jibala-1022
commited on
Upload small model
Browse files- config.json +27 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +57 -0
- trainer_state.json +229 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./baseline_embedders/roberta-small",
|
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": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 6,
|
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 sha256:4327836fbecacda83d9a0d28b1e2c4c1e4ce17ca68f759a7a7d74f168306ac95
|
3 |
+
size 485548602
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe499d15bcf54c7fad4133ea3a37d96f4be1c0817e01e7a4d9fbcaeac098c2e
|
3 |
+
size 242766142
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5ef8982a9e4bbd0d4c210d862929057a001c901e8f1aa424b6676af40bdcd51
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba7aac7585db212bd20d6513576c33c2fa2901cfca8bdb4fa61008fd2b3683a
|
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 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.01243716301208047,
|
3 |
+
"best_model_checkpoint": "./checkpoints/easyrec-small",
|
4 |
+
"epoch": 1.733531451213472,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 14000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06191183754333829,
|
13 |
+
"grad_norm": 24.75,
|
14 |
+
"learning_rate": 4.896813604094436e-05,
|
15 |
+
"loss": 3.2576,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12382367508667658,
|
20 |
+
"grad_norm": 21.75,
|
21 |
+
"learning_rate": 4.793627208188873e-05,
|
22 |
+
"loss": 2.7834,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.18573551263001487,
|
27 |
+
"grad_norm": 21.25,
|
28 |
+
"learning_rate": 4.6904408122833086e-05,
|
29 |
+
"loss": 2.6955,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.24764735017335315,
|
34 |
+
"grad_norm": 24.375,
|
35 |
+
"learning_rate": 4.587254416377745e-05,
|
36 |
+
"loss": 2.5928,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.30955918771669144,
|
41 |
+
"grad_norm": 27.875,
|
42 |
+
"learning_rate": 4.484068020472182e-05,
|
43 |
+
"loss": 2.5848,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.37147102526002973,
|
48 |
+
"grad_norm": 21.625,
|
49 |
+
"learning_rate": 4.3808816245666175e-05,
|
50 |
+
"loss": 2.5582,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.433382862803368,
|
55 |
+
"grad_norm": 27.125,
|
56 |
+
"learning_rate": 4.2776952286610534e-05,
|
57 |
+
"loss": 2.5386,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4952947003467063,
|
62 |
+
"grad_norm": 29.625,
|
63 |
+
"learning_rate": 4.17450883275549e-05,
|
64 |
+
"loss": 2.5143,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5572065378900446,
|
69 |
+
"grad_norm": 20.0,
|
70 |
+
"learning_rate": 4.071322436849926e-05,
|
71 |
+
"loss": 2.5071,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6191183754333829,
|
76 |
+
"grad_norm": 26.25,
|
77 |
+
"learning_rate": 3.968136040944362e-05,
|
78 |
+
"loss": 2.4754,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6810302129767212,
|
83 |
+
"grad_norm": 23.0,
|
84 |
+
"learning_rate": 3.864949645038798e-05,
|
85 |
+
"loss": 2.4846,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7429420505200595,
|
90 |
+
"grad_norm": 24.5,
|
91 |
+
"learning_rate": 3.761763249133234e-05,
|
92 |
+
"loss": 2.4806,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.8048538880633977,
|
97 |
+
"grad_norm": 24.125,
|
98 |
+
"learning_rate": 3.658576853227671e-05,
|
99 |
+
"loss": 2.4532,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.866765725606736,
|
104 |
+
"grad_norm": 24.25,
|
105 |
+
"learning_rate": 3.555390457322107e-05,
|
106 |
+
"loss": 2.4561,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9286775631500743,
|
111 |
+
"grad_norm": 30.75,
|
112 |
+
"learning_rate": 3.452204061416543e-05,
|
113 |
+
"loss": 2.4607,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.9905894006934126,
|
118 |
+
"grad_norm": 26.375,
|
119 |
+
"learning_rate": 3.349017665510979e-05,
|
120 |
+
"loss": 2.4332,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.052501238236751,
|
125 |
+
"grad_norm": 29.375,
|
126 |
+
"learning_rate": 3.2458312696054156e-05,
|
127 |
+
"loss": 2.4328,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.1144130757800892,
|
132 |
+
"grad_norm": 25.0,
|
133 |
+
"learning_rate": 3.1426448736998515e-05,
|
134 |
+
"loss": 2.4362,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.1763249133234275,
|
139 |
+
"grad_norm": 24.25,
|
140 |
+
"learning_rate": 3.0394584777942874e-05,
|
141 |
+
"loss": 2.4432,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.2382367508667658,
|
146 |
+
"grad_norm": 34.75,
|
147 |
+
"learning_rate": 2.936272081888724e-05,
|
148 |
+
"loss": 2.427,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.300148588410104,
|
153 |
+
"grad_norm": 24.5,
|
154 |
+
"learning_rate": 2.83308568598316e-05,
|
155 |
+
"loss": 2.4219,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.3620604259534423,
|
160 |
+
"grad_norm": 35.0,
|
161 |
+
"learning_rate": 2.729899290077596e-05,
|
162 |
+
"loss": 2.4213,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.4239722634967806,
|
167 |
+
"grad_norm": 28.75,
|
168 |
+
"learning_rate": 2.6267128941720326e-05,
|
169 |
+
"loss": 2.424,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.485884101040119,
|
174 |
+
"grad_norm": 26.0,
|
175 |
+
"learning_rate": 2.5235264982664684e-05,
|
176 |
+
"loss": 2.4192,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.5477959385834572,
|
181 |
+
"grad_norm": 22.75,
|
182 |
+
"learning_rate": 2.420340102360905e-05,
|
183 |
+
"loss": 2.4032,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.6097077761267955,
|
188 |
+
"grad_norm": 35.0,
|
189 |
+
"learning_rate": 2.3171537064553412e-05,
|
190 |
+
"loss": 2.4317,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.6716196136701336,
|
195 |
+
"grad_norm": 20.875,
|
196 |
+
"learning_rate": 2.213967310549777e-05,
|
197 |
+
"loss": 2.432,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.733531451213472,
|
202 |
+
"grad_norm": 25.625,
|
203 |
+
"learning_rate": 2.1107809146442133e-05,
|
204 |
+
"loss": 2.4309,
|
205 |
+
"step": 14000
|
206 |
+
}
|
207 |
+
],
|
208 |
+
"logging_steps": 500,
|
209 |
+
"max_steps": 24228,
|
210 |
+
"num_input_tokens_seen": 0,
|
211 |
+
"num_train_epochs": 3,
|
212 |
+
"save_steps": 1000,
|
213 |
+
"stateful_callbacks": {
|
214 |
+
"TrainerControl": {
|
215 |
+
"args": {
|
216 |
+
"should_epoch_stop": false,
|
217 |
+
"should_evaluate": false,
|
218 |
+
"should_log": false,
|
219 |
+
"should_save": false,
|
220 |
+
"should_training_stop": false
|
221 |
+
},
|
222 |
+
"attributes": {}
|
223 |
+
}
|
224 |
+
},
|
225 |
+
"total_flos": 0.0,
|
226 |
+
"train_batch_size": 16,
|
227 |
+
"trial_name": null,
|
228 |
+
"trial_params": null
|
229 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c6049104a9643616ea195fc3a09356190da167a8af115fe5300721aa5a3b35
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|