anuragshas
commited on
Commit
•
3c23620
1
Parent(s):
a710f89
End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.47,
|
3 |
+
"eval_loss": 0.3451443016529083,
|
4 |
+
"eval_runtime": 1575.2104,
|
5 |
+
"eval_samples_per_second": 0.196,
|
6 |
+
"eval_steps_per_second": 0.025,
|
7 |
+
"eval_wer": 23.69608373939722,
|
8 |
+
"train_loss": 0.11590570814907551,
|
9 |
+
"train_runtime": 3725.2193,
|
10 |
+
"train_samples_per_second": 2.148,
|
11 |
+
"train_steps_per_second": 0.134
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.47,
|
3 |
+
"eval_loss": 0.3451443016529083,
|
4 |
+
"eval_runtime": 1575.2104,
|
5 |
+
"eval_samples_per_second": 0.196,
|
6 |
+
"eval_steps_per_second": 0.025,
|
7 |
+
"eval_wer": 23.69608373939722
|
8 |
+
}
|
runs/Dec12_22-23-45_129-213-87-7/events.out.tfevents.1670889380.129-213-87-7.2226053.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8baa0e4bb74da7b6a2825a23a6b45691f2eb30543bc3292f882800698b6aa2b
|
3 |
+
size 358
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.47,
|
3 |
+
"train_loss": 0.11590570814907551,
|
4 |
+
"train_runtime": 3725.2193,
|
5 |
+
"train_samples_per_second": 2.148,
|
6 |
+
"train_steps_per_second": 0.134
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.474576271186441,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.42,
|
12 |
+
"learning_rate": 4.600000000000001e-06,
|
13 |
+
"loss": 0.9141,
|
14 |
+
"step": 25
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.85,
|
18 |
+
"learning_rate": 9.200000000000002e-06,
|
19 |
+
"loss": 0.3615,
|
20 |
+
"step": 50
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.27,
|
24 |
+
"learning_rate": 9.533333333333334e-06,
|
25 |
+
"loss": 0.2375,
|
26 |
+
"step": 75
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.69,
|
30 |
+
"learning_rate": 8.977777777777778e-06,
|
31 |
+
"loss": 0.1874,
|
32 |
+
"step": 100
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.12,
|
36 |
+
"learning_rate": 8.422222222222223e-06,
|
37 |
+
"loss": 0.1611,
|
38 |
+
"step": 125
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.54,
|
42 |
+
"learning_rate": 7.866666666666667e-06,
|
43 |
+
"loss": 0.103,
|
44 |
+
"step": 150
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.97,
|
48 |
+
"learning_rate": 7.3111111111111125e-06,
|
49 |
+
"loss": 0.1012,
|
50 |
+
"step": 175
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.39,
|
54 |
+
"learning_rate": 6.755555555555556e-06,
|
55 |
+
"loss": 0.0549,
|
56 |
+
"step": 200
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.81,
|
60 |
+
"learning_rate": 6.200000000000001e-06,
|
61 |
+
"loss": 0.055,
|
62 |
+
"step": 225
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 4.24,
|
66 |
+
"learning_rate": 5.6444444444444445e-06,
|
67 |
+
"loss": 0.038,
|
68 |
+
"step": 250
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 4.66,
|
72 |
+
"learning_rate": 5.088888888888889e-06,
|
73 |
+
"loss": 0.0305,
|
74 |
+
"step": 275
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.08,
|
78 |
+
"learning_rate": 4.533333333333334e-06,
|
79 |
+
"loss": 0.0272,
|
80 |
+
"step": 300
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.51,
|
84 |
+
"learning_rate": 3.977777777777778e-06,
|
85 |
+
"loss": 0.012,
|
86 |
+
"step": 325
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 5.93,
|
90 |
+
"learning_rate": 3.4222222222222224e-06,
|
91 |
+
"loss": 0.0133,
|
92 |
+
"step": 350
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 6.36,
|
96 |
+
"learning_rate": 2.866666666666667e-06,
|
97 |
+
"loss": 0.0077,
|
98 |
+
"step": 375
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.78,
|
102 |
+
"learning_rate": 2.311111111111111e-06,
|
103 |
+
"loss": 0.0058,
|
104 |
+
"step": 400
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.2,
|
108 |
+
"learning_rate": 1.7555555555555556e-06,
|
109 |
+
"loss": 0.0039,
|
110 |
+
"step": 425
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.63,
|
114 |
+
"learning_rate": 1.2000000000000002e-06,
|
115 |
+
"loss": 0.0019,
|
116 |
+
"step": 450
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 8.05,
|
120 |
+
"learning_rate": 6.444444444444445e-07,
|
121 |
+
"loss": 0.0016,
|
122 |
+
"step": 475
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 8.47,
|
126 |
+
"learning_rate": 8.88888888888889e-08,
|
127 |
+
"loss": 0.0008,
|
128 |
+
"step": 500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.47,
|
132 |
+
"eval_loss": 0.3451443016529083,
|
133 |
+
"eval_runtime": 1585.5901,
|
134 |
+
"eval_samples_per_second": 0.194,
|
135 |
+
"eval_steps_per_second": 0.025,
|
136 |
+
"eval_wer": 23.69608373939722,
|
137 |
+
"step": 500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 8.47,
|
141 |
+
"step": 500,
|
142 |
+
"total_flos": 1.68834559574016e+19,
|
143 |
+
"train_loss": 0.11590570814907551,
|
144 |
+
"train_runtime": 3725.2193,
|
145 |
+
"train_samples_per_second": 2.148,
|
146 |
+
"train_steps_per_second": 0.134
|
147 |
+
}
|
148 |
+
],
|
149 |
+
"max_steps": 500,
|
150 |
+
"num_train_epochs": 9,
|
151 |
+
"total_flos": 1.68834559574016e+19,
|
152 |
+
"trial_name": null,
|
153 |
+
"trial_params": null
|
154 |
+
}
|