Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- tmp-checkpoint-1115/config.json +65 -0
- tmp-checkpoint-1115/model.safetensors +3 -0
- tmp-checkpoint-1115/optimizer.pt +3 -0
- tmp-checkpoint-1115/preprocessor_config.json +22 -0
- tmp-checkpoint-1115/rng_state.pth +3 -0
- tmp-checkpoint-1115/scheduler.pt +3 -0
- tmp-checkpoint-1115/trainer_state.json +727 -0
- tmp-checkpoint-1115/training_args.bin +3 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110348984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:101e4a2089b0d1dc68769c947886c96f54297652a70397d6e34d3ca42c48a8f8
|
3 |
size 110348984
|
tmp-checkpoint-1115/config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
6,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 96,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "noncrack",
|
21 |
+
"1": "sealedcrack",
|
22 |
+
"2": "sealedpatch",
|
23 |
+
"3": "thincrack"
|
24 |
+
},
|
25 |
+
"image_size": 224,
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"label2id": {
|
28 |
+
"noncrack": 0,
|
29 |
+
"sealedcrack": 1,
|
30 |
+
"sealedpatch": 2,
|
31 |
+
"thincrack": 3
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"mlp_ratio": 4.0,
|
35 |
+
"model_type": "swin",
|
36 |
+
"num_channels": 3,
|
37 |
+
"num_heads": [
|
38 |
+
3,
|
39 |
+
6,
|
40 |
+
12,
|
41 |
+
24
|
42 |
+
],
|
43 |
+
"num_layers": 4,
|
44 |
+
"out_features": [
|
45 |
+
"stage4"
|
46 |
+
],
|
47 |
+
"out_indices": [
|
48 |
+
4
|
49 |
+
],
|
50 |
+
"patch_size": 4,
|
51 |
+
"path_norm": true,
|
52 |
+
"problem_type": "single_label_classification",
|
53 |
+
"qkv_bias": true,
|
54 |
+
"stage_names": [
|
55 |
+
"stem",
|
56 |
+
"stage1",
|
57 |
+
"stage2",
|
58 |
+
"stage3",
|
59 |
+
"stage4"
|
60 |
+
],
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.37.2",
|
63 |
+
"use_absolute_embeddings": false,
|
64 |
+
"window_size": 7
|
65 |
+
}
|
tmp-checkpoint-1115/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:101e4a2089b0d1dc68769c947886c96f54297652a70397d6e34d3ca42c48a8f8
|
3 |
+
size 110348984
|
tmp-checkpoint-1115/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a23986ad746e4936d8e8f9b70bae3cc0d69d62074f0b0ad7174af5749937700
|
3 |
+
size 220362874
|
tmp-checkpoint-1115/preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.229,
|
13 |
+
0.224,
|
14 |
+
0.225
|
15 |
+
],
|
16 |
+
"resample": 3,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
tmp-checkpoint-1115/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1348e49468be32c1d565d2ea50df7a8b7a69bf840c001cb89fb57f7bb3f1fec0
|
3 |
+
size 14244
|
tmp-checkpoint-1115/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad8caf515f723b96c39b80b844d0200f4b9494223a4ad00746cbb030c6d9f015
|
3 |
+
size 1064
|
tmp-checkpoint-1115/trainer_state.json
ADDED
@@ -0,0 +1,727 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2781514525413513,
|
3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-crack-detectorMAIN50epochsFINAL\\checkpoint-1115",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1115,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 1.7953321364452426e-07,
|
14 |
+
"loss": 1.4257,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.04,
|
19 |
+
"learning_rate": 3.590664272890485e-07,
|
20 |
+
"loss": 1.4227,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 5.385996409335728e-07,
|
26 |
+
"loss": 1.4112,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.07,
|
31 |
+
"learning_rate": 7.18132854578097e-07,
|
32 |
+
"loss": 1.4052,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.09,
|
37 |
+
"learning_rate": 8.976660682226213e-07,
|
38 |
+
"loss": 1.3954,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.11,
|
43 |
+
"learning_rate": 1.0771992818671456e-06,
|
44 |
+
"loss": 1.3978,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.13,
|
49 |
+
"learning_rate": 1.2567324955116697e-06,
|
50 |
+
"loss": 1.3862,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.14,
|
55 |
+
"learning_rate": 1.436265709156194e-06,
|
56 |
+
"loss": 1.3651,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.16,
|
61 |
+
"learning_rate": 1.6157989228007182e-06,
|
62 |
+
"loss": 1.359,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.18,
|
67 |
+
"learning_rate": 1.7953321364452425e-06,
|
68 |
+
"loss": 1.3476,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.2,
|
73 |
+
"learning_rate": 1.9748653500897667e-06,
|
74 |
+
"loss": 1.3303,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.22,
|
79 |
+
"learning_rate": 2.1543985637342912e-06,
|
80 |
+
"loss": 1.3047,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.23,
|
85 |
+
"learning_rate": 2.333931777378815e-06,
|
86 |
+
"loss": 1.2944,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.25,
|
91 |
+
"learning_rate": 2.5134649910233395e-06,
|
92 |
+
"loss": 1.284,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.27,
|
97 |
+
"learning_rate": 2.6929982046678636e-06,
|
98 |
+
"loss": 1.23,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.29,
|
103 |
+
"learning_rate": 2.872531418312388e-06,
|
104 |
+
"loss": 1.2103,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.3,
|
109 |
+
"learning_rate": 3.0520646319569123e-06,
|
110 |
+
"loss": 1.187,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.32,
|
115 |
+
"learning_rate": 3.2315978456014364e-06,
|
116 |
+
"loss": 1.1591,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.34,
|
121 |
+
"learning_rate": 3.411131059245961e-06,
|
122 |
+
"loss": 1.144,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.36,
|
127 |
+
"learning_rate": 3.590664272890485e-06,
|
128 |
+
"loss": 1.0904,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.38,
|
133 |
+
"learning_rate": 3.770197486535009e-06,
|
134 |
+
"loss": 1.0401,
|
135 |
+
"step": 210
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.39,
|
139 |
+
"learning_rate": 3.949730700179533e-06,
|
140 |
+
"loss": 1.0281,
|
141 |
+
"step": 220
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.41,
|
145 |
+
"learning_rate": 4.129263913824058e-06,
|
146 |
+
"loss": 0.9577,
|
147 |
+
"step": 230
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.43,
|
151 |
+
"learning_rate": 4.3087971274685824e-06,
|
152 |
+
"loss": 0.9251,
|
153 |
+
"step": 240
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.45,
|
157 |
+
"learning_rate": 4.488330341113106e-06,
|
158 |
+
"loss": 0.8964,
|
159 |
+
"step": 250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.47,
|
163 |
+
"learning_rate": 4.66786355475763e-06,
|
164 |
+
"loss": 0.8897,
|
165 |
+
"step": 260
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.48,
|
169 |
+
"learning_rate": 4.847396768402154e-06,
|
170 |
+
"loss": 0.8481,
|
171 |
+
"step": 270
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.5,
|
175 |
+
"learning_rate": 5.026929982046679e-06,
|
176 |
+
"loss": 0.8048,
|
177 |
+
"step": 280
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.52,
|
181 |
+
"learning_rate": 5.206463195691203e-06,
|
182 |
+
"loss": 0.8014,
|
183 |
+
"step": 290
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.54,
|
187 |
+
"learning_rate": 5.385996409335727e-06,
|
188 |
+
"loss": 0.7511,
|
189 |
+
"step": 300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.56,
|
193 |
+
"learning_rate": 5.565529622980251e-06,
|
194 |
+
"loss": 0.741,
|
195 |
+
"step": 310
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.57,
|
199 |
+
"learning_rate": 5.745062836624776e-06,
|
200 |
+
"loss": 0.7327,
|
201 |
+
"step": 320
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.59,
|
205 |
+
"learning_rate": 5.9245960502693004e-06,
|
206 |
+
"loss": 0.7492,
|
207 |
+
"step": 330
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.61,
|
211 |
+
"learning_rate": 6.1041292639138246e-06,
|
212 |
+
"loss": 0.7613,
|
213 |
+
"step": 340
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.63,
|
217 |
+
"learning_rate": 6.283662477558349e-06,
|
218 |
+
"loss": 0.6902,
|
219 |
+
"step": 350
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.65,
|
223 |
+
"learning_rate": 6.463195691202873e-06,
|
224 |
+
"loss": 0.6687,
|
225 |
+
"step": 360
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.66,
|
229 |
+
"learning_rate": 6.642728904847396e-06,
|
230 |
+
"loss": 0.6623,
|
231 |
+
"step": 370
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.68,
|
235 |
+
"learning_rate": 6.822262118491922e-06,
|
236 |
+
"loss": 0.6901,
|
237 |
+
"step": 380
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.7,
|
241 |
+
"learning_rate": 7.001795332136446e-06,
|
242 |
+
"loss": 0.6638,
|
243 |
+
"step": 390
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.72,
|
247 |
+
"learning_rate": 7.18132854578097e-06,
|
248 |
+
"loss": 0.6414,
|
249 |
+
"step": 400
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.74,
|
253 |
+
"learning_rate": 7.360861759425494e-06,
|
254 |
+
"loss": 0.6877,
|
255 |
+
"step": 410
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.75,
|
259 |
+
"learning_rate": 7.540394973070018e-06,
|
260 |
+
"loss": 0.6249,
|
261 |
+
"step": 420
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.77,
|
265 |
+
"learning_rate": 7.719928186714543e-06,
|
266 |
+
"loss": 0.6099,
|
267 |
+
"step": 430
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.79,
|
271 |
+
"learning_rate": 7.899461400359067e-06,
|
272 |
+
"loss": 0.6321,
|
273 |
+
"step": 440
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.81,
|
277 |
+
"learning_rate": 8.07899461400359e-06,
|
278 |
+
"loss": 0.6431,
|
279 |
+
"step": 450
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.83,
|
283 |
+
"learning_rate": 8.258527827648117e-06,
|
284 |
+
"loss": 0.6404,
|
285 |
+
"step": 460
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.84,
|
289 |
+
"learning_rate": 8.43806104129264e-06,
|
290 |
+
"loss": 0.6148,
|
291 |
+
"step": 470
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.86,
|
295 |
+
"learning_rate": 8.617594254937165e-06,
|
296 |
+
"loss": 0.5844,
|
297 |
+
"step": 480
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.88,
|
301 |
+
"learning_rate": 8.797127468581689e-06,
|
302 |
+
"loss": 0.6316,
|
303 |
+
"step": 490
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.9,
|
307 |
+
"learning_rate": 8.976660682226211e-06,
|
308 |
+
"loss": 0.6018,
|
309 |
+
"step": 500
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.91,
|
313 |
+
"learning_rate": 9.156193895870736e-06,
|
314 |
+
"loss": 0.5843,
|
315 |
+
"step": 510
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.93,
|
319 |
+
"learning_rate": 9.33572710951526e-06,
|
320 |
+
"loss": 0.5986,
|
321 |
+
"step": 520
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.95,
|
325 |
+
"learning_rate": 9.515260323159784e-06,
|
326 |
+
"loss": 0.5718,
|
327 |
+
"step": 530
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.97,
|
331 |
+
"learning_rate": 9.694793536804308e-06,
|
332 |
+
"loss": 0.5163,
|
333 |
+
"step": 540
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.99,
|
337 |
+
"learning_rate": 9.874326750448834e-06,
|
338 |
+
"loss": 0.5448,
|
339 |
+
"step": 550
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.0,
|
343 |
+
"eval_accuracy": {
|
344 |
+
"accuracy": 0.8387530836510428
|
345 |
+
},
|
346 |
+
"eval_f1": {
|
347 |
+
"f1": 0.8242528613153339
|
348 |
+
},
|
349 |
+
"eval_loss": 0.43474748730659485,
|
350 |
+
"eval_precision": {
|
351 |
+
"precision": 0.8238035334510331
|
352 |
+
},
|
353 |
+
"eval_recall": {
|
354 |
+
"recall": 0.8266051811271123
|
355 |
+
},
|
356 |
+
"eval_runtime": 171.551,
|
357 |
+
"eval_samples_per_second": 103.969,
|
358 |
+
"eval_steps_per_second": 3.253,
|
359 |
+
"step": 557
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.0,
|
363 |
+
"learning_rate": 1.0053859964093358e-05,
|
364 |
+
"loss": 0.58,
|
365 |
+
"step": 560
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.02,
|
369 |
+
"learning_rate": 1.0233393177737882e-05,
|
370 |
+
"loss": 0.5298,
|
371 |
+
"step": 570
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.04,
|
375 |
+
"learning_rate": 1.0412926391382406e-05,
|
376 |
+
"loss": 0.5592,
|
377 |
+
"step": 580
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.06,
|
381 |
+
"learning_rate": 1.059245960502693e-05,
|
382 |
+
"loss": 0.5352,
|
383 |
+
"step": 590
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.08,
|
387 |
+
"learning_rate": 1.0771992818671454e-05,
|
388 |
+
"loss": 0.5683,
|
389 |
+
"step": 600
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 1.09,
|
393 |
+
"learning_rate": 1.0951526032315979e-05,
|
394 |
+
"loss": 0.571,
|
395 |
+
"step": 610
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.11,
|
399 |
+
"learning_rate": 1.1131059245960503e-05,
|
400 |
+
"loss": 0.5603,
|
401 |
+
"step": 620
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.13,
|
405 |
+
"learning_rate": 1.1310592459605028e-05,
|
406 |
+
"loss": 0.5157,
|
407 |
+
"step": 630
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 1.15,
|
411 |
+
"learning_rate": 1.1490125673249553e-05,
|
412 |
+
"loss": 0.4885,
|
413 |
+
"step": 640
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.17,
|
417 |
+
"learning_rate": 1.1669658886894077e-05,
|
418 |
+
"loss": 0.5005,
|
419 |
+
"step": 650
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.18,
|
423 |
+
"learning_rate": 1.1849192100538601e-05,
|
424 |
+
"loss": 0.4951,
|
425 |
+
"step": 660
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 1.2,
|
429 |
+
"learning_rate": 1.2028725314183125e-05,
|
430 |
+
"loss": 0.5197,
|
431 |
+
"step": 670
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.22,
|
435 |
+
"learning_rate": 1.2208258527827649e-05,
|
436 |
+
"loss": 0.4746,
|
437 |
+
"step": 680
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.24,
|
441 |
+
"learning_rate": 1.2387791741472173e-05,
|
442 |
+
"loss": 0.486,
|
443 |
+
"step": 690
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 1.26,
|
447 |
+
"learning_rate": 1.2567324955116697e-05,
|
448 |
+
"loss": 0.4932,
|
449 |
+
"step": 700
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.27,
|
453 |
+
"learning_rate": 1.2746858168761221e-05,
|
454 |
+
"loss": 0.5222,
|
455 |
+
"step": 710
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 1.29,
|
459 |
+
"learning_rate": 1.2926391382405746e-05,
|
460 |
+
"loss": 0.434,
|
461 |
+
"step": 720
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 1.31,
|
465 |
+
"learning_rate": 1.310592459605027e-05,
|
466 |
+
"loss": 0.4817,
|
467 |
+
"step": 730
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 1.33,
|
471 |
+
"learning_rate": 1.3285457809694792e-05,
|
472 |
+
"loss": 0.487,
|
473 |
+
"step": 740
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.35,
|
477 |
+
"learning_rate": 1.3464991023339318e-05,
|
478 |
+
"loss": 0.4478,
|
479 |
+
"step": 750
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.36,
|
483 |
+
"learning_rate": 1.3644524236983844e-05,
|
484 |
+
"loss": 0.4564,
|
485 |
+
"step": 760
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 1.38,
|
489 |
+
"learning_rate": 1.3824057450628366e-05,
|
490 |
+
"loss": 0.4455,
|
491 |
+
"step": 770
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 1.4,
|
495 |
+
"learning_rate": 1.4003590664272892e-05,
|
496 |
+
"loss": 0.4701,
|
497 |
+
"step": 780
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.42,
|
501 |
+
"learning_rate": 1.4183123877917415e-05,
|
502 |
+
"loss": 0.4333,
|
503 |
+
"step": 790
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 1.43,
|
507 |
+
"learning_rate": 1.436265709156194e-05,
|
508 |
+
"loss": 0.4409,
|
509 |
+
"step": 800
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 1.45,
|
513 |
+
"learning_rate": 1.4542190305206463e-05,
|
514 |
+
"loss": 0.4639,
|
515 |
+
"step": 810
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 1.47,
|
519 |
+
"learning_rate": 1.4721723518850989e-05,
|
520 |
+
"loss": 0.4552,
|
521 |
+
"step": 820
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.49,
|
525 |
+
"learning_rate": 1.4901256732495511e-05,
|
526 |
+
"loss": 0.4759,
|
527 |
+
"step": 830
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 1.51,
|
531 |
+
"learning_rate": 1.5080789946140037e-05,
|
532 |
+
"loss": 0.4584,
|
533 |
+
"step": 840
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 1.52,
|
537 |
+
"learning_rate": 1.5260323159784563e-05,
|
538 |
+
"loss": 0.4502,
|
539 |
+
"step": 850
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 1.54,
|
543 |
+
"learning_rate": 1.5439856373429085e-05,
|
544 |
+
"loss": 0.4519,
|
545 |
+
"step": 860
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.56,
|
549 |
+
"learning_rate": 1.561938958707361e-05,
|
550 |
+
"loss": 0.4695,
|
551 |
+
"step": 870
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 1.58,
|
555 |
+
"learning_rate": 1.5798922800718133e-05,
|
556 |
+
"loss": 0.4466,
|
557 |
+
"step": 880
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 1.6,
|
561 |
+
"learning_rate": 1.597845601436266e-05,
|
562 |
+
"loss": 0.4531,
|
563 |
+
"step": 890
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.61,
|
567 |
+
"learning_rate": 1.615798922800718e-05,
|
568 |
+
"loss": 0.4674,
|
569 |
+
"step": 900
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.63,
|
573 |
+
"learning_rate": 1.6337522441651707e-05,
|
574 |
+
"loss": 0.4262,
|
575 |
+
"step": 910
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 1.65,
|
579 |
+
"learning_rate": 1.6517055655296233e-05,
|
580 |
+
"loss": 0.3945,
|
581 |
+
"step": 920
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 1.67,
|
585 |
+
"learning_rate": 1.6696588868940756e-05,
|
586 |
+
"loss": 0.4318,
|
587 |
+
"step": 930
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 1.69,
|
591 |
+
"learning_rate": 1.687612208258528e-05,
|
592 |
+
"loss": 0.439,
|
593 |
+
"step": 940
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 1.7,
|
597 |
+
"learning_rate": 1.7055655296229804e-05,
|
598 |
+
"loss": 0.4036,
|
599 |
+
"step": 950
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 1.72,
|
603 |
+
"learning_rate": 1.723518850987433e-05,
|
604 |
+
"loss": 0.422,
|
605 |
+
"step": 960
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.74,
|
609 |
+
"learning_rate": 1.7414721723518852e-05,
|
610 |
+
"loss": 0.4315,
|
611 |
+
"step": 970
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 1.76,
|
615 |
+
"learning_rate": 1.7594254937163378e-05,
|
616 |
+
"loss": 0.4516,
|
617 |
+
"step": 980
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 1.78,
|
621 |
+
"learning_rate": 1.77737881508079e-05,
|
622 |
+
"loss": 0.4092,
|
623 |
+
"step": 990
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 1.79,
|
627 |
+
"learning_rate": 1.7953321364452423e-05,
|
628 |
+
"loss": 0.4367,
|
629 |
+
"step": 1000
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 1.81,
|
633 |
+
"learning_rate": 1.813285457809695e-05,
|
634 |
+
"loss": 0.4321,
|
635 |
+
"step": 1010
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 1.83,
|
639 |
+
"learning_rate": 1.831238779174147e-05,
|
640 |
+
"loss": 0.3859,
|
641 |
+
"step": 1020
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.85,
|
645 |
+
"learning_rate": 1.8491921005385997e-05,
|
646 |
+
"loss": 0.415,
|
647 |
+
"step": 1030
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 1.87,
|
651 |
+
"learning_rate": 1.867145421903052e-05,
|
652 |
+
"loss": 0.4388,
|
653 |
+
"step": 1040
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.88,
|
657 |
+
"learning_rate": 1.8850987432675045e-05,
|
658 |
+
"loss": 0.3968,
|
659 |
+
"step": 1050
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 1.9,
|
663 |
+
"learning_rate": 1.9030520646319568e-05,
|
664 |
+
"loss": 0.4172,
|
665 |
+
"step": 1060
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.92,
|
669 |
+
"learning_rate": 1.9210053859964093e-05,
|
670 |
+
"loss": 0.4593,
|
671 |
+
"step": 1070
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.94,
|
675 |
+
"learning_rate": 1.9389587073608616e-05,
|
676 |
+
"loss": 0.3924,
|
677 |
+
"step": 1080
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 1.96,
|
681 |
+
"learning_rate": 1.9569120287253142e-05,
|
682 |
+
"loss": 0.4067,
|
683 |
+
"step": 1090
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 1.97,
|
687 |
+
"learning_rate": 1.9748653500897668e-05,
|
688 |
+
"loss": 0.3906,
|
689 |
+
"step": 1100
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.99,
|
693 |
+
"learning_rate": 1.992818671454219e-05,
|
694 |
+
"loss": 0.3915,
|
695 |
+
"step": 1110
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 2.0,
|
699 |
+
"eval_accuracy": {
|
700 |
+
"accuracy": 0.8952679973088137
|
701 |
+
},
|
702 |
+
"eval_f1": {
|
703 |
+
"f1": 0.8895212539619177
|
704 |
+
},
|
705 |
+
"eval_loss": 0.2781514525413513,
|
706 |
+
"eval_precision": {
|
707 |
+
"precision": 0.8895590270096669
|
708 |
+
},
|
709 |
+
"eval_recall": {
|
710 |
+
"recall": 0.892156947982043
|
711 |
+
},
|
712 |
+
"eval_runtime": 99.0662,
|
713 |
+
"eval_samples_per_second": 180.041,
|
714 |
+
"eval_steps_per_second": 5.633,
|
715 |
+
"step": 1115
|
716 |
+
}
|
717 |
+
],
|
718 |
+
"logging_steps": 10,
|
719 |
+
"max_steps": 27850,
|
720 |
+
"num_input_tokens_seen": 0,
|
721 |
+
"num_train_epochs": 50,
|
722 |
+
"save_steps": 500,
|
723 |
+
"total_flos": 3.546650701349683e+18,
|
724 |
+
"train_batch_size": 32,
|
725 |
+
"trial_name": null,
|
726 |
+
"trial_params": null
|
727 |
+
}
|
tmp-checkpoint-1115/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c081bc3c7c7c6c246b97a8d5de1f01d4b69caf186a7167574020cb94e76e323a
|
3 |
+
size 4792
|