Commit
•
d87741f
1
Parent(s):
f7e978f
Create README.md
Browse files
README.md
CHANGED
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"best_metric": 0.4796141982078552,<br>
|
2 |
+
"best_model_checkpoint": "/content/output_dir/checkpoint-268",<br>
|
3 |
+
"epoch": 10.0,<br>
|
4 |
+
"global_step": 2680,<br>
|
5 |
+
"is_hyper_param_search": false,<br>
|
6 |
+
"is_local_process_zero": true,<br>
|
7 |
+
"is_world_process_zero": true,<br>
|
8 |
+
"max_steps": 2680,<br>
|
9 |
+
"num_train_epochs": 10,<br>
|
10 |
+
"total_flos": 7113018526540800.0,<br>
|
11 |
+
"trial_name": null,<br>
|
12 |
+
"trial_params": null<br>
|
13 |
+
<br>
|
14 |
+
<table class="table table-bordered table-hover table-condensed">
|
15 |
+
<thead><tr><th title="Field #1">epoch</th>
|
16 |
+
<th title="Field #2">eval_loss</th>
|
17 |
+
<th title="Field #3">eval_matthews_correlation</th>
|
18 |
+
<th title="Field #4">eval_runtime</th>
|
19 |
+
<th title="Field #5">eval_samples_per_second</th>
|
20 |
+
<th title="Field #6">eval_steps_per_second</th>
|
21 |
+
<th title="Field #7">step</th>
|
22 |
+
<th title="Field #8">learning_rate</th>
|
23 |
+
<th title="Field #9">loss</th>
|
24 |
+
</tr></thead>
|
25 |
+
<tbody><tr>
|
26 |
+
<td align="right">1</td>
|
27 |
+
<td align="right">0.4796141982078552</td>
|
28 |
+
<td align="right">0.5351033849356494</td>
|
29 |
+
<td align="right">8.8067</td>
|
30 |
+
<td align="right">118.433</td>
|
31 |
+
<td align="right">14.875</td>
|
32 |
+
<td align="right">268</td>
|
33 |
+
<td align="right">0.000018067415730337083</td>
|
34 |
+
<td align="right">0.4913</td>
|
35 |
+
</tr>
|
36 |
+
<tr>
|
37 |
+
<td align="right">2</td>
|
38 |
+
<td align="right">0.5334435701370239</td>
|
39 |
+
<td align="right">0.5178799252679331</td>
|
40 |
+
<td align="right">8.9439</td>
|
41 |
+
<td align="right">116.616</td>
|
42 |
+
<td align="right">14.647</td>
|
43 |
+
<td align="right">536</td>
|
44 |
+
<td align="right">0.00001605992509363296</td>
|
45 |
+
<td align="right">0.2872</td>
|
46 |
+
</tr>
|
47 |
+
<tr>
|
48 |
+
<td align="right">3</td>
|
49 |
+
<td align="right">0.5544090270996094</td>
|
50 |
+
<td align="right">0.5649788851042796</td>
|
51 |
+
<td align="right">8.9467</td>
|
52 |
+
<td align="right">116.58</td>
|
53 |
+
<td align="right">14.642</td>
|
54 |
+
<td align="right">804</td>
|
55 |
+
<td align="right">0.000014052434456928841</td>
|
56 |
+
<td align="right">0.1777</td>
|
57 |
+
</tr>
|
58 |
+
<tr>
|
59 |
+
<td align="right">4</td>
|
60 |
+
<td align="right">0.5754779577255249</td>
|
61 |
+
<td align="right">0.6105374636148787</td>
|
62 |
+
<td align="right">8.8982</td>
|
63 |
+
<td align="right">117.215</td>
|
64 |
+
<td align="right">14.722</td>
|
65 |
+
<td align="right">1072</td>
|
66 |
+
<td align="right">0.000012044943820224718</td>
|
67 |
+
<td align="right">0.1263</td>
|
68 |
+
</tr>
|
69 |
+
<tr>
|
70 |
+
<td align="right">5</td>
|
71 |
+
<td align="right">0.7263916730880737</td>
|
72 |
+
<td align="right">0.5807606001872874</td>
|
73 |
+
<td align="right">8.9705</td>
|
74 |
+
<td align="right">116.27</td>
|
75 |
+
<td align="right">14.603</td>
|
76 |
+
<td align="right">1340</td>
|
77 |
+
<td align="right">0.000010037453183520601</td>
|
78 |
+
<td align="right">0.0905</td>
|
79 |
+
</tr>
|
80 |
+
<tr>
|
81 |
+
<td align="right">6</td>
|
82 |
+
<td align="right">0.8121512532234192</td>
|
83 |
+
<td align="right">0.5651092792103851</td>
|
84 |
+
<td align="right">8.9924</td>
|
85 |
+
<td align="right">115.987</td>
|
86 |
+
<td align="right">14.568</td>
|
87 |
+
<td align="right">1608</td>
|
88 |
+
<td align="right">0.00000802996254681648</td>
|
89 |
+
<td align="right">0.0692</td>
|
90 |
+
</tr>
|
91 |
+
<tr>
|
92 |
+
<td align="right">7</td>
|
93 |
+
<td align="right">0.941014289855957</td>
|
94 |
+
<td align="right">0.5632084517291658</td>
|
95 |
+
<td align="right">8.9583</td>
|
96 |
+
<td align="right">116.428</td>
|
97 |
+
<td align="right">14.623</td>
|
98 |
+
<td align="right">1876</td>
|
99 |
+
<td align="right">0.000006022471910112359</td>
|
100 |
+
<td align="right">0.0413</td>
|
101 |
+
</tr>
|
102 |
+
<tr>
|
103 |
+
<td align="right">8</td>
|
104 |
+
<td align="right">1.0095174312591553</td>
|
105 |
+
<td align="right">0.5856531698367675</td>
|
106 |
+
<td align="right">9.0029</td>
|
107 |
+
<td align="right">115.851</td>
|
108 |
+
<td align="right">14.551</td>
|
109 |
+
<td align="right">2144</td>
|
110 |
+
<td align="right">0.00000401498127340824</td>
|
111 |
+
<td align="right">0.0327</td>
|
112 |
+
</tr>
|
113 |
+
<tr>
|
114 |
+
<td align="right">9</td>
|
115 |
+
<td align="right">1.0425965785980225</td>
|
116 |
+
<td align="right">0.5941395545037332</td>
|
117 |
+
<td align="right">8.9217</td>
|
118 |
+
<td align="right">116.906</td>
|
119 |
+
<td align="right">14.683</td>
|
120 |
+
<td align="right">2412</td>
|
121 |
+
<td align="right">0.00000200749063670412</td>
|
122 |
+
<td align="right">0.0202</td>
|
123 |
+
</tr>
|
124 |
+
<tr>
|
125 |
+
<td align="right">10</td>
|
126 |
+
<td align="right">1.0782166719436646</td>
|
127 |
+
<td align="right">0.5956649094312695</td>
|
128 |
+
<td align="right">8.9472</td>
|
129 |
+
<td align="right">116.572</td>
|
130 |
+
<td align="right">14.641</td>
|
131 |
+
<td align="right">2680</td>
|
132 |
+
<td align="right">0</td>
|
133 |
+
<td align="right">0.0104</td>
|
134 |
+
</tr>
|
135 |
+
</tbody></table>
|