hidden_dropout_prob": 0.1,
118
+ "hidden_size": 768,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 3072,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "max_position_embeddings": 514,
135
+ "min_length": 0,
136
+ "model_type": "roberta",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 12,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_hidden_layers": 12,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": 1,
147
+ "position_embedding_type": "absolute",
148
+ "prefix": null,
149
+ "problem_type": null,
150
+ "pruned_heads": {},
151
+ "remove_invalid_values": false,
152
+ "repetition_penalty": 1.0,
153
+ "return_dict": true,
154
+ "return_dict_in_generate": false,
155
+ "sep_token_id": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "transformers_version": "4.12.0.dev0",
166
+ "type_vocab_size": 1,
167
+ "use_bfloat16": false,
168
+ "use_cache": true,
169
+ "vocab_size": 50265
170
+ },
171
+ "is_encoder_decoder": true,
172
+ "length_penalty": 2.0,
173
+ "max_length": 142,
174
+ "min_length": 56,
175
+ "model_type": "encoder-decoder",
176
+ "no_repeat_ngram_size": 3,
177
+ "num_beams": 4,
178
+ "pad_token_id": 50256,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": null,
181
+ "vocab_size": 50265
182
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a38030cde84fe394379da2a6c7cd2da9c214ae3b32f55db2dab341c2c0c7f8c
3
+ size 1135171497
runs/Dec14_03-13-59_c0c5d64954fd/1639451660.6888287/events.out.tfevents.1639451660.c0c5d64954fd.301.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1273f76ec2e9f4775fb6f5bda283891ea5396e3a99a8201cf3bfef90345e2b6
3
+ size 4757
runs/Dec14_03-13-59_c0c5d64954fd/events.out.tfevents.1639451660.c0c5d64954fd.301.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b77cd3377f64e63762332eb523716bea9dbf47a55c161cc7c6846dcca478884a
3
+ size 7342
runs/Dec14_03-45-59_c0c5d64954fd/1639453571.7108502/events.out.tfevents.1639453571.c0c5d64954fd.3442.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c07f246ea21b46f2adb759aa8cdb329b5dacda87049c8eb91e44cb8faa62a0
3
+ size 4757
runs/Dec14_03-45-59_c0c5d64954fd/events.out.tfevents.1639453571.c0c5d64954fd.3442.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3755f5ba84f89f50e862fd7a7cbbf8719c9f11aa1f073f8691ef9fc190b07cc
3
+ size 7497
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbabd7584c6e6b9bc3d26327bef4d499900943fdc216c38382c335f00359b7af
3
+ size 2991