Matthew Finlayson
commited on
Commit
·
b39dcfe
1
Parent(s):
47268a8
adding model
Browse files- README.md +238 -0
- all_results.json +15 -0
- config.json +82 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- train_results.json +8 -0
- trainer_state.json +1819 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: output
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# output
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [EleutherAI/gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B) on the [Lila dataset](https://github.com/allenai/Lila).
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.5884
|
20 |
+
- Accuracy: 0.8664
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 5e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 4
|
42 |
+
- seed: 42
|
43 |
+
- distributed_type: multi-GPU
|
44 |
+
- num_devices: 2
|
45 |
+
- total_train_batch_size: 8
|
46 |
+
- total_eval_batch_size: 8
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 10.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
55 |
+
| No log | 0.06 | 100 | 0.7930 | 0.8214 |
|
56 |
+
| No log | 0.11 | 200 | 0.7544 | 0.8290 |
|
57 |
+
| No log | 0.17 | 300 | 0.7358 | 0.8328 |
|
58 |
+
| No log | 0.23 | 400 | 0.7192 | 0.8357 |
|
59 |
+
| 0.8156 | 0.28 | 500 | 0.7012 | 0.8397 |
|
60 |
+
| 0.8156 | 0.34 | 600 | 0.6904 | 0.8419 |
|
61 |
+
| 0.8156 | 0.4 | 700 | 0.6802 | 0.8440 |
|
62 |
+
| 0.8156 | 0.45 | 800 | 0.6670 | 0.8465 |
|
63 |
+
| 0.8156 | 0.51 | 900 | 0.6572 | 0.8486 |
|
64 |
+
| 0.7219 | 0.57 | 1000 | 0.6499 | 0.8500 |
|
65 |
+
| 0.7219 | 0.62 | 1100 | 0.6411 | 0.8522 |
|
66 |
+
| 0.7219 | 0.68 | 1200 | 0.6343 | 0.8537 |
|
67 |
+
| 0.7219 | 0.74 | 1300 | 0.6299 | 0.8546 |
|
68 |
+
| 0.7219 | 0.79 | 1400 | 0.6221 | 0.8561 |
|
69 |
+
| 0.662 | 0.85 | 1500 | 0.6157 | 0.8574 |
|
70 |
+
| 0.662 | 0.91 | 1600 | 0.6138 | 0.8579 |
|
71 |
+
| 0.662 | 0.96 | 1700 | 0.6055 | 0.8595 |
|
72 |
+
| 0.662 | 1.02 | 1800 | 0.6143 | 0.8598 |
|
73 |
+
| 0.662 | 1.08 | 1900 | 0.6191 | 0.8599 |
|
74 |
+
| 0.5707 | 1.14 | 2000 | 0.6118 | 0.8607 |
|
75 |
+
| 0.5707 | 1.19 | 2100 | 0.6123 | 0.8611 |
|
76 |
+
| 0.5707 | 1.25 | 2200 | 0.6089 | 0.8617 |
|
77 |
+
| 0.5707 | 1.31 | 2300 | 0.6064 | 0.8619 |
|
78 |
+
| 0.5707 | 1.36 | 2400 | 0.6079 | 0.8625 |
|
79 |
+
| 0.4923 | 1.42 | 2500 | 0.6040 | 0.8625 |
|
80 |
+
| 0.4923 | 1.48 | 2600 | 0.6030 | 0.8630 |
|
81 |
+
| 0.4923 | 1.53 | 2700 | 0.6021 | 0.8636 |
|
82 |
+
| 0.4923 | 1.59 | 2800 | 0.6001 | 0.8643 |
|
83 |
+
| 0.4923 | 1.65 | 2900 | 0.5981 | 0.8644 |
|
84 |
+
| 0.4909 | 1.7 | 3000 | 0.5942 | 0.8648 |
|
85 |
+
| 0.4909 | 1.76 | 3100 | 0.5918 | 0.8650 |
|
86 |
+
| 0.4909 | 1.82 | 3200 | 0.5923 | 0.8659 |
|
87 |
+
| 0.4909 | 1.87 | 3300 | 0.5884 | 0.8664 |
|
88 |
+
| 0.4909 | 1.93 | 3400 | 0.5884 | 0.8663 |
|
89 |
+
| 0.4964 | 1.99 | 3500 | 0.5903 | 0.8669 |
|
90 |
+
| 0.4964 | 2.04 | 3600 | 0.6421 | 0.8655 |
|
91 |
+
| 0.4964 | 2.1 | 3700 | 0.6401 | 0.8651 |
|
92 |
+
| 0.4964 | 2.16 | 3800 | 0.6411 | 0.8649 |
|
93 |
+
| 0.4964 | 2.21 | 3900 | 0.6387 | 0.8645 |
|
94 |
+
| 0.345 | 2.27 | 4000 | 0.6362 | 0.8654 |
|
95 |
+
| 0.345 | 2.33 | 4100 | 0.6362 | 0.8654 |
|
96 |
+
| 0.345 | 2.38 | 4200 | 0.6362 | 0.8654 |
|
97 |
+
| 0.345 | 2.44 | 4300 | 0.6357 | 0.8655 |
|
98 |
+
| 0.345 | 2.5 | 4400 | 0.6362 | 0.8656 |
|
99 |
+
| 0.3463 | 2.55 | 4500 | 0.6377 | 0.8658 |
|
100 |
+
| 0.3463 | 2.61 | 4600 | 0.6357 | 0.8660 |
|
101 |
+
| 0.3463 | 2.67 | 4700 | 0.6294 | 0.8665 |
|
102 |
+
| 0.3463 | 2.72 | 4800 | 0.6333 | 0.8665 |
|
103 |
+
| 0.3463 | 2.78 | 4900 | 0.6362 | 0.8662 |
|
104 |
+
| 0.3508 | 2.84 | 5000 | 0.6357 | 0.8666 |
|
105 |
+
| 0.3508 | 2.89 | 5100 | 0.6299 | 0.8673 |
|
106 |
+
| 0.3508 | 2.95 | 5200 | 0.6313 | 0.8668 |
|
107 |
+
| 0.3508 | 3.01 | 5300 | 0.7188 | 0.8646 |
|
108 |
+
| 0.3508 | 3.06 | 5400 | 0.7017 | 0.8656 |
|
109 |
+
| 0.295 | 3.12 | 5500 | 0.6982 | 0.8653 |
|
110 |
+
| 0.295 | 3.18 | 5600 | 0.7031 | 0.8655 |
|
111 |
+
| 0.295 | 3.23 | 5700 | 0.6992 | 0.8651 |
|
112 |
+
| 0.295 | 3.29 | 5800 | 0.6997 | 0.8653 |
|
113 |
+
| 0.295 | 3.35 | 5900 | 0.7041 | 0.8651 |
|
114 |
+
| 0.2348 | 3.41 | 6000 | 0.7075 | 0.8649 |
|
115 |
+
| 0.2348 | 3.46 | 6100 | 0.6992 | 0.8650 |
|
116 |
+
| 0.2348 | 3.52 | 6200 | 0.7065 | 0.8647 |
|
117 |
+
| 0.2348 | 3.58 | 6300 | 0.6997 | 0.8652 |
|
118 |
+
| 0.2348 | 3.63 | 6400 | 0.7026 | 0.8651 |
|
119 |
+
| 0.2411 | 3.69 | 6500 | 0.7046 | 0.8656 |
|
120 |
+
| 0.2411 | 3.75 | 6600 | 0.7007 | 0.8655 |
|
121 |
+
| 0.2411 | 3.8 | 6700 | 0.7026 | 0.8651 |
|
122 |
+
| 0.2411 | 3.86 | 6800 | 0.7031 | 0.8655 |
|
123 |
+
| 0.2411 | 3.92 | 6900 | 0.7012 | 0.8658 |
|
124 |
+
| 0.251 | 3.97 | 7000 | 0.7051 | 0.8656 |
|
125 |
+
| 0.251 | 4.03 | 7100 | 0.7607 | 0.8650 |
|
126 |
+
| 0.251 | 4.09 | 7200 | 0.7632 | 0.8656 |
|
127 |
+
| 0.251 | 4.14 | 7300 | 0.7588 | 0.8655 |
|
128 |
+
| 0.251 | 4.2 | 7400 | 0.7578 | 0.8651 |
|
129 |
+
| 0.1797 | 4.26 | 7500 | 0.7710 | 0.8645 |
|
130 |
+
| 0.1797 | 4.31 | 7600 | 0.7627 | 0.8648 |
|
131 |
+
| 0.1797 | 4.37 | 7700 | 0.7583 | 0.8650 |
|
132 |
+
| 0.1797 | 4.43 | 7800 | 0.7646 | 0.8649 |
|
133 |
+
| 0.1797 | 4.48 | 7900 | 0.7598 | 0.8646 |
|
134 |
+
| 0.1784 | 4.54 | 8000 | 0.7656 | 0.8650 |
|
135 |
+
| 0.1784 | 4.6 | 8100 | 0.7617 | 0.8648 |
|
136 |
+
| 0.1784 | 4.65 | 8200 | 0.7573 | 0.8651 |
|
137 |
+
| 0.1784 | 4.71 | 8300 | 0.7671 | 0.8648 |
|
138 |
+
| 0.1784 | 4.77 | 8400 | 0.7563 | 0.8651 |
|
139 |
+
| 0.1827 | 4.82 | 8500 | 0.7651 | 0.8649 |
|
140 |
+
| 0.1827 | 4.88 | 8600 | 0.7637 | 0.8650 |
|
141 |
+
| 0.1827 | 4.94 | 8700 | 0.7607 | 0.8654 |
|
142 |
+
| 0.1827 | 4.99 | 8800 | 0.7607 | 0.8650 |
|
143 |
+
| 0.1827 | 5.05 | 8900 | 0.8149 | 0.8646 |
|
144 |
+
| 0.167 | 5.11 | 9000 | 0.8081 | 0.8648 |
|
145 |
+
| 0.167 | 5.16 | 9100 | 0.8184 | 0.8644 |
|
146 |
+
| 0.167 | 5.22 | 9200 | 0.8140 | 0.8647 |
|
147 |
+
| 0.167 | 5.28 | 9300 | 0.8169 | 0.8644 |
|
148 |
+
| 0.167 | 5.33 | 9400 | 0.8120 | 0.8645 |
|
149 |
+
| 0.1371 | 5.39 | 9500 | 0.8154 | 0.8643 |
|
150 |
+
| 0.1371 | 5.45 | 9600 | 0.8179 | 0.8642 |
|
151 |
+
| 0.1371 | 5.51 | 9700 | 0.8154 | 0.8643 |
|
152 |
+
| 0.1371 | 5.56 | 9800 | 0.8120 | 0.8645 |
|
153 |
+
| 0.1371 | 5.62 | 9900 | 0.8110 | 0.8650 |
|
154 |
+
| 0.1425 | 5.68 | 10000 | 0.8159 | 0.8645 |
|
155 |
+
| 0.1425 | 5.73 | 10100 | 0.8174 | 0.8646 |
|
156 |
+
| 0.1425 | 5.79 | 10200 | 0.8159 | 0.8649 |
|
157 |
+
| 0.1425 | 5.85 | 10300 | 0.8110 | 0.8639 |
|
158 |
+
| 0.1425 | 5.9 | 10400 | 0.8135 | 0.8645 |
|
159 |
+
| 0.1505 | 5.96 | 10500 | 0.8140 | 0.8642 |
|
160 |
+
| 0.1505 | 6.02 | 10600 | 0.8628 | 0.8640 |
|
161 |
+
| 0.1505 | 6.07 | 10700 | 0.8540 | 0.8644 |
|
162 |
+
| 0.1505 | 6.13 | 10800 | 0.8530 | 0.8642 |
|
163 |
+
| 0.1505 | 6.19 | 10900 | 0.8560 | 0.8647 |
|
164 |
+
| 0.1086 | 6.24 | 11000 | 0.8555 | 0.8649 |
|
165 |
+
| 0.1086 | 6.3 | 11100 | 0.8604 | 0.8644 |
|
166 |
+
| 0.1086 | 6.36 | 11200 | 0.8569 | 0.8642 |
|
167 |
+
| 0.1086 | 6.41 | 11300 | 0.8530 | 0.8639 |
|
168 |
+
| 0.1086 | 6.47 | 11400 | 0.8589 | 0.8643 |
|
169 |
+
| 0.1076 | 6.53 | 11500 | 0.8525 | 0.8639 |
|
170 |
+
| 0.1076 | 6.58 | 11600 | 0.8579 | 0.8640 |
|
171 |
+
| 0.1076 | 6.64 | 11700 | 0.8594 | 0.8640 |
|
172 |
+
| 0.1076 | 6.7 | 11800 | 0.8599 | 0.8643 |
|
173 |
+
| 0.1076 | 6.75 | 11900 | 0.8564 | 0.8640 |
|
174 |
+
| 0.1109 | 6.81 | 12000 | 0.8633 | 0.8640 |
|
175 |
+
| 0.1109 | 6.87 | 12100 | 0.8584 | 0.8638 |
|
176 |
+
| 0.1109 | 6.92 | 12200 | 0.8647 | 0.8636 |
|
177 |
+
| 0.1109 | 6.98 | 12300 | 0.8599 | 0.8635 |
|
178 |
+
| 0.1109 | 7.04 | 12400 | 0.8979 | 0.8632 |
|
179 |
+
| 0.1028 | 7.09 | 12500 | 0.8936 | 0.8635 |
|
180 |
+
| 0.1028 | 7.15 | 12600 | 0.9043 | 0.8637 |
|
181 |
+
| 0.1028 | 7.21 | 12700 | 0.8989 | 0.8642 |
|
182 |
+
| 0.1028 | 7.26 | 12800 | 0.8936 | 0.8642 |
|
183 |
+
| 0.1028 | 7.32 | 12900 | 0.8921 | 0.8641 |
|
184 |
+
| 0.0774 | 7.38 | 13000 | 0.8955 | 0.8634 |
|
185 |
+
| 0.0774 | 7.43 | 13100 | 0.8950 | 0.8636 |
|
186 |
+
| 0.0774 | 7.49 | 13200 | 0.8994 | 0.8635 |
|
187 |
+
| 0.0774 | 7.55 | 13300 | 0.8999 | 0.8635 |
|
188 |
+
| 0.0774 | 7.6 | 13400 | 0.8936 | 0.8631 |
|
189 |
+
| 0.0852 | 7.66 | 13500 | 0.9048 | 0.8634 |
|
190 |
+
| 0.0852 | 7.72 | 13600 | 0.8960 | 0.8632 |
|
191 |
+
| 0.0852 | 7.78 | 13700 | 0.9023 | 0.8635 |
|
192 |
+
| 0.0852 | 7.83 | 13800 | 0.8984 | 0.8638 |
|
193 |
+
| 0.0852 | 7.89 | 13900 | 0.9019 | 0.8635 |
|
194 |
+
| 0.0879 | 7.95 | 14000 | 0.9014 | 0.8634 |
|
195 |
+
| 0.0879 | 8.0 | 14100 | 0.9136 | 0.8630 |
|
196 |
+
| 0.0879 | 8.06 | 14200 | 0.9312 | 0.8639 |
|
197 |
+
| 0.0879 | 8.12 | 14300 | 0.9346 | 0.8635 |
|
198 |
+
| 0.0879 | 8.17 | 14400 | 0.9307 | 0.8635 |
|
199 |
+
| 0.0611 | 8.23 | 14500 | 0.9419 | 0.8641 |
|
200 |
+
| 0.0611 | 8.29 | 14600 | 0.9331 | 0.8631 |
|
201 |
+
| 0.0611 | 8.34 | 14700 | 0.9375 | 0.8636 |
|
202 |
+
| 0.0611 | 8.4 | 14800 | 0.9292 | 0.8626 |
|
203 |
+
| 0.0611 | 8.46 | 14900 | 0.9458 | 0.8637 |
|
204 |
+
| 0.061 | 8.51 | 15000 | 0.9336 | 0.8634 |
|
205 |
+
| 0.061 | 8.57 | 15100 | 0.9409 | 0.8630 |
|
206 |
+
| 0.061 | 8.63 | 15200 | 0.9390 | 0.8632 |
|
207 |
+
| 0.061 | 8.68 | 15300 | 0.9375 | 0.8628 |
|
208 |
+
| 0.061 | 8.74 | 15400 | 0.9365 | 0.8630 |
|
209 |
+
| 0.0646 | 8.8 | 15500 | 0.9370 | 0.8628 |
|
210 |
+
| 0.0646 | 8.85 | 15600 | 0.9355 | 0.8629 |
|
211 |
+
| 0.0646 | 8.91 | 15700 | 0.9375 | 0.8632 |
|
212 |
+
| 0.0646 | 8.97 | 15800 | 0.9390 | 0.8630 |
|
213 |
+
| 0.0646 | 9.02 | 15900 | 0.9717 | 0.8630 |
|
214 |
+
| 0.0593 | 9.08 | 16000 | 0.9673 | 0.8626 |
|
215 |
+
| 0.0593 | 9.14 | 16100 | 0.9644 | 0.8630 |
|
216 |
+
| 0.0593 | 9.19 | 16200 | 0.9624 | 0.8631 |
|
217 |
+
| 0.0593 | 9.25 | 16300 | 0.9648 | 0.8633 |
|
218 |
+
| 0.0593 | 9.31 | 16400 | 0.9673 | 0.8632 |
|
219 |
+
| 0.0415 | 9.36 | 16500 | 0.9658 | 0.8633 |
|
220 |
+
| 0.0415 | 9.42 | 16600 | 0.9688 | 0.8628 |
|
221 |
+
| 0.0415 | 9.48 | 16700 | 0.9653 | 0.8632 |
|
222 |
+
| 0.0415 | 9.53 | 16800 | 0.9658 | 0.8628 |
|
223 |
+
| 0.0415 | 9.59 | 16900 | 0.9668 | 0.8629 |
|
224 |
+
| 0.0471 | 9.65 | 17000 | 0.9604 | 0.8625 |
|
225 |
+
| 0.0471 | 9.7 | 17100 | 0.9658 | 0.8621 |
|
226 |
+
| 0.0471 | 9.76 | 17200 | 0.9731 | 0.8630 |
|
227 |
+
| 0.0471 | 9.82 | 17300 | 0.9692 | 0.8626 |
|
228 |
+
| 0.0471 | 9.88 | 17400 | 0.9673 | 0.8623 |
|
229 |
+
| 0.0528 | 9.93 | 17500 | 0.9614 | 0.8620 |
|
230 |
+
| 0.0528 | 9.99 | 17600 | 0.9697 | 0.8621 |
|
231 |
+
|
232 |
+
|
233 |
+
### Framework versions
|
234 |
+
|
235 |
+
- Transformers 4.21.0.dev0
|
236 |
+
- Pytorch 1.12.1+cu113
|
237 |
+
- Datasets 2.4.0
|
238 |
+
- Tokenizers 0.12.1
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8663780555904803,
|
4 |
+
"eval_loss": 0.58837890625,
|
5 |
+
"eval_runtime": 291.8211,
|
6 |
+
"eval_samples": 4315,
|
7 |
+
"eval_samples_per_second": 14.786,
|
8 |
+
"eval_steps_per_second": 1.85,
|
9 |
+
"perplexity": 1.8010663501633464,
|
10 |
+
"train_loss": 0.2421213565700847,
|
11 |
+
"train_runtime": 122603.1424,
|
12 |
+
"train_samples": 14090,
|
13 |
+
"train_samples_per_second": 1.149,
|
14 |
+
"train_steps_per_second": 0.144
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/gpt-neo-2.7B",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local",
|
21 |
+
"global",
|
22 |
+
"local",
|
23 |
+
"global",
|
24 |
+
"local",
|
25 |
+
"global",
|
26 |
+
"local",
|
27 |
+
"global",
|
28 |
+
"local",
|
29 |
+
"global",
|
30 |
+
"local",
|
31 |
+
"global",
|
32 |
+
"local",
|
33 |
+
"global",
|
34 |
+
"local",
|
35 |
+
"global",
|
36 |
+
"local",
|
37 |
+
"global",
|
38 |
+
"local",
|
39 |
+
"global",
|
40 |
+
"local"
|
41 |
+
],
|
42 |
+
"attention_types": [
|
43 |
+
[
|
44 |
+
[
|
45 |
+
"global",
|
46 |
+
"local"
|
47 |
+
],
|
48 |
+
16
|
49 |
+
]
|
50 |
+
],
|
51 |
+
"bos_token_id": 50256,
|
52 |
+
"embed_dropout": 0,
|
53 |
+
"eos_token_id": 50256,
|
54 |
+
"gradient_checkpointing": false,
|
55 |
+
"hidden_size": 2560,
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": null,
|
58 |
+
"layer_norm_epsilon": 1e-05,
|
59 |
+
"max_position_embeddings": 2048,
|
60 |
+
"model_type": "gpt_neo",
|
61 |
+
"num_heads": 20,
|
62 |
+
"num_layers": 32,
|
63 |
+
"resid_dropout": 0,
|
64 |
+
"summary_activation": null,
|
65 |
+
"summary_first_dropout": 0.1,
|
66 |
+
"summary_proj_to_labels": true,
|
67 |
+
"summary_type": "cls_index",
|
68 |
+
"summary_use_proj": true,
|
69 |
+
"task_specific_params": {
|
70 |
+
"text-generation": {
|
71 |
+
"do_sample": true,
|
72 |
+
"max_length": 50,
|
73 |
+
"temperature": 0.9
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"tokenizer_class": "GPT2Tokenizer",
|
77 |
+
"torch_dtype": "float16",
|
78 |
+
"transformers_version": "4.21.0.dev0",
|
79 |
+
"use_cache": true,
|
80 |
+
"vocab_size": 50257,
|
81 |
+
"window_size": 256
|
82 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.8663780555904803,
|
4 |
+
"eval_loss": 0.58837890625,
|
5 |
+
"eval_runtime": 291.8211,
|
6 |
+
"eval_samples": 4315,
|
7 |
+
"eval_samples_per_second": 14.786,
|
8 |
+
"eval_steps_per_second": 1.85,
|
9 |
+
"perplexity": 1.8010663501633464
|
10 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:078fb54c98e33d61f8d121f0b99e7bbbe3d79b6dd9f40fe7c021bedf08162fdf
|
3 |
+
size 5436910218
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 2048,
|
22 |
+
"name_or_path": "EleutherAI/gpt-neo-2.7B",
|
23 |
+
"pad_token": null,
|
24 |
+
"special_tokens_map_file": null,
|
25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.2421213565700847,
|
4 |
+
"train_runtime": 122603.1424,
|
5 |
+
"train_samples": 14090,
|
6 |
+
"train_samples_per_second": 1.149,
|
7 |
+
"train_steps_per_second": 0.144
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1819 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.58837890625,
|
3 |
+
"best_model_checkpoint": "/output/checkpoint-3300",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 17620,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.06,
|
12 |
+
"eval_accuracy": 0.8214358287770616,
|
13 |
+
"eval_loss": 0.79296875,
|
14 |
+
"eval_runtime": 301.7299,
|
15 |
+
"eval_samples_per_second": 14.301,
|
16 |
+
"eval_steps_per_second": 1.79,
|
17 |
+
"step": 100
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.11,
|
21 |
+
"eval_accuracy": 0.828983212304709,
|
22 |
+
"eval_loss": 0.75439453125,
|
23 |
+
"eval_runtime": 295.5652,
|
24 |
+
"eval_samples_per_second": 14.599,
|
25 |
+
"eval_steps_per_second": 1.827,
|
26 |
+
"step": 200
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.17,
|
30 |
+
"eval_accuracy": 0.83275463867547,
|
31 |
+
"eval_loss": 0.73583984375,
|
32 |
+
"eval_runtime": 297.8323,
|
33 |
+
"eval_samples_per_second": 14.488,
|
34 |
+
"eval_steps_per_second": 1.813,
|
35 |
+
"step": 300
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.23,
|
39 |
+
"eval_accuracy": 0.8357279670702464,
|
40 |
+
"eval_loss": 0.71923828125,
|
41 |
+
"eval_runtime": 297.4382,
|
42 |
+
"eval_samples_per_second": 14.507,
|
43 |
+
"eval_steps_per_second": 1.816,
|
44 |
+
"step": 400
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.28,
|
48 |
+
"learning_rate": 5e-05,
|
49 |
+
"loss": 0.8156,
|
50 |
+
"step": 500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.28,
|
54 |
+
"eval_accuracy": 0.8396754144819782,
|
55 |
+
"eval_loss": 0.701171875,
|
56 |
+
"eval_runtime": 295.955,
|
57 |
+
"eval_samples_per_second": 14.58,
|
58 |
+
"eval_steps_per_second": 1.825,
|
59 |
+
"step": 500
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.34,
|
63 |
+
"eval_accuracy": 0.8418578941585707,
|
64 |
+
"eval_loss": 0.6904296875,
|
65 |
+
"eval_runtime": 305.3997,
|
66 |
+
"eval_samples_per_second": 14.129,
|
67 |
+
"eval_steps_per_second": 1.768,
|
68 |
+
"step": 600
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.4,
|
72 |
+
"eval_accuracy": 0.8439807939976145,
|
73 |
+
"eval_loss": 0.68017578125,
|
74 |
+
"eval_runtime": 303.944,
|
75 |
+
"eval_samples_per_second": 14.197,
|
76 |
+
"eval_steps_per_second": 1.777,
|
77 |
+
"step": 700
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.45,
|
81 |
+
"eval_accuracy": 0.8464999110833223,
|
82 |
+
"eval_loss": 0.6669921875,
|
83 |
+
"eval_runtime": 297.0827,
|
84 |
+
"eval_samples_per_second": 14.525,
|
85 |
+
"eval_steps_per_second": 1.818,
|
86 |
+
"step": 800
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.51,
|
90 |
+
"eval_accuracy": 0.8485815807686252,
|
91 |
+
"eval_loss": 0.6572265625,
|
92 |
+
"eval_runtime": 292.5803,
|
93 |
+
"eval_samples_per_second": 14.748,
|
94 |
+
"eval_steps_per_second": 1.846,
|
95 |
+
"step": 900
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.57,
|
99 |
+
"learning_rate": 5e-05,
|
100 |
+
"loss": 0.7219,
|
101 |
+
"step": 1000
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.57,
|
105 |
+
"eval_accuracy": 0.8500273546212319,
|
106 |
+
"eval_loss": 0.64990234375,
|
107 |
+
"eval_runtime": 292.7704,
|
108 |
+
"eval_samples_per_second": 14.739,
|
109 |
+
"eval_steps_per_second": 1.844,
|
110 |
+
"step": 1000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.62,
|
114 |
+
"eval_accuracy": 0.8521808372666221,
|
115 |
+
"eval_loss": 0.64111328125,
|
116 |
+
"eval_runtime": 292.5084,
|
117 |
+
"eval_samples_per_second": 14.752,
|
118 |
+
"eval_steps_per_second": 1.846,
|
119 |
+
"step": 1100
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.68,
|
123 |
+
"eval_accuracy": 0.853712016437692,
|
124 |
+
"eval_loss": 0.63427734375,
|
125 |
+
"eval_runtime": 292.6573,
|
126 |
+
"eval_samples_per_second": 14.744,
|
127 |
+
"eval_steps_per_second": 1.845,
|
128 |
+
"step": 1200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.74,
|
132 |
+
"eval_accuracy": 0.8545884970136456,
|
133 |
+
"eval_loss": 0.6298828125,
|
134 |
+
"eval_runtime": 291.6972,
|
135 |
+
"eval_samples_per_second": 14.793,
|
136 |
+
"eval_steps_per_second": 1.851,
|
137 |
+
"step": 1300
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.79,
|
141 |
+
"eval_accuracy": 0.856088866839063,
|
142 |
+
"eval_loss": 0.6220703125,
|
143 |
+
"eval_runtime": 291.6264,
|
144 |
+
"eval_samples_per_second": 14.796,
|
145 |
+
"eval_steps_per_second": 1.852,
|
146 |
+
"step": 1400
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.85,
|
150 |
+
"learning_rate": 5e-05,
|
151 |
+
"loss": 0.662,
|
152 |
+
"step": 1500
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.85,
|
156 |
+
"eval_accuracy": 0.857388975917739,
|
157 |
+
"eval_loss": 0.61572265625,
|
158 |
+
"eval_runtime": 292.8293,
|
159 |
+
"eval_samples_per_second": 14.736,
|
160 |
+
"eval_steps_per_second": 1.844,
|
161 |
+
"step": 1500
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.91,
|
165 |
+
"eval_accuracy": 0.8579150001868949,
|
166 |
+
"eval_loss": 0.61376953125,
|
167 |
+
"eval_runtime": 292.6424,
|
168 |
+
"eval_samples_per_second": 14.745,
|
169 |
+
"eval_steps_per_second": 1.845,
|
170 |
+
"step": 1600
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.96,
|
174 |
+
"eval_accuracy": 0.8595497078209298,
|
175 |
+
"eval_loss": 0.60546875,
|
176 |
+
"eval_runtime": 292.7935,
|
177 |
+
"eval_samples_per_second": 14.737,
|
178 |
+
"eval_steps_per_second": 1.844,
|
179 |
+
"step": 1700
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.02,
|
183 |
+
"eval_accuracy": 0.8597678651728665,
|
184 |
+
"eval_loss": 0.6142578125,
|
185 |
+
"eval_runtime": 292.6887,
|
186 |
+
"eval_samples_per_second": 14.743,
|
187 |
+
"eval_steps_per_second": 1.845,
|
188 |
+
"step": 1800
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.08,
|
192 |
+
"eval_accuracy": 0.8598800021294695,
|
193 |
+
"eval_loss": 0.619140625,
|
194 |
+
"eval_runtime": 291.7039,
|
195 |
+
"eval_samples_per_second": 14.792,
|
196 |
+
"eval_steps_per_second": 1.851,
|
197 |
+
"step": 1900
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.14,
|
201 |
+
"learning_rate": 5e-05,
|
202 |
+
"loss": 0.5707,
|
203 |
+
"step": 2000
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 1.14,
|
207 |
+
"eval_accuracy": 0.8606622423540152,
|
208 |
+
"eval_loss": 0.61181640625,
|
209 |
+
"eval_runtime": 292.661,
|
210 |
+
"eval_samples_per_second": 14.744,
|
211 |
+
"eval_steps_per_second": 1.845,
|
212 |
+
"step": 2000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.19,
|
216 |
+
"eval_accuracy": 0.8611497549411055,
|
217 |
+
"eval_loss": 0.6123046875,
|
218 |
+
"eval_runtime": 292.734,
|
219 |
+
"eval_samples_per_second": 14.74,
|
220 |
+
"eval_steps_per_second": 1.845,
|
221 |
+
"step": 2100
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.25,
|
225 |
+
"eval_accuracy": 0.8616524456617156,
|
226 |
+
"eval_loss": 0.60888671875,
|
227 |
+
"eval_runtime": 291.6011,
|
228 |
+
"eval_samples_per_second": 14.798,
|
229 |
+
"eval_steps_per_second": 1.852,
|
230 |
+
"step": 2200
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.31,
|
234 |
+
"eval_accuracy": 0.8618950692587294,
|
235 |
+
"eval_loss": 0.6064453125,
|
236 |
+
"eval_runtime": 291.5809,
|
237 |
+
"eval_samples_per_second": 14.799,
|
238 |
+
"eval_steps_per_second": 1.852,
|
239 |
+
"step": 2300
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.36,
|
243 |
+
"eval_accuracy": 0.8625089907787176,
|
244 |
+
"eval_loss": 0.60791015625,
|
245 |
+
"eval_runtime": 292.7393,
|
246 |
+
"eval_samples_per_second": 14.74,
|
247 |
+
"eval_steps_per_second": 1.845,
|
248 |
+
"step": 2400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.42,
|
252 |
+
"learning_rate": 5e-05,
|
253 |
+
"loss": 0.4923,
|
254 |
+
"step": 2500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.42,
|
258 |
+
"eval_accuracy": 0.8624713852538769,
|
259 |
+
"eval_loss": 0.60400390625,
|
260 |
+
"eval_runtime": 292.7894,
|
261 |
+
"eval_samples_per_second": 14.738,
|
262 |
+
"eval_steps_per_second": 1.844,
|
263 |
+
"step": 2500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.48,
|
267 |
+
"eval_accuracy": 0.8630089630276525,
|
268 |
+
"eval_loss": 0.60302734375,
|
269 |
+
"eval_runtime": 291.5842,
|
270 |
+
"eval_samples_per_second": 14.798,
|
271 |
+
"eval_steps_per_second": 1.852,
|
272 |
+
"step": 2600
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.53,
|
276 |
+
"eval_accuracy": 0.8636167679863714,
|
277 |
+
"eval_loss": 0.60205078125,
|
278 |
+
"eval_runtime": 291.6586,
|
279 |
+
"eval_samples_per_second": 14.795,
|
280 |
+
"eval_steps_per_second": 1.851,
|
281 |
+
"step": 2700
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.59,
|
285 |
+
"eval_accuracy": 0.8643006901519965,
|
286 |
+
"eval_loss": 0.60009765625,
|
287 |
+
"eval_runtime": 291.5536,
|
288 |
+
"eval_samples_per_second": 14.8,
|
289 |
+
"eval_steps_per_second": 1.852,
|
290 |
+
"step": 2800
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.65,
|
294 |
+
"eval_accuracy": 0.864360949607464,
|
295 |
+
"eval_loss": 0.59814453125,
|
296 |
+
"eval_runtime": 292.9127,
|
297 |
+
"eval_samples_per_second": 14.731,
|
298 |
+
"eval_steps_per_second": 1.844,
|
299 |
+
"step": 2900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.7,
|
303 |
+
"learning_rate": 5e-05,
|
304 |
+
"loss": 0.4909,
|
305 |
+
"step": 3000
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 1.7,
|
309 |
+
"eval_accuracy": 0.8647961316148062,
|
310 |
+
"eval_loss": 0.59423828125,
|
311 |
+
"eval_runtime": 292.7189,
|
312 |
+
"eval_samples_per_second": 14.741,
|
313 |
+
"eval_steps_per_second": 1.845,
|
314 |
+
"step": 3000
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.76,
|
318 |
+
"eval_accuracy": 0.8649898227216659,
|
319 |
+
"eval_loss": 0.591796875,
|
320 |
+
"eval_runtime": 291.4828,
|
321 |
+
"eval_samples_per_second": 14.804,
|
322 |
+
"eval_steps_per_second": 1.853,
|
323 |
+
"step": 3100
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.82,
|
327 |
+
"eval_accuracy": 0.8659145561698547,
|
328 |
+
"eval_loss": 0.59228515625,
|
329 |
+
"eval_runtime": 291.6085,
|
330 |
+
"eval_samples_per_second": 14.797,
|
331 |
+
"eval_steps_per_second": 1.852,
|
332 |
+
"step": 3200
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.87,
|
336 |
+
"eval_accuracy": 0.8663780555904803,
|
337 |
+
"eval_loss": 0.58837890625,
|
338 |
+
"eval_runtime": 291.6163,
|
339 |
+
"eval_samples_per_second": 14.797,
|
340 |
+
"eval_steps_per_second": 1.852,
|
341 |
+
"step": 3300
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.93,
|
345 |
+
"eval_accuracy": 0.8662514201182762,
|
346 |
+
"eval_loss": 0.58837890625,
|
347 |
+
"eval_runtime": 291.7936,
|
348 |
+
"eval_samples_per_second": 14.788,
|
349 |
+
"eval_steps_per_second": 1.851,
|
350 |
+
"step": 3400
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.99,
|
354 |
+
"learning_rate": 5e-05,
|
355 |
+
"loss": 0.4964,
|
356 |
+
"step": 3500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.99,
|
360 |
+
"eval_accuracy": 0.8669489346422774,
|
361 |
+
"eval_loss": 0.59033203125,
|
362 |
+
"eval_runtime": 291.5679,
|
363 |
+
"eval_samples_per_second": 14.799,
|
364 |
+
"eval_steps_per_second": 1.852,
|
365 |
+
"step": 3500
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 2.04,
|
369 |
+
"eval_accuracy": 0.8654691798937304,
|
370 |
+
"eval_loss": 0.64208984375,
|
371 |
+
"eval_runtime": 291.7326,
|
372 |
+
"eval_samples_per_second": 14.791,
|
373 |
+
"eval_steps_per_second": 1.851,
|
374 |
+
"step": 3600
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.1,
|
378 |
+
"eval_accuracy": 0.8650994677459,
|
379 |
+
"eval_loss": 0.64013671875,
|
380 |
+
"eval_runtime": 293.0337,
|
381 |
+
"eval_samples_per_second": 14.725,
|
382 |
+
"eval_steps_per_second": 1.843,
|
383 |
+
"step": 3700
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 2.16,
|
387 |
+
"eval_accuracy": 0.8649474598713937,
|
388 |
+
"eval_loss": 0.64111328125,
|
389 |
+
"eval_runtime": 291.5404,
|
390 |
+
"eval_samples_per_second": 14.801,
|
391 |
+
"eval_steps_per_second": 1.852,
|
392 |
+
"step": 3800
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.21,
|
396 |
+
"eval_accuracy": 0.8645410483559476,
|
397 |
+
"eval_loss": 0.638671875,
|
398 |
+
"eval_runtime": 291.6679,
|
399 |
+
"eval_samples_per_second": 14.794,
|
400 |
+
"eval_steps_per_second": 1.851,
|
401 |
+
"step": 3900
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.27,
|
405 |
+
"learning_rate": 5e-05,
|
406 |
+
"loss": 0.345,
|
407 |
+
"step": 4000
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 2.27,
|
411 |
+
"eval_accuracy": 0.8653572694764337,
|
412 |
+
"eval_loss": 0.63623046875,
|
413 |
+
"eval_runtime": 291.7901,
|
414 |
+
"eval_samples_per_second": 14.788,
|
415 |
+
"eval_steps_per_second": 1.851,
|
416 |
+
"step": 4000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.33,
|
420 |
+
"eval_accuracy": 0.8654186616284325,
|
421 |
+
"eval_loss": 0.63623046875,
|
422 |
+
"eval_runtime": 291.6935,
|
423 |
+
"eval_samples_per_second": 14.793,
|
424 |
+
"eval_steps_per_second": 1.851,
|
425 |
+
"step": 4100
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 2.38,
|
429 |
+
"eval_accuracy": 0.8653559102405961,
|
430 |
+
"eval_loss": 0.63623046875,
|
431 |
+
"eval_runtime": 291.8601,
|
432 |
+
"eval_samples_per_second": 14.784,
|
433 |
+
"eval_steps_per_second": 1.85,
|
434 |
+
"step": 4200
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.44,
|
438 |
+
"eval_accuracy": 0.8654696329723429,
|
439 |
+
"eval_loss": 0.6357421875,
|
440 |
+
"eval_runtime": 292.876,
|
441 |
+
"eval_samples_per_second": 14.733,
|
442 |
+
"eval_steps_per_second": 1.844,
|
443 |
+
"step": 4300
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.5,
|
447 |
+
"eval_accuracy": 0.8655647794809758,
|
448 |
+
"eval_loss": 0.63623046875,
|
449 |
+
"eval_runtime": 291.8742,
|
450 |
+
"eval_samples_per_second": 14.784,
|
451 |
+
"eval_steps_per_second": 1.85,
|
452 |
+
"step": 4400
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 2.55,
|
456 |
+
"learning_rate": 5e-05,
|
457 |
+
"loss": 0.3463,
|
458 |
+
"step": 4500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.55,
|
462 |
+
"eval_accuracy": 0.865790865708632,
|
463 |
+
"eval_loss": 0.6376953125,
|
464 |
+
"eval_runtime": 292.8657,
|
465 |
+
"eval_samples_per_second": 14.734,
|
466 |
+
"eval_steps_per_second": 1.844,
|
467 |
+
"step": 4500
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 2.61,
|
471 |
+
"eval_accuracy": 0.8660047188137496,
|
472 |
+
"eval_loss": 0.6357421875,
|
473 |
+
"eval_runtime": 292.8962,
|
474 |
+
"eval_samples_per_second": 14.732,
|
475 |
+
"eval_steps_per_second": 1.844,
|
476 |
+
"step": 4600
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.67,
|
480 |
+
"eval_accuracy": 0.8664827167499765,
|
481 |
+
"eval_loss": 0.62939453125,
|
482 |
+
"eval_runtime": 291.8634,
|
483 |
+
"eval_samples_per_second": 14.784,
|
484 |
+
"eval_steps_per_second": 1.85,
|
485 |
+
"step": 4700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.72,
|
489 |
+
"eval_accuracy": 0.8664838494465078,
|
490 |
+
"eval_loss": 0.63330078125,
|
491 |
+
"eval_runtime": 292.9139,
|
492 |
+
"eval_samples_per_second": 14.731,
|
493 |
+
"eval_steps_per_second": 1.844,
|
494 |
+
"step": 4800
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 2.78,
|
498 |
+
"eval_accuracy": 0.8661707721252445,
|
499 |
+
"eval_loss": 0.63623046875,
|
500 |
+
"eval_runtime": 291.8657,
|
501 |
+
"eval_samples_per_second": 14.784,
|
502 |
+
"eval_steps_per_second": 1.85,
|
503 |
+
"step": 4900
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 2.84,
|
507 |
+
"learning_rate": 5e-05,
|
508 |
+
"loss": 0.3508,
|
509 |
+
"step": 5000
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.84,
|
513 |
+
"eval_accuracy": 0.8666297407597449,
|
514 |
+
"eval_loss": 0.6357421875,
|
515 |
+
"eval_runtime": 291.8826,
|
516 |
+
"eval_samples_per_second": 14.783,
|
517 |
+
"eval_steps_per_second": 1.85,
|
518 |
+
"step": 5000
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 2.89,
|
522 |
+
"eval_accuracy": 0.8673172875542703,
|
523 |
+
"eval_loss": 0.6298828125,
|
524 |
+
"eval_runtime": 291.7729,
|
525 |
+
"eval_samples_per_second": 14.789,
|
526 |
+
"eval_steps_per_second": 1.851,
|
527 |
+
"step": 5100
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 2.95,
|
531 |
+
"eval_accuracy": 0.866801004475284,
|
532 |
+
"eval_loss": 0.63134765625,
|
533 |
+
"eval_runtime": 291.9322,
|
534 |
+
"eval_samples_per_second": 14.781,
|
535 |
+
"eval_steps_per_second": 1.85,
|
536 |
+
"step": 5200
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 3.01,
|
540 |
+
"eval_accuracy": 0.8646230555848169,
|
541 |
+
"eval_loss": 0.71875,
|
542 |
+
"eval_runtime": 291.8776,
|
543 |
+
"eval_samples_per_second": 14.784,
|
544 |
+
"eval_steps_per_second": 1.85,
|
545 |
+
"step": 5300
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 3.06,
|
549 |
+
"eval_accuracy": 0.8655867537936839,
|
550 |
+
"eval_loss": 0.70166015625,
|
551 |
+
"eval_runtime": 293.0438,
|
552 |
+
"eval_samples_per_second": 14.725,
|
553 |
+
"eval_steps_per_second": 1.843,
|
554 |
+
"step": 5400
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 3.12,
|
558 |
+
"learning_rate": 5e-05,
|
559 |
+
"loss": 0.295,
|
560 |
+
"step": 5500
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 3.12,
|
564 |
+
"eval_accuracy": 0.8652775276406272,
|
565 |
+
"eval_loss": 0.6982421875,
|
566 |
+
"eval_runtime": 291.9251,
|
567 |
+
"eval_samples_per_second": 14.781,
|
568 |
+
"eval_steps_per_second": 1.85,
|
569 |
+
"step": 5500
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 3.18,
|
573 |
+
"eval_accuracy": 0.8654533221422916,
|
574 |
+
"eval_loss": 0.703125,
|
575 |
+
"eval_runtime": 292.9873,
|
576 |
+
"eval_samples_per_second": 14.728,
|
577 |
+
"eval_steps_per_second": 1.843,
|
578 |
+
"step": 5600
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 3.23,
|
582 |
+
"eval_accuracy": 0.8650992412065936,
|
583 |
+
"eval_loss": 0.69921875,
|
584 |
+
"eval_runtime": 293.1169,
|
585 |
+
"eval_samples_per_second": 14.721,
|
586 |
+
"eval_steps_per_second": 1.842,
|
587 |
+
"step": 5700
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 3.29,
|
591 |
+
"eval_accuracy": 0.8652641618215573,
|
592 |
+
"eval_loss": 0.69970703125,
|
593 |
+
"eval_runtime": 293.0467,
|
594 |
+
"eval_samples_per_second": 14.725,
|
595 |
+
"eval_steps_per_second": 1.843,
|
596 |
+
"step": 5800
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 3.35,
|
600 |
+
"eval_accuracy": 0.865102865835494,
|
601 |
+
"eval_loss": 0.7041015625,
|
602 |
+
"eval_runtime": 292.9654,
|
603 |
+
"eval_samples_per_second": 14.729,
|
604 |
+
"eval_steps_per_second": 1.843,
|
605 |
+
"step": 5900
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 3.41,
|
609 |
+
"learning_rate": 5e-05,
|
610 |
+
"loss": 0.2348,
|
611 |
+
"step": 6000
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 3.41,
|
615 |
+
"eval_accuracy": 0.8649191424581101,
|
616 |
+
"eval_loss": 0.70751953125,
|
617 |
+
"eval_runtime": 291.6546,
|
618 |
+
"eval_samples_per_second": 14.795,
|
619 |
+
"eval_steps_per_second": 1.852,
|
620 |
+
"step": 6000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 3.46,
|
624 |
+
"eval_accuracy": 0.8649929942719536,
|
625 |
+
"eval_loss": 0.69921875,
|
626 |
+
"eval_runtime": 293.0033,
|
627 |
+
"eval_samples_per_second": 14.727,
|
628 |
+
"eval_steps_per_second": 1.843,
|
629 |
+
"step": 6100
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 3.52,
|
633 |
+
"eval_accuracy": 0.8647333802269698,
|
634 |
+
"eval_loss": 0.70654296875,
|
635 |
+
"eval_runtime": 292.0433,
|
636 |
+
"eval_samples_per_second": 14.775,
|
637 |
+
"eval_steps_per_second": 1.849,
|
638 |
+
"step": 6200
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 3.58,
|
642 |
+
"eval_accuracy": 0.8651932550186952,
|
643 |
+
"eval_loss": 0.69970703125,
|
644 |
+
"eval_runtime": 292.8338,
|
645 |
+
"eval_samples_per_second": 14.735,
|
646 |
+
"eval_steps_per_second": 1.844,
|
647 |
+
"step": 6300
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 3.63,
|
651 |
+
"eval_accuracy": 0.8651128335649698,
|
652 |
+
"eval_loss": 0.70263671875,
|
653 |
+
"eval_runtime": 291.8152,
|
654 |
+
"eval_samples_per_second": 14.787,
|
655 |
+
"eval_steps_per_second": 1.85,
|
656 |
+
"step": 6400
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 3.69,
|
660 |
+
"learning_rate": 5e-05,
|
661 |
+
"loss": 0.2411,
|
662 |
+
"step": 6500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 3.69,
|
666 |
+
"eval_accuracy": 0.8655713491208575,
|
667 |
+
"eval_loss": 0.70458984375,
|
668 |
+
"eval_runtime": 292.9241,
|
669 |
+
"eval_samples_per_second": 14.731,
|
670 |
+
"eval_steps_per_second": 1.843,
|
671 |
+
"step": 6500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 3.75,
|
675 |
+
"eval_accuracy": 0.8655097304295525,
|
676 |
+
"eval_loss": 0.70068359375,
|
677 |
+
"eval_runtime": 293.0902,
|
678 |
+
"eval_samples_per_second": 14.722,
|
679 |
+
"eval_steps_per_second": 1.842,
|
680 |
+
"step": 6600
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 3.8,
|
684 |
+
"eval_accuracy": 0.8651318628666963,
|
685 |
+
"eval_loss": 0.70263671875,
|
686 |
+
"eval_runtime": 292.9879,
|
687 |
+
"eval_samples_per_second": 14.728,
|
688 |
+
"eval_steps_per_second": 1.843,
|
689 |
+
"step": 6700
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 3.86,
|
693 |
+
"eval_accuracy": 0.8654825457128003,
|
694 |
+
"eval_loss": 0.703125,
|
695 |
+
"eval_runtime": 292.8939,
|
696 |
+
"eval_samples_per_second": 14.732,
|
697 |
+
"eval_steps_per_second": 1.844,
|
698 |
+
"step": 6800
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 3.92,
|
702 |
+
"eval_accuracy": 0.8657906391693256,
|
703 |
+
"eval_loss": 0.701171875,
|
704 |
+
"eval_runtime": 292.7957,
|
705 |
+
"eval_samples_per_second": 14.737,
|
706 |
+
"eval_steps_per_second": 1.844,
|
707 |
+
"step": 6900
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 3.97,
|
711 |
+
"learning_rate": 5e-05,
|
712 |
+
"loss": 0.251,
|
713 |
+
"step": 7000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 3.97,
|
717 |
+
"eval_accuracy": 0.8656236797006056,
|
718 |
+
"eval_loss": 0.705078125,
|
719 |
+
"eval_runtime": 292.768,
|
720 |
+
"eval_samples_per_second": 14.739,
|
721 |
+
"eval_steps_per_second": 1.844,
|
722 |
+
"step": 7000
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 4.03,
|
726 |
+
"eval_accuracy": 0.8650197259100934,
|
727 |
+
"eval_loss": 0.7607421875,
|
728 |
+
"eval_runtime": 293.0243,
|
729 |
+
"eval_samples_per_second": 14.726,
|
730 |
+
"eval_steps_per_second": 1.843,
|
731 |
+
"step": 7100
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 4.09,
|
735 |
+
"eval_accuracy": 0.8655654590988946,
|
736 |
+
"eval_loss": 0.76318359375,
|
737 |
+
"eval_runtime": 293.1258,
|
738 |
+
"eval_samples_per_second": 14.721,
|
739 |
+
"eval_steps_per_second": 1.842,
|
740 |
+
"step": 7200
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 4.14,
|
744 |
+
"eval_accuracy": 0.8654986300035453,
|
745 |
+
"eval_loss": 0.7587890625,
|
746 |
+
"eval_runtime": 291.7489,
|
747 |
+
"eval_samples_per_second": 14.79,
|
748 |
+
"eval_steps_per_second": 1.851,
|
749 |
+
"step": 7300
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 4.2,
|
753 |
+
"eval_accuracy": 0.8650992412065936,
|
754 |
+
"eval_loss": 0.7578125,
|
755 |
+
"eval_runtime": 291.7365,
|
756 |
+
"eval_samples_per_second": 14.791,
|
757 |
+
"eval_steps_per_second": 1.851,
|
758 |
+
"step": 7400
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 4.26,
|
762 |
+
"learning_rate": 5e-05,
|
763 |
+
"loss": 0.1797,
|
764 |
+
"step": 7500
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 4.26,
|
768 |
+
"eval_accuracy": 0.8644635719132038,
|
769 |
+
"eval_loss": 0.77099609375,
|
770 |
+
"eval_runtime": 292.8962,
|
771 |
+
"eval_samples_per_second": 14.732,
|
772 |
+
"eval_steps_per_second": 1.844,
|
773 |
+
"step": 7500
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 4.31,
|
777 |
+
"eval_accuracy": 0.8648369086899346,
|
778 |
+
"eval_loss": 0.7626953125,
|
779 |
+
"eval_runtime": 291.9443,
|
780 |
+
"eval_samples_per_second": 14.78,
|
781 |
+
"eval_steps_per_second": 1.85,
|
782 |
+
"step": 7600
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 4.37,
|
786 |
+
"eval_accuracy": 0.8650006966083668,
|
787 |
+
"eval_loss": 0.75830078125,
|
788 |
+
"eval_runtime": 292.6223,
|
789 |
+
"eval_samples_per_second": 14.746,
|
790 |
+
"eval_steps_per_second": 1.845,
|
791 |
+
"step": 7700
|
792 |
+
},
|
793 |
+
{
|
794 |
+
"epoch": 4.43,
|
795 |
+
"eval_accuracy": 0.8648572972274987,
|
796 |
+
"eval_loss": 0.7646484375,
|
797 |
+
"eval_runtime": 292.6746,
|
798 |
+
"eval_samples_per_second": 14.743,
|
799 |
+
"eval_steps_per_second": 1.845,
|
800 |
+
"step": 7800
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 4.48,
|
804 |
+
"eval_accuracy": 0.8645709515443751,
|
805 |
+
"eval_loss": 0.759765625,
|
806 |
+
"eval_runtime": 292.8238,
|
807 |
+
"eval_samples_per_second": 14.736,
|
808 |
+
"eval_steps_per_second": 1.844,
|
809 |
+
"step": 7900
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 4.54,
|
813 |
+
"learning_rate": 5e-05,
|
814 |
+
"loss": 0.1784,
|
815 |
+
"step": 8000
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 4.54,
|
819 |
+
"eval_accuracy": 0.8649886900251346,
|
820 |
+
"eval_loss": 0.765625,
|
821 |
+
"eval_runtime": 292.7739,
|
822 |
+
"eval_samples_per_second": 14.738,
|
823 |
+
"eval_steps_per_second": 1.844,
|
824 |
+
"step": 8000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 4.6,
|
828 |
+
"eval_accuracy": 0.8647777819309984,
|
829 |
+
"eval_loss": 0.76171875,
|
830 |
+
"eval_runtime": 291.5794,
|
831 |
+
"eval_samples_per_second": 14.799,
|
832 |
+
"eval_steps_per_second": 1.852,
|
833 |
+
"step": 8100
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 4.65,
|
837 |
+
"eval_accuracy": 0.8650895000164242,
|
838 |
+
"eval_loss": 0.75732421875,
|
839 |
+
"eval_runtime": 292.5766,
|
840 |
+
"eval_samples_per_second": 14.748,
|
841 |
+
"eval_steps_per_second": 1.846,
|
842 |
+
"step": 8200
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 4.71,
|
846 |
+
"eval_accuracy": 0.8647773288523859,
|
847 |
+
"eval_loss": 0.76708984375,
|
848 |
+
"eval_runtime": 292.8751,
|
849 |
+
"eval_samples_per_second": 14.733,
|
850 |
+
"eval_steps_per_second": 1.844,
|
851 |
+
"step": 8300
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 4.77,
|
855 |
+
"eval_accuracy": 0.8651295974736336,
|
856 |
+
"eval_loss": 0.75634765625,
|
857 |
+
"eval_runtime": 292.7435,
|
858 |
+
"eval_samples_per_second": 14.74,
|
859 |
+
"eval_steps_per_second": 1.845,
|
860 |
+
"step": 8400
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 4.82,
|
864 |
+
"learning_rate": 5e-05,
|
865 |
+
"loss": 0.1827,
|
866 |
+
"step": 8500
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 4.82,
|
870 |
+
"eval_accuracy": 0.8648883331124575,
|
871 |
+
"eval_loss": 0.76513671875,
|
872 |
+
"eval_runtime": 291.561,
|
873 |
+
"eval_samples_per_second": 14.8,
|
874 |
+
"eval_steps_per_second": 1.852,
|
875 |
+
"step": 8500
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 4.88,
|
879 |
+
"eval_accuracy": 0.8649513110396002,
|
880 |
+
"eval_loss": 0.763671875,
|
881 |
+
"eval_runtime": 292.871,
|
882 |
+
"eval_samples_per_second": 14.733,
|
883 |
+
"eval_steps_per_second": 1.844,
|
884 |
+
"step": 8600
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 4.94,
|
888 |
+
"eval_accuracy": 0.8653917034509865,
|
889 |
+
"eval_loss": 0.7607421875,
|
890 |
+
"eval_runtime": 292.9668,
|
891 |
+
"eval_samples_per_second": 14.729,
|
892 |
+
"eval_steps_per_second": 1.843,
|
893 |
+
"step": 8700
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 4.99,
|
897 |
+
"eval_accuracy": 0.86499322081126,
|
898 |
+
"eval_loss": 0.7607421875,
|
899 |
+
"eval_runtime": 292.8128,
|
900 |
+
"eval_samples_per_second": 14.736,
|
901 |
+
"eval_steps_per_second": 1.844,
|
902 |
+
"step": 8800
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 5.05,
|
906 |
+
"eval_accuracy": 0.8645997220362712,
|
907 |
+
"eval_loss": 0.81494140625,
|
908 |
+
"eval_runtime": 292.864,
|
909 |
+
"eval_samples_per_second": 14.734,
|
910 |
+
"eval_steps_per_second": 1.844,
|
911 |
+
"step": 8900
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 5.11,
|
915 |
+
"learning_rate": 5e-05,
|
916 |
+
"loss": 0.167,
|
917 |
+
"step": 9000
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 5.11,
|
921 |
+
"eval_accuracy": 0.8647852577281052,
|
922 |
+
"eval_loss": 0.80810546875,
|
923 |
+
"eval_runtime": 292.7519,
|
924 |
+
"eval_samples_per_second": 14.739,
|
925 |
+
"eval_steps_per_second": 1.845,
|
926 |
+
"step": 9000
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 5.16,
|
930 |
+
"eval_accuracy": 0.8643582311357888,
|
931 |
+
"eval_loss": 0.818359375,
|
932 |
+
"eval_runtime": 291.6434,
|
933 |
+
"eval_samples_per_second": 14.795,
|
934 |
+
"eval_steps_per_second": 1.852,
|
935 |
+
"step": 9100
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 5.22,
|
939 |
+
"eval_accuracy": 0.8647263575084754,
|
940 |
+
"eval_loss": 0.81396484375,
|
941 |
+
"eval_runtime": 292.5189,
|
942 |
+
"eval_samples_per_second": 14.751,
|
943 |
+
"eval_steps_per_second": 1.846,
|
944 |
+
"step": 9200
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 5.28,
|
948 |
+
"eval_accuracy": 0.8643802054484968,
|
949 |
+
"eval_loss": 0.81689453125,
|
950 |
+
"eval_runtime": 291.4921,
|
951 |
+
"eval_samples_per_second": 14.803,
|
952 |
+
"eval_steps_per_second": 1.853,
|
953 |
+
"step": 9300
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 5.33,
|
957 |
+
"eval_accuracy": 0.8644685557779417,
|
958 |
+
"eval_loss": 0.81201171875,
|
959 |
+
"eval_runtime": 292.6907,
|
960 |
+
"eval_samples_per_second": 14.743,
|
961 |
+
"eval_steps_per_second": 1.845,
|
962 |
+
"step": 9400
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 5.39,
|
966 |
+
"learning_rate": 5e-05,
|
967 |
+
"loss": 0.1371,
|
968 |
+
"step": 9500
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 5.39,
|
972 |
+
"eval_accuracy": 0.8642560619086617,
|
973 |
+
"eval_loss": 0.8154296875,
|
974 |
+
"eval_runtime": 292.8129,
|
975 |
+
"eval_samples_per_second": 14.736,
|
976 |
+
"eval_steps_per_second": 1.844,
|
977 |
+
"step": 9500
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 5.45,
|
981 |
+
"eval_accuracy": 0.8642103009687954,
|
982 |
+
"eval_loss": 0.81787109375,
|
983 |
+
"eval_runtime": 292.7443,
|
984 |
+
"eval_samples_per_second": 14.74,
|
985 |
+
"eval_steps_per_second": 1.845,
|
986 |
+
"step": 9600
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 5.51,
|
990 |
+
"eval_accuracy": 0.8642599130768682,
|
991 |
+
"eval_loss": 0.8154296875,
|
992 |
+
"eval_runtime": 291.6813,
|
993 |
+
"eval_samples_per_second": 14.794,
|
994 |
+
"eval_steps_per_second": 1.851,
|
995 |
+
"step": 9700
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 5.56,
|
999 |
+
"eval_accuracy": 0.8645023101345757,
|
1000 |
+
"eval_loss": 0.81201171875,
|
1001 |
+
"eval_runtime": 292.6716,
|
1002 |
+
"eval_samples_per_second": 14.743,
|
1003 |
+
"eval_steps_per_second": 1.845,
|
1004 |
+
"step": 9800
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 5.62,
|
1008 |
+
"eval_accuracy": 0.8649979781366915,
|
1009 |
+
"eval_loss": 0.81103515625,
|
1010 |
+
"eval_runtime": 292.7654,
|
1011 |
+
"eval_samples_per_second": 14.739,
|
1012 |
+
"eval_steps_per_second": 1.844,
|
1013 |
+
"step": 9900
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 5.68,
|
1017 |
+
"learning_rate": 5e-05,
|
1018 |
+
"loss": 0.1425,
|
1019 |
+
"step": 10000
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 5.68,
|
1023 |
+
"eval_accuracy": 0.8645428606703978,
|
1024 |
+
"eval_loss": 0.81591796875,
|
1025 |
+
"eval_runtime": 292.6875,
|
1026 |
+
"eval_samples_per_second": 14.743,
|
1027 |
+
"eval_steps_per_second": 1.845,
|
1028 |
+
"step": 10000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 5.73,
|
1032 |
+
"eval_accuracy": 0.8646024405079464,
|
1033 |
+
"eval_loss": 0.8173828125,
|
1034 |
+
"eval_runtime": 292.6736,
|
1035 |
+
"eval_samples_per_second": 14.743,
|
1036 |
+
"eval_steps_per_second": 1.845,
|
1037 |
+
"step": 10100
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 5.79,
|
1041 |
+
"eval_accuracy": 0.8649073624141841,
|
1042 |
+
"eval_loss": 0.81591796875,
|
1043 |
+
"eval_runtime": 292.7868,
|
1044 |
+
"eval_samples_per_second": 14.738,
|
1045 |
+
"eval_steps_per_second": 1.844,
|
1046 |
+
"step": 10200
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 5.85,
|
1050 |
+
"eval_accuracy": 0.8639400395764169,
|
1051 |
+
"eval_loss": 0.81103515625,
|
1052 |
+
"eval_runtime": 292.8417,
|
1053 |
+
"eval_samples_per_second": 14.735,
|
1054 |
+
"eval_steps_per_second": 1.844,
|
1055 |
+
"step": 10300
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 5.9,
|
1059 |
+
"eval_accuracy": 0.8645482976137482,
|
1060 |
+
"eval_loss": 0.8134765625,
|
1061 |
+
"eval_runtime": 292.765,
|
1062 |
+
"eval_samples_per_second": 14.739,
|
1063 |
+
"eval_steps_per_second": 1.844,
|
1064 |
+
"step": 10400
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 5.96,
|
1068 |
+
"learning_rate": 5e-05,
|
1069 |
+
"loss": 0.1505,
|
1070 |
+
"step": 10500
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 5.96,
|
1074 |
+
"eval_accuracy": 0.8642195890803523,
|
1075 |
+
"eval_loss": 0.81396484375,
|
1076 |
+
"eval_runtime": 292.5807,
|
1077 |
+
"eval_samples_per_second": 14.748,
|
1078 |
+
"eval_steps_per_second": 1.846,
|
1079 |
+
"step": 10500
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 6.02,
|
1083 |
+
"eval_accuracy": 0.8639674508324753,
|
1084 |
+
"eval_loss": 0.86279296875,
|
1085 |
+
"eval_runtime": 292.6261,
|
1086 |
+
"eval_samples_per_second": 14.746,
|
1087 |
+
"eval_steps_per_second": 1.845,
|
1088 |
+
"step": 10600
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 6.07,
|
1092 |
+
"eval_accuracy": 0.8644205294450127,
|
1093 |
+
"eval_loss": 0.85400390625,
|
1094 |
+
"eval_runtime": 292.6297,
|
1095 |
+
"eval_samples_per_second": 14.746,
|
1096 |
+
"eval_steps_per_second": 1.845,
|
1097 |
+
"step": 10700
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 6.13,
|
1101 |
+
"eval_accuracy": 0.8642433757075105,
|
1102 |
+
"eval_loss": 0.85302734375,
|
1103 |
+
"eval_runtime": 291.5398,
|
1104 |
+
"eval_samples_per_second": 14.801,
|
1105 |
+
"eval_steps_per_second": 1.852,
|
1106 |
+
"step": 10800
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 6.19,
|
1110 |
+
"eval_accuracy": 0.8646898846801662,
|
1111 |
+
"eval_loss": 0.85595703125,
|
1112 |
+
"eval_runtime": 291.664,
|
1113 |
+
"eval_samples_per_second": 14.794,
|
1114 |
+
"eval_steps_per_second": 1.851,
|
1115 |
+
"step": 10900
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 6.24,
|
1119 |
+
"learning_rate": 5e-05,
|
1120 |
+
"loss": 0.1086,
|
1121 |
+
"step": 11000
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 6.24,
|
1125 |
+
"eval_accuracy": 0.864855937991661,
|
1126 |
+
"eval_loss": 0.85546875,
|
1127 |
+
"eval_runtime": 292.8292,
|
1128 |
+
"eval_samples_per_second": 14.736,
|
1129 |
+
"eval_steps_per_second": 1.844,
|
1130 |
+
"step": 11000
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 6.3,
|
1134 |
+
"eval_accuracy": 0.8643829239201721,
|
1135 |
+
"eval_loss": 0.8603515625,
|
1136 |
+
"eval_runtime": 292.6815,
|
1137 |
+
"eval_samples_per_second": 14.743,
|
1138 |
+
"eval_steps_per_second": 1.845,
|
1139 |
+
"step": 11100
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 6.36,
|
1143 |
+
"eval_accuracy": 0.8641971616890317,
|
1144 |
+
"eval_loss": 0.85693359375,
|
1145 |
+
"eval_runtime": 292.4181,
|
1146 |
+
"eval_samples_per_second": 14.756,
|
1147 |
+
"eval_steps_per_second": 1.847,
|
1148 |
+
"step": 11200
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 6.41,
|
1152 |
+
"eval_accuracy": 0.8638854436036061,
|
1153 |
+
"eval_loss": 0.85302734375,
|
1154 |
+
"eval_runtime": 293.018,
|
1155 |
+
"eval_samples_per_second": 14.726,
|
1156 |
+
"eval_steps_per_second": 1.843,
|
1157 |
+
"step": 11300
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 6.47,
|
1161 |
+
"eval_accuracy": 0.8642818873895762,
|
1162 |
+
"eval_loss": 0.85888671875,
|
1163 |
+
"eval_runtime": 291.7384,
|
1164 |
+
"eval_samples_per_second": 14.791,
|
1165 |
+
"eval_steps_per_second": 1.851,
|
1166 |
+
"step": 11400
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 6.53,
|
1170 |
+
"learning_rate": 5e-05,
|
1171 |
+
"loss": 0.1076,
|
1172 |
+
"step": 11500
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 6.53,
|
1176 |
+
"eval_accuracy": 0.8638872559180562,
|
1177 |
+
"eval_loss": 0.8525390625,
|
1178 |
+
"eval_runtime": 293.4652,
|
1179 |
+
"eval_samples_per_second": 14.704,
|
1180 |
+
"eval_steps_per_second": 1.84,
|
1181 |
+
"step": 11500
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 6.58,
|
1185 |
+
"eval_accuracy": 0.8640002990318842,
|
1186 |
+
"eval_loss": 0.85791015625,
|
1187 |
+
"eval_runtime": 292.9912,
|
1188 |
+
"eval_samples_per_second": 14.727,
|
1189 |
+
"eval_steps_per_second": 1.843,
|
1190 |
+
"step": 11600
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 6.64,
|
1194 |
+
"eval_accuracy": 0.8639792308764013,
|
1195 |
+
"eval_loss": 0.859375,
|
1196 |
+
"eval_runtime": 292.1362,
|
1197 |
+
"eval_samples_per_second": 14.771,
|
1198 |
+
"eval_steps_per_second": 1.848,
|
1199 |
+
"step": 11700
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 6.7,
|
1203 |
+
"eval_accuracy": 0.864300237073384,
|
1204 |
+
"eval_loss": 0.85986328125,
|
1205 |
+
"eval_runtime": 292.9015,
|
1206 |
+
"eval_samples_per_second": 14.732,
|
1207 |
+
"eval_steps_per_second": 1.844,
|
1208 |
+
"step": 11800
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 6.75,
|
1212 |
+
"eval_accuracy": 0.8639912374596336,
|
1213 |
+
"eval_loss": 0.8564453125,
|
1214 |
+
"eval_runtime": 292.927,
|
1215 |
+
"eval_samples_per_second": 14.731,
|
1216 |
+
"eval_steps_per_second": 1.843,
|
1217 |
+
"step": 11900
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 6.81,
|
1221 |
+
"learning_rate": 5e-05,
|
1222 |
+
"loss": 0.1109,
|
1223 |
+
"step": 12000
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 6.81,
|
1227 |
+
"eval_accuracy": 0.8640392637925625,
|
1228 |
+
"eval_loss": 0.86328125,
|
1229 |
+
"eval_runtime": 292.9284,
|
1230 |
+
"eval_samples_per_second": 14.731,
|
1231 |
+
"eval_steps_per_second": 1.843,
|
1232 |
+
"step": 12000
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 6.87,
|
1236 |
+
"eval_accuracy": 0.8638109121718437,
|
1237 |
+
"eval_loss": 0.8583984375,
|
1238 |
+
"eval_runtime": 292.6011,
|
1239 |
+
"eval_samples_per_second": 14.747,
|
1240 |
+
"eval_steps_per_second": 1.846,
|
1241 |
+
"step": 12100
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 6.92,
|
1245 |
+
"eval_accuracy": 0.863599550999095,
|
1246 |
+
"eval_loss": 0.86474609375,
|
1247 |
+
"eval_runtime": 292.8714,
|
1248 |
+
"eval_samples_per_second": 14.733,
|
1249 |
+
"eval_steps_per_second": 1.844,
|
1250 |
+
"step": 12200
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 6.98,
|
1254 |
+
"eval_accuracy": 0.8634767666950973,
|
1255 |
+
"eval_loss": 0.85986328125,
|
1256 |
+
"eval_runtime": 291.6716,
|
1257 |
+
"eval_samples_per_second": 14.794,
|
1258 |
+
"eval_steps_per_second": 1.851,
|
1259 |
+
"step": 12300
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 7.04,
|
1263 |
+
"eval_accuracy": 0.8632459231420095,
|
1264 |
+
"eval_loss": 0.89794921875,
|
1265 |
+
"eval_runtime": 292.8834,
|
1266 |
+
"eval_samples_per_second": 14.733,
|
1267 |
+
"eval_steps_per_second": 1.844,
|
1268 |
+
"step": 12400
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 7.09,
|
1272 |
+
"learning_rate": 5e-05,
|
1273 |
+
"loss": 0.1028,
|
1274 |
+
"step": 12500
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 7.09,
|
1278 |
+
"eval_accuracy": 0.8634595497078209,
|
1279 |
+
"eval_loss": 0.8935546875,
|
1280 |
+
"eval_runtime": 291.8248,
|
1281 |
+
"eval_samples_per_second": 14.786,
|
1282 |
+
"eval_steps_per_second": 1.85,
|
1283 |
+
"step": 12500
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 7.15,
|
1287 |
+
"eval_accuracy": 0.8637445361551069,
|
1288 |
+
"eval_loss": 0.904296875,
|
1289 |
+
"eval_runtime": 293.127,
|
1290 |
+
"eval_samples_per_second": 14.721,
|
1291 |
+
"eval_steps_per_second": 1.842,
|
1292 |
+
"step": 12600
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 7.21,
|
1296 |
+
"eval_accuracy": 0.8641618215572539,
|
1297 |
+
"eval_loss": 0.89892578125,
|
1298 |
+
"eval_runtime": 291.7379,
|
1299 |
+
"eval_samples_per_second": 14.791,
|
1300 |
+
"eval_steps_per_second": 1.851,
|
1301 |
+
"step": 12700
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 7.26,
|
1305 |
+
"eval_accuracy": 0.8641742812190987,
|
1306 |
+
"eval_loss": 0.8935546875,
|
1307 |
+
"eval_runtime": 291.8762,
|
1308 |
+
"eval_samples_per_second": 14.784,
|
1309 |
+
"eval_steps_per_second": 1.85,
|
1310 |
+
"step": 12800
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 7.32,
|
1314 |
+
"eval_accuracy": 0.8641423391769147,
|
1315 |
+
"eval_loss": 0.89208984375,
|
1316 |
+
"eval_runtime": 293.0894,
|
1317 |
+
"eval_samples_per_second": 14.722,
|
1318 |
+
"eval_steps_per_second": 1.842,
|
1319 |
+
"step": 12900
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 7.38,
|
1323 |
+
"learning_rate": 5e-05,
|
1324 |
+
"loss": 0.0774,
|
1325 |
+
"step": 13000
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 7.38,
|
1329 |
+
"eval_accuracy": 0.8633791282540956,
|
1330 |
+
"eval_loss": 0.8955078125,
|
1331 |
+
"eval_runtime": 292.6585,
|
1332 |
+
"eval_samples_per_second": 14.744,
|
1333 |
+
"eval_steps_per_second": 1.845,
|
1334 |
+
"step": 13000
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 7.43,
|
1338 |
+
"eval_accuracy": 0.8636269622551535,
|
1339 |
+
"eval_loss": 0.89501953125,
|
1340 |
+
"eval_runtime": 294.4392,
|
1341 |
+
"eval_samples_per_second": 14.655,
|
1342 |
+
"eval_steps_per_second": 1.834,
|
1343 |
+
"step": 13100
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 7.49,
|
1347 |
+
"eval_accuracy": 0.8635223010956573,
|
1348 |
+
"eval_loss": 0.8994140625,
|
1349 |
+
"eval_runtime": 292.0929,
|
1350 |
+
"eval_samples_per_second": 14.773,
|
1351 |
+
"eval_steps_per_second": 1.849,
|
1352 |
+
"step": 13200
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 7.55,
|
1356 |
+
"eval_accuracy": 0.8635028187153182,
|
1357 |
+
"eval_loss": 0.89990234375,
|
1358 |
+
"eval_runtime": 291.6539,
|
1359 |
+
"eval_samples_per_second": 14.795,
|
1360 |
+
"eval_steps_per_second": 1.852,
|
1361 |
+
"step": 13300
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 7.6,
|
1365 |
+
"eval_accuracy": 0.8631285757813624,
|
1366 |
+
"eval_loss": 0.8935546875,
|
1367 |
+
"eval_runtime": 293.1835,
|
1368 |
+
"eval_samples_per_second": 14.718,
|
1369 |
+
"eval_steps_per_second": 1.842,
|
1370 |
+
"step": 13400
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 7.66,
|
1374 |
+
"learning_rate": 5e-05,
|
1375 |
+
"loss": 0.0852,
|
1376 |
+
"step": 13500
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 7.66,
|
1380 |
+
"eval_accuracy": 0.863441879641932,
|
1381 |
+
"eval_loss": 0.90478515625,
|
1382 |
+
"eval_runtime": 292.8044,
|
1383 |
+
"eval_samples_per_second": 14.737,
|
1384 |
+
"eval_steps_per_second": 1.844,
|
1385 |
+
"step": 13500
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 7.72,
|
1389 |
+
"eval_accuracy": 0.8632284796154269,
|
1390 |
+
"eval_loss": 0.89599609375,
|
1391 |
+
"eval_runtime": 292.7129,
|
1392 |
+
"eval_samples_per_second": 14.741,
|
1393 |
+
"eval_steps_per_second": 1.845,
|
1394 |
+
"step": 13600
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 7.78,
|
1398 |
+
"eval_accuracy": 0.8634731420661971,
|
1399 |
+
"eval_loss": 0.90234375,
|
1400 |
+
"eval_runtime": 292.9408,
|
1401 |
+
"eval_samples_per_second": 14.73,
|
1402 |
+
"eval_steps_per_second": 1.843,
|
1403 |
+
"step": 13700
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 7.83,
|
1407 |
+
"eval_accuracy": 0.8638301680128765,
|
1408 |
+
"eval_loss": 0.8984375,
|
1409 |
+
"eval_runtime": 292.9793,
|
1410 |
+
"eval_samples_per_second": 14.728,
|
1411 |
+
"eval_steps_per_second": 1.843,
|
1412 |
+
"step": 13800
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 7.89,
|
1416 |
+
"eval_accuracy": 0.8635458611835093,
|
1417 |
+
"eval_loss": 0.90185546875,
|
1418 |
+
"eval_runtime": 292.8153,
|
1419 |
+
"eval_samples_per_second": 14.736,
|
1420 |
+
"eval_steps_per_second": 1.844,
|
1421 |
+
"step": 13900
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 7.95,
|
1425 |
+
"learning_rate": 5e-05,
|
1426 |
+
"loss": 0.0879,
|
1427 |
+
"step": 14000
|
1428 |
+
},
|
1429 |
+
{
|
1430 |
+
"epoch": 7.95,
|
1431 |
+
"eval_accuracy": 0.863396345241372,
|
1432 |
+
"eval_loss": 0.9013671875,
|
1433 |
+
"eval_runtime": 292.8988,
|
1434 |
+
"eval_samples_per_second": 14.732,
|
1435 |
+
"eval_steps_per_second": 1.844,
|
1436 |
+
"step": 14000
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 8.0,
|
1440 |
+
"eval_accuracy": 0.8630044322415271,
|
1441 |
+
"eval_loss": 0.91357421875,
|
1442 |
+
"eval_runtime": 292.7911,
|
1443 |
+
"eval_samples_per_second": 14.737,
|
1444 |
+
"eval_steps_per_second": 1.844,
|
1445 |
+
"step": 14100
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 8.06,
|
1449 |
+
"eval_accuracy": 0.8638926928614067,
|
1450 |
+
"eval_loss": 0.93115234375,
|
1451 |
+
"eval_runtime": 292.7997,
|
1452 |
+
"eval_samples_per_second": 14.737,
|
1453 |
+
"eval_steps_per_second": 1.844,
|
1454 |
+
"step": 14200
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 8.12,
|
1458 |
+
"eval_accuracy": 0.8635213949384323,
|
1459 |
+
"eval_loss": 0.9345703125,
|
1460 |
+
"eval_runtime": 292.7958,
|
1461 |
+
"eval_samples_per_second": 14.737,
|
1462 |
+
"eval_steps_per_second": 1.844,
|
1463 |
+
"step": 14300
|
1464 |
+
},
|
1465 |
+
{
|
1466 |
+
"epoch": 8.17,
|
1467 |
+
"eval_accuracy": 0.8635272849603952,
|
1468 |
+
"eval_loss": 0.9306640625,
|
1469 |
+
"eval_runtime": 291.7965,
|
1470 |
+
"eval_samples_per_second": 14.788,
|
1471 |
+
"eval_steps_per_second": 1.851,
|
1472 |
+
"step": 14400
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 8.23,
|
1476 |
+
"learning_rate": 5e-05,
|
1477 |
+
"loss": 0.0611,
|
1478 |
+
"step": 14500
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 8.23,
|
1482 |
+
"eval_accuracy": 0.8640974843942736,
|
1483 |
+
"eval_loss": 0.94189453125,
|
1484 |
+
"eval_runtime": 292.9438,
|
1485 |
+
"eval_samples_per_second": 14.73,
|
1486 |
+
"eval_steps_per_second": 1.843,
|
1487 |
+
"step": 14500
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 8.29,
|
1491 |
+
"eval_accuracy": 0.863091196795828,
|
1492 |
+
"eval_loss": 0.93310546875,
|
1493 |
+
"eval_runtime": 292.6114,
|
1494 |
+
"eval_samples_per_second": 14.747,
|
1495 |
+
"eval_steps_per_second": 1.845,
|
1496 |
+
"step": 14600
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 8.34,
|
1500 |
+
"eval_accuracy": 0.8635660231817672,
|
1501 |
+
"eval_loss": 0.9375,
|
1502 |
+
"eval_runtime": 292.5076,
|
1503 |
+
"eval_samples_per_second": 14.752,
|
1504 |
+
"eval_steps_per_second": 1.846,
|
1505 |
+
"step": 14700
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 8.4,
|
1509 |
+
"eval_accuracy": 0.8626125192416824,
|
1510 |
+
"eval_loss": 0.92919921875,
|
1511 |
+
"eval_runtime": 292.6676,
|
1512 |
+
"eval_samples_per_second": 14.744,
|
1513 |
+
"eval_steps_per_second": 1.845,
|
1514 |
+
"step": 14800
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 8.46,
|
1518 |
+
"eval_accuracy": 0.8637236945389302,
|
1519 |
+
"eval_loss": 0.94580078125,
|
1520 |
+
"eval_runtime": 291.6673,
|
1521 |
+
"eval_samples_per_second": 14.794,
|
1522 |
+
"eval_steps_per_second": 1.851,
|
1523 |
+
"step": 14900
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 8.51,
|
1527 |
+
"learning_rate": 5e-05,
|
1528 |
+
"loss": 0.061,
|
1529 |
+
"step": 15000
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 8.51,
|
1533 |
+
"eval_accuracy": 0.8634267015084119,
|
1534 |
+
"eval_loss": 0.93359375,
|
1535 |
+
"eval_runtime": 291.6632,
|
1536 |
+
"eval_samples_per_second": 14.794,
|
1537 |
+
"eval_steps_per_second": 1.851,
|
1538 |
+
"step": 15000
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 8.57,
|
1542 |
+
"eval_accuracy": 0.8629693186490555,
|
1543 |
+
"eval_loss": 0.94091796875,
|
1544 |
+
"eval_runtime": 292.9394,
|
1545 |
+
"eval_samples_per_second": 14.73,
|
1546 |
+
"eval_steps_per_second": 1.843,
|
1547 |
+
"step": 15100
|
1548 |
+
},
|
1549 |
+
{
|
1550 |
+
"epoch": 8.63,
|
1551 |
+
"eval_accuracy": 0.8632108095495379,
|
1552 |
+
"eval_loss": 0.93896484375,
|
1553 |
+
"eval_runtime": 292.836,
|
1554 |
+
"eval_samples_per_second": 14.735,
|
1555 |
+
"eval_steps_per_second": 1.844,
|
1556 |
+
"step": 15200
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 8.68,
|
1560 |
+
"eval_accuracy": 0.862787634125428,
|
1561 |
+
"eval_loss": 0.9375,
|
1562 |
+
"eval_runtime": 291.5974,
|
1563 |
+
"eval_samples_per_second": 14.798,
|
1564 |
+
"eval_steps_per_second": 1.852,
|
1565 |
+
"step": 15300
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 8.74,
|
1569 |
+
"eval_accuracy": 0.8629693186490555,
|
1570 |
+
"eval_loss": 0.9365234375,
|
1571 |
+
"eval_runtime": 292.847,
|
1572 |
+
"eval_samples_per_second": 14.735,
|
1573 |
+
"eval_steps_per_second": 1.844,
|
1574 |
+
"step": 15400
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 8.8,
|
1578 |
+
"learning_rate": 5e-05,
|
1579 |
+
"loss": 0.0646,
|
1580 |
+
"step": 15500
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 8.8,
|
1584 |
+
"eval_accuracy": 0.8628259192681874,
|
1585 |
+
"eval_loss": 0.93701171875,
|
1586 |
+
"eval_runtime": 292.6735,
|
1587 |
+
"eval_samples_per_second": 14.743,
|
1588 |
+
"eval_steps_per_second": 1.845,
|
1589 |
+
"step": 15500
|
1590 |
+
},
|
1591 |
+
{
|
1592 |
+
"epoch": 8.85,
|
1593 |
+
"eval_accuracy": 0.8629194800016764,
|
1594 |
+
"eval_loss": 0.935546875,
|
1595 |
+
"eval_runtime": 292.789,
|
1596 |
+
"eval_samples_per_second": 14.738,
|
1597 |
+
"eval_steps_per_second": 1.844,
|
1598 |
+
"step": 15600
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 8.91,
|
1602 |
+
"eval_accuracy": 0.8632305184691833,
|
1603 |
+
"eval_loss": 0.9375,
|
1604 |
+
"eval_runtime": 291.6374,
|
1605 |
+
"eval_samples_per_second": 14.796,
|
1606 |
+
"eval_steps_per_second": 1.852,
|
1607 |
+
"step": 15700
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 8.97,
|
1611 |
+
"eval_accuracy": 0.8629763413675499,
|
1612 |
+
"eval_loss": 0.93896484375,
|
1613 |
+
"eval_runtime": 293.0327,
|
1614 |
+
"eval_samples_per_second": 14.725,
|
1615 |
+
"eval_steps_per_second": 1.843,
|
1616 |
+
"step": 15800
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 9.02,
|
1620 |
+
"eval_accuracy": 0.8630309373403606,
|
1621 |
+
"eval_loss": 0.9716796875,
|
1622 |
+
"eval_runtime": 292.645,
|
1623 |
+
"eval_samples_per_second": 14.745,
|
1624 |
+
"eval_steps_per_second": 1.845,
|
1625 |
+
"step": 15900
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 9.08,
|
1629 |
+
"learning_rate": 5e-05,
|
1630 |
+
"loss": 0.0593,
|
1631 |
+
"step": 16000
|
1632 |
+
},
|
1633 |
+
{
|
1634 |
+
"epoch": 9.08,
|
1635 |
+
"eval_accuracy": 0.8626426489694161,
|
1636 |
+
"eval_loss": 0.96728515625,
|
1637 |
+
"eval_runtime": 292.8134,
|
1638 |
+
"eval_samples_per_second": 14.736,
|
1639 |
+
"eval_steps_per_second": 1.844,
|
1640 |
+
"step": 16000
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 9.14,
|
1644 |
+
"eval_accuracy": 0.862975661749631,
|
1645 |
+
"eval_loss": 0.96435546875,
|
1646 |
+
"eval_runtime": 292.9061,
|
1647 |
+
"eval_samples_per_second": 14.732,
|
1648 |
+
"eval_steps_per_second": 1.844,
|
1649 |
+
"step": 16100
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 9.19,
|
1653 |
+
"eval_accuracy": 0.8630644651576883,
|
1654 |
+
"eval_loss": 0.96240234375,
|
1655 |
+
"eval_runtime": 293.8107,
|
1656 |
+
"eval_samples_per_second": 14.686,
|
1657 |
+
"eval_steps_per_second": 1.838,
|
1658 |
+
"step": 16200
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 9.25,
|
1662 |
+
"eval_accuracy": 0.8633050499009457,
|
1663 |
+
"eval_loss": 0.96484375,
|
1664 |
+
"eval_runtime": 291.7944,
|
1665 |
+
"eval_samples_per_second": 14.788,
|
1666 |
+
"eval_steps_per_second": 1.851,
|
1667 |
+
"step": 16300
|
1668 |
+
},
|
1669 |
+
{
|
1670 |
+
"epoch": 9.31,
|
1671 |
+
"eval_accuracy": 0.8632493212316036,
|
1672 |
+
"eval_loss": 0.96728515625,
|
1673 |
+
"eval_runtime": 291.6912,
|
1674 |
+
"eval_samples_per_second": 14.793,
|
1675 |
+
"eval_steps_per_second": 1.851,
|
1676 |
+
"step": 16400
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 9.36,
|
1680 |
+
"learning_rate": 5e-05,
|
1681 |
+
"loss": 0.0415,
|
1682 |
+
"step": 16500
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 9.36,
|
1686 |
+
"eval_accuracy": 0.8633073152940084,
|
1687 |
+
"eval_loss": 0.9658203125,
|
1688 |
+
"eval_runtime": 291.6781,
|
1689 |
+
"eval_samples_per_second": 14.794,
|
1690 |
+
"eval_steps_per_second": 1.851,
|
1691 |
+
"step": 16500
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 9.42,
|
1695 |
+
"eval_accuracy": 0.8627819706427713,
|
1696 |
+
"eval_loss": 0.96875,
|
1697 |
+
"eval_runtime": 292.5363,
|
1698 |
+
"eval_samples_per_second": 14.75,
|
1699 |
+
"eval_steps_per_second": 1.846,
|
1700 |
+
"step": 16600
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 9.48,
|
1704 |
+
"eval_accuracy": 0.8632289326940394,
|
1705 |
+
"eval_loss": 0.96533203125,
|
1706 |
+
"eval_runtime": 292.6096,
|
1707 |
+
"eval_samples_per_second": 14.747,
|
1708 |
+
"eval_steps_per_second": 1.845,
|
1709 |
+
"step": 16700
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 9.53,
|
1713 |
+
"eval_accuracy": 0.862821388482062,
|
1714 |
+
"eval_loss": 0.9658203125,
|
1715 |
+
"eval_runtime": 291.5436,
|
1716 |
+
"eval_samples_per_second": 14.801,
|
1717 |
+
"eval_steps_per_second": 1.852,
|
1718 |
+
"step": 16800
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 9.59,
|
1722 |
+
"eval_accuracy": 0.8629199330802889,
|
1723 |
+
"eval_loss": 0.966796875,
|
1724 |
+
"eval_runtime": 292.7541,
|
1725 |
+
"eval_samples_per_second": 14.739,
|
1726 |
+
"eval_steps_per_second": 1.845,
|
1727 |
+
"step": 16900
|
1728 |
+
},
|
1729 |
+
{
|
1730 |
+
"epoch": 9.65,
|
1731 |
+
"learning_rate": 5e-05,
|
1732 |
+
"loss": 0.0471,
|
1733 |
+
"step": 17000
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 9.65,
|
1737 |
+
"eval_accuracy": 0.8625384408885325,
|
1738 |
+
"eval_loss": 0.96044921875,
|
1739 |
+
"eval_runtime": 292.6838,
|
1740 |
+
"eval_samples_per_second": 14.743,
|
1741 |
+
"eval_steps_per_second": 1.845,
|
1742 |
+
"step": 17000
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 9.7,
|
1746 |
+
"eval_accuracy": 0.8620747149286004,
|
1747 |
+
"eval_loss": 0.9658203125,
|
1748 |
+
"eval_runtime": 291.636,
|
1749 |
+
"eval_samples_per_second": 14.796,
|
1750 |
+
"eval_steps_per_second": 1.852,
|
1751 |
+
"step": 17100
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 9.76,
|
1755 |
+
"eval_accuracy": 0.8629695451883618,
|
1756 |
+
"eval_loss": 0.97314453125,
|
1757 |
+
"eval_runtime": 291.7564,
|
1758 |
+
"eval_samples_per_second": 14.79,
|
1759 |
+
"eval_steps_per_second": 1.851,
|
1760 |
+
"step": 17200
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 9.82,
|
1764 |
+
"eval_accuracy": 0.8626276973752023,
|
1765 |
+
"eval_loss": 0.96923828125,
|
1766 |
+
"eval_runtime": 291.4249,
|
1767 |
+
"eval_samples_per_second": 14.807,
|
1768 |
+
"eval_steps_per_second": 1.853,
|
1769 |
+
"step": 17300
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 9.88,
|
1773 |
+
"eval_accuracy": 0.8622577586880655,
|
1774 |
+
"eval_loss": 0.96728515625,
|
1775 |
+
"eval_runtime": 291.5949,
|
1776 |
+
"eval_samples_per_second": 14.798,
|
1777 |
+
"eval_steps_per_second": 1.852,
|
1778 |
+
"step": 17400
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 9.93,
|
1782 |
+
"learning_rate": 5e-05,
|
1783 |
+
"loss": 0.0528,
|
1784 |
+
"step": 17500
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 9.93,
|
1788 |
+
"eval_accuracy": 0.8619999569575318,
|
1789 |
+
"eval_loss": 0.96142578125,
|
1790 |
+
"eval_runtime": 292.6583,
|
1791 |
+
"eval_samples_per_second": 14.744,
|
1792 |
+
"eval_steps_per_second": 1.845,
|
1793 |
+
"step": 17500
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 9.99,
|
1797 |
+
"eval_accuracy": 0.8620715433783127,
|
1798 |
+
"eval_loss": 0.9697265625,
|
1799 |
+
"eval_runtime": 291.7031,
|
1800 |
+
"eval_samples_per_second": 14.792,
|
1801 |
+
"eval_steps_per_second": 1.851,
|
1802 |
+
"step": 17600
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 10.0,
|
1806 |
+
"step": 17620,
|
1807 |
+
"total_flos": 2.179292736824279e+18,
|
1808 |
+
"train_loss": 0.2421213565700847,
|
1809 |
+
"train_runtime": 122603.1424,
|
1810 |
+
"train_samples_per_second": 1.149,
|
1811 |
+
"train_steps_per_second": 0.144
|
1812 |
+
}
|
1813 |
+
],
|
1814 |
+
"max_steps": 17620,
|
1815 |
+
"num_train_epochs": 10,
|
1816 |
+
"total_flos": 2.179292736824279e+18,
|
1817 |
+
"trial_name": null,
|
1818 |
+
"trial_params": null
|
1819 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1329a0f14c187b18f591e204cf458a0fc5d096cbe27c3326c557bbea66879f40
|
3 |
+
size 4463
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|