End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +115 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.96,
|
3 |
+
"total_flos": 5.347091052398592e+17,
|
4 |
+
"train_loss": 0.12152913654292072,
|
5 |
+
"train_runtime": 316.4284,
|
6 |
+
"train_samples_per_second": 22.09,
|
7 |
+
"train_steps_per_second": 0.341
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.96,
|
3 |
+
"total_flos": 5.347091052398592e+17,
|
4 |
+
"train_loss": 0.12152913654292072,
|
5 |
+
"train_runtime": 316.4284,
|
6 |
+
"train_samples_per_second": 22.09,
|
7 |
+
"train_steps_per_second": 0.341
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.972972972972973,
|
3 |
+
"best_model_checkpoint": "finetuned-vit-flowers/checkpoint-36",
|
4 |
+
"epoch": 2.958904109589041,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 108,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.27,
|
13 |
+
"learning_rate": 4.545454545454546e-05,
|
14 |
+
"loss": 0.1457,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.55,
|
19 |
+
"learning_rate": 4.536082474226804e-05,
|
20 |
+
"loss": 0.1297,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.82,
|
25 |
+
"learning_rate": 4.020618556701031e-05,
|
26 |
+
"loss": 0.1236,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.99,
|
31 |
+
"eval_accuracy": 0.972972972972973,
|
32 |
+
"eval_loss": 0.1508660614490509,
|
33 |
+
"eval_runtime": 5.2228,
|
34 |
+
"eval_samples_per_second": 49.59,
|
35 |
+
"eval_steps_per_second": 3.255,
|
36 |
+
"step": 36
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.1,
|
40 |
+
"learning_rate": 3.5051546391752576e-05,
|
41 |
+
"loss": 0.1215,
|
42 |
+
"step": 40
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.37,
|
46 |
+
"learning_rate": 2.9896907216494846e-05,
|
47 |
+
"loss": 0.1158,
|
48 |
+
"step": 50
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.64,
|
52 |
+
"learning_rate": 2.4742268041237116e-05,
|
53 |
+
"loss": 0.0942,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.92,
|
58 |
+
"learning_rate": 1.9587628865979382e-05,
|
59 |
+
"loss": 0.1043,
|
60 |
+
"step": 70
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 2.0,
|
64 |
+
"eval_accuracy": 0.972972972972973,
|
65 |
+
"eval_loss": 0.12350893765687943,
|
66 |
+
"eval_runtime": 5.8451,
|
67 |
+
"eval_samples_per_second": 44.311,
|
68 |
+
"eval_steps_per_second": 2.908,
|
69 |
+
"step": 73
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.19,
|
73 |
+
"learning_rate": 1.4432989690721649e-05,
|
74 |
+
"loss": 0.148,
|
75 |
+
"step": 80
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.47,
|
79 |
+
"learning_rate": 9.278350515463918e-06,
|
80 |
+
"loss": 0.1162,
|
81 |
+
"step": 90
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.74,
|
85 |
+
"learning_rate": 4.123711340206186e-06,
|
86 |
+
"loss": 0.1077,
|
87 |
+
"step": 100
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.96,
|
91 |
+
"eval_accuracy": 0.9652509652509652,
|
92 |
+
"eval_loss": 0.1365247368812561,
|
93 |
+
"eval_runtime": 5.8827,
|
94 |
+
"eval_samples_per_second": 44.028,
|
95 |
+
"eval_steps_per_second": 2.89,
|
96 |
+
"step": 108
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 2.96,
|
100 |
+
"step": 108,
|
101 |
+
"total_flos": 5.347091052398592e+17,
|
102 |
+
"train_loss": 0.12152913654292072,
|
103 |
+
"train_runtime": 316.4284,
|
104 |
+
"train_samples_per_second": 22.09,
|
105 |
+
"train_steps_per_second": 0.341
|
106 |
+
}
|
107 |
+
],
|
108 |
+
"logging_steps": 10,
|
109 |
+
"max_steps": 108,
|
110 |
+
"num_train_epochs": 3,
|
111 |
+
"save_steps": 500,
|
112 |
+
"total_flos": 5.347091052398592e+17,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|