Training in progress, epoch 0
Browse files
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.82,
|
3 |
+
"total_flos": 1.721344993041365e+18,
|
4 |
+
"train_loss": 0.6865291487086903,
|
5 |
+
"train_runtime": 716.0754,
|
6 |
+
"train_samples_per_second": 31.673,
|
7 |
+
"train_steps_per_second": 0.123
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343271789
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:171b2021dabf84ce6647f419f5de6135964a9ec30cb9c875977bf8f1e4ba8e2a
|
3 |
size 343271789
|
runs/Mar21_11-04-01_teesta/events.out.tfevents.1710999254.teesta.31117.0
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 sha256:696e803214b6c4b06dd6b36792d00ded9213f23af1e717c9309a8c2445858732
|
3 |
+
size 8133
|
runs/Mar21_11-19-01_teesta/events.out.tfevents.1711000150.teesta.35625.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40389e6a7b50a9bf13ba56fa14d905469adacda94959b444e44d4d136384c7ec
|
3 |
+
size 4489
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 7.82,
|
3 |
+
"total_flos": 1.721344993041365e+18,
|
4 |
+
"train_loss": 0.6865291487086903,
|
5 |
+
"train_runtime": 716.0754,
|
6 |
+
"train_samples_per_second": 31.673,
|
7 |
+
"train_steps_per_second": 0.123
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7334273624823695,
|
3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-harm-C/checkpoint-45",
|
4 |
+
"epoch": 7.822222222222222,
|
5 |
+
"global_step": 88,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.89,
|
12 |
+
"learning_rate": 0.00011848101265822785,
|
13 |
+
"loss": 0.9489,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.98,
|
18 |
+
"eval_accuracy": 0.6629055007052186,
|
19 |
+
"eval_loss": 0.7731553316116333,
|
20 |
+
"eval_runtime": 11.023,
|
21 |
+
"eval_samples_per_second": 64.32,
|
22 |
+
"eval_steps_per_second": 1.089,
|
23 |
+
"step": 11
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.78,
|
27 |
+
"learning_rate": 0.00010329113924050633,
|
28 |
+
"loss": 0.7902,
|
29 |
+
"step": 20
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.96,
|
33 |
+
"eval_accuracy": 0.7009873060648801,
|
34 |
+
"eval_loss": 0.7204822897911072,
|
35 |
+
"eval_runtime": 10.8566,
|
36 |
+
"eval_samples_per_second": 65.306,
|
37 |
+
"eval_steps_per_second": 1.105,
|
38 |
+
"step": 22
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.67,
|
42 |
+
"learning_rate": 8.810126582278482e-05,
|
43 |
+
"loss": 0.7452,
|
44 |
+
"step": 30
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.93,
|
48 |
+
"eval_accuracy": 0.7207334273624824,
|
49 |
+
"eval_loss": 0.6992235779762268,
|
50 |
+
"eval_runtime": 10.7875,
|
51 |
+
"eval_samples_per_second": 65.724,
|
52 |
+
"eval_steps_per_second": 1.112,
|
53 |
+
"step": 33
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 3.56,
|
57 |
+
"learning_rate": 7.29113924050633e-05,
|
58 |
+
"loss": 0.6899,
|
59 |
+
"step": 40
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.7334273624823695,
|
64 |
+
"eval_loss": 0.6885057687759399,
|
65 |
+
"eval_runtime": 11.0176,
|
66 |
+
"eval_samples_per_second": 64.351,
|
67 |
+
"eval_steps_per_second": 1.089,
|
68 |
+
"step": 45
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 4.44,
|
72 |
+
"learning_rate": 5.7721518987341775e-05,
|
73 |
+
"loss": 0.6788,
|
74 |
+
"step": 50
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 4.98,
|
78 |
+
"eval_accuracy": 0.7136812411847673,
|
79 |
+
"eval_loss": 0.6880338788032532,
|
80 |
+
"eval_runtime": 10.9845,
|
81 |
+
"eval_samples_per_second": 64.545,
|
82 |
+
"eval_steps_per_second": 1.092,
|
83 |
+
"step": 56
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 5.33,
|
87 |
+
"learning_rate": 4.253164556962025e-05,
|
88 |
+
"loss": 0.6116,
|
89 |
+
"step": 60
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 5.96,
|
93 |
+
"eval_accuracy": 0.7122708039492243,
|
94 |
+
"eval_loss": 0.6894987225532532,
|
95 |
+
"eval_runtime": 10.9278,
|
96 |
+
"eval_samples_per_second": 64.88,
|
97 |
+
"eval_steps_per_second": 1.098,
|
98 |
+
"step": 67
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.22,
|
102 |
+
"learning_rate": 2.7341772151898733e-05,
|
103 |
+
"loss": 0.5875,
|
104 |
+
"step": 70
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 6.93,
|
108 |
+
"eval_accuracy": 0.7193229901269393,
|
109 |
+
"eval_loss": 0.6877116560935974,
|
110 |
+
"eval_runtime": 10.9862,
|
111 |
+
"eval_samples_per_second": 64.535,
|
112 |
+
"eval_steps_per_second": 1.092,
|
113 |
+
"step": 78
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 7.11,
|
117 |
+
"learning_rate": 1.2151898734177216e-05,
|
118 |
+
"loss": 0.562,
|
119 |
+
"step": 80
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 7.82,
|
123 |
+
"eval_accuracy": 0.7136812411847673,
|
124 |
+
"eval_loss": 0.6862055659294128,
|
125 |
+
"eval_runtime": 10.9399,
|
126 |
+
"eval_samples_per_second": 64.809,
|
127 |
+
"eval_steps_per_second": 1.097,
|
128 |
+
"step": 88
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 7.82,
|
132 |
+
"step": 88,
|
133 |
+
"total_flos": 1.721344993041365e+18,
|
134 |
+
"train_loss": 0.6865291487086903,
|
135 |
+
"train_runtime": 716.0754,
|
136 |
+
"train_samples_per_second": 31.673,
|
137 |
+
"train_steps_per_second": 0.123
|
138 |
+
}
|
139 |
+
],
|
140 |
+
"max_steps": 88,
|
141 |
+
"num_train_epochs": 8,
|
142 |
+
"total_flos": 1.721344993041365e+18,
|
143 |
+
"trial_name": null,
|
144 |
+
"trial_params": null
|
145 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2a40b3f3644f4fb52825dc2a75da2c17f2436305d7b22d413184a2460550e19
|
3 |
size 3963
|