Hugging Face's logo

BugraHamza
/
bert_gpt2_dialog_generation

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
BugraHamza commited on
Commit
5773958
•
1 Parent(s): 74ca8f7

Training in progress, step 500

Browse files
Files changed (10) hide show
  1. checkpoint-500/config.json +178 -0
  2. checkpoint-500/optimizer.pt +3 -0
  3. checkpoint-500/pytorch_model.bin +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/trainer_state.json +30 -0
  7. checkpoint-500/training_args.bin +3 -0
  8. config.json +178 -0
  9. pytorch_model.bin +3 -0
  10. training_args.bin +3 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_epsilon": 1e-05,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "model_type": "gpt2",
44
+ "n_ctx": 1024,
45
+ "n_embd": 768,
46
+ "n_head": 12,
47
+ "n_inner": null,
48
+ "n_layer": 12,
49
+ "n_positions": 1024,
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "reorder_and_upcast_attn": false,
63
+ "repetition_penalty": 1.0,
64
+ "resid_pdrop": 0.1,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "scale_attn_by_inverse_layer_idx": false,
68
+ "scale_attn_weights": true,
69
+ "sep_token_id": null,
70
+ "summary_activation": null,
71
+ "summary_first_dropout": 0.1,
72
+ "summary_proj_to_labels": true,
73
+ "summary_type": "cls_index",
74
+ "summary_use_proj": true,
75
+ "task_specific_params": {
76
+ "text-generation": {
77
+ "do_sample": true,
78
+ "max_length": 50
79
+ }
80
+ },
81
+ "temperature": 1.0,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "transformers_version": "4.20.1",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 50260
94
+ },
95
+ "encoder": {
96
+ "_name_or_path": "bert-base-cased",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "BertForMaskedLM"
100
+ ],
101
+ "attention_probs_dropout_prob": 0.1,
102
+ "bad_words_ids": null,
103
+ "bos_token_id": null,
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": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "gradient_checkpointing": false,
118
+ "hidden_act": "gelu",
119
+ "hidden_dropout_prob": 0.1,
120
+ "hidden_size": 768,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 3072,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-12,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "max_position_embeddings": 512,
137
+ "min_length": 0,
138
+ "model_type": "bert",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_attention_heads": 12,
141
+ "num_beam_groups": 1,
142
+ "num_beams": 1,
143
+ "num_hidden_layers": 12,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": 0,
149
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.20.1",
168
+ "type_vocab_size": 2,
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false,
171
+ "use_cache": true,
172
+ "vocab_size": 28996
173
+ },
174
+ "is_encoder_decoder": true,
175
+ "model_type": "encoder-decoder",
176
+ "torch_dtype": "float32",
177
+ "transformers_version": null
178
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d33f1e0c38d25bcf19c09f18865204466a71903a4b425034b03ecc3a8900137
3
+ size 2089211733
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342eab432357573a720aa1ff2d1627c0cd33b1803435f14544b3ee73fb51ce60
3
+ size 1069811305
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f322bc247acdd6beaf2fd13087f80fb9d734db1f808f972ed48d9e79cc3387a1
3
+ size 15523
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f84bbb22b30fa6f75a6023621a67cdf088b068e3a11e95b76d387e8134612d
3
+ size 623
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.15114873035066506,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 0.0009848851269649336,
13
+ "loss": 0.3001,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.15,
18
+ "eval_loss": 0.0005047954618930817,
19
+ "eval_runtime": 82.2643,
20
+ "eval_samples_per_second": 50.933,
21
+ "eval_steps_per_second": 3.185,
22
+ "step": 500
23
+ }
24
+ ],
25
+ "max_steps": 33080,
26
+ "num_train_epochs": 10,
27
+ "total_flos": 2446165278720000.0,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc415c9733b334475118561ffd0fbd7ee756c72cac8dcae37bc30f81ad3eef8
3
+ size 3439
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_epsilon": 1e-05,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "model_type": "gpt2",
44
+ "n_ctx": 1024,
45
+ "n_embd": 768,
46
+ "n_head": 12,
47
+ "n_inner": null,
48
+ "n_layer": 12,
49
+ "n_positions": 1024,
50
+ "no_repeat_ngram_size": 0,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_return_sequences": 1,
54
+ "output_attentions": false,
55
+ "output_hidden_states": false,
56
+ "output_scores": false,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "reorder_and_upcast_attn": false,
63
+ "repetition_penalty": 1.0,
64
+ "resid_pdrop": 0.1,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "scale_attn_by_inverse_layer_idx": false,
68
+ "scale_attn_weights": true,
69
+ "sep_token_id": null,
70
+ "summary_activation": null,
71
+ "summary_first_dropout": 0.1,
72
+ "summary_proj_to_labels": true,
73
+ "summary_type": "cls_index",
74
+ "summary_use_proj": true,
75
+ "task_specific_params": {
76
+ "text-generation": {
77
+ "do_sample": true,
78
+ "max_length": 50
79
+ }
80
+ },
81
+ "temperature": 1.0,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "transformers_version": "4.20.1",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 50260
94
+ },
95
+ "encoder": {
96
+ "_name_or_path": "bert-base-cased",
97
+ "add_cross_attention": false,
98
+ "architectures": [
99
+ "BertForMaskedLM"
100
+ ],
101
+ "attention_probs_dropout_prob": 0.1,
102
+ "bad_words_ids": null,
103
+ "bos_token_id": null,
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": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "gradient_checkpointing": false,
118
+ "hidden_act": "gelu",
119
+ "hidden_dropout_prob": 0.1,
120
+ "hidden_size": 768,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 3072,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-12,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "max_position_embeddings": 512,
137
+ "min_length": 0,
138
+ "model_type": "bert",
139
+ "no_repeat_ngram_size": 0,
140
+ "num_attention_heads": 12,
141
+ "num_beam_groups": 1,
142
+ "num_beams": 1,
143
+ "num_hidden_layers": 12,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": 0,
149
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tie_encoder_decoder": false,
161
+ "tie_word_embeddings": true,
162
+ "tokenizer_class": null,
163
+ "top_k": 50,
164
+ "top_p": 1.0,
165
+ "torch_dtype": null,
166
+ "torchscript": false,
167
+ "transformers_version": "4.20.1",
168
+ "type_vocab_size": 2,
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false,
171
+ "use_cache": true,
172
+ "vocab_size": 28996
173
+ },
174
+ "is_encoder_decoder": true,
175
+ "model_type": "encoder-decoder",
176
+ "torch_dtype": "float32",
177
+ "transformers_version": null
178
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342eab432357573a720aa1ff2d1627c0cd33b1803435f14544b3ee73fb51ce60
3
+ size 1069811305
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc415c9733b334475118561ffd0fbd7ee756c72cac8dcae37bc30f81ad3eef8
3
+ size 3439