All Dunn!!!
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +181 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 1.496570381991936e+19,
|
4 |
+
"train_loss": 0.3501619976043701,
|
5 |
+
"train_runtime": 17883.0624,
|
6 |
+
"train_samples_per_second": 1.118,
|
7 |
+
"train_steps_per_second": 0.14
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 1.496570381991936e+19,
|
4 |
+
"train_loss": 0.3501619976043701,
|
5 |
+
"train_runtime": 17883.0624,
|
6 |
+
"train_samples_per_second": 1.118,
|
7 |
+
"train_steps_per_second": 0.14
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 2500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 8.0806,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"learning_rate": 4.8060000000000004e-05,
|
19 |
+
"loss": 1.2685,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.08,
|
24 |
+
"learning_rate": 4.606e-05,
|
25 |
+
"loss": 0.7447,
|
26 |
+
"step": 200
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 4.4080000000000005e-05,
|
31 |
+
"loss": 0.6506,
|
32 |
+
"step": 300
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 4.2080000000000004e-05,
|
37 |
+
"loss": 0.7171,
|
38 |
+
"step": 400
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.2,
|
42 |
+
"learning_rate": 4.008e-05,
|
43 |
+
"loss": 0.5667,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24,
|
48 |
+
"learning_rate": 3.808e-05,
|
49 |
+
"loss": 0.5265,
|
50 |
+
"step": 600
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.28,
|
54 |
+
"learning_rate": 3.608e-05,
|
55 |
+
"loss": 0.4884,
|
56 |
+
"step": 700
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.32,
|
60 |
+
"learning_rate": 3.408e-05,
|
61 |
+
"loss": 0.4605,
|
62 |
+
"step": 800
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.36,
|
66 |
+
"learning_rate": 3.208e-05,
|
67 |
+
"loss": 0.3832,
|
68 |
+
"step": 900
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.4,
|
72 |
+
"learning_rate": 3.01e-05,
|
73 |
+
"loss": 0.385,
|
74 |
+
"step": 1000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.44,
|
78 |
+
"learning_rate": 2.8100000000000005e-05,
|
79 |
+
"loss": 0.3362,
|
80 |
+
"step": 1100
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.48,
|
84 |
+
"learning_rate": 2.61e-05,
|
85 |
+
"loss": 0.2882,
|
86 |
+
"step": 1200
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.52,
|
90 |
+
"learning_rate": 2.41e-05,
|
91 |
+
"loss": 0.2704,
|
92 |
+
"step": 1300
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.56,
|
96 |
+
"learning_rate": 2.2100000000000002e-05,
|
97 |
+
"loss": 0.2177,
|
98 |
+
"step": 1400
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.6,
|
102 |
+
"learning_rate": 2.01e-05,
|
103 |
+
"loss": 0.2197,
|
104 |
+
"step": 1500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.64,
|
108 |
+
"learning_rate": 1.81e-05,
|
109 |
+
"loss": 0.1808,
|
110 |
+
"step": 1600
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.68,
|
114 |
+
"learning_rate": 1.6100000000000002e-05,
|
115 |
+
"loss": 0.1755,
|
116 |
+
"step": 1700
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.72,
|
120 |
+
"learning_rate": 1.4099999999999999e-05,
|
121 |
+
"loss": 0.1549,
|
122 |
+
"step": 1800
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.76,
|
126 |
+
"learning_rate": 1.2100000000000001e-05,
|
127 |
+
"loss": 0.1254,
|
128 |
+
"step": 1900
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8,
|
132 |
+
"learning_rate": 1.0100000000000002e-05,
|
133 |
+
"loss": 0.1057,
|
134 |
+
"step": 2000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.84,
|
138 |
+
"learning_rate": 8.1e-06,
|
139 |
+
"loss": 0.1035,
|
140 |
+
"step": 2100
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.88,
|
144 |
+
"learning_rate": 6.1e-06,
|
145 |
+
"loss": 0.0938,
|
146 |
+
"step": 2200
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.92,
|
150 |
+
"learning_rate": 4.1000000000000006e-06,
|
151 |
+
"loss": 0.0882,
|
152 |
+
"step": 2300
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.96,
|
156 |
+
"learning_rate": 2.1000000000000002e-06,
|
157 |
+
"loss": 0.0721,
|
158 |
+
"step": 2400
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.0,
|
162 |
+
"learning_rate": 1.0000000000000001e-07,
|
163 |
+
"loss": 0.0627,
|
164 |
+
"step": 2500
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.0,
|
168 |
+
"step": 2500,
|
169 |
+
"total_flos": 1.496570381991936e+19,
|
170 |
+
"train_loss": 0.3501619976043701,
|
171 |
+
"train_runtime": 17883.0624,
|
172 |
+
"train_samples_per_second": 1.118,
|
173 |
+
"train_steps_per_second": 0.14
|
174 |
+
}
|
175 |
+
],
|
176 |
+
"max_steps": 2500,
|
177 |
+
"num_train_epochs": 1,
|
178 |
+
"total_flos": 1.496570381991936e+19,
|
179 |
+
"trial_name": null,
|
180 |
+
"trial_params": null
|
181 |
+
}
|