Hugging Face's logo

jibala-1022
/
easyrec-large

Sentence Similarity
PyTorch
English
roberta
recommendation
collaborative filtering
Model card Files Community
2
jibala-1022 commited on
Commit
9a00e55
·
verified ·
1 Parent(s): 3262bcb

Upload large model

Browse files
Files changed (11) hide show
  1. config.json +27 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +51 -0
  8. tokenizer_config.json +57 -0
  9. trainer_state.json +187 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./baseline_embedders/roberta-large",
3
+ "architectures": [
4
+ "Easyrec"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.46.1",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6493d3aaee6fb76ce28cb5d7e6083a63b741237623ddd797abe689519bb6302d
3
+ size 1632064249
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c567670b209ae295e9ae14ed9b5505e1b5e967c232a2c696241419e3faa324e
3
+ size 816003390
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1fc0bc12610caaa53a84b127f023f36af27d71a8120a8dfdd23397b4693bcd
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6bb826523dc2ae86440b35d3091fd0a763d4b56bc2bca306f34d1faa66bb92
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "padding_side": "right",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
trainer_state.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.02853687417768363,
3
+ "best_model_checkpoint": "./checkpoints/easyrec-large",
4
+ "epoch": 2.588844433984467,
5
+ "eval_steps": 1000,
6
+ "global_step": 11000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11767474699929395,
13
+ "grad_norm": 99.0,
14
+ "learning_rate": 4.803875421667844e-05,
15
+ "loss": 2.8035,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2353494939985879,
20
+ "grad_norm": 120.5,
21
+ "learning_rate": 4.607750843335687e-05,
22
+ "loss": 2.3662,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3530242409978819,
27
+ "grad_norm": 46.0,
28
+ "learning_rate": 4.411626265003531e-05,
29
+ "loss": 2.2534,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.4706989879971758,
34
+ "grad_norm": 41.5,
35
+ "learning_rate": 4.215501686671374e-05,
36
+ "loss": 2.1194,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.5883737349964697,
41
+ "grad_norm": 56.5,
42
+ "learning_rate": 4.019377108339217e-05,
43
+ "loss": 2.0655,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.7060484819957638,
48
+ "grad_norm": 56.25,
49
+ "learning_rate": 3.82325253000706e-05,
50
+ "loss": 2.084,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.8237232289950577,
55
+ "grad_norm": 44.0,
56
+ "learning_rate": 3.627127951674904e-05,
57
+ "loss": 2.0148,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.9413979759943516,
62
+ "grad_norm": 43.0,
63
+ "learning_rate": 3.431003373342748e-05,
64
+ "loss": 2.0612,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 1.0590727229936456,
69
+ "grad_norm": 80.5,
70
+ "learning_rate": 3.234878795010591e-05,
71
+ "loss": 1.9376,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.1767474699929394,
76
+ "grad_norm": 48.25,
77
+ "learning_rate": 3.0387542166784343e-05,
78
+ "loss": 1.9588,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 1.2944222169922335,
83
+ "grad_norm": 67.5,
84
+ "learning_rate": 2.8426296383462774e-05,
85
+ "loss": 1.9291,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 1.4120969639915275,
90
+ "grad_norm": 75.5,
91
+ "learning_rate": 2.6465050600141212e-05,
92
+ "loss": 1.9643,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 1.5297717109908213,
97
+ "grad_norm": 45.75,
98
+ "learning_rate": 2.4503804816819646e-05,
99
+ "loss": 1.9045,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 1.6474464579901154,
104
+ "grad_norm": 44.5,
105
+ "learning_rate": 2.2542559033498077e-05,
106
+ "loss": 1.9263,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 1.7651212049894092,
111
+ "grad_norm": 56.25,
112
+ "learning_rate": 2.0581313250176512e-05,
113
+ "loss": 1.9065,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 1.8827959519887032,
118
+ "grad_norm": 44.75,
119
+ "learning_rate": 1.862006746685495e-05,
120
+ "loss": 1.9187,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 2.0004706989879972,
125
+ "grad_norm": 57.0,
126
+ "learning_rate": 1.665882168353338e-05,
127
+ "loss": 1.9198,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 2.1181454459872913,
132
+ "grad_norm": 49.5,
133
+ "learning_rate": 1.4697575900211815e-05,
134
+ "loss": 1.9371,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 2.2358201929865853,
139
+ "grad_norm": 45.0,
140
+ "learning_rate": 1.273633011689025e-05,
141
+ "loss": 1.8927,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 2.353494939985879,
146
+ "grad_norm": 45.0,
147
+ "learning_rate": 1.0775084333568684e-05,
148
+ "loss": 1.8996,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 2.471169686985173,
153
+ "grad_norm": 34.75,
154
+ "learning_rate": 8.813838550247118e-06,
155
+ "loss": 1.8713,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 2.588844433984467,
160
+ "grad_norm": 37.75,
161
+ "learning_rate": 6.852592766925552e-06,
162
+ "loss": 1.9081,
163
+ "step": 11000
164
+ }
165
+ ],
166
+ "logging_steps": 500,
167
+ "max_steps": 12747,
168
+ "num_input_tokens_seen": 0,
169
+ "num_train_epochs": 3,
170
+ "save_steps": 1000,
171
+ "stateful_callbacks": {
172
+ "TrainerControl": {
173
+ "args": {
174
+ "should_epoch_stop": false,
175
+ "should_evaluate": false,
176
+ "should_log": false,
177
+ "should_save": false,
178
+ "should_training_stop": false
179
+ },
180
+ "attributes": {}
181
+ }
182
+ },
183
+ "total_flos": 0.0,
184
+ "train_batch_size": 4,
185
+ "trial_name": null,
186
+ "trial_params": null
187
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b121b30990e20974e69bc13829699d3b4d7d8faa655692895a022967e5859a
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff