Upload folder using huggingface_hub
Browse files- pytorch_model-00001-of-00003.bin +1 -1
- pytorch_model-00002-of-00003.bin +1 -1
- pytorch_model-00003-of-00003.bin +1 -1
- trainer_state.json +678 -120
- training_args.bin +1 -1
pytorch_model-00001-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9877989586
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a374a9f1d01331767790359848209f2a896a799d7e4af25cea164e7bde00f111
|
3 |
size 9877989586
|
pytorch_model-00002-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9894801014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8334dd8394f8989710e613e3e5bec93abe3eb367b4c56be58b2d2b4100d269ec
|
3 |
size 9894801014
|
pytorch_model-00003-of-00003.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7180990649
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c149b4a60e50d9b2e1d032a0928746bebffdbe1fd1838d5d41059a1fba5860f
|
3 |
size 7180990649
|
trainer_state.json
CHANGED
@@ -1,241 +1,799 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
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.
|
12 |
-
"learning_rate":
|
13 |
-
"loss": 0.
|
14 |
"step": 1
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0.
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 0.
|
20 |
"step": 2
|
21 |
},
|
22 |
{
|
23 |
-
"epoch": 0.
|
24 |
-
"learning_rate":
|
25 |
-
"loss": 0.
|
26 |
"step": 3
|
27 |
},
|
28 |
{
|
29 |
-
"epoch": 0.
|
30 |
-
"learning_rate": 1.
|
31 |
-
"loss": 0.
|
32 |
"step": 4
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"learning_rate": 1.
|
37 |
-
"loss": 0.
|
38 |
"step": 5
|
39 |
},
|
40 |
{
|
41 |
-
"epoch": 0.
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 0.
|
44 |
"step": 6
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"learning_rate": 1.
|
49 |
-
"loss": 0.
|
50 |
"step": 7
|
51 |
},
|
52 |
{
|
53 |
-
"epoch": 0.
|
54 |
-
"learning_rate": 1.
|
55 |
-
"loss": 0.
|
56 |
"step": 8
|
57 |
},
|
58 |
{
|
59 |
-
"epoch": 0.
|
60 |
-
"learning_rate": 1.
|
61 |
-
"loss": 0.
|
62 |
"step": 9
|
63 |
},
|
64 |
{
|
65 |
-
"epoch": 0.
|
66 |
-
"learning_rate": 1.
|
67 |
-
"loss": 0.
|
68 |
"step": 10
|
69 |
},
|
70 |
{
|
71 |
-
"epoch": 0.
|
72 |
-
"learning_rate": 1.
|
73 |
-
"loss": 0.
|
74 |
"step": 11
|
75 |
},
|
76 |
{
|
77 |
-
"epoch": 0.
|
78 |
-
"learning_rate": 1.
|
79 |
-
"loss": 0.
|
80 |
"step": 12
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 0.
|
84 |
-
"learning_rate": 1.
|
85 |
-
"loss": 0.
|
86 |
"step": 13
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"learning_rate": 1.
|
91 |
-
"loss": 0.
|
92 |
"step": 14
|
93 |
},
|
94 |
{
|
95 |
-
"epoch": 0.
|
96 |
-
"learning_rate": 1.
|
97 |
-
"loss": 0.
|
98 |
"step": 15
|
99 |
},
|
100 |
{
|
101 |
-
"epoch": 0.
|
102 |
-
"learning_rate": 1.
|
103 |
-
"loss": 0.
|
104 |
"step": 16
|
105 |
},
|
106 |
{
|
107 |
-
"epoch": 0.
|
108 |
-
"learning_rate": 1.
|
109 |
-
"loss": 0.
|
110 |
"step": 17
|
111 |
},
|
112 |
{
|
113 |
-
"epoch": 0.
|
114 |
-
"learning_rate": 1.
|
115 |
-
"loss": 0.
|
116 |
"step": 18
|
117 |
},
|
118 |
{
|
119 |
-
"epoch":
|
120 |
-
"learning_rate":
|
121 |
-
"loss": 0.
|
122 |
"step": 19
|
123 |
},
|
124 |
{
|
125 |
-
"epoch":
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 0.
|
128 |
"step": 20
|
129 |
},
|
130 |
{
|
131 |
-
"epoch":
|
132 |
-
"learning_rate":
|
133 |
-
"loss": 0.
|
134 |
"step": 21
|
135 |
},
|
136 |
{
|
137 |
-
"epoch":
|
138 |
-
"learning_rate":
|
139 |
-
"loss": 0.
|
140 |
"step": 22
|
141 |
},
|
142 |
{
|
143 |
-
"epoch":
|
144 |
-
"learning_rate":
|
145 |
-
"loss": 0.
|
146 |
"step": 23
|
147 |
},
|
148 |
{
|
149 |
-
"epoch":
|
150 |
-
"learning_rate":
|
151 |
-
"loss": 0.
|
152 |
"step": 24
|
153 |
},
|
154 |
{
|
155 |
-
"epoch":
|
156 |
-
"learning_rate":
|
157 |
-
"loss": 0.
|
158 |
"step": 25
|
159 |
},
|
160 |
{
|
161 |
-
"epoch":
|
162 |
-
"learning_rate":
|
163 |
-
"loss": 0.
|
164 |
"step": 26
|
165 |
},
|
166 |
{
|
167 |
-
"epoch":
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 0.
|
170 |
"step": 27
|
171 |
},
|
172 |
{
|
173 |
-
"epoch":
|
174 |
-
"learning_rate":
|
175 |
-
"loss": 0.
|
176 |
"step": 28
|
177 |
},
|
178 |
{
|
179 |
-
"epoch":
|
180 |
-
"learning_rate":
|
181 |
-
"loss": 0.
|
182 |
"step": 29
|
183 |
},
|
184 |
{
|
185 |
-
"epoch":
|
186 |
-
"learning_rate": 1.
|
187 |
-
"loss": 0.
|
188 |
"step": 30
|
189 |
},
|
190 |
{
|
191 |
-
"epoch":
|
192 |
-
"learning_rate": 1.
|
193 |
-
"loss": 0.
|
194 |
"step": 31
|
195 |
},
|
196 |
{
|
197 |
-
"epoch":
|
198 |
-
"learning_rate":
|
199 |
-
"loss": 0.
|
200 |
"step": 32
|
201 |
},
|
202 |
{
|
203 |
-
"epoch":
|
204 |
-
"learning_rate":
|
205 |
-
"loss": 0.
|
206 |
"step": 33
|
207 |
},
|
208 |
{
|
209 |
-
"epoch":
|
210 |
-
"learning_rate": 1.
|
211 |
-
"loss": 0.
|
212 |
"step": 34
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"learning_rate":
|
217 |
-
"loss": 0.
|
218 |
"step": 35
|
219 |
},
|
220 |
{
|
221 |
-
"epoch":
|
222 |
-
"learning_rate":
|
223 |
-
"loss": 0.
|
224 |
"step": 36
|
225 |
},
|
226 |
{
|
227 |
-
"epoch":
|
228 |
-
"
|
229 |
-
"
|
230 |
-
"
|
231 |
-
|
232 |
-
|
233 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
-
"max_steps":
|
237 |
-
"num_train_epochs":
|
238 |
-
"total_flos":
|
239 |
"trial_name": null,
|
240 |
"trial_params": null
|
241 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9961389961389961,
|
5 |
+
"global_step": 129,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 3.3333333333333333e-06,
|
13 |
+
"loss": 0.285,
|
14 |
"step": 1
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 6.666666666666667e-06,
|
19 |
+
"loss": 0.2933,
|
20 |
"step": 2
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 1e-05,
|
25 |
+
"loss": 0.2853,
|
26 |
"step": 3
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 0.03,
|
30 |
+
"learning_rate": 1.3333333333333333e-05,
|
31 |
+
"loss": 0.2804,
|
32 |
"step": 4
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.04,
|
36 |
+
"learning_rate": 1.6666666666666667e-05,
|
37 |
+
"loss": 0.2834,
|
38 |
"step": 5
|
39 |
},
|
40 |
{
|
41 |
+
"epoch": 0.05,
|
42 |
+
"learning_rate": 2e-05,
|
43 |
+
"loss": 0.2805,
|
44 |
"step": 6
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.05,
|
48 |
+
"learning_rate": 1.9996738360808566e-05,
|
49 |
+
"loss": 0.2805,
|
50 |
"step": 7
|
51 |
},
|
52 |
{
|
53 |
+
"epoch": 0.06,
|
54 |
+
"learning_rate": 1.9986955570892302e-05,
|
55 |
+
"loss": 0.2906,
|
56 |
"step": 8
|
57 |
},
|
58 |
{
|
59 |
+
"epoch": 0.07,
|
60 |
+
"learning_rate": 1.9970658011837404e-05,
|
61 |
+
"loss": 0.2822,
|
62 |
"step": 9
|
63 |
},
|
64 |
{
|
65 |
+
"epoch": 0.08,
|
66 |
+
"learning_rate": 1.994785631499535e-05,
|
67 |
+
"loss": 0.2994,
|
68 |
"step": 10
|
69 |
},
|
70 |
{
|
71 |
+
"epoch": 0.08,
|
72 |
+
"learning_rate": 1.9918565354547738e-05,
|
73 |
+
"loss": 0.3013,
|
74 |
"step": 11
|
75 |
},
|
76 |
{
|
77 |
+
"epoch": 0.09,
|
78 |
+
"learning_rate": 1.9882804237803487e-05,
|
79 |
+
"loss": 0.2954,
|
80 |
"step": 12
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 0.1,
|
84 |
+
"learning_rate": 1.9840596292734573e-05,
|
85 |
+
"loss": 0.2929,
|
86 |
"step": 13
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.11,
|
90 |
+
"learning_rate": 1.9791969052758563e-05,
|
91 |
+
"loss": 0.2956,
|
92 |
"step": 14
|
93 |
},
|
94 |
{
|
95 |
+
"epoch": 0.12,
|
96 |
+
"learning_rate": 1.9736954238777793e-05,
|
97 |
+
"loss": 0.3002,
|
98 |
"step": 15
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 0.12,
|
102 |
+
"learning_rate": 1.9675587738486935e-05,
|
103 |
+
"loss": 0.2918,
|
104 |
"step": 16
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 0.13,
|
108 |
+
"learning_rate": 1.9607909582962478e-05,
|
109 |
+
"loss": 0.2791,
|
110 |
"step": 17
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 0.14,
|
114 |
+
"learning_rate": 1.9533963920549307e-05,
|
115 |
+
"loss": 0.2777,
|
116 |
"step": 18
|
117 |
},
|
118 |
{
|
119 |
+
"epoch": 0.15,
|
120 |
+
"learning_rate": 1.9453798988061535e-05,
|
121 |
+
"loss": 0.2885,
|
122 |
"step": 19
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 0.15,
|
126 |
+
"learning_rate": 1.936746707931628e-05,
|
127 |
+
"loss": 0.2957,
|
128 |
"step": 20
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.16,
|
132 |
+
"learning_rate": 1.927502451102095e-05,
|
133 |
+
"loss": 0.2913,
|
134 |
"step": 21
|
135 |
},
|
136 |
{
|
137 |
+
"epoch": 0.17,
|
138 |
+
"learning_rate": 1.9176531586036282e-05,
|
139 |
+
"loss": 0.2945,
|
140 |
"step": 22
|
141 |
},
|
142 |
{
|
143 |
+
"epoch": 0.18,
|
144 |
+
"learning_rate": 1.9072052554039123e-05,
|
145 |
+
"loss": 0.2802,
|
146 |
"step": 23
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 0.19,
|
150 |
+
"learning_rate": 1.8961655569610557e-05,
|
151 |
+
"loss": 0.2885,
|
152 |
"step": 24
|
153 |
},
|
154 |
{
|
155 |
+
"epoch": 0.19,
|
156 |
+
"learning_rate": 1.8845412647776795e-05,
|
157 |
+
"loss": 0.2888,
|
158 |
"step": 25
|
159 |
},
|
160 |
{
|
161 |
+
"epoch": 0.2,
|
162 |
+
"learning_rate": 1.8723399617031754e-05,
|
163 |
+
"loss": 0.2772,
|
164 |
"step": 26
|
165 |
},
|
166 |
{
|
167 |
+
"epoch": 0.21,
|
168 |
+
"learning_rate": 1.8595696069872013e-05,
|
169 |
+
"loss": 0.2705,
|
170 |
"step": 27
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 0.22,
|
174 |
+
"learning_rate": 1.8462385310876444e-05,
|
175 |
+
"loss": 0.2831,
|
176 |
"step": 28
|
177 |
},
|
178 |
{
|
179 |
+
"epoch": 0.22,
|
180 |
+
"learning_rate": 1.8323554302364273e-05,
|
181 |
+
"loss": 0.28,
|
182 |
"step": 29
|
183 |
},
|
184 |
{
|
185 |
+
"epoch": 0.23,
|
186 |
+
"learning_rate": 1.8179293607667177e-05,
|
187 |
+
"loss": 0.28,
|
188 |
"step": 30
|
189 |
},
|
190 |
{
|
191 |
+
"epoch": 0.24,
|
192 |
+
"learning_rate": 1.8029697332052277e-05,
|
193 |
+
"loss": 0.2819,
|
194 |
"step": 31
|
195 |
},
|
196 |
{
|
197 |
+
"epoch": 0.25,
|
198 |
+
"learning_rate": 1.7874863061334658e-05,
|
199 |
+
"loss": 0.2847,
|
200 |
"step": 32
|
201 |
},
|
202 |
{
|
203 |
+
"epoch": 0.25,
|
204 |
+
"learning_rate": 1.7714891798219432e-05,
|
205 |
+
"loss": 0.2809,
|
206 |
"step": 33
|
207 |
},
|
208 |
{
|
209 |
+
"epoch": 0.26,
|
210 |
+
"learning_rate": 1.7549887896414853e-05,
|
211 |
+
"loss": 0.2666,
|
212 |
"step": 34
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 0.27,
|
216 |
+
"learning_rate": 1.7379958992559494e-05,
|
217 |
+
"loss": 0.2837,
|
218 |
"step": 35
|
219 |
},
|
220 |
{
|
221 |
+
"epoch": 0.28,
|
222 |
+
"learning_rate": 1.720521593600787e-05,
|
223 |
+
"loss": 0.2822,
|
224 |
"step": 36
|
225 |
},
|
226 |
{
|
227 |
+
"epoch": 0.29,
|
228 |
+
"learning_rate": 1.7025772716520324e-05,
|
229 |
+
"loss": 0.2764,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.29,
|
234 |
+
"learning_rate": 1.6841746389904306e-05,
|
235 |
+
"loss": 0.2795,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.3,
|
240 |
+
"learning_rate": 1.6653257001655652e-05,
|
241 |
+
"loss": 0.2686,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.31,
|
246 |
+
"learning_rate": 1.6460427508649546e-05,
|
247 |
+
"loss": 0.2655,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.32,
|
252 |
+
"learning_rate": 1.6263383698932307e-05,
|
253 |
+
"loss": 0.2715,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.32,
|
258 |
+
"learning_rate": 1.6062254109666383e-05,
|
259 |
+
"loss": 0.276,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.33,
|
264 |
+
"learning_rate": 1.5857169943281948e-05,
|
265 |
+
"loss": 0.274,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.34,
|
270 |
+
"learning_rate": 1.5648264981889936e-05,
|
271 |
+
"loss": 0.2831,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.35,
|
276 |
+
"learning_rate": 1.5435675500012212e-05,
|
277 |
+
"loss": 0.2685,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.36,
|
282 |
+
"learning_rate": 1.5219540175685938e-05,
|
283 |
+
"loss": 0.2746,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.36,
|
288 |
+
"learning_rate": 1.5000000000000002e-05,
|
289 |
+
"loss": 0.2624,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.37,
|
294 |
+
"learning_rate": 1.477719818512263e-05,
|
295 |
+
"loss": 0.2709,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.38,
|
300 |
+
"learning_rate": 1.4551280070880089e-05,
|
301 |
+
"loss": 0.2801,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.39,
|
306 |
+
"learning_rate": 1.432239302994747e-05,
|
307 |
+
"loss": 0.2724,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.39,
|
312 |
+
"learning_rate": 1.4090686371713403e-05,
|
313 |
+
"loss": 0.2661,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.4,
|
318 |
+
"learning_rate": 1.385631124488136e-05,
|
319 |
+
"loss": 0.262,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.41,
|
324 |
+
"learning_rate": 1.361942053887118e-05,
|
325 |
+
"loss": 0.2653,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.42,
|
330 |
+
"learning_rate": 1.3380168784085028e-05,
|
331 |
+
"loss": 0.2618,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.42,
|
336 |
+
"learning_rate": 1.3138712051102908e-05,
|
337 |
+
"loss": 0.2619,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.43,
|
342 |
+
"learning_rate": 1.2895207848873488e-05,
|
343 |
+
"loss": 0.2597,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.44,
|
348 |
+
"learning_rate": 1.264981502196662e-05,
|
349 |
+
"loss": 0.2592,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.45,
|
354 |
+
"learning_rate": 1.2402693646954607e-05,
|
355 |
+
"loss": 0.2658,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.46,
|
360 |
+
"learning_rate": 1.2154004927989815e-05,
|
361 |
+
"loss": 0.2535,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.46,
|
366 |
+
"learning_rate": 1.1903911091646684e-05,
|
367 |
+
"loss": 0.2711,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.47,
|
372 |
+
"learning_rate": 1.165257528109685e-05,
|
373 |
+
"loss": 0.2601,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.48,
|
378 |
+
"learning_rate": 1.1400161449686293e-05,
|
379 |
+
"loss": 0.2532,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.49,
|
384 |
+
"learning_rate": 1.1146834253984008e-05,
|
385 |
+
"loss": 0.2621,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.49,
|
390 |
+
"learning_rate": 1.0892758946371943e-05,
|
391 |
+
"loss": 0.2612,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.5,
|
396 |
+
"learning_rate": 1.0638101267246283e-05,
|
397 |
+
"loss": 0.2521,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.51,
|
402 |
+
"learning_rate": 1.0383027336900356e-05,
|
403 |
+
"loss": 0.2611,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.52,
|
408 |
+
"learning_rate": 1.012770354715974e-05,
|
409 |
+
"loss": 0.256,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.53,
|
414 |
+
"learning_rate": 9.872296452840266e-06,
|
415 |
+
"loss": 0.2584,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.53,
|
420 |
+
"learning_rate": 9.616972663099648e-06,
|
421 |
+
"loss": 0.2502,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.54,
|
426 |
+
"learning_rate": 9.361898732753715e-06,
|
427 |
+
"loss": 0.2384,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.55,
|
432 |
+
"learning_rate": 9.107241053628058e-06,
|
433 |
+
"loss": 0.258,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.56,
|
438 |
+
"learning_rate": 8.853165746015997e-06,
|
439 |
+
"loss": 0.2536,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.56,
|
444 |
+
"learning_rate": 8.599838550313714e-06,
|
445 |
+
"loss": 0.263,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.57,
|
450 |
+
"learning_rate": 8.347424718903152e-06,
|
451 |
+
"loss": 0.247,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.58,
|
456 |
+
"learning_rate": 8.096088908353316e-06,
|
457 |
+
"loss": 0.2523,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.59,
|
462 |
+
"learning_rate": 7.845995072010188e-06,
|
463 |
+
"loss": 0.2454,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.59,
|
468 |
+
"learning_rate": 7.597306353045393e-06,
|
469 |
+
"loss": 0.2618,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.6,
|
474 |
+
"learning_rate": 7.350184978033386e-06,
|
475 |
+
"loss": 0.2536,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.61,
|
480 |
+
"learning_rate": 7.104792151126515e-06,
|
481 |
+
"loss": 0.2454,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.62,
|
486 |
+
"learning_rate": 6.861287948897091e-06,
|
487 |
+
"loss": 0.2636,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.63,
|
492 |
+
"learning_rate": 6.619831215914974e-06,
|
493 |
+
"loss": 0.2415,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.63,
|
498 |
+
"learning_rate": 6.38057946112882e-06,
|
499 |
+
"loss": 0.2415,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.64,
|
504 |
+
"learning_rate": 6.1436887551186466e-06,
|
505 |
+
"loss": 0.248,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.65,
|
510 |
+
"learning_rate": 5.9093136282866014e-06,
|
511 |
+
"loss": 0.247,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.66,
|
516 |
+
"learning_rate": 5.67760697005253e-06,
|
517 |
+
"loss": 0.245,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.66,
|
522 |
+
"learning_rate": 5.448719929119916e-06,
|
523 |
+
"loss": 0.2298,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.67,
|
528 |
+
"learning_rate": 5.22280181487737e-06,
|
529 |
+
"loss": 0.2465,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.68,
|
534 |
+
"learning_rate": 5.000000000000003e-06,
|
535 |
+
"loss": 0.2403,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.69,
|
540 |
+
"learning_rate": 4.7804598243140664e-06,
|
541 |
+
"loss": 0.242,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.69,
|
546 |
+
"learning_rate": 4.56432449998779e-06,
|
547 |
+
"loss": 0.2402,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.7,
|
552 |
+
"learning_rate": 4.351735018110066e-06,
|
553 |
+
"loss": 0.2423,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.71,
|
558 |
+
"learning_rate": 4.142830056718052e-06,
|
559 |
+
"loss": 0.2453,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.72,
|
564 |
+
"learning_rate": 3.937745890333623e-06,
|
565 |
+
"loss": 0.2467,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.73,
|
570 |
+
"learning_rate": 3.7366163010676937e-06,
|
571 |
+
"loss": 0.2354,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.73,
|
576 |
+
"learning_rate": 3.5395724913504546e-06,
|
577 |
+
"loss": 0.2497,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.74,
|
582 |
+
"learning_rate": 3.3467429983443477e-06,
|
583 |
+
"loss": 0.2362,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.75,
|
588 |
+
"learning_rate": 3.1582536100956973e-06,
|
589 |
+
"loss": 0.2444,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.76,
|
594 |
+
"learning_rate": 2.9742272834796813e-06,
|
595 |
+
"loss": 0.2495,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.76,
|
600 |
+
"learning_rate": 2.7947840639921308e-06,
|
601 |
+
"loss": 0.2242,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.77,
|
606 |
+
"learning_rate": 2.620041007440508e-06,
|
607 |
+
"loss": 0.2356,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.78,
|
612 |
+
"learning_rate": 2.4501121035851494e-06,
|
613 |
+
"loss": 0.2369,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.79,
|
618 |
+
"learning_rate": 2.2851082017805704e-06,
|
619 |
+
"loss": 0.2424,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 0.8,
|
624 |
+
"learning_rate": 2.1251369386653454e-06,
|
625 |
+
"loss": 0.248,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.8,
|
630 |
+
"learning_rate": 1.9703026679477253e-06,
|
631 |
+
"loss": 0.2354,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.81,
|
636 |
+
"learning_rate": 1.820706392332824e-06,
|
637 |
+
"loss": 0.2518,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 0.82,
|
642 |
+
"learning_rate": 1.6764456976357279e-06,
|
643 |
+
"loss": 0.2402,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.83,
|
648 |
+
"learning_rate": 1.53761468912356e-06,
|
649 |
+
"loss": 0.2509,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.83,
|
654 |
+
"learning_rate": 1.4043039301279904e-06,
|
655 |
+
"loss": 0.2446,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 0.84,
|
660 |
+
"learning_rate": 1.2766003829682504e-06,
|
661 |
+
"loss": 0.2343,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.85,
|
666 |
+
"learning_rate": 1.1545873522232055e-06,
|
667 |
+
"loss": 0.2363,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.86,
|
672 |
+
"learning_rate": 1.0383444303894453e-06,
|
673 |
+
"loss": 0.2332,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.86,
|
678 |
+
"learning_rate": 9.279474459608806e-07,
|
679 |
+
"loss": 0.2388,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.87,
|
684 |
+
"learning_rate": 8.234684139637205e-07,
|
685 |
+
"loss": 0.2414,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.88,
|
690 |
+
"learning_rate": 7.249754889790539e-07,
|
691 |
+
"loss": 0.2407,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 0.89,
|
696 |
+
"learning_rate": 6.325329206837217e-07,
|
697 |
+
"loss": 0.2363,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.9,
|
702 |
+
"learning_rate": 5.462010119384665e-07,
|
703 |
+
"loss": 0.2463,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.9,
|
708 |
+
"learning_rate": 4.660360794506946e-07,
|
709 |
+
"loss": 0.2328,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.91,
|
714 |
+
"learning_rate": 3.920904170375239e-07,
|
715 |
+
"loss": 0.2308,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.92,
|
720 |
+
"learning_rate": 3.2441226151306403e-07,
|
721 |
+
"loss": 0.2474,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.93,
|
726 |
+
"learning_rate": 2.6304576122221035e-07,
|
727 |
+
"loss": 0.2353,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 0.93,
|
732 |
+
"learning_rate": 2.0803094724143879e-07,
|
733 |
+
"loss": 0.2331,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.94,
|
738 |
+
"learning_rate": 1.5940370726542864e-07,
|
739 |
+
"loss": 0.2374,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.95,
|
744 |
+
"learning_rate": 1.1719576219651585e-07,
|
745 |
+
"loss": 0.2279,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.96,
|
750 |
+
"learning_rate": 8.143464545226298e-08,
|
751 |
+
"loss": 0.2498,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.97,
|
756 |
+
"learning_rate": 5.214368500465305e-08,
|
757 |
+
"loss": 0.2452,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.97,
|
762 |
+
"learning_rate": 2.9341988162595593e-08,
|
763 |
+
"loss": 0.2374,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 0.98,
|
768 |
+
"learning_rate": 1.3044429107700319e-08,
|
769 |
+
"loss": 0.2405,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.99,
|
774 |
+
"learning_rate": 3.2616391914364056e-09,
|
775 |
+
"loss": 0.246,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.0,
|
780 |
+
"learning_rate": 0.0,
|
781 |
+
"loss": 0.2311,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 1.0,
|
786 |
+
"step": 129,
|
787 |
+
"total_flos": 1.0254156470912287e+18,
|
788 |
+
"train_loss": 0.2606376674055129,
|
789 |
+
"train_runtime": 20090.4454,
|
790 |
+
"train_samples_per_second": 4.947,
|
791 |
+
"train_steps_per_second": 0.006
|
792 |
}
|
793 |
],
|
794 |
+
"max_steps": 129,
|
795 |
+
"num_train_epochs": 1,
|
796 |
+
"total_flos": 1.0254156470912287e+18,
|
797 |
"trial_name": null,
|
798 |
"trial_params": null
|
799 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86db5b26b025cde82a2aa084a23b6e7d928d912530cfff8a617c19f7aa56dafd
|
3 |
size 3771
|