Training in progress, epoch 1, checkpoint
Browse files- checkpoint-375/config.json +49 -0
- checkpoint-375/model.safetensors +3 -0
- checkpoint-375/optimizer.pt +3 -0
- checkpoint-375/rng_state.pth +3 -0
- checkpoint-375/scheduler.pt +3 -0
- checkpoint-375/special_tokens_map.json +51 -0
- checkpoint-375/tokenizer_config.json +75 -0
- checkpoint-375/trainer_state.json +250 -0
- checkpoint-375/training_args.bin +3 -0
- checkpoint-375/vocab.txt +0 -0
checkpoint-375/config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "funnel-transformer/small-base",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"architectures": [
|
5 |
+
"FunnelForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"attention_type": "relative_shift",
|
9 |
+
"block_repeats": [
|
10 |
+
1,
|
11 |
+
1,
|
12 |
+
1
|
13 |
+
],
|
14 |
+
"block_sizes": [
|
15 |
+
4,
|
16 |
+
4,
|
17 |
+
4
|
18 |
+
],
|
19 |
+
"d_head": 64,
|
20 |
+
"d_inner": 3072,
|
21 |
+
"d_model": 768,
|
22 |
+
"hidden_act": "gelu_new",
|
23 |
+
"hidden_dropout": 0.1,
|
24 |
+
"id2label": {
|
25 |
+
"0": "HUMAN",
|
26 |
+
"1": "AI"
|
27 |
+
},
|
28 |
+
"initializer_range": 0.1,
|
29 |
+
"initializer_std": null,
|
30 |
+
"label2id": {
|
31 |
+
"AI": 1,
|
32 |
+
"HUMAN": 0
|
33 |
+
},
|
34 |
+
"layer_norm_eps": 1e-09,
|
35 |
+
"max_position_embeddings": 512,
|
36 |
+
"model_type": "funnel",
|
37 |
+
"n_head": 12,
|
38 |
+
"num_decoder_layers": 2,
|
39 |
+
"pool_q_only": true,
|
40 |
+
"pooling_type": "mean",
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"rel_attn_type": "factorized",
|
43 |
+
"separate_cls": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.35.2",
|
46 |
+
"truncate_seq": true,
|
47 |
+
"type_vocab_size": 3,
|
48 |
+
"vocab_size": 30522
|
49 |
+
}
|
checkpoint-375/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4db909fd51e361b60643fc6f21778d5b3e2e9472548f1f86588c72ba5a98e4d4
|
3 |
+
size 464844376
|
checkpoint-375/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b4f4b22722dd06e63983529ff27cac86422c299b2469ed12d212c08d5d7a78
|
3 |
+
size 929837114
|
checkpoint-375/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:130ce7b5fe76f0e2d69eba7245d93a56442c485c965a62c7f546d89bc304e719
|
3 |
+
size 14244
|
checkpoint-375/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d39b9eb37cc9b77a1cd829d5986b7652e47f00c889e3135213a3bbf1688de88f
|
3 |
+
size 1064
|
checkpoint-375/special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<cls>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "<sep>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
checkpoint-375/tokenizer_config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"96": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"97": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"100": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"101": {
|
36 |
+
"content": "<cls>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"102": {
|
44 |
+
"content": "<sep>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"103": {
|
52 |
+
"content": "<mask>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
},
|
60 |
+
"bos_token": "<s>",
|
61 |
+
"clean_up_tokenization_spaces": true,
|
62 |
+
"cls_token": "<cls>",
|
63 |
+
"do_basic_tokenize": true,
|
64 |
+
"do_lower_case": true,
|
65 |
+
"eos_token": "</s>",
|
66 |
+
"mask_token": "<mask>",
|
67 |
+
"model_max_length": 512,
|
68 |
+
"never_split": null,
|
69 |
+
"pad_token": "<pad>",
|
70 |
+
"sep_token": "<sep>",
|
71 |
+
"strip_accents": null,
|
72 |
+
"tokenize_chinese_chars": true,
|
73 |
+
"tokenizer_class": "FunnelTokenizer",
|
74 |
+
"unk_token": "<unk>"
|
75 |
+
}
|
checkpoint-375/trainer_state.json
ADDED
@@ -0,0 +1,250 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 375,
|
6 |
+
"global_step": 375,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 9.866666666666668e-06,
|
14 |
+
"loss": 0.6931,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.05,
|
19 |
+
"learning_rate": 9.733333333333334e-06,
|
20 |
+
"loss": 0.6765,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.08,
|
25 |
+
"learning_rate": 9.600000000000001e-06,
|
26 |
+
"loss": 0.4544,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.11,
|
31 |
+
"learning_rate": 9.48e-06,
|
32 |
+
"loss": 0.2259,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.13,
|
37 |
+
"learning_rate": 9.346666666666666e-06,
|
38 |
+
"loss": 0.1407,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.16,
|
43 |
+
"learning_rate": 9.213333333333334e-06,
|
44 |
+
"loss": 0.1243,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.19,
|
49 |
+
"learning_rate": 9.080000000000001e-06,
|
50 |
+
"loss": 0.0641,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.21,
|
55 |
+
"learning_rate": 8.946666666666669e-06,
|
56 |
+
"loss": 0.0083,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.24,
|
61 |
+
"learning_rate": 8.813333333333334e-06,
|
62 |
+
"loss": 0.0066,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.27,
|
67 |
+
"learning_rate": 8.693333333333334e-06,
|
68 |
+
"loss": 0.0596,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.29,
|
73 |
+
"learning_rate": 8.560000000000001e-06,
|
74 |
+
"loss": 0.0792,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.32,
|
79 |
+
"learning_rate": 8.44e-06,
|
80 |
+
"loss": 0.1432,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.35,
|
85 |
+
"learning_rate": 8.306666666666668e-06,
|
86 |
+
"loss": 0.117,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.37,
|
91 |
+
"learning_rate": 8.173333333333334e-06,
|
92 |
+
"loss": 0.2646,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4,
|
97 |
+
"learning_rate": 8.040000000000001e-06,
|
98 |
+
"loss": 0.0097,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.43,
|
103 |
+
"learning_rate": 7.906666666666667e-06,
|
104 |
+
"loss": 0.0333,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.45,
|
109 |
+
"learning_rate": 7.773333333333334e-06,
|
110 |
+
"loss": 0.0016,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.48,
|
115 |
+
"learning_rate": 7.640000000000001e-06,
|
116 |
+
"loss": 0.0038,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.51,
|
121 |
+
"learning_rate": 7.506666666666668e-06,
|
122 |
+
"loss": 0.074,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.53,
|
127 |
+
"learning_rate": 7.373333333333334e-06,
|
128 |
+
"loss": 0.1338,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.56,
|
133 |
+
"learning_rate": 7.24e-06,
|
134 |
+
"loss": 0.0035,
|
135 |
+
"step": 210
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.59,
|
139 |
+
"learning_rate": 7.1066666666666675e-06,
|
140 |
+
"loss": 0.1519,
|
141 |
+
"step": 220
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.61,
|
145 |
+
"learning_rate": 6.973333333333334e-06,
|
146 |
+
"loss": 0.0095,
|
147 |
+
"step": 230
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.64,
|
151 |
+
"learning_rate": 6.8400000000000014e-06,
|
152 |
+
"loss": 0.1465,
|
153 |
+
"step": 240
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.67,
|
157 |
+
"learning_rate": 6.706666666666667e-06,
|
158 |
+
"loss": 0.0022,
|
159 |
+
"step": 250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.69,
|
163 |
+
"learning_rate": 6.573333333333334e-06,
|
164 |
+
"loss": 0.0551,
|
165 |
+
"step": 260
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.72,
|
169 |
+
"learning_rate": 6.440000000000001e-06,
|
170 |
+
"loss": 0.0028,
|
171 |
+
"step": 270
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.75,
|
175 |
+
"learning_rate": 6.3066666666666676e-06,
|
176 |
+
"loss": 0.0566,
|
177 |
+
"step": 280
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.77,
|
181 |
+
"learning_rate": 6.173333333333333e-06,
|
182 |
+
"loss": 0.0009,
|
183 |
+
"step": 290
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.8,
|
187 |
+
"learning_rate": 6.040000000000001e-06,
|
188 |
+
"loss": 0.0902,
|
189 |
+
"step": 300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.83,
|
193 |
+
"learning_rate": 5.906666666666667e-06,
|
194 |
+
"loss": 0.0008,
|
195 |
+
"step": 310
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.85,
|
199 |
+
"learning_rate": 5.7733333333333345e-06,
|
200 |
+
"loss": 0.0011,
|
201 |
+
"step": 320
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.88,
|
205 |
+
"learning_rate": 5.64e-06,
|
206 |
+
"loss": 0.0196,
|
207 |
+
"step": 330
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.91,
|
211 |
+
"learning_rate": 5.506666666666667e-06,
|
212 |
+
"loss": 0.0826,
|
213 |
+
"step": 340
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.93,
|
217 |
+
"learning_rate": 5.373333333333334e-06,
|
218 |
+
"loss": 0.0408,
|
219 |
+
"step": 350
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.96,
|
223 |
+
"learning_rate": 5.240000000000001e-06,
|
224 |
+
"loss": 0.0466,
|
225 |
+
"step": 360
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.99,
|
229 |
+
"learning_rate": 5.106666666666667e-06,
|
230 |
+
"loss": 0.0013,
|
231 |
+
"step": 370
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 1.0,
|
235 |
+
"eval_accuracy": 0.992,
|
236 |
+
"eval_loss": 0.05685167387127876,
|
237 |
+
"eval_runtime": 14.5309,
|
238 |
+
"eval_samples_per_second": 68.819,
|
239 |
+
"eval_steps_per_second": 8.602,
|
240 |
+
"step": 375
|
241 |
+
}
|
242 |
+
],
|
243 |
+
"logging_steps": 10,
|
244 |
+
"max_steps": 750,
|
245 |
+
"num_train_epochs": 2,
|
246 |
+
"save_steps": 500,
|
247 |
+
"total_flos": 846042010023360.0,
|
248 |
+
"trial_name": null,
|
249 |
+
"trial_params": null
|
250 |
+
}
|
checkpoint-375/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c447d199ad29bb02a1c18507c2ef1baf344faf85ac1c60fba1abfb7baee9a5f1
|
3 |
+
size 4600
|
checkpoint-375/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|