Upload 8 files
Browse files- config.json +52 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +925 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_first_stage": false,
|
13 |
+
"embedding_size": 64,
|
14 |
+
"hidden_act": "relu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
256,
|
17 |
+
512,
|
18 |
+
1024,
|
19 |
+
2048
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "skinny",
|
23 |
+
"1": "ordinary",
|
24 |
+
"2": "overweight",
|
25 |
+
"3": "hulk"
|
26 |
+
},
|
27 |
+
"label2id": {
|
28 |
+
"hulk": 3,
|
29 |
+
"ordinary": 1,
|
30 |
+
"overweight": 2,
|
31 |
+
"skinny": 0
|
32 |
+
},
|
33 |
+
"layer_type": "bottleneck",
|
34 |
+
"model_type": "resnet",
|
35 |
+
"num_channels": 3,
|
36 |
+
"out_features": [
|
37 |
+
"stage4"
|
38 |
+
],
|
39 |
+
"out_indices": [
|
40 |
+
4
|
41 |
+
],
|
42 |
+
"problem_type": "single_label_classification",
|
43 |
+
"stage_names": [
|
44 |
+
"stem",
|
45 |
+
"stage1",
|
46 |
+
"stage2",
|
47 |
+
"stage3",
|
48 |
+
"stage4"
|
49 |
+
],
|
50 |
+
"torch_dtype": "float32",
|
51 |
+
"transformers_version": "4.32.1"
|
52 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d8955560524dcdbfbe9b6b9ae699f6ab10aaa28b0a5eaad47bb49bcb3fb84ef
|
3 |
+
size 188260794
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c25b1650605916840a2e116e856ff8a962ac354248e090e2ca5067659f5111af
|
3 |
+
size 94387338
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42686a8973870b47a73c6c2082486f3aa3b0783dc3b23e2a98d72270442aac04
|
3 |
+
size 13990
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc8f9fbd55d6b73398f59b651ee1ad3f54fc5f752abc73f7f160adb053254995
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,925 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 900,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.1111111111111111,
|
14 |
+
"eval_loss": 1.3930704593658447,
|
15 |
+
"eval_runtime": 0.7497,
|
16 |
+
"eval_samples_per_second": 24.01,
|
17 |
+
"eval_steps_per_second": 4.002,
|
18 |
+
"step": 9
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.16666666666666666,
|
23 |
+
"eval_loss": 1.376913070678711,
|
24 |
+
"eval_runtime": 0.5755,
|
25 |
+
"eval_samples_per_second": 31.277,
|
26 |
+
"eval_steps_per_second": 5.213,
|
27 |
+
"step": 18
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.5555555555555556,
|
32 |
+
"eval_loss": 1.3498488664627075,
|
33 |
+
"eval_runtime": 0.5792,
|
34 |
+
"eval_samples_per_second": 31.078,
|
35 |
+
"eval_steps_per_second": 5.18,
|
36 |
+
"step": 27
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 4.0,
|
40 |
+
"eval_accuracy": 0.6666666666666666,
|
41 |
+
"eval_loss": 1.3331588506698608,
|
42 |
+
"eval_runtime": 0.5535,
|
43 |
+
"eval_samples_per_second": 32.518,
|
44 |
+
"eval_steps_per_second": 5.42,
|
45 |
+
"step": 36
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 5.0,
|
49 |
+
"eval_accuracy": 0.7777777777777778,
|
50 |
+
"eval_loss": 1.3144757747650146,
|
51 |
+
"eval_runtime": 0.5818,
|
52 |
+
"eval_samples_per_second": 30.94,
|
53 |
+
"eval_steps_per_second": 5.157,
|
54 |
+
"step": 45
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 6.0,
|
58 |
+
"eval_accuracy": 0.7777777777777778,
|
59 |
+
"eval_loss": 1.300213098526001,
|
60 |
+
"eval_runtime": 0.5539,
|
61 |
+
"eval_samples_per_second": 32.496,
|
62 |
+
"eval_steps_per_second": 5.416,
|
63 |
+
"step": 54
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 7.0,
|
67 |
+
"eval_accuracy": 0.7777777777777778,
|
68 |
+
"eval_loss": 1.2916626930236816,
|
69 |
+
"eval_runtime": 0.5489,
|
70 |
+
"eval_samples_per_second": 32.791,
|
71 |
+
"eval_steps_per_second": 5.465,
|
72 |
+
"step": 63
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 8.0,
|
76 |
+
"eval_accuracy": 0.7777777777777778,
|
77 |
+
"eval_loss": 1.270052194595337,
|
78 |
+
"eval_runtime": 0.5746,
|
79 |
+
"eval_samples_per_second": 31.328,
|
80 |
+
"eval_steps_per_second": 5.221,
|
81 |
+
"step": 72
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 9.0,
|
85 |
+
"eval_accuracy": 0.7777777777777778,
|
86 |
+
"eval_loss": 1.2555011510849,
|
87 |
+
"eval_runtime": 0.5489,
|
88 |
+
"eval_samples_per_second": 32.791,
|
89 |
+
"eval_steps_per_second": 5.465,
|
90 |
+
"step": 81
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 10.0,
|
94 |
+
"eval_accuracy": 0.7777777777777778,
|
95 |
+
"eval_loss": 1.2477619647979736,
|
96 |
+
"eval_runtime": 0.5687,
|
97 |
+
"eval_samples_per_second": 31.651,
|
98 |
+
"eval_steps_per_second": 5.275,
|
99 |
+
"step": 90
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 11.0,
|
103 |
+
"eval_accuracy": 0.7777777777777778,
|
104 |
+
"eval_loss": 1.2382668256759644,
|
105 |
+
"eval_runtime": 0.5502,
|
106 |
+
"eval_samples_per_second": 32.716,
|
107 |
+
"eval_steps_per_second": 5.453,
|
108 |
+
"step": 99
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 12.0,
|
112 |
+
"eval_accuracy": 0.7222222222222222,
|
113 |
+
"eval_loss": 1.223071575164795,
|
114 |
+
"eval_runtime": 0.5476,
|
115 |
+
"eval_samples_per_second": 32.873,
|
116 |
+
"eval_steps_per_second": 5.479,
|
117 |
+
"step": 108
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 13.0,
|
121 |
+
"eval_accuracy": 0.7222222222222222,
|
122 |
+
"eval_loss": 1.2033451795578003,
|
123 |
+
"eval_runtime": 0.5538,
|
124 |
+
"eval_samples_per_second": 32.503,
|
125 |
+
"eval_steps_per_second": 5.417,
|
126 |
+
"step": 117
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 14.0,
|
130 |
+
"eval_accuracy": 0.7777777777777778,
|
131 |
+
"eval_loss": 1.186124563217163,
|
132 |
+
"eval_runtime": 0.5442,
|
133 |
+
"eval_samples_per_second": 33.075,
|
134 |
+
"eval_steps_per_second": 5.512,
|
135 |
+
"step": 126
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 15.0,
|
139 |
+
"eval_accuracy": 0.7777777777777778,
|
140 |
+
"eval_loss": 1.182234287261963,
|
141 |
+
"eval_runtime": 0.5735,
|
142 |
+
"eval_samples_per_second": 31.387,
|
143 |
+
"eval_steps_per_second": 5.231,
|
144 |
+
"step": 135
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 16.0,
|
148 |
+
"eval_accuracy": 0.7777777777777778,
|
149 |
+
"eval_loss": 1.1588956117630005,
|
150 |
+
"eval_runtime": 0.5533,
|
151 |
+
"eval_samples_per_second": 32.534,
|
152 |
+
"eval_steps_per_second": 5.422,
|
153 |
+
"step": 144
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 17.0,
|
157 |
+
"eval_accuracy": 0.7777777777777778,
|
158 |
+
"eval_loss": 1.1478044986724854,
|
159 |
+
"eval_runtime": 0.5826,
|
160 |
+
"eval_samples_per_second": 30.897,
|
161 |
+
"eval_steps_per_second": 5.15,
|
162 |
+
"step": 153
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 18.0,
|
166 |
+
"eval_accuracy": 0.7777777777777778,
|
167 |
+
"eval_loss": 1.1322474479675293,
|
168 |
+
"eval_runtime": 0.5883,
|
169 |
+
"eval_samples_per_second": 30.598,
|
170 |
+
"eval_steps_per_second": 5.1,
|
171 |
+
"step": 162
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 19.0,
|
175 |
+
"eval_accuracy": 0.7777777777777778,
|
176 |
+
"eval_loss": 1.110813021659851,
|
177 |
+
"eval_runtime": 0.5594,
|
178 |
+
"eval_samples_per_second": 32.177,
|
179 |
+
"eval_steps_per_second": 5.363,
|
180 |
+
"step": 171
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 20.0,
|
184 |
+
"eval_accuracy": 0.7222222222222222,
|
185 |
+
"eval_loss": 1.1011286973953247,
|
186 |
+
"eval_runtime": 0.5793,
|
187 |
+
"eval_samples_per_second": 31.073,
|
188 |
+
"eval_steps_per_second": 5.179,
|
189 |
+
"step": 180
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 21.0,
|
193 |
+
"eval_accuracy": 0.7222222222222222,
|
194 |
+
"eval_loss": 1.093163251876831,
|
195 |
+
"eval_runtime": 0.5654,
|
196 |
+
"eval_samples_per_second": 31.836,
|
197 |
+
"eval_steps_per_second": 5.306,
|
198 |
+
"step": 189
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 22.0,
|
202 |
+
"eval_accuracy": 0.7222222222222222,
|
203 |
+
"eval_loss": 1.0637242794036865,
|
204 |
+
"eval_runtime": 0.5679,
|
205 |
+
"eval_samples_per_second": 31.695,
|
206 |
+
"eval_steps_per_second": 5.283,
|
207 |
+
"step": 198
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 23.0,
|
211 |
+
"eval_accuracy": 0.7222222222222222,
|
212 |
+
"eval_loss": 1.0390856266021729,
|
213 |
+
"eval_runtime": 0.574,
|
214 |
+
"eval_samples_per_second": 31.358,
|
215 |
+
"eval_steps_per_second": 5.226,
|
216 |
+
"step": 207
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 24.0,
|
220 |
+
"eval_accuracy": 0.7222222222222222,
|
221 |
+
"eval_loss": 1.0522559881210327,
|
222 |
+
"eval_runtime": 0.6203,
|
223 |
+
"eval_samples_per_second": 29.02,
|
224 |
+
"eval_steps_per_second": 4.837,
|
225 |
+
"step": 216
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 25.0,
|
229 |
+
"eval_accuracy": 0.7777777777777778,
|
230 |
+
"eval_loss": 1.0473227500915527,
|
231 |
+
"eval_runtime": 0.5963,
|
232 |
+
"eval_samples_per_second": 30.186,
|
233 |
+
"eval_steps_per_second": 5.031,
|
234 |
+
"step": 225
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 26.0,
|
238 |
+
"eval_accuracy": 0.7222222222222222,
|
239 |
+
"eval_loss": 0.9998855590820312,
|
240 |
+
"eval_runtime": 0.6467,
|
241 |
+
"eval_samples_per_second": 27.834,
|
242 |
+
"eval_steps_per_second": 4.639,
|
243 |
+
"step": 234
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 27.0,
|
247 |
+
"eval_accuracy": 0.7222222222222222,
|
248 |
+
"eval_loss": 1.0170878171920776,
|
249 |
+
"eval_runtime": 0.5994,
|
250 |
+
"eval_samples_per_second": 30.032,
|
251 |
+
"eval_steps_per_second": 5.005,
|
252 |
+
"step": 243
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 28.0,
|
256 |
+
"eval_accuracy": 0.7222222222222222,
|
257 |
+
"eval_loss": 1.028573989868164,
|
258 |
+
"eval_runtime": 0.6332,
|
259 |
+
"eval_samples_per_second": 28.427,
|
260 |
+
"eval_steps_per_second": 4.738,
|
261 |
+
"step": 252
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 29.0,
|
265 |
+
"eval_accuracy": 0.7222222222222222,
|
266 |
+
"eval_loss": 1.0290330648422241,
|
267 |
+
"eval_runtime": 0.5676,
|
268 |
+
"eval_samples_per_second": 31.712,
|
269 |
+
"eval_steps_per_second": 5.285,
|
270 |
+
"step": 261
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 30.0,
|
274 |
+
"eval_accuracy": 0.7777777777777778,
|
275 |
+
"eval_loss": 0.9571393132209778,
|
276 |
+
"eval_runtime": 0.5753,
|
277 |
+
"eval_samples_per_second": 31.286,
|
278 |
+
"eval_steps_per_second": 5.214,
|
279 |
+
"step": 270
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 31.0,
|
283 |
+
"eval_accuracy": 0.7777777777777778,
|
284 |
+
"eval_loss": 0.9450912475585938,
|
285 |
+
"eval_runtime": 0.5556,
|
286 |
+
"eval_samples_per_second": 32.4,
|
287 |
+
"eval_steps_per_second": 5.4,
|
288 |
+
"step": 279
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 32.0,
|
292 |
+
"eval_accuracy": 0.7777777777777778,
|
293 |
+
"eval_loss": 0.85059654712677,
|
294 |
+
"eval_runtime": 0.5543,
|
295 |
+
"eval_samples_per_second": 32.473,
|
296 |
+
"eval_steps_per_second": 5.412,
|
297 |
+
"step": 288
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 33.0,
|
301 |
+
"eval_accuracy": 0.7777777777777778,
|
302 |
+
"eval_loss": 0.8480208516120911,
|
303 |
+
"eval_runtime": 0.5762,
|
304 |
+
"eval_samples_per_second": 31.241,
|
305 |
+
"eval_steps_per_second": 5.207,
|
306 |
+
"step": 297
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 34.0,
|
310 |
+
"eval_accuracy": 0.7777777777777778,
|
311 |
+
"eval_loss": 0.8499312400817871,
|
312 |
+
"eval_runtime": 0.555,
|
313 |
+
"eval_samples_per_second": 32.433,
|
314 |
+
"eval_steps_per_second": 5.405,
|
315 |
+
"step": 306
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 35.0,
|
319 |
+
"eval_accuracy": 0.7777777777777778,
|
320 |
+
"eval_loss": 0.8403282165527344,
|
321 |
+
"eval_runtime": 0.5709,
|
322 |
+
"eval_samples_per_second": 31.532,
|
323 |
+
"eval_steps_per_second": 5.255,
|
324 |
+
"step": 315
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 36.0,
|
328 |
+
"eval_accuracy": 0.7777777777777778,
|
329 |
+
"eval_loss": 0.7771400809288025,
|
330 |
+
"eval_runtime": 0.5569,
|
331 |
+
"eval_samples_per_second": 32.319,
|
332 |
+
"eval_steps_per_second": 5.387,
|
333 |
+
"step": 324
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 37.0,
|
337 |
+
"eval_accuracy": 0.7777777777777778,
|
338 |
+
"eval_loss": 0.7591123580932617,
|
339 |
+
"eval_runtime": 0.6487,
|
340 |
+
"eval_samples_per_second": 27.747,
|
341 |
+
"eval_steps_per_second": 4.625,
|
342 |
+
"step": 333
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 38.0,
|
346 |
+
"eval_accuracy": 0.7777777777777778,
|
347 |
+
"eval_loss": 0.7476389408111572,
|
348 |
+
"eval_runtime": 0.5654,
|
349 |
+
"eval_samples_per_second": 31.835,
|
350 |
+
"eval_steps_per_second": 5.306,
|
351 |
+
"step": 342
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 39.0,
|
355 |
+
"eval_accuracy": 0.7777777777777778,
|
356 |
+
"eval_loss": 0.7831047773361206,
|
357 |
+
"eval_runtime": 0.5458,
|
358 |
+
"eval_samples_per_second": 32.977,
|
359 |
+
"eval_steps_per_second": 5.496,
|
360 |
+
"step": 351
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 40.0,
|
364 |
+
"eval_accuracy": 0.7777777777777778,
|
365 |
+
"eval_loss": 0.7049207091331482,
|
366 |
+
"eval_runtime": 0.5872,
|
367 |
+
"eval_samples_per_second": 30.653,
|
368 |
+
"eval_steps_per_second": 5.109,
|
369 |
+
"step": 360
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 41.0,
|
373 |
+
"eval_accuracy": 0.7777777777777778,
|
374 |
+
"eval_loss": 0.6811972856521606,
|
375 |
+
"eval_runtime": 0.5667,
|
376 |
+
"eval_samples_per_second": 31.762,
|
377 |
+
"eval_steps_per_second": 5.294,
|
378 |
+
"step": 369
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 42.0,
|
382 |
+
"eval_accuracy": 0.7777777777777778,
|
383 |
+
"eval_loss": 0.6736953258514404,
|
384 |
+
"eval_runtime": 0.5538,
|
385 |
+
"eval_samples_per_second": 32.502,
|
386 |
+
"eval_steps_per_second": 5.417,
|
387 |
+
"step": 378
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 43.0,
|
391 |
+
"eval_accuracy": 0.7777777777777778,
|
392 |
+
"eval_loss": 0.6515324711799622,
|
393 |
+
"eval_runtime": 0.5632,
|
394 |
+
"eval_samples_per_second": 31.958,
|
395 |
+
"eval_steps_per_second": 5.326,
|
396 |
+
"step": 387
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 44.0,
|
400 |
+
"eval_accuracy": 0.7777777777777778,
|
401 |
+
"eval_loss": 0.6634184122085571,
|
402 |
+
"eval_runtime": 1.1806,
|
403 |
+
"eval_samples_per_second": 15.246,
|
404 |
+
"eval_steps_per_second": 2.541,
|
405 |
+
"step": 396
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 45.0,
|
409 |
+
"eval_accuracy": 0.8333333333333334,
|
410 |
+
"eval_loss": 0.6234365105628967,
|
411 |
+
"eval_runtime": 0.6418,
|
412 |
+
"eval_samples_per_second": 28.044,
|
413 |
+
"eval_steps_per_second": 4.674,
|
414 |
+
"step": 405
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 46.0,
|
418 |
+
"eval_accuracy": 0.8333333333333334,
|
419 |
+
"eval_loss": 0.8482791185379028,
|
420 |
+
"eval_runtime": 0.5859,
|
421 |
+
"eval_samples_per_second": 30.723,
|
422 |
+
"eval_steps_per_second": 5.121,
|
423 |
+
"step": 414
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 47.0,
|
427 |
+
"eval_accuracy": 0.8333333333333334,
|
428 |
+
"eval_loss": 0.7264916896820068,
|
429 |
+
"eval_runtime": 0.5835,
|
430 |
+
"eval_samples_per_second": 30.847,
|
431 |
+
"eval_steps_per_second": 5.141,
|
432 |
+
"step": 423
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 48.0,
|
436 |
+
"eval_accuracy": 0.7777777777777778,
|
437 |
+
"eval_loss": 0.7383356094360352,
|
438 |
+
"eval_runtime": 0.5549,
|
439 |
+
"eval_samples_per_second": 32.437,
|
440 |
+
"eval_steps_per_second": 5.406,
|
441 |
+
"step": 432
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 49.0,
|
445 |
+
"eval_accuracy": 0.8333333333333334,
|
446 |
+
"eval_loss": 0.7005217671394348,
|
447 |
+
"eval_runtime": 0.5608,
|
448 |
+
"eval_samples_per_second": 32.095,
|
449 |
+
"eval_steps_per_second": 5.349,
|
450 |
+
"step": 441
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 50.0,
|
454 |
+
"eval_accuracy": 0.8333333333333334,
|
455 |
+
"eval_loss": 0.5740242004394531,
|
456 |
+
"eval_runtime": 0.5536,
|
457 |
+
"eval_samples_per_second": 32.517,
|
458 |
+
"eval_steps_per_second": 5.42,
|
459 |
+
"step": 450
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 51.0,
|
463 |
+
"eval_accuracy": 0.8333333333333334,
|
464 |
+
"eval_loss": 0.5622536540031433,
|
465 |
+
"eval_runtime": 0.5935,
|
466 |
+
"eval_samples_per_second": 30.329,
|
467 |
+
"eval_steps_per_second": 5.055,
|
468 |
+
"step": 459
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 52.0,
|
472 |
+
"eval_accuracy": 0.8333333333333334,
|
473 |
+
"eval_loss": 0.557184636592865,
|
474 |
+
"eval_runtime": 0.5545,
|
475 |
+
"eval_samples_per_second": 32.463,
|
476 |
+
"eval_steps_per_second": 5.41,
|
477 |
+
"step": 468
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 53.0,
|
481 |
+
"eval_accuracy": 0.8333333333333334,
|
482 |
+
"eval_loss": 0.5769361853599548,
|
483 |
+
"eval_runtime": 0.5844,
|
484 |
+
"eval_samples_per_second": 30.802,
|
485 |
+
"eval_steps_per_second": 5.134,
|
486 |
+
"step": 477
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 54.0,
|
490 |
+
"eval_accuracy": 0.8333333333333334,
|
491 |
+
"eval_loss": 0.550247311592102,
|
492 |
+
"eval_runtime": 0.615,
|
493 |
+
"eval_samples_per_second": 29.266,
|
494 |
+
"eval_steps_per_second": 4.878,
|
495 |
+
"step": 486
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 55.0,
|
499 |
+
"eval_accuracy": 0.8888888888888888,
|
500 |
+
"eval_loss": 0.6281833052635193,
|
501 |
+
"eval_runtime": 0.5457,
|
502 |
+
"eval_samples_per_second": 32.988,
|
503 |
+
"eval_steps_per_second": 5.498,
|
504 |
+
"step": 495
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 55.56,
|
508 |
+
"learning_rate": 2.2222222222222223e-05,
|
509 |
+
"loss": 1.1157,
|
510 |
+
"step": 500
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 56.0,
|
514 |
+
"eval_accuracy": 0.8333333333333334,
|
515 |
+
"eval_loss": 0.5906974077224731,
|
516 |
+
"eval_runtime": 0.5821,
|
517 |
+
"eval_samples_per_second": 30.92,
|
518 |
+
"eval_steps_per_second": 5.153,
|
519 |
+
"step": 504
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 57.0,
|
523 |
+
"eval_accuracy": 0.9444444444444444,
|
524 |
+
"eval_loss": 0.6346855163574219,
|
525 |
+
"eval_runtime": 0.5542,
|
526 |
+
"eval_samples_per_second": 32.481,
|
527 |
+
"eval_steps_per_second": 5.414,
|
528 |
+
"step": 513
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 58.0,
|
532 |
+
"eval_accuracy": 0.8888888888888888,
|
533 |
+
"eval_loss": 0.6413730382919312,
|
534 |
+
"eval_runtime": 0.5829,
|
535 |
+
"eval_samples_per_second": 30.882,
|
536 |
+
"eval_steps_per_second": 5.147,
|
537 |
+
"step": 522
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 59.0,
|
541 |
+
"eval_accuracy": 0.8888888888888888,
|
542 |
+
"eval_loss": 0.465614378452301,
|
543 |
+
"eval_runtime": 0.5965,
|
544 |
+
"eval_samples_per_second": 30.178,
|
545 |
+
"eval_steps_per_second": 5.03,
|
546 |
+
"step": 531
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 60.0,
|
550 |
+
"eval_accuracy": 0.8888888888888888,
|
551 |
+
"eval_loss": 0.48488152027130127,
|
552 |
+
"eval_runtime": 0.5621,
|
553 |
+
"eval_samples_per_second": 32.02,
|
554 |
+
"eval_steps_per_second": 5.337,
|
555 |
+
"step": 540
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 61.0,
|
559 |
+
"eval_accuracy": 0.9444444444444444,
|
560 |
+
"eval_loss": 0.8426976799964905,
|
561 |
+
"eval_runtime": 0.5798,
|
562 |
+
"eval_samples_per_second": 31.045,
|
563 |
+
"eval_steps_per_second": 5.174,
|
564 |
+
"step": 549
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 62.0,
|
568 |
+
"eval_accuracy": 0.8888888888888888,
|
569 |
+
"eval_loss": 0.5708574652671814,
|
570 |
+
"eval_runtime": 0.5531,
|
571 |
+
"eval_samples_per_second": 32.544,
|
572 |
+
"eval_steps_per_second": 5.424,
|
573 |
+
"step": 558
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 63.0,
|
577 |
+
"eval_accuracy": 0.8888888888888888,
|
578 |
+
"eval_loss": 0.5026788115501404,
|
579 |
+
"eval_runtime": 0.5575,
|
580 |
+
"eval_samples_per_second": 32.289,
|
581 |
+
"eval_steps_per_second": 5.381,
|
582 |
+
"step": 567
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 64.0,
|
586 |
+
"eval_accuracy": 0.8888888888888888,
|
587 |
+
"eval_loss": 0.5724208354949951,
|
588 |
+
"eval_runtime": 0.5481,
|
589 |
+
"eval_samples_per_second": 32.844,
|
590 |
+
"eval_steps_per_second": 5.474,
|
591 |
+
"step": 576
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 65.0,
|
595 |
+
"eval_accuracy": 0.8888888888888888,
|
596 |
+
"eval_loss": 0.5301716327667236,
|
597 |
+
"eval_runtime": 0.553,
|
598 |
+
"eval_samples_per_second": 32.551,
|
599 |
+
"eval_steps_per_second": 5.425,
|
600 |
+
"step": 585
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 66.0,
|
604 |
+
"eval_accuracy": 0.8333333333333334,
|
605 |
+
"eval_loss": 0.5272272825241089,
|
606 |
+
"eval_runtime": 0.5566,
|
607 |
+
"eval_samples_per_second": 32.34,
|
608 |
+
"eval_steps_per_second": 5.39,
|
609 |
+
"step": 594
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 67.0,
|
613 |
+
"eval_accuracy": 0.8888888888888888,
|
614 |
+
"eval_loss": 0.5444329380989075,
|
615 |
+
"eval_runtime": 0.555,
|
616 |
+
"eval_samples_per_second": 32.435,
|
617 |
+
"eval_steps_per_second": 5.406,
|
618 |
+
"step": 603
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 68.0,
|
622 |
+
"eval_accuracy": 0.8888888888888888,
|
623 |
+
"eval_loss": 0.3936518132686615,
|
624 |
+
"eval_runtime": 0.6001,
|
625 |
+
"eval_samples_per_second": 29.994,
|
626 |
+
"eval_steps_per_second": 4.999,
|
627 |
+
"step": 612
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 69.0,
|
631 |
+
"eval_accuracy": 0.9444444444444444,
|
632 |
+
"eval_loss": 0.41802236437797546,
|
633 |
+
"eval_runtime": 0.5658,
|
634 |
+
"eval_samples_per_second": 31.816,
|
635 |
+
"eval_steps_per_second": 5.303,
|
636 |
+
"step": 621
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"epoch": 70.0,
|
640 |
+
"eval_accuracy": 0.8888888888888888,
|
641 |
+
"eval_loss": 0.5185115337371826,
|
642 |
+
"eval_runtime": 0.5619,
|
643 |
+
"eval_samples_per_second": 32.036,
|
644 |
+
"eval_steps_per_second": 5.339,
|
645 |
+
"step": 630
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 71.0,
|
649 |
+
"eval_accuracy": 1.0,
|
650 |
+
"eval_loss": 0.39606520533561707,
|
651 |
+
"eval_runtime": 0.5983,
|
652 |
+
"eval_samples_per_second": 30.085,
|
653 |
+
"eval_steps_per_second": 5.014,
|
654 |
+
"step": 639
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 72.0,
|
658 |
+
"eval_accuracy": 0.9444444444444444,
|
659 |
+
"eval_loss": 0.3859682083129883,
|
660 |
+
"eval_runtime": 0.5757,
|
661 |
+
"eval_samples_per_second": 31.268,
|
662 |
+
"eval_steps_per_second": 5.211,
|
663 |
+
"step": 648
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 73.0,
|
667 |
+
"eval_accuracy": 0.9444444444444444,
|
668 |
+
"eval_loss": 0.39656686782836914,
|
669 |
+
"eval_runtime": 0.6158,
|
670 |
+
"eval_samples_per_second": 29.228,
|
671 |
+
"eval_steps_per_second": 4.871,
|
672 |
+
"step": 657
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 74.0,
|
676 |
+
"eval_accuracy": 0.8888888888888888,
|
677 |
+
"eval_loss": 0.39676183462142944,
|
678 |
+
"eval_runtime": 0.6324,
|
679 |
+
"eval_samples_per_second": 28.462,
|
680 |
+
"eval_steps_per_second": 4.744,
|
681 |
+
"step": 666
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 75.0,
|
685 |
+
"eval_accuracy": 0.8888888888888888,
|
686 |
+
"eval_loss": 0.4546321630477905,
|
687 |
+
"eval_runtime": 0.5605,
|
688 |
+
"eval_samples_per_second": 32.114,
|
689 |
+
"eval_steps_per_second": 5.352,
|
690 |
+
"step": 675
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 76.0,
|
694 |
+
"eval_accuracy": 0.8888888888888888,
|
695 |
+
"eval_loss": 0.4021334648132324,
|
696 |
+
"eval_runtime": 0.553,
|
697 |
+
"eval_samples_per_second": 32.55,
|
698 |
+
"eval_steps_per_second": 5.425,
|
699 |
+
"step": 684
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 77.0,
|
703 |
+
"eval_accuracy": 0.9444444444444444,
|
704 |
+
"eval_loss": 0.414422869682312,
|
705 |
+
"eval_runtime": 0.5759,
|
706 |
+
"eval_samples_per_second": 31.256,
|
707 |
+
"eval_steps_per_second": 5.209,
|
708 |
+
"step": 693
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 78.0,
|
712 |
+
"eval_accuracy": 1.0,
|
713 |
+
"eval_loss": 0.35500773787498474,
|
714 |
+
"eval_runtime": 0.5802,
|
715 |
+
"eval_samples_per_second": 31.024,
|
716 |
+
"eval_steps_per_second": 5.171,
|
717 |
+
"step": 702
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 79.0,
|
721 |
+
"eval_accuracy": 0.9444444444444444,
|
722 |
+
"eval_loss": 0.3838707506656647,
|
723 |
+
"eval_runtime": 0.5616,
|
724 |
+
"eval_samples_per_second": 32.052,
|
725 |
+
"eval_steps_per_second": 5.342,
|
726 |
+
"step": 711
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 80.0,
|
730 |
+
"eval_accuracy": 0.8888888888888888,
|
731 |
+
"eval_loss": 0.437086820602417,
|
732 |
+
"eval_runtime": 0.554,
|
733 |
+
"eval_samples_per_second": 32.49,
|
734 |
+
"eval_steps_per_second": 5.415,
|
735 |
+
"step": 720
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 81.0,
|
739 |
+
"eval_accuracy": 0.8888888888888888,
|
740 |
+
"eval_loss": 0.36943355202674866,
|
741 |
+
"eval_runtime": 0.5894,
|
742 |
+
"eval_samples_per_second": 30.537,
|
743 |
+
"eval_steps_per_second": 5.09,
|
744 |
+
"step": 729
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 82.0,
|
748 |
+
"eval_accuracy": 0.8888888888888888,
|
749 |
+
"eval_loss": 0.36648380756378174,
|
750 |
+
"eval_runtime": 0.5615,
|
751 |
+
"eval_samples_per_second": 32.058,
|
752 |
+
"eval_steps_per_second": 5.343,
|
753 |
+
"step": 738
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 83.0,
|
757 |
+
"eval_accuracy": 0.8888888888888888,
|
758 |
+
"eval_loss": 0.4732191264629364,
|
759 |
+
"eval_runtime": 0.5632,
|
760 |
+
"eval_samples_per_second": 31.959,
|
761 |
+
"eval_steps_per_second": 5.327,
|
762 |
+
"step": 747
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 84.0,
|
766 |
+
"eval_accuracy": 0.9444444444444444,
|
767 |
+
"eval_loss": 0.4652000665664673,
|
768 |
+
"eval_runtime": 0.592,
|
769 |
+
"eval_samples_per_second": 30.406,
|
770 |
+
"eval_steps_per_second": 5.068,
|
771 |
+
"step": 756
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 85.0,
|
775 |
+
"eval_accuracy": 0.8888888888888888,
|
776 |
+
"eval_loss": 0.670432448387146,
|
777 |
+
"eval_runtime": 0.5801,
|
778 |
+
"eval_samples_per_second": 31.028,
|
779 |
+
"eval_steps_per_second": 5.171,
|
780 |
+
"step": 765
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 86.0,
|
784 |
+
"eval_accuracy": 0.8333333333333334,
|
785 |
+
"eval_loss": 0.7354382872581482,
|
786 |
+
"eval_runtime": 0.5599,
|
787 |
+
"eval_samples_per_second": 32.151,
|
788 |
+
"eval_steps_per_second": 5.359,
|
789 |
+
"step": 774
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 87.0,
|
793 |
+
"eval_accuracy": 0.8333333333333334,
|
794 |
+
"eval_loss": 0.5439589023590088,
|
795 |
+
"eval_runtime": 0.5486,
|
796 |
+
"eval_samples_per_second": 32.811,
|
797 |
+
"eval_steps_per_second": 5.468,
|
798 |
+
"step": 783
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 88.0,
|
802 |
+
"eval_accuracy": 0.8888888888888888,
|
803 |
+
"eval_loss": 0.4809061586856842,
|
804 |
+
"eval_runtime": 0.6101,
|
805 |
+
"eval_samples_per_second": 29.505,
|
806 |
+
"eval_steps_per_second": 4.917,
|
807 |
+
"step": 792
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 89.0,
|
811 |
+
"eval_accuracy": 0.9444444444444444,
|
812 |
+
"eval_loss": 0.6704312562942505,
|
813 |
+
"eval_runtime": 0.5954,
|
814 |
+
"eval_samples_per_second": 30.229,
|
815 |
+
"eval_steps_per_second": 5.038,
|
816 |
+
"step": 801
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 90.0,
|
820 |
+
"eval_accuracy": 0.8888888888888888,
|
821 |
+
"eval_loss": 0.41327810287475586,
|
822 |
+
"eval_runtime": 0.5783,
|
823 |
+
"eval_samples_per_second": 31.124,
|
824 |
+
"eval_steps_per_second": 5.187,
|
825 |
+
"step": 810
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 91.0,
|
829 |
+
"eval_accuracy": 0.9444444444444444,
|
830 |
+
"eval_loss": 0.350969523191452,
|
831 |
+
"eval_runtime": 0.5507,
|
832 |
+
"eval_samples_per_second": 32.686,
|
833 |
+
"eval_steps_per_second": 5.448,
|
834 |
+
"step": 819
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 92.0,
|
838 |
+
"eval_accuracy": 0.8888888888888888,
|
839 |
+
"eval_loss": 0.39819759130477905,
|
840 |
+
"eval_runtime": 0.5465,
|
841 |
+
"eval_samples_per_second": 32.939,
|
842 |
+
"eval_steps_per_second": 5.49,
|
843 |
+
"step": 828
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 93.0,
|
847 |
+
"eval_accuracy": 0.9444444444444444,
|
848 |
+
"eval_loss": 0.34932640194892883,
|
849 |
+
"eval_runtime": 0.5635,
|
850 |
+
"eval_samples_per_second": 31.941,
|
851 |
+
"eval_steps_per_second": 5.323,
|
852 |
+
"step": 837
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 94.0,
|
856 |
+
"eval_accuracy": 0.8888888888888888,
|
857 |
+
"eval_loss": 0.48363664746284485,
|
858 |
+
"eval_runtime": 0.5411,
|
859 |
+
"eval_samples_per_second": 33.263,
|
860 |
+
"eval_steps_per_second": 5.544,
|
861 |
+
"step": 846
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 95.0,
|
865 |
+
"eval_accuracy": 0.9444444444444444,
|
866 |
+
"eval_loss": 0.4434005320072174,
|
867 |
+
"eval_runtime": 0.5964,
|
868 |
+
"eval_samples_per_second": 30.181,
|
869 |
+
"eval_steps_per_second": 5.03,
|
870 |
+
"step": 855
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 96.0,
|
874 |
+
"eval_accuracy": 0.8333333333333334,
|
875 |
+
"eval_loss": 0.4290742874145508,
|
876 |
+
"eval_runtime": 0.5584,
|
877 |
+
"eval_samples_per_second": 32.235,
|
878 |
+
"eval_steps_per_second": 5.373,
|
879 |
+
"step": 864
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 97.0,
|
883 |
+
"eval_accuracy": 0.9444444444444444,
|
884 |
+
"eval_loss": 0.34131091833114624,
|
885 |
+
"eval_runtime": 0.5715,
|
886 |
+
"eval_samples_per_second": 31.493,
|
887 |
+
"eval_steps_per_second": 5.249,
|
888 |
+
"step": 873
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 98.0,
|
892 |
+
"eval_accuracy": 0.8888888888888888,
|
893 |
+
"eval_loss": 0.3645610511302948,
|
894 |
+
"eval_runtime": 0.5506,
|
895 |
+
"eval_samples_per_second": 32.692,
|
896 |
+
"eval_steps_per_second": 5.449,
|
897 |
+
"step": 882
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 99.0,
|
901 |
+
"eval_accuracy": 0.9444444444444444,
|
902 |
+
"eval_loss": 0.5591509938240051,
|
903 |
+
"eval_runtime": 0.5908,
|
904 |
+
"eval_samples_per_second": 30.468,
|
905 |
+
"eval_steps_per_second": 5.078,
|
906 |
+
"step": 891
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 100.0,
|
910 |
+
"eval_accuracy": 0.9444444444444444,
|
911 |
+
"eval_loss": 0.48491573333740234,
|
912 |
+
"eval_runtime": 0.5689,
|
913 |
+
"eval_samples_per_second": 31.643,
|
914 |
+
"eval_steps_per_second": 5.274,
|
915 |
+
"step": 900
|
916 |
+
}
|
917 |
+
],
|
918 |
+
"logging_steps": 500,
|
919 |
+
"max_steps": 900,
|
920 |
+
"num_train_epochs": 100,
|
921 |
+
"save_steps": 500,
|
922 |
+
"total_flos": 1.507976427331584e+17,
|
923 |
+
"trial_name": null,
|
924 |
+
"trial_params": null
|
925 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b96faf171c2424278071615eee0427e37d71d76381d743e379faddb5bf4bd032
|
3 |
+
size 4472
|