Ayham commited on
Commit
57991d7
1 Parent(s): 03470e8

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "distilbert-base-cased",
97
+ "activation": "gelu",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.1,
101
+ "bad_words_ids": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "dim": 768,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "dropout": 0.1,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_dim": 3072,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "max_position_embeddings": 512,
131
+ "min_length": 0,
132
+ "model_type": "distilbert",
133
+ "n_heads": 12,
134
+ "n_layers": 6,
135
+ "no_repeat_ngram_size": 0,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_past": true,
142
+ "output_scores": false,
143
+ "pad_token_id": 0,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "qa_dropout": 0.1,
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "seq_classif_dropout": 0.2,
154
+ "sinusoidal_pos_embds": false,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tie_encoder_decoder": false,
158
+ "tie_weights_": true,
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
+ "use_bfloat16": false,
167
+ "vocab_size": 28996
168
+ },
169
+ "is_encoder_decoder": true,
170
+ "length_penalty": 2.0,
171
+ "max_length": 64,
172
+ "min_length": 56,
173
+ "model_type": "encoder-decoder",
174
+ "no_repeat_ngram_size": 3,
175
+ "num_beams": 4,
176
+ "pad_token_id": 50256,
177
+ "torch_dtype": "float32",
178
+ "transformers_version": null,
179
+ "vocab_size": 28996
180
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a1d2112d3d006e878361fe29455e9a1969156ea5154830e31257c16d6c5657
3
+ size 897306033
runs/Dec20_16-38-07_b8bd2b653f79/1640018321.631938/events.out.tfevents.1640018321.b8bd2b653f79.774.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad98b209a8a490410fb5e453da40b37ff2fca09818b21d625af56ab7a63d045d
3
+ size 4802
runs/Dec20_16-38-07_b8bd2b653f79/events.out.tfevents.1640018321.b8bd2b653f79.774.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bb9d64f17263117321043fdfad1bb1ac6941db27836383386ed372e3218861
3
+ size 7457
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58507ce38218a728904ad8edef8813e13407cde9a15b4e05e4993b1e855e634f
3
+ size 2991