Upload folder using huggingface_hub
Browse files- config.json +22 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +201 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPModel"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 512,
|
10 |
+
"text_config": {
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"dropout": 0.0,
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"model_type": "clip_text_model"
|
15 |
+
},
|
16 |
+
"torch_dtype": "float32",
|
17 |
+
"transformers_version": "4.36.2",
|
18 |
+
"vision_config": {
|
19 |
+
"dropout": 0.0,
|
20 |
+
"model_type": "clip_vision_model"
|
21 |
+
}
|
22 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e3d919cb1a8afc3aa5009d3b8284c627ff60bcad188d6323a0ab89642319f42
|
3 |
+
size 605156676
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b900b49aab12a9eb446f950269c1a3aa1981fe7a5e00e9954d4565296c10e3d2
|
3 |
+
size 1210551612
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:854d44a3446226203a88f1fc642af80860bfb849fcb9be9cb5df2b3857efab6f
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8871ca3d638a3f76c4ff048b08020ee125e1e31672157fae152f7e6263c6bb5
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,201 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7317073170731707,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 30,
|
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": 4.9995000000000005e-05,
|
14 |
+
"loss": 1.5986,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.05,
|
19 |
+
"learning_rate": 4.999e-05,
|
20 |
+
"loss": 2.5591,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.07,
|
25 |
+
"learning_rate": 4.9985e-05,
|
26 |
+
"loss": 1.8778,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.1,
|
31 |
+
"learning_rate": 4.9980000000000006e-05,
|
32 |
+
"loss": 2.6038,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.12,
|
37 |
+
"learning_rate": 4.9975e-05,
|
38 |
+
"loss": 1.7417,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.15,
|
43 |
+
"learning_rate": 4.997e-05,
|
44 |
+
"loss": 1.6722,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.17,
|
49 |
+
"learning_rate": 4.9965e-05,
|
50 |
+
"loss": 1.4006,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2,
|
55 |
+
"learning_rate": 4.996e-05,
|
56 |
+
"loss": 1.2633,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.22,
|
61 |
+
"learning_rate": 4.9955e-05,
|
62 |
+
"loss": 1.1828,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.24,
|
67 |
+
"learning_rate": 4.995e-05,
|
68 |
+
"loss": 1.0802,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.27,
|
73 |
+
"learning_rate": 4.9945000000000004e-05,
|
74 |
+
"loss": 0.9983,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.29,
|
79 |
+
"learning_rate": 4.9940000000000006e-05,
|
80 |
+
"loss": 1.0225,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.32,
|
85 |
+
"learning_rate": 4.9935e-05,
|
86 |
+
"loss": 0.996,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.34,
|
91 |
+
"learning_rate": 4.9930000000000005e-05,
|
92 |
+
"loss": 0.9677,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.37,
|
97 |
+
"learning_rate": 4.992500000000001e-05,
|
98 |
+
"loss": 0.8863,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.39,
|
103 |
+
"learning_rate": 4.992e-05,
|
104 |
+
"loss": 0.925,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.41,
|
109 |
+
"learning_rate": 4.9915e-05,
|
110 |
+
"loss": 0.8541,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.44,
|
115 |
+
"learning_rate": 4.991e-05,
|
116 |
+
"loss": 0.8547,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.46,
|
121 |
+
"learning_rate": 4.9905000000000004e-05,
|
122 |
+
"loss": 0.8159,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.49,
|
127 |
+
"learning_rate": 4.99e-05,
|
128 |
+
"loss": 0.8186,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.51,
|
133 |
+
"learning_rate": 4.9895e-05,
|
134 |
+
"loss": 0.7936,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.54,
|
139 |
+
"learning_rate": 4.9890000000000005e-05,
|
140 |
+
"loss": 0.792,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.56,
|
145 |
+
"learning_rate": 4.9885e-05,
|
146 |
+
"loss": 0.7438,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.59,
|
151 |
+
"learning_rate": 4.9880000000000004e-05,
|
152 |
+
"loss": 0.7641,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.61,
|
157 |
+
"learning_rate": 4.9875000000000006e-05,
|
158 |
+
"loss": 0.7644,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.63,
|
163 |
+
"learning_rate": 4.987e-05,
|
164 |
+
"loss": 0.7188,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.66,
|
169 |
+
"learning_rate": 4.9865e-05,
|
170 |
+
"loss": 0.7475,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.68,
|
175 |
+
"learning_rate": 4.986e-05,
|
176 |
+
"loss": 0.729,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.71,
|
181 |
+
"learning_rate": 4.9855e-05,
|
182 |
+
"loss": 0.719,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.73,
|
187 |
+
"learning_rate": 4.9850000000000006e-05,
|
188 |
+
"loss": 0.69,
|
189 |
+
"step": 30
|
190 |
+
}
|
191 |
+
],
|
192 |
+
"logging_steps": 1,
|
193 |
+
"max_steps": 10000,
|
194 |
+
"num_input_tokens_seen": 0,
|
195 |
+
"num_train_epochs": 244,
|
196 |
+
"save_steps": 10,
|
197 |
+
"total_flos": 5157614830556160.0,
|
198 |
+
"train_batch_size": 3584,
|
199 |
+
"trial_name": null,
|
200 |
+
"trial_params": null
|
201 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcd267734380b181e34dfef34e0ee3300fd8441ca7d8784e4a2c5e660587fddb
|
3 |
+
size 4664
|