End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.96,
|
3 |
+
"eval_accuracy": 0.8342792281498297,
|
4 |
+
"eval_loss": 0.48094892501831055,
|
5 |
+
"eval_runtime": 7.0271,
|
6 |
+
"eval_samples_per_second": 125.371,
|
7 |
+
"eval_steps_per_second": 15.796,
|
8 |
+
"total_flos": 1.6760839403221402e+18,
|
9 |
+
"train_loss": 0.9043752511342367,
|
10 |
+
"train_runtime": 8036.8099,
|
11 |
+
"train_samples_per_second": 9.858,
|
12 |
+
"train_steps_per_second": 0.175
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.96,
|
3 |
+
"eval_accuracy": 0.8342792281498297,
|
4 |
+
"eval_loss": 0.48094892501831055,
|
5 |
+
"eval_runtime": 7.0271,
|
6 |
+
"eval_samples_per_second": 125.371,
|
7 |
+
"eval_steps_per_second": 15.796
|
8 |
+
}
|
runs/May06_17-13-04_cfa7f4cd76a3/events.out.tfevents.1683401257.cfa7f4cd76a3.950.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9599f7d1d292137eda3ac0ad800dbe762e101b5702a769fcbcba7b5f0dd6d38
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.96,
|
3 |
+
"total_flos": 1.6760839403221402e+18,
|
4 |
+
"train_loss": 0.9043752511342367,
|
5 |
+
"train_runtime": 8036.8099,
|
6 |
+
"train_samples_per_second": 9.858,
|
7 |
+
"train_steps_per_second": 0.175
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,961 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8342792281498297,
|
3 |
+
"best_model_checkpoint": "resnet-50-bottomCleanedData/checkpoint-1410",
|
4 |
+
"epoch": 9.959636730575177,
|
5 |
+
"global_step": 1410,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 3.3333333333333335e-05,
|
13 |
+
"loss": 1.3868,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.14,
|
18 |
+
"learning_rate": 4.982078853046595e-05,
|
19 |
+
"loss": 1.3831,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.21,
|
24 |
+
"learning_rate": 4.9462365591397855e-05,
|
25 |
+
"loss": 1.3793,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.28,
|
30 |
+
"learning_rate": 4.910394265232976e-05,
|
31 |
+
"loss": 1.3799,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.35,
|
36 |
+
"learning_rate": 4.874551971326165e-05,
|
37 |
+
"loss": 1.3732,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.42,
|
42 |
+
"learning_rate": 4.8387096774193554e-05,
|
43 |
+
"loss": 1.3681,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.49,
|
48 |
+
"learning_rate": 4.802867383512545e-05,
|
49 |
+
"loss": 1.3693,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.57,
|
54 |
+
"learning_rate": 4.767025089605735e-05,
|
55 |
+
"loss": 1.3644,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.64,
|
60 |
+
"learning_rate": 4.731182795698925e-05,
|
61 |
+
"loss": 1.3626,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.71,
|
66 |
+
"learning_rate": 4.695340501792115e-05,
|
67 |
+
"loss": 1.3576,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.78,
|
72 |
+
"learning_rate": 4.659498207885305e-05,
|
73 |
+
"loss": 1.348,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.85,
|
78 |
+
"learning_rate": 4.6236559139784944e-05,
|
79 |
+
"loss": 1.34,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.92,
|
84 |
+
"learning_rate": 4.5878136200716846e-05,
|
85 |
+
"loss": 1.3357,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.99,
|
90 |
+
"learning_rate": 4.551971326164875e-05,
|
91 |
+
"loss": 1.3235,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.0,
|
96 |
+
"eval_accuracy": 0.5096481271282634,
|
97 |
+
"eval_loss": 1.3266013860702515,
|
98 |
+
"eval_runtime": 648.045,
|
99 |
+
"eval_samples_per_second": 1.359,
|
100 |
+
"eval_steps_per_second": 0.171,
|
101 |
+
"step": 141
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.06,
|
105 |
+
"learning_rate": 4.516129032258064e-05,
|
106 |
+
"loss": 1.3128,
|
107 |
+
"step": 150
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.13,
|
111 |
+
"learning_rate": 4.4802867383512545e-05,
|
112 |
+
"loss": 1.311,
|
113 |
+
"step": 160
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.2,
|
117 |
+
"learning_rate": 4.4444444444444447e-05,
|
118 |
+
"loss": 1.2957,
|
119 |
+
"step": 170
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.27,
|
123 |
+
"learning_rate": 4.408602150537635e-05,
|
124 |
+
"loss": 1.2956,
|
125 |
+
"step": 180
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.34,
|
129 |
+
"learning_rate": 4.372759856630825e-05,
|
130 |
+
"loss": 1.2798,
|
131 |
+
"step": 190
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.41,
|
135 |
+
"learning_rate": 4.3369175627240145e-05,
|
136 |
+
"loss": 1.2693,
|
137 |
+
"step": 200
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.48,
|
141 |
+
"learning_rate": 4.301075268817205e-05,
|
142 |
+
"loss": 1.265,
|
143 |
+
"step": 210
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.55,
|
147 |
+
"learning_rate": 4.265232974910394e-05,
|
148 |
+
"loss": 1.2554,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.62,
|
153 |
+
"learning_rate": 4.2293906810035844e-05,
|
154 |
+
"loss": 1.2435,
|
155 |
+
"step": 230
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 1.7,
|
159 |
+
"learning_rate": 4.1935483870967746e-05,
|
160 |
+
"loss": 1.2251,
|
161 |
+
"step": 240
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 1.77,
|
165 |
+
"learning_rate": 4.157706093189964e-05,
|
166 |
+
"loss": 1.2136,
|
167 |
+
"step": 250
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 1.84,
|
171 |
+
"learning_rate": 4.121863799283154e-05,
|
172 |
+
"loss": 1.1784,
|
173 |
+
"step": 260
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 1.91,
|
177 |
+
"learning_rate": 4.0860215053763444e-05,
|
178 |
+
"loss": 1.1691,
|
179 |
+
"step": 270
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.98,
|
183 |
+
"learning_rate": 4.050179211469534e-05,
|
184 |
+
"loss": 1.1546,
|
185 |
+
"step": 280
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.0,
|
189 |
+
"eval_accuracy": 0.5153234960272418,
|
190 |
+
"eval_loss": 1.1380490064620972,
|
191 |
+
"eval_runtime": 7.1826,
|
192 |
+
"eval_samples_per_second": 122.658,
|
193 |
+
"eval_steps_per_second": 15.454,
|
194 |
+
"step": 283
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.05,
|
198 |
+
"learning_rate": 4.014336917562724e-05,
|
199 |
+
"loss": 1.1353,
|
200 |
+
"step": 290
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.12,
|
204 |
+
"learning_rate": 3.978494623655914e-05,
|
205 |
+
"loss": 1.1329,
|
206 |
+
"step": 300
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.19,
|
210 |
+
"learning_rate": 3.9426523297491045e-05,
|
211 |
+
"loss": 1.1246,
|
212 |
+
"step": 310
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.26,
|
216 |
+
"learning_rate": 3.906810035842295e-05,
|
217 |
+
"loss": 1.0971,
|
218 |
+
"step": 320
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.33,
|
222 |
+
"learning_rate": 3.870967741935484e-05,
|
223 |
+
"loss": 1.0763,
|
224 |
+
"step": 330
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.4,
|
228 |
+
"learning_rate": 3.8351254480286743e-05,
|
229 |
+
"loss": 1.0741,
|
230 |
+
"step": 340
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.47,
|
234 |
+
"learning_rate": 3.799283154121864e-05,
|
235 |
+
"loss": 1.0241,
|
236 |
+
"step": 350
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.54,
|
240 |
+
"learning_rate": 3.763440860215054e-05,
|
241 |
+
"loss": 1.0103,
|
242 |
+
"step": 360
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.61,
|
246 |
+
"learning_rate": 3.727598566308244e-05,
|
247 |
+
"loss": 1.0049,
|
248 |
+
"step": 370
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.68,
|
252 |
+
"learning_rate": 3.691756272401434e-05,
|
253 |
+
"loss": 0.9883,
|
254 |
+
"step": 380
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.75,
|
258 |
+
"learning_rate": 3.655913978494624e-05,
|
259 |
+
"loss": 0.9864,
|
260 |
+
"step": 390
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.83,
|
264 |
+
"learning_rate": 3.6200716845878134e-05,
|
265 |
+
"loss": 0.9871,
|
266 |
+
"step": 400
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.9,
|
270 |
+
"learning_rate": 3.5842293906810036e-05,
|
271 |
+
"loss": 0.9547,
|
272 |
+
"step": 410
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.97,
|
276 |
+
"learning_rate": 3.548387096774194e-05,
|
277 |
+
"loss": 0.9412,
|
278 |
+
"step": 420
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.99,
|
282 |
+
"eval_accuracy": 0.6515323496027242,
|
283 |
+
"eval_loss": 0.8690479397773743,
|
284 |
+
"eval_runtime": 6.9421,
|
285 |
+
"eval_samples_per_second": 126.907,
|
286 |
+
"eval_steps_per_second": 15.989,
|
287 |
+
"step": 424
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 3.04,
|
291 |
+
"learning_rate": 3.512544802867383e-05,
|
292 |
+
"loss": 0.9049,
|
293 |
+
"step": 430
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 3.11,
|
297 |
+
"learning_rate": 3.4767025089605734e-05,
|
298 |
+
"loss": 0.9843,
|
299 |
+
"step": 440
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 3.18,
|
303 |
+
"learning_rate": 3.4408602150537636e-05,
|
304 |
+
"loss": 0.9074,
|
305 |
+
"step": 450
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 3.25,
|
309 |
+
"learning_rate": 3.405017921146954e-05,
|
310 |
+
"loss": 0.9251,
|
311 |
+
"step": 460
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 3.32,
|
315 |
+
"learning_rate": 3.369175627240144e-05,
|
316 |
+
"loss": 0.9401,
|
317 |
+
"step": 470
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.39,
|
321 |
+
"learning_rate": 3.3333333333333335e-05,
|
322 |
+
"loss": 0.907,
|
323 |
+
"step": 480
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 3.46,
|
327 |
+
"learning_rate": 3.297491039426524e-05,
|
328 |
+
"loss": 0.909,
|
329 |
+
"step": 490
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 3.53,
|
333 |
+
"learning_rate": 3.261648745519714e-05,
|
334 |
+
"loss": 0.8676,
|
335 |
+
"step": 500
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 3.6,
|
339 |
+
"learning_rate": 3.2258064516129034e-05,
|
340 |
+
"loss": 0.8435,
|
341 |
+
"step": 510
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 3.67,
|
345 |
+
"learning_rate": 3.1899641577060935e-05,
|
346 |
+
"loss": 0.8634,
|
347 |
+
"step": 520
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 3.74,
|
351 |
+
"learning_rate": 3.154121863799283e-05,
|
352 |
+
"loss": 0.8802,
|
353 |
+
"step": 530
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 3.81,
|
357 |
+
"learning_rate": 3.118279569892473e-05,
|
358 |
+
"loss": 0.8687,
|
359 |
+
"step": 540
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.88,
|
363 |
+
"learning_rate": 3.0824372759856634e-05,
|
364 |
+
"loss": 0.8587,
|
365 |
+
"step": 550
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 3.96,
|
369 |
+
"learning_rate": 3.046594982078853e-05,
|
370 |
+
"loss": 0.8539,
|
371 |
+
"step": 560
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 4.0,
|
375 |
+
"eval_accuracy": 0.7593643586833144,
|
376 |
+
"eval_loss": 0.6672292351722717,
|
377 |
+
"eval_runtime": 7.0907,
|
378 |
+
"eval_samples_per_second": 124.247,
|
379 |
+
"eval_steps_per_second": 15.654,
|
380 |
+
"step": 566
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.03,
|
384 |
+
"learning_rate": 3.010752688172043e-05,
|
385 |
+
"loss": 0.8467,
|
386 |
+
"step": 570
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.1,
|
390 |
+
"learning_rate": 2.974910394265233e-05,
|
391 |
+
"loss": 0.8657,
|
392 |
+
"step": 580
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.17,
|
396 |
+
"learning_rate": 2.939068100358423e-05,
|
397 |
+
"loss": 0.8671,
|
398 |
+
"step": 590
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.24,
|
402 |
+
"learning_rate": 2.9032258064516133e-05,
|
403 |
+
"loss": 0.814,
|
404 |
+
"step": 600
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.31,
|
408 |
+
"learning_rate": 2.8673835125448028e-05,
|
409 |
+
"loss": 0.8287,
|
410 |
+
"step": 610
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 4.38,
|
414 |
+
"learning_rate": 2.831541218637993e-05,
|
415 |
+
"loss": 0.8733,
|
416 |
+
"step": 620
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 4.45,
|
420 |
+
"learning_rate": 2.7956989247311828e-05,
|
421 |
+
"loss": 0.8241,
|
422 |
+
"step": 630
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.52,
|
426 |
+
"learning_rate": 2.759856630824373e-05,
|
427 |
+
"loss": 0.8157,
|
428 |
+
"step": 640
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 4.59,
|
432 |
+
"learning_rate": 2.7240143369175632e-05,
|
433 |
+
"loss": 0.8597,
|
434 |
+
"step": 650
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 4.66,
|
438 |
+
"learning_rate": 2.6881720430107527e-05,
|
439 |
+
"loss": 0.8599,
|
440 |
+
"step": 660
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 4.73,
|
444 |
+
"learning_rate": 2.652329749103943e-05,
|
445 |
+
"loss": 0.7635,
|
446 |
+
"step": 670
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 4.8,
|
450 |
+
"learning_rate": 2.616487455197133e-05,
|
451 |
+
"loss": 0.8585,
|
452 |
+
"step": 680
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 4.87,
|
456 |
+
"learning_rate": 2.5806451612903226e-05,
|
457 |
+
"loss": 0.8159,
|
458 |
+
"step": 690
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 4.94,
|
462 |
+
"learning_rate": 2.5448028673835127e-05,
|
463 |
+
"loss": 0.7967,
|
464 |
+
"step": 700
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 4.99,
|
468 |
+
"eval_accuracy": 0.7502837684449489,
|
469 |
+
"eval_loss": 0.625583827495575,
|
470 |
+
"eval_runtime": 7.1065,
|
471 |
+
"eval_samples_per_second": 123.971,
|
472 |
+
"eval_steps_per_second": 15.62,
|
473 |
+
"step": 707
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 5.02,
|
477 |
+
"learning_rate": 2.5089605734767026e-05,
|
478 |
+
"loss": 0.807,
|
479 |
+
"step": 710
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 5.09,
|
483 |
+
"learning_rate": 2.4731182795698928e-05,
|
484 |
+
"loss": 0.8029,
|
485 |
+
"step": 720
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 5.16,
|
489 |
+
"learning_rate": 2.4372759856630826e-05,
|
490 |
+
"loss": 0.7848,
|
491 |
+
"step": 730
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 5.23,
|
495 |
+
"learning_rate": 2.4014336917562724e-05,
|
496 |
+
"loss": 0.7913,
|
497 |
+
"step": 740
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 5.3,
|
501 |
+
"learning_rate": 2.3655913978494626e-05,
|
502 |
+
"loss": 0.8001,
|
503 |
+
"step": 750
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 5.37,
|
507 |
+
"learning_rate": 2.3297491039426525e-05,
|
508 |
+
"loss": 0.7831,
|
509 |
+
"step": 760
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 5.44,
|
513 |
+
"learning_rate": 2.2939068100358423e-05,
|
514 |
+
"loss": 0.8103,
|
515 |
+
"step": 770
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 5.51,
|
519 |
+
"learning_rate": 2.258064516129032e-05,
|
520 |
+
"loss": 0.7803,
|
521 |
+
"step": 780
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 5.58,
|
525 |
+
"learning_rate": 2.2222222222222223e-05,
|
526 |
+
"loss": 0.7639,
|
527 |
+
"step": 790
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 5.65,
|
531 |
+
"learning_rate": 2.1863799283154125e-05,
|
532 |
+
"loss": 0.7671,
|
533 |
+
"step": 800
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 5.72,
|
537 |
+
"learning_rate": 2.1505376344086024e-05,
|
538 |
+
"loss": 0.7457,
|
539 |
+
"step": 810
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 5.79,
|
543 |
+
"learning_rate": 2.1146953405017922e-05,
|
544 |
+
"loss": 0.8118,
|
545 |
+
"step": 820
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 5.86,
|
549 |
+
"learning_rate": 2.078853046594982e-05,
|
550 |
+
"loss": 0.7935,
|
551 |
+
"step": 830
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 5.93,
|
555 |
+
"learning_rate": 2.0430107526881722e-05,
|
556 |
+
"loss": 0.7679,
|
557 |
+
"step": 840
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 6.0,
|
561 |
+
"eval_accuracy": 0.8229284903518729,
|
562 |
+
"eval_loss": 0.5356738567352295,
|
563 |
+
"eval_runtime": 6.9588,
|
564 |
+
"eval_samples_per_second": 126.603,
|
565 |
+
"eval_steps_per_second": 15.951,
|
566 |
+
"step": 849
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 6.0,
|
570 |
+
"learning_rate": 2.007168458781362e-05,
|
571 |
+
"loss": 0.804,
|
572 |
+
"step": 850
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 6.07,
|
576 |
+
"learning_rate": 1.9713261648745522e-05,
|
577 |
+
"loss": 0.7701,
|
578 |
+
"step": 860
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 6.15,
|
582 |
+
"learning_rate": 1.935483870967742e-05,
|
583 |
+
"loss": 0.7442,
|
584 |
+
"step": 870
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 6.22,
|
588 |
+
"learning_rate": 1.899641577060932e-05,
|
589 |
+
"loss": 0.7167,
|
590 |
+
"step": 880
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 6.29,
|
594 |
+
"learning_rate": 1.863799283154122e-05,
|
595 |
+
"loss": 0.7309,
|
596 |
+
"step": 890
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 6.36,
|
600 |
+
"learning_rate": 1.827956989247312e-05,
|
601 |
+
"loss": 0.7587,
|
602 |
+
"step": 900
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 6.43,
|
606 |
+
"learning_rate": 1.7921146953405018e-05,
|
607 |
+
"loss": 0.781,
|
608 |
+
"step": 910
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 6.5,
|
612 |
+
"learning_rate": 1.7562724014336916e-05,
|
613 |
+
"loss": 0.785,
|
614 |
+
"step": 920
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 6.57,
|
618 |
+
"learning_rate": 1.7204301075268818e-05,
|
619 |
+
"loss": 0.7486,
|
620 |
+
"step": 930
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 6.64,
|
624 |
+
"learning_rate": 1.684587813620072e-05,
|
625 |
+
"loss": 0.7597,
|
626 |
+
"step": 940
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 6.71,
|
630 |
+
"learning_rate": 1.648745519713262e-05,
|
631 |
+
"loss": 0.6813,
|
632 |
+
"step": 950
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 6.78,
|
636 |
+
"learning_rate": 1.6129032258064517e-05,
|
637 |
+
"loss": 0.75,
|
638 |
+
"step": 960
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 6.85,
|
642 |
+
"learning_rate": 1.5770609318996415e-05,
|
643 |
+
"loss": 0.7543,
|
644 |
+
"step": 970
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 6.92,
|
648 |
+
"learning_rate": 1.5412186379928317e-05,
|
649 |
+
"loss": 0.7112,
|
650 |
+
"step": 980
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 6.99,
|
654 |
+
"learning_rate": 1.5053763440860215e-05,
|
655 |
+
"loss": 0.7265,
|
656 |
+
"step": 990
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 7.0,
|
660 |
+
"eval_accuracy": 0.7832009080590239,
|
661 |
+
"eval_loss": 0.5698212385177612,
|
662 |
+
"eval_runtime": 7.061,
|
663 |
+
"eval_samples_per_second": 124.77,
|
664 |
+
"eval_steps_per_second": 15.72,
|
665 |
+
"step": 991
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 7.06,
|
669 |
+
"learning_rate": 1.4695340501792116e-05,
|
670 |
+
"loss": 0.7152,
|
671 |
+
"step": 1000
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 7.13,
|
675 |
+
"learning_rate": 1.4336917562724014e-05,
|
676 |
+
"loss": 0.742,
|
677 |
+
"step": 1010
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 7.2,
|
681 |
+
"learning_rate": 1.3978494623655914e-05,
|
682 |
+
"loss": 0.742,
|
683 |
+
"step": 1020
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 7.28,
|
687 |
+
"learning_rate": 1.3620071684587816e-05,
|
688 |
+
"loss": 0.7282,
|
689 |
+
"step": 1030
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 7.35,
|
693 |
+
"learning_rate": 1.3261648745519714e-05,
|
694 |
+
"loss": 0.7105,
|
695 |
+
"step": 1040
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 7.42,
|
699 |
+
"learning_rate": 1.2903225806451613e-05,
|
700 |
+
"loss": 0.7683,
|
701 |
+
"step": 1050
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 7.49,
|
705 |
+
"learning_rate": 1.2544802867383513e-05,
|
706 |
+
"loss": 0.7343,
|
707 |
+
"step": 1060
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 7.56,
|
711 |
+
"learning_rate": 1.2186379928315413e-05,
|
712 |
+
"loss": 0.6884,
|
713 |
+
"step": 1070
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 7.63,
|
717 |
+
"learning_rate": 1.1827956989247313e-05,
|
718 |
+
"loss": 0.7065,
|
719 |
+
"step": 1080
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 7.7,
|
723 |
+
"learning_rate": 1.1469534050179212e-05,
|
724 |
+
"loss": 0.6961,
|
725 |
+
"step": 1090
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 7.77,
|
729 |
+
"learning_rate": 1.1111111111111112e-05,
|
730 |
+
"loss": 0.7079,
|
731 |
+
"step": 1100
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 7.84,
|
735 |
+
"learning_rate": 1.0752688172043012e-05,
|
736 |
+
"loss": 0.7012,
|
737 |
+
"step": 1110
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 7.91,
|
741 |
+
"learning_rate": 1.039426523297491e-05,
|
742 |
+
"loss": 0.633,
|
743 |
+
"step": 1120
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 7.98,
|
747 |
+
"learning_rate": 1.003584229390681e-05,
|
748 |
+
"loss": 0.7395,
|
749 |
+
"step": 1130
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 8.0,
|
753 |
+
"eval_accuracy": 0.8161180476730987,
|
754 |
+
"eval_loss": 0.5125163197517395,
|
755 |
+
"eval_runtime": 6.6771,
|
756 |
+
"eval_samples_per_second": 131.944,
|
757 |
+
"eval_steps_per_second": 16.624,
|
758 |
+
"step": 1132
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 8.05,
|
762 |
+
"learning_rate": 9.67741935483871e-06,
|
763 |
+
"loss": 0.7309,
|
764 |
+
"step": 1140
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 8.12,
|
768 |
+
"learning_rate": 9.31899641577061e-06,
|
769 |
+
"loss": 0.6818,
|
770 |
+
"step": 1150
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 8.19,
|
774 |
+
"learning_rate": 8.960573476702509e-06,
|
775 |
+
"loss": 0.7509,
|
776 |
+
"step": 1160
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 8.26,
|
780 |
+
"learning_rate": 8.602150537634409e-06,
|
781 |
+
"loss": 0.679,
|
782 |
+
"step": 1170
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 8.34,
|
786 |
+
"learning_rate": 8.24372759856631e-06,
|
787 |
+
"loss": 0.7765,
|
788 |
+
"step": 1180
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 8.41,
|
792 |
+
"learning_rate": 7.885304659498208e-06,
|
793 |
+
"loss": 0.7271,
|
794 |
+
"step": 1190
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 8.48,
|
798 |
+
"learning_rate": 7.526881720430108e-06,
|
799 |
+
"loss": 0.6982,
|
800 |
+
"step": 1200
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 8.55,
|
804 |
+
"learning_rate": 7.168458781362007e-06,
|
805 |
+
"loss": 0.6922,
|
806 |
+
"step": 1210
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 8.62,
|
810 |
+
"learning_rate": 6.810035842293908e-06,
|
811 |
+
"loss": 0.7429,
|
812 |
+
"step": 1220
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 8.69,
|
816 |
+
"learning_rate": 6.451612903225806e-06,
|
817 |
+
"loss": 0.7055,
|
818 |
+
"step": 1230
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 8.76,
|
822 |
+
"learning_rate": 6.0931899641577065e-06,
|
823 |
+
"loss": 0.7341,
|
824 |
+
"step": 1240
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 8.83,
|
828 |
+
"learning_rate": 5.734767025089606e-06,
|
829 |
+
"loss": 0.7545,
|
830 |
+
"step": 1250
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 8.9,
|
834 |
+
"learning_rate": 5.376344086021506e-06,
|
835 |
+
"loss": 0.7029,
|
836 |
+
"step": 1260
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 8.97,
|
840 |
+
"learning_rate": 5.017921146953405e-06,
|
841 |
+
"loss": 0.7029,
|
842 |
+
"step": 1270
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 9.0,
|
846 |
+
"eval_accuracy": 0.8149829738933031,
|
847 |
+
"eval_loss": 0.4992757737636566,
|
848 |
+
"eval_runtime": 6.2439,
|
849 |
+
"eval_samples_per_second": 141.097,
|
850 |
+
"eval_steps_per_second": 17.777,
|
851 |
+
"step": 1274
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 9.04,
|
855 |
+
"learning_rate": 4.659498207885305e-06,
|
856 |
+
"loss": 0.7542,
|
857 |
+
"step": 1280
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 9.11,
|
861 |
+
"learning_rate": 4.3010752688172045e-06,
|
862 |
+
"loss": 0.7201,
|
863 |
+
"step": 1290
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 9.18,
|
867 |
+
"learning_rate": 3.942652329749104e-06,
|
868 |
+
"loss": 0.6967,
|
869 |
+
"step": 1300
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 9.25,
|
873 |
+
"learning_rate": 3.5842293906810035e-06,
|
874 |
+
"loss": 0.7151,
|
875 |
+
"step": 1310
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 9.32,
|
879 |
+
"learning_rate": 3.225806451612903e-06,
|
880 |
+
"loss": 0.7127,
|
881 |
+
"step": 1320
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 9.39,
|
885 |
+
"learning_rate": 2.867383512544803e-06,
|
886 |
+
"loss": 0.6665,
|
887 |
+
"step": 1330
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 9.47,
|
891 |
+
"learning_rate": 2.5089605734767026e-06,
|
892 |
+
"loss": 0.7662,
|
893 |
+
"step": 1340
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 9.54,
|
897 |
+
"learning_rate": 2.1505376344086023e-06,
|
898 |
+
"loss": 0.7602,
|
899 |
+
"step": 1350
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 9.61,
|
903 |
+
"learning_rate": 1.7921146953405017e-06,
|
904 |
+
"loss": 0.7054,
|
905 |
+
"step": 1360
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 9.68,
|
909 |
+
"learning_rate": 1.4336917562724014e-06,
|
910 |
+
"loss": 0.6655,
|
911 |
+
"step": 1370
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 9.75,
|
915 |
+
"learning_rate": 1.0752688172043011e-06,
|
916 |
+
"loss": 0.6564,
|
917 |
+
"step": 1380
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 9.82,
|
921 |
+
"learning_rate": 7.168458781362007e-07,
|
922 |
+
"loss": 0.7077,
|
923 |
+
"step": 1390
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 9.89,
|
927 |
+
"learning_rate": 3.5842293906810036e-07,
|
928 |
+
"loss": 0.6575,
|
929 |
+
"step": 1400
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 9.96,
|
933 |
+
"learning_rate": 0.0,
|
934 |
+
"loss": 0.7275,
|
935 |
+
"step": 1410
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 9.96,
|
939 |
+
"eval_accuracy": 0.8342792281498297,
|
940 |
+
"eval_loss": 0.48094892501831055,
|
941 |
+
"eval_runtime": 6.3075,
|
942 |
+
"eval_samples_per_second": 139.674,
|
943 |
+
"eval_steps_per_second": 17.598,
|
944 |
+
"step": 1410
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 9.96,
|
948 |
+
"step": 1410,
|
949 |
+
"total_flos": 1.6760839403221402e+18,
|
950 |
+
"train_loss": 0.9043752511342367,
|
951 |
+
"train_runtime": 8036.8099,
|
952 |
+
"train_samples_per_second": 9.858,
|
953 |
+
"train_steps_per_second": 0.175
|
954 |
+
}
|
955 |
+
],
|
956 |
+
"max_steps": 1410,
|
957 |
+
"num_train_epochs": 10,
|
958 |
+
"total_flos": 1.6760839403221402e+18,
|
959 |
+
"trial_name": null,
|
960 |
+
"trial_params": null
|
961 |
+
}
|