Cameron Clarke
commited on
Commit
•
36f33b0
1
Parent(s):
9af1571
add model files
Browse files- config.json +24 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +146 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"transformers_version": "4.5.0",
|
21 |
+
"type_vocab_size": 2,
|
22 |
+
"use_cache": true,
|
23 |
+
"vocab_size": 28996
|
24 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b147b8c151bac4053c544dfe9276315b15be6ec44c070b5c0cdc96892ccbe63
|
3 |
+
size 866620625
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d4219adcc6844afd400ccf32dabd00a954a2593cedf78ca98c3d11de97d3d1f
|
3 |
+
size 433336585
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a1ef680b075840373a88ed789cf8762c0adb180f3bc44bfd94c2bf45d7d77a9
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased"}
|
trainer_state.json
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6329699372315825,
|
3 |
+
"best_model_checkpoint": "/scratch/ccc779/rtgender_opgender_annotations_model/checkpoint-9210",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 9210,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.11,
|
12 |
+
"learning_rate": 1.1520220054230351e-05,
|
13 |
+
"loss": 0.6943,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.22,
|
18 |
+
"learning_rate": 1.085889858154204e-05,
|
19 |
+
"loss": 0.6774,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.33,
|
24 |
+
"learning_rate": 1.0197577108853733e-05,
|
25 |
+
"loss": 0.6879,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.43,
|
30 |
+
"learning_rate": 9.536255636165422e-06,
|
31 |
+
"loss": 0.6953,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.54,
|
36 |
+
"learning_rate": 8.874934163477113e-06,
|
37 |
+
"loss": 0.7215,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.65,
|
42 |
+
"learning_rate": 8.213612690788802e-06,
|
43 |
+
"loss": 0.6924,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.76,
|
48 |
+
"learning_rate": 7.552291218100494e-06,
|
49 |
+
"loss": 0.6984,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.87,
|
54 |
+
"learning_rate": 6.8909697454121845e-06,
|
55 |
+
"loss": 0.702,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.98,
|
60 |
+
"learning_rate": 6.2296482727238754e-06,
|
61 |
+
"loss": 0.6821,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.0,
|
66 |
+
"eval_accuracy": 0.6304135460761967,
|
67 |
+
"eval_f1": 0.628963713631906,
|
68 |
+
"eval_loss": 0.7998125553131104,
|
69 |
+
"eval_precision": 0.6421895861148198,
|
70 |
+
"eval_recall": 0.6162716207559257,
|
71 |
+
"eval_runtime": 12.7284,
|
72 |
+
"eval_samples_per_second": 241.272,
|
73 |
+
"step": 4605
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.09,
|
77 |
+
"learning_rate": 5.5683268000355656e-06,
|
78 |
+
"loss": 0.8274,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.19,
|
83 |
+
"learning_rate": 4.9070053273472565e-06,
|
84 |
+
"loss": 0.7584,
|
85 |
+
"step": 5500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.3,
|
89 |
+
"learning_rate": 4.245683854658947e-06,
|
90 |
+
"loss": 0.7485,
|
91 |
+
"step": 6000
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.41,
|
95 |
+
"learning_rate": 3.5843623819706372e-06,
|
96 |
+
"loss": 0.8287,
|
97 |
+
"step": 6500
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.52,
|
101 |
+
"learning_rate": 2.923040909282328e-06,
|
102 |
+
"loss": 0.7596,
|
103 |
+
"step": 7000
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 1.63,
|
107 |
+
"learning_rate": 2.2617194365940184e-06,
|
108 |
+
"loss": 0.7292,
|
109 |
+
"step": 7500
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.74,
|
113 |
+
"learning_rate": 1.600397963905709e-06,
|
114 |
+
"loss": 0.7779,
|
115 |
+
"step": 8000
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.85,
|
119 |
+
"learning_rate": 9.390764912173995e-07,
|
120 |
+
"loss": 0.7819,
|
121 |
+
"step": 8500
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.95,
|
125 |
+
"learning_rate": 2.7775501852908997e-07,
|
126 |
+
"loss": 0.7811,
|
127 |
+
"step": 9000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 2.0,
|
131 |
+
"eval_accuracy": 0.638228590035819,
|
132 |
+
"eval_f1": 0.6329699372315825,
|
133 |
+
"eval_loss": 1.1031067371368408,
|
134 |
+
"eval_precision": 0.6534788540245566,
|
135 |
+
"eval_recall": 0.6137091607943626,
|
136 |
+
"eval_runtime": 12.7111,
|
137 |
+
"eval_samples_per_second": 241.6,
|
138 |
+
"step": 9210
|
139 |
+
}
|
140 |
+
],
|
141 |
+
"max_steps": 9210,
|
142 |
+
"num_train_epochs": 2,
|
143 |
+
"total_flos": 434334690572400.0,
|
144 |
+
"trial_name": null,
|
145 |
+
"trial_params": null
|
146 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ffee4d478344979e2f30768ce00733d2003627cf5238efc28fb43e3455df09
|
3 |
+
size 2351
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|