noflm
commited on
Commit
•
fd7bcb7
1
Parent(s):
81dd039
End of training
Browse files- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec24_15-42-50_srv/events.out.tfevents.1671920410.srv.1557.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +130 -0
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 294.0,
|
3 |
+
"eval_loss": 0.15023881196975708,
|
4 |
+
"eval_runtime": 12.4887,
|
5 |
+
"eval_samples_per_second": 1.441,
|
6 |
+
"eval_steps_per_second": 0.24,
|
7 |
+
"eval_wer": 4.878048780487805,
|
8 |
+
"train_loss": 0.006433991515403613,
|
9 |
+
"train_runtime": 23651.0479,
|
10 |
+
"train_samples_per_second": 3.383,
|
11 |
+
"train_steps_per_second": 0.211
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 294.0,
|
3 |
+
"eval_loss": 0.15023881196975708,
|
4 |
+
"eval_runtime": 12.4887,
|
5 |
+
"eval_samples_per_second": 1.441,
|
6 |
+
"eval_steps_per_second": 0.24,
|
7 |
+
"eval_wer": 4.878048780487805
|
8 |
+
}
|
runs/Dec24_15-42-50_srv/events.out.tfevents.1671920410.srv.1557.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851a5e056b2282aa6d1ee98acacd85adfc2a7dac5c8d05e7a5c541c9a4594d90
|
3 |
+
size 358
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 294.0,
|
3 |
+
"train_loss": 0.006433991515403613,
|
4 |
+
"train_runtime": 23651.0479,
|
5 |
+
"train_samples_per_second": 3.383,
|
6 |
+
"train_steps_per_second": 0.211
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 294.0004,
|
5 |
+
"global_step": 5000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 29.0,
|
12 |
+
"learning_rate": 1e-05,
|
13 |
+
"loss": 0.0638,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 58.0,
|
18 |
+
"learning_rate": 1e-05,
|
19 |
+
"loss": 0.0004,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 58.0,
|
24 |
+
"eval_loss": 0.11287793517112732,
|
25 |
+
"eval_runtime": 14.5402,
|
26 |
+
"eval_samples_per_second": 1.238,
|
27 |
+
"eval_steps_per_second": 0.206,
|
28 |
+
"eval_wer": 1.8292682926829267,
|
29 |
+
"step": 1000
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 88.0,
|
33 |
+
"learning_rate": 1e-05,
|
34 |
+
"loss": 0.0001,
|
35 |
+
"step": 1500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 117.0,
|
39 |
+
"learning_rate": 1e-05,
|
40 |
+
"loss": 0.0,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 117.0,
|
45 |
+
"eval_loss": 0.12321429699659348,
|
46 |
+
"eval_runtime": 12.3922,
|
47 |
+
"eval_samples_per_second": 1.453,
|
48 |
+
"eval_steps_per_second": 0.242,
|
49 |
+
"eval_wer": 1.8292682926829267,
|
50 |
+
"step": 2000
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 147.0,
|
54 |
+
"learning_rate": 1e-05,
|
55 |
+
"loss": 0.0,
|
56 |
+
"step": 2500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 176.0,
|
60 |
+
"learning_rate": 1e-05,
|
61 |
+
"loss": 0.0,
|
62 |
+
"step": 3000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 176.0,
|
66 |
+
"eval_loss": 0.13265825808048248,
|
67 |
+
"eval_runtime": 14.0309,
|
68 |
+
"eval_samples_per_second": 1.283,
|
69 |
+
"eval_steps_per_second": 0.214,
|
70 |
+
"eval_wer": 1.8292682926829267,
|
71 |
+
"step": 3000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 205.0,
|
75 |
+
"learning_rate": 1e-05,
|
76 |
+
"loss": 0.0,
|
77 |
+
"step": 3500
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 235.0,
|
81 |
+
"learning_rate": 1e-05,
|
82 |
+
"loss": 0.0,
|
83 |
+
"step": 4000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 235.0,
|
87 |
+
"eval_loss": 0.14010873436927795,
|
88 |
+
"eval_runtime": 12.2156,
|
89 |
+
"eval_samples_per_second": 1.474,
|
90 |
+
"eval_steps_per_second": 0.246,
|
91 |
+
"eval_wer": 4.878048780487805,
|
92 |
+
"step": 4000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 264.0,
|
96 |
+
"learning_rate": 1e-05,
|
97 |
+
"loss": 0.0,
|
98 |
+
"step": 4500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 294.0,
|
102 |
+
"learning_rate": 1e-05,
|
103 |
+
"loss": 0.0,
|
104 |
+
"step": 5000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 294.0,
|
108 |
+
"eval_loss": 0.15023881196975708,
|
109 |
+
"eval_runtime": 13.2184,
|
110 |
+
"eval_samples_per_second": 1.362,
|
111 |
+
"eval_steps_per_second": 0.227,
|
112 |
+
"eval_wer": 4.878048780487805,
|
113 |
+
"step": 5000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 294.0,
|
117 |
+
"step": 5000,
|
118 |
+
"total_flos": 2.30868320256e+19,
|
119 |
+
"train_loss": 0.006433991515403613,
|
120 |
+
"train_runtime": 23651.0479,
|
121 |
+
"train_samples_per_second": 3.383,
|
122 |
+
"train_steps_per_second": 0.211
|
123 |
+
}
|
124 |
+
],
|
125 |
+
"max_steps": 5000,
|
126 |
+
"num_train_epochs": 9223372036854775807,
|
127 |
+
"total_flos": 2.30868320256e+19,
|
128 |
+
"trial_name": null,
|
129 |
+
"trial_params": null
|
130 |
+
}
|