End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_samples": 12458,
|
4 |
+
"train_loss": 0.764641843215564,
|
5 |
+
"train_runtime": 18256.242,
|
6 |
+
"train_samples": 130319,
|
7 |
+
"train_samples_per_second": 35.692,
|
8 |
+
"train_steps_per_second": 1.116
|
9 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_samples": 12458
|
4 |
+
}
|
runs/Mar14_07-54-59_1ca1daddd6ef/events.out.tfevents.1678799269.1ca1daddd6ef.83661.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f9a39aee9391d899556e3e6cd57c81d7cee12162898fb238ef85a60ebc69fdf
|
3 |
+
size 91
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 0.764641843215564,
|
4 |
+
"train_runtime": 18256.242,
|
5 |
+
"train_samples": 130319,
|
6 |
+
"train_samples_per_second": 35.692,
|
7 |
+
"train_steps_per_second": 1.116
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,225 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 20365,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.25,
|
12 |
+
"learning_rate": 2.8526884360422293e-05,
|
13 |
+
"loss": 3.7774,
|
14 |
+
"step": 1000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.25,
|
18 |
+
"step": 1000
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.49,
|
22 |
+
"learning_rate": 2.705376872084459e-05,
|
23 |
+
"loss": 1.1215,
|
24 |
+
"step": 2000
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.49,
|
28 |
+
"step": 2000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.74,
|
32 |
+
"learning_rate": 2.558065308126688e-05,
|
33 |
+
"loss": 0.891,
|
34 |
+
"step": 3000
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.74,
|
38 |
+
"step": 3000
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.98,
|
42 |
+
"learning_rate": 2.4107537441689173e-05,
|
43 |
+
"loss": 0.7978,
|
44 |
+
"step": 4000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.98,
|
48 |
+
"step": 4000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.23,
|
52 |
+
"learning_rate": 2.263442180211147e-05,
|
53 |
+
"loss": 0.7133,
|
54 |
+
"step": 5000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.23,
|
58 |
+
"step": 5000
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.47,
|
62 |
+
"learning_rate": 2.116130616253376e-05,
|
63 |
+
"loss": 0.6749,
|
64 |
+
"step": 6000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 1.47,
|
68 |
+
"step": 6000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.72,
|
72 |
+
"learning_rate": 1.9688190522956053e-05,
|
73 |
+
"loss": 0.6433,
|
74 |
+
"step": 7000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.72,
|
78 |
+
"step": 7000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.96,
|
82 |
+
"learning_rate": 1.8215074883378345e-05,
|
83 |
+
"loss": 0.6125,
|
84 |
+
"step": 8000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.96,
|
88 |
+
"step": 8000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 2.21,
|
92 |
+
"learning_rate": 1.674195924380064e-05,
|
93 |
+
"loss": 0.5748,
|
94 |
+
"step": 9000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 2.21,
|
98 |
+
"step": 9000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.46,
|
102 |
+
"learning_rate": 1.5268843604222933e-05,
|
103 |
+
"loss": 0.5683,
|
104 |
+
"step": 10000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.46,
|
108 |
+
"step": 10000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 2.7,
|
112 |
+
"learning_rate": 1.3795727964645225e-05,
|
113 |
+
"loss": 0.5413,
|
114 |
+
"step": 11000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 2.7,
|
118 |
+
"step": 11000
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 2.95,
|
122 |
+
"learning_rate": 1.2322612325067517e-05,
|
123 |
+
"loss": 0.5412,
|
124 |
+
"step": 12000
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 2.95,
|
128 |
+
"step": 12000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.19,
|
132 |
+
"learning_rate": 1.0849496685489811e-05,
|
133 |
+
"loss": 0.5168,
|
134 |
+
"step": 13000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.19,
|
138 |
+
"step": 13000
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 3.44,
|
142 |
+
"learning_rate": 9.376381045912103e-06,
|
143 |
+
"loss": 0.5038,
|
144 |
+
"step": 14000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.44,
|
148 |
+
"step": 14000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.68,
|
152 |
+
"learning_rate": 7.903265406334397e-06,
|
153 |
+
"loss": 0.5042,
|
154 |
+
"step": 15000
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 3.68,
|
158 |
+
"step": 15000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 3.93,
|
162 |
+
"learning_rate": 6.43014976675669e-06,
|
163 |
+
"loss": 0.4929,
|
164 |
+
"step": 16000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 3.93,
|
168 |
+
"step": 16000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 4.17,
|
172 |
+
"learning_rate": 4.957034127178984e-06,
|
173 |
+
"loss": 0.4919,
|
174 |
+
"step": 17000
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 4.17,
|
178 |
+
"step": 17000
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 4.42,
|
182 |
+
"learning_rate": 3.483918487601277e-06,
|
183 |
+
"loss": 0.4765,
|
184 |
+
"step": 18000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 4.42,
|
188 |
+
"step": 18000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 4.66,
|
192 |
+
"learning_rate": 2.01080284802357e-06,
|
193 |
+
"loss": 0.4772,
|
194 |
+
"step": 19000
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 4.66,
|
198 |
+
"step": 19000
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 4.91,
|
202 |
+
"learning_rate": 5.37687208445863e-07,
|
203 |
+
"loss": 0.4729,
|
204 |
+
"step": 20000
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 4.91,
|
208 |
+
"step": 20000
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 5.0,
|
212 |
+
"step": 20365,
|
213 |
+
"total_flos": 5.859693481446605e+17,
|
214 |
+
"train_loss": 0.764641843215564,
|
215 |
+
"train_runtime": 18256.242,
|
216 |
+
"train_samples_per_second": 35.692,
|
217 |
+
"train_steps_per_second": 1.116
|
218 |
+
}
|
219 |
+
],
|
220 |
+
"max_steps": 20365,
|
221 |
+
"num_train_epochs": 5,
|
222 |
+
"total_flos": 5.859693481446605e+17,
|
223 |
+
"trial_name": null,
|
224 |
+
"trial_params": null
|
225 |
+
}
|