Upload folder using huggingface_hub
Browse files- README.md +4 -4
- all_results.json +5 -5
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +26 -212
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,14 +3,14 @@ base_model: ./output4
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
-
- name:
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
#
|
14 |
|
15 |
This model is a fine-tuned version of [./output4](https://huggingface.co/./output4) on an unknown dataset.
|
16 |
|
@@ -31,7 +31,7 @@ More information needed
|
|
31 |
### Training hyperparameters
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
-
- learning_rate: 0.
|
35 |
- train_batch_size: 1
|
36 |
- eval_batch_size: 1
|
37 |
- seed: 42
|
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
|
|
39 |
- total_train_batch_size: 8
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: constant
|
42 |
-
- num_epochs:
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
+
- name: output5
|
7 |
results: []
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
should probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
+
# output5
|
14 |
|
15 |
This model is a fine-tuned version of [./output4](https://huggingface.co/./output4) on an unknown dataset.
|
16 |
|
|
|
31 |
### Training hyperparameters
|
32 |
|
33 |
The following hyperparameters were used during training:
|
34 |
+
- learning_rate: 0.001
|
35 |
- train_batch_size: 1
|
36 |
- eval_batch_size: 1
|
37 |
- seed: 42
|
|
|
39 |
- total_train_batch_size: 8
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: constant
|
42 |
+
- num_epochs: 1.0
|
43 |
|
44 |
### Training results
|
45 |
|
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 308,
|
6 |
-
"train_samples_per_second": 4.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.99,
|
3 |
+
"train_loss": 1.9883024441568475,
|
4 |
+
"train_runtime": 66.056,
|
5 |
"train_samples": 308,
|
6 |
+
"train_samples_per_second": 4.663,
|
7 |
+
"train_steps_per_second": 0.575
|
8 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70790896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c891c8adc8cb44121a355168ea7485416fca89f4893f2c0dcc97eada7d85ec7
|
3 |
size 70790896
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 308,
|
6 |
-
"train_samples_per_second": 4.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.99,
|
3 |
+
"train_loss": 1.9883024441568475,
|
4 |
+
"train_runtime": 66.056,
|
5 |
"train_samples": 308,
|
6 |
+
"train_samples_per_second": 4.663,
|
7 |
+
"train_steps_per_second": 0.575
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,256 +1,70 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.13,
|
13 |
-
"learning_rate": 0.
|
14 |
-
"loss": 2.
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.26,
|
19 |
-
"learning_rate": 0.
|
20 |
-
"loss": 1.
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.39,
|
25 |
-
"learning_rate": 0.
|
26 |
-
"loss": 1.
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.52,
|
31 |
-
"learning_rate": 0.
|
32 |
-
"loss":
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.65,
|
37 |
-
"learning_rate": 0.
|
38 |
-
"loss": 1.
|
39 |
"step": 25
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.78,
|
43 |
-
"learning_rate": 0.
|
44 |
-
"loss": 1.
|
45 |
"step": 30
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.91,
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss": 2.
|
51 |
"step": 35
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
|
59 |
-
|
60 |
-
"
|
61 |
-
"learning_rate": 0.0001,
|
62 |
-
"loss": 1.9942,
|
63 |
-
"step": 45
|
64 |
-
},
|
65 |
-
{
|
66 |
-
"epoch": 1.3,
|
67 |
-
"learning_rate": 0.0001,
|
68 |
-
"loss": 1.8956,
|
69 |
-
"step": 50
|
70 |
-
},
|
71 |
-
{
|
72 |
-
"epoch": 1.43,
|
73 |
-
"learning_rate": 0.0001,
|
74 |
-
"loss": 1.8971,
|
75 |
-
"step": 55
|
76 |
-
},
|
77 |
-
{
|
78 |
-
"epoch": 1.56,
|
79 |
-
"learning_rate": 0.0001,
|
80 |
-
"loss": 1.8397,
|
81 |
-
"step": 60
|
82 |
-
},
|
83 |
-
{
|
84 |
-
"epoch": 1.69,
|
85 |
-
"learning_rate": 0.0001,
|
86 |
-
"loss": 1.9135,
|
87 |
-
"step": 65
|
88 |
-
},
|
89 |
-
{
|
90 |
-
"epoch": 1.82,
|
91 |
-
"learning_rate": 0.0001,
|
92 |
-
"loss": 1.8782,
|
93 |
-
"step": 70
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 1.95,
|
97 |
-
"learning_rate": 0.0001,
|
98 |
-
"loss": 1.8756,
|
99 |
-
"step": 75
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"epoch": 2.08,
|
103 |
-
"learning_rate": 0.0001,
|
104 |
-
"loss": 1.887,
|
105 |
-
"step": 80
|
106 |
-
},
|
107 |
-
{
|
108 |
-
"epoch": 2.21,
|
109 |
-
"learning_rate": 0.0001,
|
110 |
-
"loss": 1.8408,
|
111 |
-
"step": 85
|
112 |
-
},
|
113 |
-
{
|
114 |
-
"epoch": 2.34,
|
115 |
-
"learning_rate": 0.0001,
|
116 |
-
"loss": 1.8352,
|
117 |
-
"step": 90
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"epoch": 2.47,
|
121 |
-
"learning_rate": 0.0001,
|
122 |
-
"loss": 1.8403,
|
123 |
-
"step": 95
|
124 |
-
},
|
125 |
-
{
|
126 |
-
"epoch": 2.6,
|
127 |
-
"learning_rate": 0.0001,
|
128 |
-
"loss": 1.8519,
|
129 |
-
"step": 100
|
130 |
-
},
|
131 |
-
{
|
132 |
-
"epoch": 2.73,
|
133 |
-
"learning_rate": 0.0001,
|
134 |
-
"loss": 1.8683,
|
135 |
-
"step": 105
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"epoch": 2.86,
|
139 |
-
"learning_rate": 0.0001,
|
140 |
-
"loss": 1.8082,
|
141 |
-
"step": 110
|
142 |
-
},
|
143 |
-
{
|
144 |
-
"epoch": 2.99,
|
145 |
-
"learning_rate": 0.0001,
|
146 |
-
"loss": 1.811,
|
147 |
-
"step": 115
|
148 |
-
},
|
149 |
-
{
|
150 |
-
"epoch": 3.12,
|
151 |
-
"learning_rate": 0.0001,
|
152 |
-
"loss": 1.8451,
|
153 |
-
"step": 120
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"epoch": 3.25,
|
157 |
-
"learning_rate": 0.0001,
|
158 |
-
"loss": 1.7562,
|
159 |
-
"step": 125
|
160 |
-
},
|
161 |
-
{
|
162 |
-
"epoch": 3.38,
|
163 |
-
"learning_rate": 0.0001,
|
164 |
-
"loss": 1.8435,
|
165 |
-
"step": 130
|
166 |
-
},
|
167 |
-
{
|
168 |
-
"epoch": 3.51,
|
169 |
-
"learning_rate": 0.0001,
|
170 |
-
"loss": 1.7416,
|
171 |
-
"step": 135
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"epoch": 3.64,
|
175 |
-
"learning_rate": 0.0001,
|
176 |
-
"loss": 1.8242,
|
177 |
-
"step": 140
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 3.77,
|
181 |
-
"learning_rate": 0.0001,
|
182 |
-
"loss": 1.7191,
|
183 |
-
"step": 145
|
184 |
-
},
|
185 |
-
{
|
186 |
-
"epoch": 3.9,
|
187 |
-
"learning_rate": 0.0001,
|
188 |
-
"loss": 1.8372,
|
189 |
-
"step": 150
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"epoch": 4.03,
|
193 |
-
"learning_rate": 0.0001,
|
194 |
-
"loss": 1.6897,
|
195 |
-
"step": 155
|
196 |
-
},
|
197 |
-
{
|
198 |
-
"epoch": 4.16,
|
199 |
-
"learning_rate": 0.0001,
|
200 |
-
"loss": 1.7764,
|
201 |
-
"step": 160
|
202 |
-
},
|
203 |
-
{
|
204 |
-
"epoch": 4.29,
|
205 |
-
"learning_rate": 0.0001,
|
206 |
-
"loss": 1.7044,
|
207 |
-
"step": 165
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"epoch": 4.42,
|
211 |
-
"learning_rate": 0.0001,
|
212 |
-
"loss": 1.6948,
|
213 |
-
"step": 170
|
214 |
-
},
|
215 |
-
{
|
216 |
-
"epoch": 4.55,
|
217 |
-
"learning_rate": 0.0001,
|
218 |
-
"loss": 1.7268,
|
219 |
-
"step": 175
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 4.68,
|
223 |
-
"learning_rate": 0.0001,
|
224 |
-
"loss": 1.7703,
|
225 |
-
"step": 180
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"epoch": 4.81,
|
229 |
-
"learning_rate": 0.0001,
|
230 |
-
"loss": 1.7836,
|
231 |
-
"step": 185
|
232 |
-
},
|
233 |
-
{
|
234 |
-
"epoch": 4.94,
|
235 |
-
"learning_rate": 0.0001,
|
236 |
-
"loss": 1.7871,
|
237 |
-
"step": 190
|
238 |
-
},
|
239 |
-
{
|
240 |
-
"epoch": 4.94,
|
241 |
-
"step": 190,
|
242 |
-
"total_flos": 697572311040000.0,
|
243 |
-
"train_loss": 1.8531885046707957,
|
244 |
-
"train_runtime": 316.8119,
|
245 |
-
"train_samples_per_second": 4.861,
|
246 |
-
"train_steps_per_second": 0.6
|
247 |
}
|
248 |
],
|
249 |
"logging_steps": 5,
|
250 |
-
"max_steps":
|
251 |
-
"num_train_epochs":
|
252 |
"save_steps": 1000,
|
253 |
-
"total_flos":
|
254 |
"trial_name": null,
|
255 |
"trial_params": null
|
256 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.987012987012987,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 38,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.13,
|
13 |
+
"learning_rate": 0.001,
|
14 |
+
"loss": 2.281,
|
15 |
"step": 5
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.26,
|
19 |
+
"learning_rate": 0.001,
|
20 |
+
"loss": 1.9633,
|
21 |
"step": 10
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.39,
|
25 |
+
"learning_rate": 0.001,
|
26 |
+
"loss": 1.9001,
|
27 |
"step": 15
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.52,
|
31 |
+
"learning_rate": 0.001,
|
32 |
+
"loss": 1.972,
|
33 |
"step": 20
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.65,
|
37 |
+
"learning_rate": 0.001,
|
38 |
+
"loss": 1.9153,
|
39 |
"step": 25
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.78,
|
43 |
+
"learning_rate": 0.001,
|
44 |
+
"loss": 1.9156,
|
45 |
"step": 30
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.91,
|
49 |
+
"learning_rate": 0.001,
|
50 |
+
"loss": 2.0138,
|
51 |
"step": 35
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.99,
|
55 |
+
"step": 38,
|
56 |
+
"total_flos": 139514462208000.0,
|
57 |
+
"train_loss": 1.9883024441568475,
|
58 |
+
"train_runtime": 66.056,
|
59 |
+
"train_samples_per_second": 4.663,
|
60 |
+
"train_steps_per_second": 0.575
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 5,
|
64 |
+
"max_steps": 38,
|
65 |
+
"num_train_epochs": 1,
|
66 |
"save_steps": 1000,
|
67 |
+
"total_flos": 139514462208000.0,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c5807cfe87acd4ae9c18b97ae7cfab12413970c9e1a7acc835a180ce3eb0baa
|
3 |
size 4027
|