End of training
Browse files- README.md +3 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +112 -0
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
library_name: transformers
|
3 |
base_model: andro-flock/b2-classification
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
7 |
- name: b2-segmentation
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# b2-segmentation
|
15 |
|
16 |
-
This model is a fine-tuned version of [andro-flock/b2-classification](https://huggingface.co/andro-flock/b2-classification) on
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
2 |
library_name: transformers
|
3 |
base_model: andro-flock/b2-classification
|
4 |
tags:
|
5 |
+
- image-segmentation
|
6 |
+
- vision
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: b2-segmentation
|
|
|
15 |
|
16 |
# b2-segmentation
|
17 |
|
18 |
+
This model is a fine-tuned version of [andro-flock/b2-classification](https://huggingface.co/andro-flock/b2-classification) on the andro-flock/semantic-segment dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 125.0,
|
3 |
+
"total_flos": 4.67800620466176e+17,
|
4 |
+
"train_loss": 0.1090870885848999,
|
5 |
+
"train_runtime": 959.3782,
|
6 |
+
"train_samples_per_second": 4.169,
|
7 |
+
"train_steps_per_second": 0.521
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 125.0,
|
3 |
+
"total_flos": 4.67800620466176e+17,
|
4 |
+
"train_loss": 0.1090870885848999,
|
5 |
+
"train_runtime": 959.3782,
|
6 |
+
"train_samples_per_second": 4.169,
|
7 |
+
"train_steps_per_second": 0.521
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 125.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 12.5,
|
13 |
+
"grad_norm": 3.6458182334899902,
|
14 |
+
"learning_rate": 5.401e-05,
|
15 |
+
"loss": 0.3174,
|
16 |
+
"step": 50
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 25.0,
|
20 |
+
"grad_norm": 2.206636905670166,
|
21 |
+
"learning_rate": 4.8020000000000004e-05,
|
22 |
+
"loss": 0.1611,
|
23 |
+
"step": 100
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 37.5,
|
27 |
+
"grad_norm": 0.8555470705032349,
|
28 |
+
"learning_rate": 4.203e-05,
|
29 |
+
"loss": 0.1319,
|
30 |
+
"step": 150
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 50.0,
|
34 |
+
"grad_norm": 0.6757478713989258,
|
35 |
+
"learning_rate": 3.604e-05,
|
36 |
+
"loss": 0.1038,
|
37 |
+
"step": 200
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 62.5,
|
41 |
+
"grad_norm": 1.159254550933838,
|
42 |
+
"learning_rate": 3.0050000000000002e-05,
|
43 |
+
"loss": 0.0701,
|
44 |
+
"step": 250
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 75.0,
|
48 |
+
"grad_norm": 2.89020037651062,
|
49 |
+
"learning_rate": 2.406e-05,
|
50 |
+
"loss": 0.0658,
|
51 |
+
"step": 300
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 87.5,
|
55 |
+
"grad_norm": 1.4937611818313599,
|
56 |
+
"learning_rate": 1.807e-05,
|
57 |
+
"loss": 0.0635,
|
58 |
+
"step": 350
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 100.0,
|
62 |
+
"grad_norm": 0.5791894197463989,
|
63 |
+
"learning_rate": 1.2079999999999998e-05,
|
64 |
+
"loss": 0.0692,
|
65 |
+
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 112.5,
|
69 |
+
"grad_norm": 0.22667507827281952,
|
70 |
+
"learning_rate": 6.0899999999999984e-06,
|
71 |
+
"loss": 0.0585,
|
72 |
+
"step": 450
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 125.0,
|
76 |
+
"grad_norm": 0.2987639307975769,
|
77 |
+
"learning_rate": 1e-07,
|
78 |
+
"loss": 0.0497,
|
79 |
+
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 125.0,
|
83 |
+
"step": 500,
|
84 |
+
"total_flos": 4.67800620466176e+17,
|
85 |
+
"train_loss": 0.1090870885848999,
|
86 |
+
"train_runtime": 959.3782,
|
87 |
+
"train_samples_per_second": 4.169,
|
88 |
+
"train_steps_per_second": 0.521
|
89 |
+
}
|
90 |
+
],
|
91 |
+
"logging_steps": 50,
|
92 |
+
"max_steps": 500,
|
93 |
+
"num_input_tokens_seen": 0,
|
94 |
+
"num_train_epochs": 125,
|
95 |
+
"save_steps": 500,
|
96 |
+
"stateful_callbacks": {
|
97 |
+
"TrainerControl": {
|
98 |
+
"args": {
|
99 |
+
"should_epoch_stop": false,
|
100 |
+
"should_evaluate": false,
|
101 |
+
"should_log": false,
|
102 |
+
"should_save": true,
|
103 |
+
"should_training_stop": true
|
104 |
+
},
|
105 |
+
"attributes": {}
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"total_flos": 4.67800620466176e+17,
|
109 |
+
"train_batch_size": 4,
|
110 |
+
"trial_name": null,
|
111 |
+
"trial_params": null
|
112 |
+
}
|