End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.1,
|
3 |
+
"eval_accuracy": 0.8888888888888888,
|
4 |
+
"eval_loss": 0.6103625893592834,
|
5 |
+
"eval_runtime": 22.37,
|
6 |
+
"eval_samples_per_second": 1.207,
|
7 |
+
"eval_steps_per_second": 0.179
|
8 |
+
}
|
runs/Jun15_21-16-09_DESKTOP-SGO0ICV/events.out.tfevents.1718457938.DESKTOP-SGO0ICV.160328.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:646470abc5b7ae71f0ba7427b68e1c80a2b70b9d640ea2ff07bfe2e27c06f72a
|
3 |
+
size 722
|
test_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.1,
|
3 |
+
"eval_accuracy": 0.8888888888888888,
|
4 |
+
"eval_loss": 0.6103625893592834,
|
5 |
+
"eval_runtime": 22.37,
|
6 |
+
"eval_samples_per_second": 1.207,
|
7 |
+
"eval_steps_per_second": 0.179
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.0,
|
3 |
+
"best_model_checkpoint": "videomae-base-ASD_Eye_Contact_v1\\checkpoint-8",
|
4 |
+
"epoch": 9.1,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"eval_accuracy": 0.23255813953488372,
|
14 |
+
"eval_loss": 0.778777539730072,
|
15 |
+
"eval_runtime": 23.3409,
|
16 |
+
"eval_samples_per_second": 1.842,
|
17 |
+
"eval_steps_per_second": 0.257,
|
18 |
+
"step": 1
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.1,
|
22 |
+
"eval_accuracy": 0.5581395348837209,
|
23 |
+
"eval_loss": 0.6848530769348145,
|
24 |
+
"eval_runtime": 48.989,
|
25 |
+
"eval_samples_per_second": 0.878,
|
26 |
+
"eval_steps_per_second": 0.122,
|
27 |
+
"step": 2
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.1,
|
31 |
+
"eval_accuracy": 0.9767441860465116,
|
32 |
+
"eval_loss": 0.6216737031936646,
|
33 |
+
"eval_runtime": 45.3106,
|
34 |
+
"eval_samples_per_second": 0.949,
|
35 |
+
"eval_steps_per_second": 0.132,
|
36 |
+
"step": 3
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.1,
|
40 |
+
"eval_accuracy": 0.9767441860465116,
|
41 |
+
"eval_loss": 0.566657543182373,
|
42 |
+
"eval_runtime": 35.6533,
|
43 |
+
"eval_samples_per_second": 1.206,
|
44 |
+
"eval_steps_per_second": 0.168,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 4.1,
|
49 |
+
"eval_accuracy": 0.9767441860465116,
|
50 |
+
"eval_loss": 0.5196951627731323,
|
51 |
+
"eval_runtime": 34.823,
|
52 |
+
"eval_samples_per_second": 1.235,
|
53 |
+
"eval_steps_per_second": 0.172,
|
54 |
+
"step": 5
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 5.1,
|
58 |
+
"eval_accuracy": 0.9767441860465116,
|
59 |
+
"eval_loss": 0.4812885522842407,
|
60 |
+
"eval_runtime": 34.865,
|
61 |
+
"eval_samples_per_second": 1.233,
|
62 |
+
"eval_steps_per_second": 0.172,
|
63 |
+
"step": 6
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 6.1,
|
67 |
+
"eval_accuracy": 0.9767441860465116,
|
68 |
+
"eval_loss": 0.4521254599094391,
|
69 |
+
"eval_runtime": 35.0776,
|
70 |
+
"eval_samples_per_second": 1.226,
|
71 |
+
"eval_steps_per_second": 0.171,
|
72 |
+
"step": 7
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 7.1,
|
76 |
+
"eval_accuracy": 1.0,
|
77 |
+
"eval_loss": 0.4295775294303894,
|
78 |
+
"eval_runtime": 34.919,
|
79 |
+
"eval_samples_per_second": 1.231,
|
80 |
+
"eval_steps_per_second": 0.172,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 8.1,
|
85 |
+
"eval_accuracy": 1.0,
|
86 |
+
"eval_loss": 0.4157649278640747,
|
87 |
+
"eval_runtime": 34.8052,
|
88 |
+
"eval_samples_per_second": 1.235,
|
89 |
+
"eval_steps_per_second": 0.172,
|
90 |
+
"step": 9
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 9.1,
|
94 |
+
"grad_norm": 3.7759058475494385,
|
95 |
+
"learning_rate": 0.0,
|
96 |
+
"loss": 0.5774,
|
97 |
+
"step": 10
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 9.1,
|
101 |
+
"eval_accuracy": 1.0,
|
102 |
+
"eval_loss": 0.40911319851875305,
|
103 |
+
"eval_runtime": 35.5192,
|
104 |
+
"eval_samples_per_second": 1.211,
|
105 |
+
"eval_steps_per_second": 0.169,
|
106 |
+
"step": 10
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 9.1,
|
110 |
+
"step": 10,
|
111 |
+
"total_flos": 9.968516715773952e+16,
|
112 |
+
"train_loss": 0.5774221897125245,
|
113 |
+
"train_runtime": 466.5566,
|
114 |
+
"train_samples_per_second": 0.171,
|
115 |
+
"train_steps_per_second": 0.021
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 9.1,
|
119 |
+
"eval_accuracy": 0.8888888888888888,
|
120 |
+
"eval_loss": 0.6103625297546387,
|
121 |
+
"eval_runtime": 23.2606,
|
122 |
+
"eval_samples_per_second": 1.161,
|
123 |
+
"eval_steps_per_second": 0.172,
|
124 |
+
"step": 10
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 9.1,
|
128 |
+
"eval_accuracy": 0.8888888888888888,
|
129 |
+
"eval_loss": 0.6103625893592834,
|
130 |
+
"eval_runtime": 22.37,
|
131 |
+
"eval_samples_per_second": 1.207,
|
132 |
+
"eval_steps_per_second": 0.179,
|
133 |
+
"step": 10
|
134 |
+
}
|
135 |
+
],
|
136 |
+
"logging_steps": 10,
|
137 |
+
"max_steps": 10,
|
138 |
+
"num_input_tokens_seen": 0,
|
139 |
+
"num_train_epochs": 9223372036854775807,
|
140 |
+
"save_steps": 500,
|
141 |
+
"stateful_callbacks": {
|
142 |
+
"TrainerControl": {
|
143 |
+
"args": {
|
144 |
+
"should_epoch_stop": false,
|
145 |
+
"should_evaluate": false,
|
146 |
+
"should_log": false,
|
147 |
+
"should_save": true,
|
148 |
+
"should_training_stop": true
|
149 |
+
},
|
150 |
+
"attributes": {}
|
151 |
+
}
|
152 |
+
},
|
153 |
+
"total_flos": 9.968516715773952e+16,
|
154 |
+
"train_batch_size": 8,
|
155 |
+
"trial_name": null,
|
156 |
+
"trial_params": null
|
157 |
+
}
|