lombardata
commited on
Commit
•
4834c01
1
Parent(s):
840b521
Evaluation on the test set completed on 2024_11_03.
Browse files- README.md +151 -0
- all_results.json +16 -0
- logs/events.out.tfevents.1730642710.datavisu2 +2 -2
- logs/events.out.tfevents.1730673734.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +11 -0
- train_results.json +9 -0
- trainer_state.json +1325 -0
README.md
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/dinov2-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: drone-DinoVdeau-produttoria_binary-binary-large-2024_11_03-batch-size64_freeze
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# drone-DinoVdeau-produttoria_binary-binary-large-2024_11_03-batch-size64_freeze
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2854
|
21 |
+
- F1 Micro: 0.8468
|
22 |
+
- F1 Macro: 0.6351
|
23 |
+
- Accuracy: 0.2786
|
24 |
+
- Learning Rate: 0.0000
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.001
|
44 |
+
- train_batch_size: 64
|
45 |
+
- eval_batch_size: 64
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 150
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy | Rate |
|
55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|:------:|
|
56 |
+
| No log | 1.0 | 181 | 0.3236 | 0.8262 | 0.5774 | 0.2630 | 0.001 |
|
57 |
+
| No log | 2.0 | 362 | 0.3146 | 0.8379 | 0.6199 | 0.2412 | 0.001 |
|
58 |
+
| 0.3995 | 3.0 | 543 | 0.3090 | 0.8398 | 0.6044 | 0.2555 | 0.001 |
|
59 |
+
| 0.3995 | 4.0 | 724 | 0.3074 | 0.8349 | 0.6003 | 0.2562 | 0.001 |
|
60 |
+
| 0.3995 | 5.0 | 905 | 0.3039 | 0.8406 | 0.6248 | 0.2516 | 0.001 |
|
61 |
+
| 0.3299 | 6.0 | 1086 | 0.3060 | 0.8420 | 0.6225 | 0.2596 | 0.001 |
|
62 |
+
| 0.3299 | 7.0 | 1267 | 0.3014 | 0.8387 | 0.5955 | 0.2820 | 0.001 |
|
63 |
+
| 0.3299 | 8.0 | 1448 | 0.3013 | 0.8391 | 0.5975 | 0.2703 | 0.001 |
|
64 |
+
| 0.3216 | 9.0 | 1629 | 0.3010 | 0.8407 | 0.5974 | 0.2841 | 0.001 |
|
65 |
+
| 0.3216 | 10.0 | 1810 | 0.3007 | 0.8376 | 0.5938 | 0.2711 | 0.001 |
|
66 |
+
| 0.3216 | 11.0 | 1991 | 0.3036 | 0.8349 | 0.5762 | 0.2773 | 0.001 |
|
67 |
+
| 0.3167 | 12.0 | 2172 | 0.3013 | 0.8385 | 0.6115 | 0.2674 | 0.001 |
|
68 |
+
| 0.3167 | 13.0 | 2353 | 0.2978 | 0.8421 | 0.6146 | 0.2648 | 0.001 |
|
69 |
+
| 0.315 | 14.0 | 2534 | 0.2977 | 0.8400 | 0.6059 | 0.2734 | 0.001 |
|
70 |
+
| 0.315 | 15.0 | 2715 | 0.2981 | 0.8434 | 0.6075 | 0.2666 | 0.001 |
|
71 |
+
| 0.315 | 16.0 | 2896 | 0.2974 | 0.8394 | 0.5933 | 0.2747 | 0.001 |
|
72 |
+
| 0.3147 | 17.0 | 3077 | 0.2984 | 0.8438 | 0.6147 | 0.2664 | 0.001 |
|
73 |
+
| 0.3147 | 18.0 | 3258 | 0.3023 | 0.8356 | 0.5804 | 0.2763 | 0.001 |
|
74 |
+
| 0.3147 | 19.0 | 3439 | 0.2985 | 0.8424 | 0.6159 | 0.2739 | 0.001 |
|
75 |
+
| 0.3122 | 20.0 | 3620 | 0.2968 | 0.8412 | 0.5984 | 0.2807 | 0.001 |
|
76 |
+
| 0.3122 | 21.0 | 3801 | 0.3005 | 0.8419 | 0.6060 | 0.2703 | 0.001 |
|
77 |
+
| 0.3122 | 22.0 | 3982 | 0.2982 | 0.8375 | 0.5804 | 0.2747 | 0.001 |
|
78 |
+
| 0.3149 | 23.0 | 4163 | 0.2939 | 0.8436 | 0.6152 | 0.2781 | 0.001 |
|
79 |
+
| 0.3149 | 24.0 | 4344 | 0.2948 | 0.8453 | 0.6229 | 0.2760 | 0.001 |
|
80 |
+
| 0.3118 | 25.0 | 4525 | 0.2968 | 0.8427 | 0.6103 | 0.2737 | 0.001 |
|
81 |
+
| 0.3118 | 26.0 | 4706 | 0.2956 | 0.8421 | 0.6045 | 0.2755 | 0.001 |
|
82 |
+
| 0.3118 | 27.0 | 4887 | 0.2959 | 0.8438 | 0.6115 | 0.2765 | 0.001 |
|
83 |
+
| 0.3126 | 28.0 | 5068 | 0.2955 | 0.8447 | 0.6191 | 0.2693 | 0.001 |
|
84 |
+
| 0.3126 | 29.0 | 5249 | 0.3011 | 0.8438 | 0.6216 | 0.2664 | 0.001 |
|
85 |
+
| 0.3126 | 30.0 | 5430 | 0.2921 | 0.8437 | 0.6025 | 0.2810 | 0.0001 |
|
86 |
+
| 0.3093 | 31.0 | 5611 | 0.2904 | 0.8439 | 0.6072 | 0.2812 | 0.0001 |
|
87 |
+
| 0.3093 | 32.0 | 5792 | 0.2903 | 0.8437 | 0.6112 | 0.2810 | 0.0001 |
|
88 |
+
| 0.3093 | 33.0 | 5973 | 0.2889 | 0.8462 | 0.6202 | 0.2854 | 0.0001 |
|
89 |
+
| 0.3049 | 34.0 | 6154 | 0.2896 | 0.8446 | 0.6151 | 0.2862 | 0.0001 |
|
90 |
+
| 0.3049 | 35.0 | 6335 | 0.2887 | 0.8449 | 0.6112 | 0.2867 | 0.0001 |
|
91 |
+
| 0.3012 | 36.0 | 6516 | 0.2889 | 0.8447 | 0.6120 | 0.2836 | 0.0001 |
|
92 |
+
| 0.3012 | 37.0 | 6697 | 0.2883 | 0.8476 | 0.6256 | 0.2867 | 0.0001 |
|
93 |
+
| 0.3012 | 38.0 | 6878 | 0.2905 | 0.8453 | 0.6057 | 0.2825 | 0.0001 |
|
94 |
+
| 0.299 | 39.0 | 7059 | 0.2878 | 0.8471 | 0.6254 | 0.2854 | 0.0001 |
|
95 |
+
| 0.299 | 40.0 | 7240 | 0.2886 | 0.8468 | 0.6223 | 0.2810 | 0.0001 |
|
96 |
+
| 0.299 | 41.0 | 7421 | 0.2877 | 0.8473 | 0.6261 | 0.2843 | 0.0001 |
|
97 |
+
| 0.2989 | 42.0 | 7602 | 0.2878 | 0.8477 | 0.6199 | 0.2856 | 0.0001 |
|
98 |
+
| 0.2989 | 43.0 | 7783 | 0.2872 | 0.8479 | 0.6288 | 0.2830 | 0.0001 |
|
99 |
+
| 0.2989 | 44.0 | 7964 | 0.2868 | 0.8464 | 0.6190 | 0.2841 | 0.0001 |
|
100 |
+
| 0.2983 | 45.0 | 8145 | 0.2870 | 0.8463 | 0.6236 | 0.2838 | 0.0001 |
|
101 |
+
| 0.2983 | 46.0 | 8326 | 0.2868 | 0.8460 | 0.6151 | 0.2825 | 0.0001 |
|
102 |
+
| 0.298 | 47.0 | 8507 | 0.2872 | 0.8462 | 0.6211 | 0.2846 | 0.0001 |
|
103 |
+
| 0.298 | 48.0 | 8688 | 0.2866 | 0.8467 | 0.6231 | 0.2836 | 0.0001 |
|
104 |
+
| 0.298 | 49.0 | 8869 | 0.2863 | 0.8460 | 0.6161 | 0.2859 | 0.0001 |
|
105 |
+
| 0.2965 | 50.0 | 9050 | 0.2864 | 0.8483 | 0.6255 | 0.2846 | 0.0001 |
|
106 |
+
| 0.2965 | 51.0 | 9231 | 0.2891 | 0.8486 | 0.6278 | 0.2849 | 0.0001 |
|
107 |
+
| 0.2965 | 52.0 | 9412 | 0.2856 | 0.8464 | 0.6255 | 0.2851 | 0.0001 |
|
108 |
+
| 0.2956 | 53.0 | 9593 | 0.2872 | 0.8490 | 0.6458 | 0.2789 | 0.0001 |
|
109 |
+
| 0.2956 | 54.0 | 9774 | 0.2856 | 0.8477 | 0.6244 | 0.2903 | 0.0001 |
|
110 |
+
| 0.2956 | 55.0 | 9955 | 0.2857 | 0.8475 | 0.6340 | 0.2846 | 0.0001 |
|
111 |
+
| 0.2958 | 56.0 | 10136 | 0.2862 | 0.8466 | 0.6241 | 0.2867 | 0.0001 |
|
112 |
+
| 0.2958 | 57.0 | 10317 | 0.2871 | 0.8454 | 0.6249 | 0.2862 | 0.0001 |
|
113 |
+
| 0.2958 | 58.0 | 10498 | 0.2858 | 0.8492 | 0.6334 | 0.2812 | 0.0001 |
|
114 |
+
| 0.2954 | 59.0 | 10679 | 0.2862 | 0.8468 | 0.6178 | 0.2888 | 1e-05 |
|
115 |
+
| 0.2954 | 60.0 | 10860 | 0.2847 | 0.8485 | 0.6276 | 0.2854 | 1e-05 |
|
116 |
+
| 0.2923 | 61.0 | 11041 | 0.2849 | 0.8480 | 0.6224 | 0.2830 | 1e-05 |
|
117 |
+
| 0.2923 | 62.0 | 11222 | 0.2855 | 0.8469 | 0.6248 | 0.2843 | 1e-05 |
|
118 |
+
| 0.2923 | 63.0 | 11403 | 0.2849 | 0.8489 | 0.6275 | 0.2828 | 1e-05 |
|
119 |
+
| 0.2918 | 64.0 | 11584 | 0.2846 | 0.8475 | 0.6371 | 0.2823 | 1e-05 |
|
120 |
+
| 0.2918 | 65.0 | 11765 | 0.2860 | 0.8468 | 0.6241 | 0.2869 | 1e-05 |
|
121 |
+
| 0.2918 | 66.0 | 11946 | 0.2847 | 0.8481 | 0.6347 | 0.2841 | 1e-05 |
|
122 |
+
| 0.2906 | 67.0 | 12127 | 0.2853 | 0.8488 | 0.6287 | 0.2854 | 1e-05 |
|
123 |
+
| 0.2906 | 68.0 | 12308 | 0.2853 | 0.8480 | 0.6321 | 0.2867 | 1e-05 |
|
124 |
+
| 0.2906 | 69.0 | 12489 | 0.2848 | 0.8477 | 0.6397 | 0.2836 | 1e-05 |
|
125 |
+
| 0.2918 | 70.0 | 12670 | 0.2853 | 0.8492 | 0.6381 | 0.2823 | 1e-05 |
|
126 |
+
| 0.2918 | 71.0 | 12851 | 0.2851 | 0.8476 | 0.6325 | 0.2882 | 0.0000 |
|
127 |
+
| 0.2918 | 72.0 | 13032 | 0.2845 | 0.8474 | 0.6236 | 0.2849 | 0.0000 |
|
128 |
+
| 0.2918 | 73.0 | 13213 | 0.2845 | 0.8476 | 0.6333 | 0.2812 | 0.0000 |
|
129 |
+
| 0.2918 | 74.0 | 13394 | 0.2845 | 0.8466 | 0.6300 | 0.2828 | 0.0000 |
|
130 |
+
| 0.2913 | 75.0 | 13575 | 0.2851 | 0.8474 | 0.6235 | 0.2820 | 0.0000 |
|
131 |
+
| 0.2913 | 76.0 | 13756 | 0.2860 | 0.8473 | 0.6186 | 0.2880 | 0.0000 |
|
132 |
+
| 0.2913 | 77.0 | 13937 | 0.2858 | 0.8459 | 0.6173 | 0.2856 | 0.0000 |
|
133 |
+
| 0.2913 | 78.0 | 14118 | 0.2844 | 0.8481 | 0.6326 | 0.2843 | 0.0000 |
|
134 |
+
| 0.2913 | 79.0 | 14299 | 0.2871 | 0.8472 | 0.6179 | 0.2875 | 0.0000 |
|
135 |
+
| 0.2913 | 80.0 | 14480 | 0.2848 | 0.8477 | 0.6287 | 0.2838 | 0.0000 |
|
136 |
+
| 0.2915 | 81.0 | 14661 | 0.2848 | 0.8490 | 0.6305 | 0.2854 | 0.0000 |
|
137 |
+
| 0.2915 | 82.0 | 14842 | 0.2851 | 0.8480 | 0.6394 | 0.2859 | 0.0000 |
|
138 |
+
| 0.2913 | 83.0 | 15023 | 0.2846 | 0.8488 | 0.6255 | 0.2856 | 0.0000 |
|
139 |
+
| 0.2913 | 84.0 | 15204 | 0.2857 | 0.8482 | 0.6458 | 0.2833 | 0.0000 |
|
140 |
+
| 0.2913 | 85.0 | 15385 | 0.2855 | 0.8488 | 0.6340 | 0.2812 | 0.0000 |
|
141 |
+
| 0.2922 | 86.0 | 15566 | 0.2849 | 0.8480 | 0.6363 | 0.2859 | 0.0000 |
|
142 |
+
| 0.2922 | 87.0 | 15747 | 0.2845 | 0.8474 | 0.6328 | 0.2851 | 0.0000 |
|
143 |
+
| 0.2922 | 88.0 | 15928 | 0.2854 | 0.8478 | 0.6371 | 0.2812 | 0.0000 |
|
144 |
+
|
145 |
+
|
146 |
+
### Framework versions
|
147 |
+
|
148 |
+
- Transformers 4.41.0
|
149 |
+
- Pytorch 2.5.0+cu124
|
150 |
+
- Datasets 3.0.2
|
151 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 88.0,
|
3 |
+
"eval_accuracy": 0.2786458333333333,
|
4 |
+
"eval_f1_macro": 0.6350734566442581,
|
5 |
+
"eval_f1_micro": 0.8467861336600807,
|
6 |
+
"eval_loss": 0.28541260957717896,
|
7 |
+
"eval_runtime": 76.7857,
|
8 |
+
"eval_samples_per_second": 50.009,
|
9 |
+
"eval_steps_per_second": 0.781,
|
10 |
+
"learning_rate": 1.0000000000000002e-07,
|
11 |
+
"total_flos": 1.500719176717825e+20,
|
12 |
+
"train_loss": 0.3047179739897961,
|
13 |
+
"train_runtime": 30841.8451,
|
14 |
+
"train_samples_per_second": 56.038,
|
15 |
+
"train_steps_per_second": 0.88
|
16 |
+
}
|
logs/events.out.tfevents.1730642710.datavisu2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1153ede07b604838b374d477545613ec02b5fef26fc96b8b0af1ba3fabb69be
|
3 |
+
size 55905
|
logs/events.out.tfevents.1730673734.datavisu2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d9f10a9c09da967e73fe949bac0d9f1f288eca3b0e5fa21454b3fe17c038fda
|
3 |
+
size 40
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1222958756
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ec6d0a15d562cc3f4d35744dd773595c117cff73cc265a352ca85718ba80955
|
3 |
size 1222958756
|
test_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 88.0,
|
3 |
+
"eval_accuracy": 0.2786458333333333,
|
4 |
+
"eval_f1_macro": 0.6350734566442581,
|
5 |
+
"eval_f1_micro": 0.8467861336600807,
|
6 |
+
"eval_loss": 0.28541260957717896,
|
7 |
+
"eval_runtime": 76.7857,
|
8 |
+
"eval_samples_per_second": 50.009,
|
9 |
+
"eval_steps_per_second": 0.781,
|
10 |
+
"learning_rate": 1.0000000000000002e-07
|
11 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 88.0,
|
3 |
+
"learning_rate": 1.0000000000000002e-07,
|
4 |
+
"total_flos": 1.500719176717825e+20,
|
5 |
+
"train_loss": 0.3047179739897961,
|
6 |
+
"train_runtime": 30841.8451,
|
7 |
+
"train_samples_per_second": 56.038,
|
8 |
+
"train_steps_per_second": 0.88
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.28438833355903625,
|
3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-produttoria_binary-binary-large-2024_11_03-batch-size64_freeze/checkpoint-14118",
|
4 |
+
"epoch": 88.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 15928,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.2630072840790843,
|
14 |
+
"eval_f1_macro": 0.5774239185038708,
|
15 |
+
"eval_f1_micro": 0.8262109753225342,
|
16 |
+
"eval_loss": 0.3235681354999542,
|
17 |
+
"eval_runtime": 79.5924,
|
18 |
+
"eval_samples_per_second": 48.296,
|
19 |
+
"eval_steps_per_second": 0.766,
|
20 |
+
"learning_rate": 0.001,
|
21 |
+
"step": 181
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 2.0,
|
25 |
+
"eval_accuracy": 0.24115504682622269,
|
26 |
+
"eval_f1_macro": 0.6199165901601139,
|
27 |
+
"eval_f1_micro": 0.8378565084377776,
|
28 |
+
"eval_loss": 0.3146470785140991,
|
29 |
+
"eval_runtime": 78.3589,
|
30 |
+
"eval_samples_per_second": 49.056,
|
31 |
+
"eval_steps_per_second": 0.778,
|
32 |
+
"learning_rate": 0.001,
|
33 |
+
"step": 362
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.7624309392265194,
|
37 |
+
"grad_norm": 0.39133042097091675,
|
38 |
+
"learning_rate": 0.001,
|
39 |
+
"loss": 0.3995,
|
40 |
+
"step": 500
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"eval_accuracy": 0.2554630593132154,
|
45 |
+
"eval_f1_macro": 0.6043570009634397,
|
46 |
+
"eval_f1_micro": 0.8398465111582348,
|
47 |
+
"eval_loss": 0.3090434670448303,
|
48 |
+
"eval_runtime": 77.1271,
|
49 |
+
"eval_samples_per_second": 49.84,
|
50 |
+
"eval_steps_per_second": 0.791,
|
51 |
+
"learning_rate": 0.001,
|
52 |
+
"step": 543
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 4.0,
|
56 |
+
"eval_accuracy": 0.25624349635796045,
|
57 |
+
"eval_f1_macro": 0.600278483167516,
|
58 |
+
"eval_f1_micro": 0.8348980169243037,
|
59 |
+
"eval_loss": 0.30735355615615845,
|
60 |
+
"eval_runtime": 77.9527,
|
61 |
+
"eval_samples_per_second": 49.312,
|
62 |
+
"eval_steps_per_second": 0.783,
|
63 |
+
"learning_rate": 0.001,
|
64 |
+
"step": 724
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"eval_accuracy": 0.2515608740894901,
|
69 |
+
"eval_f1_macro": 0.6247746971203368,
|
70 |
+
"eval_f1_micro": 0.8405948994360434,
|
71 |
+
"eval_loss": 0.30385810136795044,
|
72 |
+
"eval_runtime": 79.3747,
|
73 |
+
"eval_samples_per_second": 48.429,
|
74 |
+
"eval_steps_per_second": 0.769,
|
75 |
+
"learning_rate": 0.001,
|
76 |
+
"step": 905
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.524861878453039,
|
80 |
+
"grad_norm": 0.30673518776893616,
|
81 |
+
"learning_rate": 0.001,
|
82 |
+
"loss": 0.3299,
|
83 |
+
"step": 1000
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"eval_accuracy": 0.2596253902185224,
|
88 |
+
"eval_f1_macro": 0.6225111439021958,
|
89 |
+
"eval_f1_micro": 0.841987466427932,
|
90 |
+
"eval_loss": 0.3059956729412079,
|
91 |
+
"eval_runtime": 78.3475,
|
92 |
+
"eval_samples_per_second": 49.063,
|
93 |
+
"eval_steps_per_second": 0.779,
|
94 |
+
"learning_rate": 0.001,
|
95 |
+
"step": 1086
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 7.0,
|
99 |
+
"eval_accuracy": 0.28199791883454733,
|
100 |
+
"eval_f1_macro": 0.5954695621655504,
|
101 |
+
"eval_f1_micro": 0.8387498056289846,
|
102 |
+
"eval_loss": 0.3013758361339569,
|
103 |
+
"eval_runtime": 77.8519,
|
104 |
+
"eval_samples_per_second": 49.376,
|
105 |
+
"eval_steps_per_second": 0.784,
|
106 |
+
"learning_rate": 0.001,
|
107 |
+
"step": 1267
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_accuracy": 0.2702913631633715,
|
112 |
+
"eval_f1_macro": 0.5974832028652961,
|
113 |
+
"eval_f1_micro": 0.8390550208451284,
|
114 |
+
"eval_loss": 0.30131709575653076,
|
115 |
+
"eval_runtime": 76.3356,
|
116 |
+
"eval_samples_per_second": 50.357,
|
117 |
+
"eval_steps_per_second": 0.799,
|
118 |
+
"learning_rate": 0.001,
|
119 |
+
"step": 1448
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.287292817679559,
|
123 |
+
"grad_norm": 0.2473623901605606,
|
124 |
+
"learning_rate": 0.001,
|
125 |
+
"loss": 0.3216,
|
126 |
+
"step": 1500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_accuracy": 0.28407908428720086,
|
131 |
+
"eval_f1_macro": 0.5974259992816957,
|
132 |
+
"eval_f1_micro": 0.8406665130922214,
|
133 |
+
"eval_loss": 0.30098479986190796,
|
134 |
+
"eval_runtime": 76.6263,
|
135 |
+
"eval_samples_per_second": 50.166,
|
136 |
+
"eval_steps_per_second": 0.796,
|
137 |
+
"learning_rate": 0.001,
|
138 |
+
"step": 1629
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 10.0,
|
142 |
+
"eval_accuracy": 0.27107180020811655,
|
143 |
+
"eval_f1_macro": 0.5937940362628795,
|
144 |
+
"eval_f1_micro": 0.8376187886791475,
|
145 |
+
"eval_loss": 0.30072343349456787,
|
146 |
+
"eval_runtime": 78.1999,
|
147 |
+
"eval_samples_per_second": 49.156,
|
148 |
+
"eval_steps_per_second": 0.78,
|
149 |
+
"learning_rate": 0.001,
|
150 |
+
"step": 1810
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 11.0,
|
154 |
+
"eval_accuracy": 0.277315296566077,
|
155 |
+
"eval_f1_macro": 0.5761905737205768,
|
156 |
+
"eval_f1_micro": 0.8348592565387339,
|
157 |
+
"eval_loss": 0.3035621643066406,
|
158 |
+
"eval_runtime": 77.9385,
|
159 |
+
"eval_samples_per_second": 49.321,
|
160 |
+
"eval_steps_per_second": 0.783,
|
161 |
+
"learning_rate": 0.001,
|
162 |
+
"step": 1991
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 11.049723756906078,
|
166 |
+
"grad_norm": 0.24565815925598145,
|
167 |
+
"learning_rate": 0.001,
|
168 |
+
"loss": 0.3167,
|
169 |
+
"step": 2000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 12.0,
|
173 |
+
"eval_accuracy": 0.26742976066597296,
|
174 |
+
"eval_f1_macro": 0.6114755503631268,
|
175 |
+
"eval_f1_micro": 0.838466245156027,
|
176 |
+
"eval_loss": 0.3012838363647461,
|
177 |
+
"eval_runtime": 77.6902,
|
178 |
+
"eval_samples_per_second": 49.479,
|
179 |
+
"eval_steps_per_second": 0.785,
|
180 |
+
"learning_rate": 0.001,
|
181 |
+
"step": 2172
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 13.0,
|
185 |
+
"eval_accuracy": 0.2648283038501561,
|
186 |
+
"eval_f1_macro": 0.6145726431106396,
|
187 |
+
"eval_f1_micro": 0.8421213122252433,
|
188 |
+
"eval_loss": 0.29778778553009033,
|
189 |
+
"eval_runtime": 77.1253,
|
190 |
+
"eval_samples_per_second": 49.841,
|
191 |
+
"eval_steps_per_second": 0.791,
|
192 |
+
"learning_rate": 0.001,
|
193 |
+
"step": 2353
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 13.812154696132596,
|
197 |
+
"grad_norm": 0.2421799898147583,
|
198 |
+
"learning_rate": 0.001,
|
199 |
+
"loss": 0.315,
|
200 |
+
"step": 2500
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 14.0,
|
204 |
+
"eval_accuracy": 0.27341311134235174,
|
205 |
+
"eval_f1_macro": 0.605884177295118,
|
206 |
+
"eval_f1_micro": 0.8399742101869762,
|
207 |
+
"eval_loss": 0.29774588346481323,
|
208 |
+
"eval_runtime": 76.619,
|
209 |
+
"eval_samples_per_second": 50.17,
|
210 |
+
"eval_steps_per_second": 0.796,
|
211 |
+
"learning_rate": 0.001,
|
212 |
+
"step": 2534
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 15.0,
|
216 |
+
"eval_accuracy": 0.2666493236212279,
|
217 |
+
"eval_f1_macro": 0.6074624445346274,
|
218 |
+
"eval_f1_micro": 0.8433503513117323,
|
219 |
+
"eval_loss": 0.29809942841529846,
|
220 |
+
"eval_runtime": 77.2846,
|
221 |
+
"eval_samples_per_second": 49.738,
|
222 |
+
"eval_steps_per_second": 0.789,
|
223 |
+
"learning_rate": 0.001,
|
224 |
+
"step": 2715
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 16.0,
|
228 |
+
"eval_accuracy": 0.27471383975026015,
|
229 |
+
"eval_f1_macro": 0.5932952143692389,
|
230 |
+
"eval_f1_micro": 0.8394100355835181,
|
231 |
+
"eval_loss": 0.29744812846183777,
|
232 |
+
"eval_runtime": 77.1329,
|
233 |
+
"eval_samples_per_second": 49.836,
|
234 |
+
"eval_steps_per_second": 0.791,
|
235 |
+
"learning_rate": 0.001,
|
236 |
+
"step": 2896
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 16.574585635359117,
|
240 |
+
"grad_norm": 0.2012377828359604,
|
241 |
+
"learning_rate": 0.001,
|
242 |
+
"loss": 0.3147,
|
243 |
+
"step": 3000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 17.0,
|
247 |
+
"eval_accuracy": 0.2663891779396462,
|
248 |
+
"eval_f1_macro": 0.6146867059353278,
|
249 |
+
"eval_f1_micro": 0.8437578624264077,
|
250 |
+
"eval_loss": 0.2983638644218445,
|
251 |
+
"eval_runtime": 77.7728,
|
252 |
+
"eval_samples_per_second": 49.426,
|
253 |
+
"eval_steps_per_second": 0.784,
|
254 |
+
"learning_rate": 0.001,
|
255 |
+
"step": 3077
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 18.0,
|
259 |
+
"eval_accuracy": 0.2762747138397503,
|
260 |
+
"eval_f1_macro": 0.5803903225868541,
|
261 |
+
"eval_f1_micro": 0.8356339535005088,
|
262 |
+
"eval_loss": 0.3023049235343933,
|
263 |
+
"eval_runtime": 77.2379,
|
264 |
+
"eval_samples_per_second": 49.768,
|
265 |
+
"eval_steps_per_second": 0.79,
|
266 |
+
"learning_rate": 0.001,
|
267 |
+
"step": 3258
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 19.0,
|
271 |
+
"eval_accuracy": 0.2739334027055151,
|
272 |
+
"eval_f1_macro": 0.6158875389283108,
|
273 |
+
"eval_f1_micro": 0.8423529411764706,
|
274 |
+
"eval_loss": 0.2984697222709656,
|
275 |
+
"eval_runtime": 76.7734,
|
276 |
+
"eval_samples_per_second": 50.069,
|
277 |
+
"eval_steps_per_second": 0.795,
|
278 |
+
"learning_rate": 0.001,
|
279 |
+
"step": 3439
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 19.337016574585636,
|
283 |
+
"grad_norm": 0.20086592435836792,
|
284 |
+
"learning_rate": 0.001,
|
285 |
+
"loss": 0.3122,
|
286 |
+
"step": 3500
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 20.0,
|
290 |
+
"eval_accuracy": 0.28069719042663893,
|
291 |
+
"eval_f1_macro": 0.5984147849283556,
|
292 |
+
"eval_f1_micro": 0.8411767731317183,
|
293 |
+
"eval_loss": 0.29680272936820984,
|
294 |
+
"eval_runtime": 77.2197,
|
295 |
+
"eval_samples_per_second": 49.78,
|
296 |
+
"eval_steps_per_second": 0.79,
|
297 |
+
"learning_rate": 0.001,
|
298 |
+
"step": 3620
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 21.0,
|
302 |
+
"eval_accuracy": 0.2702913631633715,
|
303 |
+
"eval_f1_macro": 0.6060492619397649,
|
304 |
+
"eval_f1_micro": 0.8418969323285377,
|
305 |
+
"eval_loss": 0.30051520466804504,
|
306 |
+
"eval_runtime": 76.7663,
|
307 |
+
"eval_samples_per_second": 50.074,
|
308 |
+
"eval_steps_per_second": 0.795,
|
309 |
+
"learning_rate": 0.001,
|
310 |
+
"step": 3801
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 22.0,
|
314 |
+
"eval_accuracy": 0.27471383975026015,
|
315 |
+
"eval_f1_macro": 0.580353532272699,
|
316 |
+
"eval_f1_micro": 0.8374817746302854,
|
317 |
+
"eval_loss": 0.29818177223205566,
|
318 |
+
"eval_runtime": 77.0688,
|
319 |
+
"eval_samples_per_second": 49.877,
|
320 |
+
"eval_steps_per_second": 0.792,
|
321 |
+
"learning_rate": 0.001,
|
322 |
+
"step": 3982
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 22.099447513812155,
|
326 |
+
"grad_norm": 0.21317744255065918,
|
327 |
+
"learning_rate": 0.001,
|
328 |
+
"loss": 0.3149,
|
329 |
+
"step": 4000
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 23.0,
|
333 |
+
"eval_accuracy": 0.27809573361082207,
|
334 |
+
"eval_f1_macro": 0.615237110287355,
|
335 |
+
"eval_f1_micro": 0.8436262061960386,
|
336 |
+
"eval_loss": 0.29393449425697327,
|
337 |
+
"eval_runtime": 76.8217,
|
338 |
+
"eval_samples_per_second": 50.038,
|
339 |
+
"eval_steps_per_second": 0.794,
|
340 |
+
"learning_rate": 0.001,
|
341 |
+
"step": 4163
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 24.0,
|
345 |
+
"eval_accuracy": 0.27601456815816855,
|
346 |
+
"eval_f1_macro": 0.6228721497006335,
|
347 |
+
"eval_f1_micro": 0.8453232862164007,
|
348 |
+
"eval_loss": 0.2948347330093384,
|
349 |
+
"eval_runtime": 77.3517,
|
350 |
+
"eval_samples_per_second": 49.695,
|
351 |
+
"eval_steps_per_second": 0.789,
|
352 |
+
"learning_rate": 0.001,
|
353 |
+
"step": 4344
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 24.861878453038674,
|
357 |
+
"grad_norm": 0.17206734418869019,
|
358 |
+
"learning_rate": 0.001,
|
359 |
+
"loss": 0.3118,
|
360 |
+
"step": 4500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 25.0,
|
364 |
+
"eval_accuracy": 0.2736732570239334,
|
365 |
+
"eval_f1_macro": 0.610255370235793,
|
366 |
+
"eval_f1_micro": 0.8427456149244652,
|
367 |
+
"eval_loss": 0.29676035046577454,
|
368 |
+
"eval_runtime": 77.1567,
|
369 |
+
"eval_samples_per_second": 49.821,
|
370 |
+
"eval_steps_per_second": 0.791,
|
371 |
+
"learning_rate": 0.001,
|
372 |
+
"step": 4525
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"epoch": 26.0,
|
376 |
+
"eval_accuracy": 0.2754942767950052,
|
377 |
+
"eval_f1_macro": 0.6045462014226007,
|
378 |
+
"eval_f1_micro": 0.8420542140997499,
|
379 |
+
"eval_loss": 0.2955995500087738,
|
380 |
+
"eval_runtime": 77.6213,
|
381 |
+
"eval_samples_per_second": 49.522,
|
382 |
+
"eval_steps_per_second": 0.786,
|
383 |
+
"learning_rate": 0.001,
|
384 |
+
"step": 4706
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 27.0,
|
388 |
+
"eval_accuracy": 0.27653485952133194,
|
389 |
+
"eval_f1_macro": 0.6115221375683754,
|
390 |
+
"eval_f1_micro": 0.8437684356323902,
|
391 |
+
"eval_loss": 0.29585039615631104,
|
392 |
+
"eval_runtime": 76.6184,
|
393 |
+
"eval_samples_per_second": 50.171,
|
394 |
+
"eval_steps_per_second": 0.796,
|
395 |
+
"learning_rate": 0.001,
|
396 |
+
"step": 4887
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 27.624309392265193,
|
400 |
+
"grad_norm": 0.1697782576084137,
|
401 |
+
"learning_rate": 0.001,
|
402 |
+
"loss": 0.3126,
|
403 |
+
"step": 5000
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"epoch": 28.0,
|
407 |
+
"eval_accuracy": 0.26925078043704476,
|
408 |
+
"eval_f1_macro": 0.6191186747828321,
|
409 |
+
"eval_f1_micro": 0.8446938104986479,
|
410 |
+
"eval_loss": 0.295540988445282,
|
411 |
+
"eval_runtime": 76.9629,
|
412 |
+
"eval_samples_per_second": 49.946,
|
413 |
+
"eval_steps_per_second": 0.793,
|
414 |
+
"learning_rate": 0.001,
|
415 |
+
"step": 5068
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 29.0,
|
419 |
+
"eval_accuracy": 0.2663891779396462,
|
420 |
+
"eval_f1_macro": 0.6215750043898619,
|
421 |
+
"eval_f1_micro": 0.8437664387164651,
|
422 |
+
"eval_loss": 0.3010655343532562,
|
423 |
+
"eval_runtime": 77.7511,
|
424 |
+
"eval_samples_per_second": 49.44,
|
425 |
+
"eval_steps_per_second": 0.785,
|
426 |
+
"learning_rate": 0.001,
|
427 |
+
"step": 5249
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"epoch": 30.0,
|
431 |
+
"eval_accuracy": 0.2809573361082206,
|
432 |
+
"eval_f1_macro": 0.6025311078598518,
|
433 |
+
"eval_f1_micro": 0.8437435686355217,
|
434 |
+
"eval_loss": 0.29214760661125183,
|
435 |
+
"eval_runtime": 76.285,
|
436 |
+
"eval_samples_per_second": 50.39,
|
437 |
+
"eval_steps_per_second": 0.8,
|
438 |
+
"learning_rate": 0.0001,
|
439 |
+
"step": 5430
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 30.386740331491712,
|
443 |
+
"grad_norm": 0.15570667386054993,
|
444 |
+
"learning_rate": 0.0001,
|
445 |
+
"loss": 0.3093,
|
446 |
+
"step": 5500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 31.0,
|
450 |
+
"eval_accuracy": 0.28121748178980227,
|
451 |
+
"eval_f1_macro": 0.6071651131848005,
|
452 |
+
"eval_f1_micro": 0.8439103638567266,
|
453 |
+
"eval_loss": 0.29040178656578064,
|
454 |
+
"eval_runtime": 80.1919,
|
455 |
+
"eval_samples_per_second": 47.935,
|
456 |
+
"eval_steps_per_second": 0.761,
|
457 |
+
"learning_rate": 0.0001,
|
458 |
+
"step": 5611
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 32.0,
|
462 |
+
"eval_accuracy": 0.2809573361082206,
|
463 |
+
"eval_f1_macro": 0.6111569473926136,
|
464 |
+
"eval_f1_micro": 0.8437194965322373,
|
465 |
+
"eval_loss": 0.29034462571144104,
|
466 |
+
"eval_runtime": 76.5731,
|
467 |
+
"eval_samples_per_second": 50.2,
|
468 |
+
"eval_steps_per_second": 0.797,
|
469 |
+
"learning_rate": 0.0001,
|
470 |
+
"step": 5792
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 33.0,
|
474 |
+
"eval_accuracy": 0.28537981269510926,
|
475 |
+
"eval_f1_macro": 0.6202495870793918,
|
476 |
+
"eval_f1_micro": 0.8461617038663874,
|
477 |
+
"eval_loss": 0.2888760268688202,
|
478 |
+
"eval_runtime": 78.8612,
|
479 |
+
"eval_samples_per_second": 48.744,
|
480 |
+
"eval_steps_per_second": 0.774,
|
481 |
+
"learning_rate": 0.0001,
|
482 |
+
"step": 5973
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 33.149171270718234,
|
486 |
+
"grad_norm": 0.16711881756782532,
|
487 |
+
"learning_rate": 0.0001,
|
488 |
+
"loss": 0.3049,
|
489 |
+
"step": 6000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 34.0,
|
493 |
+
"eval_accuracy": 0.2861602497398543,
|
494 |
+
"eval_f1_macro": 0.6150504150317478,
|
495 |
+
"eval_f1_micro": 0.8446023671361742,
|
496 |
+
"eval_loss": 0.28964364528656006,
|
497 |
+
"eval_runtime": 78.2568,
|
498 |
+
"eval_samples_per_second": 49.12,
|
499 |
+
"eval_steps_per_second": 0.779,
|
500 |
+
"learning_rate": 0.0001,
|
501 |
+
"step": 6154
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 35.0,
|
505 |
+
"eval_accuracy": 0.2866805411030177,
|
506 |
+
"eval_f1_macro": 0.611180048847438,
|
507 |
+
"eval_f1_micro": 0.8449244728566273,
|
508 |
+
"eval_loss": 0.28874215483665466,
|
509 |
+
"eval_runtime": 78.411,
|
510 |
+
"eval_samples_per_second": 49.024,
|
511 |
+
"eval_steps_per_second": 0.778,
|
512 |
+
"learning_rate": 0.0001,
|
513 |
+
"step": 6335
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 35.91160220994475,
|
517 |
+
"grad_norm": 0.1489323228597641,
|
518 |
+
"learning_rate": 0.0001,
|
519 |
+
"loss": 0.3012,
|
520 |
+
"step": 6500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 36.0,
|
524 |
+
"eval_accuracy": 0.28355879292403746,
|
525 |
+
"eval_f1_macro": 0.6119874534823754,
|
526 |
+
"eval_f1_micro": 0.8447173058645225,
|
527 |
+
"eval_loss": 0.2888963222503662,
|
528 |
+
"eval_runtime": 80.9886,
|
529 |
+
"eval_samples_per_second": 47.463,
|
530 |
+
"eval_steps_per_second": 0.753,
|
531 |
+
"learning_rate": 0.0001,
|
532 |
+
"step": 6516
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 37.0,
|
536 |
+
"eval_accuracy": 0.2866805411030177,
|
537 |
+
"eval_f1_macro": 0.6255767175486281,
|
538 |
+
"eval_f1_micro": 0.8475834540970686,
|
539 |
+
"eval_loss": 0.288282573223114,
|
540 |
+
"eval_runtime": 78.5643,
|
541 |
+
"eval_samples_per_second": 48.928,
|
542 |
+
"eval_steps_per_second": 0.776,
|
543 |
+
"learning_rate": 0.0001,
|
544 |
+
"step": 6697
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 38.0,
|
548 |
+
"eval_accuracy": 0.28251821019771073,
|
549 |
+
"eval_f1_macro": 0.6057239934398935,
|
550 |
+
"eval_f1_micro": 0.8452536426724028,
|
551 |
+
"eval_loss": 0.29050976037979126,
|
552 |
+
"eval_runtime": 79.802,
|
553 |
+
"eval_samples_per_second": 48.169,
|
554 |
+
"eval_steps_per_second": 0.764,
|
555 |
+
"learning_rate": 0.0001,
|
556 |
+
"step": 6878
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 38.67403314917127,
|
560 |
+
"grad_norm": 0.1844823658466339,
|
561 |
+
"learning_rate": 0.0001,
|
562 |
+
"loss": 0.299,
|
563 |
+
"step": 7000
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 39.0,
|
567 |
+
"eval_accuracy": 0.28537981269510926,
|
568 |
+
"eval_f1_macro": 0.625366961909805,
|
569 |
+
"eval_f1_micro": 0.8470600182796791,
|
570 |
+
"eval_loss": 0.28778275847435,
|
571 |
+
"eval_runtime": 78.7507,
|
572 |
+
"eval_samples_per_second": 48.812,
|
573 |
+
"eval_steps_per_second": 0.775,
|
574 |
+
"learning_rate": 0.0001,
|
575 |
+
"step": 7059
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 40.0,
|
579 |
+
"eval_accuracy": 0.2809573361082206,
|
580 |
+
"eval_f1_macro": 0.622337777946806,
|
581 |
+
"eval_f1_micro": 0.8468000302716884,
|
582 |
+
"eval_loss": 0.2885717749595642,
|
583 |
+
"eval_runtime": 79.0959,
|
584 |
+
"eval_samples_per_second": 48.599,
|
585 |
+
"eval_steps_per_second": 0.771,
|
586 |
+
"learning_rate": 0.0001,
|
587 |
+
"step": 7240
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 41.0,
|
591 |
+
"eval_accuracy": 0.2843392299687825,
|
592 |
+
"eval_f1_macro": 0.6260539681026288,
|
593 |
+
"eval_f1_micro": 0.847323400258903,
|
594 |
+
"eval_loss": 0.28773826360702515,
|
595 |
+
"eval_runtime": 81.7413,
|
596 |
+
"eval_samples_per_second": 47.026,
|
597 |
+
"eval_steps_per_second": 0.746,
|
598 |
+
"learning_rate": 0.0001,
|
599 |
+
"step": 7421
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 41.43646408839779,
|
603 |
+
"grad_norm": 0.16540081799030304,
|
604 |
+
"learning_rate": 0.0001,
|
605 |
+
"loss": 0.2989,
|
606 |
+
"step": 7500
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 42.0,
|
610 |
+
"eval_accuracy": 0.28563995837669093,
|
611 |
+
"eval_f1_macro": 0.6199392946357273,
|
612 |
+
"eval_f1_micro": 0.8476613005450627,
|
613 |
+
"eval_loss": 0.28776827454566956,
|
614 |
+
"eval_runtime": 78.9339,
|
615 |
+
"eval_samples_per_second": 48.699,
|
616 |
+
"eval_steps_per_second": 0.773,
|
617 |
+
"learning_rate": 0.0001,
|
618 |
+
"step": 7602
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 43.0,
|
622 |
+
"eval_accuracy": 0.28303850156087407,
|
623 |
+
"eval_f1_macro": 0.6287571427217789,
|
624 |
+
"eval_f1_micro": 0.8479237095716232,
|
625 |
+
"eval_loss": 0.28717148303985596,
|
626 |
+
"eval_runtime": 77.7099,
|
627 |
+
"eval_samples_per_second": 49.466,
|
628 |
+
"eval_steps_per_second": 0.785,
|
629 |
+
"learning_rate": 0.0001,
|
630 |
+
"step": 7783
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 44.0,
|
634 |
+
"eval_accuracy": 0.28407908428720086,
|
635 |
+
"eval_f1_macro": 0.6189979239207937,
|
636 |
+
"eval_f1_micro": 0.8463665693654939,
|
637 |
+
"eval_loss": 0.28678667545318604,
|
638 |
+
"eval_runtime": 78.2343,
|
639 |
+
"eval_samples_per_second": 49.134,
|
640 |
+
"eval_steps_per_second": 0.78,
|
641 |
+
"learning_rate": 0.0001,
|
642 |
+
"step": 7964
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 44.19889502762431,
|
646 |
+
"grad_norm": 0.17522749304771423,
|
647 |
+
"learning_rate": 0.0001,
|
648 |
+
"loss": 0.2983,
|
649 |
+
"step": 8000
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 45.0,
|
653 |
+
"eval_accuracy": 0.28381893860561913,
|
654 |
+
"eval_f1_macro": 0.6235508782461164,
|
655 |
+
"eval_f1_micro": 0.8462928555066304,
|
656 |
+
"eval_loss": 0.28698909282684326,
|
657 |
+
"eval_runtime": 78.0653,
|
658 |
+
"eval_samples_per_second": 49.241,
|
659 |
+
"eval_steps_per_second": 0.781,
|
660 |
+
"learning_rate": 0.0001,
|
661 |
+
"step": 8145
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 46.0,
|
665 |
+
"eval_accuracy": 0.28251821019771073,
|
666 |
+
"eval_f1_macro": 0.6151318511304835,
|
667 |
+
"eval_f1_micro": 0.8459846547314578,
|
668 |
+
"eval_loss": 0.2868472635746002,
|
669 |
+
"eval_runtime": 77.6178,
|
670 |
+
"eval_samples_per_second": 49.525,
|
671 |
+
"eval_steps_per_second": 0.786,
|
672 |
+
"learning_rate": 0.0001,
|
673 |
+
"step": 8326
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 46.96132596685083,
|
677 |
+
"grad_norm": 0.20419611036777496,
|
678 |
+
"learning_rate": 0.0001,
|
679 |
+
"loss": 0.298,
|
680 |
+
"step": 8500
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 47.0,
|
684 |
+
"eval_accuracy": 0.2845993756503642,
|
685 |
+
"eval_f1_macro": 0.6211457155619424,
|
686 |
+
"eval_f1_micro": 0.8462129359348595,
|
687 |
+
"eval_loss": 0.28715068101882935,
|
688 |
+
"eval_runtime": 77.3289,
|
689 |
+
"eval_samples_per_second": 49.71,
|
690 |
+
"eval_steps_per_second": 0.789,
|
691 |
+
"learning_rate": 0.0001,
|
692 |
+
"step": 8507
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 48.0,
|
696 |
+
"eval_accuracy": 0.28355879292403746,
|
697 |
+
"eval_f1_macro": 0.6231150403485404,
|
698 |
+
"eval_f1_micro": 0.8466852933705867,
|
699 |
+
"eval_loss": 0.28661593794822693,
|
700 |
+
"eval_runtime": 76.7641,
|
701 |
+
"eval_samples_per_second": 50.075,
|
702 |
+
"eval_steps_per_second": 0.795,
|
703 |
+
"learning_rate": 0.0001,
|
704 |
+
"step": 8688
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 49.0,
|
708 |
+
"eval_accuracy": 0.28590010405827265,
|
709 |
+
"eval_f1_macro": 0.616055362439494,
|
710 |
+
"eval_f1_micro": 0.8460415439387342,
|
711 |
+
"eval_loss": 0.28633347153663635,
|
712 |
+
"eval_runtime": 76.5745,
|
713 |
+
"eval_samples_per_second": 50.199,
|
714 |
+
"eval_steps_per_second": 0.797,
|
715 |
+
"learning_rate": 0.0001,
|
716 |
+
"step": 8869
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 49.72375690607735,
|
720 |
+
"grad_norm": 0.2103131115436554,
|
721 |
+
"learning_rate": 0.0001,
|
722 |
+
"loss": 0.2965,
|
723 |
+
"step": 9000
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 50.0,
|
727 |
+
"eval_accuracy": 0.2845993756503642,
|
728 |
+
"eval_f1_macro": 0.625458075101288,
|
729 |
+
"eval_f1_micro": 0.8482882700250868,
|
730 |
+
"eval_loss": 0.28642749786376953,
|
731 |
+
"eval_runtime": 76.3371,
|
732 |
+
"eval_samples_per_second": 50.356,
|
733 |
+
"eval_steps_per_second": 0.799,
|
734 |
+
"learning_rate": 0.0001,
|
735 |
+
"step": 9050
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 51.0,
|
739 |
+
"eval_accuracy": 0.28485952133194586,
|
740 |
+
"eval_f1_macro": 0.6278100779578839,
|
741 |
+
"eval_f1_micro": 0.848592785832539,
|
742 |
+
"eval_loss": 0.2890762686729431,
|
743 |
+
"eval_runtime": 77.0258,
|
744 |
+
"eval_samples_per_second": 49.905,
|
745 |
+
"eval_steps_per_second": 0.792,
|
746 |
+
"learning_rate": 0.0001,
|
747 |
+
"step": 9231
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 52.0,
|
751 |
+
"eval_accuracy": 0.2851196670135276,
|
752 |
+
"eval_f1_macro": 0.6255462096645672,
|
753 |
+
"eval_f1_micro": 0.8464228285561143,
|
754 |
+
"eval_loss": 0.2855978012084961,
|
755 |
+
"eval_runtime": 76.6781,
|
756 |
+
"eval_samples_per_second": 50.132,
|
757 |
+
"eval_steps_per_second": 0.796,
|
758 |
+
"learning_rate": 0.0001,
|
759 |
+
"step": 9412
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 52.48618784530387,
|
763 |
+
"grad_norm": 0.24192312359809875,
|
764 |
+
"learning_rate": 0.0001,
|
765 |
+
"loss": 0.2956,
|
766 |
+
"step": 9500
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 53.0,
|
770 |
+
"eval_accuracy": 0.27887617065556713,
|
771 |
+
"eval_f1_macro": 0.6457587856102145,
|
772 |
+
"eval_f1_micro": 0.8489991514001897,
|
773 |
+
"eval_loss": 0.2872205674648285,
|
774 |
+
"eval_runtime": 76.6479,
|
775 |
+
"eval_samples_per_second": 50.151,
|
776 |
+
"eval_steps_per_second": 0.796,
|
777 |
+
"learning_rate": 0.0001,
|
778 |
+
"step": 9593
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 54.0,
|
782 |
+
"eval_accuracy": 0.2903225806451613,
|
783 |
+
"eval_f1_macro": 0.6243869856844756,
|
784 |
+
"eval_f1_micro": 0.8476844874709444,
|
785 |
+
"eval_loss": 0.2855803072452545,
|
786 |
+
"eval_runtime": 77.582,
|
787 |
+
"eval_samples_per_second": 49.548,
|
788 |
+
"eval_steps_per_second": 0.786,
|
789 |
+
"learning_rate": 0.0001,
|
790 |
+
"step": 9774
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 55.0,
|
794 |
+
"eval_accuracy": 0.2845993756503642,
|
795 |
+
"eval_f1_macro": 0.6339630509281279,
|
796 |
+
"eval_f1_micro": 0.8475136716266056,
|
797 |
+
"eval_loss": 0.28568968176841736,
|
798 |
+
"eval_runtime": 77.102,
|
799 |
+
"eval_samples_per_second": 49.856,
|
800 |
+
"eval_steps_per_second": 0.791,
|
801 |
+
"learning_rate": 0.0001,
|
802 |
+
"step": 9955
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 55.248618784530386,
|
806 |
+
"grad_norm": 0.21083500981330872,
|
807 |
+
"learning_rate": 0.0001,
|
808 |
+
"loss": 0.2958,
|
809 |
+
"step": 10000
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 56.0,
|
813 |
+
"eval_accuracy": 0.2866805411030177,
|
814 |
+
"eval_f1_macro": 0.6241465491773776,
|
815 |
+
"eval_f1_micro": 0.8465597622829039,
|
816 |
+
"eval_loss": 0.28617897629737854,
|
817 |
+
"eval_runtime": 76.1445,
|
818 |
+
"eval_samples_per_second": 50.483,
|
819 |
+
"eval_steps_per_second": 0.801,
|
820 |
+
"learning_rate": 0.0001,
|
821 |
+
"step": 10136
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 57.0,
|
825 |
+
"eval_accuracy": 0.2861602497398543,
|
826 |
+
"eval_f1_macro": 0.6249269702519318,
|
827 |
+
"eval_f1_micro": 0.845436853426201,
|
828 |
+
"eval_loss": 0.2870914936065674,
|
829 |
+
"eval_runtime": 77.4556,
|
830 |
+
"eval_samples_per_second": 49.628,
|
831 |
+
"eval_steps_per_second": 0.788,
|
832 |
+
"learning_rate": 0.0001,
|
833 |
+
"step": 10317
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 58.0,
|
837 |
+
"eval_accuracy": 0.28121748178980227,
|
838 |
+
"eval_f1_macro": 0.6333866717026029,
|
839 |
+
"eval_f1_micro": 0.8491941382702348,
|
840 |
+
"eval_loss": 0.2857914865016937,
|
841 |
+
"eval_runtime": 77.2551,
|
842 |
+
"eval_samples_per_second": 49.757,
|
843 |
+
"eval_steps_per_second": 0.79,
|
844 |
+
"learning_rate": 0.0001,
|
845 |
+
"step": 10498
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 58.011049723756905,
|
849 |
+
"grad_norm": 0.22250542044639587,
|
850 |
+
"learning_rate": 1e-05,
|
851 |
+
"loss": 0.2954,
|
852 |
+
"step": 10500
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 59.0,
|
856 |
+
"eval_accuracy": 0.2887617065556712,
|
857 |
+
"eval_f1_macro": 0.6178461796051926,
|
858 |
+
"eval_f1_micro": 0.8468232576049287,
|
859 |
+
"eval_loss": 0.28617140650749207,
|
860 |
+
"eval_runtime": 76.6548,
|
861 |
+
"eval_samples_per_second": 50.147,
|
862 |
+
"eval_steps_per_second": 0.796,
|
863 |
+
"learning_rate": 1e-05,
|
864 |
+
"step": 10679
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 60.0,
|
868 |
+
"eval_accuracy": 0.28537981269510926,
|
869 |
+
"eval_f1_macro": 0.6275748058546806,
|
870 |
+
"eval_f1_micro": 0.8485033598045205,
|
871 |
+
"eval_loss": 0.2846605181694031,
|
872 |
+
"eval_runtime": 76.2984,
|
873 |
+
"eval_samples_per_second": 50.381,
|
874 |
+
"eval_steps_per_second": 0.799,
|
875 |
+
"learning_rate": 1e-05,
|
876 |
+
"step": 10860
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 60.773480662983424,
|
880 |
+
"grad_norm": 0.25101110339164734,
|
881 |
+
"learning_rate": 1e-05,
|
882 |
+
"loss": 0.2923,
|
883 |
+
"step": 11000
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 61.0,
|
887 |
+
"eval_accuracy": 0.28303850156087407,
|
888 |
+
"eval_f1_macro": 0.6223888517425455,
|
889 |
+
"eval_f1_micro": 0.8479865171982329,
|
890 |
+
"eval_loss": 0.2848633825778961,
|
891 |
+
"eval_runtime": 76.6322,
|
892 |
+
"eval_samples_per_second": 50.162,
|
893 |
+
"eval_steps_per_second": 0.796,
|
894 |
+
"learning_rate": 1e-05,
|
895 |
+
"step": 11041
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 62.0,
|
899 |
+
"eval_accuracy": 0.2843392299687825,
|
900 |
+
"eval_f1_macro": 0.6247632003821695,
|
901 |
+
"eval_f1_micro": 0.8469200122586577,
|
902 |
+
"eval_loss": 0.28548601269721985,
|
903 |
+
"eval_runtime": 77.5636,
|
904 |
+
"eval_samples_per_second": 49.559,
|
905 |
+
"eval_steps_per_second": 0.786,
|
906 |
+
"learning_rate": 1e-05,
|
907 |
+
"step": 11222
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 63.0,
|
911 |
+
"eval_accuracy": 0.2827783558792924,
|
912 |
+
"eval_f1_macro": 0.6274806463168713,
|
913 |
+
"eval_f1_micro": 0.8488979777323336,
|
914 |
+
"eval_loss": 0.28493326902389526,
|
915 |
+
"eval_runtime": 77.2321,
|
916 |
+
"eval_samples_per_second": 49.772,
|
917 |
+
"eval_steps_per_second": 0.79,
|
918 |
+
"learning_rate": 1e-05,
|
919 |
+
"step": 11403
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 63.53591160220994,
|
923 |
+
"grad_norm": 0.23796355724334717,
|
924 |
+
"learning_rate": 1e-05,
|
925 |
+
"loss": 0.2918,
|
926 |
+
"step": 11500
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 64.0,
|
930 |
+
"eval_accuracy": 0.28225806451612906,
|
931 |
+
"eval_f1_macro": 0.6370787064578803,
|
932 |
+
"eval_f1_micro": 0.8475187206498287,
|
933 |
+
"eval_loss": 0.28459736704826355,
|
934 |
+
"eval_runtime": 77.0797,
|
935 |
+
"eval_samples_per_second": 49.87,
|
936 |
+
"eval_steps_per_second": 0.791,
|
937 |
+
"learning_rate": 1e-05,
|
938 |
+
"step": 11584
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 65.0,
|
942 |
+
"eval_accuracy": 0.2869406867845994,
|
943 |
+
"eval_f1_macro": 0.6240984315849201,
|
944 |
+
"eval_f1_micro": 0.8467700785794469,
|
945 |
+
"eval_loss": 0.2860054671764374,
|
946 |
+
"eval_runtime": 76.4904,
|
947 |
+
"eval_samples_per_second": 50.255,
|
948 |
+
"eval_steps_per_second": 0.797,
|
949 |
+
"learning_rate": 1e-05,
|
950 |
+
"step": 11765
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 66.0,
|
954 |
+
"eval_accuracy": 0.28407908428720086,
|
955 |
+
"eval_f1_macro": 0.6346693986906206,
|
956 |
+
"eval_f1_micro": 0.8481340441736481,
|
957 |
+
"eval_loss": 0.2847185730934143,
|
958 |
+
"eval_runtime": 77.2653,
|
959 |
+
"eval_samples_per_second": 49.751,
|
960 |
+
"eval_steps_per_second": 0.789,
|
961 |
+
"learning_rate": 1e-05,
|
962 |
+
"step": 11946
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 66.29834254143647,
|
966 |
+
"grad_norm": 0.25470152497291565,
|
967 |
+
"learning_rate": 1e-05,
|
968 |
+
"loss": 0.2906,
|
969 |
+
"step": 12000
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 67.0,
|
973 |
+
"eval_accuracy": 0.28537981269510926,
|
974 |
+
"eval_f1_macro": 0.6287121285420982,
|
975 |
+
"eval_f1_micro": 0.8487528745798691,
|
976 |
+
"eval_loss": 0.28529325127601624,
|
977 |
+
"eval_runtime": 79.9065,
|
978 |
+
"eval_samples_per_second": 48.106,
|
979 |
+
"eval_steps_per_second": 0.763,
|
980 |
+
"learning_rate": 1e-05,
|
981 |
+
"step": 12127
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 68.0,
|
985 |
+
"eval_accuracy": 0.2866805411030177,
|
986 |
+
"eval_f1_macro": 0.6321379394582358,
|
987 |
+
"eval_f1_micro": 0.8480251642525557,
|
988 |
+
"eval_loss": 0.2852926254272461,
|
989 |
+
"eval_runtime": 78.4728,
|
990 |
+
"eval_samples_per_second": 48.985,
|
991 |
+
"eval_steps_per_second": 0.777,
|
992 |
+
"learning_rate": 1e-05,
|
993 |
+
"step": 12308
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 69.0,
|
997 |
+
"eval_accuracy": 0.28355879292403746,
|
998 |
+
"eval_f1_macro": 0.6397237492354447,
|
999 |
+
"eval_f1_micro": 0.847692190707931,
|
1000 |
+
"eval_loss": 0.284834623336792,
|
1001 |
+
"eval_runtime": 77.7721,
|
1002 |
+
"eval_samples_per_second": 49.426,
|
1003 |
+
"eval_steps_per_second": 0.784,
|
1004 |
+
"learning_rate": 1e-05,
|
1005 |
+
"step": 12489
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 69.06077348066299,
|
1009 |
+
"grad_norm": 0.19653503596782684,
|
1010 |
+
"learning_rate": 1e-05,
|
1011 |
+
"loss": 0.2918,
|
1012 |
+
"step": 12500
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 70.0,
|
1016 |
+
"eval_accuracy": 0.28225806451612906,
|
1017 |
+
"eval_f1_macro": 0.6381143671040704,
|
1018 |
+
"eval_f1_micro": 0.8492167101827677,
|
1019 |
+
"eval_loss": 0.28527727723121643,
|
1020 |
+
"eval_runtime": 76.6607,
|
1021 |
+
"eval_samples_per_second": 50.143,
|
1022 |
+
"eval_steps_per_second": 0.796,
|
1023 |
+
"learning_rate": 1e-05,
|
1024 |
+
"step": 12670
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 71.0,
|
1028 |
+
"eval_accuracy": 0.2882414151925078,
|
1029 |
+
"eval_f1_macro": 0.6325489300082728,
|
1030 |
+
"eval_f1_micro": 0.8475971370143149,
|
1031 |
+
"eval_loss": 0.28507113456726074,
|
1032 |
+
"eval_runtime": 76.9731,
|
1033 |
+
"eval_samples_per_second": 49.94,
|
1034 |
+
"eval_steps_per_second": 0.792,
|
1035 |
+
"learning_rate": 1.0000000000000002e-06,
|
1036 |
+
"step": 12851
|
1037 |
+
},
|
1038 |
+
{
|
1039 |
+
"epoch": 71.8232044198895,
|
1040 |
+
"grad_norm": 0.19946995377540588,
|
1041 |
+
"learning_rate": 1.0000000000000002e-06,
|
1042 |
+
"loss": 0.2918,
|
1043 |
+
"step": 13000
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 72.0,
|
1047 |
+
"eval_accuracy": 0.28485952133194586,
|
1048 |
+
"eval_f1_macro": 0.6236352127811986,
|
1049 |
+
"eval_f1_micro": 0.8474255781269963,
|
1050 |
+
"eval_loss": 0.28452861309051514,
|
1051 |
+
"eval_runtime": 79.7463,
|
1052 |
+
"eval_samples_per_second": 48.203,
|
1053 |
+
"eval_steps_per_second": 0.765,
|
1054 |
+
"learning_rate": 1.0000000000000002e-06,
|
1055 |
+
"step": 13032
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 73.0,
|
1059 |
+
"eval_accuracy": 0.28121748178980227,
|
1060 |
+
"eval_f1_macro": 0.6333277250193455,
|
1061 |
+
"eval_f1_micro": 0.847641772858811,
|
1062 |
+
"eval_loss": 0.28448227047920227,
|
1063 |
+
"eval_runtime": 76.9059,
|
1064 |
+
"eval_samples_per_second": 49.983,
|
1065 |
+
"eval_steps_per_second": 0.793,
|
1066 |
+
"learning_rate": 1.0000000000000002e-06,
|
1067 |
+
"step": 13213
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 74.0,
|
1071 |
+
"eval_accuracy": 0.2827783558792924,
|
1072 |
+
"eval_f1_macro": 0.6300187593616763,
|
1073 |
+
"eval_f1_micro": 0.8465770953294945,
|
1074 |
+
"eval_loss": 0.28447526693344116,
|
1075 |
+
"eval_runtime": 77.6657,
|
1076 |
+
"eval_samples_per_second": 49.494,
|
1077 |
+
"eval_steps_per_second": 0.785,
|
1078 |
+
"learning_rate": 1.0000000000000002e-06,
|
1079 |
+
"step": 13394
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 74.58563535911603,
|
1083 |
+
"grad_norm": 0.251558780670166,
|
1084 |
+
"learning_rate": 1.0000000000000002e-06,
|
1085 |
+
"loss": 0.2913,
|
1086 |
+
"step": 13500
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 75.0,
|
1090 |
+
"eval_accuracy": 0.28199791883454733,
|
1091 |
+
"eval_f1_macro": 0.6235297745568456,
|
1092 |
+
"eval_f1_micro": 0.8473772748126625,
|
1093 |
+
"eval_loss": 0.2851284146308899,
|
1094 |
+
"eval_runtime": 77.914,
|
1095 |
+
"eval_samples_per_second": 49.336,
|
1096 |
+
"eval_steps_per_second": 0.783,
|
1097 |
+
"learning_rate": 1.0000000000000002e-06,
|
1098 |
+
"step": 13575
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 76.0,
|
1102 |
+
"eval_accuracy": 0.2879812695109261,
|
1103 |
+
"eval_f1_macro": 0.6186062513830065,
|
1104 |
+
"eval_f1_micro": 0.847320835674516,
|
1105 |
+
"eval_loss": 0.2859683036804199,
|
1106 |
+
"eval_runtime": 77.7414,
|
1107 |
+
"eval_samples_per_second": 49.446,
|
1108 |
+
"eval_steps_per_second": 0.785,
|
1109 |
+
"learning_rate": 1.0000000000000002e-06,
|
1110 |
+
"step": 13756
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 77.0,
|
1114 |
+
"eval_accuracy": 0.28563995837669093,
|
1115 |
+
"eval_f1_macro": 0.6172786558676017,
|
1116 |
+
"eval_f1_micro": 0.8459046737621472,
|
1117 |
+
"eval_loss": 0.2858298718929291,
|
1118 |
+
"eval_runtime": 79.1015,
|
1119 |
+
"eval_samples_per_second": 48.596,
|
1120 |
+
"eval_steps_per_second": 0.771,
|
1121 |
+
"learning_rate": 1.0000000000000002e-06,
|
1122 |
+
"step": 13937
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 77.34806629834254,
|
1126 |
+
"grad_norm": 0.22088366746902466,
|
1127 |
+
"learning_rate": 1.0000000000000002e-06,
|
1128 |
+
"loss": 0.2913,
|
1129 |
+
"step": 14000
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 78.0,
|
1133 |
+
"eval_accuracy": 0.2843392299687825,
|
1134 |
+
"eval_f1_macro": 0.6325947858436887,
|
1135 |
+
"eval_f1_micro": 0.8480547459130655,
|
1136 |
+
"eval_loss": 0.28438833355903625,
|
1137 |
+
"eval_runtime": 77.2562,
|
1138 |
+
"eval_samples_per_second": 49.757,
|
1139 |
+
"eval_steps_per_second": 0.79,
|
1140 |
+
"learning_rate": 1.0000000000000002e-06,
|
1141 |
+
"step": 14118
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 79.0,
|
1145 |
+
"eval_accuracy": 0.2874609781477627,
|
1146 |
+
"eval_f1_macro": 0.617917490234713,
|
1147 |
+
"eval_f1_micro": 0.8472353346431579,
|
1148 |
+
"eval_loss": 0.2870919704437256,
|
1149 |
+
"eval_runtime": 76.5647,
|
1150 |
+
"eval_samples_per_second": 50.206,
|
1151 |
+
"eval_steps_per_second": 0.797,
|
1152 |
+
"learning_rate": 1.0000000000000002e-06,
|
1153 |
+
"step": 14299
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 80.0,
|
1157 |
+
"eval_accuracy": 0.28381893860561913,
|
1158 |
+
"eval_f1_macro": 0.6286567457369128,
|
1159 |
+
"eval_f1_micro": 0.8477330616403465,
|
1160 |
+
"eval_loss": 0.28482332825660706,
|
1161 |
+
"eval_runtime": 76.83,
|
1162 |
+
"eval_samples_per_second": 50.033,
|
1163 |
+
"eval_steps_per_second": 0.794,
|
1164 |
+
"learning_rate": 1.0000000000000002e-06,
|
1165 |
+
"step": 14480
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 80.11049723756906,
|
1169 |
+
"grad_norm": 0.21530944108963013,
|
1170 |
+
"learning_rate": 1.0000000000000002e-06,
|
1171 |
+
"loss": 0.2915,
|
1172 |
+
"step": 14500
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 81.0,
|
1176 |
+
"eval_accuracy": 0.28537981269510926,
|
1177 |
+
"eval_f1_macro": 0.6304525529970205,
|
1178 |
+
"eval_f1_micro": 0.8489678202792957,
|
1179 |
+
"eval_loss": 0.2847617268562317,
|
1180 |
+
"eval_runtime": 77.26,
|
1181 |
+
"eval_samples_per_second": 49.754,
|
1182 |
+
"eval_steps_per_second": 0.79,
|
1183 |
+
"learning_rate": 1.0000000000000002e-06,
|
1184 |
+
"step": 14661
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 82.0,
|
1188 |
+
"eval_accuracy": 0.28590010405827265,
|
1189 |
+
"eval_f1_macro": 0.6394217270135759,
|
1190 |
+
"eval_f1_micro": 0.8480416961845967,
|
1191 |
+
"eval_loss": 0.28511229157447815,
|
1192 |
+
"eval_runtime": 78.9926,
|
1193 |
+
"eval_samples_per_second": 48.663,
|
1194 |
+
"eval_steps_per_second": 0.772,
|
1195 |
+
"learning_rate": 1.0000000000000002e-06,
|
1196 |
+
"step": 14842
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 82.87292817679558,
|
1200 |
+
"grad_norm": 0.2371624857187271,
|
1201 |
+
"learning_rate": 1.0000000000000002e-06,
|
1202 |
+
"loss": 0.2913,
|
1203 |
+
"step": 15000
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 83.0,
|
1207 |
+
"eval_accuracy": 0.28563995837669093,
|
1208 |
+
"eval_f1_macro": 0.6255055774993536,
|
1209 |
+
"eval_f1_micro": 0.8488055562622434,
|
1210 |
+
"eval_loss": 0.284644216299057,
|
1211 |
+
"eval_runtime": 76.4754,
|
1212 |
+
"eval_samples_per_second": 50.265,
|
1213 |
+
"eval_steps_per_second": 0.798,
|
1214 |
+
"learning_rate": 1.0000000000000002e-06,
|
1215 |
+
"step": 15023
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 84.0,
|
1219 |
+
"eval_accuracy": 0.2832986472424558,
|
1220 |
+
"eval_f1_macro": 0.6457553263622914,
|
1221 |
+
"eval_f1_micro": 0.848188643119867,
|
1222 |
+
"eval_loss": 0.2857225835323334,
|
1223 |
+
"eval_runtime": 77.2675,
|
1224 |
+
"eval_samples_per_second": 49.749,
|
1225 |
+
"eval_steps_per_second": 0.789,
|
1226 |
+
"learning_rate": 1.0000000000000002e-06,
|
1227 |
+
"step": 15204
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 85.0,
|
1231 |
+
"eval_accuracy": 0.28121748178980227,
|
1232 |
+
"eval_f1_macro": 0.6339586571635658,
|
1233 |
+
"eval_f1_micro": 0.848818698673405,
|
1234 |
+
"eval_loss": 0.28550758957862854,
|
1235 |
+
"eval_runtime": 77.3218,
|
1236 |
+
"eval_samples_per_second": 49.714,
|
1237 |
+
"eval_steps_per_second": 0.789,
|
1238 |
+
"learning_rate": 1.0000000000000002e-07,
|
1239 |
+
"step": 15385
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 85.6353591160221,
|
1243 |
+
"grad_norm": 0.22222235798835754,
|
1244 |
+
"learning_rate": 1.0000000000000002e-07,
|
1245 |
+
"loss": 0.2922,
|
1246 |
+
"step": 15500
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 86.0,
|
1250 |
+
"eval_accuracy": 0.28590010405827265,
|
1251 |
+
"eval_f1_macro": 0.6362631688004041,
|
1252 |
+
"eval_f1_micro": 0.8479890588592848,
|
1253 |
+
"eval_loss": 0.284895658493042,
|
1254 |
+
"eval_runtime": 76.6317,
|
1255 |
+
"eval_samples_per_second": 50.162,
|
1256 |
+
"eval_steps_per_second": 0.796,
|
1257 |
+
"learning_rate": 1.0000000000000002e-07,
|
1258 |
+
"step": 15566
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 87.0,
|
1262 |
+
"eval_accuracy": 0.2851196670135276,
|
1263 |
+
"eval_f1_macro": 0.6327749126527296,
|
1264 |
+
"eval_f1_micro": 0.8473590201582036,
|
1265 |
+
"eval_loss": 0.2845035493373871,
|
1266 |
+
"eval_runtime": 77.1171,
|
1267 |
+
"eval_samples_per_second": 49.846,
|
1268 |
+
"eval_steps_per_second": 0.791,
|
1269 |
+
"learning_rate": 1.0000000000000002e-07,
|
1270 |
+
"step": 15747
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 88.0,
|
1274 |
+
"eval_accuracy": 0.28121748178980227,
|
1275 |
+
"eval_f1_macro": 0.6370893160624239,
|
1276 |
+
"eval_f1_micro": 0.8477551536613127,
|
1277 |
+
"eval_loss": 0.28541097044944763,
|
1278 |
+
"eval_runtime": 76.6873,
|
1279 |
+
"eval_samples_per_second": 50.126,
|
1280 |
+
"eval_steps_per_second": 0.795,
|
1281 |
+
"learning_rate": 1.0000000000000002e-07,
|
1282 |
+
"step": 15928
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 88.0,
|
1286 |
+
"learning_rate": 1.0000000000000002e-07,
|
1287 |
+
"step": 15928,
|
1288 |
+
"total_flos": 1.500719176717825e+20,
|
1289 |
+
"train_loss": 0.3047179739897961,
|
1290 |
+
"train_runtime": 30841.8451,
|
1291 |
+
"train_samples_per_second": 56.038,
|
1292 |
+
"train_steps_per_second": 0.88
|
1293 |
+
}
|
1294 |
+
],
|
1295 |
+
"logging_steps": 500,
|
1296 |
+
"max_steps": 27150,
|
1297 |
+
"num_input_tokens_seen": 0,
|
1298 |
+
"num_train_epochs": 150,
|
1299 |
+
"save_steps": 500,
|
1300 |
+
"stateful_callbacks": {
|
1301 |
+
"EarlyStoppingCallback": {
|
1302 |
+
"args": {
|
1303 |
+
"early_stopping_patience": 10,
|
1304 |
+
"early_stopping_threshold": 0.0
|
1305 |
+
},
|
1306 |
+
"attributes": {
|
1307 |
+
"early_stopping_patience_counter": 0
|
1308 |
+
}
|
1309 |
+
},
|
1310 |
+
"TrainerControl": {
|
1311 |
+
"args": {
|
1312 |
+
"should_epoch_stop": false,
|
1313 |
+
"should_evaluate": false,
|
1314 |
+
"should_log": false,
|
1315 |
+
"should_save": true,
|
1316 |
+
"should_training_stop": true
|
1317 |
+
},
|
1318 |
+
"attributes": {}
|
1319 |
+
}
|
1320 |
+
},
|
1321 |
+
"total_flos": 1.500719176717825e+20,
|
1322 |
+
"train_batch_size": 64,
|
1323 |
+
"trial_name": null,
|
1324 |
+
"trial_params": null
|
1325 |
+
}
|