RealFalconsAI
commited on
Commit
·
9d8ddb0
1
Parent(s):
f0a35f8
Upload 11 files
Browse files- config.json +1 -1
- optimizer.pt +3 -0
- pytorch_model.bin +1 -1
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- trainer_state.json +151 -0
- training_args.bin +3 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Falconsai/offensive_speech_detection",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4df7121aec1c35c069337a74d42c53b4a5b4923ca88aca3f5b33a51e937ced73
|
3 |
+
size 535701061
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267855533
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbc0d5fa6c859f571867e1c85354a56e06713c815ab1694e8dfcf40c64f92978
|
3 |
size 267855533
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6160847c51c08356e853c3bca23f598a8d8a42785e2458b0c5fc923e4f1dadf
|
3 |
+
size 14511
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e06238497f705c88cffe1b96791159faf151e3e1acd4bc0004a4c3260ed549
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.01884845644235611,
|
3 |
+
"best_model_checkpoint": "./results/checkpoint-4500",
|
4 |
+
"epoch": 0.9439899307740718,
|
5 |
+
"global_step": 4500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 1.9300748199426614e-05,
|
13 |
+
"loss": 0.0391,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1,
|
18 |
+
"eval_accuracy": 0.990558615263572,
|
19 |
+
"eval_loss": 0.04349859058856964,
|
20 |
+
"eval_runtime": 154.2476,
|
21 |
+
"eval_samples_per_second": 123.6,
|
22 |
+
"eval_steps_per_second": 7.728,
|
23 |
+
"step": 500
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.21,
|
27 |
+
"learning_rate": 1.860149639885323e-05,
|
28 |
+
"loss": 0.0327,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.21,
|
33 |
+
"eval_accuracy": 0.9903488067138736,
|
34 |
+
"eval_loss": 0.04805811867117882,
|
35 |
+
"eval_runtime": 154.05,
|
36 |
+
"eval_samples_per_second": 123.759,
|
37 |
+
"eval_steps_per_second": 7.738,
|
38 |
+
"step": 1000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.31,
|
42 |
+
"learning_rate": 1.790224459827984e-05,
|
43 |
+
"loss": 0.0266,
|
44 |
+
"step": 1500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.31,
|
48 |
+
"eval_accuracy": 0.9911355887752425,
|
49 |
+
"eval_loss": 0.0459710918366909,
|
50 |
+
"eval_runtime": 154.4944,
|
51 |
+
"eval_samples_per_second": 123.403,
|
52 |
+
"eval_steps_per_second": 7.715,
|
53 |
+
"step": 1500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.42,
|
57 |
+
"learning_rate": 1.7202992797706454e-05,
|
58 |
+
"loss": 0.035,
|
59 |
+
"step": 2000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.42,
|
63 |
+
"eval_accuracy": 0.9916601101494886,
|
64 |
+
"eval_loss": 0.03351669758558273,
|
65 |
+
"eval_runtime": 154.0214,
|
66 |
+
"eval_samples_per_second": 123.782,
|
67 |
+
"eval_steps_per_second": 7.739,
|
68 |
+
"step": 2000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.52,
|
72 |
+
"learning_rate": 1.650374099713307e-05,
|
73 |
+
"loss": 0.0371,
|
74 |
+
"step": 2500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.52,
|
78 |
+
"eval_accuracy": 0.9930763178599528,
|
79 |
+
"eval_loss": 0.025116313248872757,
|
80 |
+
"eval_runtime": 153.2057,
|
81 |
+
"eval_samples_per_second": 124.441,
|
82 |
+
"eval_steps_per_second": 7.78,
|
83 |
+
"step": 2500
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.63,
|
87 |
+
"learning_rate": 1.580448919655968e-05,
|
88 |
+
"loss": 0.026,
|
89 |
+
"step": 3000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.63,
|
93 |
+
"eval_accuracy": 0.9938630999213218,
|
94 |
+
"eval_loss": 0.027913494035601616,
|
95 |
+
"eval_runtime": 153.7631,
|
96 |
+
"eval_samples_per_second": 123.989,
|
97 |
+
"eval_steps_per_second": 7.752,
|
98 |
+
"step": 3000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.73,
|
102 |
+
"learning_rate": 1.5105237395986297e-05,
|
103 |
+
"loss": 0.0299,
|
104 |
+
"step": 3500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.73,
|
108 |
+
"eval_accuracy": 0.9934959349593496,
|
109 |
+
"eval_loss": 0.027549268677830696,
|
110 |
+
"eval_runtime": 153.8917,
|
111 |
+
"eval_samples_per_second": 123.886,
|
112 |
+
"eval_steps_per_second": 7.746,
|
113 |
+
"step": 3500
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.84,
|
117 |
+
"learning_rate": 1.4405985595412911e-05,
|
118 |
+
"loss": 0.0254,
|
119 |
+
"step": 4000
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.84,
|
123 |
+
"eval_accuracy": 0.9945449777078416,
|
124 |
+
"eval_loss": 0.024684084579348564,
|
125 |
+
"eval_runtime": 153.4415,
|
126 |
+
"eval_samples_per_second": 124.249,
|
127 |
+
"eval_steps_per_second": 7.768,
|
128 |
+
"step": 4000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.94,
|
132 |
+
"learning_rate": 1.3706733794839521e-05,
|
133 |
+
"loss": 0.0219,
|
134 |
+
"step": 4500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.94,
|
138 |
+
"eval_accuracy": 0.9954366640440598,
|
139 |
+
"eval_loss": 0.01884845644235611,
|
140 |
+
"eval_runtime": 153.901,
|
141 |
+
"eval_samples_per_second": 123.878,
|
142 |
+
"eval_steps_per_second": 7.745,
|
143 |
+
"step": 4500
|
144 |
+
}
|
145 |
+
],
|
146 |
+
"max_steps": 14301,
|
147 |
+
"num_train_epochs": 3,
|
148 |
+
"total_flos": 9537652703232000.0,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": null
|
151 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1317ed9b28a901fc802c67584193ee79f96fe31da7695bec1e79e610e483cf78
|
3 |
+
size 3963
|