groderg commited on
Commit
a3260b6
1 Parent(s): fd5a942

Evaluation on the test set completed on 2024_10_31.

Browse files
README.md ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/dinov2-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Ziboiai-large-2024_10_31-prova_batch-size32_freeze_probs
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Ziboiai-large-2024_10_31-prova_batch-size32_freeze_probs
16
+
17
+ This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.6333
20
+ - Rmse: 0.3468
21
+ - Mae: 0.3060
22
+ - R2: -1.9752
23
+ - Explained Variance: 0.1029
24
+ - Learning Rate: 0.0000
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.001
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 150
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | R2 | Explained Variance | Rate |
55
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:------------------:|:------:|
56
+ | No log | 1.0 | 2 | 0.7005 | 0.3966 | 0.3705 | -21.5069 | 0.0684 | 0.001 |
57
+ | No log | 2.0 | 4 | 0.7249 | 0.4021 | 0.3746 | -26.3836 | 0.0822 | 0.001 |
58
+ | No log | 3.0 | 6 | 0.7532 | 0.4114 | 0.3816 | -29.6868 | 0.1178 | 0.001 |
59
+ | No log | 4.0 | 8 | 0.7681 | 0.4186 | 0.3850 | -29.0398 | 0.0566 | 0.001 |
60
+ | No log | 5.0 | 10 | 0.7665 | 0.4178 | 0.3827 | -26.6101 | 0.0116 | 0.001 |
61
+ | No log | 6.0 | 12 | 0.7594 | 0.4152 | 0.3779 | -24.2590 | -0.0414 | 0.001 |
62
+ | No log | 7.0 | 14 | 0.7494 | 0.4108 | 0.3715 | -22.3016 | -0.1878 | 0.001 |
63
+ | No log | 8.0 | 16 | 0.7214 | 0.3992 | 0.3610 | -20.1630 | -0.1876 | 0.0001 |
64
+ | No log | 9.0 | 18 | 0.7013 | 0.3905 | 0.3530 | -18.6708 | -0.1643 | 0.0001 |
65
+ | No log | 10.0 | 20 | 0.6869 | 0.3836 | 0.3467 | -17.4192 | -0.1505 | 0.0001 |
66
+ | No log | 11.0 | 22 | 0.6764 | 0.3787 | 0.3425 | -16.5076 | -0.1282 | 0.0001 |
67
+ | No log | 12.0 | 24 | 0.6669 | 0.3740 | 0.3384 | -16.0072 | -0.1085 | 0.0001 |
68
+ | No log | 13.0 | 26 | 0.6617 | 0.3712 | 0.3358 | -15.5612 | -0.0882 | 0.0001 |
69
+ | No log | 14.0 | 28 | 0.6557 | 0.3683 | 0.3332 | -14.8471 | -0.0399 | 0.0001 |
70
+ | No log | 15.0 | 30 | 0.6517 | 0.3661 | 0.3313 | -14.3744 | -0.0149 | 0.0001 |
71
+ | No log | 16.0 | 32 | 0.6494 | 0.3650 | 0.3302 | -14.0923 | 0.0009 | 0.0001 |
72
+ | No log | 17.0 | 34 | 0.6469 | 0.3634 | 0.3284 | -14.0430 | 0.0076 | 0.0001 |
73
+ | No log | 18.0 | 36 | 0.6455 | 0.3626 | 0.3275 | -13.8481 | 0.0275 | 0.0001 |
74
+ | No log | 19.0 | 38 | 0.6437 | 0.3617 | 0.3270 | -13.7294 | 0.0458 | 0.0001 |
75
+ | No log | 20.0 | 40 | 0.6426 | 0.3611 | 0.3265 | -13.4695 | 0.0571 | 0.0001 |
76
+ | No log | 21.0 | 42 | 0.6414 | 0.3605 | 0.3256 | -13.4449 | 0.0581 | 0.0001 |
77
+ | No log | 22.0 | 44 | 0.6422 | 0.3605 | 0.3257 | -13.3180 | 0.0542 | 0.0001 |
78
+ | No log | 23.0 | 46 | 0.6407 | 0.3593 | 0.3246 | -13.2487 | 0.0755 | 0.0001 |
79
+ | No log | 24.0 | 48 | 0.6375 | 0.3576 | 0.3230 | -13.2495 | 0.0741 | 0.0001 |
80
+ | No log | 25.0 | 50 | 0.6332 | 0.3551 | 0.3205 | -12.9650 | 0.0843 | 0.0001 |
81
+ | No log | 26.0 | 52 | 0.6316 | 0.3540 | 0.3191 | -12.7124 | 0.0903 | 0.0001 |
82
+ | No log | 27.0 | 54 | 0.6298 | 0.3527 | 0.3176 | -12.5315 | 0.0972 | 0.0001 |
83
+ | No log | 28.0 | 56 | 0.6287 | 0.3519 | 0.3168 | -12.3934 | 0.1010 | 0.0001 |
84
+ | No log | 29.0 | 58 | 0.6279 | 0.3514 | 0.3163 | -12.3234 | 0.1064 | 0.0001 |
85
+ | No log | 30.0 | 60 | 0.6246 | 0.3494 | 0.3141 | -12.2314 | 0.1160 | 0.0001 |
86
+ | No log | 31.0 | 62 | 0.6211 | 0.3475 | 0.3123 | -12.0643 | 0.1264 | 0.0001 |
87
+ | No log | 32.0 | 64 | 0.6218 | 0.3477 | 0.3125 | -11.9670 | 0.1294 | 0.0001 |
88
+ | No log | 33.0 | 66 | 0.6202 | 0.3470 | 0.3120 | -11.7550 | 0.1365 | 0.0001 |
89
+ | No log | 34.0 | 68 | 0.6191 | 0.3463 | 0.3111 | -11.6145 | 0.1364 | 0.0001 |
90
+ | No log | 35.0 | 70 | 0.6174 | 0.3455 | 0.3105 | -11.5861 | 0.1400 | 0.0001 |
91
+ | No log | 36.0 | 72 | 0.6195 | 0.3462 | 0.3109 | -11.7605 | 0.1398 | 0.0001 |
92
+ | No log | 37.0 | 74 | 0.6210 | 0.3470 | 0.3114 | -11.7035 | 0.1367 | 0.0001 |
93
+ | No log | 38.0 | 76 | 0.6201 | 0.3463 | 0.3107 | -11.6608 | 0.1387 | 0.0001 |
94
+ | No log | 39.0 | 78 | 0.6195 | 0.3461 | 0.3106 | -11.6294 | 0.1362 | 0.0001 |
95
+ | No log | 40.0 | 80 | 0.6195 | 0.3459 | 0.3101 | -11.6709 | 0.1279 | 0.0001 |
96
+ | No log | 41.0 | 82 | 0.6196 | 0.3456 | 0.3095 | -11.4656 | 0.1154 | 0.0001 |
97
+ | No log | 42.0 | 84 | 0.6185 | 0.3453 | 0.3096 | -11.4190 | 0.1220 | 1e-05 |
98
+ | No log | 43.0 | 86 | 0.6196 | 0.3457 | 0.3099 | -11.4211 | 0.1224 | 1e-05 |
99
+ | No log | 44.0 | 88 | 0.6175 | 0.3448 | 0.3091 | -11.3422 | 0.1252 | 1e-05 |
100
+ | No log | 45.0 | 90 | 0.6148 | 0.3435 | 0.3079 | -11.2377 | 0.1267 | 1e-05 |
101
+ | No log | 46.0 | 92 | 0.6156 | 0.3439 | 0.3081 | -11.2161 | 0.1232 | 1e-05 |
102
+ | No log | 47.0 | 94 | 0.6162 | 0.3442 | 0.3084 | -11.2359 | 0.1219 | 1e-05 |
103
+ | No log | 48.0 | 96 | 0.6153 | 0.3438 | 0.3079 | -11.1407 | 0.1218 | 1e-05 |
104
+ | No log | 49.0 | 98 | 0.6142 | 0.3434 | 0.3075 | -11.0878 | 0.1259 | 1e-05 |
105
+ | No log | 50.0 | 100 | 0.6125 | 0.3427 | 0.3071 | -11.1648 | 0.1241 | 1e-05 |
106
+ | No log | 51.0 | 102 | 0.6131 | 0.3430 | 0.3072 | -11.2371 | 0.1274 | 1e-05 |
107
+ | No log | 52.0 | 104 | 0.6137 | 0.3434 | 0.3077 | -11.3909 | 0.1274 | 1e-05 |
108
+ | No log | 53.0 | 106 | 0.6139 | 0.3434 | 0.3077 | -11.5018 | 0.1224 | 1e-05 |
109
+ | No log | 54.0 | 108 | 0.6157 | 0.3445 | 0.3089 | -11.6674 | 0.1222 | 1e-05 |
110
+ | No log | 55.0 | 110 | 0.6168 | 0.3448 | 0.3090 | -11.6467 | 0.1222 | 1e-05 |
111
+ | No log | 56.0 | 112 | 0.6140 | 0.3434 | 0.3077 | -11.4968 | 0.1250 | 1e-05 |
112
+ | No log | 57.0 | 114 | 0.6133 | 0.3430 | 0.3071 | -11.5002 | 0.1216 | 0.0000 |
113
+ | No log | 58.0 | 116 | 0.6130 | 0.3428 | 0.3070 | -11.4475 | 0.1210 | 0.0000 |
114
+ | No log | 59.0 | 118 | 0.6150 | 0.3441 | 0.3083 | -11.5562 | 0.1178 | 0.0000 |
115
+ | No log | 60.0 | 120 | 0.6167 | 0.3450 | 0.3092 | -11.4676 | 0.1243 | 0.0000 |
116
+
117
+
118
+ ### Framework versions
119
+
120
+ - Transformers 4.44.2
121
+ - Pytorch 2.4.1+cu121
122
+ - Datasets 3.0.0
123
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 60.0,
3
+ "eval_explained_variance": 0.10288698971271515,
4
+ "eval_loss": 0.633324384689331,
5
+ "eval_mae": 0.30597275495529175,
6
+ "eval_r2": -1.975172758102417,
7
+ "eval_rmse": 0.3468049466609955,
8
+ "eval_runtime": 1.0485,
9
+ "eval_samples_per_second": 47.685,
10
+ "eval_steps_per_second": 1.907,
11
+ "learning_rate": 1.0000000000000002e-06,
12
+ "total_flos": 4.4402778184752e+17,
13
+ "train_loss": 0.6329069137573242,
14
+ "train_runtime": 375.0945,
15
+ "train_samples_per_second": 19.995,
16
+ "train_steps_per_second": 0.8
17
+ }
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/dinov2-large",
3
+ "apply_layernorm": true,
4
+ "architectures": [
5
+ "Dinov2ForImageClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.0,
8
+ "drop_path_rate": 0.0,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.0,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "Acropore_branched",
14
+ "1": "Acropore_digitised",
15
+ "2": "Acropore_tabular",
16
+ "3": "Algae",
17
+ "4": "Dead_coral",
18
+ "5": "Fish",
19
+ "6": "Millepore",
20
+ "7": "No_acropore_encrusting",
21
+ "8": "No_acropore_massive",
22
+ "9": "No_acropore_sub_massive",
23
+ "10": "Rock",
24
+ "11": "Rubble",
25
+ "12": "Sand"
26
+ },
27
+ "image_size": 164,
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "Acropore_branched": 0,
31
+ "Acropore_digitised": 1,
32
+ "Acropore_tabular": 2,
33
+ "Algae": 3,
34
+ "Dead_coral": 4,
35
+ "Fish": 5,
36
+ "Millepore": 6,
37
+ "No_acropore_encrusting": 7,
38
+ "No_acropore_massive": 8,
39
+ "No_acropore_sub_massive": 9,
40
+ "Rock": 10,
41
+ "Rubble": 11,
42
+ "Sand": 12
43
+ },
44
+ "layer_norm_eps": 1e-06,
45
+ "layerscale_value": 1.0,
46
+ "mlp_ratio": 4,
47
+ "model_type": "dinov2",
48
+ "num_attention_heads": 16,
49
+ "num_channels": 3,
50
+ "num_hidden_layers": 24,
51
+ "out_features": [
52
+ "stage24"
53
+ ],
54
+ "out_indices": [
55
+ 24
56
+ ],
57
+ "patch_size": 14,
58
+ "problem_type": "multi_label_classification",
59
+ "qkv_bias": true,
60
+ "reshape_hidden_states": true,
61
+ "stage_names": [
62
+ "stem",
63
+ "stage1",
64
+ "stage2",
65
+ "stage3",
66
+ "stage4",
67
+ "stage5",
68
+ "stage6",
69
+ "stage7",
70
+ "stage8",
71
+ "stage9",
72
+ "stage10",
73
+ "stage11",
74
+ "stage12",
75
+ "stage13",
76
+ "stage14",
77
+ "stage15",
78
+ "stage16",
79
+ "stage17",
80
+ "stage18",
81
+ "stage19",
82
+ "stage20",
83
+ "stage21",
84
+ "stage22",
85
+ "stage23",
86
+ "stage24"
87
+ ],
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.44.2",
90
+ "use_swiglu_ffn": false
91
+ }
logs/events.out.tfevents.1730352536.datavisu4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46bab5cda3969cf96a14b3772b9d5c852f85cbb55c74c92c12248b4305ec896
3
+ size 25085
logs/events.out.tfevents.1730352893.datavisu3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3272147ad7b72743e1ede37aeb5e39bd63f0a6e49f8b1d3eb286323e1c1ec7c
3
+ size 38018
logs/events.out.tfevents.1730353344.datavisu3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599619c4bf040e2e2108488a096b7ab47b8d33f71ba2deaec16843b577491876
3
+ size 40
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec42591f36bdfb80f97bb92cd3915ad2b8ba59617c4a381b145ce5e3de2f726
3
+ size 1222958756
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": false,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.485,
13
+ 0.456,
14
+ 0.406
15
+ ],
16
+ "image_processor_type": "BitImageProcessor",
17
+ "image_std": [
18
+ 0.229,
19
+ 0.224,
20
+ 0.225
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "height": 164,
26
+ "width": 164
27
+ }
28
+ }
runs/events.out.tfevents.1730352525.datavisu4 ADDED
File without changes
runs/events.out.tfevents.1730352882.datavisu3 ADDED
File without changes
test_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 60.0,
3
+ "eval_explained_variance": 0.10288698971271515,
4
+ "eval_loss": 0.633324384689331,
5
+ "eval_mae": 0.30597275495529175,
6
+ "eval_r2": -1.975172758102417,
7
+ "eval_rmse": 0.3468049466609955,
8
+ "eval_runtime": 1.0485,
9
+ "eval_samples_per_second": 47.685,
10
+ "eval_steps_per_second": 1.907,
11
+ "learning_rate": 1.0000000000000002e-06
12
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 60.0,
3
+ "learning_rate": 1.0000000000000002e-06,
4
+ "total_flos": 4.4402778184752e+17,
5
+ "train_loss": 0.6329069137573242,
6
+ "train_runtime": 375.0945,
7
+ "train_samples_per_second": 19.995,
8
+ "train_steps_per_second": 0.8
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,832 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6125256419181824,
3
+ "best_model_checkpoint": "/home1/datahome/villien/project_hub/DinoVdeau/models/Ziboiai-large-2024_10_31-prova_batch-size32_freeze_probs/checkpoint-100",
4
+ "epoch": 60.0,
5
+ "eval_steps": 500,
6
+ "global_step": 120,
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_explained_variance": 0.06840751320123672,
14
+ "eval_loss": 0.7004616260528564,
15
+ "eval_mae": 0.37051576375961304,
16
+ "eval_r2": -21.506893157958984,
17
+ "eval_rmse": 0.3965546190738678,
18
+ "eval_runtime": 1.2359,
19
+ "eval_samples_per_second": 40.458,
20
+ "eval_steps_per_second": 1.618,
21
+ "learning_rate": 0.001,
22
+ "step": 2
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_explained_variance": 0.08221305161714554,
27
+ "eval_loss": 0.7249369621276855,
28
+ "eval_mae": 0.37463027238845825,
29
+ "eval_r2": -26.38355827331543,
30
+ "eval_rmse": 0.40212786197662354,
31
+ "eval_runtime": 0.3187,
32
+ "eval_samples_per_second": 156.871,
33
+ "eval_steps_per_second": 6.275,
34
+ "learning_rate": 0.001,
35
+ "step": 4
36
+ },
37
+ {
38
+ "epoch": 3.0,
39
+ "eval_explained_variance": 0.11782943457365036,
40
+ "eval_loss": 0.7532215118408203,
41
+ "eval_mae": 0.3815617859363556,
42
+ "eval_r2": -29.68680763244629,
43
+ "eval_rmse": 0.4113939702510834,
44
+ "eval_runtime": 0.3018,
45
+ "eval_samples_per_second": 165.696,
46
+ "eval_steps_per_second": 6.628,
47
+ "learning_rate": 0.001,
48
+ "step": 6
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_explained_variance": 0.05660984292626381,
53
+ "eval_loss": 0.7681224942207336,
54
+ "eval_mae": 0.384958416223526,
55
+ "eval_r2": -29.039794921875,
56
+ "eval_rmse": 0.4185601472854614,
57
+ "eval_runtime": 0.3198,
58
+ "eval_samples_per_second": 156.355,
59
+ "eval_steps_per_second": 6.254,
60
+ "learning_rate": 0.001,
61
+ "step": 8
62
+ },
63
+ {
64
+ "epoch": 5.0,
65
+ "eval_explained_variance": 0.011602365411818027,
66
+ "eval_loss": 0.7665389776229858,
67
+ "eval_mae": 0.3826686143875122,
68
+ "eval_r2": -26.610107421875,
69
+ "eval_rmse": 0.4177513122558594,
70
+ "eval_runtime": 0.2997,
71
+ "eval_samples_per_second": 166.846,
72
+ "eval_steps_per_second": 6.674,
73
+ "learning_rate": 0.001,
74
+ "step": 10
75
+ },
76
+ {
77
+ "epoch": 6.0,
78
+ "eval_explained_variance": -0.041439518332481384,
79
+ "eval_loss": 0.7593734860420227,
80
+ "eval_mae": 0.37791818380355835,
81
+ "eval_r2": -24.258955001831055,
82
+ "eval_rmse": 0.41521450877189636,
83
+ "eval_runtime": 0.3036,
84
+ "eval_samples_per_second": 164.675,
85
+ "eval_steps_per_second": 6.587,
86
+ "learning_rate": 0.001,
87
+ "step": 12
88
+ },
89
+ {
90
+ "epoch": 7.0,
91
+ "eval_explained_variance": -0.18780630826950073,
92
+ "eval_loss": 0.7493597269058228,
93
+ "eval_mae": 0.3714950978755951,
94
+ "eval_r2": -22.30160903930664,
95
+ "eval_rmse": 0.41082921624183655,
96
+ "eval_runtime": 0.3045,
97
+ "eval_samples_per_second": 164.187,
98
+ "eval_steps_per_second": 6.567,
99
+ "learning_rate": 0.001,
100
+ "step": 14
101
+ },
102
+ {
103
+ "epoch": 8.0,
104
+ "eval_explained_variance": -0.1876310557126999,
105
+ "eval_loss": 0.7214367389678955,
106
+ "eval_mae": 0.36099693179130554,
107
+ "eval_r2": -20.16297149658203,
108
+ "eval_rmse": 0.3992151916027069,
109
+ "eval_runtime": 0.325,
110
+ "eval_samples_per_second": 153.846,
111
+ "eval_steps_per_second": 6.154,
112
+ "learning_rate": 0.0001,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 9.0,
117
+ "eval_explained_variance": -0.164337158203125,
118
+ "eval_loss": 0.7012718915939331,
119
+ "eval_mae": 0.352971613407135,
120
+ "eval_r2": -18.67078971862793,
121
+ "eval_rmse": 0.3905433118343353,
122
+ "eval_runtime": 0.3097,
123
+ "eval_samples_per_second": 161.468,
124
+ "eval_steps_per_second": 6.459,
125
+ "learning_rate": 0.0001,
126
+ "step": 18
127
+ },
128
+ {
129
+ "epoch": 10.0,
130
+ "eval_explained_variance": -0.15046803653240204,
131
+ "eval_loss": 0.6868528723716736,
132
+ "eval_mae": 0.346741646528244,
133
+ "eval_r2": -17.41924476623535,
134
+ "eval_rmse": 0.3835551142692566,
135
+ "eval_runtime": 0.3073,
136
+ "eval_samples_per_second": 162.696,
137
+ "eval_steps_per_second": 6.508,
138
+ "learning_rate": 0.0001,
139
+ "step": 20
140
+ },
141
+ {
142
+ "epoch": 11.0,
143
+ "eval_explained_variance": -0.12824733555316925,
144
+ "eval_loss": 0.6764166951179504,
145
+ "eval_mae": 0.34248146414756775,
146
+ "eval_r2": -16.507604598999023,
147
+ "eval_rmse": 0.3787185549736023,
148
+ "eval_runtime": 0.3242,
149
+ "eval_samples_per_second": 154.219,
150
+ "eval_steps_per_second": 6.169,
151
+ "learning_rate": 0.0001,
152
+ "step": 22
153
+ },
154
+ {
155
+ "epoch": 12.0,
156
+ "eval_explained_variance": -0.10852393507957458,
157
+ "eval_loss": 0.6669396758079529,
158
+ "eval_mae": 0.33840715885162354,
159
+ "eval_r2": -16.007225036621094,
160
+ "eval_rmse": 0.3739539384841919,
161
+ "eval_runtime": 0.3298,
162
+ "eval_samples_per_second": 151.614,
163
+ "eval_steps_per_second": 6.065,
164
+ "learning_rate": 0.0001,
165
+ "step": 24
166
+ },
167
+ {
168
+ "epoch": 13.0,
169
+ "eval_explained_variance": -0.08818976581096649,
170
+ "eval_loss": 0.661744236946106,
171
+ "eval_mae": 0.3357750177383423,
172
+ "eval_r2": -15.561150550842285,
173
+ "eval_rmse": 0.3711845278739929,
174
+ "eval_runtime": 0.3053,
175
+ "eval_samples_per_second": 163.757,
176
+ "eval_steps_per_second": 6.55,
177
+ "learning_rate": 0.0001,
178
+ "step": 26
179
+ },
180
+ {
181
+ "epoch": 14.0,
182
+ "eval_explained_variance": -0.03988352045416832,
183
+ "eval_loss": 0.6557328701019287,
184
+ "eval_mae": 0.33316293358802795,
185
+ "eval_r2": -14.847132682800293,
186
+ "eval_rmse": 0.3683193624019623,
187
+ "eval_runtime": 0.3055,
188
+ "eval_samples_per_second": 163.645,
189
+ "eval_steps_per_second": 6.546,
190
+ "learning_rate": 0.0001,
191
+ "step": 28
192
+ },
193
+ {
194
+ "epoch": 15.0,
195
+ "eval_explained_variance": -0.014903265982866287,
196
+ "eval_loss": 0.6516609787940979,
197
+ "eval_mae": 0.33125975728034973,
198
+ "eval_r2": -14.374401092529297,
199
+ "eval_rmse": 0.36609962582588196,
200
+ "eval_runtime": 0.3245,
201
+ "eval_samples_per_second": 154.102,
202
+ "eval_steps_per_second": 6.164,
203
+ "learning_rate": 0.0001,
204
+ "step": 30
205
+ },
206
+ {
207
+ "epoch": 16.0,
208
+ "eval_explained_variance": 0.0008760415366850793,
209
+ "eval_loss": 0.6493728756904602,
210
+ "eval_mae": 0.33018919825553894,
211
+ "eval_r2": -14.09227180480957,
212
+ "eval_rmse": 0.36498352885246277,
213
+ "eval_runtime": 0.2973,
214
+ "eval_samples_per_second": 168.196,
215
+ "eval_steps_per_second": 6.728,
216
+ "learning_rate": 0.0001,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 17.0,
221
+ "eval_explained_variance": 0.007616698741912842,
222
+ "eval_loss": 0.6469070315361023,
223
+ "eval_mae": 0.3284085690975189,
224
+ "eval_r2": -14.042997360229492,
225
+ "eval_rmse": 0.3634098768234253,
226
+ "eval_runtime": 0.2968,
227
+ "eval_samples_per_second": 168.439,
228
+ "eval_steps_per_second": 6.738,
229
+ "learning_rate": 0.0001,
230
+ "step": 34
231
+ },
232
+ {
233
+ "epoch": 18.0,
234
+ "eval_explained_variance": 0.027522683143615723,
235
+ "eval_loss": 0.6455032825469971,
236
+ "eval_mae": 0.327472984790802,
237
+ "eval_r2": -13.848074913024902,
238
+ "eval_rmse": 0.3625529706478119,
239
+ "eval_runtime": 0.3023,
240
+ "eval_samples_per_second": 165.395,
241
+ "eval_steps_per_second": 6.616,
242
+ "learning_rate": 0.0001,
243
+ "step": 36
244
+ },
245
+ {
246
+ "epoch": 19.0,
247
+ "eval_explained_variance": 0.04580416530370712,
248
+ "eval_loss": 0.64373379945755,
249
+ "eval_mae": 0.3270127475261688,
250
+ "eval_r2": -13.729372024536133,
251
+ "eval_rmse": 0.36171066761016846,
252
+ "eval_runtime": 0.2975,
253
+ "eval_samples_per_second": 168.069,
254
+ "eval_steps_per_second": 6.723,
255
+ "learning_rate": 0.0001,
256
+ "step": 38
257
+ },
258
+ {
259
+ "epoch": 20.0,
260
+ "eval_explained_variance": 0.05705893412232399,
261
+ "eval_loss": 0.6426065564155579,
262
+ "eval_mae": 0.3264869153499603,
263
+ "eval_r2": -13.46953296661377,
264
+ "eval_rmse": 0.3610925078392029,
265
+ "eval_runtime": 0.303,
266
+ "eval_samples_per_second": 164.994,
267
+ "eval_steps_per_second": 6.6,
268
+ "learning_rate": 0.0001,
269
+ "step": 40
270
+ },
271
+ {
272
+ "epoch": 21.0,
273
+ "eval_explained_variance": 0.058054760098457336,
274
+ "eval_loss": 0.6413648128509521,
275
+ "eval_mae": 0.32564398646354675,
276
+ "eval_r2": -13.444860458374023,
277
+ "eval_rmse": 0.36047738790512085,
278
+ "eval_runtime": 0.2971,
279
+ "eval_samples_per_second": 168.316,
280
+ "eval_steps_per_second": 6.733,
281
+ "learning_rate": 0.0001,
282
+ "step": 42
283
+ },
284
+ {
285
+ "epoch": 22.0,
286
+ "eval_explained_variance": 0.05415903031826019,
287
+ "eval_loss": 0.6421814560890198,
288
+ "eval_mae": 0.32565081119537354,
289
+ "eval_r2": -13.317983627319336,
290
+ "eval_rmse": 0.360535204410553,
291
+ "eval_runtime": 0.2965,
292
+ "eval_samples_per_second": 168.653,
293
+ "eval_steps_per_second": 6.746,
294
+ "learning_rate": 0.0001,
295
+ "step": 44
296
+ },
297
+ {
298
+ "epoch": 23.0,
299
+ "eval_explained_variance": 0.07554426789283752,
300
+ "eval_loss": 0.6406619548797607,
301
+ "eval_mae": 0.3246156871318817,
302
+ "eval_r2": -13.248732566833496,
303
+ "eval_rmse": 0.35933929681777954,
304
+ "eval_runtime": 0.2972,
305
+ "eval_samples_per_second": 168.22,
306
+ "eval_steps_per_second": 6.729,
307
+ "learning_rate": 0.0001,
308
+ "step": 46
309
+ },
310
+ {
311
+ "epoch": 24.0,
312
+ "eval_explained_variance": 0.07407143712043762,
313
+ "eval_loss": 0.637528121471405,
314
+ "eval_mae": 0.32300955057144165,
315
+ "eval_r2": -13.249483108520508,
316
+ "eval_rmse": 0.35758209228515625,
317
+ "eval_runtime": 0.3004,
318
+ "eval_samples_per_second": 166.463,
319
+ "eval_steps_per_second": 6.659,
320
+ "learning_rate": 0.0001,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 25.0,
325
+ "eval_explained_variance": 0.08428207039833069,
326
+ "eval_loss": 0.6331558227539062,
327
+ "eval_mae": 0.3205055892467499,
328
+ "eval_r2": -12.964966773986816,
329
+ "eval_rmse": 0.35511815547943115,
330
+ "eval_runtime": 0.2968,
331
+ "eval_samples_per_second": 168.439,
332
+ "eval_steps_per_second": 6.738,
333
+ "learning_rate": 0.0001,
334
+ "step": 50
335
+ },
336
+ {
337
+ "epoch": 26.0,
338
+ "eval_explained_variance": 0.0902879610657692,
339
+ "eval_loss": 0.6315688490867615,
340
+ "eval_mae": 0.3191172182559967,
341
+ "eval_r2": -12.712376594543457,
342
+ "eval_rmse": 0.3540325164794922,
343
+ "eval_runtime": 0.3046,
344
+ "eval_samples_per_second": 164.139,
345
+ "eval_steps_per_second": 6.566,
346
+ "learning_rate": 0.0001,
347
+ "step": 52
348
+ },
349
+ {
350
+ "epoch": 27.0,
351
+ "eval_explained_variance": 0.09721990674734116,
352
+ "eval_loss": 0.6297861337661743,
353
+ "eval_mae": 0.3175807297229767,
354
+ "eval_r2": -12.53150749206543,
355
+ "eval_rmse": 0.3526574671268463,
356
+ "eval_runtime": 0.2981,
357
+ "eval_samples_per_second": 167.733,
358
+ "eval_steps_per_second": 6.709,
359
+ "learning_rate": 0.0001,
360
+ "step": 54
361
+ },
362
+ {
363
+ "epoch": 28.0,
364
+ "eval_explained_variance": 0.10100533068180084,
365
+ "eval_loss": 0.6287277340888977,
366
+ "eval_mae": 0.3168259263038635,
367
+ "eval_r2": -12.393423080444336,
368
+ "eval_rmse": 0.35192248225212097,
369
+ "eval_runtime": 0.305,
370
+ "eval_samples_per_second": 163.956,
371
+ "eval_steps_per_second": 6.558,
372
+ "learning_rate": 0.0001,
373
+ "step": 56
374
+ },
375
+ {
376
+ "epoch": 29.0,
377
+ "eval_explained_variance": 0.1064082533121109,
378
+ "eval_loss": 0.627882719039917,
379
+ "eval_mae": 0.3163486123085022,
380
+ "eval_r2": -12.323440551757812,
381
+ "eval_rmse": 0.35138675570487976,
382
+ "eval_runtime": 0.2979,
383
+ "eval_samples_per_second": 167.823,
384
+ "eval_steps_per_second": 6.713,
385
+ "learning_rate": 0.0001,
386
+ "step": 58
387
+ },
388
+ {
389
+ "epoch": 30.0,
390
+ "eval_explained_variance": 0.1159624308347702,
391
+ "eval_loss": 0.6246291995048523,
392
+ "eval_mae": 0.3141040503978729,
393
+ "eval_r2": -12.231378555297852,
394
+ "eval_rmse": 0.3494300842285156,
395
+ "eval_runtime": 0.2969,
396
+ "eval_samples_per_second": 168.407,
397
+ "eval_steps_per_second": 6.736,
398
+ "learning_rate": 0.0001,
399
+ "step": 60
400
+ },
401
+ {
402
+ "epoch": 31.0,
403
+ "eval_explained_variance": 0.1264413446187973,
404
+ "eval_loss": 0.6210973262786865,
405
+ "eval_mae": 0.31232017278671265,
406
+ "eval_r2": -12.064345359802246,
407
+ "eval_rmse": 0.34745490550994873,
408
+ "eval_runtime": 0.2987,
409
+ "eval_samples_per_second": 167.391,
410
+ "eval_steps_per_second": 6.696,
411
+ "learning_rate": 0.0001,
412
+ "step": 62
413
+ },
414
+ {
415
+ "epoch": 32.0,
416
+ "eval_explained_variance": 0.12937316298484802,
417
+ "eval_loss": 0.6217814087867737,
418
+ "eval_mae": 0.31251102685928345,
419
+ "eval_r2": -11.966958045959473,
420
+ "eval_rmse": 0.3476860225200653,
421
+ "eval_runtime": 0.2966,
422
+ "eval_samples_per_second": 168.6,
423
+ "eval_steps_per_second": 6.744,
424
+ "learning_rate": 0.0001,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 33.0,
429
+ "eval_explained_variance": 0.13646358251571655,
430
+ "eval_loss": 0.6202294230461121,
431
+ "eval_mae": 0.3120400309562683,
432
+ "eval_r2": -11.754964828491211,
433
+ "eval_rmse": 0.3470361530780792,
434
+ "eval_runtime": 0.2983,
435
+ "eval_samples_per_second": 167.594,
436
+ "eval_steps_per_second": 6.704,
437
+ "learning_rate": 0.0001,
438
+ "step": 66
439
+ },
440
+ {
441
+ "epoch": 34.0,
442
+ "eval_explained_variance": 0.13642433285713196,
443
+ "eval_loss": 0.6191384792327881,
444
+ "eval_mae": 0.31109973788261414,
445
+ "eval_r2": -11.614458084106445,
446
+ "eval_rmse": 0.34630581736564636,
447
+ "eval_runtime": 0.2968,
448
+ "eval_samples_per_second": 168.491,
449
+ "eval_steps_per_second": 6.74,
450
+ "learning_rate": 0.0001,
451
+ "step": 68
452
+ },
453
+ {
454
+ "epoch": 35.0,
455
+ "eval_explained_variance": 0.1399742215871811,
456
+ "eval_loss": 0.617404043674469,
457
+ "eval_mae": 0.31046897172927856,
458
+ "eval_r2": -11.586063385009766,
459
+ "eval_rmse": 0.3454545736312866,
460
+ "eval_runtime": 0.3043,
461
+ "eval_samples_per_second": 164.292,
462
+ "eval_steps_per_second": 6.572,
463
+ "learning_rate": 0.0001,
464
+ "step": 70
465
+ },
466
+ {
467
+ "epoch": 36.0,
468
+ "eval_explained_variance": 0.13982802629470825,
469
+ "eval_loss": 0.6194512248039246,
470
+ "eval_mae": 0.31094375252723694,
471
+ "eval_r2": -11.760537147521973,
472
+ "eval_rmse": 0.34623825550079346,
473
+ "eval_runtime": 0.3044,
474
+ "eval_samples_per_second": 164.269,
475
+ "eval_steps_per_second": 6.571,
476
+ "learning_rate": 0.0001,
477
+ "step": 72
478
+ },
479
+ {
480
+ "epoch": 37.0,
481
+ "eval_explained_variance": 0.13672398030757904,
482
+ "eval_loss": 0.6209845542907715,
483
+ "eval_mae": 0.3114151358604431,
484
+ "eval_r2": -11.703511238098145,
485
+ "eval_rmse": 0.34697073698043823,
486
+ "eval_runtime": 0.2966,
487
+ "eval_samples_per_second": 168.568,
488
+ "eval_steps_per_second": 6.743,
489
+ "learning_rate": 0.0001,
490
+ "step": 74
491
+ },
492
+ {
493
+ "epoch": 38.0,
494
+ "eval_explained_variance": 0.1387355923652649,
495
+ "eval_loss": 0.6201078295707703,
496
+ "eval_mae": 0.31073129177093506,
497
+ "eval_r2": -11.660818099975586,
498
+ "eval_rmse": 0.3463174104690552,
499
+ "eval_runtime": 0.3051,
500
+ "eval_samples_per_second": 163.878,
501
+ "eval_steps_per_second": 6.555,
502
+ "learning_rate": 0.0001,
503
+ "step": 76
504
+ },
505
+ {
506
+ "epoch": 39.0,
507
+ "eval_explained_variance": 0.1361588090658188,
508
+ "eval_loss": 0.6195101141929626,
509
+ "eval_mae": 0.31057408452033997,
510
+ "eval_r2": -11.629423141479492,
511
+ "eval_rmse": 0.34605538845062256,
512
+ "eval_runtime": 0.3059,
513
+ "eval_samples_per_second": 163.478,
514
+ "eval_steps_per_second": 6.539,
515
+ "learning_rate": 0.0001,
516
+ "step": 78
517
+ },
518
+ {
519
+ "epoch": 40.0,
520
+ "eval_explained_variance": 0.12785865366458893,
521
+ "eval_loss": 0.619523823261261,
522
+ "eval_mae": 0.3101230263710022,
523
+ "eval_r2": -11.670927047729492,
524
+ "eval_rmse": 0.34588271379470825,
525
+ "eval_runtime": 0.2984,
526
+ "eval_samples_per_second": 167.532,
527
+ "eval_steps_per_second": 6.701,
528
+ "learning_rate": 0.0001,
529
+ "step": 80
530
+ },
531
+ {
532
+ "epoch": 41.0,
533
+ "eval_explained_variance": 0.11544161289930344,
534
+ "eval_loss": 0.6195899844169617,
535
+ "eval_mae": 0.30954211950302124,
536
+ "eval_r2": -11.46561050415039,
537
+ "eval_rmse": 0.34560662508010864,
538
+ "eval_runtime": 0.3049,
539
+ "eval_samples_per_second": 163.969,
540
+ "eval_steps_per_second": 6.559,
541
+ "learning_rate": 0.0001,
542
+ "step": 82
543
+ },
544
+ {
545
+ "epoch": 42.0,
546
+ "eval_explained_variance": 0.12202569097280502,
547
+ "eval_loss": 0.6184768676757812,
548
+ "eval_mae": 0.3095985949039459,
549
+ "eval_r2": -11.41903305053711,
550
+ "eval_rmse": 0.3453018367290497,
551
+ "eval_runtime": 0.3052,
552
+ "eval_samples_per_second": 163.826,
553
+ "eval_steps_per_second": 6.553,
554
+ "learning_rate": 1e-05,
555
+ "step": 84
556
+ },
557
+ {
558
+ "epoch": 43.0,
559
+ "eval_explained_variance": 0.12239150702953339,
560
+ "eval_loss": 0.619608998298645,
561
+ "eval_mae": 0.3099028468132019,
562
+ "eval_r2": -11.421133995056152,
563
+ "eval_rmse": 0.3457002341747284,
564
+ "eval_runtime": 0.2987,
565
+ "eval_samples_per_second": 167.405,
566
+ "eval_steps_per_second": 6.696,
567
+ "learning_rate": 1e-05,
568
+ "step": 86
569
+ },
570
+ {
571
+ "epoch": 44.0,
572
+ "eval_explained_variance": 0.12524205446243286,
573
+ "eval_loss": 0.6175010204315186,
574
+ "eval_mae": 0.3090519905090332,
575
+ "eval_r2": -11.342177391052246,
576
+ "eval_rmse": 0.34480178356170654,
577
+ "eval_runtime": 0.3287,
578
+ "eval_samples_per_second": 152.124,
579
+ "eval_steps_per_second": 6.085,
580
+ "learning_rate": 1e-05,
581
+ "step": 88
582
+ },
583
+ {
584
+ "epoch": 45.0,
585
+ "eval_explained_variance": 0.12674368917942047,
586
+ "eval_loss": 0.6147510409355164,
587
+ "eval_mae": 0.307899534702301,
588
+ "eval_r2": -11.237728118896484,
589
+ "eval_rmse": 0.3434869647026062,
590
+ "eval_runtime": 0.3235,
591
+ "eval_samples_per_second": 154.557,
592
+ "eval_steps_per_second": 6.182,
593
+ "learning_rate": 1e-05,
594
+ "step": 90
595
+ },
596
+ {
597
+ "epoch": 46.0,
598
+ "eval_explained_variance": 0.12321905046701431,
599
+ "eval_loss": 0.6155768036842346,
600
+ "eval_mae": 0.3080970048904419,
601
+ "eval_r2": -11.216095924377441,
602
+ "eval_rmse": 0.3438577651977539,
603
+ "eval_runtime": 0.299,
604
+ "eval_samples_per_second": 167.246,
605
+ "eval_steps_per_second": 6.69,
606
+ "learning_rate": 1e-05,
607
+ "step": 92
608
+ },
609
+ {
610
+ "epoch": 47.0,
611
+ "eval_explained_variance": 0.12190257012844086,
612
+ "eval_loss": 0.616154670715332,
613
+ "eval_mae": 0.30844491720199585,
614
+ "eval_r2": -11.23585319519043,
615
+ "eval_rmse": 0.3442190885543823,
616
+ "eval_runtime": 0.299,
617
+ "eval_samples_per_second": 167.245,
618
+ "eval_steps_per_second": 6.69,
619
+ "learning_rate": 1e-05,
620
+ "step": 94
621
+ },
622
+ {
623
+ "epoch": 48.0,
624
+ "eval_explained_variance": 0.12182028591632843,
625
+ "eval_loss": 0.6153092980384827,
626
+ "eval_mae": 0.3079487085342407,
627
+ "eval_r2": -11.14069652557373,
628
+ "eval_rmse": 0.34381839632987976,
629
+ "eval_runtime": 0.3282,
630
+ "eval_samples_per_second": 152.339,
631
+ "eval_steps_per_second": 6.094,
632
+ "learning_rate": 1e-05,
633
+ "step": 96
634
+ },
635
+ {
636
+ "epoch": 49.0,
637
+ "eval_explained_variance": 0.12591353058815002,
638
+ "eval_loss": 0.6142339110374451,
639
+ "eval_mae": 0.3075259327888489,
640
+ "eval_r2": -11.087849617004395,
641
+ "eval_rmse": 0.3433670699596405,
642
+ "eval_runtime": 0.3232,
643
+ "eval_samples_per_second": 154.7,
644
+ "eval_steps_per_second": 6.188,
645
+ "learning_rate": 1e-05,
646
+ "step": 98
647
+ },
648
+ {
649
+ "epoch": 50.0,
650
+ "eval_explained_variance": 0.12409819662570953,
651
+ "eval_loss": 0.6125256419181824,
652
+ "eval_mae": 0.3070906400680542,
653
+ "eval_r2": -11.164841651916504,
654
+ "eval_rmse": 0.34268108010292053,
655
+ "eval_runtime": 0.323,
656
+ "eval_samples_per_second": 154.8,
657
+ "eval_steps_per_second": 6.192,
658
+ "learning_rate": 1e-05,
659
+ "step": 100
660
+ },
661
+ {
662
+ "epoch": 51.0,
663
+ "eval_explained_variance": 0.12737669050693512,
664
+ "eval_loss": 0.6131001114845276,
665
+ "eval_mae": 0.3071759045124054,
666
+ "eval_r2": -11.23709487915039,
667
+ "eval_rmse": 0.34303510189056396,
668
+ "eval_runtime": 0.3251,
669
+ "eval_samples_per_second": 153.791,
670
+ "eval_steps_per_second": 6.152,
671
+ "learning_rate": 1e-05,
672
+ "step": 102
673
+ },
674
+ {
675
+ "epoch": 52.0,
676
+ "eval_explained_variance": 0.12739494442939758,
677
+ "eval_loss": 0.6136941313743591,
678
+ "eval_mae": 0.30773404240608215,
679
+ "eval_r2": -11.390901565551758,
680
+ "eval_rmse": 0.34343937039375305,
681
+ "eval_runtime": 0.3154,
682
+ "eval_samples_per_second": 158.551,
683
+ "eval_steps_per_second": 6.342,
684
+ "learning_rate": 1e-05,
685
+ "step": 104
686
+ },
687
+ {
688
+ "epoch": 53.0,
689
+ "eval_explained_variance": 0.12241682410240173,
690
+ "eval_loss": 0.613895058631897,
691
+ "eval_mae": 0.3076512813568115,
692
+ "eval_r2": -11.501760482788086,
693
+ "eval_rmse": 0.3434452712535858,
694
+ "eval_runtime": 0.3001,
695
+ "eval_samples_per_second": 166.603,
696
+ "eval_steps_per_second": 6.664,
697
+ "learning_rate": 1e-05,
698
+ "step": 106
699
+ },
700
+ {
701
+ "epoch": 54.0,
702
+ "eval_explained_variance": 0.1222328469157219,
703
+ "eval_loss": 0.6156599521636963,
704
+ "eval_mae": 0.30890733003616333,
705
+ "eval_r2": -11.667372703552246,
706
+ "eval_rmse": 0.3445097804069519,
707
+ "eval_runtime": 0.3773,
708
+ "eval_samples_per_second": 132.51,
709
+ "eval_steps_per_second": 5.3,
710
+ "learning_rate": 1e-05,
711
+ "step": 108
712
+ },
713
+ {
714
+ "epoch": 55.0,
715
+ "eval_explained_variance": 0.12218669801950455,
716
+ "eval_loss": 0.6167553067207336,
717
+ "eval_mae": 0.30896657705307007,
718
+ "eval_r2": -11.646692276000977,
719
+ "eval_rmse": 0.34482434391975403,
720
+ "eval_runtime": 0.3779,
721
+ "eval_samples_per_second": 132.317,
722
+ "eval_steps_per_second": 5.293,
723
+ "learning_rate": 1e-05,
724
+ "step": 110
725
+ },
726
+ {
727
+ "epoch": 56.0,
728
+ "eval_explained_variance": 0.12501628696918488,
729
+ "eval_loss": 0.6139956116676331,
730
+ "eval_mae": 0.3077108561992645,
731
+ "eval_r2": -11.49679946899414,
732
+ "eval_rmse": 0.3434431850910187,
733
+ "eval_runtime": 0.2984,
734
+ "eval_samples_per_second": 167.575,
735
+ "eval_steps_per_second": 6.703,
736
+ "learning_rate": 1e-05,
737
+ "step": 112
738
+ },
739
+ {
740
+ "epoch": 57.0,
741
+ "eval_explained_variance": 0.12155170738697052,
742
+ "eval_loss": 0.6132706999778748,
743
+ "eval_mae": 0.3070979416370392,
744
+ "eval_r2": -11.500228881835938,
745
+ "eval_rmse": 0.342957466840744,
746
+ "eval_runtime": 0.3776,
747
+ "eval_samples_per_second": 132.398,
748
+ "eval_steps_per_second": 5.296,
749
+ "learning_rate": 1.0000000000000002e-06,
750
+ "step": 114
751
+ },
752
+ {
753
+ "epoch": 58.0,
754
+ "eval_explained_variance": 0.12097452580928802,
755
+ "eval_loss": 0.6130067706108093,
756
+ "eval_mae": 0.30698391795158386,
757
+ "eval_r2": -11.447521209716797,
758
+ "eval_rmse": 0.3428483307361603,
759
+ "eval_runtime": 0.3786,
760
+ "eval_samples_per_second": 132.082,
761
+ "eval_steps_per_second": 5.283,
762
+ "learning_rate": 1.0000000000000002e-06,
763
+ "step": 116
764
+ },
765
+ {
766
+ "epoch": 59.0,
767
+ "eval_explained_variance": 0.11784002184867859,
768
+ "eval_loss": 0.61500084400177,
769
+ "eval_mae": 0.30830222368240356,
770
+ "eval_r2": -11.556161880493164,
771
+ "eval_rmse": 0.34413495659828186,
772
+ "eval_runtime": 0.3056,
773
+ "eval_samples_per_second": 163.604,
774
+ "eval_steps_per_second": 6.544,
775
+ "learning_rate": 1.0000000000000002e-06,
776
+ "step": 118
777
+ },
778
+ {
779
+ "epoch": 60.0,
780
+ "eval_explained_variance": 0.12427856028079987,
781
+ "eval_loss": 0.6166698336601257,
782
+ "eval_mae": 0.30922549962997437,
783
+ "eval_r2": -11.467646598815918,
784
+ "eval_rmse": 0.34501928091049194,
785
+ "eval_runtime": 0.3778,
786
+ "eval_samples_per_second": 132.332,
787
+ "eval_steps_per_second": 5.293,
788
+ "learning_rate": 1.0000000000000002e-06,
789
+ "step": 120
790
+ },
791
+ {
792
+ "epoch": 60.0,
793
+ "learning_rate": 1.0000000000000002e-06,
794
+ "step": 120,
795
+ "total_flos": 4.4402778184752e+17,
796
+ "train_loss": 0.6329069137573242,
797
+ "train_runtime": 375.0945,
798
+ "train_samples_per_second": 19.995,
799
+ "train_steps_per_second": 0.8
800
+ }
801
+ ],
802
+ "logging_steps": 500,
803
+ "max_steps": 300,
804
+ "num_input_tokens_seen": 0,
805
+ "num_train_epochs": 150,
806
+ "save_steps": 500,
807
+ "stateful_callbacks": {
808
+ "EarlyStoppingCallback": {
809
+ "args": {
810
+ "early_stopping_patience": 10,
811
+ "early_stopping_threshold": 0.0
812
+ },
813
+ "attributes": {
814
+ "early_stopping_patience_counter": 0
815
+ }
816
+ },
817
+ "TrainerControl": {
818
+ "args": {
819
+ "should_epoch_stop": false,
820
+ "should_evaluate": false,
821
+ "should_log": false,
822
+ "should_save": true,
823
+ "should_training_stop": true
824
+ },
825
+ "attributes": {}
826
+ }
827
+ },
828
+ "total_flos": 4.4402778184752e+17,
829
+ "train_batch_size": 32,
830
+ "trial_name": null,
831
+ "trial_params": null
832
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a119b8776e0770eb2f992ef55dd161f65fc6173a483cb20c3f81351e0b57661c
3
+ size 5368
transforms.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "train_transforms": [
3
+ {
4
+ "operation": "PreProcess"
5
+ },
6
+ {
7
+ "operation": "Resize",
8
+ "probability": 1.0
9
+ },
10
+ {
11
+ "operation": "RandomHorizontalFlip",
12
+ "probability": 0.25
13
+ },
14
+ {
15
+ "operation": "RandomVerticalFlip",
16
+ "probability": 0.25
17
+ },
18
+ {
19
+ "operation": "ColorJiggle",
20
+ "probability": 0.25
21
+ },
22
+ {
23
+ "operation": "RandomPerspective",
24
+ "probability": 0.25
25
+ },
26
+ {
27
+ "operation": "Normalize",
28
+ "probability": 1.0
29
+ }
30
+ ],
31
+ "val_transforms": [
32
+ {
33
+ "operation": "PreProcess"
34
+ },
35
+ {
36
+ "operation": "Resize",
37
+ "probability": 1.0
38
+ },
39
+ {
40
+ "operation": "Normalize",
41
+ "probability": 1.0
42
+ }
43
+ ]
44
+ }