ahotrod/deberta-v3-large-finetuned-squadv2
Browse files- README.md +162 -0
- added_tokens.json +7 -0
- all_results.json +14 -0
- config.json +35 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
- train_results.json +9 -0
- trainer_state.json +2396 -0
- training_args.bin +3 -0
- validation_results.json +8 -0
README.md
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/deberta-v3-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- squad_v2
|
8 |
+
model-index:
|
9 |
+
- name: deberta-v3-large-finetuned-squadv2
|
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 |
+
# deberta-v3-large-finetuned-squadv2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the squad_v2 dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.5579
|
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: 1e-05
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 1000
|
48 |
+
- training_steps: 5200
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.5293 | 1.57 | 3200 | 0.5739 |
|
55 |
+
| 0.5106 | 1.58 | 3220 | 0.5783 |
|
56 |
+
| 0.5338 | 1.59 | 3240 | 0.5718 |
|
57 |
+
| 0.5128 | 1.6 | 3260 | 0.5827 |
|
58 |
+
| 0.5205 | 1.61 | 3280 | 0.6045 |
|
59 |
+
| 0.5114 | 1.62 | 3300 | 0.5880 |
|
60 |
+
| 0.5072 | 1.63 | 3320 | 0.5788 |
|
61 |
+
| 0.5512 | 1.64 | 3340 | 0.5863 |
|
62 |
+
| 0.4723 | 1.65 | 3360 | 0.5898 |
|
63 |
+
| 0.5011 | 1.66 | 3380 | 0.5917 |
|
64 |
+
| 0.5419 | 1.67 | 3400 | 0.6027 |
|
65 |
+
| 0.5425 | 1.68 | 3420 | 0.5699 |
|
66 |
+
| 0.5703 | 1.69 | 3440 | 0.5897 |
|
67 |
+
| 0.4646 | 1.7 | 3460 | 0.5917 |
|
68 |
+
| 0.4652 | 1.71 | 3480 | 0.5745 |
|
69 |
+
| 0.5323 | 1.72 | 3500 | 0.5860 |
|
70 |
+
| 0.5129 | 1.73 | 3520 | 0.5656 |
|
71 |
+
| 0.5441 | 1.74 | 3540 | 0.5642 |
|
72 |
+
| 0.5624 | 1.75 | 3560 | 0.5873 |
|
73 |
+
| 0.4645 | 1.76 | 3580 | 0.5891 |
|
74 |
+
| 0.5577 | 1.77 | 3600 | 0.5816 |
|
75 |
+
| 0.5199 | 1.78 | 3620 | 0.5579 |
|
76 |
+
| 0.5061 | 1.79 | 3640 | 0.5837 |
|
77 |
+
| 0.484 | 1.79 | 3660 | 0.5721 |
|
78 |
+
| 0.5095 | 1.8 | 3680 | 0.5821 |
|
79 |
+
| 0.5342 | 1.81 | 3700 | 0.5602 |
|
80 |
+
| 0.5435 | 1.82 | 3720 | 0.5911 |
|
81 |
+
| 0.5288 | 1.83 | 3740 | 0.5647 |
|
82 |
+
| 0.5476 | 1.84 | 3760 | 0.5733 |
|
83 |
+
| 0.5199 | 1.85 | 3780 | 0.5675 |
|
84 |
+
| 0.5067 | 1.86 | 3800 | 0.5839 |
|
85 |
+
| 0.5418 | 1.87 | 3820 | 0.5757 |
|
86 |
+
| 0.4965 | 1.88 | 3840 | 0.5764 |
|
87 |
+
| 0.5273 | 1.89 | 3860 | 0.5906 |
|
88 |
+
| 0.5808 | 1.9 | 3880 | 0.5762 |
|
89 |
+
| 0.5161 | 1.91 | 3900 | 0.5612 |
|
90 |
+
| 0.4863 | 1.92 | 3920 | 0.5804 |
|
91 |
+
| 0.4827 | 1.93 | 3940 | 0.5841 |
|
92 |
+
| 0.4643 | 1.94 | 3960 | 0.5822 |
|
93 |
+
| 0.5029 | 1.95 | 3980 | 0.6052 |
|
94 |
+
| 0.509 | 1.96 | 4000 | 0.5800 |
|
95 |
+
| 0.5382 | 1.97 | 4020 | 0.5645 |
|
96 |
+
| 0.469 | 1.98 | 4040 | 0.5685 |
|
97 |
+
| 0.5032 | 1.99 | 4060 | 0.5779 |
|
98 |
+
| 0.5171 | 2.0 | 4080 | 0.5686 |
|
99 |
+
| 0.3938 | 2.01 | 4100 | 0.5889 |
|
100 |
+
| 0.4321 | 2.02 | 4120 | 0.6039 |
|
101 |
+
| 0.4185 | 2.03 | 4140 | 0.5996 |
|
102 |
+
| 0.4782 | 2.04 | 4160 | 0.5800 |
|
103 |
+
| 0.424 | 2.05 | 4180 | 0.6374 |
|
104 |
+
| 0.3766 | 2.06 | 4200 | 0.6096 |
|
105 |
+
| 0.415 | 2.07 | 4220 | 0.6221 |
|
106 |
+
| 0.4352 | 2.08 | 4240 | 0.6150 |
|
107 |
+
| 0.4336 | 2.09 | 4260 | 0.6055 |
|
108 |
+
| 0.4289 | 2.1 | 4280 | 0.6138 |
|
109 |
+
| 0.4433 | 2.11 | 4300 | 0.5946 |
|
110 |
+
| 0.4478 | 2.12 | 4320 | 0.6118 |
|
111 |
+
| 0.4787 | 2.13 | 4340 | 0.5969 |
|
112 |
+
| 0.4432 | 2.14 | 4360 | 0.6048 |
|
113 |
+
| 0.4319 | 2.15 | 4380 | 0.5948 |
|
114 |
+
| 0.3939 | 2.16 | 4400 | 0.6116 |
|
115 |
+
| 0.3921 | 2.17 | 4420 | 0.6082 |
|
116 |
+
| 0.4381 | 2.18 | 4440 | 0.6282 |
|
117 |
+
| 0.4461 | 2.19 | 4460 | 0.6084 |
|
118 |
+
| 0.4012 | 2.2 | 4480 | 0.6092 |
|
119 |
+
| 0.3849 | 2.21 | 4500 | 0.6152 |
|
120 |
+
| 0.4178 | 2.22 | 4520 | 0.6004 |
|
121 |
+
| 0.4163 | 2.23 | 4540 | 0.6059 |
|
122 |
+
| 0.4006 | 2.24 | 4560 | 0.6115 |
|
123 |
+
| 0.4225 | 2.25 | 4580 | 0.6130 |
|
124 |
+
| 0.4008 | 2.26 | 4600 | 0.6095 |
|
125 |
+
| 0.4706 | 2.27 | 4620 | 0.6136 |
|
126 |
+
| 0.3902 | 2.28 | 4640 | 0.6103 |
|
127 |
+
| 0.4048 | 2.29 | 4660 | 0.6085 |
|
128 |
+
| 0.4411 | 2.3 | 4680 | 0.6139 |
|
129 |
+
| 0.403 | 2.31 | 4700 | 0.6047 |
|
130 |
+
| 0.4799 | 2.31 | 4720 | 0.6043 |
|
131 |
+
| 0.4316 | 2.32 | 4740 | 0.5960 |
|
132 |
+
| 0.4198 | 2.33 | 4760 | 0.6031 |
|
133 |
+
| 0.4254 | 2.34 | 4780 | 0.6033 |
|
134 |
+
| 0.387 | 2.35 | 4800 | 0.6120 |
|
135 |
+
| 0.3882 | 2.36 | 4820 | 0.6128 |
|
136 |
+
| 0.4307 | 2.37 | 4840 | 0.6150 |
|
137 |
+
| 0.434 | 2.38 | 4860 | 0.6077 |
|
138 |
+
| 0.4225 | 2.39 | 4880 | 0.6071 |
|
139 |
+
| 0.4134 | 2.4 | 4900 | 0.6036 |
|
140 |
+
| 0.3846 | 2.41 | 4920 | 0.6124 |
|
141 |
+
| 0.3943 | 2.42 | 4940 | 0.6291 |
|
142 |
+
| 0.4455 | 2.43 | 4960 | 0.6185 |
|
143 |
+
| 0.4104 | 2.44 | 4980 | 0.6064 |
|
144 |
+
| 0.4158 | 2.45 | 5000 | 0.6095 |
|
145 |
+
| 0.4135 | 2.46 | 5020 | 0.6155 |
|
146 |
+
| 0.3789 | 2.47 | 5040 | 0.6209 |
|
147 |
+
| 0.418 | 2.48 | 5060 | 0.6106 |
|
148 |
+
| 0.3931 | 2.49 | 5080 | 0.6047 |
|
149 |
+
| 0.4289 | 2.5 | 5100 | 0.6055 |
|
150 |
+
| 0.4051 | 2.51 | 5120 | 0.6084 |
|
151 |
+
| 0.4217 | 2.52 | 5140 | 0.6118 |
|
152 |
+
| 0.3843 | 2.53 | 5160 | 0.6139 |
|
153 |
+
| 0.4435 | 2.54 | 5180 | 0.6126 |
|
154 |
+
| 0.4274 | 2.55 | 5200 | 0.6120 |
|
155 |
+
|
156 |
+
|
157 |
+
### Framework versions
|
158 |
+
|
159 |
+
- Transformers 4.35.0.dev0
|
160 |
+
- Pytorch 2.1.0+cu121
|
161 |
+
- Datasets 2.14.5
|
162 |
+
- Tokenizers 0.14.0
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 1,
|
3 |
+
"[MASK]": 128000,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 2,
|
6 |
+
"[UNK]": 3
|
7 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.55,
|
3 |
+
"eval_loss": 0.5579236745834351,
|
4 |
+
"eval_runtime": 277.7608,
|
5 |
+
"eval_samples_per_second": 43.026,
|
6 |
+
"eval_steps_per_second": 5.379,
|
7 |
+
"total_flos": 3.09073923350188e+17,
|
8 |
+
"train_loss": 0.820626282783655,
|
9 |
+
"train_runtime": 52836.9017,
|
10 |
+
"train_samples": 130319,
|
11 |
+
"train_samples_per_second": 6.299,
|
12 |
+
"train_steps_per_second": 0.098,
|
13 |
+
"validation_samples": 11873
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-large",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4096,
|
12 |
+
"layer_norm_eps": 1e-07,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"max_relative_positions": -1,
|
15 |
+
"model_type": "deberta-v2",
|
16 |
+
"norm_rel_ebd": "layer_norm",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pooler_dropout": 0,
|
21 |
+
"pooler_hidden_act": "gelu",
|
22 |
+
"pooler_hidden_size": 1024,
|
23 |
+
"pos_att_type": [
|
24 |
+
"p2c",
|
25 |
+
"c2p"
|
26 |
+
],
|
27 |
+
"position_biased_input": false,
|
28 |
+
"position_buckets": 256,
|
29 |
+
"relative_attention": true,
|
30 |
+
"share_att_key": true,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.35.0.dev0",
|
33 |
+
"type_vocab_size": 0,
|
34 |
+
"vocab_size": 128100
|
35 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b191b6409c8b62441219101ca301e19a384072b02c3b4836804b5e17d3e59b1c
|
3 |
+
size 1736193258
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[UNK]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128000": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"bos_token": "[CLS]",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "[CLS]",
|
48 |
+
"do_lower_case": false,
|
49 |
+
"eos_token": "[SEP]",
|
50 |
+
"mask_token": "[MASK]",
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"sp_model_kwargs": {},
|
55 |
+
"split_by_punct": false,
|
56 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
57 |
+
"unk_token": "[UNK]",
|
58 |
+
"vocab_type": "spm"
|
59 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.55,
|
3 |
+
"total_flos": 3.09073923350188e+17,
|
4 |
+
"train_loss": 0.820626282783655,
|
5 |
+
"train_runtime": 52836.9017,
|
6 |
+
"train_samples": 130319,
|
7 |
+
"train_samples_per_second": 6.299,
|
8 |
+
"train_steps_per_second": 0.098
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5579236745834351,
|
3 |
+
"best_model_checkpoint": "deberta-v3-large-finetuned-squadv2/checkpoint-3620",
|
4 |
+
"epoch": 2.550269740068661,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 5200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2.0000000000000002e-07,
|
14 |
+
"loss": 6.0843,
|
15 |
+
"step": 20
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.02,
|
19 |
+
"learning_rate": 4.0000000000000003e-07,
|
20 |
+
"loss": 6.0629,
|
21 |
+
"step": 40
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.03,
|
25 |
+
"learning_rate": 6.000000000000001e-07,
|
26 |
+
"loss": 6.0196,
|
27 |
+
"step": 60
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.04,
|
31 |
+
"learning_rate": 8.000000000000001e-07,
|
32 |
+
"loss": 5.9309,
|
33 |
+
"step": 80
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.05,
|
37 |
+
"learning_rate": 1.0000000000000002e-06,
|
38 |
+
"loss": 5.768,
|
39 |
+
"step": 100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.06,
|
43 |
+
"learning_rate": 1.2000000000000002e-06,
|
44 |
+
"loss": 5.4721,
|
45 |
+
"step": 120
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.07,
|
49 |
+
"learning_rate": 1.3900000000000002e-06,
|
50 |
+
"loss": 5.1112,
|
51 |
+
"step": 140
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.08,
|
55 |
+
"learning_rate": 1.5900000000000002e-06,
|
56 |
+
"loss": 4.6482,
|
57 |
+
"step": 160
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.09,
|
61 |
+
"learning_rate": 1.79e-06,
|
62 |
+
"loss": 4.2226,
|
63 |
+
"step": 180
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.1,
|
67 |
+
"learning_rate": 1.9900000000000004e-06,
|
68 |
+
"loss": 3.7989,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.11,
|
73 |
+
"learning_rate": 2.19e-06,
|
74 |
+
"loss": 3.4023,
|
75 |
+
"step": 220
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.12,
|
79 |
+
"learning_rate": 2.39e-06,
|
80 |
+
"loss": 3.0793,
|
81 |
+
"step": 240
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.13,
|
85 |
+
"learning_rate": 2.59e-06,
|
86 |
+
"loss": 2.5037,
|
87 |
+
"step": 260
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.14,
|
91 |
+
"learning_rate": 2.7900000000000004e-06,
|
92 |
+
"loss": 1.9528,
|
93 |
+
"step": 280
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.15,
|
97 |
+
"learning_rate": 2.99e-06,
|
98 |
+
"loss": 1.736,
|
99 |
+
"step": 300
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.16,
|
103 |
+
"learning_rate": 3.1900000000000004e-06,
|
104 |
+
"loss": 1.5742,
|
105 |
+
"step": 320
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.17,
|
109 |
+
"learning_rate": 3.3900000000000006e-06,
|
110 |
+
"loss": 1.4485,
|
111 |
+
"step": 340
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.18,
|
115 |
+
"learning_rate": 3.58e-06,
|
116 |
+
"loss": 1.4103,
|
117 |
+
"step": 360
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.19,
|
121 |
+
"learning_rate": 3.7800000000000002e-06,
|
122 |
+
"loss": 1.3205,
|
123 |
+
"step": 380
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.2,
|
127 |
+
"learning_rate": 3.980000000000001e-06,
|
128 |
+
"loss": 1.2793,
|
129 |
+
"step": 400
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.21,
|
133 |
+
"learning_rate": 4.18e-06,
|
134 |
+
"loss": 1.1896,
|
135 |
+
"step": 420
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.22,
|
139 |
+
"learning_rate": 4.38e-06,
|
140 |
+
"loss": 1.1228,
|
141 |
+
"step": 440
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.23,
|
145 |
+
"learning_rate": 4.57e-06,
|
146 |
+
"loss": 1.0661,
|
147 |
+
"step": 460
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.24,
|
151 |
+
"learning_rate": 4.77e-06,
|
152 |
+
"loss": 1.0459,
|
153 |
+
"step": 480
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.25,
|
157 |
+
"learning_rate": 4.970000000000001e-06,
|
158 |
+
"loss": 1.0062,
|
159 |
+
"step": 500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.26,
|
163 |
+
"learning_rate": 5.1700000000000005e-06,
|
164 |
+
"loss": 0.9441,
|
165 |
+
"step": 520
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.26,
|
169 |
+
"learning_rate": 5.370000000000001e-06,
|
170 |
+
"loss": 0.9871,
|
171 |
+
"step": 540
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.27,
|
175 |
+
"learning_rate": 5.570000000000001e-06,
|
176 |
+
"loss": 0.9291,
|
177 |
+
"step": 560
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.28,
|
181 |
+
"learning_rate": 5.77e-06,
|
182 |
+
"loss": 0.9635,
|
183 |
+
"step": 580
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.29,
|
187 |
+
"learning_rate": 5.9700000000000004e-06,
|
188 |
+
"loss": 0.9874,
|
189 |
+
"step": 600
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.3,
|
193 |
+
"learning_rate": 6.17e-06,
|
194 |
+
"loss": 0.8922,
|
195 |
+
"step": 620
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.31,
|
199 |
+
"learning_rate": 6.370000000000001e-06,
|
200 |
+
"loss": 0.9304,
|
201 |
+
"step": 640
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.32,
|
205 |
+
"learning_rate": 6.570000000000001e-06,
|
206 |
+
"loss": 0.8742,
|
207 |
+
"step": 660
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.33,
|
211 |
+
"learning_rate": 6.770000000000001e-06,
|
212 |
+
"loss": 0.8423,
|
213 |
+
"step": 680
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.34,
|
217 |
+
"learning_rate": 6.97e-06,
|
218 |
+
"loss": 0.8286,
|
219 |
+
"step": 700
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.35,
|
223 |
+
"learning_rate": 7.17e-06,
|
224 |
+
"loss": 0.8192,
|
225 |
+
"step": 720
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.36,
|
229 |
+
"learning_rate": 7.370000000000001e-06,
|
230 |
+
"loss": 0.8451,
|
231 |
+
"step": 740
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.37,
|
235 |
+
"learning_rate": 7.57e-06,
|
236 |
+
"loss": 0.7954,
|
237 |
+
"step": 760
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.38,
|
241 |
+
"learning_rate": 7.77e-06,
|
242 |
+
"loss": 0.8322,
|
243 |
+
"step": 780
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.39,
|
247 |
+
"learning_rate": 7.970000000000002e-06,
|
248 |
+
"loss": 0.8318,
|
249 |
+
"step": 800
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.4,
|
253 |
+
"learning_rate": 8.17e-06,
|
254 |
+
"loss": 0.8396,
|
255 |
+
"step": 820
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.41,
|
259 |
+
"learning_rate": 8.370000000000001e-06,
|
260 |
+
"loss": 0.7922,
|
261 |
+
"step": 840
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.42,
|
265 |
+
"learning_rate": 8.570000000000001e-06,
|
266 |
+
"loss": 0.7931,
|
267 |
+
"step": 860
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.43,
|
271 |
+
"learning_rate": 8.77e-06,
|
272 |
+
"loss": 0.7942,
|
273 |
+
"step": 880
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.44,
|
277 |
+
"learning_rate": 8.97e-06,
|
278 |
+
"loss": 0.8017,
|
279 |
+
"step": 900
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.45,
|
283 |
+
"learning_rate": 9.17e-06,
|
284 |
+
"loss": 0.7346,
|
285 |
+
"step": 920
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.46,
|
289 |
+
"learning_rate": 9.370000000000002e-06,
|
290 |
+
"loss": 0.6792,
|
291 |
+
"step": 940
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.47,
|
295 |
+
"learning_rate": 9.57e-06,
|
296 |
+
"loss": 0.8069,
|
297 |
+
"step": 960
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.48,
|
301 |
+
"learning_rate": 9.770000000000001e-06,
|
302 |
+
"loss": 0.8058,
|
303 |
+
"step": 980
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.49,
|
307 |
+
"learning_rate": 9.970000000000001e-06,
|
308 |
+
"loss": 0.8398,
|
309 |
+
"step": 1000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.5,
|
313 |
+
"learning_rate": 9.95952380952381e-06,
|
314 |
+
"loss": 0.8148,
|
315 |
+
"step": 1020
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.51,
|
319 |
+
"learning_rate": 9.911904761904762e-06,
|
320 |
+
"loss": 0.7888,
|
321 |
+
"step": 1040
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.52,
|
325 |
+
"learning_rate": 9.864285714285715e-06,
|
326 |
+
"loss": 0.7423,
|
327 |
+
"step": 1060
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.53,
|
331 |
+
"learning_rate": 9.816666666666667e-06,
|
332 |
+
"loss": 0.7855,
|
333 |
+
"step": 1080
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.54,
|
337 |
+
"learning_rate": 9.76904761904762e-06,
|
338 |
+
"loss": 0.7303,
|
339 |
+
"step": 1100
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.55,
|
343 |
+
"learning_rate": 9.721428571428573e-06,
|
344 |
+
"loss": 0.7156,
|
345 |
+
"step": 1120
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.56,
|
349 |
+
"learning_rate": 9.673809523809525e-06,
|
350 |
+
"loss": 0.7542,
|
351 |
+
"step": 1140
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.57,
|
355 |
+
"learning_rate": 9.626190476190477e-06,
|
356 |
+
"loss": 0.723,
|
357 |
+
"step": 1160
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.58,
|
361 |
+
"learning_rate": 9.57857142857143e-06,
|
362 |
+
"loss": 0.7025,
|
363 |
+
"step": 1180
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.59,
|
367 |
+
"learning_rate": 9.530952380952381e-06,
|
368 |
+
"loss": 0.7755,
|
369 |
+
"step": 1200
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.6,
|
373 |
+
"learning_rate": 9.483333333333335e-06,
|
374 |
+
"loss": 0.7225,
|
375 |
+
"step": 1220
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.61,
|
379 |
+
"learning_rate": 9.435714285714286e-06,
|
380 |
+
"loss": 0.7389,
|
381 |
+
"step": 1240
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.62,
|
385 |
+
"learning_rate": 9.388095238095238e-06,
|
386 |
+
"loss": 0.7083,
|
387 |
+
"step": 1260
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.63,
|
391 |
+
"learning_rate": 9.340476190476191e-06,
|
392 |
+
"loss": 0.6863,
|
393 |
+
"step": 1280
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.64,
|
397 |
+
"learning_rate": 9.292857142857144e-06,
|
398 |
+
"loss": 0.7167,
|
399 |
+
"step": 1300
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.65,
|
403 |
+
"learning_rate": 9.245238095238096e-06,
|
404 |
+
"loss": 0.7006,
|
405 |
+
"step": 1320
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.66,
|
409 |
+
"learning_rate": 9.197619047619049e-06,
|
410 |
+
"loss": 0.7058,
|
411 |
+
"step": 1340
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.67,
|
415 |
+
"learning_rate": 9.15e-06,
|
416 |
+
"loss": 0.7068,
|
417 |
+
"step": 1360
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.68,
|
421 |
+
"learning_rate": 9.102380952380954e-06,
|
422 |
+
"loss": 0.713,
|
423 |
+
"step": 1380
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.69,
|
427 |
+
"learning_rate": 9.054761904761905e-06,
|
428 |
+
"loss": 0.743,
|
429 |
+
"step": 1400
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.7,
|
433 |
+
"learning_rate": 9.007142857142857e-06,
|
434 |
+
"loss": 0.6588,
|
435 |
+
"step": 1420
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.71,
|
439 |
+
"learning_rate": 8.95952380952381e-06,
|
440 |
+
"loss": 0.7087,
|
441 |
+
"step": 1440
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.72,
|
445 |
+
"learning_rate": 8.911904761904763e-06,
|
446 |
+
"loss": 0.7172,
|
447 |
+
"step": 1460
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.73,
|
451 |
+
"learning_rate": 8.864285714285715e-06,
|
452 |
+
"loss": 0.6935,
|
453 |
+
"step": 1480
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.74,
|
457 |
+
"learning_rate": 8.816666666666668e-06,
|
458 |
+
"loss": 0.7049,
|
459 |
+
"step": 1500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.75,
|
463 |
+
"learning_rate": 8.76904761904762e-06,
|
464 |
+
"loss": 0.6749,
|
465 |
+
"step": 1520
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.76,
|
469 |
+
"learning_rate": 8.721428571428571e-06,
|
470 |
+
"loss": 0.6773,
|
471 |
+
"step": 1540
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.77,
|
475 |
+
"learning_rate": 8.673809523809524e-06,
|
476 |
+
"loss": 0.7028,
|
477 |
+
"step": 1560
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.77,
|
481 |
+
"learning_rate": 8.626190476190478e-06,
|
482 |
+
"loss": 0.6754,
|
483 |
+
"step": 1580
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.78,
|
487 |
+
"learning_rate": 8.57857142857143e-06,
|
488 |
+
"loss": 0.744,
|
489 |
+
"step": 1600
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.79,
|
493 |
+
"learning_rate": 8.530952380952382e-06,
|
494 |
+
"loss": 0.6175,
|
495 |
+
"step": 1620
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.8,
|
499 |
+
"learning_rate": 8.483333333333334e-06,
|
500 |
+
"loss": 0.6788,
|
501 |
+
"step": 1640
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.81,
|
505 |
+
"learning_rate": 8.435714285714286e-06,
|
506 |
+
"loss": 0.6728,
|
507 |
+
"step": 1660
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.82,
|
511 |
+
"learning_rate": 8.388095238095239e-06,
|
512 |
+
"loss": 0.7451,
|
513 |
+
"step": 1680
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.83,
|
517 |
+
"learning_rate": 8.34047619047619e-06,
|
518 |
+
"loss": 0.6392,
|
519 |
+
"step": 1700
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.84,
|
523 |
+
"learning_rate": 8.292857142857144e-06,
|
524 |
+
"loss": 0.6522,
|
525 |
+
"step": 1720
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.85,
|
529 |
+
"learning_rate": 8.245238095238097e-06,
|
530 |
+
"loss": 0.6665,
|
531 |
+
"step": 1740
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.86,
|
535 |
+
"learning_rate": 8.197619047619048e-06,
|
536 |
+
"loss": 0.6178,
|
537 |
+
"step": 1760
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.87,
|
541 |
+
"learning_rate": 8.15e-06,
|
542 |
+
"loss": 0.6699,
|
543 |
+
"step": 1780
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.88,
|
547 |
+
"learning_rate": 8.102380952380953e-06,
|
548 |
+
"loss": 0.6543,
|
549 |
+
"step": 1800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.89,
|
553 |
+
"learning_rate": 8.054761904761905e-06,
|
554 |
+
"loss": 0.6724,
|
555 |
+
"step": 1820
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.9,
|
559 |
+
"learning_rate": 8.007142857142858e-06,
|
560 |
+
"loss": 0.7194,
|
561 |
+
"step": 1840
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.91,
|
565 |
+
"learning_rate": 7.959523809523811e-06,
|
566 |
+
"loss": 0.6695,
|
567 |
+
"step": 1860
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.92,
|
571 |
+
"learning_rate": 7.911904761904763e-06,
|
572 |
+
"loss": 0.6542,
|
573 |
+
"step": 1880
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.93,
|
577 |
+
"learning_rate": 7.864285714285716e-06,
|
578 |
+
"loss": 0.6986,
|
579 |
+
"step": 1900
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.94,
|
583 |
+
"learning_rate": 7.816666666666667e-06,
|
584 |
+
"loss": 0.6527,
|
585 |
+
"step": 1920
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.95,
|
589 |
+
"learning_rate": 7.769047619047619e-06,
|
590 |
+
"loss": 0.6036,
|
591 |
+
"step": 1940
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.96,
|
595 |
+
"learning_rate": 7.721428571428572e-06,
|
596 |
+
"loss": 0.6309,
|
597 |
+
"step": 1960
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.97,
|
601 |
+
"learning_rate": 7.673809523809524e-06,
|
602 |
+
"loss": 0.6647,
|
603 |
+
"step": 1980
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.98,
|
607 |
+
"learning_rate": 7.626190476190477e-06,
|
608 |
+
"loss": 0.6625,
|
609 |
+
"step": 2000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.99,
|
613 |
+
"learning_rate": 7.5785714285714295e-06,
|
614 |
+
"loss": 0.673,
|
615 |
+
"step": 2020
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.0,
|
619 |
+
"learning_rate": 7.530952380952381e-06,
|
620 |
+
"loss": 0.6615,
|
621 |
+
"step": 2040
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 1.01,
|
625 |
+
"learning_rate": 7.483333333333333e-06,
|
626 |
+
"loss": 0.5771,
|
627 |
+
"step": 2060
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 1.02,
|
631 |
+
"learning_rate": 7.435714285714286e-06,
|
632 |
+
"loss": 0.5824,
|
633 |
+
"step": 2080
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.03,
|
637 |
+
"learning_rate": 7.388095238095239e-06,
|
638 |
+
"loss": 0.5038,
|
639 |
+
"step": 2100
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 1.04,
|
643 |
+
"learning_rate": 7.3404761904761914e-06,
|
644 |
+
"loss": 0.5524,
|
645 |
+
"step": 2120
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 1.05,
|
649 |
+
"learning_rate": 7.292857142857144e-06,
|
650 |
+
"loss": 0.5903,
|
651 |
+
"step": 2140
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 1.06,
|
655 |
+
"learning_rate": 7.245238095238096e-06,
|
656 |
+
"loss": 0.609,
|
657 |
+
"step": 2160
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.07,
|
661 |
+
"learning_rate": 7.197619047619048e-06,
|
662 |
+
"loss": 0.5303,
|
663 |
+
"step": 2180
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 1.08,
|
667 |
+
"learning_rate": 7.15e-06,
|
668 |
+
"loss": 0.5637,
|
669 |
+
"step": 2200
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 1.09,
|
673 |
+
"learning_rate": 7.1023809523809525e-06,
|
674 |
+
"loss": 0.5513,
|
675 |
+
"step": 2220
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 1.1,
|
679 |
+
"learning_rate": 7.054761904761906e-06,
|
680 |
+
"loss": 0.5648,
|
681 |
+
"step": 2240
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.11,
|
685 |
+
"learning_rate": 7.007142857142858e-06,
|
686 |
+
"loss": 0.5907,
|
687 |
+
"step": 2260
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 1.12,
|
691 |
+
"learning_rate": 6.9595238095238106e-06,
|
692 |
+
"loss": 0.5791,
|
693 |
+
"step": 2280
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 1.13,
|
697 |
+
"learning_rate": 6.911904761904763e-06,
|
698 |
+
"loss": 0.5485,
|
699 |
+
"step": 2300
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 1.14,
|
703 |
+
"learning_rate": 6.8642857142857145e-06,
|
704 |
+
"loss": 0.5279,
|
705 |
+
"step": 2320
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 1.15,
|
709 |
+
"learning_rate": 6.816666666666667e-06,
|
710 |
+
"loss": 0.5283,
|
711 |
+
"step": 2340
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 1.16,
|
715 |
+
"learning_rate": 6.769047619047619e-06,
|
716 |
+
"loss": 0.5294,
|
717 |
+
"step": 2360
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 1.17,
|
721 |
+
"learning_rate": 6.721428571428572e-06,
|
722 |
+
"loss": 0.4647,
|
723 |
+
"step": 2380
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 1.18,
|
727 |
+
"learning_rate": 6.673809523809525e-06,
|
728 |
+
"loss": 0.5571,
|
729 |
+
"step": 2400
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 1.19,
|
733 |
+
"learning_rate": 6.626190476190477e-06,
|
734 |
+
"loss": 0.5188,
|
735 |
+
"step": 2420
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 1.2,
|
739 |
+
"learning_rate": 6.578571428571429e-06,
|
740 |
+
"loss": 0.5099,
|
741 |
+
"step": 2440
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 1.21,
|
745 |
+
"learning_rate": 6.530952380952381e-06,
|
746 |
+
"loss": 0.5371,
|
747 |
+
"step": 2460
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 1.22,
|
751 |
+
"learning_rate": 6.483333333333334e-06,
|
752 |
+
"loss": 0.55,
|
753 |
+
"step": 2480
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 1.23,
|
757 |
+
"learning_rate": 6.435714285714286e-06,
|
758 |
+
"loss": 0.5546,
|
759 |
+
"step": 2500
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 1.24,
|
763 |
+
"learning_rate": 6.3880952380952384e-06,
|
764 |
+
"loss": 0.5465,
|
765 |
+
"step": 2520
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 1.25,
|
769 |
+
"learning_rate": 6.340476190476192e-06,
|
770 |
+
"loss": 0.4944,
|
771 |
+
"step": 2540
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 1.26,
|
775 |
+
"learning_rate": 6.292857142857144e-06,
|
776 |
+
"loss": 0.5248,
|
777 |
+
"step": 2560
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 1.27,
|
781 |
+
"learning_rate": 6.245238095238096e-06,
|
782 |
+
"loss": 0.5585,
|
783 |
+
"step": 2580
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 1.28,
|
787 |
+
"learning_rate": 6.197619047619048e-06,
|
788 |
+
"loss": 0.5562,
|
789 |
+
"step": 2600
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 1.28,
|
793 |
+
"learning_rate": 6.15e-06,
|
794 |
+
"loss": 0.5402,
|
795 |
+
"step": 2620
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 1.29,
|
799 |
+
"learning_rate": 6.102380952380953e-06,
|
800 |
+
"loss": 0.5674,
|
801 |
+
"step": 2640
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 1.3,
|
805 |
+
"learning_rate": 6.054761904761905e-06,
|
806 |
+
"loss": 0.5641,
|
807 |
+
"step": 2660
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 1.31,
|
811 |
+
"learning_rate": 6.0071428571428584e-06,
|
812 |
+
"loss": 0.4678,
|
813 |
+
"step": 2680
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 1.32,
|
817 |
+
"learning_rate": 5.959523809523809e-06,
|
818 |
+
"loss": 0.5162,
|
819 |
+
"step": 2700
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 1.33,
|
823 |
+
"learning_rate": 5.911904761904762e-06,
|
824 |
+
"loss": 0.5826,
|
825 |
+
"step": 2720
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 1.34,
|
829 |
+
"learning_rate": 5.864285714285715e-06,
|
830 |
+
"loss": 0.518,
|
831 |
+
"step": 2740
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 1.35,
|
835 |
+
"learning_rate": 5.816666666666667e-06,
|
836 |
+
"loss": 0.512,
|
837 |
+
"step": 2760
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 1.36,
|
841 |
+
"learning_rate": 5.7690476190476196e-06,
|
842 |
+
"loss": 0.5848,
|
843 |
+
"step": 2780
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 1.37,
|
847 |
+
"learning_rate": 5.721428571428572e-06,
|
848 |
+
"loss": 0.526,
|
849 |
+
"step": 2800
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.38,
|
853 |
+
"learning_rate": 5.673809523809525e-06,
|
854 |
+
"loss": 0.5419,
|
855 |
+
"step": 2820
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 1.39,
|
859 |
+
"learning_rate": 5.626190476190476e-06,
|
860 |
+
"loss": 0.5642,
|
861 |
+
"step": 2840
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 1.4,
|
865 |
+
"learning_rate": 5.578571428571429e-06,
|
866 |
+
"loss": 0.5126,
|
867 |
+
"step": 2860
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 1.41,
|
871 |
+
"learning_rate": 5.5309523809523815e-06,
|
872 |
+
"loss": 0.5687,
|
873 |
+
"step": 2880
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 1.42,
|
877 |
+
"learning_rate": 5.483333333333334e-06,
|
878 |
+
"loss": 0.5498,
|
879 |
+
"step": 2900
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 1.43,
|
883 |
+
"learning_rate": 5.435714285714286e-06,
|
884 |
+
"loss": 0.5213,
|
885 |
+
"step": 2920
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 1.44,
|
889 |
+
"learning_rate": 5.388095238095239e-06,
|
890 |
+
"loss": 0.575,
|
891 |
+
"step": 2940
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 1.45,
|
895 |
+
"learning_rate": 5.34047619047619e-06,
|
896 |
+
"loss": 0.5524,
|
897 |
+
"step": 2960
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 1.46,
|
901 |
+
"learning_rate": 5.292857142857143e-06,
|
902 |
+
"loss": 0.5304,
|
903 |
+
"step": 2980
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 1.47,
|
907 |
+
"learning_rate": 5.245238095238096e-06,
|
908 |
+
"loss": 0.4706,
|
909 |
+
"step": 3000
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 1.48,
|
913 |
+
"learning_rate": 5.197619047619048e-06,
|
914 |
+
"loss": 0.5716,
|
915 |
+
"step": 3020
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 1.49,
|
919 |
+
"learning_rate": 5.150000000000001e-06,
|
920 |
+
"loss": 0.4976,
|
921 |
+
"step": 3040
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 1.5,
|
925 |
+
"learning_rate": 5.102380952380953e-06,
|
926 |
+
"loss": 0.5022,
|
927 |
+
"step": 3060
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 1.51,
|
931 |
+
"learning_rate": 5.0547619047619055e-06,
|
932 |
+
"loss": 0.556,
|
933 |
+
"step": 3080
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.52,
|
937 |
+
"learning_rate": 5.007142857142857e-06,
|
938 |
+
"loss": 0.5023,
|
939 |
+
"step": 3100
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.53,
|
943 |
+
"learning_rate": 4.95952380952381e-06,
|
944 |
+
"loss": 0.5613,
|
945 |
+
"step": 3120
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 1.54,
|
949 |
+
"learning_rate": 4.911904761904762e-06,
|
950 |
+
"loss": 0.6031,
|
951 |
+
"step": 3140
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 1.55,
|
955 |
+
"learning_rate": 4.864285714285715e-06,
|
956 |
+
"loss": 0.5346,
|
957 |
+
"step": 3160
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 1.56,
|
961 |
+
"learning_rate": 4.816666666666667e-06,
|
962 |
+
"loss": 0.5665,
|
963 |
+
"step": 3180
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 1.57,
|
967 |
+
"learning_rate": 4.769047619047619e-06,
|
968 |
+
"loss": 0.5293,
|
969 |
+
"step": 3200
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 1.57,
|
973 |
+
"eval_loss": 0.5739259123802185,
|
974 |
+
"eval_runtime": 277.0719,
|
975 |
+
"eval_samples_per_second": 43.133,
|
976 |
+
"eval_steps_per_second": 5.392,
|
977 |
+
"step": 3200
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 1.58,
|
981 |
+
"learning_rate": 4.721428571428572e-06,
|
982 |
+
"loss": 0.5106,
|
983 |
+
"step": 3220
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 1.58,
|
987 |
+
"eval_loss": 0.5783331990242004,
|
988 |
+
"eval_runtime": 276.9686,
|
989 |
+
"eval_samples_per_second": 43.149,
|
990 |
+
"eval_steps_per_second": 5.394,
|
991 |
+
"step": 3220
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 1.59,
|
995 |
+
"learning_rate": 4.673809523809525e-06,
|
996 |
+
"loss": 0.5338,
|
997 |
+
"step": 3240
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 1.59,
|
1001 |
+
"eval_loss": 0.5718061327934265,
|
1002 |
+
"eval_runtime": 276.8816,
|
1003 |
+
"eval_samples_per_second": 43.163,
|
1004 |
+
"eval_steps_per_second": 5.396,
|
1005 |
+
"step": 3240
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 1.6,
|
1009 |
+
"learning_rate": 4.626190476190476e-06,
|
1010 |
+
"loss": 0.5128,
|
1011 |
+
"step": 3260
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 1.6,
|
1015 |
+
"eval_loss": 0.5826650261878967,
|
1016 |
+
"eval_runtime": 276.9662,
|
1017 |
+
"eval_samples_per_second": 43.15,
|
1018 |
+
"eval_steps_per_second": 5.394,
|
1019 |
+
"step": 3260
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 1.61,
|
1023 |
+
"learning_rate": 4.5785714285714285e-06,
|
1024 |
+
"loss": 0.5205,
|
1025 |
+
"step": 3280
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 1.61,
|
1029 |
+
"eval_loss": 0.6044849157333374,
|
1030 |
+
"eval_runtime": 276.8959,
|
1031 |
+
"eval_samples_per_second": 43.161,
|
1032 |
+
"eval_steps_per_second": 5.396,
|
1033 |
+
"step": 3280
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 1.62,
|
1037 |
+
"learning_rate": 4.530952380952382e-06,
|
1038 |
+
"loss": 0.5114,
|
1039 |
+
"step": 3300
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 1.62,
|
1043 |
+
"eval_loss": 0.5880448818206787,
|
1044 |
+
"eval_runtime": 276.8767,
|
1045 |
+
"eval_samples_per_second": 43.164,
|
1046 |
+
"eval_steps_per_second": 5.396,
|
1047 |
+
"step": 3300
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 1.63,
|
1051 |
+
"learning_rate": 4.483333333333333e-06,
|
1052 |
+
"loss": 0.5072,
|
1053 |
+
"step": 3320
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 1.63,
|
1057 |
+
"eval_loss": 0.5788173079490662,
|
1058 |
+
"eval_runtime": 276.8866,
|
1059 |
+
"eval_samples_per_second": 43.162,
|
1060 |
+
"eval_steps_per_second": 5.396,
|
1061 |
+
"step": 3320
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 1.64,
|
1065 |
+
"learning_rate": 4.435714285714286e-06,
|
1066 |
+
"loss": 0.5512,
|
1067 |
+
"step": 3340
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 1.64,
|
1071 |
+
"eval_loss": 0.5863245725631714,
|
1072 |
+
"eval_runtime": 276.8934,
|
1073 |
+
"eval_samples_per_second": 43.161,
|
1074 |
+
"eval_steps_per_second": 5.396,
|
1075 |
+
"step": 3340
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 1.65,
|
1079 |
+
"learning_rate": 4.388095238095238e-06,
|
1080 |
+
"loss": 0.4723,
|
1081 |
+
"step": 3360
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 1.65,
|
1085 |
+
"eval_loss": 0.5898299813270569,
|
1086 |
+
"eval_runtime": 276.9062,
|
1087 |
+
"eval_samples_per_second": 43.159,
|
1088 |
+
"eval_steps_per_second": 5.395,
|
1089 |
+
"step": 3360
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 1.66,
|
1093 |
+
"learning_rate": 4.340476190476191e-06,
|
1094 |
+
"loss": 0.5011,
|
1095 |
+
"step": 3380
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 1.66,
|
1099 |
+
"eval_loss": 0.5917273163795471,
|
1100 |
+
"eval_runtime": 276.8734,
|
1101 |
+
"eval_samples_per_second": 43.164,
|
1102 |
+
"eval_steps_per_second": 5.396,
|
1103 |
+
"step": 3380
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 1.67,
|
1107 |
+
"learning_rate": 4.292857142857143e-06,
|
1108 |
+
"loss": 0.5419,
|
1109 |
+
"step": 3400
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 1.67,
|
1113 |
+
"eval_loss": 0.6026594042778015,
|
1114 |
+
"eval_runtime": 276.8544,
|
1115 |
+
"eval_samples_per_second": 43.167,
|
1116 |
+
"eval_steps_per_second": 5.396,
|
1117 |
+
"step": 3400
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 1.68,
|
1121 |
+
"learning_rate": 4.245238095238095e-06,
|
1122 |
+
"loss": 0.5425,
|
1123 |
+
"step": 3420
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 1.68,
|
1127 |
+
"eval_loss": 0.5699217915534973,
|
1128 |
+
"eval_runtime": 276.8159,
|
1129 |
+
"eval_samples_per_second": 43.173,
|
1130 |
+
"eval_steps_per_second": 5.397,
|
1131 |
+
"step": 3420
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 1.69,
|
1135 |
+
"learning_rate": 4.1976190476190485e-06,
|
1136 |
+
"loss": 0.5703,
|
1137 |
+
"step": 3440
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 1.69,
|
1141 |
+
"eval_loss": 0.5897491574287415,
|
1142 |
+
"eval_runtime": 276.8228,
|
1143 |
+
"eval_samples_per_second": 43.172,
|
1144 |
+
"eval_steps_per_second": 5.397,
|
1145 |
+
"step": 3440
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 1.7,
|
1149 |
+
"learning_rate": 4.15e-06,
|
1150 |
+
"loss": 0.4646,
|
1151 |
+
"step": 3460
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 1.7,
|
1155 |
+
"eval_loss": 0.5916581153869629,
|
1156 |
+
"eval_runtime": 276.8047,
|
1157 |
+
"eval_samples_per_second": 43.175,
|
1158 |
+
"eval_steps_per_second": 5.397,
|
1159 |
+
"step": 3460
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 1.71,
|
1163 |
+
"learning_rate": 4.1023809523809525e-06,
|
1164 |
+
"loss": 0.4652,
|
1165 |
+
"step": 3480
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 1.71,
|
1169 |
+
"eval_loss": 0.5745313167572021,
|
1170 |
+
"eval_runtime": 276.8115,
|
1171 |
+
"eval_samples_per_second": 43.174,
|
1172 |
+
"eval_steps_per_second": 5.397,
|
1173 |
+
"step": 3480
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 1.72,
|
1177 |
+
"learning_rate": 4.054761904761905e-06,
|
1178 |
+
"loss": 0.5323,
|
1179 |
+
"step": 3500
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.72,
|
1183 |
+
"eval_loss": 0.5859553217887878,
|
1184 |
+
"eval_runtime": 276.8471,
|
1185 |
+
"eval_samples_per_second": 43.168,
|
1186 |
+
"eval_steps_per_second": 5.396,
|
1187 |
+
"step": 3500
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 1.73,
|
1191 |
+
"learning_rate": 4.007142857142857e-06,
|
1192 |
+
"loss": 0.5129,
|
1193 |
+
"step": 3520
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 1.73,
|
1197 |
+
"eval_loss": 0.5655719637870789,
|
1198 |
+
"eval_runtime": 276.8529,
|
1199 |
+
"eval_samples_per_second": 43.167,
|
1200 |
+
"eval_steps_per_second": 5.396,
|
1201 |
+
"step": 3520
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 1.74,
|
1205 |
+
"learning_rate": 3.95952380952381e-06,
|
1206 |
+
"loss": 0.5441,
|
1207 |
+
"step": 3540
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 1.74,
|
1211 |
+
"eval_loss": 0.5642224550247192,
|
1212 |
+
"eval_runtime": 276.8896,
|
1213 |
+
"eval_samples_per_second": 43.162,
|
1214 |
+
"eval_steps_per_second": 5.396,
|
1215 |
+
"step": 3540
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.75,
|
1219 |
+
"learning_rate": 3.911904761904762e-06,
|
1220 |
+
"loss": 0.5624,
|
1221 |
+
"step": 3560
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.75,
|
1225 |
+
"eval_loss": 0.5872688293457031,
|
1226 |
+
"eval_runtime": 276.8743,
|
1227 |
+
"eval_samples_per_second": 43.164,
|
1228 |
+
"eval_steps_per_second": 5.396,
|
1229 |
+
"step": 3560
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 1.76,
|
1233 |
+
"learning_rate": 3.864285714285715e-06,
|
1234 |
+
"loss": 0.4645,
|
1235 |
+
"step": 3580
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 1.76,
|
1239 |
+
"eval_loss": 0.5890788435935974,
|
1240 |
+
"eval_runtime": 276.8469,
|
1241 |
+
"eval_samples_per_second": 43.168,
|
1242 |
+
"eval_steps_per_second": 5.396,
|
1243 |
+
"step": 3580
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 1.77,
|
1247 |
+
"learning_rate": 3.816666666666667e-06,
|
1248 |
+
"loss": 0.5577,
|
1249 |
+
"step": 3600
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 1.77,
|
1253 |
+
"eval_loss": 0.5816096663475037,
|
1254 |
+
"eval_runtime": 276.8584,
|
1255 |
+
"eval_samples_per_second": 43.166,
|
1256 |
+
"eval_steps_per_second": 5.396,
|
1257 |
+
"step": 3600
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 1.78,
|
1261 |
+
"learning_rate": 3.7690476190476192e-06,
|
1262 |
+
"loss": 0.5199,
|
1263 |
+
"step": 3620
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.78,
|
1267 |
+
"eval_loss": 0.5579236745834351,
|
1268 |
+
"eval_runtime": 276.8666,
|
1269 |
+
"eval_samples_per_second": 43.165,
|
1270 |
+
"eval_steps_per_second": 5.396,
|
1271 |
+
"step": 3620
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 1.79,
|
1275 |
+
"learning_rate": 3.721428571428572e-06,
|
1276 |
+
"loss": 0.5061,
|
1277 |
+
"step": 3640
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 1.79,
|
1281 |
+
"eval_loss": 0.5837463140487671,
|
1282 |
+
"eval_runtime": 276.8995,
|
1283 |
+
"eval_samples_per_second": 43.16,
|
1284 |
+
"eval_steps_per_second": 5.395,
|
1285 |
+
"step": 3640
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 1.79,
|
1289 |
+
"learning_rate": 3.673809523809524e-06,
|
1290 |
+
"loss": 0.484,
|
1291 |
+
"step": 3660
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 1.79,
|
1295 |
+
"eval_loss": 0.5721494555473328,
|
1296 |
+
"eval_runtime": 277.0285,
|
1297 |
+
"eval_samples_per_second": 43.14,
|
1298 |
+
"eval_steps_per_second": 5.393,
|
1299 |
+
"step": 3660
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 1.8,
|
1303 |
+
"learning_rate": 3.6261904761904764e-06,
|
1304 |
+
"loss": 0.5095,
|
1305 |
+
"step": 3680
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.8,
|
1309 |
+
"eval_loss": 0.5820609927177429,
|
1310 |
+
"eval_runtime": 277.1157,
|
1311 |
+
"eval_samples_per_second": 43.126,
|
1312 |
+
"eval_steps_per_second": 5.391,
|
1313 |
+
"step": 3680
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 1.81,
|
1317 |
+
"learning_rate": 3.5785714285714292e-06,
|
1318 |
+
"loss": 0.5342,
|
1319 |
+
"step": 3700
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.81,
|
1323 |
+
"eval_loss": 0.5602211356163025,
|
1324 |
+
"eval_runtime": 277.1392,
|
1325 |
+
"eval_samples_per_second": 43.123,
|
1326 |
+
"eval_steps_per_second": 5.391,
|
1327 |
+
"step": 3700
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 1.82,
|
1331 |
+
"learning_rate": 3.530952380952381e-06,
|
1332 |
+
"loss": 0.5435,
|
1333 |
+
"step": 3720
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.82,
|
1337 |
+
"eval_loss": 0.5910717248916626,
|
1338 |
+
"eval_runtime": 277.1237,
|
1339 |
+
"eval_samples_per_second": 43.125,
|
1340 |
+
"eval_steps_per_second": 5.391,
|
1341 |
+
"step": 3720
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 1.83,
|
1345 |
+
"learning_rate": 3.4833333333333336e-06,
|
1346 |
+
"loss": 0.5288,
|
1347 |
+
"step": 3740
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.83,
|
1351 |
+
"eval_loss": 0.5647350549697876,
|
1352 |
+
"eval_runtime": 277.1519,
|
1353 |
+
"eval_samples_per_second": 43.121,
|
1354 |
+
"eval_steps_per_second": 5.391,
|
1355 |
+
"step": 3740
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 1.84,
|
1359 |
+
"learning_rate": 3.435714285714286e-06,
|
1360 |
+
"loss": 0.5476,
|
1361 |
+
"step": 3760
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.84,
|
1365 |
+
"eval_loss": 0.5733036398887634,
|
1366 |
+
"eval_runtime": 277.012,
|
1367 |
+
"eval_samples_per_second": 43.143,
|
1368 |
+
"eval_steps_per_second": 5.393,
|
1369 |
+
"step": 3760
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 1.85,
|
1373 |
+
"learning_rate": 3.388095238095238e-06,
|
1374 |
+
"loss": 0.5199,
|
1375 |
+
"step": 3780
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 1.85,
|
1379 |
+
"eval_loss": 0.5674840807914734,
|
1380 |
+
"eval_runtime": 276.9911,
|
1381 |
+
"eval_samples_per_second": 43.146,
|
1382 |
+
"eval_steps_per_second": 5.394,
|
1383 |
+
"step": 3780
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 1.86,
|
1387 |
+
"learning_rate": 3.3404761904761908e-06,
|
1388 |
+
"loss": 0.5067,
|
1389 |
+
"step": 3800
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.86,
|
1393 |
+
"eval_loss": 0.5838811993598938,
|
1394 |
+
"eval_runtime": 276.9655,
|
1395 |
+
"eval_samples_per_second": 43.15,
|
1396 |
+
"eval_steps_per_second": 5.394,
|
1397 |
+
"step": 3800
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 1.87,
|
1401 |
+
"learning_rate": 3.292857142857143e-06,
|
1402 |
+
"loss": 0.5418,
|
1403 |
+
"step": 3820
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 1.87,
|
1407 |
+
"eval_loss": 0.5757073163986206,
|
1408 |
+
"eval_runtime": 277.0012,
|
1409 |
+
"eval_samples_per_second": 43.144,
|
1410 |
+
"eval_steps_per_second": 5.393,
|
1411 |
+
"step": 3820
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 1.88,
|
1415 |
+
"learning_rate": 3.2452380952380955e-06,
|
1416 |
+
"loss": 0.4965,
|
1417 |
+
"step": 3840
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.88,
|
1421 |
+
"eval_loss": 0.5763747692108154,
|
1422 |
+
"eval_runtime": 276.9993,
|
1423 |
+
"eval_samples_per_second": 43.145,
|
1424 |
+
"eval_steps_per_second": 5.394,
|
1425 |
+
"step": 3840
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 1.89,
|
1429 |
+
"learning_rate": 3.197619047619048e-06,
|
1430 |
+
"loss": 0.5273,
|
1431 |
+
"step": 3860
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.89,
|
1435 |
+
"eval_loss": 0.5905867218971252,
|
1436 |
+
"eval_runtime": 276.9687,
|
1437 |
+
"eval_samples_per_second": 43.149,
|
1438 |
+
"eval_steps_per_second": 5.394,
|
1439 |
+
"step": 3860
|
1440 |
+
},
|
1441 |
+
{
|
1442 |
+
"epoch": 1.9,
|
1443 |
+
"learning_rate": 3.1500000000000003e-06,
|
1444 |
+
"loss": 0.5808,
|
1445 |
+
"step": 3880
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.9,
|
1449 |
+
"eval_loss": 0.5761615633964539,
|
1450 |
+
"eval_runtime": 276.9979,
|
1451 |
+
"eval_samples_per_second": 43.145,
|
1452 |
+
"eval_steps_per_second": 5.394,
|
1453 |
+
"step": 3880
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 1.91,
|
1457 |
+
"learning_rate": 3.1023809523809527e-06,
|
1458 |
+
"loss": 0.5161,
|
1459 |
+
"step": 3900
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.91,
|
1463 |
+
"eval_loss": 0.5611954927444458,
|
1464 |
+
"eval_runtime": 276.9358,
|
1465 |
+
"eval_samples_per_second": 43.154,
|
1466 |
+
"eval_steps_per_second": 5.395,
|
1467 |
+
"step": 3900
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 1.92,
|
1471 |
+
"learning_rate": 3.0547619047619047e-06,
|
1472 |
+
"loss": 0.4863,
|
1473 |
+
"step": 3920
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.92,
|
1477 |
+
"eval_loss": 0.5804067254066467,
|
1478 |
+
"eval_runtime": 276.9544,
|
1479 |
+
"eval_samples_per_second": 43.152,
|
1480 |
+
"eval_steps_per_second": 5.394,
|
1481 |
+
"step": 3920
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 1.93,
|
1485 |
+
"learning_rate": 3.0071428571428575e-06,
|
1486 |
+
"loss": 0.4827,
|
1487 |
+
"step": 3940
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.93,
|
1491 |
+
"eval_loss": 0.584104597568512,
|
1492 |
+
"eval_runtime": 276.9708,
|
1493 |
+
"eval_samples_per_second": 43.149,
|
1494 |
+
"eval_steps_per_second": 5.394,
|
1495 |
+
"step": 3940
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 1.94,
|
1499 |
+
"learning_rate": 2.95952380952381e-06,
|
1500 |
+
"loss": 0.4643,
|
1501 |
+
"step": 3960
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.94,
|
1505 |
+
"eval_loss": 0.5822347402572632,
|
1506 |
+
"eval_runtime": 276.9742,
|
1507 |
+
"eval_samples_per_second": 43.148,
|
1508 |
+
"eval_steps_per_second": 5.394,
|
1509 |
+
"step": 3960
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 1.95,
|
1513 |
+
"learning_rate": 2.911904761904762e-06,
|
1514 |
+
"loss": 0.5029,
|
1515 |
+
"step": 3980
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.95,
|
1519 |
+
"eval_loss": 0.6052400469779968,
|
1520 |
+
"eval_runtime": 276.9537,
|
1521 |
+
"eval_samples_per_second": 43.152,
|
1522 |
+
"eval_steps_per_second": 5.394,
|
1523 |
+
"step": 3980
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"epoch": 1.96,
|
1527 |
+
"learning_rate": 2.8642857142857143e-06,
|
1528 |
+
"loss": 0.509,
|
1529 |
+
"step": 4000
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.96,
|
1533 |
+
"eval_loss": 0.5799996852874756,
|
1534 |
+
"eval_runtime": 276.9867,
|
1535 |
+
"eval_samples_per_second": 43.146,
|
1536 |
+
"eval_steps_per_second": 5.394,
|
1537 |
+
"step": 4000
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 1.97,
|
1541 |
+
"learning_rate": 2.816666666666667e-06,
|
1542 |
+
"loss": 0.5382,
|
1543 |
+
"step": 4020
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 1.97,
|
1547 |
+
"eval_loss": 0.5645180940628052,
|
1548 |
+
"eval_runtime": 277.0026,
|
1549 |
+
"eval_samples_per_second": 43.144,
|
1550 |
+
"eval_steps_per_second": 5.393,
|
1551 |
+
"step": 4020
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.98,
|
1555 |
+
"learning_rate": 2.7690476190476195e-06,
|
1556 |
+
"loss": 0.469,
|
1557 |
+
"step": 4040
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.98,
|
1561 |
+
"eval_loss": 0.5685124397277832,
|
1562 |
+
"eval_runtime": 276.9786,
|
1563 |
+
"eval_samples_per_second": 43.148,
|
1564 |
+
"eval_steps_per_second": 5.394,
|
1565 |
+
"step": 4040
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 1.99,
|
1569 |
+
"learning_rate": 2.7214285714285714e-06,
|
1570 |
+
"loss": 0.5032,
|
1571 |
+
"step": 4060
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.99,
|
1575 |
+
"eval_loss": 0.5778502225875854,
|
1576 |
+
"eval_runtime": 277.0026,
|
1577 |
+
"eval_samples_per_second": 43.144,
|
1578 |
+
"eval_steps_per_second": 5.393,
|
1579 |
+
"step": 4060
|
1580 |
+
},
|
1581 |
+
{
|
1582 |
+
"epoch": 2.0,
|
1583 |
+
"learning_rate": 2.6738095238095243e-06,
|
1584 |
+
"loss": 0.5171,
|
1585 |
+
"step": 4080
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 2.0,
|
1589 |
+
"eval_loss": 0.5685559511184692,
|
1590 |
+
"eval_runtime": 277.0003,
|
1591 |
+
"eval_samples_per_second": 43.144,
|
1592 |
+
"eval_steps_per_second": 5.393,
|
1593 |
+
"step": 4080
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 2.01,
|
1597 |
+
"learning_rate": 2.6261904761904767e-06,
|
1598 |
+
"loss": 0.3938,
|
1599 |
+
"step": 4100
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 2.01,
|
1603 |
+
"eval_loss": 0.5889346599578857,
|
1604 |
+
"eval_runtime": 277.0343,
|
1605 |
+
"eval_samples_per_second": 43.139,
|
1606 |
+
"eval_steps_per_second": 5.393,
|
1607 |
+
"step": 4100
|
1608 |
+
},
|
1609 |
+
{
|
1610 |
+
"epoch": 2.02,
|
1611 |
+
"learning_rate": 2.5785714285714286e-06,
|
1612 |
+
"loss": 0.4321,
|
1613 |
+
"step": 4120
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 2.02,
|
1617 |
+
"eval_loss": 0.6039115190505981,
|
1618 |
+
"eval_runtime": 276.9943,
|
1619 |
+
"eval_samples_per_second": 43.145,
|
1620 |
+
"eval_steps_per_second": 5.394,
|
1621 |
+
"step": 4120
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 2.03,
|
1625 |
+
"learning_rate": 2.530952380952381e-06,
|
1626 |
+
"loss": 0.4185,
|
1627 |
+
"step": 4140
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 2.03,
|
1631 |
+
"eval_loss": 0.599577009677887,
|
1632 |
+
"eval_runtime": 277.0077,
|
1633 |
+
"eval_samples_per_second": 43.143,
|
1634 |
+
"eval_steps_per_second": 5.393,
|
1635 |
+
"step": 4140
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 2.04,
|
1639 |
+
"learning_rate": 2.4833333333333334e-06,
|
1640 |
+
"loss": 0.4782,
|
1641 |
+
"step": 4160
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 2.04,
|
1645 |
+
"eval_loss": 0.580022931098938,
|
1646 |
+
"eval_runtime": 277.0163,
|
1647 |
+
"eval_samples_per_second": 43.142,
|
1648 |
+
"eval_steps_per_second": 5.393,
|
1649 |
+
"step": 4160
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 2.05,
|
1653 |
+
"learning_rate": 2.435714285714286e-06,
|
1654 |
+
"loss": 0.424,
|
1655 |
+
"step": 4180
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 2.05,
|
1659 |
+
"eval_loss": 0.6373934745788574,
|
1660 |
+
"eval_runtime": 277.0011,
|
1661 |
+
"eval_samples_per_second": 43.144,
|
1662 |
+
"eval_steps_per_second": 5.393,
|
1663 |
+
"step": 4180
|
1664 |
+
},
|
1665 |
+
{
|
1666 |
+
"epoch": 2.06,
|
1667 |
+
"learning_rate": 2.388095238095238e-06,
|
1668 |
+
"loss": 0.3766,
|
1669 |
+
"step": 4200
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 2.06,
|
1673 |
+
"eval_loss": 0.6096173524856567,
|
1674 |
+
"eval_runtime": 276.9796,
|
1675 |
+
"eval_samples_per_second": 43.148,
|
1676 |
+
"eval_steps_per_second": 5.394,
|
1677 |
+
"step": 4200
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 2.07,
|
1681 |
+
"learning_rate": 2.3404761904761906e-06,
|
1682 |
+
"loss": 0.415,
|
1683 |
+
"step": 4220
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 2.07,
|
1687 |
+
"eval_loss": 0.6220654249191284,
|
1688 |
+
"eval_runtime": 277.0595,
|
1689 |
+
"eval_samples_per_second": 43.135,
|
1690 |
+
"eval_steps_per_second": 5.392,
|
1691 |
+
"step": 4220
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 2.08,
|
1695 |
+
"learning_rate": 2.292857142857143e-06,
|
1696 |
+
"loss": 0.4352,
|
1697 |
+
"step": 4240
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 2.08,
|
1701 |
+
"eval_loss": 0.615013599395752,
|
1702 |
+
"eval_runtime": 277.0601,
|
1703 |
+
"eval_samples_per_second": 43.135,
|
1704 |
+
"eval_steps_per_second": 5.392,
|
1705 |
+
"step": 4240
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 2.09,
|
1709 |
+
"learning_rate": 2.2452380952380954e-06,
|
1710 |
+
"loss": 0.4336,
|
1711 |
+
"step": 4260
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 2.09,
|
1715 |
+
"eval_loss": 0.6055351495742798,
|
1716 |
+
"eval_runtime": 277.0825,
|
1717 |
+
"eval_samples_per_second": 43.132,
|
1718 |
+
"eval_steps_per_second": 5.392,
|
1719 |
+
"step": 4260
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 2.1,
|
1723 |
+
"learning_rate": 2.1976190476190478e-06,
|
1724 |
+
"loss": 0.4289,
|
1725 |
+
"step": 4280
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 2.1,
|
1729 |
+
"eval_loss": 0.6138429641723633,
|
1730 |
+
"eval_runtime": 277.0898,
|
1731 |
+
"eval_samples_per_second": 43.13,
|
1732 |
+
"eval_steps_per_second": 5.392,
|
1733 |
+
"step": 4280
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 2.11,
|
1737 |
+
"learning_rate": 2.15e-06,
|
1738 |
+
"loss": 0.4433,
|
1739 |
+
"step": 4300
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 2.11,
|
1743 |
+
"eval_loss": 0.5946049094200134,
|
1744 |
+
"eval_runtime": 277.0747,
|
1745 |
+
"eval_samples_per_second": 43.133,
|
1746 |
+
"eval_steps_per_second": 5.392,
|
1747 |
+
"step": 4300
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"epoch": 2.12,
|
1751 |
+
"learning_rate": 2.1023809523809526e-06,
|
1752 |
+
"loss": 0.4478,
|
1753 |
+
"step": 4320
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 2.12,
|
1757 |
+
"eval_loss": 0.611806333065033,
|
1758 |
+
"eval_runtime": 277.0164,
|
1759 |
+
"eval_samples_per_second": 43.142,
|
1760 |
+
"eval_steps_per_second": 5.393,
|
1761 |
+
"step": 4320
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 2.13,
|
1765 |
+
"learning_rate": 2.054761904761905e-06,
|
1766 |
+
"loss": 0.4787,
|
1767 |
+
"step": 4340
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 2.13,
|
1771 |
+
"eval_loss": 0.5969259738922119,
|
1772 |
+
"eval_runtime": 277.0423,
|
1773 |
+
"eval_samples_per_second": 43.138,
|
1774 |
+
"eval_steps_per_second": 5.393,
|
1775 |
+
"step": 4340
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 2.14,
|
1779 |
+
"learning_rate": 2.0071428571428573e-06,
|
1780 |
+
"loss": 0.4432,
|
1781 |
+
"step": 4360
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 2.14,
|
1785 |
+
"eval_loss": 0.6047642230987549,
|
1786 |
+
"eval_runtime": 277.0355,
|
1787 |
+
"eval_samples_per_second": 43.139,
|
1788 |
+
"eval_steps_per_second": 5.393,
|
1789 |
+
"step": 4360
|
1790 |
+
},
|
1791 |
+
{
|
1792 |
+
"epoch": 2.15,
|
1793 |
+
"learning_rate": 1.9595238095238097e-06,
|
1794 |
+
"loss": 0.4319,
|
1795 |
+
"step": 4380
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 2.15,
|
1799 |
+
"eval_loss": 0.5948361158370972,
|
1800 |
+
"eval_runtime": 277.1353,
|
1801 |
+
"eval_samples_per_second": 43.123,
|
1802 |
+
"eval_steps_per_second": 5.391,
|
1803 |
+
"step": 4380
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 2.16,
|
1807 |
+
"learning_rate": 1.911904761904762e-06,
|
1808 |
+
"loss": 0.3939,
|
1809 |
+
"step": 4400
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 2.16,
|
1813 |
+
"eval_loss": 0.6115566492080688,
|
1814 |
+
"eval_runtime": 277.1102,
|
1815 |
+
"eval_samples_per_second": 43.127,
|
1816 |
+
"eval_steps_per_second": 5.391,
|
1817 |
+
"step": 4400
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 2.17,
|
1821 |
+
"learning_rate": 1.8642857142857143e-06,
|
1822 |
+
"loss": 0.3921,
|
1823 |
+
"step": 4420
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 2.17,
|
1827 |
+
"eval_loss": 0.608245849609375,
|
1828 |
+
"eval_runtime": 277.1416,
|
1829 |
+
"eval_samples_per_second": 43.122,
|
1830 |
+
"eval_steps_per_second": 5.391,
|
1831 |
+
"step": 4420
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 2.18,
|
1835 |
+
"learning_rate": 1.816666666666667e-06,
|
1836 |
+
"loss": 0.4381,
|
1837 |
+
"step": 4440
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 2.18,
|
1841 |
+
"eval_loss": 0.6282362937927246,
|
1842 |
+
"eval_runtime": 277.0787,
|
1843 |
+
"eval_samples_per_second": 43.132,
|
1844 |
+
"eval_steps_per_second": 5.392,
|
1845 |
+
"step": 4440
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 2.19,
|
1849 |
+
"learning_rate": 1.769047619047619e-06,
|
1850 |
+
"loss": 0.4461,
|
1851 |
+
"step": 4460
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 2.19,
|
1855 |
+
"eval_loss": 0.6083888411521912,
|
1856 |
+
"eval_runtime": 277.0933,
|
1857 |
+
"eval_samples_per_second": 43.13,
|
1858 |
+
"eval_steps_per_second": 5.392,
|
1859 |
+
"step": 4460
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 2.2,
|
1863 |
+
"learning_rate": 1.7214285714285717e-06,
|
1864 |
+
"loss": 0.4012,
|
1865 |
+
"step": 4480
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 2.2,
|
1869 |
+
"eval_loss": 0.6091529726982117,
|
1870 |
+
"eval_runtime": 277.0771,
|
1871 |
+
"eval_samples_per_second": 43.132,
|
1872 |
+
"eval_steps_per_second": 5.392,
|
1873 |
+
"step": 4480
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 2.21,
|
1877 |
+
"learning_rate": 1.6738095238095239e-06,
|
1878 |
+
"loss": 0.3849,
|
1879 |
+
"step": 4500
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 2.21,
|
1883 |
+
"eval_loss": 0.6152328848838806,
|
1884 |
+
"eval_runtime": 277.2346,
|
1885 |
+
"eval_samples_per_second": 43.108,
|
1886 |
+
"eval_steps_per_second": 5.389,
|
1887 |
+
"step": 4500
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 2.22,
|
1891 |
+
"learning_rate": 1.6261904761904763e-06,
|
1892 |
+
"loss": 0.4178,
|
1893 |
+
"step": 4520
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 2.22,
|
1897 |
+
"eval_loss": 0.6003779172897339,
|
1898 |
+
"eval_runtime": 277.2625,
|
1899 |
+
"eval_samples_per_second": 43.104,
|
1900 |
+
"eval_steps_per_second": 5.388,
|
1901 |
+
"step": 4520
|
1902 |
+
},
|
1903 |
+
{
|
1904 |
+
"epoch": 2.23,
|
1905 |
+
"learning_rate": 1.5785714285714287e-06,
|
1906 |
+
"loss": 0.4163,
|
1907 |
+
"step": 4540
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 2.23,
|
1911 |
+
"eval_loss": 0.6059258580207825,
|
1912 |
+
"eval_runtime": 277.3365,
|
1913 |
+
"eval_samples_per_second": 43.092,
|
1914 |
+
"eval_steps_per_second": 5.387,
|
1915 |
+
"step": 4540
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 2.24,
|
1919 |
+
"learning_rate": 1.530952380952381e-06,
|
1920 |
+
"loss": 0.4006,
|
1921 |
+
"step": 4560
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 2.24,
|
1925 |
+
"eval_loss": 0.6115380525588989,
|
1926 |
+
"eval_runtime": 277.2201,
|
1927 |
+
"eval_samples_per_second": 43.11,
|
1928 |
+
"eval_steps_per_second": 5.389,
|
1929 |
+
"step": 4560
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 2.25,
|
1933 |
+
"learning_rate": 1.4833333333333337e-06,
|
1934 |
+
"loss": 0.4225,
|
1935 |
+
"step": 4580
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 2.25,
|
1939 |
+
"eval_loss": 0.6130145192146301,
|
1940 |
+
"eval_runtime": 277.4178,
|
1941 |
+
"eval_samples_per_second": 43.079,
|
1942 |
+
"eval_steps_per_second": 5.385,
|
1943 |
+
"step": 4580
|
1944 |
+
},
|
1945 |
+
{
|
1946 |
+
"epoch": 2.26,
|
1947 |
+
"learning_rate": 1.4357142857142859e-06,
|
1948 |
+
"loss": 0.4008,
|
1949 |
+
"step": 4600
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 2.26,
|
1953 |
+
"eval_loss": 0.6094552278518677,
|
1954 |
+
"eval_runtime": 277.5161,
|
1955 |
+
"eval_samples_per_second": 43.064,
|
1956 |
+
"eval_steps_per_second": 5.383,
|
1957 |
+
"step": 4600
|
1958 |
+
},
|
1959 |
+
{
|
1960 |
+
"epoch": 2.27,
|
1961 |
+
"learning_rate": 1.388095238095238e-06,
|
1962 |
+
"loss": 0.4706,
|
1963 |
+
"step": 4620
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 2.27,
|
1967 |
+
"eval_loss": 0.6135911345481873,
|
1968 |
+
"eval_runtime": 277.6184,
|
1969 |
+
"eval_samples_per_second": 43.048,
|
1970 |
+
"eval_steps_per_second": 5.381,
|
1971 |
+
"step": 4620
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 2.28,
|
1975 |
+
"learning_rate": 1.3404761904761906e-06,
|
1976 |
+
"loss": 0.3902,
|
1977 |
+
"step": 4640
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 2.28,
|
1981 |
+
"eval_loss": 0.6103312373161316,
|
1982 |
+
"eval_runtime": 277.532,
|
1983 |
+
"eval_samples_per_second": 43.062,
|
1984 |
+
"eval_steps_per_second": 5.383,
|
1985 |
+
"step": 4640
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 2.29,
|
1989 |
+
"learning_rate": 1.2928571428571428e-06,
|
1990 |
+
"loss": 0.4048,
|
1991 |
+
"step": 4660
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 2.29,
|
1995 |
+
"eval_loss": 0.608475923538208,
|
1996 |
+
"eval_runtime": 277.3473,
|
1997 |
+
"eval_samples_per_second": 43.09,
|
1998 |
+
"eval_steps_per_second": 5.387,
|
1999 |
+
"step": 4660
|
2000 |
+
},
|
2001 |
+
{
|
2002 |
+
"epoch": 2.3,
|
2003 |
+
"learning_rate": 1.2452380952380954e-06,
|
2004 |
+
"loss": 0.4411,
|
2005 |
+
"step": 4680
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 2.3,
|
2009 |
+
"eval_loss": 0.6138780117034912,
|
2010 |
+
"eval_runtime": 277.4196,
|
2011 |
+
"eval_samples_per_second": 43.079,
|
2012 |
+
"eval_steps_per_second": 5.385,
|
2013 |
+
"step": 4680
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 2.31,
|
2017 |
+
"learning_rate": 1.1976190476190478e-06,
|
2018 |
+
"loss": 0.403,
|
2019 |
+
"step": 4700
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 2.31,
|
2023 |
+
"eval_loss": 0.6047297120094299,
|
2024 |
+
"eval_runtime": 277.4316,
|
2025 |
+
"eval_samples_per_second": 43.077,
|
2026 |
+
"eval_steps_per_second": 5.385,
|
2027 |
+
"step": 4700
|
2028 |
+
},
|
2029 |
+
{
|
2030 |
+
"epoch": 2.31,
|
2031 |
+
"learning_rate": 1.1500000000000002e-06,
|
2032 |
+
"loss": 0.4799,
|
2033 |
+
"step": 4720
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 2.31,
|
2037 |
+
"eval_loss": 0.6043194532394409,
|
2038 |
+
"eval_runtime": 277.378,
|
2039 |
+
"eval_samples_per_second": 43.086,
|
2040 |
+
"eval_steps_per_second": 5.386,
|
2041 |
+
"step": 4720
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 2.32,
|
2045 |
+
"learning_rate": 1.1023809523809524e-06,
|
2046 |
+
"loss": 0.4316,
|
2047 |
+
"step": 4740
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 2.32,
|
2051 |
+
"eval_loss": 0.5959681868553162,
|
2052 |
+
"eval_runtime": 277.4868,
|
2053 |
+
"eval_samples_per_second": 43.069,
|
2054 |
+
"eval_steps_per_second": 5.384,
|
2055 |
+
"step": 4740
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 2.33,
|
2059 |
+
"learning_rate": 1.0547619047619048e-06,
|
2060 |
+
"loss": 0.4198,
|
2061 |
+
"step": 4760
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 2.33,
|
2065 |
+
"eval_loss": 0.6030734181404114,
|
2066 |
+
"eval_runtime": 277.3901,
|
2067 |
+
"eval_samples_per_second": 43.084,
|
2068 |
+
"eval_steps_per_second": 5.386,
|
2069 |
+
"step": 4760
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 2.34,
|
2073 |
+
"learning_rate": 1.0071428571428572e-06,
|
2074 |
+
"loss": 0.4254,
|
2075 |
+
"step": 4780
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 2.34,
|
2079 |
+
"eval_loss": 0.60329669713974,
|
2080 |
+
"eval_runtime": 277.3302,
|
2081 |
+
"eval_samples_per_second": 43.093,
|
2082 |
+
"eval_steps_per_second": 5.387,
|
2083 |
+
"step": 4780
|
2084 |
+
},
|
2085 |
+
{
|
2086 |
+
"epoch": 2.35,
|
2087 |
+
"learning_rate": 9.595238095238096e-07,
|
2088 |
+
"loss": 0.387,
|
2089 |
+
"step": 4800
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 2.35,
|
2093 |
+
"eval_loss": 0.611955463886261,
|
2094 |
+
"eval_runtime": 277.4816,
|
2095 |
+
"eval_samples_per_second": 43.07,
|
2096 |
+
"eval_steps_per_second": 5.384,
|
2097 |
+
"step": 4800
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 2.36,
|
2101 |
+
"learning_rate": 9.119047619047621e-07,
|
2102 |
+
"loss": 0.3882,
|
2103 |
+
"step": 4820
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 2.36,
|
2107 |
+
"eval_loss": 0.612755298614502,
|
2108 |
+
"eval_runtime": 277.4062,
|
2109 |
+
"eval_samples_per_second": 43.081,
|
2110 |
+
"eval_steps_per_second": 5.386,
|
2111 |
+
"step": 4820
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 2.37,
|
2115 |
+
"learning_rate": 8.642857142857144e-07,
|
2116 |
+
"loss": 0.4307,
|
2117 |
+
"step": 4840
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 2.37,
|
2121 |
+
"eval_loss": 0.6149932742118835,
|
2122 |
+
"eval_runtime": 277.4451,
|
2123 |
+
"eval_samples_per_second": 43.075,
|
2124 |
+
"eval_steps_per_second": 5.385,
|
2125 |
+
"step": 4840
|
2126 |
+
},
|
2127 |
+
{
|
2128 |
+
"epoch": 2.38,
|
2129 |
+
"learning_rate": 8.166666666666668e-07,
|
2130 |
+
"loss": 0.434,
|
2131 |
+
"step": 4860
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 2.38,
|
2135 |
+
"eval_loss": 0.6077226400375366,
|
2136 |
+
"eval_runtime": 277.2986,
|
2137 |
+
"eval_samples_per_second": 43.098,
|
2138 |
+
"eval_steps_per_second": 5.388,
|
2139 |
+
"step": 4860
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 2.39,
|
2143 |
+
"learning_rate": 7.690476190476191e-07,
|
2144 |
+
"loss": 0.4225,
|
2145 |
+
"step": 4880
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 2.39,
|
2149 |
+
"eval_loss": 0.6070570945739746,
|
2150 |
+
"eval_runtime": 277.4566,
|
2151 |
+
"eval_samples_per_second": 43.073,
|
2152 |
+
"eval_steps_per_second": 5.385,
|
2153 |
+
"step": 4880
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 2.4,
|
2157 |
+
"learning_rate": 7.214285714285715e-07,
|
2158 |
+
"loss": 0.4134,
|
2159 |
+
"step": 4900
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 2.4,
|
2163 |
+
"eval_loss": 0.6035702228546143,
|
2164 |
+
"eval_runtime": 277.4001,
|
2165 |
+
"eval_samples_per_second": 43.082,
|
2166 |
+
"eval_steps_per_second": 5.386,
|
2167 |
+
"step": 4900
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"epoch": 2.41,
|
2171 |
+
"learning_rate": 6.738095238095238e-07,
|
2172 |
+
"loss": 0.3846,
|
2173 |
+
"step": 4920
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 2.41,
|
2177 |
+
"eval_loss": 0.612420380115509,
|
2178 |
+
"eval_runtime": 277.4205,
|
2179 |
+
"eval_samples_per_second": 43.079,
|
2180 |
+
"eval_steps_per_second": 5.385,
|
2181 |
+
"step": 4920
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 2.42,
|
2185 |
+
"learning_rate": 6.261904761904762e-07,
|
2186 |
+
"loss": 0.3943,
|
2187 |
+
"step": 4940
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 2.42,
|
2191 |
+
"eval_loss": 0.6291103959083557,
|
2192 |
+
"eval_runtime": 277.2666,
|
2193 |
+
"eval_samples_per_second": 43.103,
|
2194 |
+
"eval_steps_per_second": 5.388,
|
2195 |
+
"step": 4940
|
2196 |
+
},
|
2197 |
+
{
|
2198 |
+
"epoch": 2.43,
|
2199 |
+
"learning_rate": 5.785714285714286e-07,
|
2200 |
+
"loss": 0.4455,
|
2201 |
+
"step": 4960
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 2.43,
|
2205 |
+
"eval_loss": 0.6184937953948975,
|
2206 |
+
"eval_runtime": 277.2863,
|
2207 |
+
"eval_samples_per_second": 43.1,
|
2208 |
+
"eval_steps_per_second": 5.388,
|
2209 |
+
"step": 4960
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 2.44,
|
2213 |
+
"learning_rate": 5.30952380952381e-07,
|
2214 |
+
"loss": 0.4104,
|
2215 |
+
"step": 4980
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 2.44,
|
2219 |
+
"eval_loss": 0.6063624620437622,
|
2220 |
+
"eval_runtime": 277.3406,
|
2221 |
+
"eval_samples_per_second": 43.091,
|
2222 |
+
"eval_steps_per_second": 5.387,
|
2223 |
+
"step": 4980
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 2.45,
|
2227 |
+
"learning_rate": 4.833333333333334e-07,
|
2228 |
+
"loss": 0.4158,
|
2229 |
+
"step": 5000
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 2.45,
|
2233 |
+
"eval_loss": 0.6095247268676758,
|
2234 |
+
"eval_runtime": 277.4398,
|
2235 |
+
"eval_samples_per_second": 43.076,
|
2236 |
+
"eval_steps_per_second": 5.385,
|
2237 |
+
"step": 5000
|
2238 |
+
},
|
2239 |
+
{
|
2240 |
+
"epoch": 2.46,
|
2241 |
+
"learning_rate": 4.357142857142858e-07,
|
2242 |
+
"loss": 0.4135,
|
2243 |
+
"step": 5020
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 2.46,
|
2247 |
+
"eval_loss": 0.6154703497886658,
|
2248 |
+
"eval_runtime": 277.3849,
|
2249 |
+
"eval_samples_per_second": 43.085,
|
2250 |
+
"eval_steps_per_second": 5.386,
|
2251 |
+
"step": 5020
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 2.47,
|
2255 |
+
"learning_rate": 3.8809523809523813e-07,
|
2256 |
+
"loss": 0.3789,
|
2257 |
+
"step": 5040
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 2.47,
|
2261 |
+
"eval_loss": 0.6208740472793579,
|
2262 |
+
"eval_runtime": 277.33,
|
2263 |
+
"eval_samples_per_second": 43.093,
|
2264 |
+
"eval_steps_per_second": 5.387,
|
2265 |
+
"step": 5040
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 2.48,
|
2269 |
+
"learning_rate": 3.404761904761905e-07,
|
2270 |
+
"loss": 0.418,
|
2271 |
+
"step": 5060
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 2.48,
|
2275 |
+
"eval_loss": 0.6106104850769043,
|
2276 |
+
"eval_runtime": 277.377,
|
2277 |
+
"eval_samples_per_second": 43.086,
|
2278 |
+
"eval_steps_per_second": 5.386,
|
2279 |
+
"step": 5060
|
2280 |
+
},
|
2281 |
+
{
|
2282 |
+
"epoch": 2.49,
|
2283 |
+
"learning_rate": 2.9285714285714287e-07,
|
2284 |
+
"loss": 0.3931,
|
2285 |
+
"step": 5080
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 2.49,
|
2289 |
+
"eval_loss": 0.604749858379364,
|
2290 |
+
"eval_runtime": 277.377,
|
2291 |
+
"eval_samples_per_second": 43.086,
|
2292 |
+
"eval_steps_per_second": 5.386,
|
2293 |
+
"step": 5080
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 2.5,
|
2297 |
+
"learning_rate": 2.4523809523809526e-07,
|
2298 |
+
"loss": 0.4289,
|
2299 |
+
"step": 5100
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 2.5,
|
2303 |
+
"eval_loss": 0.6055382490158081,
|
2304 |
+
"eval_runtime": 277.4628,
|
2305 |
+
"eval_samples_per_second": 43.072,
|
2306 |
+
"eval_steps_per_second": 5.385,
|
2307 |
+
"step": 5100
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 2.51,
|
2311 |
+
"learning_rate": 1.9761904761904763e-07,
|
2312 |
+
"loss": 0.4051,
|
2313 |
+
"step": 5120
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 2.51,
|
2317 |
+
"eval_loss": 0.6083624958992004,
|
2318 |
+
"eval_runtime": 277.3533,
|
2319 |
+
"eval_samples_per_second": 43.089,
|
2320 |
+
"eval_steps_per_second": 5.387,
|
2321 |
+
"step": 5120
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 2.52,
|
2325 |
+
"learning_rate": 1.5000000000000002e-07,
|
2326 |
+
"loss": 0.4217,
|
2327 |
+
"step": 5140
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 2.52,
|
2331 |
+
"eval_loss": 0.611778736114502,
|
2332 |
+
"eval_runtime": 277.4092,
|
2333 |
+
"eval_samples_per_second": 43.081,
|
2334 |
+
"eval_steps_per_second": 5.386,
|
2335 |
+
"step": 5140
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"epoch": 2.53,
|
2339 |
+
"learning_rate": 1.023809523809524e-07,
|
2340 |
+
"loss": 0.3843,
|
2341 |
+
"step": 5160
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 2.53,
|
2345 |
+
"eval_loss": 0.613944411277771,
|
2346 |
+
"eval_runtime": 277.3668,
|
2347 |
+
"eval_samples_per_second": 43.087,
|
2348 |
+
"eval_steps_per_second": 5.386,
|
2349 |
+
"step": 5160
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 2.54,
|
2353 |
+
"learning_rate": 5.4761904761904766e-08,
|
2354 |
+
"loss": 0.4435,
|
2355 |
+
"step": 5180
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 2.54,
|
2359 |
+
"eval_loss": 0.6125811338424683,
|
2360 |
+
"eval_runtime": 277.4188,
|
2361 |
+
"eval_samples_per_second": 43.079,
|
2362 |
+
"eval_steps_per_second": 5.385,
|
2363 |
+
"step": 5180
|
2364 |
+
},
|
2365 |
+
{
|
2366 |
+
"epoch": 2.55,
|
2367 |
+
"learning_rate": 7.142857142857144e-09,
|
2368 |
+
"loss": 0.4274,
|
2369 |
+
"step": 5200
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 2.55,
|
2373 |
+
"eval_loss": 0.6120193600654602,
|
2374 |
+
"eval_runtime": 277.4157,
|
2375 |
+
"eval_samples_per_second": 43.08,
|
2376 |
+
"eval_steps_per_second": 5.385,
|
2377 |
+
"step": 5200
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 2.55,
|
2381 |
+
"step": 5200,
|
2382 |
+
"total_flos": 3.09073923350188e+17,
|
2383 |
+
"train_loss": 0.820626282783655,
|
2384 |
+
"train_runtime": 52836.9017,
|
2385 |
+
"train_samples_per_second": 6.299,
|
2386 |
+
"train_steps_per_second": 0.098
|
2387 |
+
}
|
2388 |
+
],
|
2389 |
+
"logging_steps": 20,
|
2390 |
+
"max_steps": 5200,
|
2391 |
+
"num_train_epochs": 3,
|
2392 |
+
"save_steps": 20,
|
2393 |
+
"total_flos": 3.09073923350188e+17,
|
2394 |
+
"trial_name": null,
|
2395 |
+
"trial_params": null
|
2396 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ca203eda63948cd93799ce1d47ea864d0bcc15b9ca0e08ebdd995a2892d87bc
|
3 |
+
size 4472
|
validation_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.55,
|
3 |
+
"eval_loss": 0.5579236745834351,
|
4 |
+
"eval_runtime": 277.7608,
|
5 |
+
"eval_samples_per_second": 43.026,
|
6 |
+
"eval_steps_per_second": 5.379,
|
7 |
+
"validation_samples": 11873
|
8 |
+
}
|