Splend1dchan
commited on
Commit
•
1f13176
1
Parent(s):
442d3ee
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1645 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 49.95,
|
3 |
+
"train_loss": 0.970869776725769,
|
4 |
+
"train_runtime": 888.1973,
|
5 |
+
"train_samples": 167,
|
6 |
+
"train_samples_per_second": 9.401,
|
7 |
+
"train_steps_per_second": 0.281
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 49.95,
|
3 |
+
"train_loss": 0.970869776725769,
|
4 |
+
"train_runtime": 888.1973,
|
5 |
+
"train_samples": 167,
|
6 |
+
"train_samples_per_second": 9.401,
|
7 |
+
"train_steps_per_second": 0.281
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.875886524822695,
|
3 |
+
"best_model_checkpoint": "xtreme_s_xlsr_300m_minds14.en-US_2/checkpoint-180",
|
4 |
+
"epoch": 49.95238095238095,
|
5 |
+
"global_step": 250,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.19,
|
12 |
+
"learning_rate": 2.9999999999999997e-06,
|
13 |
+
"loss": 2.6385,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.38,
|
18 |
+
"learning_rate": 5.999999999999999e-06,
|
19 |
+
"loss": 2.6393,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.57,
|
24 |
+
"learning_rate": 8.999999999999999e-06,
|
25 |
+
"loss": 2.6383,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.76,
|
30 |
+
"learning_rate": 1.1999999999999999e-05,
|
31 |
+
"loss": 2.6341,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.95,
|
36 |
+
"learning_rate": 1.4999999999999999e-05,
|
37 |
+
"loss": 2.6426,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.19,
|
42 |
+
"learning_rate": 1.7999999999999997e-05,
|
43 |
+
"loss": 3.2976,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.38,
|
48 |
+
"learning_rate": 2.1e-05,
|
49 |
+
"loss": 2.6427,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.57,
|
54 |
+
"learning_rate": 2.3999999999999997e-05,
|
55 |
+
"loss": 2.638,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.76,
|
60 |
+
"learning_rate": 2.6999999999999996e-05,
|
61 |
+
"loss": 2.6369,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 1.95,
|
66 |
+
"learning_rate": 2.9999999999999997e-05,
|
67 |
+
"loss": 2.6352,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.19,
|
72 |
+
"learning_rate": 3.2999999999999996e-05,
|
73 |
+
"loss": 3.2899,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.38,
|
78 |
+
"learning_rate": 3.5999999999999994e-05,
|
79 |
+
"loss": 2.6354,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.57,
|
84 |
+
"learning_rate": 3.9e-05,
|
85 |
+
"loss": 2.6296,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.76,
|
90 |
+
"learning_rate": 4.2e-05,
|
91 |
+
"loss": 2.6469,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.95,
|
96 |
+
"learning_rate": 4.4999999999999996e-05,
|
97 |
+
"loss": 2.6332,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.19,
|
102 |
+
"learning_rate": 4.7999999999999994e-05,
|
103 |
+
"loss": 3.2997,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 3.38,
|
108 |
+
"learning_rate": 5.1e-05,
|
109 |
+
"loss": 2.6299,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.57,
|
114 |
+
"learning_rate": 5.399999999999999e-05,
|
115 |
+
"loss": 2.6381,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 3.76,
|
120 |
+
"learning_rate": 5.6999999999999996e-05,
|
121 |
+
"loss": 2.637,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 3.95,
|
126 |
+
"learning_rate": 5.9999999999999995e-05,
|
127 |
+
"loss": 2.6195,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.95,
|
132 |
+
"eval_accuracy": 0.08156028368794327,
|
133 |
+
"eval_f1": 0.017200191113234592,
|
134 |
+
"eval_loss": 2.6347639560699463,
|
135 |
+
"eval_runtime": 17.0067,
|
136 |
+
"eval_samples_per_second": 16.582,
|
137 |
+
"eval_steps_per_second": 1.058,
|
138 |
+
"step": 20
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 4.19,
|
142 |
+
"learning_rate": 6.299999999999999e-05,
|
143 |
+
"loss": 3.2793,
|
144 |
+
"step": 21
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 4.38,
|
148 |
+
"learning_rate": 6.599999999999999e-05,
|
149 |
+
"loss": 2.6309,
|
150 |
+
"step": 22
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 4.57,
|
154 |
+
"learning_rate": 6.9e-05,
|
155 |
+
"loss": 2.6306,
|
156 |
+
"step": 23
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 4.76,
|
160 |
+
"learning_rate": 7.199999999999999e-05,
|
161 |
+
"loss": 2.6235,
|
162 |
+
"step": 24
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 4.95,
|
166 |
+
"learning_rate": 7.5e-05,
|
167 |
+
"loss": 2.6328,
|
168 |
+
"step": 25
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 5.19,
|
172 |
+
"learning_rate": 7.8e-05,
|
173 |
+
"loss": 3.2753,
|
174 |
+
"step": 26
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 5.38,
|
178 |
+
"learning_rate": 8.1e-05,
|
179 |
+
"loss": 2.6277,
|
180 |
+
"step": 27
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 5.57,
|
184 |
+
"learning_rate": 8.4e-05,
|
185 |
+
"loss": 2.624,
|
186 |
+
"step": 28
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 5.76,
|
190 |
+
"learning_rate": 8.699999999999999e-05,
|
191 |
+
"loss": 2.6107,
|
192 |
+
"step": 29
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 5.95,
|
196 |
+
"learning_rate": 8.999999999999999e-05,
|
197 |
+
"loss": 2.6068,
|
198 |
+
"step": 30
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 6.19,
|
202 |
+
"learning_rate": 9.3e-05,
|
203 |
+
"loss": 3.2691,
|
204 |
+
"step": 31
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 6.38,
|
208 |
+
"learning_rate": 9.599999999999999e-05,
|
209 |
+
"loss": 2.6094,
|
210 |
+
"step": 32
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 6.57,
|
214 |
+
"learning_rate": 9.9e-05,
|
215 |
+
"loss": 2.6068,
|
216 |
+
"step": 33
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 6.76,
|
220 |
+
"learning_rate": 0.000102,
|
221 |
+
"loss": 2.5809,
|
222 |
+
"step": 34
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 6.95,
|
226 |
+
"learning_rate": 0.00010499999999999999,
|
227 |
+
"loss": 2.5934,
|
228 |
+
"step": 35
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 7.19,
|
232 |
+
"learning_rate": 0.00010799999999999998,
|
233 |
+
"loss": 3.192,
|
234 |
+
"step": 36
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 7.38,
|
238 |
+
"learning_rate": 0.00011099999999999999,
|
239 |
+
"loss": 2.5513,
|
240 |
+
"step": 37
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 7.57,
|
244 |
+
"learning_rate": 0.00011399999999999999,
|
245 |
+
"loss": 2.6196,
|
246 |
+
"step": 38
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 7.76,
|
250 |
+
"learning_rate": 0.000117,
|
251 |
+
"loss": 2.5949,
|
252 |
+
"step": 39
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 7.95,
|
256 |
+
"learning_rate": 0.00011999999999999999,
|
257 |
+
"loss": 2.5925,
|
258 |
+
"step": 40
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 7.95,
|
262 |
+
"eval_accuracy": 0.0851063829787234,
|
263 |
+
"eval_f1": 0.035230613984724324,
|
264 |
+
"eval_loss": 2.611875295639038,
|
265 |
+
"eval_runtime": 16.3097,
|
266 |
+
"eval_samples_per_second": 17.29,
|
267 |
+
"eval_steps_per_second": 1.104,
|
268 |
+
"step": 40
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 8.19,
|
272 |
+
"learning_rate": 0.00012299999999999998,
|
273 |
+
"loss": 3.205,
|
274 |
+
"step": 41
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 8.38,
|
278 |
+
"learning_rate": 0.00012599999999999997,
|
279 |
+
"loss": 2.5316,
|
280 |
+
"step": 42
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 8.57,
|
284 |
+
"learning_rate": 0.000129,
|
285 |
+
"loss": 2.5142,
|
286 |
+
"step": 43
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 8.76,
|
290 |
+
"learning_rate": 0.00013199999999999998,
|
291 |
+
"loss": 2.4874,
|
292 |
+
"step": 44
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 8.95,
|
296 |
+
"learning_rate": 0.000135,
|
297 |
+
"loss": 2.5622,
|
298 |
+
"step": 45
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 9.19,
|
302 |
+
"learning_rate": 0.000138,
|
303 |
+
"loss": 3.1398,
|
304 |
+
"step": 46
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 9.38,
|
308 |
+
"learning_rate": 0.00014099999999999998,
|
309 |
+
"loss": 2.4462,
|
310 |
+
"step": 47
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 9.57,
|
314 |
+
"learning_rate": 0.00014399999999999998,
|
315 |
+
"loss": 2.4995,
|
316 |
+
"step": 48
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 9.76,
|
320 |
+
"learning_rate": 0.000147,
|
321 |
+
"loss": 2.4876,
|
322 |
+
"step": 49
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 9.95,
|
326 |
+
"learning_rate": 0.00015,
|
327 |
+
"loss": 2.377,
|
328 |
+
"step": 50
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 10.19,
|
332 |
+
"learning_rate": 0.00015299999999999998,
|
333 |
+
"loss": 2.9698,
|
334 |
+
"step": 51
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 10.38,
|
338 |
+
"learning_rate": 0.000156,
|
339 |
+
"loss": 2.3821,
|
340 |
+
"step": 52
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 10.57,
|
344 |
+
"learning_rate": 0.000159,
|
345 |
+
"loss": 2.2798,
|
346 |
+
"step": 53
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 10.76,
|
350 |
+
"learning_rate": 0.000162,
|
351 |
+
"loss": 2.2958,
|
352 |
+
"step": 54
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 10.95,
|
356 |
+
"learning_rate": 0.000165,
|
357 |
+
"loss": 2.3266,
|
358 |
+
"step": 55
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"epoch": 11.19,
|
362 |
+
"learning_rate": 0.000168,
|
363 |
+
"loss": 2.8351,
|
364 |
+
"step": 56
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 11.38,
|
368 |
+
"learning_rate": 0.00017099999999999998,
|
369 |
+
"loss": 2.2491,
|
370 |
+
"step": 57
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 11.57,
|
374 |
+
"learning_rate": 0.00017399999999999997,
|
375 |
+
"loss": 2.1973,
|
376 |
+
"step": 58
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 11.76,
|
380 |
+
"learning_rate": 0.00017699999999999997,
|
381 |
+
"loss": 2.0763,
|
382 |
+
"step": 59
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 11.95,
|
386 |
+
"learning_rate": 0.00017999999999999998,
|
387 |
+
"loss": 2.1271,
|
388 |
+
"step": 60
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 11.95,
|
392 |
+
"eval_accuracy": 0.19858156028368795,
|
393 |
+
"eval_f1": 0.15555698930698927,
|
394 |
+
"eval_loss": 2.3066093921661377,
|
395 |
+
"eval_runtime": 16.1461,
|
396 |
+
"eval_samples_per_second": 17.466,
|
397 |
+
"eval_steps_per_second": 1.115,
|
398 |
+
"step": 60
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 12.19,
|
402 |
+
"learning_rate": 0.00018299999999999998,
|
403 |
+
"loss": 2.5432,
|
404 |
+
"step": 61
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 12.38,
|
408 |
+
"learning_rate": 0.000186,
|
409 |
+
"loss": 2.0774,
|
410 |
+
"step": 62
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 12.57,
|
414 |
+
"learning_rate": 0.00018899999999999999,
|
415 |
+
"loss": 2.0708,
|
416 |
+
"step": 63
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 12.76,
|
420 |
+
"learning_rate": 0.00019199999999999998,
|
421 |
+
"loss": 1.898,
|
422 |
+
"step": 64
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 12.95,
|
426 |
+
"learning_rate": 0.000195,
|
427 |
+
"loss": 1.8782,
|
428 |
+
"step": 65
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 13.19,
|
432 |
+
"learning_rate": 0.000198,
|
433 |
+
"loss": 2.3485,
|
434 |
+
"step": 66
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 13.38,
|
438 |
+
"learning_rate": 0.000201,
|
439 |
+
"loss": 1.7709,
|
440 |
+
"step": 67
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 13.57,
|
444 |
+
"learning_rate": 0.000204,
|
445 |
+
"loss": 1.8035,
|
446 |
+
"step": 68
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 13.76,
|
450 |
+
"learning_rate": 0.00020699999999999996,
|
451 |
+
"loss": 1.657,
|
452 |
+
"step": 69
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 13.95,
|
456 |
+
"learning_rate": 0.00020999999999999998,
|
457 |
+
"loss": 1.6485,
|
458 |
+
"step": 70
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 14.19,
|
462 |
+
"learning_rate": 0.00021299999999999997,
|
463 |
+
"loss": 1.92,
|
464 |
+
"step": 71
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 14.38,
|
468 |
+
"learning_rate": 0.00021599999999999996,
|
469 |
+
"loss": 1.5454,
|
470 |
+
"step": 72
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 14.57,
|
474 |
+
"learning_rate": 0.00021899999999999998,
|
475 |
+
"loss": 1.5563,
|
476 |
+
"step": 73
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 14.76,
|
480 |
+
"learning_rate": 0.00022199999999999998,
|
481 |
+
"loss": 1.5107,
|
482 |
+
"step": 74
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 14.95,
|
486 |
+
"learning_rate": 0.000225,
|
487 |
+
"loss": 1.5645,
|
488 |
+
"step": 75
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 15.19,
|
492 |
+
"learning_rate": 0.00022799999999999999,
|
493 |
+
"loss": 1.6461,
|
494 |
+
"step": 76
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 15.38,
|
498 |
+
"learning_rate": 0.00023099999999999998,
|
499 |
+
"loss": 1.2531,
|
500 |
+
"step": 77
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 15.57,
|
504 |
+
"learning_rate": 0.000234,
|
505 |
+
"loss": 1.3016,
|
506 |
+
"step": 78
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 15.76,
|
510 |
+
"learning_rate": 0.000237,
|
511 |
+
"loss": 1.154,
|
512 |
+
"step": 79
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 15.95,
|
516 |
+
"learning_rate": 0.00023999999999999998,
|
517 |
+
"loss": 1.2618,
|
518 |
+
"step": 80
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 15.95,
|
522 |
+
"eval_accuracy": 0.7127659574468085,
|
523 |
+
"eval_f1": 0.6877481849792252,
|
524 |
+
"eval_loss": 1.381032109260559,
|
525 |
+
"eval_runtime": 16.3482,
|
526 |
+
"eval_samples_per_second": 17.25,
|
527 |
+
"eval_steps_per_second": 1.101,
|
528 |
+
"step": 80
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 16.19,
|
532 |
+
"learning_rate": 0.000243,
|
533 |
+
"loss": 1.3269,
|
534 |
+
"step": 81
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 16.38,
|
538 |
+
"learning_rate": 0.00024599999999999996,
|
539 |
+
"loss": 1.267,
|
540 |
+
"step": 82
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 16.57,
|
544 |
+
"learning_rate": 0.000249,
|
545 |
+
"loss": 1.3008,
|
546 |
+
"step": 83
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 16.76,
|
550 |
+
"learning_rate": 0.00025199999999999995,
|
551 |
+
"loss": 1.1131,
|
552 |
+
"step": 84
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 16.95,
|
556 |
+
"learning_rate": 0.00025499999999999996,
|
557 |
+
"loss": 1.1345,
|
558 |
+
"step": 85
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 17.19,
|
562 |
+
"learning_rate": 0.000258,
|
563 |
+
"loss": 1.1702,
|
564 |
+
"step": 86
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 17.38,
|
568 |
+
"learning_rate": 0.000261,
|
569 |
+
"loss": 0.8821,
|
570 |
+
"step": 87
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 17.57,
|
574 |
+
"learning_rate": 0.00026399999999999997,
|
575 |
+
"loss": 1.1497,
|
576 |
+
"step": 88
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 17.76,
|
580 |
+
"learning_rate": 0.000267,
|
581 |
+
"loss": 1.1509,
|
582 |
+
"step": 89
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 17.95,
|
586 |
+
"learning_rate": 0.00027,
|
587 |
+
"loss": 1.0648,
|
588 |
+
"step": 90
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 18.19,
|
592 |
+
"learning_rate": 0.00027299999999999997,
|
593 |
+
"loss": 1.2844,
|
594 |
+
"step": 91
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 18.38,
|
598 |
+
"learning_rate": 0.000276,
|
599 |
+
"loss": 0.9621,
|
600 |
+
"step": 92
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 18.57,
|
604 |
+
"learning_rate": 0.000279,
|
605 |
+
"loss": 0.8527,
|
606 |
+
"step": 93
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 18.76,
|
610 |
+
"learning_rate": 0.00028199999999999997,
|
611 |
+
"loss": 1.0502,
|
612 |
+
"step": 94
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 18.95,
|
616 |
+
"learning_rate": 0.000285,
|
617 |
+
"loss": 0.6719,
|
618 |
+
"step": 95
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 19.19,
|
622 |
+
"learning_rate": 0.00028799999999999995,
|
623 |
+
"loss": 0.8417,
|
624 |
+
"step": 96
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 19.38,
|
628 |
+
"learning_rate": 0.00029099999999999997,
|
629 |
+
"loss": 0.7657,
|
630 |
+
"step": 97
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 19.57,
|
634 |
+
"learning_rate": 0.000294,
|
635 |
+
"loss": 0.724,
|
636 |
+
"step": 98
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 19.76,
|
640 |
+
"learning_rate": 0.00029699999999999996,
|
641 |
+
"loss": 0.4878,
|
642 |
+
"step": 99
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 19.95,
|
646 |
+
"learning_rate": 0.0003,
|
647 |
+
"loss": 0.5455,
|
648 |
+
"step": 100
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 19.95,
|
652 |
+
"eval_accuracy": 0.7269503546099291,
|
653 |
+
"eval_f1": 0.6991854490807772,
|
654 |
+
"eval_loss": 1.0403251647949219,
|
655 |
+
"eval_runtime": 16.2432,
|
656 |
+
"eval_samples_per_second": 17.361,
|
657 |
+
"eval_steps_per_second": 1.108,
|
658 |
+
"step": 100
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 20.19,
|
662 |
+
"learning_rate": 0.000298,
|
663 |
+
"loss": 0.7783,
|
664 |
+
"step": 101
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 20.38,
|
668 |
+
"learning_rate": 0.000296,
|
669 |
+
"loss": 0.6694,
|
670 |
+
"step": 102
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 20.57,
|
674 |
+
"learning_rate": 0.000294,
|
675 |
+
"loss": 0.504,
|
676 |
+
"step": 103
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 20.76,
|
680 |
+
"learning_rate": 0.000292,
|
681 |
+
"loss": 0.3801,
|
682 |
+
"step": 104
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 20.95,
|
686 |
+
"learning_rate": 0.00029,
|
687 |
+
"loss": 0.7225,
|
688 |
+
"step": 105
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 21.19,
|
692 |
+
"learning_rate": 0.00028799999999999995,
|
693 |
+
"loss": 0.8528,
|
694 |
+
"step": 106
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 21.38,
|
698 |
+
"learning_rate": 0.00028599999999999996,
|
699 |
+
"loss": 1.0327,
|
700 |
+
"step": 107
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 21.57,
|
704 |
+
"learning_rate": 0.00028399999999999996,
|
705 |
+
"loss": 1.0904,
|
706 |
+
"step": 108
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 21.76,
|
710 |
+
"learning_rate": 0.00028199999999999997,
|
711 |
+
"loss": 0.6435,
|
712 |
+
"step": 109
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 21.95,
|
716 |
+
"learning_rate": 0.00028,
|
717 |
+
"loss": 0.5316,
|
718 |
+
"step": 110
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 22.19,
|
722 |
+
"learning_rate": 0.000278,
|
723 |
+
"loss": 0.5442,
|
724 |
+
"step": 111
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 22.38,
|
728 |
+
"learning_rate": 0.000276,
|
729 |
+
"loss": 0.4732,
|
730 |
+
"step": 112
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 22.57,
|
734 |
+
"learning_rate": 0.000274,
|
735 |
+
"loss": 0.3529,
|
736 |
+
"step": 113
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 22.76,
|
740 |
+
"learning_rate": 0.00027199999999999994,
|
741 |
+
"loss": 0.4958,
|
742 |
+
"step": 114
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 22.95,
|
746 |
+
"learning_rate": 0.00027,
|
747 |
+
"loss": 0.6046,
|
748 |
+
"step": 115
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 23.19,
|
752 |
+
"learning_rate": 0.00026799999999999995,
|
753 |
+
"loss": 0.4016,
|
754 |
+
"step": 116
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 23.38,
|
758 |
+
"learning_rate": 0.000266,
|
759 |
+
"loss": 0.5724,
|
760 |
+
"step": 117
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 23.57,
|
764 |
+
"learning_rate": 0.00026399999999999997,
|
765 |
+
"loss": 0.3282,
|
766 |
+
"step": 118
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 23.76,
|
770 |
+
"learning_rate": 0.00026199999999999997,
|
771 |
+
"loss": 0.3314,
|
772 |
+
"step": 119
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 23.95,
|
776 |
+
"learning_rate": 0.00026,
|
777 |
+
"loss": 0.2571,
|
778 |
+
"step": 120
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 23.95,
|
782 |
+
"eval_accuracy": 0.8120567375886525,
|
783 |
+
"eval_f1": 0.81601355118773,
|
784 |
+
"eval_loss": 0.8423281311988831,
|
785 |
+
"eval_runtime": 16.3321,
|
786 |
+
"eval_samples_per_second": 17.267,
|
787 |
+
"eval_steps_per_second": 1.102,
|
788 |
+
"step": 120
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 24.19,
|
792 |
+
"learning_rate": 0.000258,
|
793 |
+
"loss": 0.3314,
|
794 |
+
"step": 121
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 24.38,
|
798 |
+
"learning_rate": 0.000256,
|
799 |
+
"loss": 0.214,
|
800 |
+
"step": 122
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 24.57,
|
804 |
+
"learning_rate": 0.000254,
|
805 |
+
"loss": 0.2825,
|
806 |
+
"step": 123
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 24.76,
|
810 |
+
"learning_rate": 0.00025199999999999995,
|
811 |
+
"loss": 0.5121,
|
812 |
+
"step": 124
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 24.95,
|
816 |
+
"learning_rate": 0.00025,
|
817 |
+
"loss": 0.3832,
|
818 |
+
"step": 125
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 25.19,
|
822 |
+
"learning_rate": 0.00024799999999999996,
|
823 |
+
"loss": 0.5013,
|
824 |
+
"step": 126
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 25.38,
|
828 |
+
"learning_rate": 0.00024599999999999996,
|
829 |
+
"loss": 0.3286,
|
830 |
+
"step": 127
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 25.57,
|
834 |
+
"learning_rate": 0.000244,
|
835 |
+
"loss": 0.2521,
|
836 |
+
"step": 128
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 25.76,
|
840 |
+
"learning_rate": 0.00024199999999999997,
|
841 |
+
"loss": 0.2546,
|
842 |
+
"step": 129
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 25.95,
|
846 |
+
"learning_rate": 0.00023999999999999998,
|
847 |
+
"loss": 0.1844,
|
848 |
+
"step": 130
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 26.19,
|
852 |
+
"learning_rate": 0.00023799999999999998,
|
853 |
+
"loss": 0.3035,
|
854 |
+
"step": 131
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 26.38,
|
858 |
+
"learning_rate": 0.00023599999999999996,
|
859 |
+
"loss": 0.2392,
|
860 |
+
"step": 132
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 26.57,
|
864 |
+
"learning_rate": 0.000234,
|
865 |
+
"loss": 0.5093,
|
866 |
+
"step": 133
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 26.76,
|
870 |
+
"learning_rate": 0.00023199999999999997,
|
871 |
+
"loss": 0.8045,
|
872 |
+
"step": 134
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 26.95,
|
876 |
+
"learning_rate": 0.00023,
|
877 |
+
"loss": 0.1891,
|
878 |
+
"step": 135
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 27.19,
|
882 |
+
"learning_rate": 0.00022799999999999999,
|
883 |
+
"loss": 0.2445,
|
884 |
+
"step": 136
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 27.38,
|
888 |
+
"learning_rate": 0.00022599999999999996,
|
889 |
+
"loss": 0.2789,
|
890 |
+
"step": 137
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 27.57,
|
894 |
+
"learning_rate": 0.000224,
|
895 |
+
"loss": 0.179,
|
896 |
+
"step": 138
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 27.76,
|
900 |
+
"learning_rate": 0.00022199999999999998,
|
901 |
+
"loss": 0.2237,
|
902 |
+
"step": 139
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 27.95,
|
906 |
+
"learning_rate": 0.00021999999999999995,
|
907 |
+
"loss": 0.3478,
|
908 |
+
"step": 140
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 27.95,
|
912 |
+
"eval_accuracy": 0.8439716312056738,
|
913 |
+
"eval_f1": 0.851591970396411,
|
914 |
+
"eval_loss": 0.6499652862548828,
|
915 |
+
"eval_runtime": 16.333,
|
916 |
+
"eval_samples_per_second": 17.266,
|
917 |
+
"eval_steps_per_second": 1.102,
|
918 |
+
"step": 140
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 28.19,
|
922 |
+
"learning_rate": 0.00021799999999999999,
|
923 |
+
"loss": 0.4559,
|
924 |
+
"step": 141
|
925 |
+
},
|
926 |
+
{
|
927 |
+
"epoch": 28.38,
|
928 |
+
"learning_rate": 0.00021599999999999996,
|
929 |
+
"loss": 0.2259,
|
930 |
+
"step": 142
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 28.57,
|
934 |
+
"learning_rate": 0.000214,
|
935 |
+
"loss": 0.412,
|
936 |
+
"step": 143
|
937 |
+
},
|
938 |
+
{
|
939 |
+
"epoch": 28.76,
|
940 |
+
"learning_rate": 0.00021199999999999998,
|
941 |
+
"loss": 0.4065,
|
942 |
+
"step": 144
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 28.95,
|
946 |
+
"learning_rate": 0.00020999999999999998,
|
947 |
+
"loss": 0.1336,
|
948 |
+
"step": 145
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 29.19,
|
952 |
+
"learning_rate": 0.000208,
|
953 |
+
"loss": 0.1519,
|
954 |
+
"step": 146
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 29.38,
|
958 |
+
"learning_rate": 0.00020599999999999997,
|
959 |
+
"loss": 0.2387,
|
960 |
+
"step": 147
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 29.57,
|
964 |
+
"learning_rate": 0.000204,
|
965 |
+
"loss": 0.1746,
|
966 |
+
"step": 148
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 29.76,
|
970 |
+
"learning_rate": 0.00020199999999999998,
|
971 |
+
"loss": 0.5495,
|
972 |
+
"step": 149
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 29.95,
|
976 |
+
"learning_rate": 0.00019999999999999998,
|
977 |
+
"loss": 0.3561,
|
978 |
+
"step": 150
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 30.19,
|
982 |
+
"learning_rate": 0.000198,
|
983 |
+
"loss": 0.1945,
|
984 |
+
"step": 151
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 30.38,
|
988 |
+
"learning_rate": 0.00019599999999999997,
|
989 |
+
"loss": 0.1289,
|
990 |
+
"step": 152
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 30.57,
|
994 |
+
"learning_rate": 0.00019399999999999997,
|
995 |
+
"loss": 0.133,
|
996 |
+
"step": 153
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 30.76,
|
1000 |
+
"learning_rate": 0.00019199999999999998,
|
1001 |
+
"loss": 0.1371,
|
1002 |
+
"step": 154
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 30.95,
|
1006 |
+
"learning_rate": 0.00018999999999999998,
|
1007 |
+
"loss": 0.1858,
|
1008 |
+
"step": 155
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 31.19,
|
1012 |
+
"learning_rate": 0.000188,
|
1013 |
+
"loss": 0.1205,
|
1014 |
+
"step": 156
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 31.38,
|
1018 |
+
"learning_rate": 0.000186,
|
1019 |
+
"loss": 0.1084,
|
1020 |
+
"step": 157
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 31.57,
|
1024 |
+
"learning_rate": 0.00018399999999999997,
|
1025 |
+
"loss": 0.125,
|
1026 |
+
"step": 158
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 31.76,
|
1030 |
+
"learning_rate": 0.00018199999999999998,
|
1031 |
+
"loss": 0.2521,
|
1032 |
+
"step": 159
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 31.95,
|
1036 |
+
"learning_rate": 0.00017999999999999998,
|
1037 |
+
"loss": 0.0732,
|
1038 |
+
"step": 160
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 31.95,
|
1042 |
+
"eval_accuracy": 0.8156028368794326,
|
1043 |
+
"eval_f1": 0.812294475915318,
|
1044 |
+
"eval_loss": 0.7066314816474915,
|
1045 |
+
"eval_runtime": 16.2944,
|
1046 |
+
"eval_samples_per_second": 17.307,
|
1047 |
+
"eval_steps_per_second": 1.105,
|
1048 |
+
"step": 160
|
1049 |
+
},
|
1050 |
+
{
|
1051 |
+
"epoch": 32.19,
|
1052 |
+
"learning_rate": 0.000178,
|
1053 |
+
"loss": 0.1074,
|
1054 |
+
"step": 161
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 32.38,
|
1058 |
+
"learning_rate": 0.000176,
|
1059 |
+
"loss": 0.0687,
|
1060 |
+
"step": 162
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 32.57,
|
1064 |
+
"learning_rate": 0.00017399999999999997,
|
1065 |
+
"loss": 0.2088,
|
1066 |
+
"step": 163
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 32.76,
|
1070 |
+
"learning_rate": 0.000172,
|
1071 |
+
"loss": 0.0658,
|
1072 |
+
"step": 164
|
1073 |
+
},
|
1074 |
+
{
|
1075 |
+
"epoch": 32.95,
|
1076 |
+
"learning_rate": 0.00016999999999999999,
|
1077 |
+
"loss": 0.1021,
|
1078 |
+
"step": 165
|
1079 |
+
},
|
1080 |
+
{
|
1081 |
+
"epoch": 33.19,
|
1082 |
+
"learning_rate": 0.000168,
|
1083 |
+
"loss": 0.0714,
|
1084 |
+
"step": 166
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 33.38,
|
1088 |
+
"learning_rate": 0.000166,
|
1089 |
+
"loss": 0.055,
|
1090 |
+
"step": 167
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 33.57,
|
1094 |
+
"learning_rate": 0.00016399999999999997,
|
1095 |
+
"loss": 0.0711,
|
1096 |
+
"step": 168
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 33.76,
|
1100 |
+
"learning_rate": 0.000162,
|
1101 |
+
"loss": 0.1285,
|
1102 |
+
"step": 169
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 33.95,
|
1106 |
+
"learning_rate": 0.00015999999999999999,
|
1107 |
+
"loss": 0.0777,
|
1108 |
+
"step": 170
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 34.19,
|
1112 |
+
"learning_rate": 0.00015799999999999996,
|
1113 |
+
"loss": 0.0951,
|
1114 |
+
"step": 171
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 34.38,
|
1118 |
+
"learning_rate": 0.000156,
|
1119 |
+
"loss": 0.1975,
|
1120 |
+
"step": 172
|
1121 |
+
},
|
1122 |
+
{
|
1123 |
+
"epoch": 34.57,
|
1124 |
+
"learning_rate": 0.00015399999999999998,
|
1125 |
+
"loss": 0.0395,
|
1126 |
+
"step": 173
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"epoch": 34.76,
|
1130 |
+
"learning_rate": 0.000152,
|
1131 |
+
"loss": 0.0471,
|
1132 |
+
"step": 174
|
1133 |
+
},
|
1134 |
+
{
|
1135 |
+
"epoch": 34.95,
|
1136 |
+
"learning_rate": 0.00015,
|
1137 |
+
"loss": 0.1489,
|
1138 |
+
"step": 175
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 35.19,
|
1142 |
+
"learning_rate": 0.000148,
|
1143 |
+
"loss": 0.0512,
|
1144 |
+
"step": 176
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 35.38,
|
1148 |
+
"learning_rate": 0.000146,
|
1149 |
+
"loss": 0.3909,
|
1150 |
+
"step": 177
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 35.57,
|
1154 |
+
"learning_rate": 0.00014399999999999998,
|
1155 |
+
"loss": 0.0396,
|
1156 |
+
"step": 178
|
1157 |
+
},
|
1158 |
+
{
|
1159 |
+
"epoch": 35.76,
|
1160 |
+
"learning_rate": 0.00014199999999999998,
|
1161 |
+
"loss": 0.0473,
|
1162 |
+
"step": 179
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 35.95,
|
1166 |
+
"learning_rate": 0.00014199999999999998,
|
1167 |
+
"loss": 0.1092,
|
1168 |
+
"step": 180
|
1169 |
+
},
|
1170 |
+
{
|
1171 |
+
"epoch": 35.95,
|
1172 |
+
"eval_accuracy": 0.875886524822695,
|
1173 |
+
"eval_f1": 0.8766602604385049,
|
1174 |
+
"eval_loss": 0.5878153443336487,
|
1175 |
+
"eval_runtime": 16.268,
|
1176 |
+
"eval_samples_per_second": 17.335,
|
1177 |
+
"eval_steps_per_second": 1.106,
|
1178 |
+
"step": 180
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 36.19,
|
1182 |
+
"learning_rate": 0.00014,
|
1183 |
+
"loss": 0.0433,
|
1184 |
+
"step": 181
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 36.38,
|
1188 |
+
"learning_rate": 0.000138,
|
1189 |
+
"loss": 0.0424,
|
1190 |
+
"step": 182
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 36.57,
|
1194 |
+
"learning_rate": 0.00013599999999999997,
|
1195 |
+
"loss": 0.0325,
|
1196 |
+
"step": 183
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 36.76,
|
1200 |
+
"learning_rate": 0.00013399999999999998,
|
1201 |
+
"loss": 0.0357,
|
1202 |
+
"step": 184
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 36.95,
|
1206 |
+
"learning_rate": 0.00013199999999999998,
|
1207 |
+
"loss": 0.043,
|
1208 |
+
"step": 185
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 37.19,
|
1212 |
+
"learning_rate": 0.00013,
|
1213 |
+
"loss": 0.1738,
|
1214 |
+
"step": 186
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 37.38,
|
1218 |
+
"learning_rate": 0.000128,
|
1219 |
+
"loss": 0.1993,
|
1220 |
+
"step": 187
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 37.57,
|
1224 |
+
"learning_rate": 0.00012599999999999997,
|
1225 |
+
"loss": 0.061,
|
1226 |
+
"step": 188
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 37.76,
|
1230 |
+
"learning_rate": 0.00012399999999999998,
|
1231 |
+
"loss": 0.0337,
|
1232 |
+
"step": 189
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 37.95,
|
1236 |
+
"learning_rate": 0.000122,
|
1237 |
+
"loss": 0.0306,
|
1238 |
+
"step": 190
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 38.19,
|
1242 |
+
"learning_rate": 0.00011999999999999999,
|
1243 |
+
"loss": 0.041,
|
1244 |
+
"step": 191
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 38.38,
|
1248 |
+
"learning_rate": 0.00011799999999999998,
|
1249 |
+
"loss": 0.1831,
|
1250 |
+
"step": 192
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 38.57,
|
1254 |
+
"learning_rate": 0.00011599999999999999,
|
1255 |
+
"loss": 0.0457,
|
1256 |
+
"step": 193
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 38.76,
|
1260 |
+
"learning_rate": 0.00011399999999999999,
|
1261 |
+
"loss": 0.2698,
|
1262 |
+
"step": 194
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 38.95,
|
1266 |
+
"learning_rate": 0.000112,
|
1267 |
+
"loss": 0.1268,
|
1268 |
+
"step": 195
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 39.19,
|
1272 |
+
"learning_rate": 0.00010999999999999998,
|
1273 |
+
"loss": 0.0408,
|
1274 |
+
"step": 196
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 39.38,
|
1278 |
+
"learning_rate": 0.00010799999999999998,
|
1279 |
+
"loss": 0.1086,
|
1280 |
+
"step": 197
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 39.57,
|
1284 |
+
"learning_rate": 0.00010599999999999999,
|
1285 |
+
"loss": 0.0435,
|
1286 |
+
"step": 198
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 39.76,
|
1290 |
+
"learning_rate": 0.000104,
|
1291 |
+
"loss": 0.1343,
|
1292 |
+
"step": 199
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 39.95,
|
1296 |
+
"learning_rate": 0.000102,
|
1297 |
+
"loss": 0.0271,
|
1298 |
+
"step": 200
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 39.95,
|
1302 |
+
"eval_accuracy": 0.8617021276595744,
|
1303 |
+
"eval_f1": 0.8578022762116569,
|
1304 |
+
"eval_loss": 0.5993813872337341,
|
1305 |
+
"eval_runtime": 16.2429,
|
1306 |
+
"eval_samples_per_second": 17.361,
|
1307 |
+
"eval_steps_per_second": 1.108,
|
1308 |
+
"step": 200
|
1309 |
+
},
|
1310 |
+
{
|
1311 |
+
"epoch": 40.19,
|
1312 |
+
"learning_rate": 9.999999999999999e-05,
|
1313 |
+
"loss": 0.0756,
|
1314 |
+
"step": 201
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 40.38,
|
1318 |
+
"learning_rate": 9.799999999999998e-05,
|
1319 |
+
"loss": 0.0385,
|
1320 |
+
"step": 202
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 40.57,
|
1324 |
+
"learning_rate": 9.599999999999999e-05,
|
1325 |
+
"loss": 0.0659,
|
1326 |
+
"step": 203
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 40.76,
|
1330 |
+
"learning_rate": 9.4e-05,
|
1331 |
+
"loss": 0.0579,
|
1332 |
+
"step": 204
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 40.95,
|
1336 |
+
"learning_rate": 9.199999999999999e-05,
|
1337 |
+
"loss": 0.031,
|
1338 |
+
"step": 205
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 41.19,
|
1342 |
+
"learning_rate": 8.999999999999999e-05,
|
1343 |
+
"loss": 0.0363,
|
1344 |
+
"step": 206
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 41.38,
|
1348 |
+
"learning_rate": 8.8e-05,
|
1349 |
+
"loss": 0.0857,
|
1350 |
+
"step": 207
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 41.57,
|
1354 |
+
"learning_rate": 8.6e-05,
|
1355 |
+
"loss": 0.0338,
|
1356 |
+
"step": 208
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 41.76,
|
1360 |
+
"learning_rate": 8.4e-05,
|
1361 |
+
"loss": 0.0378,
|
1362 |
+
"step": 209
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 41.95,
|
1366 |
+
"learning_rate": 8.199999999999999e-05,
|
1367 |
+
"loss": 0.0263,
|
1368 |
+
"step": 210
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 42.19,
|
1372 |
+
"learning_rate": 7.999999999999999e-05,
|
1373 |
+
"loss": 0.0433,
|
1374 |
+
"step": 211
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 42.38,
|
1378 |
+
"learning_rate": 7.8e-05,
|
1379 |
+
"loss": 0.0274,
|
1380 |
+
"step": 212
|
1381 |
+
},
|
1382 |
+
{
|
1383 |
+
"epoch": 42.57,
|
1384 |
+
"learning_rate": 7.6e-05,
|
1385 |
+
"loss": 0.0433,
|
1386 |
+
"step": 213
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 42.76,
|
1390 |
+
"learning_rate": 7.4e-05,
|
1391 |
+
"loss": 0.0698,
|
1392 |
+
"step": 214
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 42.95,
|
1396 |
+
"learning_rate": 7.199999999999999e-05,
|
1397 |
+
"loss": 0.0217,
|
1398 |
+
"step": 215
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 43.19,
|
1402 |
+
"learning_rate": 7e-05,
|
1403 |
+
"loss": 0.0471,
|
1404 |
+
"step": 216
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 43.38,
|
1408 |
+
"learning_rate": 6.799999999999999e-05,
|
1409 |
+
"loss": 0.0226,
|
1410 |
+
"step": 217
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 43.57,
|
1414 |
+
"learning_rate": 6.599999999999999e-05,
|
1415 |
+
"loss": 0.0224,
|
1416 |
+
"step": 218
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 43.76,
|
1420 |
+
"learning_rate": 6.4e-05,
|
1421 |
+
"loss": 0.0214,
|
1422 |
+
"step": 219
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 43.95,
|
1426 |
+
"learning_rate": 6.199999999999999e-05,
|
1427 |
+
"loss": 0.4664,
|
1428 |
+
"step": 220
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 43.95,
|
1432 |
+
"eval_accuracy": 0.8439716312056738,
|
1433 |
+
"eval_f1": 0.8402871437379335,
|
1434 |
+
"eval_loss": 0.7830185890197754,
|
1435 |
+
"eval_runtime": 16.2374,
|
1436 |
+
"eval_samples_per_second": 17.367,
|
1437 |
+
"eval_steps_per_second": 1.109,
|
1438 |
+
"step": 220
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 44.19,
|
1442 |
+
"learning_rate": 5.9999999999999995e-05,
|
1443 |
+
"loss": 0.3105,
|
1444 |
+
"step": 221
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 44.38,
|
1448 |
+
"learning_rate": 5.7999999999999994e-05,
|
1449 |
+
"loss": 0.081,
|
1450 |
+
"step": 222
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 44.57,
|
1454 |
+
"learning_rate": 5.6e-05,
|
1455 |
+
"loss": 0.0277,
|
1456 |
+
"step": 223
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 44.76,
|
1460 |
+
"learning_rate": 5.399999999999999e-05,
|
1461 |
+
"loss": 0.0273,
|
1462 |
+
"step": 224
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"epoch": 44.95,
|
1466 |
+
"learning_rate": 5.2e-05,
|
1467 |
+
"loss": 0.0269,
|
1468 |
+
"step": 225
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 45.19,
|
1472 |
+
"learning_rate": 4.9999999999999996e-05,
|
1473 |
+
"loss": 0.0394,
|
1474 |
+
"step": 226
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 45.38,
|
1478 |
+
"learning_rate": 4.7999999999999994e-05,
|
1479 |
+
"loss": 0.0699,
|
1480 |
+
"step": 227
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 45.57,
|
1484 |
+
"learning_rate": 4.599999999999999e-05,
|
1485 |
+
"loss": 0.0639,
|
1486 |
+
"step": 228
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 45.76,
|
1490 |
+
"learning_rate": 4.4e-05,
|
1491 |
+
"loss": 0.02,
|
1492 |
+
"step": 229
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 45.95,
|
1496 |
+
"learning_rate": 4.2e-05,
|
1497 |
+
"loss": 0.0237,
|
1498 |
+
"step": 230
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 46.19,
|
1502 |
+
"learning_rate": 3.9999999999999996e-05,
|
1503 |
+
"loss": 0.0268,
|
1504 |
+
"step": 231
|
1505 |
+
},
|
1506 |
+
{
|
1507 |
+
"epoch": 46.38,
|
1508 |
+
"learning_rate": 3.8e-05,
|
1509 |
+
"loss": 0.0195,
|
1510 |
+
"step": 232
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 46.57,
|
1514 |
+
"learning_rate": 3.5999999999999994e-05,
|
1515 |
+
"loss": 0.0199,
|
1516 |
+
"step": 233
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"epoch": 46.76,
|
1520 |
+
"learning_rate": 3.399999999999999e-05,
|
1521 |
+
"loss": 0.0205,
|
1522 |
+
"step": 234
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 46.95,
|
1526 |
+
"learning_rate": 3.2e-05,
|
1527 |
+
"loss": 0.0231,
|
1528 |
+
"step": 235
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 47.19,
|
1532 |
+
"learning_rate": 2.9999999999999997e-05,
|
1533 |
+
"loss": 0.0242,
|
1534 |
+
"step": 236
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 47.38,
|
1538 |
+
"learning_rate": 2.8e-05,
|
1539 |
+
"loss": 0.0219,
|
1540 |
+
"step": 237
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 47.57,
|
1544 |
+
"learning_rate": 2.6e-05,
|
1545 |
+
"loss": 0.0226,
|
1546 |
+
"step": 238
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 47.76,
|
1550 |
+
"learning_rate": 2.3999999999999997e-05,
|
1551 |
+
"loss": 0.0213,
|
1552 |
+
"step": 239
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 47.95,
|
1556 |
+
"learning_rate": 2.2e-05,
|
1557 |
+
"loss": 0.0192,
|
1558 |
+
"step": 240
|
1559 |
+
},
|
1560 |
+
{
|
1561 |
+
"epoch": 47.95,
|
1562 |
+
"eval_accuracy": 0.875886524822695,
|
1563 |
+
"eval_f1": 0.874718376861234,
|
1564 |
+
"eval_loss": 0.5684738159179688,
|
1565 |
+
"eval_runtime": 16.3149,
|
1566 |
+
"eval_samples_per_second": 17.285,
|
1567 |
+
"eval_steps_per_second": 1.103,
|
1568 |
+
"step": 240
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 48.19,
|
1572 |
+
"learning_rate": 1.9999999999999998e-05,
|
1573 |
+
"loss": 0.022,
|
1574 |
+
"step": 241
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 48.38,
|
1578 |
+
"learning_rate": 1.7999999999999997e-05,
|
1579 |
+
"loss": 0.02,
|
1580 |
+
"step": 242
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 48.57,
|
1584 |
+
"learning_rate": 1.6e-05,
|
1585 |
+
"loss": 0.0185,
|
1586 |
+
"step": 243
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 48.76,
|
1590 |
+
"learning_rate": 1.4e-05,
|
1591 |
+
"loss": 0.0185,
|
1592 |
+
"step": 244
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 48.95,
|
1596 |
+
"learning_rate": 1.1999999999999999e-05,
|
1597 |
+
"loss": 0.0207,
|
1598 |
+
"step": 245
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 49.19,
|
1602 |
+
"learning_rate": 9.999999999999999e-06,
|
1603 |
+
"loss": 0.1504,
|
1604 |
+
"step": 246
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 49.38,
|
1608 |
+
"learning_rate": 8e-06,
|
1609 |
+
"loss": 0.0932,
|
1610 |
+
"step": 247
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 49.57,
|
1614 |
+
"learning_rate": 5.999999999999999e-06,
|
1615 |
+
"loss": 0.0191,
|
1616 |
+
"step": 248
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 49.76,
|
1620 |
+
"learning_rate": 4e-06,
|
1621 |
+
"loss": 0.0204,
|
1622 |
+
"step": 249
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 49.95,
|
1626 |
+
"learning_rate": 2e-06,
|
1627 |
+
"loss": 0.0192,
|
1628 |
+
"step": 250
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 49.95,
|
1632 |
+
"step": 250,
|
1633 |
+
"total_flos": 2.2169595227007877e+18,
|
1634 |
+
"train_loss": 0.970869776725769,
|
1635 |
+
"train_runtime": 888.1973,
|
1636 |
+
"train_samples_per_second": 9.401,
|
1637 |
+
"train_steps_per_second": 0.281
|
1638 |
+
}
|
1639 |
+
],
|
1640 |
+
"max_steps": 250,
|
1641 |
+
"num_train_epochs": 50,
|
1642 |
+
"total_flos": 2.2169595227007877e+18,
|
1643 |
+
"trial_name": null,
|
1644 |
+
"trial_params": null
|
1645 |
+
}
|