Ayham commited on
Commit
6201114
1 Parent(s): 074a1e4

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "xlnet-base-cased",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "XLNetLMHeadModel"
100
+ ],
101
+ "attn_type": "bi",
102
+ "bad_words_ids": null,
103
+ "bi_data": false,
104
+ "bos_token_id": 1,
105
+ "chunk_size_feed_forward": 0,
106
+ "clamp_len": -1,
107
+ "cross_attention_hidden_size": null,
108
+ "d_head": 64,
109
+ "d_inner": 3072,
110
+ "d_model": 768,
111
+ "decoder_start_token_id": null,
112
+ "diversity_penalty": 0.0,
113
+ "do_sample": false,
114
+ "dropout": 0.1,
115
+ "early_stopping": false,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "end_n_top": 5,
118
+ "eos_token_id": 2,
119
+ "ff_activation": "gelu",
120
+ "finetuning_task": null,
121
+ "forced_bos_token_id": null,
122
+ "forced_eos_token_id": null,
123
+ "id2label": {
124
+ "0": "LABEL_0",
125
+ "1": "LABEL_1"
126
+ },
127
+ "initializer_range": 0.02,
128
+ "is_decoder": false,
129
+ "is_encoder_decoder": false,
130
+ "label2id": {
131
+ "LABEL_0": 0,
132
+ "LABEL_1": 1
133
+ },
134
+ "layer_norm_eps": 1e-12,
135
+ "length_penalty": 1.0,
136
+ "max_length": 20,
137
+ "mem_len": null,
138
+ "min_length": 0,
139
+ "model_type": "xlnet",
140
+ "n_head": 12,
141
+ "n_layer": 12,
142
+ "no_repeat_ngram_size": 0,
143
+ "num_beam_groups": 1,
144
+ "num_beams": 1,
145
+ "num_return_sequences": 1,
146
+ "output_attentions": false,
147
+ "output_hidden_states": false,
148
+ "output_scores": false,
149
+ "pad_token_id": 5,
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "reuse_len": null,
158
+ "same_length": false,
159
+ "sep_token_id": null,
160
+ "start_n_top": 5,
161
+ "summary_activation": "tanh",
162
+ "summary_last_dropout": 0.1,
163
+ "summary_type": "last",
164
+ "summary_use_proj": true,
165
+ "task_specific_params": {
166
+ "text-generation": {
167
+ "do_sample": true,
168
+ "max_length": 250
169
+ }
170
+ },
171
+ "temperature": 1.0,
172
+ "tie_encoder_decoder": false,
173
+ "tie_word_embeddings": true,
174
+ "tokenizer_class": null,
175
+ "top_k": 50,
176
+ "top_p": 1.0,
177
+ "torch_dtype": null,
178
+ "torchscript": false,
179
+ "transformers_version": "4.12.0.dev0",
180
+ "untie_r": true,
181
+ "use_bfloat16": false,
182
+ "use_mems_eval": true,
183
+ "use_mems_train": false,
184
+ "vocab_size": 32000
185
+ },
186
+ "is_encoder_decoder": true,
187
+ "length_penalty": 2.0,
188
+ "max_length": 142,
189
+ "min_length": 56,
190
+ "model_type": "encoder-decoder",
191
+ "no_repeat_ngram_size": 3,
192
+ "num_beams": 4,
193
+ "pad_token_id": 50256,
194
+ "torch_dtype": "float32",
195
+ "transformers_version": null,
196
+ "vocab_size": 32000
197
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39d0a2fffdc0e844111b4e4d4704858bbf53ba8b338984ee4ae98fd7fd7d41c
3
+ size 1103449693
runs/Dec15_04-04-22_751fa8a05588/1639541100.8343656/events.out.tfevents.1639541100.751fa8a05588.5251.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9db868e5f406726d81af66bfe5e755df5c7c99da851e4d715f652f36331e98
3
+ size 4814
runs/Dec15_04-04-22_751fa8a05588/events.out.tfevents.1639541100.751fa8a05588.5251.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17518c202d3d8af6c2cb2a54cda5196bdc1a535e1707d6fd483cdf310935b010
3
+ size 7796
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:637696add8bf479300f0a69ed1927c1c80b67259b48e5325e57a3a5072adea39
3
+ size 2991