farleyknight
commited on
Commit
•
97084b1
1
Parent(s):
5e0c7e1
End of training
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +901 -0
all_results.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_gen_len": 78.97017596182523,
|
4 |
+
"eval_loss": 2.408818006515503,
|
5 |
+
"eval_rouge1": 39.4401,
|
6 |
+
"eval_rouge2": 14.2445,
|
7 |
+
"eval_rougeL": 26.2701,
|
8 |
+
"eval_rougeLsum": 33.7535,
|
9 |
+
"eval_runtime": 3434.8131,
|
10 |
+
"eval_samples": 3353,
|
11 |
+
"eval_samples_per_second": 0.976,
|
12 |
+
"eval_steps_per_second": 0.976,
|
13 |
+
"train_loss": 2.76828055864371,
|
14 |
+
"train_runtime": 19432.47,
|
15 |
+
"train_samples": 60361,
|
16 |
+
"train_samples_per_second": 3.106,
|
17 |
+
"train_steps_per_second": 3.106
|
18 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_gen_len": 78.97017596182523,
|
4 |
+
"eval_loss": 2.408818006515503,
|
5 |
+
"eval_rouge1": 39.4401,
|
6 |
+
"eval_rouge2": 14.2445,
|
7 |
+
"eval_rougeL": 26.2701,
|
8 |
+
"eval_rougeLsum": 33.7535,
|
9 |
+
"eval_runtime": 3434.8131,
|
10 |
+
"eval_samples": 3353,
|
11 |
+
"eval_samples_per_second": 0.976,
|
12 |
+
"eval_steps_per_second": 0.976
|
13 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 2.76828055864371,
|
4 |
+
"train_runtime": 19432.47,
|
5 |
+
"train_samples": 60361,
|
6 |
+
"train_samples_per_second": 3.106,
|
7 |
+
"train_steps_per_second": 3.106
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,901 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 60361,
|
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": 4.9585825284538036e-05,
|
13 |
+
"loss": 3.6144,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 4.917165056907606e-05,
|
19 |
+
"loss": 3.4028,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"learning_rate": 4.8757475853614095e-05,
|
25 |
+
"loss": 3.3486,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.03,
|
30 |
+
"learning_rate": 4.834330113815212e-05,
|
31 |
+
"loss": 3.2449,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.04,
|
36 |
+
"learning_rate": 4.792912642269015e-05,
|
37 |
+
"loss": 3.2114,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.05,
|
42 |
+
"learning_rate": 4.7514951707228175e-05,
|
43 |
+
"loss": 3.1917,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.06,
|
48 |
+
"learning_rate": 4.710077699176621e-05,
|
49 |
+
"loss": 3.1649,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.07,
|
54 |
+
"learning_rate": 4.6686602276304234e-05,
|
55 |
+
"loss": 3.146,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.07,
|
60 |
+
"learning_rate": 4.627242756084227e-05,
|
61 |
+
"loss": 3.1357,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.08,
|
66 |
+
"learning_rate": 4.5858252845380294e-05,
|
67 |
+
"loss": 3.0567,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.08,
|
72 |
+
"eval_gen_len": 19.997912317327767,
|
73 |
+
"eval_loss": 2.886395215988159,
|
74 |
+
"eval_rouge1": 18.9387,
|
75 |
+
"eval_rouge2": 7.1014,
|
76 |
+
"eval_rougeL": 15.4506,
|
77 |
+
"eval_rougeLsum": 16.8377,
|
78 |
+
"eval_runtime": 859.9366,
|
79 |
+
"eval_samples_per_second": 3.899,
|
80 |
+
"eval_steps_per_second": 3.899,
|
81 |
+
"step": 5000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.09,
|
85 |
+
"learning_rate": 4.544407812991833e-05,
|
86 |
+
"loss": 3.1082,
|
87 |
+
"step": 5500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.1,
|
91 |
+
"learning_rate": 4.502990341445636e-05,
|
92 |
+
"loss": 3.088,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.11,
|
97 |
+
"learning_rate": 4.461572869899439e-05,
|
98 |
+
"loss": 3.0837,
|
99 |
+
"step": 6500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.12,
|
103 |
+
"learning_rate": 4.420155398353242e-05,
|
104 |
+
"loss": 3.0459,
|
105 |
+
"step": 7000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.12,
|
109 |
+
"learning_rate": 4.378737926807045e-05,
|
110 |
+
"loss": 2.9948,
|
111 |
+
"step": 7500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.13,
|
115 |
+
"learning_rate": 4.337320455260847e-05,
|
116 |
+
"loss": 2.9943,
|
117 |
+
"step": 8000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.14,
|
121 |
+
"learning_rate": 4.29590298371465e-05,
|
122 |
+
"loss": 3.0398,
|
123 |
+
"step": 8500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.15,
|
127 |
+
"learning_rate": 4.254485512168453e-05,
|
128 |
+
"loss": 2.9949,
|
129 |
+
"step": 9000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.16,
|
133 |
+
"learning_rate": 4.213068040622256e-05,
|
134 |
+
"loss": 2.9824,
|
135 |
+
"step": 9500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.17,
|
139 |
+
"learning_rate": 4.171650569076059e-05,
|
140 |
+
"loss": 2.9285,
|
141 |
+
"step": 10000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.17,
|
145 |
+
"eval_gen_len": 20.0,
|
146 |
+
"eval_loss": 2.7799806594848633,
|
147 |
+
"eval_rouge1": 19.8983,
|
148 |
+
"eval_rouge2": 7.3258,
|
149 |
+
"eval_rougeL": 16.0823,
|
150 |
+
"eval_rougeLsum": 17.7019,
|
151 |
+
"eval_runtime": 854.1045,
|
152 |
+
"eval_samples_per_second": 3.926,
|
153 |
+
"eval_steps_per_second": 3.926,
|
154 |
+
"step": 10000
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.17,
|
158 |
+
"learning_rate": 4.130233097529862e-05,
|
159 |
+
"loss": 2.9611,
|
160 |
+
"step": 10500
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.18,
|
164 |
+
"learning_rate": 4.088815625983665e-05,
|
165 |
+
"loss": 2.9401,
|
166 |
+
"step": 11000
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.19,
|
170 |
+
"learning_rate": 4.047398154437468e-05,
|
171 |
+
"loss": 2.9217,
|
172 |
+
"step": 11500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.2,
|
176 |
+
"learning_rate": 4.005980682891271e-05,
|
177 |
+
"loss": 2.9318,
|
178 |
+
"step": 12000
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.21,
|
182 |
+
"learning_rate": 3.9645632113450745e-05,
|
183 |
+
"loss": 2.8956,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.22,
|
188 |
+
"learning_rate": 3.923145739798877e-05,
|
189 |
+
"loss": 2.902,
|
190 |
+
"step": 13000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.22,
|
194 |
+
"learning_rate": 3.88172826825268e-05,
|
195 |
+
"loss": 2.8895,
|
196 |
+
"step": 13500
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.23,
|
200 |
+
"learning_rate": 3.8403107967064825e-05,
|
201 |
+
"loss": 2.9131,
|
202 |
+
"step": 14000
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.24,
|
206 |
+
"learning_rate": 3.798893325160286e-05,
|
207 |
+
"loss": 2.9017,
|
208 |
+
"step": 14500
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.25,
|
212 |
+
"learning_rate": 3.7574758536140885e-05,
|
213 |
+
"loss": 2.9252,
|
214 |
+
"step": 15000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.25,
|
218 |
+
"eval_gen_len": 20.0,
|
219 |
+
"eval_loss": 2.7080156803131104,
|
220 |
+
"eval_rouge1": 19.6623,
|
221 |
+
"eval_rouge2": 7.4627,
|
222 |
+
"eval_rougeL": 16.0153,
|
223 |
+
"eval_rougeLsum": 17.4485,
|
224 |
+
"eval_runtime": 853.6576,
|
225 |
+
"eval_samples_per_second": 3.928,
|
226 |
+
"eval_steps_per_second": 3.928,
|
227 |
+
"step": 15000
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.26,
|
231 |
+
"learning_rate": 3.716058382067892e-05,
|
232 |
+
"loss": 2.8971,
|
233 |
+
"step": 15500
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.27,
|
237 |
+
"learning_rate": 3.6746409105216944e-05,
|
238 |
+
"loss": 2.8831,
|
239 |
+
"step": 16000
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.27,
|
243 |
+
"learning_rate": 3.633223438975498e-05,
|
244 |
+
"loss": 2.8911,
|
245 |
+
"step": 16500
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.28,
|
249 |
+
"learning_rate": 3.5918059674293004e-05,
|
250 |
+
"loss": 2.8266,
|
251 |
+
"step": 17000
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.29,
|
255 |
+
"learning_rate": 3.550388495883104e-05,
|
256 |
+
"loss": 2.8465,
|
257 |
+
"step": 17500
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.3,
|
261 |
+
"learning_rate": 3.508971024336907e-05,
|
262 |
+
"loss": 2.8168,
|
263 |
+
"step": 18000
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.31,
|
267 |
+
"learning_rate": 3.46755355279071e-05,
|
268 |
+
"loss": 2.8807,
|
269 |
+
"step": 18500
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.31,
|
273 |
+
"learning_rate": 3.4261360812445123e-05,
|
274 |
+
"loss": 2.8521,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.32,
|
279 |
+
"learning_rate": 3.384718609698315e-05,
|
280 |
+
"loss": 2.8083,
|
281 |
+
"step": 19500
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.33,
|
285 |
+
"learning_rate": 3.343301138152118e-05,
|
286 |
+
"loss": 2.8123,
|
287 |
+
"step": 20000
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.33,
|
291 |
+
"eval_gen_len": 20.0,
|
292 |
+
"eval_loss": 2.658450126647949,
|
293 |
+
"eval_rouge1": 19.7414,
|
294 |
+
"eval_rouge2": 7.5251,
|
295 |
+
"eval_rougeL": 15.8166,
|
296 |
+
"eval_rougeLsum": 17.4668,
|
297 |
+
"eval_runtime": 853.1021,
|
298 |
+
"eval_samples_per_second": 3.93,
|
299 |
+
"eval_steps_per_second": 3.93,
|
300 |
+
"step": 20000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 0.34,
|
304 |
+
"learning_rate": 3.301883666605921e-05,
|
305 |
+
"loss": 2.8339,
|
306 |
+
"step": 20500
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.35,
|
310 |
+
"learning_rate": 3.260466195059724e-05,
|
311 |
+
"loss": 2.8566,
|
312 |
+
"step": 21000
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 0.36,
|
316 |
+
"learning_rate": 3.219048723513527e-05,
|
317 |
+
"loss": 2.804,
|
318 |
+
"step": 21500
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.36,
|
322 |
+
"learning_rate": 3.17763125196733e-05,
|
323 |
+
"loss": 2.7706,
|
324 |
+
"step": 22000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.37,
|
328 |
+
"learning_rate": 3.136213780421133e-05,
|
329 |
+
"loss": 2.8014,
|
330 |
+
"step": 22500
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.38,
|
334 |
+
"learning_rate": 3.094796308874936e-05,
|
335 |
+
"loss": 2.7753,
|
336 |
+
"step": 23000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 0.39,
|
340 |
+
"learning_rate": 3.053378837328739e-05,
|
341 |
+
"loss": 2.7491,
|
342 |
+
"step": 23500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.4,
|
346 |
+
"learning_rate": 3.011961365782542e-05,
|
347 |
+
"loss": 2.8093,
|
348 |
+
"step": 24000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 0.41,
|
352 |
+
"learning_rate": 2.9705438942363452e-05,
|
353 |
+
"loss": 2.7746,
|
354 |
+
"step": 24500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.41,
|
358 |
+
"learning_rate": 2.929126422690148e-05,
|
359 |
+
"loss": 2.7117,
|
360 |
+
"step": 25000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.41,
|
364 |
+
"eval_gen_len": 20.0,
|
365 |
+
"eval_loss": 2.607012987136841,
|
366 |
+
"eval_rouge1": 19.7661,
|
367 |
+
"eval_rouge2": 7.7193,
|
368 |
+
"eval_rougeL": 16.2795,
|
369 |
+
"eval_rougeLsum": 17.7884,
|
370 |
+
"eval_runtime": 852.4977,
|
371 |
+
"eval_samples_per_second": 3.933,
|
372 |
+
"eval_steps_per_second": 3.933,
|
373 |
+
"step": 25000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.42,
|
377 |
+
"learning_rate": 2.8877089511439508e-05,
|
378 |
+
"loss": 2.7638,
|
379 |
+
"step": 25500
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.43,
|
383 |
+
"learning_rate": 2.8462914795977535e-05,
|
384 |
+
"loss": 2.7299,
|
385 |
+
"step": 26000
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.44,
|
389 |
+
"learning_rate": 2.8048740080515568e-05,
|
390 |
+
"loss": 2.7383,
|
391 |
+
"step": 26500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.45,
|
395 |
+
"learning_rate": 2.7634565365053594e-05,
|
396 |
+
"loss": 2.7634,
|
397 |
+
"step": 27000
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 0.46,
|
401 |
+
"learning_rate": 2.7220390649591628e-05,
|
402 |
+
"loss": 2.7074,
|
403 |
+
"step": 27500
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 0.46,
|
407 |
+
"learning_rate": 2.6806215934129654e-05,
|
408 |
+
"loss": 2.7268,
|
409 |
+
"step": 28000
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.47,
|
413 |
+
"learning_rate": 2.6392041218667684e-05,
|
414 |
+
"loss": 2.709,
|
415 |
+
"step": 28500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.48,
|
419 |
+
"learning_rate": 2.597786650320571e-05,
|
420 |
+
"loss": 2.7451,
|
421 |
+
"step": 29000
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.49,
|
425 |
+
"learning_rate": 2.5563691787743744e-05,
|
426 |
+
"loss": 2.6797,
|
427 |
+
"step": 29500
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 0.5,
|
431 |
+
"learning_rate": 2.5149517072281774e-05,
|
432 |
+
"loss": 2.7131,
|
433 |
+
"step": 30000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.5,
|
437 |
+
"eval_gen_len": 20.0,
|
438 |
+
"eval_loss": 2.5616209506988525,
|
439 |
+
"eval_rouge1": 19.6706,
|
440 |
+
"eval_rouge2": 7.4229,
|
441 |
+
"eval_rougeL": 15.7998,
|
442 |
+
"eval_rougeLsum": 17.4324,
|
443 |
+
"eval_runtime": 853.8437,
|
444 |
+
"eval_samples_per_second": 3.927,
|
445 |
+
"eval_steps_per_second": 3.927,
|
446 |
+
"step": 30000
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.51,
|
450 |
+
"learning_rate": 2.47353423568198e-05,
|
451 |
+
"loss": 2.6996,
|
452 |
+
"step": 30500
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.51,
|
456 |
+
"learning_rate": 2.432116764135783e-05,
|
457 |
+
"loss": 2.7442,
|
458 |
+
"step": 31000
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.52,
|
462 |
+
"learning_rate": 2.390699292589586e-05,
|
463 |
+
"loss": 2.7131,
|
464 |
+
"step": 31500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.53,
|
468 |
+
"learning_rate": 2.349281821043389e-05,
|
469 |
+
"loss": 2.7108,
|
470 |
+
"step": 32000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.54,
|
474 |
+
"learning_rate": 2.307864349497192e-05,
|
475 |
+
"loss": 2.7011,
|
476 |
+
"step": 32500
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 0.55,
|
480 |
+
"learning_rate": 2.266446877950995e-05,
|
481 |
+
"loss": 2.6768,
|
482 |
+
"step": 33000
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.55,
|
486 |
+
"learning_rate": 2.225029406404798e-05,
|
487 |
+
"loss": 2.6671,
|
488 |
+
"step": 33500
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.56,
|
492 |
+
"learning_rate": 2.183611934858601e-05,
|
493 |
+
"loss": 2.6739,
|
494 |
+
"step": 34000
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 0.57,
|
498 |
+
"learning_rate": 2.142194463312404e-05,
|
499 |
+
"loss": 2.7291,
|
500 |
+
"step": 34500
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.58,
|
504 |
+
"learning_rate": 2.100776991766207e-05,
|
505 |
+
"loss": 2.6373,
|
506 |
+
"step": 35000
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.58,
|
510 |
+
"eval_gen_len": 20.0,
|
511 |
+
"eval_loss": 2.525042772293091,
|
512 |
+
"eval_rouge1": 20.0155,
|
513 |
+
"eval_rouge2": 7.6811,
|
514 |
+
"eval_rougeL": 16.1231,
|
515 |
+
"eval_rougeLsum": 17.7578,
|
516 |
+
"eval_runtime": 855.0145,
|
517 |
+
"eval_samples_per_second": 3.922,
|
518 |
+
"eval_steps_per_second": 3.922,
|
519 |
+
"step": 35000
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.59,
|
523 |
+
"learning_rate": 2.05935952022001e-05,
|
524 |
+
"loss": 2.711,
|
525 |
+
"step": 35500
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.6,
|
529 |
+
"learning_rate": 2.0179420486738125e-05,
|
530 |
+
"loss": 2.663,
|
531 |
+
"step": 36000
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.6,
|
535 |
+
"learning_rate": 1.9765245771276155e-05,
|
536 |
+
"loss": 2.6486,
|
537 |
+
"step": 36500
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.61,
|
541 |
+
"learning_rate": 1.9351071055814185e-05,
|
542 |
+
"loss": 2.6442,
|
543 |
+
"step": 37000
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.62,
|
547 |
+
"learning_rate": 1.8936896340352215e-05,
|
548 |
+
"loss": 2.6583,
|
549 |
+
"step": 37500
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.63,
|
553 |
+
"learning_rate": 1.8522721624890245e-05,
|
554 |
+
"loss": 2.6227,
|
555 |
+
"step": 38000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.64,
|
559 |
+
"learning_rate": 1.8108546909428274e-05,
|
560 |
+
"loss": 2.631,
|
561 |
+
"step": 38500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.65,
|
565 |
+
"learning_rate": 1.7694372193966304e-05,
|
566 |
+
"loss": 2.6675,
|
567 |
+
"step": 39000
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.65,
|
571 |
+
"learning_rate": 1.7280197478504334e-05,
|
572 |
+
"loss": 2.6396,
|
573 |
+
"step": 39500
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.66,
|
577 |
+
"learning_rate": 1.6866022763042364e-05,
|
578 |
+
"loss": 2.6785,
|
579 |
+
"step": 40000
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.66,
|
583 |
+
"eval_gen_len": 20.0,
|
584 |
+
"eval_loss": 2.497694253921509,
|
585 |
+
"eval_rouge1": 20.0974,
|
586 |
+
"eval_rouge2": 7.9578,
|
587 |
+
"eval_rougeL": 16.543,
|
588 |
+
"eval_rougeLsum": 18.0242,
|
589 |
+
"eval_runtime": 854.2144,
|
590 |
+
"eval_samples_per_second": 3.925,
|
591 |
+
"eval_steps_per_second": 3.925,
|
592 |
+
"step": 40000
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.67,
|
596 |
+
"learning_rate": 1.6451848047580394e-05,
|
597 |
+
"loss": 2.6492,
|
598 |
+
"step": 40500
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.68,
|
602 |
+
"learning_rate": 1.603767333211842e-05,
|
603 |
+
"loss": 2.5702,
|
604 |
+
"step": 41000
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.69,
|
608 |
+
"learning_rate": 1.562349861665645e-05,
|
609 |
+
"loss": 2.5583,
|
610 |
+
"step": 41500
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.7,
|
614 |
+
"learning_rate": 1.520932390119448e-05,
|
615 |
+
"loss": 2.6215,
|
616 |
+
"step": 42000
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.7,
|
620 |
+
"learning_rate": 1.479514918573251e-05,
|
621 |
+
"loss": 2.6198,
|
622 |
+
"step": 42500
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 0.71,
|
626 |
+
"learning_rate": 1.438097447027054e-05,
|
627 |
+
"loss": 2.6482,
|
628 |
+
"step": 43000
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 0.72,
|
632 |
+
"learning_rate": 1.3966799754808568e-05,
|
633 |
+
"loss": 2.6153,
|
634 |
+
"step": 43500
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.73,
|
638 |
+
"learning_rate": 1.3552625039346598e-05,
|
639 |
+
"loss": 2.6112,
|
640 |
+
"step": 44000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.74,
|
644 |
+
"learning_rate": 1.3138450323884628e-05,
|
645 |
+
"loss": 2.6555,
|
646 |
+
"step": 44500
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.75,
|
650 |
+
"learning_rate": 1.272427560842266e-05,
|
651 |
+
"loss": 2.6265,
|
652 |
+
"step": 45000
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 0.75,
|
656 |
+
"eval_gen_len": 20.0,
|
657 |
+
"eval_loss": 2.4701449871063232,
|
658 |
+
"eval_rouge1": 19.994,
|
659 |
+
"eval_rouge2": 7.9114,
|
660 |
+
"eval_rougeL": 16.3501,
|
661 |
+
"eval_rougeLsum": 17.8786,
|
662 |
+
"eval_runtime": 853.6465,
|
663 |
+
"eval_samples_per_second": 3.928,
|
664 |
+
"eval_steps_per_second": 3.928,
|
665 |
+
"step": 45000
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.75,
|
669 |
+
"learning_rate": 1.2310100892960687e-05,
|
670 |
+
"loss": 2.588,
|
671 |
+
"step": 45500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 0.76,
|
675 |
+
"learning_rate": 1.1895926177498716e-05,
|
676 |
+
"loss": 2.5818,
|
677 |
+
"step": 46000
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 0.77,
|
681 |
+
"learning_rate": 1.1481751462036747e-05,
|
682 |
+
"loss": 2.5937,
|
683 |
+
"step": 46500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 0.78,
|
687 |
+
"learning_rate": 1.1067576746574775e-05,
|
688 |
+
"loss": 2.6259,
|
689 |
+
"step": 47000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.79,
|
693 |
+
"learning_rate": 1.0653402031112805e-05,
|
694 |
+
"loss": 2.6067,
|
695 |
+
"step": 47500
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.8,
|
699 |
+
"learning_rate": 1.0239227315650835e-05,
|
700 |
+
"loss": 2.5841,
|
701 |
+
"step": 48000
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 0.8,
|
705 |
+
"learning_rate": 9.825052600188863e-06,
|
706 |
+
"loss": 2.581,
|
707 |
+
"step": 48500
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.81,
|
711 |
+
"learning_rate": 9.410877884726893e-06,
|
712 |
+
"loss": 2.552,
|
713 |
+
"step": 49000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 0.82,
|
717 |
+
"learning_rate": 8.996703169264925e-06,
|
718 |
+
"loss": 2.5549,
|
719 |
+
"step": 49500
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 0.83,
|
723 |
+
"learning_rate": 8.582528453802953e-06,
|
724 |
+
"loss": 2.5833,
|
725 |
+
"step": 50000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.83,
|
729 |
+
"eval_gen_len": 20.0,
|
730 |
+
"eval_loss": 2.444098472595215,
|
731 |
+
"eval_rouge1": 19.9981,
|
732 |
+
"eval_rouge2": 7.934,
|
733 |
+
"eval_rougeL": 16.3033,
|
734 |
+
"eval_rougeLsum": 17.8674,
|
735 |
+
"eval_runtime": 854.286,
|
736 |
+
"eval_samples_per_second": 3.925,
|
737 |
+
"eval_steps_per_second": 3.925,
|
738 |
+
"step": 50000
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.84,
|
742 |
+
"learning_rate": 8.168353738340983e-06,
|
743 |
+
"loss": 2.5983,
|
744 |
+
"step": 50500
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.84,
|
748 |
+
"learning_rate": 7.75417902287901e-06,
|
749 |
+
"loss": 2.6161,
|
750 |
+
"step": 51000
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 0.85,
|
754 |
+
"learning_rate": 7.3400043074170406e-06,
|
755 |
+
"loss": 2.5425,
|
756 |
+
"step": 51500
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 0.86,
|
760 |
+
"learning_rate": 6.9258295919550704e-06,
|
761 |
+
"loss": 2.5936,
|
762 |
+
"step": 52000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.87,
|
766 |
+
"learning_rate": 6.5116548764931e-06,
|
767 |
+
"loss": 2.5658,
|
768 |
+
"step": 52500
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.88,
|
772 |
+
"learning_rate": 6.09748016103113e-06,
|
773 |
+
"loss": 2.6075,
|
774 |
+
"step": 53000
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.89,
|
778 |
+
"learning_rate": 5.683305445569159e-06,
|
779 |
+
"loss": 2.6051,
|
780 |
+
"step": 53500
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.89,
|
784 |
+
"learning_rate": 5.269130730107188e-06,
|
785 |
+
"loss": 2.542,
|
786 |
+
"step": 54000
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.9,
|
790 |
+
"learning_rate": 4.854956014645219e-06,
|
791 |
+
"loss": 2.5377,
|
792 |
+
"step": 54500
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.91,
|
796 |
+
"learning_rate": 4.440781299183248e-06,
|
797 |
+
"loss": 2.5579,
|
798 |
+
"step": 55000
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 0.91,
|
802 |
+
"eval_gen_len": 20.0,
|
803 |
+
"eval_loss": 2.4251036643981934,
|
804 |
+
"eval_rouge1": 20.0544,
|
805 |
+
"eval_rouge2": 7.8966,
|
806 |
+
"eval_rougeL": 16.3889,
|
807 |
+
"eval_rougeLsum": 17.9491,
|
808 |
+
"eval_runtime": 854.2468,
|
809 |
+
"eval_samples_per_second": 3.925,
|
810 |
+
"eval_steps_per_second": 3.925,
|
811 |
+
"step": 55000
|
812 |
+
},
|
813 |
+
{
|
814 |
+
"epoch": 0.92,
|
815 |
+
"learning_rate": 4.026606583721277e-06,
|
816 |
+
"loss": 2.5384,
|
817 |
+
"step": 55500
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 0.93,
|
821 |
+
"learning_rate": 3.6124318682593068e-06,
|
822 |
+
"loss": 2.5131,
|
823 |
+
"step": 56000
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.94,
|
827 |
+
"learning_rate": 3.198257152797336e-06,
|
828 |
+
"loss": 2.5346,
|
829 |
+
"step": 56500
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.94,
|
833 |
+
"learning_rate": 2.784082437335366e-06,
|
834 |
+
"loss": 2.5782,
|
835 |
+
"step": 57000
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.95,
|
839 |
+
"learning_rate": 2.369907721873395e-06,
|
840 |
+
"loss": 2.523,
|
841 |
+
"step": 57500
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.96,
|
845 |
+
"learning_rate": 1.955733006411425e-06,
|
846 |
+
"loss": 2.5384,
|
847 |
+
"step": 58000
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 0.97,
|
851 |
+
"learning_rate": 1.5415582909494541e-06,
|
852 |
+
"loss": 2.5758,
|
853 |
+
"step": 58500
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"epoch": 0.98,
|
857 |
+
"learning_rate": 1.1273835754874836e-06,
|
858 |
+
"loss": 2.5242,
|
859 |
+
"step": 59000
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.99,
|
863 |
+
"learning_rate": 7.132088600255132e-07,
|
864 |
+
"loss": 2.5284,
|
865 |
+
"step": 59500
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.99,
|
869 |
+
"learning_rate": 2.9903414456354266e-07,
|
870 |
+
"loss": 2.5242,
|
871 |
+
"step": 60000
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.99,
|
875 |
+
"eval_gen_len": 20.0,
|
876 |
+
"eval_loss": 2.409696340560913,
|
877 |
+
"eval_rouge1": 20.1093,
|
878 |
+
"eval_rouge2": 8.0572,
|
879 |
+
"eval_rougeL": 16.4935,
|
880 |
+
"eval_rougeLsum": 17.9823,
|
881 |
+
"eval_runtime": 854.1023,
|
882 |
+
"eval_samples_per_second": 3.926,
|
883 |
+
"eval_steps_per_second": 3.926,
|
884 |
+
"step": 60000
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.0,
|
888 |
+
"step": 60361,
|
889 |
+
"total_flos": 3.65352746024448e+16,
|
890 |
+
"train_loss": 2.76828055864371,
|
891 |
+
"train_runtime": 19432.47,
|
892 |
+
"train_samples_per_second": 3.106,
|
893 |
+
"train_steps_per_second": 3.106
|
894 |
+
}
|
895 |
+
],
|
896 |
+
"max_steps": 60361,
|
897 |
+
"num_train_epochs": 1,
|
898 |
+
"total_flos": 3.65352746024448e+16,
|
899 |
+
"trial_name": null,
|
900 |
+
"trial_params": null
|
901 |
+
}
|