Training in progress, epoch 0
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Apr28_18-05-30_187a08b29384/events.out.tfevents.1714327551.187a08b29384.340.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +78 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.8085106382978724,
|
3 |
+
"total_flos": 8.251222819140403e+16,
|
4 |
+
"train_loss": 1.6961536913207083,
|
5 |
+
"train_runtime": 198.8355,
|
6 |
+
"train_samples_per_second": 22.632,
|
7 |
+
"train_steps_per_second": 0.166
|
8 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 86700952
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3022c220496dcf546cc526f6dfbb501f92b363dd3a81b2cea436aca630f182d0
|
3 |
size 86700952
|
runs/Apr28_18-05-30_187a08b29384/events.out.tfevents.1714327551.187a08b29384.340.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16125b9dc7f5d4efe4af979d16f923f17fef89ee48e141d054a911932aa14a9d
|
3 |
+
size 5665
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.8085106382978724,
|
3 |
+
"total_flos": 8.251222819140403e+16,
|
4 |
+
"train_loss": 1.6961536913207083,
|
5 |
+
"train_runtime": 198.8355,
|
6 |
+
"train_samples_per_second": 22.632,
|
7 |
+
"train_steps_per_second": 0.166
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5684210526315789,
|
3 |
+
"best_model_checkpoint": "vit-msn-small-finetuned-eurosat/checkpoint-33",
|
4 |
+
"epoch": 2.8085106382978724,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 33,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.851063829787234,
|
13 |
+
"grad_norm": 7.806485652923584,
|
14 |
+
"learning_rate": 3.965517241379311e-05,
|
15 |
+
"loss": 2.2554,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9361702127659575,
|
20 |
+
"eval_accuracy": 0.4052631578947368,
|
21 |
+
"eval_loss": 1.821715235710144,
|
22 |
+
"eval_runtime": 5.616,
|
23 |
+
"eval_samples_per_second": 33.832,
|
24 |
+
"eval_steps_per_second": 1.068,
|
25 |
+
"step": 11
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.702127659574468,
|
29 |
+
"grad_norm": 9.02415657043457,
|
30 |
+
"learning_rate": 2.2413793103448276e-05,
|
31 |
+
"loss": 1.6448,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.9574468085106385,
|
36 |
+
"eval_accuracy": 0.48947368421052634,
|
37 |
+
"eval_loss": 1.4679394960403442,
|
38 |
+
"eval_runtime": 5.5389,
|
39 |
+
"eval_samples_per_second": 34.303,
|
40 |
+
"eval_steps_per_second": 1.083,
|
41 |
+
"step": 23
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.5531914893617023,
|
45 |
+
"grad_norm": 7.699336051940918,
|
46 |
+
"learning_rate": 5.172413793103448e-06,
|
47 |
+
"loss": 1.3339,
|
48 |
+
"step": 30
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.8085106382978724,
|
52 |
+
"eval_accuracy": 0.5684210526315789,
|
53 |
+
"eval_loss": 1.3136721849441528,
|
54 |
+
"eval_runtime": 6.6132,
|
55 |
+
"eval_samples_per_second": 28.73,
|
56 |
+
"eval_steps_per_second": 0.907,
|
57 |
+
"step": 33
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.8085106382978724,
|
61 |
+
"step": 33,
|
62 |
+
"total_flos": 8.251222819140403e+16,
|
63 |
+
"train_loss": 1.6961536913207083,
|
64 |
+
"train_runtime": 198.8355,
|
65 |
+
"train_samples_per_second": 22.632,
|
66 |
+
"train_steps_per_second": 0.166
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 10,
|
70 |
+
"max_steps": 33,
|
71 |
+
"num_input_tokens_seen": 0,
|
72 |
+
"num_train_epochs": 3,
|
73 |
+
"save_steps": 500,
|
74 |
+
"total_flos": 8.251222819140403e+16,
|
75 |
+
"train_batch_size": 32,
|
76 |
+
"trial_name": null,
|
77 |
+
"trial_params": null
|
78 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:470d2b0cee2e132c5994ebf014547290be2a9b72cf1db3372d5e035cdfc7190c
|
3 |
size 5048
|