brigettesegovia
commited on
Commit
•
213c229
1
Parent(s):
59e99d2
Training in progress, step 100
Browse files- all_results.json +13 -0
- config.json +63 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Nov22_12-53-18_l-hvjvvxgp4c.local/events.out.tfevents.1732297999.l-hvjvvxgp4c.local.46519.0 +3 -0
- runs/Nov22_12-57-01_l-hvjvvxgp4c.local/events.out.tfevents.1732298226.l-hvjvvxgp4c.local.46519.1 +3 -0
- runs/Nov22_13-29-03_l-hvjvvxgp4c.local/events.out.tfevents.1732300144.l-hvjvvxgp4c.local.46519.2 +3 -0
- runs/Nov22_13-33-38_l-hvjvvxgp4c.local/events.out.tfevents.1732300419.l-hvjvvxgp4c.local.46519.3 +3 -0
- runs/Nov22_13-43-46_l-hvjvvxgp4c.local/events.out.tfevents.1732301027.l-hvjvvxgp4c.local.46519.4 +3 -0
- runs/Nov22_13-43-55_l-hvjvvxgp4c.local/events.out.tfevents.1732301036.l-hvjvvxgp4c.local.46519.5 +3 -0
- runs/Nov22_13-44-02_l-hvjvvxgp4c.local/events.out.tfevents.1732301044.l-hvjvvxgp4c.local.46519.6 +3 -0
- runs/Nov22_13-54-06_l-hvjvvxgp4c.local/events.out.tfevents.1732301647.l-hvjvvxgp4c.local.46519.7 +3 -0
- runs/Nov22_14-47-28_l-hvjvvxgp4c.local/events.out.tfevents.1732304848.l-hvjvvxgp4c.local.50334.0 +3 -0
- runs/Nov22_14-53-32_l-hvjvvxgp4c.local/events.out.tfevents.1732305213.l-hvjvvxgp4c.local.50428.0 +3 -0
- runs/Nov22_14-59-02_l-hvjvvxgp4c.local/events.out.tfevents.1732305542.l-hvjvvxgp4c.local.50592.0 +3 -0
- runs/Nov22_14-59-02_l-hvjvvxgp4c.local/events.out.tfevents.1732306024.l-hvjvvxgp4c.local.50592.1 +3 -0
- runs/Nov22_15-27-50_l-hvjvvxgp4c.local/events.out.tfevents.1732307274.l-hvjvvxgp4c.local.50592.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +242 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9924812030075187,
|
4 |
+
"eval_loss": 0.018673665821552277,
|
5 |
+
"eval_runtime": 6.8068,
|
6 |
+
"eval_samples_per_second": 19.539,
|
7 |
+
"eval_steps_per_second": 2.498,
|
8 |
+
"total_flos": 1.0280724304719053e+17,
|
9 |
+
"train_loss": 0.15423231131683748,
|
10 |
+
"train_runtime": 475.1171,
|
11 |
+
"train_samples_per_second": 8.705,
|
12 |
+
"train_steps_per_second": 0.547
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
6,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 96,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "angular_leaf_spot",
|
21 |
+
"1": "bean_rust",
|
22 |
+
"2": "healthy"
|
23 |
+
},
|
24 |
+
"image_size": 224,
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"label2id": {
|
27 |
+
"angular_leaf_spot": "0",
|
28 |
+
"bean_rust": "1",
|
29 |
+
"healthy": "2"
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-05,
|
32 |
+
"mlp_ratio": 4.0,
|
33 |
+
"model_type": "swin",
|
34 |
+
"num_channels": 3,
|
35 |
+
"num_heads": [
|
36 |
+
3,
|
37 |
+
6,
|
38 |
+
12,
|
39 |
+
24
|
40 |
+
],
|
41 |
+
"num_layers": 4,
|
42 |
+
"out_features": [
|
43 |
+
"stage4"
|
44 |
+
],
|
45 |
+
"out_indices": [
|
46 |
+
4
|
47 |
+
],
|
48 |
+
"patch_size": 4,
|
49 |
+
"path_norm": true,
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"qkv_bias": true,
|
52 |
+
"stage_names": [
|
53 |
+
"stem",
|
54 |
+
"stage1",
|
55 |
+
"stage2",
|
56 |
+
"stage3",
|
57 |
+
"stage4"
|
58 |
+
],
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.46.2",
|
61 |
+
"use_absolute_embeddings": false,
|
62 |
+
"window_size": 7
|
63 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9924812030075187,
|
4 |
+
"eval_loss": 0.018673665821552277,
|
5 |
+
"eval_runtime": 6.8068,
|
6 |
+
"eval_samples_per_second": 19.539,
|
7 |
+
"eval_steps_per_second": 2.498
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:152a4fd6982e7fb2c672ffa8c2987a1f67b453c6cd2812ae52636facbae2c0e7
|
3 |
+
size 110345908
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.485,
|
7 |
+
0.456,
|
8 |
+
0.406
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.229,
|
13 |
+
0.224,
|
14 |
+
0.225
|
15 |
+
],
|
16 |
+
"resample": 3,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Nov22_12-53-18_l-hvjvvxgp4c.local/events.out.tfevents.1732297999.l-hvjvvxgp4c.local.46519.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6965e1c821a0e344c496965fdbaaa51ac8a1f96ce3e02f528c05784c26cf349d
|
3 |
+
size 5510
|
runs/Nov22_12-57-01_l-hvjvvxgp4c.local/events.out.tfevents.1732298226.l-hvjvvxgp4c.local.46519.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77cbaf784760d7401c8206b87e60a8109349ac4886113381516db7a1889865f4
|
3 |
+
size 5510
|
runs/Nov22_13-29-03_l-hvjvvxgp4c.local/events.out.tfevents.1732300144.l-hvjvvxgp4c.local.46519.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b8d0ec8de518ec63dea704d3134ea99de45765eb9981fe0dbd665d79d918a8e
|
3 |
+
size 5510
|
runs/Nov22_13-33-38_l-hvjvvxgp4c.local/events.out.tfevents.1732300419.l-hvjvvxgp4c.local.46519.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e20abee9224ca002be3c8523e1d8596c1e7c879b8e8463ee6f5f1cc656690220
|
3 |
+
size 5510
|
runs/Nov22_13-43-46_l-hvjvvxgp4c.local/events.out.tfevents.1732301027.l-hvjvvxgp4c.local.46519.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84c66c2f467f1ae41c6a01c477811e3a32b9023a97e2749b3dc8fbda53fd40f0
|
3 |
+
size 5558
|
runs/Nov22_13-43-55_l-hvjvvxgp4c.local/events.out.tfevents.1732301036.l-hvjvvxgp4c.local.46519.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6e84576731b89954dd4658b1a36965c3238101d00e7f043bd3631523e92d711
|
3 |
+
size 5559
|
runs/Nov22_13-44-02_l-hvjvvxgp4c.local/events.out.tfevents.1732301044.l-hvjvvxgp4c.local.46519.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ace120e7a158636eef990404bd8e2db989f5edddd487b4d008edb341b2f3232
|
3 |
+
size 5558
|
runs/Nov22_13-54-06_l-hvjvvxgp4c.local/events.out.tfevents.1732301647.l-hvjvvxgp4c.local.46519.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c745267bea537124dcf6ccffe4b0586fd539f907e6a270a7a20548e135e699aa
|
3 |
+
size 5509
|
runs/Nov22_14-47-28_l-hvjvvxgp4c.local/events.out.tfevents.1732304848.l-hvjvvxgp4c.local.50334.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9009db7134070497180d0d8c42671301b539ce9163ff82eaa1587907c6b36c4e
|
3 |
+
size 7573
|
runs/Nov22_14-53-32_l-hvjvvxgp4c.local/events.out.tfevents.1732305213.l-hvjvvxgp4c.local.50428.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07c6974886aaea03d2a22f2e498c96740f5656f9736df38a5ba119300b4d32b3
|
3 |
+
size 7573
|
runs/Nov22_14-59-02_l-hvjvvxgp4c.local/events.out.tfevents.1732305542.l-hvjvvxgp4c.local.50592.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f7bf2dc43d7f2c609339263f9d53a1a96a659ec1a89b67f4c366ac7741f9f65
|
3 |
+
size 11935
|
runs/Nov22_14-59-02_l-hvjvvxgp4c.local/events.out.tfevents.1732306024.l-hvjvvxgp4c.local.50592.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:770b1522fc4e969628f2ee15318e93bbc87a9c45db3190c34abecb6625a75695
|
3 |
+
size 411
|
runs/Nov22_15-27-50_l-hvjvvxgp4c.local/events.out.tfevents.1732307274.l-hvjvvxgp4c.local.50592.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58900eb190b8f1d1a111686ff0c256b6eafd5885db07631c512d1d2a810469af
|
3 |
+
size 7898
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"total_flos": 1.0280724304719053e+17,
|
4 |
+
"train_loss": 0.15423231131683748,
|
5 |
+
"train_runtime": 475.1171,
|
6 |
+
"train_samples_per_second": 8.705,
|
7 |
+
"train_steps_per_second": 0.547
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.018673665821552277,
|
3 |
+
"best_model_checkpoint": "plant_classification/checkpoint-200",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 260,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.15384615384615385,
|
13 |
+
"grad_norm": 6.1219401359558105,
|
14 |
+
"learning_rate": 0.00019230769230769233,
|
15 |
+
"loss": 0.8735,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.3076923076923077,
|
20 |
+
"grad_norm": 6.421919345855713,
|
21 |
+
"learning_rate": 0.00018461538461538463,
|
22 |
+
"loss": 0.4227,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.46153846153846156,
|
27 |
+
"grad_norm": 8.949458122253418,
|
28 |
+
"learning_rate": 0.00017692307692307693,
|
29 |
+
"loss": 0.619,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.6153846153846154,
|
34 |
+
"grad_norm": 18.531173706054688,
|
35 |
+
"learning_rate": 0.00016923076923076923,
|
36 |
+
"loss": 0.3132,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.7692307692307693,
|
41 |
+
"grad_norm": 11.649073600769043,
|
42 |
+
"learning_rate": 0.00016153846153846155,
|
43 |
+
"loss": 0.1747,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.9230769230769231,
|
48 |
+
"grad_norm": 9.787153244018555,
|
49 |
+
"learning_rate": 0.00015384615384615385,
|
50 |
+
"loss": 0.4578,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0769230769230769,
|
55 |
+
"grad_norm": 11.584129333496094,
|
56 |
+
"learning_rate": 0.00014615384615384615,
|
57 |
+
"loss": 0.1248,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.2307692307692308,
|
62 |
+
"grad_norm": 5.55765438079834,
|
63 |
+
"learning_rate": 0.00013846153846153847,
|
64 |
+
"loss": 0.1797,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.3846153846153846,
|
69 |
+
"grad_norm": 11.325220108032227,
|
70 |
+
"learning_rate": 0.00013076923076923077,
|
71 |
+
"loss": 0.2009,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.5384615384615383,
|
76 |
+
"grad_norm": 8.960542678833008,
|
77 |
+
"learning_rate": 0.0001230769230769231,
|
78 |
+
"loss": 0.1026,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.5384615384615383,
|
83 |
+
"eval_accuracy": 0.9849624060150376,
|
84 |
+
"eval_loss": 0.03040493279695511,
|
85 |
+
"eval_runtime": 6.9438,
|
86 |
+
"eval_samples_per_second": 19.154,
|
87 |
+
"eval_steps_per_second": 2.448,
|
88 |
+
"step": 100
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.6923076923076923,
|
92 |
+
"grad_norm": 26.664871215820312,
|
93 |
+
"learning_rate": 0.00011538461538461538,
|
94 |
+
"loss": 0.0844,
|
95 |
+
"step": 110
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.8461538461538463,
|
99 |
+
"grad_norm": 0.047984011471271515,
|
100 |
+
"learning_rate": 0.0001076923076923077,
|
101 |
+
"loss": 0.1192,
|
102 |
+
"step": 120
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 2.0,
|
106 |
+
"grad_norm": 0.053843218833208084,
|
107 |
+
"learning_rate": 0.0001,
|
108 |
+
"loss": 0.0604,
|
109 |
+
"step": 130
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 2.1538461538461537,
|
113 |
+
"grad_norm": 0.12431614845991135,
|
114 |
+
"learning_rate": 9.230769230769232e-05,
|
115 |
+
"loss": 0.0354,
|
116 |
+
"step": 140
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 2.3076923076923075,
|
120 |
+
"grad_norm": 0.006539974361658096,
|
121 |
+
"learning_rate": 8.461538461538461e-05,
|
122 |
+
"loss": 0.0209,
|
123 |
+
"step": 150
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.4615384615384617,
|
127 |
+
"grad_norm": 0.0014725056244060397,
|
128 |
+
"learning_rate": 7.692307692307693e-05,
|
129 |
+
"loss": 0.0145,
|
130 |
+
"step": 160
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.6153846153846154,
|
134 |
+
"grad_norm": 0.0049270084127783775,
|
135 |
+
"learning_rate": 6.923076923076924e-05,
|
136 |
+
"loss": 0.0091,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.769230769230769,
|
141 |
+
"grad_norm": 42.14358901977539,
|
142 |
+
"learning_rate": 6.153846153846155e-05,
|
143 |
+
"loss": 0.1402,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.9230769230769234,
|
148 |
+
"grad_norm": 0.02492058463394642,
|
149 |
+
"learning_rate": 5.384615384615385e-05,
|
150 |
+
"loss": 0.0065,
|
151 |
+
"step": 190
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 3.076923076923077,
|
155 |
+
"grad_norm": 0.0023473859764635563,
|
156 |
+
"learning_rate": 4.615384615384616e-05,
|
157 |
+
"loss": 0.0101,
|
158 |
+
"step": 200
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 3.076923076923077,
|
162 |
+
"eval_accuracy": 0.9924812030075187,
|
163 |
+
"eval_loss": 0.018673665821552277,
|
164 |
+
"eval_runtime": 6.8913,
|
165 |
+
"eval_samples_per_second": 19.3,
|
166 |
+
"eval_steps_per_second": 2.467,
|
167 |
+
"step": 200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 3.230769230769231,
|
171 |
+
"grad_norm": 0.023455169051885605,
|
172 |
+
"learning_rate": 3.846153846153846e-05,
|
173 |
+
"loss": 0.0004,
|
174 |
+
"step": 210
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.3846153846153846,
|
178 |
+
"grad_norm": 0.0006098861922509968,
|
179 |
+
"learning_rate": 3.0769230769230774e-05,
|
180 |
+
"loss": 0.0001,
|
181 |
+
"step": 220
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 3.5384615384615383,
|
185 |
+
"grad_norm": 28.16423988342285,
|
186 |
+
"learning_rate": 2.307692307692308e-05,
|
187 |
+
"loss": 0.0388,
|
188 |
+
"step": 230
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 3.6923076923076925,
|
192 |
+
"grad_norm": 0.027881141752004623,
|
193 |
+
"learning_rate": 1.5384615384615387e-05,
|
194 |
+
"loss": 0.0002,
|
195 |
+
"step": 240
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 3.8461538461538463,
|
199 |
+
"grad_norm": 0.07322639971971512,
|
200 |
+
"learning_rate": 7.692307692307694e-06,
|
201 |
+
"loss": 0.0002,
|
202 |
+
"step": 250
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 4.0,
|
206 |
+
"grad_norm": 0.0007401489419862628,
|
207 |
+
"learning_rate": 0.0,
|
208 |
+
"loss": 0.0008,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 4.0,
|
213 |
+
"step": 260,
|
214 |
+
"total_flos": 1.0280724304719053e+17,
|
215 |
+
"train_loss": 0.15423231131683748,
|
216 |
+
"train_runtime": 475.1171,
|
217 |
+
"train_samples_per_second": 8.705,
|
218 |
+
"train_steps_per_second": 0.547
|
219 |
+
}
|
220 |
+
],
|
221 |
+
"logging_steps": 10,
|
222 |
+
"max_steps": 260,
|
223 |
+
"num_input_tokens_seen": 0,
|
224 |
+
"num_train_epochs": 4,
|
225 |
+
"save_steps": 100,
|
226 |
+
"stateful_callbacks": {
|
227 |
+
"TrainerControl": {
|
228 |
+
"args": {
|
229 |
+
"should_epoch_stop": false,
|
230 |
+
"should_evaluate": false,
|
231 |
+
"should_log": false,
|
232 |
+
"should_save": true,
|
233 |
+
"should_training_stop": true
|
234 |
+
},
|
235 |
+
"attributes": {}
|
236 |
+
}
|
237 |
+
},
|
238 |
+
"total_flos": 1.0280724304719053e+17,
|
239 |
+
"train_batch_size": 16,
|
240 |
+
"trial_name": null,
|
241 |
+
"trial_params": null
|
242 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:535b366c7cc1a85ea5c15b06dbf98e3e9cd34a9a045808f791f6af6ed3b7d095
|
3 |
+
size 5304
|