Augusto777
commited on
End of training
Browse files- README.md +157 -0
- all_results.json +12 -0
- config.json +77 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- runs/Dec11_18-55-56_DESKTOP-SKBE9FB/events.out.tfevents.1733964957.DESKTOP-SKBE9FB.18380.0 +3 -0
- runs/Dec11_18-55-56_DESKTOP-SKBE9FB/events.out.tfevents.1733972049.DESKTOP-SKBE9FB.18380.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +3630 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/beit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: BEiT-DMAE-13XDA-REVAL-80-32
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: validation
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8478260869565217
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# BEiT-DMAE-13XDA-REVAL-80-32
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.8105
|
36 |
+
- Accuracy: 0.8478
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 3.5e-05
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 64
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 80
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.5474 | 1.0 | 60 | 1.2945 | 0.4565 |
|
71 |
+
| 1.3959 | 1.99 | 120 | 1.2745 | 0.4565 |
|
72 |
+
| 1.0517 | 2.99 | 180 | 0.9632 | 0.6087 |
|
73 |
+
| 0.7273 | 4.0 | 241 | 0.7709 | 0.6957 |
|
74 |
+
| 0.5246 | 5.0 | 301 | 0.7217 | 0.7391 |
|
75 |
+
| 0.3645 | 5.99 | 361 | 0.7142 | 0.8043 |
|
76 |
+
| 0.2211 | 6.99 | 421 | 0.6436 | 0.8043 |
|
77 |
+
| 0.266 | 8.0 | 482 | 1.1316 | 0.6087 |
|
78 |
+
| 0.1235 | 9.0 | 542 | 0.9257 | 0.7826 |
|
79 |
+
| 0.1613 | 9.99 | 602 | 0.8527 | 0.7826 |
|
80 |
+
| 0.0946 | 10.99 | 662 | 0.8274 | 0.8043 |
|
81 |
+
| 0.1392 | 12.0 | 723 | 0.8312 | 0.7609 |
|
82 |
+
| 0.1028 | 13.0 | 783 | 1.1959 | 0.7609 |
|
83 |
+
| 0.1072 | 13.99 | 843 | 1.0017 | 0.7391 |
|
84 |
+
| 0.0888 | 14.99 | 903 | 0.9214 | 0.8043 |
|
85 |
+
| 0.0951 | 16.0 | 964 | 0.9156 | 0.7609 |
|
86 |
+
| 0.0714 | 17.0 | 1024 | 1.3116 | 0.6957 |
|
87 |
+
| 0.0804 | 17.99 | 1084 | 1.1107 | 0.7826 |
|
88 |
+
| 0.08 | 18.99 | 1144 | 0.8105 | 0.8478 |
|
89 |
+
| 0.1619 | 20.0 | 1205 | 0.7581 | 0.8261 |
|
90 |
+
| 0.084 | 21.0 | 1265 | 1.0210 | 0.8261 |
|
91 |
+
| 0.072 | 21.99 | 1325 | 1.3092 | 0.7609 |
|
92 |
+
| 0.0303 | 22.99 | 1385 | 1.3367 | 0.7826 |
|
93 |
+
| 0.0228 | 24.0 | 1446 | 1.0277 | 0.8261 |
|
94 |
+
| 0.0755 | 25.0 | 1506 | 0.9436 | 0.8261 |
|
95 |
+
| 0.0756 | 25.99 | 1566 | 1.1588 | 0.7609 |
|
96 |
+
| 0.0875 | 26.99 | 1626 | 1.3280 | 0.7174 |
|
97 |
+
| 0.0771 | 28.0 | 1687 | 1.8558 | 0.6739 |
|
98 |
+
| 0.0467 | 29.0 | 1747 | 1.6476 | 0.7391 |
|
99 |
+
| 0.0382 | 29.99 | 1807 | 0.9374 | 0.8478 |
|
100 |
+
| 0.0511 | 30.99 | 1867 | 1.0847 | 0.8043 |
|
101 |
+
| 0.0161 | 32.0 | 1928 | 1.2028 | 0.7826 |
|
102 |
+
| 0.0301 | 33.0 | 1988 | 1.2971 | 0.7391 |
|
103 |
+
| 0.0443 | 33.99 | 2048 | 1.3993 | 0.7174 |
|
104 |
+
| 0.0782 | 34.99 | 2108 | 1.3359 | 0.8043 |
|
105 |
+
| 0.0287 | 36.0 | 2169 | 1.3011 | 0.7826 |
|
106 |
+
| 0.0347 | 37.0 | 2229 | 1.2450 | 0.7826 |
|
107 |
+
| 0.0538 | 37.99 | 2289 | 1.8216 | 0.7609 |
|
108 |
+
| 0.027 | 38.99 | 2349 | 1.1701 | 0.8043 |
|
109 |
+
| 0.038 | 40.0 | 2410 | 1.1025 | 0.8043 |
|
110 |
+
| 0.0244 | 41.0 | 2470 | 1.2912 | 0.7609 |
|
111 |
+
| 0.0122 | 41.99 | 2530 | 1.5699 | 0.7609 |
|
112 |
+
| 0.023 | 42.99 | 2590 | 1.5114 | 0.7826 |
|
113 |
+
| 0.0297 | 44.0 | 2651 | 1.2189 | 0.8478 |
|
114 |
+
| 0.0284 | 45.0 | 2711 | 1.3997 | 0.7826 |
|
115 |
+
| 0.0203 | 45.99 | 2771 | 1.4792 | 0.8043 |
|
116 |
+
| 0.03 | 46.99 | 2831 | 1.7487 | 0.7174 |
|
117 |
+
| 0.025 | 48.0 | 2892 | 1.6605 | 0.7609 |
|
118 |
+
| 0.0134 | 49.0 | 2952 | 1.4106 | 0.7826 |
|
119 |
+
| 0.026 | 49.99 | 3012 | 1.2972 | 0.7609 |
|
120 |
+
| 0.0507 | 50.99 | 3072 | 1.3303 | 0.7826 |
|
121 |
+
| 0.0394 | 52.0 | 3133 | 1.1954 | 0.8478 |
|
122 |
+
| 0.0271 | 53.0 | 3193 | 1.3125 | 0.8261 |
|
123 |
+
| 0.0115 | 53.99 | 3253 | 1.3444 | 0.8478 |
|
124 |
+
| 0.0138 | 54.99 | 3313 | 1.4689 | 0.8261 |
|
125 |
+
| 0.0184 | 56.0 | 3374 | 1.4959 | 0.8261 |
|
126 |
+
| 0.0163 | 57.0 | 3434 | 1.3490 | 0.7826 |
|
127 |
+
| 0.0112 | 57.99 | 3494 | 1.4749 | 0.7826 |
|
128 |
+
| 0.0185 | 58.99 | 3554 | 1.5823 | 0.7826 |
|
129 |
+
| 0.031 | 60.0 | 3615 | 1.5190 | 0.7826 |
|
130 |
+
| 0.0161 | 61.0 | 3675 | 1.5476 | 0.8043 |
|
131 |
+
| 0.0146 | 61.99 | 3735 | 1.3930 | 0.7826 |
|
132 |
+
| 0.005 | 62.99 | 3795 | 1.5454 | 0.8043 |
|
133 |
+
| 0.0093 | 64.0 | 3856 | 1.5959 | 0.7826 |
|
134 |
+
| 0.0224 | 65.0 | 3916 | 1.4554 | 0.8043 |
|
135 |
+
| 0.0154 | 65.99 | 3976 | 1.5327 | 0.8261 |
|
136 |
+
| 0.0116 | 66.99 | 4036 | 1.6030 | 0.8043 |
|
137 |
+
| 0.0037 | 68.0 | 4097 | 1.5046 | 0.8261 |
|
138 |
+
| 0.0023 | 69.0 | 4157 | 1.5222 | 0.8261 |
|
139 |
+
| 0.0068 | 69.99 | 4217 | 1.4339 | 0.8261 |
|
140 |
+
| 0.0342 | 70.99 | 4277 | 1.6964 | 0.8043 |
|
141 |
+
| 0.0077 | 72.0 | 4338 | 1.6102 | 0.8043 |
|
142 |
+
| 0.0043 | 73.0 | 4398 | 1.6687 | 0.8043 |
|
143 |
+
| 0.0131 | 73.99 | 4458 | 1.6847 | 0.8043 |
|
144 |
+
| 0.0031 | 74.99 | 4518 | 1.7195 | 0.8043 |
|
145 |
+
| 0.0087 | 76.0 | 4579 | 1.7209 | 0.7826 |
|
146 |
+
| 0.0219 | 77.0 | 4639 | 1.6715 | 0.8043 |
|
147 |
+
| 0.0229 | 77.99 | 4699 | 1.6823 | 0.8043 |
|
148 |
+
| 0.008 | 78.99 | 4759 | 1.6751 | 0.8043 |
|
149 |
+
| 0.0051 | 79.67 | 4800 | 1.6758 | 0.8043 |
|
150 |
+
|
151 |
+
|
152 |
+
### Framework versions
|
153 |
+
|
154 |
+
- Transformers 4.36.2
|
155 |
+
- Pytorch 2.1.2+cu118
|
156 |
+
- Datasets 2.16.1
|
157 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.67,
|
3 |
+
"eval_accuracy": 0.8478260869565217,
|
4 |
+
"eval_loss": 0.8104602694511414,
|
5 |
+
"eval_runtime": 0.8232,
|
6 |
+
"eval_samples_per_second": 55.881,
|
7 |
+
"eval_steps_per_second": 3.644,
|
8 |
+
"train_loss": 0.12199072747869649,
|
9 |
+
"train_runtime": 7091.3369,
|
10 |
+
"train_samples_per_second": 43.467,
|
11 |
+
"train_steps_per_second": 0.677
|
12 |
+
}
|
config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224",
|
3 |
+
"add_fpn": false,
|
4 |
+
"architectures": [
|
5 |
+
"BeitForImageClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.0,
|
8 |
+
"auxiliary_channels": 256,
|
9 |
+
"auxiliary_concat_input": false,
|
10 |
+
"auxiliary_loss_weight": 0.4,
|
11 |
+
"auxiliary_num_convs": 1,
|
12 |
+
"drop_path_rate": 0.1,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "avanzada",
|
18 |
+
"1": "leve",
|
19 |
+
"2": "moderada",
|
20 |
+
"3": "no dmae"
|
21 |
+
},
|
22 |
+
"image_size": 224,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"avanzada": 0,
|
27 |
+
"leve": 1,
|
28 |
+
"moderada": 2,
|
29 |
+
"no dmae": 3
|
30 |
+
},
|
31 |
+
"layer_norm_eps": 1e-12,
|
32 |
+
"layer_scale_init_value": 0.1,
|
33 |
+
"model_type": "beit",
|
34 |
+
"num_attention_heads": 12,
|
35 |
+
"num_channels": 3,
|
36 |
+
"num_hidden_layers": 12,
|
37 |
+
"out_features": [
|
38 |
+
"stage12"
|
39 |
+
],
|
40 |
+
"out_indices": [
|
41 |
+
12
|
42 |
+
],
|
43 |
+
"patch_size": 16,
|
44 |
+
"pool_scales": [
|
45 |
+
1,
|
46 |
+
2,
|
47 |
+
3,
|
48 |
+
6
|
49 |
+
],
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"reshape_hidden_states": true,
|
52 |
+
"semantic_loss_ignore_index": 255,
|
53 |
+
"stage_names": [
|
54 |
+
"stem",
|
55 |
+
"stage1",
|
56 |
+
"stage2",
|
57 |
+
"stage3",
|
58 |
+
"stage4",
|
59 |
+
"stage5",
|
60 |
+
"stage6",
|
61 |
+
"stage7",
|
62 |
+
"stage8",
|
63 |
+
"stage9",
|
64 |
+
"stage10",
|
65 |
+
"stage11",
|
66 |
+
"stage12"
|
67 |
+
],
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.36.2",
|
70 |
+
"use_absolute_position_embeddings": false,
|
71 |
+
"use_auxiliary_head": true,
|
72 |
+
"use_mask_token": false,
|
73 |
+
"use_mean_pooling": true,
|
74 |
+
"use_relative_position_bias": true,
|
75 |
+
"use_shared_relative_position_bias": false,
|
76 |
+
"vocab_size": 8192
|
77 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.67,
|
3 |
+
"eval_accuracy": 0.8478260869565217,
|
4 |
+
"eval_loss": 0.8104602694511414,
|
5 |
+
"eval_runtime": 0.8232,
|
6 |
+
"eval_samples_per_second": 55.881,
|
7 |
+
"eval_steps_per_second": 3.644
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2023469c5a56435584bf0fc942ffda18b112172b479eabb680782c5c2625e019
|
3 |
+
size 343086480
|
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_normalize": true,
|
8 |
+
"do_reduce_labels": false,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"image_mean": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"image_processor_type": "BeitImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.5,
|
19 |
+
0.5,
|
20 |
+
0.5
|
21 |
+
],
|
22 |
+
"resample": 2,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"height": 224,
|
26 |
+
"width": 224
|
27 |
+
}
|
28 |
+
}
|
runs/Dec11_18-55-56_DESKTOP-SKBE9FB/events.out.tfevents.1733964957.DESKTOP-SKBE9FB.18380.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50cff70628a210535d507d3d96c0c8790c006f84559a44b0d69c0c9820a9a36f
|
3 |
+
size 106820
|
runs/Dec11_18-55-56_DESKTOP-SKBE9FB/events.out.tfevents.1733972049.DESKTOP-SKBE9FB.18380.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f258c795d204e2a90b011b4c22eb8f2dd803d83d11d1b7d7e9292930e95bdac6
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.67,
|
3 |
+
"train_loss": 0.12199072747869649,
|
4 |
+
"train_runtime": 7091.3369,
|
5 |
+
"train_samples_per_second": 43.467,
|
6 |
+
"train_steps_per_second": 0.677
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3630 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8478260869565217,
|
3 |
+
"best_model_checkpoint": "BEiT-DMAE-13XDA-REVAL-80-32\\checkpoint-1144",
|
4 |
+
"epoch": 79.66804979253112,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4800,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.17,
|
13 |
+
"learning_rate": 7.291666666666665e-07,
|
14 |
+
"loss": 1.6222,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.33,
|
19 |
+
"learning_rate": 1.458333333333333e-06,
|
20 |
+
"loss": 1.6488,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.5,
|
25 |
+
"learning_rate": 2.1875e-06,
|
26 |
+
"loss": 1.611,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.66,
|
31 |
+
"learning_rate": 2.916666666666666e-06,
|
32 |
+
"loss": 1.6356,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.83,
|
37 |
+
"learning_rate": 3.6458333333333333e-06,
|
38 |
+
"loss": 1.602,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.0,
|
43 |
+
"learning_rate": 4.375e-06,
|
44 |
+
"loss": 1.5474,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.0,
|
49 |
+
"eval_accuracy": 0.45652173913043476,
|
50 |
+
"eval_loss": 1.2944936752319336,
|
51 |
+
"eval_runtime": 0.6632,
|
52 |
+
"eval_samples_per_second": 69.361,
|
53 |
+
"eval_steps_per_second": 4.524,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.16,
|
58 |
+
"learning_rate": 5.104166666666667e-06,
|
59 |
+
"loss": 1.561,
|
60 |
+
"step": 70
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.33,
|
64 |
+
"learning_rate": 5.833333333333332e-06,
|
65 |
+
"loss": 1.4872,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 1.49,
|
70 |
+
"learning_rate": 6.5624999999999994e-06,
|
71 |
+
"loss": 1.458,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.66,
|
76 |
+
"learning_rate": 7.291666666666667e-06,
|
77 |
+
"loss": 1.4426,
|
78 |
+
"step": 100
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 1.83,
|
82 |
+
"learning_rate": 8.020833333333333e-06,
|
83 |
+
"loss": 1.4296,
|
84 |
+
"step": 110
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.99,
|
88 |
+
"learning_rate": 8.75e-06,
|
89 |
+
"loss": 1.3959,
|
90 |
+
"step": 120
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.99,
|
94 |
+
"eval_accuracy": 0.45652173913043476,
|
95 |
+
"eval_loss": 1.2745169401168823,
|
96 |
+
"eval_runtime": 0.6327,
|
97 |
+
"eval_samples_per_second": 72.708,
|
98 |
+
"eval_steps_per_second": 4.742,
|
99 |
+
"step": 120
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.16,
|
103 |
+
"learning_rate": 9.479166666666666e-06,
|
104 |
+
"loss": 1.3373,
|
105 |
+
"step": 130
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 2.32,
|
109 |
+
"learning_rate": 1.0208333333333334e-05,
|
110 |
+
"loss": 1.2946,
|
111 |
+
"step": 140
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 2.49,
|
115 |
+
"learning_rate": 1.0937499999999998e-05,
|
116 |
+
"loss": 1.236,
|
117 |
+
"step": 150
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 2.66,
|
121 |
+
"learning_rate": 1.1666666666666665e-05,
|
122 |
+
"loss": 1.1899,
|
123 |
+
"step": 160
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 2.82,
|
127 |
+
"learning_rate": 1.2395833333333333e-05,
|
128 |
+
"loss": 1.1186,
|
129 |
+
"step": 170
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 2.99,
|
133 |
+
"learning_rate": 1.3124999999999999e-05,
|
134 |
+
"loss": 1.0517,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.99,
|
139 |
+
"eval_accuracy": 0.6086956521739131,
|
140 |
+
"eval_loss": 0.9631962180137634,
|
141 |
+
"eval_runtime": 0.6872,
|
142 |
+
"eval_samples_per_second": 66.943,
|
143 |
+
"eval_steps_per_second": 4.366,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 3.15,
|
148 |
+
"learning_rate": 1.3854166666666665e-05,
|
149 |
+
"loss": 0.9828,
|
150 |
+
"step": 190
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 3.32,
|
154 |
+
"learning_rate": 1.4583333333333333e-05,
|
155 |
+
"loss": 0.9259,
|
156 |
+
"step": 200
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 3.49,
|
160 |
+
"learning_rate": 1.53125e-05,
|
161 |
+
"loss": 0.8746,
|
162 |
+
"step": 210
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 3.65,
|
166 |
+
"learning_rate": 1.6041666666666666e-05,
|
167 |
+
"loss": 0.8467,
|
168 |
+
"step": 220
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 3.82,
|
172 |
+
"learning_rate": 1.6770833333333332e-05,
|
173 |
+
"loss": 0.7669,
|
174 |
+
"step": 230
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 3.98,
|
178 |
+
"learning_rate": 1.75e-05,
|
179 |
+
"loss": 0.7273,
|
180 |
+
"step": 240
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 4.0,
|
184 |
+
"eval_accuracy": 0.6956521739130435,
|
185 |
+
"eval_loss": 0.7708569169044495,
|
186 |
+
"eval_runtime": 0.6952,
|
187 |
+
"eval_samples_per_second": 66.169,
|
188 |
+
"eval_steps_per_second": 4.315,
|
189 |
+
"step": 241
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 4.15,
|
193 |
+
"learning_rate": 1.8229166666666665e-05,
|
194 |
+
"loss": 0.6937,
|
195 |
+
"step": 250
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 4.32,
|
199 |
+
"learning_rate": 1.895833333333333e-05,
|
200 |
+
"loss": 0.6738,
|
201 |
+
"step": 260
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 4.48,
|
205 |
+
"learning_rate": 1.9687499999999997e-05,
|
206 |
+
"loss": 0.6577,
|
207 |
+
"step": 270
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 4.65,
|
211 |
+
"learning_rate": 2.0416666666666667e-05,
|
212 |
+
"loss": 0.6679,
|
213 |
+
"step": 280
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 4.81,
|
217 |
+
"learning_rate": 2.114583333333333e-05,
|
218 |
+
"loss": 0.5962,
|
219 |
+
"step": 290
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 4.98,
|
223 |
+
"learning_rate": 2.1874999999999996e-05,
|
224 |
+
"loss": 0.5246,
|
225 |
+
"step": 300
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 5.0,
|
229 |
+
"eval_accuracy": 0.7391304347826086,
|
230 |
+
"eval_loss": 0.7217094302177429,
|
231 |
+
"eval_runtime": 0.6875,
|
232 |
+
"eval_samples_per_second": 66.909,
|
233 |
+
"eval_steps_per_second": 4.364,
|
234 |
+
"step": 301
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 5.15,
|
238 |
+
"learning_rate": 2.2604166666666666e-05,
|
239 |
+
"loss": 0.4905,
|
240 |
+
"step": 310
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 5.31,
|
244 |
+
"learning_rate": 2.333333333333333e-05,
|
245 |
+
"loss": 0.4651,
|
246 |
+
"step": 320
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 5.48,
|
250 |
+
"learning_rate": 2.40625e-05,
|
251 |
+
"loss": 0.3947,
|
252 |
+
"step": 330
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 5.64,
|
256 |
+
"learning_rate": 2.4791666666666665e-05,
|
257 |
+
"loss": 0.3819,
|
258 |
+
"step": 340
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 5.81,
|
262 |
+
"learning_rate": 2.552083333333333e-05,
|
263 |
+
"loss": 0.3977,
|
264 |
+
"step": 350
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 5.98,
|
268 |
+
"learning_rate": 2.6249999999999998e-05,
|
269 |
+
"loss": 0.3645,
|
270 |
+
"step": 360
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 5.99,
|
274 |
+
"eval_accuracy": 0.8043478260869565,
|
275 |
+
"eval_loss": 0.7142456769943237,
|
276 |
+
"eval_runtime": 0.6651,
|
277 |
+
"eval_samples_per_second": 69.157,
|
278 |
+
"eval_steps_per_second": 4.51,
|
279 |
+
"step": 361
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 6.14,
|
283 |
+
"learning_rate": 2.6979166666666664e-05,
|
284 |
+
"loss": 0.3382,
|
285 |
+
"step": 370
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 6.31,
|
289 |
+
"learning_rate": 2.770833333333333e-05,
|
290 |
+
"loss": 0.2709,
|
291 |
+
"step": 380
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 6.47,
|
295 |
+
"learning_rate": 2.8437499999999997e-05,
|
296 |
+
"loss": 0.2641,
|
297 |
+
"step": 390
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 6.64,
|
301 |
+
"learning_rate": 2.9166666666666666e-05,
|
302 |
+
"loss": 0.2518,
|
303 |
+
"step": 400
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 6.8,
|
307 |
+
"learning_rate": 2.989583333333333e-05,
|
308 |
+
"loss": 0.2631,
|
309 |
+
"step": 410
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 6.97,
|
313 |
+
"learning_rate": 3.0625e-05,
|
314 |
+
"loss": 0.2211,
|
315 |
+
"step": 420
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 6.99,
|
319 |
+
"eval_accuracy": 0.8043478260869565,
|
320 |
+
"eval_loss": 0.6436068415641785,
|
321 |
+
"eval_runtime": 0.6647,
|
322 |
+
"eval_samples_per_second": 69.209,
|
323 |
+
"eval_steps_per_second": 4.514,
|
324 |
+
"step": 421
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 7.14,
|
328 |
+
"learning_rate": 3.1354166666666665e-05,
|
329 |
+
"loss": 0.225,
|
330 |
+
"step": 430
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 7.3,
|
334 |
+
"learning_rate": 3.208333333333333e-05,
|
335 |
+
"loss": 0.2625,
|
336 |
+
"step": 440
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 7.47,
|
340 |
+
"learning_rate": 3.28125e-05,
|
341 |
+
"loss": 0.183,
|
342 |
+
"step": 450
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 7.63,
|
346 |
+
"learning_rate": 3.3541666666666664e-05,
|
347 |
+
"loss": 0.1866,
|
348 |
+
"step": 460
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 7.8,
|
352 |
+
"learning_rate": 3.427083333333333e-05,
|
353 |
+
"loss": 0.2547,
|
354 |
+
"step": 470
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 7.97,
|
358 |
+
"learning_rate": 3.5e-05,
|
359 |
+
"loss": 0.266,
|
360 |
+
"step": 480
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 8.0,
|
364 |
+
"eval_accuracy": 0.6086956521739131,
|
365 |
+
"eval_loss": 1.1315726041793823,
|
366 |
+
"eval_runtime": 0.6621,
|
367 |
+
"eval_samples_per_second": 69.472,
|
368 |
+
"eval_steps_per_second": 4.531,
|
369 |
+
"step": 482
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 8.13,
|
373 |
+
"learning_rate": 3.491898148148148e-05,
|
374 |
+
"loss": 0.2918,
|
375 |
+
"step": 490
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 8.3,
|
379 |
+
"learning_rate": 3.483796296296296e-05,
|
380 |
+
"loss": 0.209,
|
381 |
+
"step": 500
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 8.46,
|
385 |
+
"learning_rate": 3.475694444444444e-05,
|
386 |
+
"loss": 0.1858,
|
387 |
+
"step": 510
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 8.63,
|
391 |
+
"learning_rate": 3.467592592592592e-05,
|
392 |
+
"loss": 0.1967,
|
393 |
+
"step": 520
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 8.8,
|
397 |
+
"learning_rate": 3.459490740740741e-05,
|
398 |
+
"loss": 0.1914,
|
399 |
+
"step": 530
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 8.96,
|
403 |
+
"learning_rate": 3.4513888888888886e-05,
|
404 |
+
"loss": 0.1235,
|
405 |
+
"step": 540
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 9.0,
|
409 |
+
"eval_accuracy": 0.782608695652174,
|
410 |
+
"eval_loss": 0.9256875514984131,
|
411 |
+
"eval_runtime": 0.6634,
|
412 |
+
"eval_samples_per_second": 69.344,
|
413 |
+
"eval_steps_per_second": 4.522,
|
414 |
+
"step": 542
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 9.13,
|
418 |
+
"learning_rate": 3.4432870370370365e-05,
|
419 |
+
"loss": 0.2088,
|
420 |
+
"step": 550
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 9.29,
|
424 |
+
"learning_rate": 3.435185185185185e-05,
|
425 |
+
"loss": 0.2034,
|
426 |
+
"step": 560
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 9.46,
|
430 |
+
"learning_rate": 3.427083333333333e-05,
|
431 |
+
"loss": 0.1289,
|
432 |
+
"step": 570
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 9.63,
|
436 |
+
"learning_rate": 3.418981481481481e-05,
|
437 |
+
"loss": 0.162,
|
438 |
+
"step": 580
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 9.79,
|
442 |
+
"learning_rate": 3.4108796296296296e-05,
|
443 |
+
"loss": 0.1831,
|
444 |
+
"step": 590
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 9.96,
|
448 |
+
"learning_rate": 3.4027777777777775e-05,
|
449 |
+
"loss": 0.1613,
|
450 |
+
"step": 600
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 9.99,
|
454 |
+
"eval_accuracy": 0.782608695652174,
|
455 |
+
"eval_loss": 0.8526802062988281,
|
456 |
+
"eval_runtime": 0.6424,
|
457 |
+
"eval_samples_per_second": 71.601,
|
458 |
+
"eval_steps_per_second": 4.67,
|
459 |
+
"step": 602
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 10.12,
|
463 |
+
"learning_rate": 3.3946759259259254e-05,
|
464 |
+
"loss": 0.0869,
|
465 |
+
"step": 610
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 10.29,
|
469 |
+
"learning_rate": 3.3865740740740734e-05,
|
470 |
+
"loss": 0.1814,
|
471 |
+
"step": 620
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 10.46,
|
475 |
+
"learning_rate": 3.378472222222222e-05,
|
476 |
+
"loss": 0.1488,
|
477 |
+
"step": 630
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 10.62,
|
481 |
+
"learning_rate": 3.37037037037037e-05,
|
482 |
+
"loss": 0.1249,
|
483 |
+
"step": 640
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 10.79,
|
487 |
+
"learning_rate": 3.3622685185185185e-05,
|
488 |
+
"loss": 0.1397,
|
489 |
+
"step": 650
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 10.95,
|
493 |
+
"learning_rate": 3.3541666666666664e-05,
|
494 |
+
"loss": 0.0946,
|
495 |
+
"step": 660
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 10.99,
|
499 |
+
"eval_accuracy": 0.8043478260869565,
|
500 |
+
"eval_loss": 0.8274199366569519,
|
501 |
+
"eval_runtime": 0.8621,
|
502 |
+
"eval_samples_per_second": 53.358,
|
503 |
+
"eval_steps_per_second": 3.48,
|
504 |
+
"step": 662
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 11.12,
|
508 |
+
"learning_rate": 3.3460648148148144e-05,
|
509 |
+
"loss": 0.1215,
|
510 |
+
"step": 670
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 11.29,
|
514 |
+
"learning_rate": 3.337962962962963e-05,
|
515 |
+
"loss": 0.1146,
|
516 |
+
"step": 680
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 11.45,
|
520 |
+
"learning_rate": 3.329861111111111e-05,
|
521 |
+
"loss": 0.0991,
|
522 |
+
"step": 690
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 11.62,
|
526 |
+
"learning_rate": 3.321759259259259e-05,
|
527 |
+
"loss": 0.1463,
|
528 |
+
"step": 700
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 11.78,
|
532 |
+
"learning_rate": 3.3136574074074074e-05,
|
533 |
+
"loss": 0.1049,
|
534 |
+
"step": 710
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 11.95,
|
538 |
+
"learning_rate": 3.3055555555555553e-05,
|
539 |
+
"loss": 0.1392,
|
540 |
+
"step": 720
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 12.0,
|
544 |
+
"eval_accuracy": 0.7608695652173914,
|
545 |
+
"eval_loss": 0.8311833739280701,
|
546 |
+
"eval_runtime": 0.6987,
|
547 |
+
"eval_samples_per_second": 65.839,
|
548 |
+
"eval_steps_per_second": 4.294,
|
549 |
+
"step": 723
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 12.12,
|
553 |
+
"learning_rate": 3.297453703703703e-05,
|
554 |
+
"loss": 0.1116,
|
555 |
+
"step": 730
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 12.28,
|
559 |
+
"learning_rate": 3.289351851851851e-05,
|
560 |
+
"loss": 0.1217,
|
561 |
+
"step": 740
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 12.45,
|
565 |
+
"learning_rate": 3.28125e-05,
|
566 |
+
"loss": 0.0952,
|
567 |
+
"step": 750
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 12.61,
|
571 |
+
"learning_rate": 3.273148148148148e-05,
|
572 |
+
"loss": 0.0972,
|
573 |
+
"step": 760
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 12.78,
|
577 |
+
"learning_rate": 3.2650462962962956e-05,
|
578 |
+
"loss": 0.1193,
|
579 |
+
"step": 770
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 12.95,
|
583 |
+
"learning_rate": 3.256944444444444e-05,
|
584 |
+
"loss": 0.1028,
|
585 |
+
"step": 780
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 13.0,
|
589 |
+
"eval_accuracy": 0.7608695652173914,
|
590 |
+
"eval_loss": 1.1959415674209595,
|
591 |
+
"eval_runtime": 0.6697,
|
592 |
+
"eval_samples_per_second": 68.691,
|
593 |
+
"eval_steps_per_second": 4.48,
|
594 |
+
"step": 783
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 13.11,
|
598 |
+
"learning_rate": 3.248842592592592e-05,
|
599 |
+
"loss": 0.1014,
|
600 |
+
"step": 790
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 13.28,
|
604 |
+
"learning_rate": 3.240740740740741e-05,
|
605 |
+
"loss": 0.1055,
|
606 |
+
"step": 800
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 13.44,
|
610 |
+
"learning_rate": 3.232638888888889e-05,
|
611 |
+
"loss": 0.1317,
|
612 |
+
"step": 810
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 13.61,
|
616 |
+
"learning_rate": 3.2245370370370366e-05,
|
617 |
+
"loss": 0.0899,
|
618 |
+
"step": 820
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 13.78,
|
622 |
+
"learning_rate": 3.216435185185185e-05,
|
623 |
+
"loss": 0.1158,
|
624 |
+
"step": 830
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 13.94,
|
628 |
+
"learning_rate": 3.208333333333333e-05,
|
629 |
+
"loss": 0.1072,
|
630 |
+
"step": 840
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 13.99,
|
634 |
+
"eval_accuracy": 0.7391304347826086,
|
635 |
+
"eval_loss": 1.0017004013061523,
|
636 |
+
"eval_runtime": 0.6881,
|
637 |
+
"eval_samples_per_second": 66.851,
|
638 |
+
"eval_steps_per_second": 4.36,
|
639 |
+
"step": 843
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 14.11,
|
643 |
+
"learning_rate": 3.200231481481481e-05,
|
644 |
+
"loss": 0.0812,
|
645 |
+
"step": 850
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 14.27,
|
649 |
+
"learning_rate": 3.19212962962963e-05,
|
650 |
+
"loss": 0.1025,
|
651 |
+
"step": 860
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 14.44,
|
655 |
+
"learning_rate": 3.1840277777777776e-05,
|
656 |
+
"loss": 0.1296,
|
657 |
+
"step": 870
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 14.61,
|
661 |
+
"learning_rate": 3.1759259259259255e-05,
|
662 |
+
"loss": 0.146,
|
663 |
+
"step": 880
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 14.77,
|
667 |
+
"learning_rate": 3.1678240740740735e-05,
|
668 |
+
"loss": 0.0782,
|
669 |
+
"step": 890
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 14.94,
|
673 |
+
"learning_rate": 3.159722222222222e-05,
|
674 |
+
"loss": 0.0888,
|
675 |
+
"step": 900
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 14.99,
|
679 |
+
"eval_accuracy": 0.8043478260869565,
|
680 |
+
"eval_loss": 0.921440064907074,
|
681 |
+
"eval_runtime": 0.714,
|
682 |
+
"eval_samples_per_second": 64.425,
|
683 |
+
"eval_steps_per_second": 4.202,
|
684 |
+
"step": 903
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 15.1,
|
688 |
+
"learning_rate": 3.15162037037037e-05,
|
689 |
+
"loss": 0.077,
|
690 |
+
"step": 910
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 15.27,
|
694 |
+
"learning_rate": 3.143518518518518e-05,
|
695 |
+
"loss": 0.0821,
|
696 |
+
"step": 920
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 15.44,
|
700 |
+
"learning_rate": 3.1354166666666665e-05,
|
701 |
+
"loss": 0.0692,
|
702 |
+
"step": 930
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 15.6,
|
706 |
+
"learning_rate": 3.1273148148148145e-05,
|
707 |
+
"loss": 0.0801,
|
708 |
+
"step": 940
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 15.77,
|
712 |
+
"learning_rate": 3.119212962962963e-05,
|
713 |
+
"loss": 0.1015,
|
714 |
+
"step": 950
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 15.93,
|
718 |
+
"learning_rate": 3.111111111111111e-05,
|
719 |
+
"loss": 0.0951,
|
720 |
+
"step": 960
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 16.0,
|
724 |
+
"eval_accuracy": 0.7608695652173914,
|
725 |
+
"eval_loss": 0.9156137704849243,
|
726 |
+
"eval_runtime": 0.6762,
|
727 |
+
"eval_samples_per_second": 68.028,
|
728 |
+
"eval_steps_per_second": 4.437,
|
729 |
+
"step": 964
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 16.1,
|
733 |
+
"learning_rate": 3.103009259259259e-05,
|
734 |
+
"loss": 0.0768,
|
735 |
+
"step": 970
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 16.27,
|
739 |
+
"learning_rate": 3.0949074074074075e-05,
|
740 |
+
"loss": 0.0494,
|
741 |
+
"step": 980
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 16.43,
|
745 |
+
"learning_rate": 3.0868055555555554e-05,
|
746 |
+
"loss": 0.1444,
|
747 |
+
"step": 990
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 16.6,
|
751 |
+
"learning_rate": 3.0787037037037034e-05,
|
752 |
+
"loss": 0.086,
|
753 |
+
"step": 1000
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 16.76,
|
757 |
+
"learning_rate": 3.070601851851851e-05,
|
758 |
+
"loss": 0.0883,
|
759 |
+
"step": 1010
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 16.93,
|
763 |
+
"learning_rate": 3.0625e-05,
|
764 |
+
"loss": 0.0714,
|
765 |
+
"step": 1020
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 17.0,
|
769 |
+
"eval_accuracy": 0.6956521739130435,
|
770 |
+
"eval_loss": 1.3116263151168823,
|
771 |
+
"eval_runtime": 0.6431,
|
772 |
+
"eval_samples_per_second": 71.525,
|
773 |
+
"eval_steps_per_second": 4.665,
|
774 |
+
"step": 1024
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 17.1,
|
778 |
+
"learning_rate": 3.054398148148148e-05,
|
779 |
+
"loss": 0.0637,
|
780 |
+
"step": 1030
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 17.26,
|
784 |
+
"learning_rate": 3.046296296296296e-05,
|
785 |
+
"loss": 0.0581,
|
786 |
+
"step": 1040
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 17.43,
|
790 |
+
"learning_rate": 3.0381944444444444e-05,
|
791 |
+
"loss": 0.1138,
|
792 |
+
"step": 1050
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 17.59,
|
796 |
+
"learning_rate": 3.0300925925925923e-05,
|
797 |
+
"loss": 0.0894,
|
798 |
+
"step": 1060
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"epoch": 17.76,
|
802 |
+
"learning_rate": 3.0219907407407405e-05,
|
803 |
+
"loss": 0.065,
|
804 |
+
"step": 1070
|
805 |
+
},
|
806 |
+
{
|
807 |
+
"epoch": 17.93,
|
808 |
+
"learning_rate": 3.0138888888888888e-05,
|
809 |
+
"loss": 0.0804,
|
810 |
+
"step": 1080
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 17.99,
|
814 |
+
"eval_accuracy": 0.782608695652174,
|
815 |
+
"eval_loss": 1.1107388734817505,
|
816 |
+
"eval_runtime": 0.7361,
|
817 |
+
"eval_samples_per_second": 62.487,
|
818 |
+
"eval_steps_per_second": 4.075,
|
819 |
+
"step": 1084
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 18.09,
|
823 |
+
"learning_rate": 3.0057870370370367e-05,
|
824 |
+
"loss": 0.1195,
|
825 |
+
"step": 1090
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 18.26,
|
829 |
+
"learning_rate": 2.997685185185185e-05,
|
830 |
+
"loss": 0.117,
|
831 |
+
"step": 1100
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 18.42,
|
835 |
+
"learning_rate": 2.989583333333333e-05,
|
836 |
+
"loss": 0.0535,
|
837 |
+
"step": 1110
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 18.59,
|
841 |
+
"learning_rate": 2.9814814814814812e-05,
|
842 |
+
"loss": 0.0778,
|
843 |
+
"step": 1120
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 18.76,
|
847 |
+
"learning_rate": 2.9733796296296295e-05,
|
848 |
+
"loss": 0.1094,
|
849 |
+
"step": 1130
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 18.92,
|
853 |
+
"learning_rate": 2.9652777777777774e-05,
|
854 |
+
"loss": 0.08,
|
855 |
+
"step": 1140
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 18.99,
|
859 |
+
"eval_accuracy": 0.8478260869565217,
|
860 |
+
"eval_loss": 0.8104602694511414,
|
861 |
+
"eval_runtime": 0.9009,
|
862 |
+
"eval_samples_per_second": 51.063,
|
863 |
+
"eval_steps_per_second": 3.33,
|
864 |
+
"step": 1144
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 19.09,
|
868 |
+
"learning_rate": 2.9571759259259257e-05,
|
869 |
+
"loss": 0.058,
|
870 |
+
"step": 1150
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 19.25,
|
874 |
+
"learning_rate": 2.9490740740740736e-05,
|
875 |
+
"loss": 0.0811,
|
876 |
+
"step": 1160
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 19.42,
|
880 |
+
"learning_rate": 2.940972222222222e-05,
|
881 |
+
"loss": 0.0626,
|
882 |
+
"step": 1170
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 19.59,
|
886 |
+
"learning_rate": 2.9328703703703698e-05,
|
887 |
+
"loss": 0.0502,
|
888 |
+
"step": 1180
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 19.75,
|
892 |
+
"learning_rate": 2.9247685185185184e-05,
|
893 |
+
"loss": 0.0799,
|
894 |
+
"step": 1190
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 19.92,
|
898 |
+
"learning_rate": 2.9166666666666666e-05,
|
899 |
+
"loss": 0.1619,
|
900 |
+
"step": 1200
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 20.0,
|
904 |
+
"eval_accuracy": 0.8260869565217391,
|
905 |
+
"eval_loss": 0.7581048011779785,
|
906 |
+
"eval_runtime": 0.6451,
|
907 |
+
"eval_samples_per_second": 71.304,
|
908 |
+
"eval_steps_per_second": 4.65,
|
909 |
+
"step": 1205
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 20.08,
|
913 |
+
"learning_rate": 2.9085648148148146e-05,
|
914 |
+
"loss": 0.0787,
|
915 |
+
"step": 1210
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 20.25,
|
919 |
+
"learning_rate": 2.9004629629629628e-05,
|
920 |
+
"loss": 0.0764,
|
921 |
+
"step": 1220
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 20.41,
|
925 |
+
"learning_rate": 2.8923611111111108e-05,
|
926 |
+
"loss": 0.0618,
|
927 |
+
"step": 1230
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 20.58,
|
931 |
+
"learning_rate": 2.884259259259259e-05,
|
932 |
+
"loss": 0.0612,
|
933 |
+
"step": 1240
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 20.75,
|
937 |
+
"learning_rate": 2.8761574074074073e-05,
|
938 |
+
"loss": 0.0666,
|
939 |
+
"step": 1250
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 20.91,
|
943 |
+
"learning_rate": 2.8680555555555552e-05,
|
944 |
+
"loss": 0.084,
|
945 |
+
"step": 1260
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 21.0,
|
949 |
+
"eval_accuracy": 0.8260869565217391,
|
950 |
+
"eval_loss": 1.0210282802581787,
|
951 |
+
"eval_runtime": 0.6611,
|
952 |
+
"eval_samples_per_second": 69.584,
|
953 |
+
"eval_steps_per_second": 4.538,
|
954 |
+
"step": 1265
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 21.08,
|
958 |
+
"learning_rate": 2.8599537037037035e-05,
|
959 |
+
"loss": 0.068,
|
960 |
+
"step": 1270
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 21.24,
|
964 |
+
"learning_rate": 2.8518518518518514e-05,
|
965 |
+
"loss": 0.0447,
|
966 |
+
"step": 1280
|
967 |
+
},
|
968 |
+
{
|
969 |
+
"epoch": 21.41,
|
970 |
+
"learning_rate": 2.8437499999999997e-05,
|
971 |
+
"loss": 0.0568,
|
972 |
+
"step": 1290
|
973 |
+
},
|
974 |
+
{
|
975 |
+
"epoch": 21.58,
|
976 |
+
"learning_rate": 2.835648148148148e-05,
|
977 |
+
"loss": 0.0823,
|
978 |
+
"step": 1300
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 21.74,
|
982 |
+
"learning_rate": 2.827546296296296e-05,
|
983 |
+
"loss": 0.0473,
|
984 |
+
"step": 1310
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 21.91,
|
988 |
+
"learning_rate": 2.819444444444444e-05,
|
989 |
+
"loss": 0.072,
|
990 |
+
"step": 1320
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 21.99,
|
994 |
+
"eval_accuracy": 0.7608695652173914,
|
995 |
+
"eval_loss": 1.3092247247695923,
|
996 |
+
"eval_runtime": 0.6707,
|
997 |
+
"eval_samples_per_second": 68.585,
|
998 |
+
"eval_steps_per_second": 4.473,
|
999 |
+
"step": 1325
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 22.07,
|
1003 |
+
"learning_rate": 2.811342592592592e-05,
|
1004 |
+
"loss": 0.0629,
|
1005 |
+
"step": 1330
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 22.24,
|
1009 |
+
"learning_rate": 2.8032407407407407e-05,
|
1010 |
+
"loss": 0.0908,
|
1011 |
+
"step": 1340
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 22.41,
|
1015 |
+
"learning_rate": 2.795138888888889e-05,
|
1016 |
+
"loss": 0.0744,
|
1017 |
+
"step": 1350
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 22.57,
|
1021 |
+
"learning_rate": 2.787037037037037e-05,
|
1022 |
+
"loss": 0.055,
|
1023 |
+
"step": 1360
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 22.74,
|
1027 |
+
"learning_rate": 2.778935185185185e-05,
|
1028 |
+
"loss": 0.0572,
|
1029 |
+
"step": 1370
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 22.9,
|
1033 |
+
"learning_rate": 2.770833333333333e-05,
|
1034 |
+
"loss": 0.0303,
|
1035 |
+
"step": 1380
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 22.99,
|
1039 |
+
"eval_accuracy": 0.782608695652174,
|
1040 |
+
"eval_loss": 1.3367185592651367,
|
1041 |
+
"eval_runtime": 0.665,
|
1042 |
+
"eval_samples_per_second": 69.17,
|
1043 |
+
"eval_steps_per_second": 4.511,
|
1044 |
+
"step": 1385
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 23.07,
|
1048 |
+
"learning_rate": 2.7627314814814813e-05,
|
1049 |
+
"loss": 0.0785,
|
1050 |
+
"step": 1390
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 23.24,
|
1054 |
+
"learning_rate": 2.7546296296296296e-05,
|
1055 |
+
"loss": 0.0877,
|
1056 |
+
"step": 1400
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 23.4,
|
1060 |
+
"learning_rate": 2.7465277777777775e-05,
|
1061 |
+
"loss": 0.0482,
|
1062 |
+
"step": 1410
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 23.57,
|
1066 |
+
"learning_rate": 2.7384259259259258e-05,
|
1067 |
+
"loss": 0.0712,
|
1068 |
+
"step": 1420
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 23.73,
|
1072 |
+
"learning_rate": 2.7303240740740737e-05,
|
1073 |
+
"loss": 0.0381,
|
1074 |
+
"step": 1430
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 23.9,
|
1078 |
+
"learning_rate": 2.722222222222222e-05,
|
1079 |
+
"loss": 0.0228,
|
1080 |
+
"step": 1440
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 24.0,
|
1084 |
+
"eval_accuracy": 0.8260869565217391,
|
1085 |
+
"eval_loss": 1.0276718139648438,
|
1086 |
+
"eval_runtime": 0.7532,
|
1087 |
+
"eval_samples_per_second": 61.074,
|
1088 |
+
"eval_steps_per_second": 3.983,
|
1089 |
+
"step": 1446
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 24.07,
|
1093 |
+
"learning_rate": 2.71412037037037e-05,
|
1094 |
+
"loss": 0.0696,
|
1095 |
+
"step": 1450
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 24.23,
|
1099 |
+
"learning_rate": 2.706018518518518e-05,
|
1100 |
+
"loss": 0.0612,
|
1101 |
+
"step": 1460
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 24.4,
|
1105 |
+
"learning_rate": 2.6979166666666664e-05,
|
1106 |
+
"loss": 0.0549,
|
1107 |
+
"step": 1470
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 24.56,
|
1111 |
+
"learning_rate": 2.6898148148148143e-05,
|
1112 |
+
"loss": 0.0253,
|
1113 |
+
"step": 1480
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 24.73,
|
1117 |
+
"learning_rate": 2.681712962962963e-05,
|
1118 |
+
"loss": 0.0472,
|
1119 |
+
"step": 1490
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 24.9,
|
1123 |
+
"learning_rate": 2.673611111111111e-05,
|
1124 |
+
"loss": 0.0755,
|
1125 |
+
"step": 1500
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 25.0,
|
1129 |
+
"eval_accuracy": 0.8260869565217391,
|
1130 |
+
"eval_loss": 0.9436376094818115,
|
1131 |
+
"eval_runtime": 0.6656,
|
1132 |
+
"eval_samples_per_second": 69.111,
|
1133 |
+
"eval_steps_per_second": 4.507,
|
1134 |
+
"step": 1506
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 25.06,
|
1138 |
+
"learning_rate": 2.665509259259259e-05,
|
1139 |
+
"loss": 0.0743,
|
1140 |
+
"step": 1510
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 25.23,
|
1144 |
+
"learning_rate": 2.6574074074074074e-05,
|
1145 |
+
"loss": 0.045,
|
1146 |
+
"step": 1520
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 25.39,
|
1150 |
+
"learning_rate": 2.6493055555555553e-05,
|
1151 |
+
"loss": 0.0669,
|
1152 |
+
"step": 1530
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 25.56,
|
1156 |
+
"learning_rate": 2.6412037037037036e-05,
|
1157 |
+
"loss": 0.0551,
|
1158 |
+
"step": 1540
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 25.73,
|
1162 |
+
"learning_rate": 2.6331018518518515e-05,
|
1163 |
+
"loss": 0.0256,
|
1164 |
+
"step": 1550
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 25.89,
|
1168 |
+
"learning_rate": 2.6249999999999998e-05,
|
1169 |
+
"loss": 0.0756,
|
1170 |
+
"step": 1560
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 25.99,
|
1174 |
+
"eval_accuracy": 0.7608695652173914,
|
1175 |
+
"eval_loss": 1.1588078737258911,
|
1176 |
+
"eval_runtime": 0.6572,
|
1177 |
+
"eval_samples_per_second": 69.997,
|
1178 |
+
"eval_steps_per_second": 4.565,
|
1179 |
+
"step": 1566
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 26.06,
|
1183 |
+
"learning_rate": 2.616898148148148e-05,
|
1184 |
+
"loss": 0.0403,
|
1185 |
+
"step": 1570
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 26.22,
|
1189 |
+
"learning_rate": 2.608796296296296e-05,
|
1190 |
+
"loss": 0.0486,
|
1191 |
+
"step": 1580
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 26.39,
|
1195 |
+
"learning_rate": 2.6006944444444442e-05,
|
1196 |
+
"loss": 0.0489,
|
1197 |
+
"step": 1590
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 26.56,
|
1201 |
+
"learning_rate": 2.592592592592592e-05,
|
1202 |
+
"loss": 0.0646,
|
1203 |
+
"step": 1600
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 26.72,
|
1207 |
+
"learning_rate": 2.5844907407407404e-05,
|
1208 |
+
"loss": 0.0713,
|
1209 |
+
"step": 1610
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 26.89,
|
1213 |
+
"learning_rate": 2.5763888888888887e-05,
|
1214 |
+
"loss": 0.0875,
|
1215 |
+
"step": 1620
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 26.99,
|
1219 |
+
"eval_accuracy": 0.717391304347826,
|
1220 |
+
"eval_loss": 1.3280256986618042,
|
1221 |
+
"eval_runtime": 0.7112,
|
1222 |
+
"eval_samples_per_second": 64.681,
|
1223 |
+
"eval_steps_per_second": 4.218,
|
1224 |
+
"step": 1626
|
1225 |
+
},
|
1226 |
+
{
|
1227 |
+
"epoch": 27.05,
|
1228 |
+
"learning_rate": 2.5682870370370366e-05,
|
1229 |
+
"loss": 0.0704,
|
1230 |
+
"step": 1630
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 27.22,
|
1234 |
+
"learning_rate": 2.5601851851851852e-05,
|
1235 |
+
"loss": 0.0606,
|
1236 |
+
"step": 1640
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 27.39,
|
1240 |
+
"learning_rate": 2.552083333333333e-05,
|
1241 |
+
"loss": 0.0385,
|
1242 |
+
"step": 1650
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 27.55,
|
1246 |
+
"learning_rate": 2.5439814814814814e-05,
|
1247 |
+
"loss": 0.0494,
|
1248 |
+
"step": 1660
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 27.72,
|
1252 |
+
"learning_rate": 2.5358796296296297e-05,
|
1253 |
+
"loss": 0.0171,
|
1254 |
+
"step": 1670
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"epoch": 27.88,
|
1258 |
+
"learning_rate": 2.5277777777777776e-05,
|
1259 |
+
"loss": 0.0771,
|
1260 |
+
"step": 1680
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"epoch": 28.0,
|
1264 |
+
"eval_accuracy": 0.6739130434782609,
|
1265 |
+
"eval_loss": 1.8558253049850464,
|
1266 |
+
"eval_runtime": 0.6528,
|
1267 |
+
"eval_samples_per_second": 70.468,
|
1268 |
+
"eval_steps_per_second": 4.596,
|
1269 |
+
"step": 1687
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 28.05,
|
1273 |
+
"learning_rate": 2.519675925925926e-05,
|
1274 |
+
"loss": 0.0447,
|
1275 |
+
"step": 1690
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 28.22,
|
1279 |
+
"learning_rate": 2.5115740740740738e-05,
|
1280 |
+
"loss": 0.0365,
|
1281 |
+
"step": 1700
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 28.38,
|
1285 |
+
"learning_rate": 2.503472222222222e-05,
|
1286 |
+
"loss": 0.0557,
|
1287 |
+
"step": 1710
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 28.55,
|
1291 |
+
"learning_rate": 2.49537037037037e-05,
|
1292 |
+
"loss": 0.0447,
|
1293 |
+
"step": 1720
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 28.71,
|
1297 |
+
"learning_rate": 2.4872685185185182e-05,
|
1298 |
+
"loss": 0.0412,
|
1299 |
+
"step": 1730
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 28.88,
|
1303 |
+
"learning_rate": 2.4791666666666665e-05,
|
1304 |
+
"loss": 0.0467,
|
1305 |
+
"step": 1740
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 29.0,
|
1309 |
+
"eval_accuracy": 0.7391304347826086,
|
1310 |
+
"eval_loss": 1.6476134061813354,
|
1311 |
+
"eval_runtime": 0.6892,
|
1312 |
+
"eval_samples_per_second": 66.748,
|
1313 |
+
"eval_steps_per_second": 4.353,
|
1314 |
+
"step": 1747
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 29.05,
|
1318 |
+
"learning_rate": 2.4710648148148144e-05,
|
1319 |
+
"loss": 0.0483,
|
1320 |
+
"step": 1750
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 29.21,
|
1324 |
+
"learning_rate": 2.4629629629629627e-05,
|
1325 |
+
"loss": 0.1003,
|
1326 |
+
"step": 1760
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 29.38,
|
1330 |
+
"learning_rate": 2.4548611111111106e-05,
|
1331 |
+
"loss": 0.0879,
|
1332 |
+
"step": 1770
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 29.54,
|
1336 |
+
"learning_rate": 2.446759259259259e-05,
|
1337 |
+
"loss": 0.0333,
|
1338 |
+
"step": 1780
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 29.71,
|
1342 |
+
"learning_rate": 2.4386574074074075e-05,
|
1343 |
+
"loss": 0.0849,
|
1344 |
+
"step": 1790
|
1345 |
+
},
|
1346 |
+
{
|
1347 |
+
"epoch": 29.88,
|
1348 |
+
"learning_rate": 2.4305555555555554e-05,
|
1349 |
+
"loss": 0.0382,
|
1350 |
+
"step": 1800
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"epoch": 29.99,
|
1354 |
+
"eval_accuracy": 0.8478260869565217,
|
1355 |
+
"eval_loss": 0.9374191164970398,
|
1356 |
+
"eval_runtime": 0.7092,
|
1357 |
+
"eval_samples_per_second": 64.864,
|
1358 |
+
"eval_steps_per_second": 4.23,
|
1359 |
+
"step": 1807
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 30.04,
|
1363 |
+
"learning_rate": 2.4224537037037037e-05,
|
1364 |
+
"loss": 0.0482,
|
1365 |
+
"step": 1810
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 30.21,
|
1369 |
+
"learning_rate": 2.4143518518518516e-05,
|
1370 |
+
"loss": 0.0232,
|
1371 |
+
"step": 1820
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 30.37,
|
1375 |
+
"learning_rate": 2.40625e-05,
|
1376 |
+
"loss": 0.0342,
|
1377 |
+
"step": 1830
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 30.54,
|
1381 |
+
"learning_rate": 2.398148148148148e-05,
|
1382 |
+
"loss": 0.0344,
|
1383 |
+
"step": 1840
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 30.71,
|
1387 |
+
"learning_rate": 2.390046296296296e-05,
|
1388 |
+
"loss": 0.0325,
|
1389 |
+
"step": 1850
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 30.87,
|
1393 |
+
"learning_rate": 2.3819444444444443e-05,
|
1394 |
+
"loss": 0.0511,
|
1395 |
+
"step": 1860
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 30.99,
|
1399 |
+
"eval_accuracy": 0.8043478260869565,
|
1400 |
+
"eval_loss": 1.0847010612487793,
|
1401 |
+
"eval_runtime": 0.7072,
|
1402 |
+
"eval_samples_per_second": 65.049,
|
1403 |
+
"eval_steps_per_second": 4.242,
|
1404 |
+
"step": 1867
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 31.04,
|
1408 |
+
"learning_rate": 2.3738425925925923e-05,
|
1409 |
+
"loss": 0.0243,
|
1410 |
+
"step": 1870
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 31.2,
|
1414 |
+
"learning_rate": 2.3657407407407405e-05,
|
1415 |
+
"loss": 0.0466,
|
1416 |
+
"step": 1880
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 31.37,
|
1420 |
+
"learning_rate": 2.3576388888888888e-05,
|
1421 |
+
"loss": 0.0543,
|
1422 |
+
"step": 1890
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 31.54,
|
1426 |
+
"learning_rate": 2.3495370370370367e-05,
|
1427 |
+
"loss": 0.0415,
|
1428 |
+
"step": 1900
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 31.7,
|
1432 |
+
"learning_rate": 2.341435185185185e-05,
|
1433 |
+
"loss": 0.0327,
|
1434 |
+
"step": 1910
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 31.87,
|
1438 |
+
"learning_rate": 2.333333333333333e-05,
|
1439 |
+
"loss": 0.0161,
|
1440 |
+
"step": 1920
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 32.0,
|
1444 |
+
"eval_accuracy": 0.782608695652174,
|
1445 |
+
"eval_loss": 1.2028273344039917,
|
1446 |
+
"eval_runtime": 0.6812,
|
1447 |
+
"eval_samples_per_second": 67.531,
|
1448 |
+
"eval_steps_per_second": 4.404,
|
1449 |
+
"step": 1928
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 32.03,
|
1453 |
+
"learning_rate": 2.325231481481481e-05,
|
1454 |
+
"loss": 0.0372,
|
1455 |
+
"step": 1930
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 32.2,
|
1459 |
+
"learning_rate": 2.3171296296296298e-05,
|
1460 |
+
"loss": 0.0433,
|
1461 |
+
"step": 1940
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 32.37,
|
1465 |
+
"learning_rate": 2.3090277777777777e-05,
|
1466 |
+
"loss": 0.0536,
|
1467 |
+
"step": 1950
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 32.53,
|
1471 |
+
"learning_rate": 2.300925925925926e-05,
|
1472 |
+
"loss": 0.0497,
|
1473 |
+
"step": 1960
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 32.7,
|
1477 |
+
"learning_rate": 2.292824074074074e-05,
|
1478 |
+
"loss": 0.0317,
|
1479 |
+
"step": 1970
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 32.86,
|
1483 |
+
"learning_rate": 2.284722222222222e-05,
|
1484 |
+
"loss": 0.0301,
|
1485 |
+
"step": 1980
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 33.0,
|
1489 |
+
"eval_accuracy": 0.7391304347826086,
|
1490 |
+
"eval_loss": 1.297067403793335,
|
1491 |
+
"eval_runtime": 0.6982,
|
1492 |
+
"eval_samples_per_second": 65.888,
|
1493 |
+
"eval_steps_per_second": 4.297,
|
1494 |
+
"step": 1988
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 33.03,
|
1498 |
+
"learning_rate": 2.27662037037037e-05,
|
1499 |
+
"loss": 0.0488,
|
1500 |
+
"step": 1990
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 33.2,
|
1504 |
+
"learning_rate": 2.2685185185185183e-05,
|
1505 |
+
"loss": 0.0382,
|
1506 |
+
"step": 2000
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 33.36,
|
1510 |
+
"learning_rate": 2.2604166666666666e-05,
|
1511 |
+
"loss": 0.0576,
|
1512 |
+
"step": 2010
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 33.53,
|
1516 |
+
"learning_rate": 2.2523148148148145e-05,
|
1517 |
+
"loss": 0.0111,
|
1518 |
+
"step": 2020
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 33.69,
|
1522 |
+
"learning_rate": 2.2442129629629628e-05,
|
1523 |
+
"loss": 0.0685,
|
1524 |
+
"step": 2030
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 33.86,
|
1528 |
+
"learning_rate": 2.2361111111111107e-05,
|
1529 |
+
"loss": 0.0443,
|
1530 |
+
"step": 2040
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 33.99,
|
1534 |
+
"eval_accuracy": 0.717391304347826,
|
1535 |
+
"eval_loss": 1.3993148803710938,
|
1536 |
+
"eval_runtime": 0.6712,
|
1537 |
+
"eval_samples_per_second": 68.537,
|
1538 |
+
"eval_steps_per_second": 4.47,
|
1539 |
+
"step": 2048
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 34.02,
|
1543 |
+
"learning_rate": 2.228009259259259e-05,
|
1544 |
+
"loss": 0.0488,
|
1545 |
+
"step": 2050
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 34.19,
|
1549 |
+
"learning_rate": 2.2199074074074073e-05,
|
1550 |
+
"loss": 0.0322,
|
1551 |
+
"step": 2060
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 34.36,
|
1555 |
+
"learning_rate": 2.2118055555555552e-05,
|
1556 |
+
"loss": 0.0353,
|
1557 |
+
"step": 2070
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 34.52,
|
1561 |
+
"learning_rate": 2.2037037037037034e-05,
|
1562 |
+
"loss": 0.0387,
|
1563 |
+
"step": 2080
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 34.69,
|
1567 |
+
"learning_rate": 2.1956018518518514e-05,
|
1568 |
+
"loss": 0.086,
|
1569 |
+
"step": 2090
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 34.85,
|
1573 |
+
"learning_rate": 2.1874999999999996e-05,
|
1574 |
+
"loss": 0.0782,
|
1575 |
+
"step": 2100
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 34.99,
|
1579 |
+
"eval_accuracy": 0.8043478260869565,
|
1580 |
+
"eval_loss": 1.3358551263809204,
|
1581 |
+
"eval_runtime": 0.6692,
|
1582 |
+
"eval_samples_per_second": 68.742,
|
1583 |
+
"eval_steps_per_second": 4.483,
|
1584 |
+
"step": 2108
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 35.02,
|
1588 |
+
"learning_rate": 2.1793981481481482e-05,
|
1589 |
+
"loss": 0.0232,
|
1590 |
+
"step": 2110
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 35.19,
|
1594 |
+
"learning_rate": 2.171296296296296e-05,
|
1595 |
+
"loss": 0.0295,
|
1596 |
+
"step": 2120
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 35.35,
|
1600 |
+
"learning_rate": 2.1631944444444444e-05,
|
1601 |
+
"loss": 0.0456,
|
1602 |
+
"step": 2130
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 35.52,
|
1606 |
+
"learning_rate": 2.1550925925925924e-05,
|
1607 |
+
"loss": 0.0266,
|
1608 |
+
"step": 2140
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 35.68,
|
1612 |
+
"learning_rate": 2.1469907407407406e-05,
|
1613 |
+
"loss": 0.0462,
|
1614 |
+
"step": 2150
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 35.85,
|
1618 |
+
"learning_rate": 2.138888888888889e-05,
|
1619 |
+
"loss": 0.0287,
|
1620 |
+
"step": 2160
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 36.0,
|
1624 |
+
"eval_accuracy": 0.782608695652174,
|
1625 |
+
"eval_loss": 1.3011459112167358,
|
1626 |
+
"eval_runtime": 0.7002,
|
1627 |
+
"eval_samples_per_second": 65.698,
|
1628 |
+
"eval_steps_per_second": 4.285,
|
1629 |
+
"step": 2169
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 36.02,
|
1633 |
+
"learning_rate": 2.1307870370370368e-05,
|
1634 |
+
"loss": 0.0502,
|
1635 |
+
"step": 2170
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 36.18,
|
1639 |
+
"learning_rate": 2.122685185185185e-05,
|
1640 |
+
"loss": 0.0499,
|
1641 |
+
"step": 2180
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 36.35,
|
1645 |
+
"learning_rate": 2.114583333333333e-05,
|
1646 |
+
"loss": 0.0313,
|
1647 |
+
"step": 2190
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 36.51,
|
1651 |
+
"learning_rate": 2.1064814814814813e-05,
|
1652 |
+
"loss": 0.0467,
|
1653 |
+
"step": 2200
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 36.68,
|
1657 |
+
"learning_rate": 2.0983796296296295e-05,
|
1658 |
+
"loss": 0.0496,
|
1659 |
+
"step": 2210
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 36.85,
|
1663 |
+
"learning_rate": 2.0902777777777775e-05,
|
1664 |
+
"loss": 0.0347,
|
1665 |
+
"step": 2220
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 37.0,
|
1669 |
+
"eval_accuracy": 0.782608695652174,
|
1670 |
+
"eval_loss": 1.2450307607650757,
|
1671 |
+
"eval_runtime": 0.7057,
|
1672 |
+
"eval_samples_per_second": 65.186,
|
1673 |
+
"eval_steps_per_second": 4.251,
|
1674 |
+
"step": 2229
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 37.01,
|
1678 |
+
"learning_rate": 2.0821759259259257e-05,
|
1679 |
+
"loss": 0.0322,
|
1680 |
+
"step": 2230
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 37.18,
|
1684 |
+
"learning_rate": 2.0740740740740737e-05,
|
1685 |
+
"loss": 0.0213,
|
1686 |
+
"step": 2240
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 37.34,
|
1690 |
+
"learning_rate": 2.065972222222222e-05,
|
1691 |
+
"loss": 0.0215,
|
1692 |
+
"step": 2250
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"epoch": 37.51,
|
1696 |
+
"learning_rate": 2.05787037037037e-05,
|
1697 |
+
"loss": 0.0172,
|
1698 |
+
"step": 2260
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 37.68,
|
1702 |
+
"learning_rate": 2.0497685185185184e-05,
|
1703 |
+
"loss": 0.0264,
|
1704 |
+
"step": 2270
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 37.84,
|
1708 |
+
"learning_rate": 2.0416666666666667e-05,
|
1709 |
+
"loss": 0.0538,
|
1710 |
+
"step": 2280
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 37.99,
|
1714 |
+
"eval_accuracy": 0.7608695652173914,
|
1715 |
+
"eval_loss": 1.8215843439102173,
|
1716 |
+
"eval_runtime": 0.6952,
|
1717 |
+
"eval_samples_per_second": 66.171,
|
1718 |
+
"eval_steps_per_second": 4.315,
|
1719 |
+
"step": 2289
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 38.01,
|
1723 |
+
"learning_rate": 2.0335648148148146e-05,
|
1724 |
+
"loss": 0.0541,
|
1725 |
+
"step": 2290
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 38.17,
|
1729 |
+
"learning_rate": 2.025462962962963e-05,
|
1730 |
+
"loss": 0.0261,
|
1731 |
+
"step": 2300
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 38.34,
|
1735 |
+
"learning_rate": 2.017361111111111e-05,
|
1736 |
+
"loss": 0.0371,
|
1737 |
+
"step": 2310
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 38.51,
|
1741 |
+
"learning_rate": 2.009259259259259e-05,
|
1742 |
+
"loss": 0.028,
|
1743 |
+
"step": 2320
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 38.67,
|
1747 |
+
"learning_rate": 2.0011574074074074e-05,
|
1748 |
+
"loss": 0.0167,
|
1749 |
+
"step": 2330
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 38.84,
|
1753 |
+
"learning_rate": 1.9930555555555553e-05,
|
1754 |
+
"loss": 0.027,
|
1755 |
+
"step": 2340
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 38.99,
|
1759 |
+
"eval_accuracy": 0.8043478260869565,
|
1760 |
+
"eval_loss": 1.170117735862732,
|
1761 |
+
"eval_runtime": 0.7309,
|
1762 |
+
"eval_samples_per_second": 62.933,
|
1763 |
+
"eval_steps_per_second": 4.104,
|
1764 |
+
"step": 2349
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 39.0,
|
1768 |
+
"learning_rate": 1.9849537037037036e-05,
|
1769 |
+
"loss": 0.0375,
|
1770 |
+
"step": 2350
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 39.17,
|
1774 |
+
"learning_rate": 1.9768518518518515e-05,
|
1775 |
+
"loss": 0.0467,
|
1776 |
+
"step": 2360
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 39.34,
|
1780 |
+
"learning_rate": 1.9687499999999997e-05,
|
1781 |
+
"loss": 0.03,
|
1782 |
+
"step": 2370
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 39.5,
|
1786 |
+
"learning_rate": 1.960648148148148e-05,
|
1787 |
+
"loss": 0.0243,
|
1788 |
+
"step": 2380
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 39.67,
|
1792 |
+
"learning_rate": 1.952546296296296e-05,
|
1793 |
+
"loss": 0.0393,
|
1794 |
+
"step": 2390
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 39.83,
|
1798 |
+
"learning_rate": 1.9444444444444442e-05,
|
1799 |
+
"loss": 0.0284,
|
1800 |
+
"step": 2400
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 40.0,
|
1804 |
+
"learning_rate": 1.936342592592592e-05,
|
1805 |
+
"loss": 0.038,
|
1806 |
+
"step": 2410
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 40.0,
|
1810 |
+
"eval_accuracy": 0.8043478260869565,
|
1811 |
+
"eval_loss": 1.1025199890136719,
|
1812 |
+
"eval_runtime": 0.7243,
|
1813 |
+
"eval_samples_per_second": 63.514,
|
1814 |
+
"eval_steps_per_second": 4.142,
|
1815 |
+
"step": 2410
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 40.17,
|
1819 |
+
"learning_rate": 1.9282407407407407e-05,
|
1820 |
+
"loss": 0.0243,
|
1821 |
+
"step": 2420
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 40.33,
|
1825 |
+
"learning_rate": 1.920138888888889e-05,
|
1826 |
+
"loss": 0.049,
|
1827 |
+
"step": 2430
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 40.5,
|
1831 |
+
"learning_rate": 1.912037037037037e-05,
|
1832 |
+
"loss": 0.0319,
|
1833 |
+
"step": 2440
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 40.66,
|
1837 |
+
"learning_rate": 1.9039351851851852e-05,
|
1838 |
+
"loss": 0.0413,
|
1839 |
+
"step": 2450
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 40.83,
|
1843 |
+
"learning_rate": 1.895833333333333e-05,
|
1844 |
+
"loss": 0.0369,
|
1845 |
+
"step": 2460
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 41.0,
|
1849 |
+
"learning_rate": 1.8877314814814814e-05,
|
1850 |
+
"loss": 0.0244,
|
1851 |
+
"step": 2470
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 41.0,
|
1855 |
+
"eval_accuracy": 0.7608695652173914,
|
1856 |
+
"eval_loss": 1.2912131547927856,
|
1857 |
+
"eval_runtime": 0.6786,
|
1858 |
+
"eval_samples_per_second": 67.783,
|
1859 |
+
"eval_steps_per_second": 4.421,
|
1860 |
+
"step": 2470
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 41.16,
|
1864 |
+
"learning_rate": 1.8796296296296296e-05,
|
1865 |
+
"loss": 0.0467,
|
1866 |
+
"step": 2480
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 41.33,
|
1870 |
+
"learning_rate": 1.8715277777777776e-05,
|
1871 |
+
"loss": 0.0295,
|
1872 |
+
"step": 2490
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 41.49,
|
1876 |
+
"learning_rate": 1.863425925925926e-05,
|
1877 |
+
"loss": 0.0241,
|
1878 |
+
"step": 2500
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 41.66,
|
1882 |
+
"learning_rate": 1.8553240740740738e-05,
|
1883 |
+
"loss": 0.0238,
|
1884 |
+
"step": 2510
|
1885 |
+
},
|
1886 |
+
{
|
1887 |
+
"epoch": 41.83,
|
1888 |
+
"learning_rate": 1.847222222222222e-05,
|
1889 |
+
"loss": 0.0201,
|
1890 |
+
"step": 2520
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 41.99,
|
1894 |
+
"learning_rate": 1.83912037037037e-05,
|
1895 |
+
"loss": 0.0122,
|
1896 |
+
"step": 2530
|
1897 |
+
},
|
1898 |
+
{
|
1899 |
+
"epoch": 41.99,
|
1900 |
+
"eval_accuracy": 0.7608695652173914,
|
1901 |
+
"eval_loss": 1.5698707103729248,
|
1902 |
+
"eval_runtime": 0.7096,
|
1903 |
+
"eval_samples_per_second": 64.826,
|
1904 |
+
"eval_steps_per_second": 4.228,
|
1905 |
+
"step": 2530
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 42.16,
|
1909 |
+
"learning_rate": 1.8310185185185182e-05,
|
1910 |
+
"loss": 0.0321,
|
1911 |
+
"step": 2540
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 42.32,
|
1915 |
+
"learning_rate": 1.8229166666666665e-05,
|
1916 |
+
"loss": 0.0336,
|
1917 |
+
"step": 2550
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 42.49,
|
1921 |
+
"learning_rate": 1.8148148148148144e-05,
|
1922 |
+
"loss": 0.0143,
|
1923 |
+
"step": 2560
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 42.66,
|
1927 |
+
"learning_rate": 1.806712962962963e-05,
|
1928 |
+
"loss": 0.0205,
|
1929 |
+
"step": 2570
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 42.82,
|
1933 |
+
"learning_rate": 1.798611111111111e-05,
|
1934 |
+
"loss": 0.0347,
|
1935 |
+
"step": 2580
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 42.99,
|
1939 |
+
"learning_rate": 1.7905092592592592e-05,
|
1940 |
+
"loss": 0.023,
|
1941 |
+
"step": 2590
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 42.99,
|
1945 |
+
"eval_accuracy": 0.782608695652174,
|
1946 |
+
"eval_loss": 1.51142156124115,
|
1947 |
+
"eval_runtime": 0.7048,
|
1948 |
+
"eval_samples_per_second": 65.263,
|
1949 |
+
"eval_steps_per_second": 4.256,
|
1950 |
+
"step": 2590
|
1951 |
+
},
|
1952 |
+
{
|
1953 |
+
"epoch": 43.15,
|
1954 |
+
"learning_rate": 1.7824074074074075e-05,
|
1955 |
+
"loss": 0.025,
|
1956 |
+
"step": 2600
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 43.32,
|
1960 |
+
"learning_rate": 1.7743055555555554e-05,
|
1961 |
+
"loss": 0.0213,
|
1962 |
+
"step": 2610
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 43.49,
|
1966 |
+
"learning_rate": 1.7662037037037037e-05,
|
1967 |
+
"loss": 0.0491,
|
1968 |
+
"step": 2620
|
1969 |
+
},
|
1970 |
+
{
|
1971 |
+
"epoch": 43.65,
|
1972 |
+
"learning_rate": 1.7581018518518516e-05,
|
1973 |
+
"loss": 0.0148,
|
1974 |
+
"step": 2630
|
1975 |
+
},
|
1976 |
+
{
|
1977 |
+
"epoch": 43.82,
|
1978 |
+
"learning_rate": 1.75e-05,
|
1979 |
+
"loss": 0.0267,
|
1980 |
+
"step": 2640
|
1981 |
+
},
|
1982 |
+
{
|
1983 |
+
"epoch": 43.98,
|
1984 |
+
"learning_rate": 1.741898148148148e-05,
|
1985 |
+
"loss": 0.0297,
|
1986 |
+
"step": 2650
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 44.0,
|
1990 |
+
"eval_accuracy": 0.8478260869565217,
|
1991 |
+
"eval_loss": 1.2188609838485718,
|
1992 |
+
"eval_runtime": 0.7237,
|
1993 |
+
"eval_samples_per_second": 63.561,
|
1994 |
+
"eval_steps_per_second": 4.145,
|
1995 |
+
"step": 2651
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 44.15,
|
1999 |
+
"learning_rate": 1.733796296296296e-05,
|
2000 |
+
"loss": 0.0183,
|
2001 |
+
"step": 2660
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 44.32,
|
2005 |
+
"learning_rate": 1.7256944444444443e-05,
|
2006 |
+
"loss": 0.0352,
|
2007 |
+
"step": 2670
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 44.48,
|
2011 |
+
"learning_rate": 1.7175925925925926e-05,
|
2012 |
+
"loss": 0.0243,
|
2013 |
+
"step": 2680
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 44.65,
|
2017 |
+
"learning_rate": 1.7094907407407405e-05,
|
2018 |
+
"loss": 0.104,
|
2019 |
+
"step": 2690
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 44.81,
|
2023 |
+
"learning_rate": 1.7013888888888888e-05,
|
2024 |
+
"loss": 0.015,
|
2025 |
+
"step": 2700
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 44.98,
|
2029 |
+
"learning_rate": 1.6932870370370367e-05,
|
2030 |
+
"loss": 0.0284,
|
2031 |
+
"step": 2710
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 45.0,
|
2035 |
+
"eval_accuracy": 0.782608695652174,
|
2036 |
+
"eval_loss": 1.3997039794921875,
|
2037 |
+
"eval_runtime": 0.7121,
|
2038 |
+
"eval_samples_per_second": 64.595,
|
2039 |
+
"eval_steps_per_second": 4.213,
|
2040 |
+
"step": 2711
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 45.15,
|
2044 |
+
"learning_rate": 1.685185185185185e-05,
|
2045 |
+
"loss": 0.0133,
|
2046 |
+
"step": 2720
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 45.31,
|
2050 |
+
"learning_rate": 1.6770833333333332e-05,
|
2051 |
+
"loss": 0.0159,
|
2052 |
+
"step": 2730
|
2053 |
+
},
|
2054 |
+
{
|
2055 |
+
"epoch": 45.48,
|
2056 |
+
"learning_rate": 1.6689814814814815e-05,
|
2057 |
+
"loss": 0.0183,
|
2058 |
+
"step": 2740
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 45.64,
|
2062 |
+
"learning_rate": 1.6608796296296294e-05,
|
2063 |
+
"loss": 0.0302,
|
2064 |
+
"step": 2750
|
2065 |
+
},
|
2066 |
+
{
|
2067 |
+
"epoch": 45.81,
|
2068 |
+
"learning_rate": 1.6527777777777777e-05,
|
2069 |
+
"loss": 0.0232,
|
2070 |
+
"step": 2760
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 45.98,
|
2074 |
+
"learning_rate": 1.6446759259259256e-05,
|
2075 |
+
"loss": 0.0203,
|
2076 |
+
"step": 2770
|
2077 |
+
},
|
2078 |
+
{
|
2079 |
+
"epoch": 45.99,
|
2080 |
+
"eval_accuracy": 0.8043478260869565,
|
2081 |
+
"eval_loss": 1.4792205095291138,
|
2082 |
+
"eval_runtime": 0.6983,
|
2083 |
+
"eval_samples_per_second": 65.879,
|
2084 |
+
"eval_steps_per_second": 4.296,
|
2085 |
+
"step": 2771
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 46.14,
|
2089 |
+
"learning_rate": 1.636574074074074e-05,
|
2090 |
+
"loss": 0.037,
|
2091 |
+
"step": 2780
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 46.31,
|
2095 |
+
"learning_rate": 1.628472222222222e-05,
|
2096 |
+
"loss": 0.0337,
|
2097 |
+
"step": 2790
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 46.47,
|
2101 |
+
"learning_rate": 1.6203703703703704e-05,
|
2102 |
+
"loss": 0.012,
|
2103 |
+
"step": 2800
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 46.64,
|
2107 |
+
"learning_rate": 1.6122685185185183e-05,
|
2108 |
+
"loss": 0.0568,
|
2109 |
+
"step": 2810
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 46.8,
|
2113 |
+
"learning_rate": 1.6041666666666666e-05,
|
2114 |
+
"loss": 0.018,
|
2115 |
+
"step": 2820
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 46.97,
|
2119 |
+
"learning_rate": 1.596064814814815e-05,
|
2120 |
+
"loss": 0.03,
|
2121 |
+
"step": 2830
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 46.99,
|
2125 |
+
"eval_accuracy": 0.717391304347826,
|
2126 |
+
"eval_loss": 1.7487258911132812,
|
2127 |
+
"eval_runtime": 0.7112,
|
2128 |
+
"eval_samples_per_second": 64.68,
|
2129 |
+
"eval_steps_per_second": 4.218,
|
2130 |
+
"step": 2831
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 47.14,
|
2134 |
+
"learning_rate": 1.5879629629629628e-05,
|
2135 |
+
"loss": 0.0083,
|
2136 |
+
"step": 2840
|
2137 |
+
},
|
2138 |
+
{
|
2139 |
+
"epoch": 47.3,
|
2140 |
+
"learning_rate": 1.579861111111111e-05,
|
2141 |
+
"loss": 0.0431,
|
2142 |
+
"step": 2850
|
2143 |
+
},
|
2144 |
+
{
|
2145 |
+
"epoch": 47.47,
|
2146 |
+
"learning_rate": 1.571759259259259e-05,
|
2147 |
+
"loss": 0.0104,
|
2148 |
+
"step": 2860
|
2149 |
+
},
|
2150 |
+
{
|
2151 |
+
"epoch": 47.63,
|
2152 |
+
"learning_rate": 1.5636574074074072e-05,
|
2153 |
+
"loss": 0.0322,
|
2154 |
+
"step": 2870
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 47.8,
|
2158 |
+
"learning_rate": 1.5555555555555555e-05,
|
2159 |
+
"loss": 0.0185,
|
2160 |
+
"step": 2880
|
2161 |
+
},
|
2162 |
+
{
|
2163 |
+
"epoch": 47.97,
|
2164 |
+
"learning_rate": 1.5474537037037038e-05,
|
2165 |
+
"loss": 0.025,
|
2166 |
+
"step": 2890
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 48.0,
|
2170 |
+
"eval_accuracy": 0.7608695652173914,
|
2171 |
+
"eval_loss": 1.6605217456817627,
|
2172 |
+
"eval_runtime": 0.6827,
|
2173 |
+
"eval_samples_per_second": 67.383,
|
2174 |
+
"eval_steps_per_second": 4.395,
|
2175 |
+
"step": 2892
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 48.13,
|
2179 |
+
"learning_rate": 1.5393518518518517e-05,
|
2180 |
+
"loss": 0.0269,
|
2181 |
+
"step": 2900
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 48.3,
|
2185 |
+
"learning_rate": 1.53125e-05,
|
2186 |
+
"loss": 0.0274,
|
2187 |
+
"step": 2910
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 48.46,
|
2191 |
+
"learning_rate": 1.523148148148148e-05,
|
2192 |
+
"loss": 0.033,
|
2193 |
+
"step": 2920
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 48.63,
|
2197 |
+
"learning_rate": 1.5150462962962961e-05,
|
2198 |
+
"loss": 0.0241,
|
2199 |
+
"step": 2930
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 48.8,
|
2203 |
+
"learning_rate": 1.5069444444444444e-05,
|
2204 |
+
"loss": 0.0445,
|
2205 |
+
"step": 2940
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 48.96,
|
2209 |
+
"learning_rate": 1.4988425925925925e-05,
|
2210 |
+
"loss": 0.0134,
|
2211 |
+
"step": 2950
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 49.0,
|
2215 |
+
"eval_accuracy": 0.782608695652174,
|
2216 |
+
"eval_loss": 1.410630226135254,
|
2217 |
+
"eval_runtime": 0.7027,
|
2218 |
+
"eval_samples_per_second": 65.459,
|
2219 |
+
"eval_steps_per_second": 4.269,
|
2220 |
+
"step": 2952
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"epoch": 49.13,
|
2224 |
+
"learning_rate": 1.4907407407407406e-05,
|
2225 |
+
"loss": 0.0366,
|
2226 |
+
"step": 2960
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 49.29,
|
2230 |
+
"learning_rate": 1.4826388888888887e-05,
|
2231 |
+
"loss": 0.0219,
|
2232 |
+
"step": 2970
|
2233 |
+
},
|
2234 |
+
{
|
2235 |
+
"epoch": 49.46,
|
2236 |
+
"learning_rate": 1.4745370370370368e-05,
|
2237 |
+
"loss": 0.0092,
|
2238 |
+
"step": 2980
|
2239 |
+
},
|
2240 |
+
{
|
2241 |
+
"epoch": 49.63,
|
2242 |
+
"learning_rate": 1.4664351851851849e-05,
|
2243 |
+
"loss": 0.0295,
|
2244 |
+
"step": 2990
|
2245 |
+
},
|
2246 |
+
{
|
2247 |
+
"epoch": 49.79,
|
2248 |
+
"learning_rate": 1.4583333333333333e-05,
|
2249 |
+
"loss": 0.0183,
|
2250 |
+
"step": 3000
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 49.96,
|
2254 |
+
"learning_rate": 1.4502314814814814e-05,
|
2255 |
+
"loss": 0.026,
|
2256 |
+
"step": 3010
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 49.99,
|
2260 |
+
"eval_accuracy": 0.7608695652173914,
|
2261 |
+
"eval_loss": 1.2972004413604736,
|
2262 |
+
"eval_runtime": 0.6842,
|
2263 |
+
"eval_samples_per_second": 67.236,
|
2264 |
+
"eval_steps_per_second": 4.385,
|
2265 |
+
"step": 3012
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 50.12,
|
2269 |
+
"learning_rate": 1.4421296296296295e-05,
|
2270 |
+
"loss": 0.0207,
|
2271 |
+
"step": 3020
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 50.29,
|
2275 |
+
"learning_rate": 1.4340277777777776e-05,
|
2276 |
+
"loss": 0.0111,
|
2277 |
+
"step": 3030
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 50.46,
|
2281 |
+
"learning_rate": 1.4259259259259257e-05,
|
2282 |
+
"loss": 0.0364,
|
2283 |
+
"step": 3040
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 50.62,
|
2287 |
+
"learning_rate": 1.417824074074074e-05,
|
2288 |
+
"loss": 0.0148,
|
2289 |
+
"step": 3050
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 50.79,
|
2293 |
+
"learning_rate": 1.409722222222222e-05,
|
2294 |
+
"loss": 0.0271,
|
2295 |
+
"step": 3060
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 50.95,
|
2299 |
+
"learning_rate": 1.4016203703703703e-05,
|
2300 |
+
"loss": 0.0507,
|
2301 |
+
"step": 3070
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 50.99,
|
2305 |
+
"eval_accuracy": 0.782608695652174,
|
2306 |
+
"eval_loss": 1.3302582502365112,
|
2307 |
+
"eval_runtime": 0.694,
|
2308 |
+
"eval_samples_per_second": 66.283,
|
2309 |
+
"eval_steps_per_second": 4.323,
|
2310 |
+
"step": 3072
|
2311 |
+
},
|
2312 |
+
{
|
2313 |
+
"epoch": 51.12,
|
2314 |
+
"learning_rate": 1.3935185185185184e-05,
|
2315 |
+
"loss": 0.0164,
|
2316 |
+
"step": 3080
|
2317 |
+
},
|
2318 |
+
{
|
2319 |
+
"epoch": 51.29,
|
2320 |
+
"learning_rate": 1.3854166666666665e-05,
|
2321 |
+
"loss": 0.0151,
|
2322 |
+
"step": 3090
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"epoch": 51.45,
|
2326 |
+
"learning_rate": 1.3773148148148148e-05,
|
2327 |
+
"loss": 0.0495,
|
2328 |
+
"step": 3100
|
2329 |
+
},
|
2330 |
+
{
|
2331 |
+
"epoch": 51.62,
|
2332 |
+
"learning_rate": 1.3692129629629629e-05,
|
2333 |
+
"loss": 0.0056,
|
2334 |
+
"step": 3110
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 51.78,
|
2338 |
+
"learning_rate": 1.361111111111111e-05,
|
2339 |
+
"loss": 0.0323,
|
2340 |
+
"step": 3120
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 51.95,
|
2344 |
+
"learning_rate": 1.353009259259259e-05,
|
2345 |
+
"loss": 0.0394,
|
2346 |
+
"step": 3130
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 52.0,
|
2350 |
+
"eval_accuracy": 0.8478260869565217,
|
2351 |
+
"eval_loss": 1.1954048871994019,
|
2352 |
+
"eval_runtime": 0.7081,
|
2353 |
+
"eval_samples_per_second": 64.959,
|
2354 |
+
"eval_steps_per_second": 4.236,
|
2355 |
+
"step": 3133
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 52.12,
|
2359 |
+
"learning_rate": 1.3449074074074072e-05,
|
2360 |
+
"loss": 0.0266,
|
2361 |
+
"step": 3140
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 52.28,
|
2365 |
+
"learning_rate": 1.3368055555555554e-05,
|
2366 |
+
"loss": 0.0354,
|
2367 |
+
"step": 3150
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 52.45,
|
2371 |
+
"learning_rate": 1.3287037037037037e-05,
|
2372 |
+
"loss": 0.0168,
|
2373 |
+
"step": 3160
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 52.61,
|
2377 |
+
"learning_rate": 1.3206018518518518e-05,
|
2378 |
+
"loss": 0.0259,
|
2379 |
+
"step": 3170
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 52.78,
|
2383 |
+
"learning_rate": 1.3124999999999999e-05,
|
2384 |
+
"loss": 0.027,
|
2385 |
+
"step": 3180
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 52.95,
|
2389 |
+
"learning_rate": 1.304398148148148e-05,
|
2390 |
+
"loss": 0.0271,
|
2391 |
+
"step": 3190
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 53.0,
|
2395 |
+
"eval_accuracy": 0.8260869565217391,
|
2396 |
+
"eval_loss": 1.312525987625122,
|
2397 |
+
"eval_runtime": 0.6832,
|
2398 |
+
"eval_samples_per_second": 67.329,
|
2399 |
+
"eval_steps_per_second": 4.391,
|
2400 |
+
"step": 3193
|
2401 |
+
},
|
2402 |
+
{
|
2403 |
+
"epoch": 53.11,
|
2404 |
+
"learning_rate": 1.296296296296296e-05,
|
2405 |
+
"loss": 0.0101,
|
2406 |
+
"step": 3200
|
2407 |
+
},
|
2408 |
+
{
|
2409 |
+
"epoch": 53.28,
|
2410 |
+
"learning_rate": 1.2881944444444443e-05,
|
2411 |
+
"loss": 0.0212,
|
2412 |
+
"step": 3210
|
2413 |
+
},
|
2414 |
+
{
|
2415 |
+
"epoch": 53.44,
|
2416 |
+
"learning_rate": 1.2800925925925926e-05,
|
2417 |
+
"loss": 0.0057,
|
2418 |
+
"step": 3220
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 53.61,
|
2422 |
+
"learning_rate": 1.2719907407407407e-05,
|
2423 |
+
"loss": 0.0132,
|
2424 |
+
"step": 3230
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 53.78,
|
2428 |
+
"learning_rate": 1.2638888888888888e-05,
|
2429 |
+
"loss": 0.0173,
|
2430 |
+
"step": 3240
|
2431 |
+
},
|
2432 |
+
{
|
2433 |
+
"epoch": 53.94,
|
2434 |
+
"learning_rate": 1.2557870370370369e-05,
|
2435 |
+
"loss": 0.0115,
|
2436 |
+
"step": 3250
|
2437 |
+
},
|
2438 |
+
{
|
2439 |
+
"epoch": 53.99,
|
2440 |
+
"eval_accuracy": 0.8478260869565217,
|
2441 |
+
"eval_loss": 1.3443913459777832,
|
2442 |
+
"eval_runtime": 0.7167,
|
2443 |
+
"eval_samples_per_second": 64.185,
|
2444 |
+
"eval_steps_per_second": 4.186,
|
2445 |
+
"step": 3253
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 54.11,
|
2449 |
+
"learning_rate": 1.247685185185185e-05,
|
2450 |
+
"loss": 0.0028,
|
2451 |
+
"step": 3260
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 54.27,
|
2455 |
+
"learning_rate": 1.2395833333333333e-05,
|
2456 |
+
"loss": 0.0184,
|
2457 |
+
"step": 3270
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 54.44,
|
2461 |
+
"learning_rate": 1.2314814814814813e-05,
|
2462 |
+
"loss": 0.0007,
|
2463 |
+
"step": 3280
|
2464 |
+
},
|
2465 |
+
{
|
2466 |
+
"epoch": 54.61,
|
2467 |
+
"learning_rate": 1.2233796296296294e-05,
|
2468 |
+
"loss": 0.0233,
|
2469 |
+
"step": 3290
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 54.77,
|
2473 |
+
"learning_rate": 1.2152777777777777e-05,
|
2474 |
+
"loss": 0.0078,
|
2475 |
+
"step": 3300
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 54.94,
|
2479 |
+
"learning_rate": 1.2071759259259258e-05,
|
2480 |
+
"loss": 0.0138,
|
2481 |
+
"step": 3310
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 54.99,
|
2485 |
+
"eval_accuracy": 0.8260869565217391,
|
2486 |
+
"eval_loss": 1.4688717126846313,
|
2487 |
+
"eval_runtime": 0.6497,
|
2488 |
+
"eval_samples_per_second": 70.806,
|
2489 |
+
"eval_steps_per_second": 4.618,
|
2490 |
+
"step": 3313
|
2491 |
+
},
|
2492 |
+
{
|
2493 |
+
"epoch": 55.1,
|
2494 |
+
"learning_rate": 1.199074074074074e-05,
|
2495 |
+
"loss": 0.0081,
|
2496 |
+
"step": 3320
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"epoch": 55.27,
|
2500 |
+
"learning_rate": 1.1909722222222222e-05,
|
2501 |
+
"loss": 0.0218,
|
2502 |
+
"step": 3330
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 55.44,
|
2506 |
+
"learning_rate": 1.1828703703703703e-05,
|
2507 |
+
"loss": 0.0143,
|
2508 |
+
"step": 3340
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 55.6,
|
2512 |
+
"learning_rate": 1.1747685185185184e-05,
|
2513 |
+
"loss": 0.0216,
|
2514 |
+
"step": 3350
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 55.77,
|
2518 |
+
"learning_rate": 1.1666666666666665e-05,
|
2519 |
+
"loss": 0.0091,
|
2520 |
+
"step": 3360
|
2521 |
+
},
|
2522 |
+
{
|
2523 |
+
"epoch": 55.93,
|
2524 |
+
"learning_rate": 1.1585648148148149e-05,
|
2525 |
+
"loss": 0.0184,
|
2526 |
+
"step": 3370
|
2527 |
+
},
|
2528 |
+
{
|
2529 |
+
"epoch": 56.0,
|
2530 |
+
"eval_accuracy": 0.8260869565217391,
|
2531 |
+
"eval_loss": 1.4959295988082886,
|
2532 |
+
"eval_runtime": 0.6842,
|
2533 |
+
"eval_samples_per_second": 67.228,
|
2534 |
+
"eval_steps_per_second": 4.384,
|
2535 |
+
"step": 3374
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 56.1,
|
2539 |
+
"learning_rate": 1.150462962962963e-05,
|
2540 |
+
"loss": 0.0134,
|
2541 |
+
"step": 3380
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 56.27,
|
2545 |
+
"learning_rate": 1.142361111111111e-05,
|
2546 |
+
"loss": 0.0193,
|
2547 |
+
"step": 3390
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 56.43,
|
2551 |
+
"learning_rate": 1.1342592592592592e-05,
|
2552 |
+
"loss": 0.0049,
|
2553 |
+
"step": 3400
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 56.6,
|
2557 |
+
"learning_rate": 1.1261574074074073e-05,
|
2558 |
+
"loss": 0.0105,
|
2559 |
+
"step": 3410
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 56.76,
|
2563 |
+
"learning_rate": 1.1180555555555554e-05,
|
2564 |
+
"loss": 0.0245,
|
2565 |
+
"step": 3420
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 56.93,
|
2569 |
+
"learning_rate": 1.1099537037037036e-05,
|
2570 |
+
"loss": 0.0163,
|
2571 |
+
"step": 3430
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 57.0,
|
2575 |
+
"eval_accuracy": 0.782608695652174,
|
2576 |
+
"eval_loss": 1.349004864692688,
|
2577 |
+
"eval_runtime": 0.6951,
|
2578 |
+
"eval_samples_per_second": 66.174,
|
2579 |
+
"eval_steps_per_second": 4.316,
|
2580 |
+
"step": 3434
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 57.1,
|
2584 |
+
"learning_rate": 1.1018518518518517e-05,
|
2585 |
+
"loss": 0.0116,
|
2586 |
+
"step": 3440
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 57.26,
|
2590 |
+
"learning_rate": 1.0937499999999998e-05,
|
2591 |
+
"loss": 0.0352,
|
2592 |
+
"step": 3450
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 57.43,
|
2596 |
+
"learning_rate": 1.085648148148148e-05,
|
2597 |
+
"loss": 0.0316,
|
2598 |
+
"step": 3460
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"epoch": 57.59,
|
2602 |
+
"learning_rate": 1.0775462962962962e-05,
|
2603 |
+
"loss": 0.0291,
|
2604 |
+
"step": 3470
|
2605 |
+
},
|
2606 |
+
{
|
2607 |
+
"epoch": 57.76,
|
2608 |
+
"learning_rate": 1.0694444444444444e-05,
|
2609 |
+
"loss": 0.0388,
|
2610 |
+
"step": 3480
|
2611 |
+
},
|
2612 |
+
{
|
2613 |
+
"epoch": 57.93,
|
2614 |
+
"learning_rate": 1.0613425925925925e-05,
|
2615 |
+
"loss": 0.0112,
|
2616 |
+
"step": 3490
|
2617 |
+
},
|
2618 |
+
{
|
2619 |
+
"epoch": 57.99,
|
2620 |
+
"eval_accuracy": 0.782608695652174,
|
2621 |
+
"eval_loss": 1.4749095439910889,
|
2622 |
+
"eval_runtime": 0.6781,
|
2623 |
+
"eval_samples_per_second": 67.833,
|
2624 |
+
"eval_steps_per_second": 4.424,
|
2625 |
+
"step": 3494
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 58.09,
|
2629 |
+
"learning_rate": 1.0532407407407406e-05,
|
2630 |
+
"loss": 0.025,
|
2631 |
+
"step": 3500
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 58.26,
|
2635 |
+
"learning_rate": 1.0451388888888887e-05,
|
2636 |
+
"loss": 0.0354,
|
2637 |
+
"step": 3510
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 58.42,
|
2641 |
+
"learning_rate": 1.0370370370370368e-05,
|
2642 |
+
"loss": 0.0064,
|
2643 |
+
"step": 3520
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 58.59,
|
2647 |
+
"learning_rate": 1.028935185185185e-05,
|
2648 |
+
"loss": 0.0058,
|
2649 |
+
"step": 3530
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 58.76,
|
2653 |
+
"learning_rate": 1.0208333333333334e-05,
|
2654 |
+
"loss": 0.0241,
|
2655 |
+
"step": 3540
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 58.92,
|
2659 |
+
"learning_rate": 1.0127314814814815e-05,
|
2660 |
+
"loss": 0.0185,
|
2661 |
+
"step": 3550
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 58.99,
|
2665 |
+
"eval_accuracy": 0.782608695652174,
|
2666 |
+
"eval_loss": 1.5823291540145874,
|
2667 |
+
"eval_runtime": 0.6695,
|
2668 |
+
"eval_samples_per_second": 68.712,
|
2669 |
+
"eval_steps_per_second": 4.481,
|
2670 |
+
"step": 3554
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 59.09,
|
2674 |
+
"learning_rate": 1.0046296296296295e-05,
|
2675 |
+
"loss": 0.0089,
|
2676 |
+
"step": 3560
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 59.25,
|
2680 |
+
"learning_rate": 9.965277777777776e-06,
|
2681 |
+
"loss": 0.0291,
|
2682 |
+
"step": 3570
|
2683 |
+
},
|
2684 |
+
{
|
2685 |
+
"epoch": 59.42,
|
2686 |
+
"learning_rate": 9.884259259259257e-06,
|
2687 |
+
"loss": 0.0118,
|
2688 |
+
"step": 3580
|
2689 |
+
},
|
2690 |
+
{
|
2691 |
+
"epoch": 59.59,
|
2692 |
+
"learning_rate": 9.80324074074074e-06,
|
2693 |
+
"loss": 0.0318,
|
2694 |
+
"step": 3590
|
2695 |
+
},
|
2696 |
+
{
|
2697 |
+
"epoch": 59.75,
|
2698 |
+
"learning_rate": 9.722222222222221e-06,
|
2699 |
+
"loss": 0.0395,
|
2700 |
+
"step": 3600
|
2701 |
+
},
|
2702 |
+
{
|
2703 |
+
"epoch": 59.92,
|
2704 |
+
"learning_rate": 9.641203703703704e-06,
|
2705 |
+
"loss": 0.031,
|
2706 |
+
"step": 3610
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 60.0,
|
2710 |
+
"eval_accuracy": 0.782608695652174,
|
2711 |
+
"eval_loss": 1.5190129280090332,
|
2712 |
+
"eval_runtime": 0.7102,
|
2713 |
+
"eval_samples_per_second": 64.766,
|
2714 |
+
"eval_steps_per_second": 4.224,
|
2715 |
+
"step": 3615
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 60.08,
|
2719 |
+
"learning_rate": 9.560185185185185e-06,
|
2720 |
+
"loss": 0.0127,
|
2721 |
+
"step": 3620
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 60.25,
|
2725 |
+
"learning_rate": 9.479166666666666e-06,
|
2726 |
+
"loss": 0.0065,
|
2727 |
+
"step": 3630
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 60.41,
|
2731 |
+
"learning_rate": 9.398148148148148e-06,
|
2732 |
+
"loss": 0.0129,
|
2733 |
+
"step": 3640
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 60.58,
|
2737 |
+
"learning_rate": 9.31712962962963e-06,
|
2738 |
+
"loss": 0.0157,
|
2739 |
+
"step": 3650
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 60.75,
|
2743 |
+
"learning_rate": 9.23611111111111e-06,
|
2744 |
+
"loss": 0.0134,
|
2745 |
+
"step": 3660
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 60.91,
|
2749 |
+
"learning_rate": 9.155092592592591e-06,
|
2750 |
+
"loss": 0.0161,
|
2751 |
+
"step": 3670
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 61.0,
|
2755 |
+
"eval_accuracy": 0.8043478260869565,
|
2756 |
+
"eval_loss": 1.5475845336914062,
|
2757 |
+
"eval_runtime": 0.7113,
|
2758 |
+
"eval_samples_per_second": 64.674,
|
2759 |
+
"eval_steps_per_second": 4.218,
|
2760 |
+
"step": 3675
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 61.08,
|
2764 |
+
"learning_rate": 9.074074074074072e-06,
|
2765 |
+
"loss": 0.0117,
|
2766 |
+
"step": 3680
|
2767 |
+
},
|
2768 |
+
{
|
2769 |
+
"epoch": 61.24,
|
2770 |
+
"learning_rate": 8.993055555555555e-06,
|
2771 |
+
"loss": 0.0135,
|
2772 |
+
"step": 3690
|
2773 |
+
},
|
2774 |
+
{
|
2775 |
+
"epoch": 61.41,
|
2776 |
+
"learning_rate": 8.912037037037037e-06,
|
2777 |
+
"loss": 0.0179,
|
2778 |
+
"step": 3700
|
2779 |
+
},
|
2780 |
+
{
|
2781 |
+
"epoch": 61.58,
|
2782 |
+
"learning_rate": 8.831018518518518e-06,
|
2783 |
+
"loss": 0.0253,
|
2784 |
+
"step": 3710
|
2785 |
+
},
|
2786 |
+
{
|
2787 |
+
"epoch": 61.74,
|
2788 |
+
"learning_rate": 8.75e-06,
|
2789 |
+
"loss": 0.0267,
|
2790 |
+
"step": 3720
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 61.91,
|
2794 |
+
"learning_rate": 8.66898148148148e-06,
|
2795 |
+
"loss": 0.0146,
|
2796 |
+
"step": 3730
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 61.99,
|
2800 |
+
"eval_accuracy": 0.782608695652174,
|
2801 |
+
"eval_loss": 1.3930317163467407,
|
2802 |
+
"eval_runtime": 0.6749,
|
2803 |
+
"eval_samples_per_second": 68.162,
|
2804 |
+
"eval_steps_per_second": 4.445,
|
2805 |
+
"step": 3735
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 62.07,
|
2809 |
+
"learning_rate": 8.587962962962963e-06,
|
2810 |
+
"loss": 0.0202,
|
2811 |
+
"step": 3740
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 62.24,
|
2815 |
+
"learning_rate": 8.506944444444444e-06,
|
2816 |
+
"loss": 0.0162,
|
2817 |
+
"step": 3750
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 62.41,
|
2821 |
+
"learning_rate": 8.425925925925925e-06,
|
2822 |
+
"loss": 0.0199,
|
2823 |
+
"step": 3760
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 62.57,
|
2827 |
+
"learning_rate": 8.344907407407407e-06,
|
2828 |
+
"loss": 0.0135,
|
2829 |
+
"step": 3770
|
2830 |
+
},
|
2831 |
+
{
|
2832 |
+
"epoch": 62.74,
|
2833 |
+
"learning_rate": 8.263888888888888e-06,
|
2834 |
+
"loss": 0.0132,
|
2835 |
+
"step": 3780
|
2836 |
+
},
|
2837 |
+
{
|
2838 |
+
"epoch": 62.9,
|
2839 |
+
"learning_rate": 8.18287037037037e-06,
|
2840 |
+
"loss": 0.005,
|
2841 |
+
"step": 3790
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 62.99,
|
2845 |
+
"eval_accuracy": 0.8043478260869565,
|
2846 |
+
"eval_loss": 1.5454456806182861,
|
2847 |
+
"eval_runtime": 0.7582,
|
2848 |
+
"eval_samples_per_second": 60.67,
|
2849 |
+
"eval_steps_per_second": 3.957,
|
2850 |
+
"step": 3795
|
2851 |
+
},
|
2852 |
+
{
|
2853 |
+
"epoch": 63.07,
|
2854 |
+
"learning_rate": 8.101851851851852e-06,
|
2855 |
+
"loss": 0.03,
|
2856 |
+
"step": 3800
|
2857 |
+
},
|
2858 |
+
{
|
2859 |
+
"epoch": 63.24,
|
2860 |
+
"learning_rate": 8.020833333333333e-06,
|
2861 |
+
"loss": 0.0326,
|
2862 |
+
"step": 3810
|
2863 |
+
},
|
2864 |
+
{
|
2865 |
+
"epoch": 63.4,
|
2866 |
+
"learning_rate": 7.939814814814814e-06,
|
2867 |
+
"loss": 0.0128,
|
2868 |
+
"step": 3820
|
2869 |
+
},
|
2870 |
+
{
|
2871 |
+
"epoch": 63.57,
|
2872 |
+
"learning_rate": 7.858796296296295e-06,
|
2873 |
+
"loss": 0.0108,
|
2874 |
+
"step": 3830
|
2875 |
+
},
|
2876 |
+
{
|
2877 |
+
"epoch": 63.73,
|
2878 |
+
"learning_rate": 7.777777777777777e-06,
|
2879 |
+
"loss": 0.0011,
|
2880 |
+
"step": 3840
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 63.9,
|
2884 |
+
"learning_rate": 7.696759259259258e-06,
|
2885 |
+
"loss": 0.0093,
|
2886 |
+
"step": 3850
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 64.0,
|
2890 |
+
"eval_accuracy": 0.782608695652174,
|
2891 |
+
"eval_loss": 1.5958888530731201,
|
2892 |
+
"eval_runtime": 0.6768,
|
2893 |
+
"eval_samples_per_second": 67.965,
|
2894 |
+
"eval_steps_per_second": 4.433,
|
2895 |
+
"step": 3856
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 64.07,
|
2899 |
+
"learning_rate": 7.61574074074074e-06,
|
2900 |
+
"loss": 0.0132,
|
2901 |
+
"step": 3860
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 64.23,
|
2905 |
+
"learning_rate": 7.534722222222222e-06,
|
2906 |
+
"loss": 0.0085,
|
2907 |
+
"step": 3870
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 64.4,
|
2911 |
+
"learning_rate": 7.453703703703703e-06,
|
2912 |
+
"loss": 0.0326,
|
2913 |
+
"step": 3880
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 64.56,
|
2917 |
+
"learning_rate": 7.372685185185184e-06,
|
2918 |
+
"loss": 0.0295,
|
2919 |
+
"step": 3890
|
2920 |
+
},
|
2921 |
+
{
|
2922 |
+
"epoch": 64.73,
|
2923 |
+
"learning_rate": 7.291666666666667e-06,
|
2924 |
+
"loss": 0.0172,
|
2925 |
+
"step": 3900
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 64.9,
|
2929 |
+
"learning_rate": 7.2106481481481475e-06,
|
2930 |
+
"loss": 0.0224,
|
2931 |
+
"step": 3910
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 65.0,
|
2935 |
+
"eval_accuracy": 0.8043478260869565,
|
2936 |
+
"eval_loss": 1.4553816318511963,
|
2937 |
+
"eval_runtime": 0.7364,
|
2938 |
+
"eval_samples_per_second": 62.467,
|
2939 |
+
"eval_steps_per_second": 4.074,
|
2940 |
+
"step": 3916
|
2941 |
+
},
|
2942 |
+
{
|
2943 |
+
"epoch": 65.06,
|
2944 |
+
"learning_rate": 7.1296296296296285e-06,
|
2945 |
+
"loss": 0.0208,
|
2946 |
+
"step": 3920
|
2947 |
+
},
|
2948 |
+
{
|
2949 |
+
"epoch": 65.23,
|
2950 |
+
"learning_rate": 7.04861111111111e-06,
|
2951 |
+
"loss": 0.023,
|
2952 |
+
"step": 3930
|
2953 |
+
},
|
2954 |
+
{
|
2955 |
+
"epoch": 65.39,
|
2956 |
+
"learning_rate": 6.967592592592592e-06,
|
2957 |
+
"loss": 0.0205,
|
2958 |
+
"step": 3940
|
2959 |
+
},
|
2960 |
+
{
|
2961 |
+
"epoch": 65.56,
|
2962 |
+
"learning_rate": 6.886574074074074e-06,
|
2963 |
+
"loss": 0.0088,
|
2964 |
+
"step": 3950
|
2965 |
+
},
|
2966 |
+
{
|
2967 |
+
"epoch": 65.73,
|
2968 |
+
"learning_rate": 6.805555555555555e-06,
|
2969 |
+
"loss": 0.0223,
|
2970 |
+
"step": 3960
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 65.89,
|
2974 |
+
"learning_rate": 6.724537037037036e-06,
|
2975 |
+
"loss": 0.0154,
|
2976 |
+
"step": 3970
|
2977 |
+
},
|
2978 |
+
{
|
2979 |
+
"epoch": 65.99,
|
2980 |
+
"eval_accuracy": 0.8260869565217391,
|
2981 |
+
"eval_loss": 1.5326697826385498,
|
2982 |
+
"eval_runtime": 0.7162,
|
2983 |
+
"eval_samples_per_second": 64.228,
|
2984 |
+
"eval_steps_per_second": 4.189,
|
2985 |
+
"step": 3976
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 66.06,
|
2989 |
+
"learning_rate": 6.6435185185185185e-06,
|
2990 |
+
"loss": 0.0093,
|
2991 |
+
"step": 3980
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 66.22,
|
2995 |
+
"learning_rate": 6.5624999999999994e-06,
|
2996 |
+
"loss": 0.0138,
|
2997 |
+
"step": 3990
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 66.39,
|
3001 |
+
"learning_rate": 6.48148148148148e-06,
|
3002 |
+
"loss": 0.0059,
|
3003 |
+
"step": 4000
|
3004 |
+
},
|
3005 |
+
{
|
3006 |
+
"epoch": 66.56,
|
3007 |
+
"learning_rate": 6.400462962962963e-06,
|
3008 |
+
"loss": 0.0033,
|
3009 |
+
"step": 4010
|
3010 |
+
},
|
3011 |
+
{
|
3012 |
+
"epoch": 66.72,
|
3013 |
+
"learning_rate": 6.319444444444444e-06,
|
3014 |
+
"loss": 0.0237,
|
3015 |
+
"step": 4020
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 66.89,
|
3019 |
+
"learning_rate": 6.238425925925925e-06,
|
3020 |
+
"loss": 0.0116,
|
3021 |
+
"step": 4030
|
3022 |
+
},
|
3023 |
+
{
|
3024 |
+
"epoch": 66.99,
|
3025 |
+
"eval_accuracy": 0.8043478260869565,
|
3026 |
+
"eval_loss": 1.6029945611953735,
|
3027 |
+
"eval_runtime": 0.7141,
|
3028 |
+
"eval_samples_per_second": 64.418,
|
3029 |
+
"eval_steps_per_second": 4.201,
|
3030 |
+
"step": 4036
|
3031 |
+
},
|
3032 |
+
{
|
3033 |
+
"epoch": 67.05,
|
3034 |
+
"learning_rate": 6.157407407407407e-06,
|
3035 |
+
"loss": 0.0064,
|
3036 |
+
"step": 4040
|
3037 |
+
},
|
3038 |
+
{
|
3039 |
+
"epoch": 67.22,
|
3040 |
+
"learning_rate": 6.0763888888888885e-06,
|
3041 |
+
"loss": 0.0129,
|
3042 |
+
"step": 4050
|
3043 |
+
},
|
3044 |
+
{
|
3045 |
+
"epoch": 67.39,
|
3046 |
+
"learning_rate": 5.99537037037037e-06,
|
3047 |
+
"loss": 0.0032,
|
3048 |
+
"step": 4060
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 67.55,
|
3052 |
+
"learning_rate": 5.914351851851851e-06,
|
3053 |
+
"loss": 0.0101,
|
3054 |
+
"step": 4070
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 67.72,
|
3058 |
+
"learning_rate": 5.833333333333332e-06,
|
3059 |
+
"loss": 0.0051,
|
3060 |
+
"step": 4080
|
3061 |
+
},
|
3062 |
+
{
|
3063 |
+
"epoch": 67.88,
|
3064 |
+
"learning_rate": 5.752314814814815e-06,
|
3065 |
+
"loss": 0.0037,
|
3066 |
+
"step": 4090
|
3067 |
+
},
|
3068 |
+
{
|
3069 |
+
"epoch": 68.0,
|
3070 |
+
"eval_accuracy": 0.8260869565217391,
|
3071 |
+
"eval_loss": 1.5046288967132568,
|
3072 |
+
"eval_runtime": 0.7027,
|
3073 |
+
"eval_samples_per_second": 65.464,
|
3074 |
+
"eval_steps_per_second": 4.269,
|
3075 |
+
"step": 4097
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 68.05,
|
3079 |
+
"learning_rate": 5.671296296296296e-06,
|
3080 |
+
"loss": 0.0151,
|
3081 |
+
"step": 4100
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 68.22,
|
3085 |
+
"learning_rate": 5.590277777777777e-06,
|
3086 |
+
"loss": 0.0007,
|
3087 |
+
"step": 4110
|
3088 |
+
},
|
3089 |
+
{
|
3090 |
+
"epoch": 68.38,
|
3091 |
+
"learning_rate": 5.509259259259259e-06,
|
3092 |
+
"loss": 0.0212,
|
3093 |
+
"step": 4120
|
3094 |
+
},
|
3095 |
+
{
|
3096 |
+
"epoch": 68.55,
|
3097 |
+
"learning_rate": 5.42824074074074e-06,
|
3098 |
+
"loss": 0.0038,
|
3099 |
+
"step": 4130
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 68.71,
|
3103 |
+
"learning_rate": 5.347222222222222e-06,
|
3104 |
+
"loss": 0.0211,
|
3105 |
+
"step": 4140
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 68.88,
|
3109 |
+
"learning_rate": 5.266203703703703e-06,
|
3110 |
+
"loss": 0.0023,
|
3111 |
+
"step": 4150
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 69.0,
|
3115 |
+
"eval_accuracy": 0.8260869565217391,
|
3116 |
+
"eval_loss": 1.5222116708755493,
|
3117 |
+
"eval_runtime": 0.6773,
|
3118 |
+
"eval_samples_per_second": 67.922,
|
3119 |
+
"eval_steps_per_second": 4.43,
|
3120 |
+
"step": 4157
|
3121 |
+
},
|
3122 |
+
{
|
3123 |
+
"epoch": 69.05,
|
3124 |
+
"learning_rate": 5.185185185185184e-06,
|
3125 |
+
"loss": 0.012,
|
3126 |
+
"step": 4160
|
3127 |
+
},
|
3128 |
+
{
|
3129 |
+
"epoch": 69.21,
|
3130 |
+
"learning_rate": 5.104166666666667e-06,
|
3131 |
+
"loss": 0.0086,
|
3132 |
+
"step": 4170
|
3133 |
+
},
|
3134 |
+
{
|
3135 |
+
"epoch": 69.38,
|
3136 |
+
"learning_rate": 5.023148148148148e-06,
|
3137 |
+
"loss": 0.0203,
|
3138 |
+
"step": 4180
|
3139 |
+
},
|
3140 |
+
{
|
3141 |
+
"epoch": 69.54,
|
3142 |
+
"learning_rate": 4.942129629629629e-06,
|
3143 |
+
"loss": 0.0074,
|
3144 |
+
"step": 4190
|
3145 |
+
},
|
3146 |
+
{
|
3147 |
+
"epoch": 69.71,
|
3148 |
+
"learning_rate": 4.8611111111111105e-06,
|
3149 |
+
"loss": 0.0071,
|
3150 |
+
"step": 4200
|
3151 |
+
},
|
3152 |
+
{
|
3153 |
+
"epoch": 69.88,
|
3154 |
+
"learning_rate": 4.780092592592592e-06,
|
3155 |
+
"loss": 0.0068,
|
3156 |
+
"step": 4210
|
3157 |
+
},
|
3158 |
+
{
|
3159 |
+
"epoch": 69.99,
|
3160 |
+
"eval_accuracy": 0.8260869565217391,
|
3161 |
+
"eval_loss": 1.4339091777801514,
|
3162 |
+
"eval_runtime": 0.686,
|
3163 |
+
"eval_samples_per_second": 67.057,
|
3164 |
+
"eval_steps_per_second": 4.373,
|
3165 |
+
"step": 4217
|
3166 |
+
},
|
3167 |
+
{
|
3168 |
+
"epoch": 70.04,
|
3169 |
+
"learning_rate": 4.699074074074074e-06,
|
3170 |
+
"loss": 0.0015,
|
3171 |
+
"step": 4220
|
3172 |
+
},
|
3173 |
+
{
|
3174 |
+
"epoch": 70.21,
|
3175 |
+
"learning_rate": 4.618055555555555e-06,
|
3176 |
+
"loss": 0.0096,
|
3177 |
+
"step": 4230
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 70.37,
|
3181 |
+
"learning_rate": 4.537037037037036e-06,
|
3182 |
+
"loss": 0.0074,
|
3183 |
+
"step": 4240
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 70.54,
|
3187 |
+
"learning_rate": 4.456018518518519e-06,
|
3188 |
+
"loss": 0.0172,
|
3189 |
+
"step": 4250
|
3190 |
+
},
|
3191 |
+
{
|
3192 |
+
"epoch": 70.71,
|
3193 |
+
"learning_rate": 4.375e-06,
|
3194 |
+
"loss": 0.0024,
|
3195 |
+
"step": 4260
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 70.87,
|
3199 |
+
"learning_rate": 4.293981481481481e-06,
|
3200 |
+
"loss": 0.0342,
|
3201 |
+
"step": 4270
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 70.99,
|
3205 |
+
"eval_accuracy": 0.8043478260869565,
|
3206 |
+
"eval_loss": 1.6964349746704102,
|
3207 |
+
"eval_runtime": 0.7042,
|
3208 |
+
"eval_samples_per_second": 65.326,
|
3209 |
+
"eval_steps_per_second": 4.26,
|
3210 |
+
"step": 4277
|
3211 |
+
},
|
3212 |
+
{
|
3213 |
+
"epoch": 71.04,
|
3214 |
+
"learning_rate": 4.212962962962962e-06,
|
3215 |
+
"loss": 0.0028,
|
3216 |
+
"step": 4280
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 71.2,
|
3220 |
+
"learning_rate": 4.131944444444444e-06,
|
3221 |
+
"loss": 0.0185,
|
3222 |
+
"step": 4290
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 71.37,
|
3226 |
+
"learning_rate": 4.050925925925926e-06,
|
3227 |
+
"loss": 0.0172,
|
3228 |
+
"step": 4300
|
3229 |
+
},
|
3230 |
+
{
|
3231 |
+
"epoch": 71.54,
|
3232 |
+
"learning_rate": 3.969907407407407e-06,
|
3233 |
+
"loss": 0.0051,
|
3234 |
+
"step": 4310
|
3235 |
+
},
|
3236 |
+
{
|
3237 |
+
"epoch": 71.7,
|
3238 |
+
"learning_rate": 3.888888888888889e-06,
|
3239 |
+
"loss": 0.0049,
|
3240 |
+
"step": 4320
|
3241 |
+
},
|
3242 |
+
{
|
3243 |
+
"epoch": 71.87,
|
3244 |
+
"learning_rate": 3.80787037037037e-06,
|
3245 |
+
"loss": 0.0077,
|
3246 |
+
"step": 4330
|
3247 |
+
},
|
3248 |
+
{
|
3249 |
+
"epoch": 72.0,
|
3250 |
+
"eval_accuracy": 0.8043478260869565,
|
3251 |
+
"eval_loss": 1.6102274656295776,
|
3252 |
+
"eval_runtime": 0.691,
|
3253 |
+
"eval_samples_per_second": 66.569,
|
3254 |
+
"eval_steps_per_second": 4.341,
|
3255 |
+
"step": 4338
|
3256 |
+
},
|
3257 |
+
{
|
3258 |
+
"epoch": 72.03,
|
3259 |
+
"learning_rate": 3.7268518518518515e-06,
|
3260 |
+
"loss": 0.0207,
|
3261 |
+
"step": 4340
|
3262 |
+
},
|
3263 |
+
{
|
3264 |
+
"epoch": 72.2,
|
3265 |
+
"learning_rate": 3.6458333333333333e-06,
|
3266 |
+
"loss": 0.0135,
|
3267 |
+
"step": 4350
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 72.37,
|
3271 |
+
"learning_rate": 3.5648148148148143e-06,
|
3272 |
+
"loss": 0.0098,
|
3273 |
+
"step": 4360
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 72.53,
|
3277 |
+
"learning_rate": 3.483796296296296e-06,
|
3278 |
+
"loss": 0.0207,
|
3279 |
+
"step": 4370
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 72.7,
|
3283 |
+
"learning_rate": 3.4027777777777774e-06,
|
3284 |
+
"loss": 0.0007,
|
3285 |
+
"step": 4380
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 72.86,
|
3289 |
+
"learning_rate": 3.3217592592592592e-06,
|
3290 |
+
"loss": 0.0043,
|
3291 |
+
"step": 4390
|
3292 |
+
},
|
3293 |
+
{
|
3294 |
+
"epoch": 73.0,
|
3295 |
+
"eval_accuracy": 0.8043478260869565,
|
3296 |
+
"eval_loss": 1.668748140335083,
|
3297 |
+
"eval_runtime": 0.7135,
|
3298 |
+
"eval_samples_per_second": 64.472,
|
3299 |
+
"eval_steps_per_second": 4.205,
|
3300 |
+
"step": 4398
|
3301 |
+
},
|
3302 |
+
{
|
3303 |
+
"epoch": 73.03,
|
3304 |
+
"learning_rate": 3.24074074074074e-06,
|
3305 |
+
"loss": 0.0045,
|
3306 |
+
"step": 4400
|
3307 |
+
},
|
3308 |
+
{
|
3309 |
+
"epoch": 73.2,
|
3310 |
+
"learning_rate": 3.159722222222222e-06,
|
3311 |
+
"loss": 0.0121,
|
3312 |
+
"step": 4410
|
3313 |
+
},
|
3314 |
+
{
|
3315 |
+
"epoch": 73.36,
|
3316 |
+
"learning_rate": 3.0787037037037034e-06,
|
3317 |
+
"loss": 0.0131,
|
3318 |
+
"step": 4420
|
3319 |
+
},
|
3320 |
+
{
|
3321 |
+
"epoch": 73.53,
|
3322 |
+
"learning_rate": 2.997685185185185e-06,
|
3323 |
+
"loss": 0.0134,
|
3324 |
+
"step": 4430
|
3325 |
+
},
|
3326 |
+
{
|
3327 |
+
"epoch": 73.69,
|
3328 |
+
"learning_rate": 2.916666666666666e-06,
|
3329 |
+
"loss": 0.0233,
|
3330 |
+
"step": 4440
|
3331 |
+
},
|
3332 |
+
{
|
3333 |
+
"epoch": 73.86,
|
3334 |
+
"learning_rate": 2.835648148148148e-06,
|
3335 |
+
"loss": 0.0131,
|
3336 |
+
"step": 4450
|
3337 |
+
},
|
3338 |
+
{
|
3339 |
+
"epoch": 73.99,
|
3340 |
+
"eval_accuracy": 0.8043478260869565,
|
3341 |
+
"eval_loss": 1.6847338676452637,
|
3342 |
+
"eval_runtime": 0.702,
|
3343 |
+
"eval_samples_per_second": 65.531,
|
3344 |
+
"eval_steps_per_second": 4.274,
|
3345 |
+
"step": 4458
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 74.02,
|
3349 |
+
"learning_rate": 2.7546296296296293e-06,
|
3350 |
+
"loss": 0.0151,
|
3351 |
+
"step": 4460
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 74.19,
|
3355 |
+
"learning_rate": 2.673611111111111e-06,
|
3356 |
+
"loss": 0.0031,
|
3357 |
+
"step": 4470
|
3358 |
+
},
|
3359 |
+
{
|
3360 |
+
"epoch": 74.36,
|
3361 |
+
"learning_rate": 2.592592592592592e-06,
|
3362 |
+
"loss": 0.0135,
|
3363 |
+
"step": 4480
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 74.52,
|
3367 |
+
"learning_rate": 2.511574074074074e-06,
|
3368 |
+
"loss": 0.0121,
|
3369 |
+
"step": 4490
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 74.69,
|
3373 |
+
"learning_rate": 2.4305555555555552e-06,
|
3374 |
+
"loss": 0.0173,
|
3375 |
+
"step": 4500
|
3376 |
+
},
|
3377 |
+
{
|
3378 |
+
"epoch": 74.85,
|
3379 |
+
"learning_rate": 2.349537037037037e-06,
|
3380 |
+
"loss": 0.0031,
|
3381 |
+
"step": 4510
|
3382 |
+
},
|
3383 |
+
{
|
3384 |
+
"epoch": 74.99,
|
3385 |
+
"eval_accuracy": 0.8043478260869565,
|
3386 |
+
"eval_loss": 1.7195295095443726,
|
3387 |
+
"eval_runtime": 0.7118,
|
3388 |
+
"eval_samples_per_second": 64.626,
|
3389 |
+
"eval_steps_per_second": 4.215,
|
3390 |
+
"step": 4518
|
3391 |
+
},
|
3392 |
+
{
|
3393 |
+
"epoch": 75.02,
|
3394 |
+
"learning_rate": 2.268518518518518e-06,
|
3395 |
+
"loss": 0.0069,
|
3396 |
+
"step": 4520
|
3397 |
+
},
|
3398 |
+
{
|
3399 |
+
"epoch": 75.19,
|
3400 |
+
"learning_rate": 2.1875e-06,
|
3401 |
+
"loss": 0.0063,
|
3402 |
+
"step": 4530
|
3403 |
+
},
|
3404 |
+
{
|
3405 |
+
"epoch": 75.35,
|
3406 |
+
"learning_rate": 2.106481481481481e-06,
|
3407 |
+
"loss": 0.0288,
|
3408 |
+
"step": 4540
|
3409 |
+
},
|
3410 |
+
{
|
3411 |
+
"epoch": 75.52,
|
3412 |
+
"learning_rate": 2.025462962962963e-06,
|
3413 |
+
"loss": 0.0162,
|
3414 |
+
"step": 4550
|
3415 |
+
},
|
3416 |
+
{
|
3417 |
+
"epoch": 75.68,
|
3418 |
+
"learning_rate": 1.9444444444444444e-06,
|
3419 |
+
"loss": 0.0041,
|
3420 |
+
"step": 4560
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 75.85,
|
3424 |
+
"learning_rate": 1.8634259259259257e-06,
|
3425 |
+
"loss": 0.0087,
|
3426 |
+
"step": 4570
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 76.0,
|
3430 |
+
"eval_accuracy": 0.782608695652174,
|
3431 |
+
"eval_loss": 1.720942735671997,
|
3432 |
+
"eval_runtime": 0.666,
|
3433 |
+
"eval_samples_per_second": 69.067,
|
3434 |
+
"eval_steps_per_second": 4.504,
|
3435 |
+
"step": 4579
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 76.02,
|
3439 |
+
"learning_rate": 1.7824074074074071e-06,
|
3440 |
+
"loss": 0.0145,
|
3441 |
+
"step": 4580
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 76.18,
|
3445 |
+
"learning_rate": 1.7013888888888887e-06,
|
3446 |
+
"loss": 0.0056,
|
3447 |
+
"step": 4590
|
3448 |
+
},
|
3449 |
+
{
|
3450 |
+
"epoch": 76.35,
|
3451 |
+
"learning_rate": 1.62037037037037e-06,
|
3452 |
+
"loss": 0.0108,
|
3453 |
+
"step": 4600
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 76.51,
|
3457 |
+
"learning_rate": 1.5393518518518517e-06,
|
3458 |
+
"loss": 0.0152,
|
3459 |
+
"step": 4610
|
3460 |
+
},
|
3461 |
+
{
|
3462 |
+
"epoch": 76.68,
|
3463 |
+
"learning_rate": 1.458333333333333e-06,
|
3464 |
+
"loss": 0.0126,
|
3465 |
+
"step": 4620
|
3466 |
+
},
|
3467 |
+
{
|
3468 |
+
"epoch": 76.85,
|
3469 |
+
"learning_rate": 1.3773148148148147e-06,
|
3470 |
+
"loss": 0.0219,
|
3471 |
+
"step": 4630
|
3472 |
+
},
|
3473 |
+
{
|
3474 |
+
"epoch": 77.0,
|
3475 |
+
"eval_accuracy": 0.8043478260869565,
|
3476 |
+
"eval_loss": 1.6714533567428589,
|
3477 |
+
"eval_runtime": 0.7121,
|
3478 |
+
"eval_samples_per_second": 64.594,
|
3479 |
+
"eval_steps_per_second": 4.213,
|
3480 |
+
"step": 4639
|
3481 |
+
},
|
3482 |
+
{
|
3483 |
+
"epoch": 77.01,
|
3484 |
+
"learning_rate": 1.296296296296296e-06,
|
3485 |
+
"loss": 0.0078,
|
3486 |
+
"step": 4640
|
3487 |
+
},
|
3488 |
+
{
|
3489 |
+
"epoch": 77.18,
|
3490 |
+
"learning_rate": 1.2152777777777776e-06,
|
3491 |
+
"loss": 0.0186,
|
3492 |
+
"step": 4650
|
3493 |
+
},
|
3494 |
+
{
|
3495 |
+
"epoch": 77.34,
|
3496 |
+
"learning_rate": 1.134259259259259e-06,
|
3497 |
+
"loss": 0.0096,
|
3498 |
+
"step": 4660
|
3499 |
+
},
|
3500 |
+
{
|
3501 |
+
"epoch": 77.51,
|
3502 |
+
"learning_rate": 1.0532407407407406e-06,
|
3503 |
+
"loss": 0.0015,
|
3504 |
+
"step": 4670
|
3505 |
+
},
|
3506 |
+
{
|
3507 |
+
"epoch": 77.68,
|
3508 |
+
"learning_rate": 9.722222222222222e-07,
|
3509 |
+
"loss": 0.005,
|
3510 |
+
"step": 4680
|
3511 |
+
},
|
3512 |
+
{
|
3513 |
+
"epoch": 77.84,
|
3514 |
+
"learning_rate": 8.912037037037036e-07,
|
3515 |
+
"loss": 0.0229,
|
3516 |
+
"step": 4690
|
3517 |
+
},
|
3518 |
+
{
|
3519 |
+
"epoch": 77.99,
|
3520 |
+
"eval_accuracy": 0.8043478260869565,
|
3521 |
+
"eval_loss": 1.6823025941848755,
|
3522 |
+
"eval_runtime": 0.6989,
|
3523 |
+
"eval_samples_per_second": 65.82,
|
3524 |
+
"eval_steps_per_second": 4.293,
|
3525 |
+
"step": 4699
|
3526 |
+
},
|
3527 |
+
{
|
3528 |
+
"epoch": 78.01,
|
3529 |
+
"learning_rate": 8.10185185185185e-07,
|
3530 |
+
"loss": 0.0117,
|
3531 |
+
"step": 4700
|
3532 |
+
},
|
3533 |
+
{
|
3534 |
+
"epoch": 78.17,
|
3535 |
+
"learning_rate": 7.291666666666665e-07,
|
3536 |
+
"loss": 0.0014,
|
3537 |
+
"step": 4710
|
3538 |
+
},
|
3539 |
+
{
|
3540 |
+
"epoch": 78.34,
|
3541 |
+
"learning_rate": 6.48148148148148e-07,
|
3542 |
+
"loss": 0.0039,
|
3543 |
+
"step": 4720
|
3544 |
+
},
|
3545 |
+
{
|
3546 |
+
"epoch": 78.51,
|
3547 |
+
"learning_rate": 5.671296296296295e-07,
|
3548 |
+
"loss": 0.0111,
|
3549 |
+
"step": 4730
|
3550 |
+
},
|
3551 |
+
{
|
3552 |
+
"epoch": 78.67,
|
3553 |
+
"learning_rate": 4.861111111111111e-07,
|
3554 |
+
"loss": 0.0129,
|
3555 |
+
"step": 4740
|
3556 |
+
},
|
3557 |
+
{
|
3558 |
+
"epoch": 78.84,
|
3559 |
+
"learning_rate": 4.050925925925925e-07,
|
3560 |
+
"loss": 0.008,
|
3561 |
+
"step": 4750
|
3562 |
+
},
|
3563 |
+
{
|
3564 |
+
"epoch": 78.99,
|
3565 |
+
"eval_accuracy": 0.8043478260869565,
|
3566 |
+
"eval_loss": 1.6750718355178833,
|
3567 |
+
"eval_runtime": 0.6921,
|
3568 |
+
"eval_samples_per_second": 66.467,
|
3569 |
+
"eval_steps_per_second": 4.335,
|
3570 |
+
"step": 4759
|
3571 |
+
},
|
3572 |
+
{
|
3573 |
+
"epoch": 79.0,
|
3574 |
+
"learning_rate": 3.24074074074074e-07,
|
3575 |
+
"loss": 0.0032,
|
3576 |
+
"step": 4760
|
3577 |
+
},
|
3578 |
+
{
|
3579 |
+
"epoch": 79.17,
|
3580 |
+
"learning_rate": 2.4305555555555555e-07,
|
3581 |
+
"loss": 0.0079,
|
3582 |
+
"step": 4770
|
3583 |
+
},
|
3584 |
+
{
|
3585 |
+
"epoch": 79.34,
|
3586 |
+
"learning_rate": 1.62037037037037e-07,
|
3587 |
+
"loss": 0.008,
|
3588 |
+
"step": 4780
|
3589 |
+
},
|
3590 |
+
{
|
3591 |
+
"epoch": 79.5,
|
3592 |
+
"learning_rate": 8.10185185185185e-08,
|
3593 |
+
"loss": 0.0057,
|
3594 |
+
"step": 4790
|
3595 |
+
},
|
3596 |
+
{
|
3597 |
+
"epoch": 79.67,
|
3598 |
+
"learning_rate": 0.0,
|
3599 |
+
"loss": 0.0051,
|
3600 |
+
"step": 4800
|
3601 |
+
},
|
3602 |
+
{
|
3603 |
+
"epoch": 79.67,
|
3604 |
+
"eval_accuracy": 0.8043478260869565,
|
3605 |
+
"eval_loss": 1.675818681716919,
|
3606 |
+
"eval_runtime": 0.6446,
|
3607 |
+
"eval_samples_per_second": 71.357,
|
3608 |
+
"eval_steps_per_second": 4.654,
|
3609 |
+
"step": 4800
|
3610 |
+
},
|
3611 |
+
{
|
3612 |
+
"epoch": 79.67,
|
3613 |
+
"step": 4800,
|
3614 |
+
"total_flos": 2.3777433087459287e+19,
|
3615 |
+
"train_loss": 0.12199072747869649,
|
3616 |
+
"train_runtime": 7091.3369,
|
3617 |
+
"train_samples_per_second": 43.467,
|
3618 |
+
"train_steps_per_second": 0.677
|
3619 |
+
}
|
3620 |
+
],
|
3621 |
+
"logging_steps": 10,
|
3622 |
+
"max_steps": 4800,
|
3623 |
+
"num_input_tokens_seen": 0,
|
3624 |
+
"num_train_epochs": 80,
|
3625 |
+
"save_steps": 500,
|
3626 |
+
"total_flos": 2.3777433087459287e+19,
|
3627 |
+
"train_batch_size": 16,
|
3628 |
+
"trial_name": null,
|
3629 |
+
"trial_params": null
|
3630 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cd3fa58ea61f8a33971ebc2d2aec0e08e3cf3a5cfd744a4341c50305fff40a9
|
3 |
+
size 4728
|