Upload 66 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1200/README.md +204 -0
- checkpoint-1200/adapter_config.json +27 -0
- checkpoint-1200/adapter_model.safetensors +3 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/special_tokens_map.json +30 -0
- checkpoint-1200/tokenizer.model +3 -0
- checkpoint-1200/tokenizer_config.json +52 -0
- checkpoint-1200/trainer_state.json +1461 -0
- checkpoint-1200/training_args.bin +3 -0
- checkpoint-3000/README.md +204 -0
- checkpoint-3000/adapter_config.json +27 -0
- checkpoint-3000/adapter_model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/special_tokens_map.json +30 -0
- checkpoint-3000/tokenizer.model +3 -0
- checkpoint-3000/tokenizer_config.json +52 -0
- checkpoint-3000/trainer_state.json +3621 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-5700/README.md +204 -0
- checkpoint-5700/adapter_config.json +27 -0
- checkpoint-5700/adapter_model.safetensors +3 -0
- checkpoint-5700/optimizer.pt +3 -0
- checkpoint-5700/rng_state.pth +3 -0
- checkpoint-5700/scheduler.pt +3 -0
- checkpoint-5700/special_tokens_map.json +30 -0
- checkpoint-5700/tokenizer.model +3 -0
- checkpoint-5700/tokenizer_config.json +52 -0
- checkpoint-5700/trainer_state.json +0 -0
- checkpoint-5700/training_args.bin +3 -0
- checkpoint-6000/README.md +204 -0
- checkpoint-6000/adapter_config.json +27 -0
- checkpoint-6000/adapter_model.safetensors +3 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/special_tokens_map.json +30 -0
- checkpoint-6000/tokenizer.model +3 -0
- checkpoint-6000/tokenizer_config.json +52 -0
- checkpoint-6000/trainer_state.json +0 -0
- checkpoint-6000/training_args.bin +3 -0
- checkpoint-900/README.md +204 -0
- checkpoint-900/adapter_config.json +27 -0
- checkpoint-900/adapter_model.safetensors +3 -0
- checkpoint-900/optimizer.pt +3 -0
- checkpoint-900/rng_state.pth +3 -0
- checkpoint-900/scheduler.pt +3 -0
checkpoint-1200/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chinese-llama-2-13b
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-1200/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chinese-llama-2-13b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-1200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdb2cd52315686b02c45e7bcbdd7a86b6ea3288a4c670b9cdb64853ece231dbe
|
3 |
+
size 26235704
|
checkpoint-1200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6c0c101c8a0a071fd990a42cf4e39066c55554fdeeb03d43d7401780a2f0761
|
3 |
+
size 52562821
|
checkpoint-1200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50f315bd4a30035a24ac96c6e52b4c92908270e748d97a7df690c6d2ce3f57a5
|
3 |
+
size 14575
|
checkpoint-1200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2279c6ee09a23ea957c9079de68edfb92c5b458c02112e0005e1739ed4caab0d
|
3 |
+
size 627
|
checkpoint-1200/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-1200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c
|
3 |
+
size 844403
|
checkpoint-1200/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": true,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"padding_side": "right",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"split_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false,
|
51 |
+
"use_fast": false
|
52 |
+
}
|
checkpoint-1200/trainer_state.json
ADDED
@@ -0,0 +1,1461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6166495375128469,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999979150098865e-05,
|
14 |
+
"loss": 4.0418,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.999989444743508e-05,
|
20 |
+
"loss": 3.8361,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999974458911041e-05,
|
26 |
+
"loss": 3.8737,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999529575515425e-05,
|
32 |
+
"loss": 3.806,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.9999249407210515e-05,
|
38 |
+
"loss": 3.4125,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.9998904084925845e-05,
|
44 |
+
"loss": 3.6489,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999849360956141e-05,
|
50 |
+
"loss": 3.4719,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.999811831976564e-05,
|
56 |
+
"loss": 3.5265,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999759057166764e-05,
|
62 |
+
"loss": 3.6889,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.9996997673913204e-05,
|
68 |
+
"loss": 3.5104,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999633962804756e-05,
|
74 |
+
"loss": 3.5778,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.999561643578575e-05,
|
80 |
+
"loss": 3.3353,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.999482809901257e-05,
|
86 |
+
"loss": 3.3511,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9993974619782625e-05,
|
92 |
+
"loss": 3.6355,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999305600032027e-05,
|
98 |
+
"loss": 3.3915,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999207224301965e-05,
|
104 |
+
"loss": 3.4926,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999102335044467e-05,
|
110 |
+
"loss": 3.4918,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.9989909325328996e-05,
|
116 |
+
"loss": 3.3984,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.998873017057605e-05,
|
122 |
+
"loss": 3.4989,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998748588925897e-05,
|
128 |
+
"loss": 3.6368,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986176484620665e-05,
|
134 |
+
"loss": 3.4412,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998480196007375e-05,
|
140 |
+
"loss": 3.4708,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.9983362319200554e-05,
|
146 |
+
"loss": 3.37,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.998185756575313e-05,
|
152 |
+
"loss": 3.4524,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9980287703653225e-05,
|
158 |
+
"loss": 3.3863,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997865273699227e-05,
|
164 |
+
"loss": 3.4414,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997729789123732e-05,
|
170 |
+
"loss": 3.3335,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997554574721849e-05,
|
176 |
+
"loss": 3.231,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997372851099727e-05,
|
182 |
+
"loss": 3.5962,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997184618730983e-05,
|
188 |
+
"loss": 3.2795,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.996989878106192e-05,
|
194 |
+
"loss": 3.5384,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996788629732897e-05,
|
200 |
+
"loss": 3.3274,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.996580874135597e-05,
|
206 |
+
"loss": 3.2292,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996366611855753e-05,
|
212 |
+
"loss": 3.4829,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996145843451785e-05,
|
218 |
+
"loss": 3.1998,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9959185694990655e-05,
|
224 |
+
"loss": 3.3757,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.1,
|
229 |
+
"learning_rate": 4.995684790589926e-05,
|
230 |
+
"loss": 3.1001,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.99544450733365e-05,
|
236 |
+
"loss": 3.2301,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.995197720356471e-05,
|
242 |
+
"loss": 3.3187,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.994944430301576e-05,
|
248 |
+
"loss": 3.527,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.11,
|
253 |
+
"learning_rate": 4.994684637829098e-05,
|
254 |
+
"loss": 3.3808,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.994418343616119e-05,
|
260 |
+
"loss": 3.2406,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.994145548356664e-05,
|
266 |
+
"loss": 3.3463,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.993866252761702e-05,
|
272 |
+
"loss": 3.2972,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.12,
|
277 |
+
"learning_rate": 4.993580457559145e-05,
|
278 |
+
"loss": 3.4135,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9932881634938424e-05,
|
284 |
+
"loss": 3.4025,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.992989371327581e-05,
|
290 |
+
"loss": 3.662,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992684081839086e-05,
|
296 |
+
"loss": 3.4279,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.13,
|
301 |
+
"learning_rate": 4.9923722958240124e-05,
|
302 |
+
"loss": 3.3075,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992054014094951e-05,
|
308 |
+
"loss": 3.2826,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.991729237481417e-05,
|
314 |
+
"loss": 3.4992,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991397966829856e-05,
|
320 |
+
"loss": 3.2421,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.14,
|
325 |
+
"learning_rate": 4.991060203003639e-05,
|
326 |
+
"loss": 3.2615,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.9907159468830585e-05,
|
332 |
+
"loss": 3.3299,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990365199365327e-05,
|
338 |
+
"loss": 3.3117,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.9900079613645754e-05,
|
344 |
+
"loss": 3.4729,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.15,
|
349 |
+
"learning_rate": 4.9896442338118524e-05,
|
350 |
+
"loss": 3.2521,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989274017655117e-05,
|
356 |
+
"loss": 3.261,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9888973138592414e-05,
|
362 |
+
"loss": 3.4403,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988514123406004e-05,
|
368 |
+
"loss": 3.3408,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.16,
|
373 |
+
"learning_rate": 4.9881244472940914e-05,
|
374 |
+
"loss": 3.3208,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.9877282865390904e-05,
|
380 |
+
"loss": 3.6889,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.9873256421734915e-05,
|
386 |
+
"loss": 3.1537,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.986916515246681e-05,
|
392 |
+
"loss": 3.1837,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.17,
|
397 |
+
"learning_rate": 4.986500906824941e-05,
|
398 |
+
"loss": 3.23,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.9860788179914456e-05,
|
404 |
+
"loss": 3.4343,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.985650249846258e-05,
|
410 |
+
"loss": 3.3317,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.9852152035063294e-05,
|
416 |
+
"loss": 3.155,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.18,
|
421 |
+
"learning_rate": 4.984773680105493e-05,
|
422 |
+
"loss": 3.3527,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984415798673684e-05,
|
428 |
+
"loss": 3.3783,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9839626194743575e-05,
|
434 |
+
"loss": 3.2567,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.983502966478656e-05,
|
440 |
+
"loss": 3.1278,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.19,
|
445 |
+
"learning_rate": 4.9830368408845425e-05,
|
446 |
+
"loss": 3.2344,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.982564243906852e-05,
|
452 |
+
"loss": 3.3458,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9820851767772844e-05,
|
458 |
+
"loss": 3.1467,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.2,
|
463 |
+
"learning_rate": 4.981599640744402e-05,
|
464 |
+
"loss": 3.217,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.2,
|
469 |
+
"learning_rate": 4.981107637073628e-05,
|
470 |
+
"loss": 3.4011,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.98060916704724e-05,
|
476 |
+
"loss": 3.4098,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.9801042319643686e-05,
|
482 |
+
"loss": 3.3332,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.21,
|
487 |
+
"learning_rate": 4.979592833140996e-05,
|
488 |
+
"loss": 3.4042,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.21,
|
493 |
+
"learning_rate": 4.979074971909948e-05,
|
494 |
+
"loss": 3.3127,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.978550649620894e-05,
|
500 |
+
"loss": 3.1726,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.978019867640342e-05,
|
506 |
+
"loss": 3.3029,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.22,
|
511 |
+
"learning_rate": 4.977482627351637e-05,
|
512 |
+
"loss": 3.3519,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.22,
|
517 |
+
"learning_rate": 4.976938930154954e-05,
|
518 |
+
"loss": 3.2507,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.976388777467297e-05,
|
524 |
+
"loss": 3.1322,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.9758321707224954e-05,
|
530 |
+
"loss": 3.1306,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.23,
|
535 |
+
"learning_rate": 4.975269111371197e-05,
|
536 |
+
"loss": 3.189,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.23,
|
541 |
+
"learning_rate": 4.974699600880869e-05,
|
542 |
+
"loss": 3.2598,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.974123640735791e-05,
|
548 |
+
"loss": 3.3483,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.973541232437052e-05,
|
554 |
+
"loss": 3.4678,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.24,
|
559 |
+
"learning_rate": 4.972952377502545e-05,
|
560 |
+
"loss": 2.9668,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.24,
|
565 |
+
"learning_rate": 4.9723570774669687e-05,
|
566 |
+
"loss": 3.372,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.971755333881814e-05,
|
572 |
+
"loss": 3.2808,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.971147148315367e-05,
|
578 |
+
"loss": 3.2235,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.25,
|
583 |
+
"learning_rate": 4.9705325223527057e-05,
|
584 |
+
"loss": 3.0441,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.25,
|
589 |
+
"learning_rate": 4.96991145759569e-05,
|
590 |
+
"loss": 3.4724,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.969283955662963e-05,
|
596 |
+
"loss": 3.389,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.968650018189943e-05,
|
602 |
+
"loss": 3.3817,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.26,
|
607 |
+
"learning_rate": 4.968009646828822e-05,
|
608 |
+
"loss": 3.2597,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.26,
|
613 |
+
"learning_rate": 4.967362843248559e-05,
|
614 |
+
"loss": 3.253,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.966709609134878e-05,
|
620 |
+
"loss": 3.1903,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.9660499461902645e-05,
|
626 |
+
"loss": 3.1286,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.27,
|
631 |
+
"learning_rate": 4.965383856133953e-05,
|
632 |
+
"loss": 3.292,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.27,
|
637 |
+
"learning_rate": 4.964711340701935e-05,
|
638 |
+
"loss": 3.4217,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.964032401646944e-05,
|
644 |
+
"loss": 3.2587,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.963347040738457e-05,
|
650 |
+
"loss": 3.3325,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.28,
|
655 |
+
"learning_rate": 4.962655259762687e-05,
|
656 |
+
"loss": 3.3475,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.28,
|
661 |
+
"learning_rate": 4.961957060522581e-05,
|
662 |
+
"loss": 3.2882,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.961252444837809e-05,
|
668 |
+
"loss": 3.3631,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.29,
|
673 |
+
"learning_rate": 4.9605414145447696e-05,
|
674 |
+
"loss": 3.2589,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.29,
|
679 |
+
"learning_rate": 4.959823971496574e-05,
|
680 |
+
"loss": 3.4855,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.29,
|
685 |
+
"learning_rate": 4.959100117563052e-05,
|
686 |
+
"loss": 3.1354,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.958369854630737e-05,
|
692 |
+
"loss": 3.3037,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.3,
|
697 |
+
"learning_rate": 4.957633184602867e-05,
|
698 |
+
"loss": 3.1023,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.3,
|
703 |
+
"learning_rate": 4.956890109399381e-05,
|
704 |
+
"loss": 3.1933,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.3,
|
709 |
+
"learning_rate": 4.956140630956908e-05,
|
710 |
+
"loss": 3.3994,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.955384751228767e-05,
|
716 |
+
"loss": 3.1178,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.31,
|
721 |
+
"learning_rate": 4.954622472184961e-05,
|
722 |
+
"loss": 3.2513,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.31,
|
727 |
+
"learning_rate": 4.9538537958121686e-05,
|
728 |
+
"loss": 3.5002,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.31,
|
733 |
+
"learning_rate": 4.953078724113744e-05,
|
734 |
+
"loss": 3.1867,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.9522972591097074e-05,
|
740 |
+
"loss": 3.3883,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.32,
|
745 |
+
"learning_rate": 4.9515094028367425e-05,
|
746 |
+
"loss": 3.3708,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.32,
|
751 |
+
"learning_rate": 4.950715157348191e-05,
|
752 |
+
"loss": 3.2425,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.32,
|
757 |
+
"learning_rate": 4.9499145247140434e-05,
|
758 |
+
"loss": 3.1046,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.9491075070209385e-05,
|
764 |
+
"loss": 3.3236,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.33,
|
769 |
+
"learning_rate": 4.9482941063721576e-05,
|
770 |
+
"loss": 3.4957,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.33,
|
775 |
+
"learning_rate": 4.947474324887614e-05,
|
776 |
+
"loss": 3.2225,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.33,
|
781 |
+
"learning_rate": 4.9466481647038554e-05,
|
782 |
+
"loss": 3.5314,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.9458156279740484e-05,
|
788 |
+
"loss": 3.1028,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.34,
|
793 |
+
"learning_rate": 4.944976716867984e-05,
|
794 |
+
"loss": 3.2322,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.34,
|
799 |
+
"learning_rate": 4.9441314335720616e-05,
|
800 |
+
"loss": 3.1332,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.34,
|
805 |
+
"learning_rate": 4.943279780289292e-05,
|
806 |
+
"loss": 3.2028,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.9424217592392854e-05,
|
812 |
+
"loss": 3.2408,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.35,
|
817 |
+
"learning_rate": 4.9415573726582465e-05,
|
818 |
+
"loss": 3.0121,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.35,
|
823 |
+
"learning_rate": 4.940686622798974e-05,
|
824 |
+
"loss": 3.2182,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.35,
|
829 |
+
"learning_rate": 4.93980951193085e-05,
|
830 |
+
"loss": 3.4794,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.93892604233983e-05,
|
836 |
+
"loss": 3.3226,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.36,
|
841 |
+
"learning_rate": 4.938036216328448e-05,
|
842 |
+
"loss": 3.1917,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.36,
|
847 |
+
"learning_rate": 4.9371400362158016e-05,
|
848 |
+
"loss": 3.2176,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.36,
|
853 |
+
"learning_rate": 4.936237504337549e-05,
|
854 |
+
"loss": 2.933,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.935328623045902e-05,
|
860 |
+
"loss": 3.134,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.37,
|
865 |
+
"learning_rate": 4.934413394709621e-05,
|
866 |
+
"loss": 2.983,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.37,
|
871 |
+
"learning_rate": 4.933491821714009e-05,
|
872 |
+
"loss": 3.4337,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.37,
|
877 |
+
"learning_rate": 4.9325639064609045e-05,
|
878 |
+
"loss": 3.4699,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.38,
|
883 |
+
"learning_rate": 4.931629651368673e-05,
|
884 |
+
"loss": 3.4081,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.38,
|
889 |
+
"learning_rate": 4.930689058872208e-05,
|
890 |
+
"loss": 3.2174,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.38,
|
895 |
+
"learning_rate": 4.929742131422913e-05,
|
896 |
+
"loss": 3.4953,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.38,
|
901 |
+
"learning_rate": 4.92878887148871e-05,
|
902 |
+
"loss": 3.217,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.39,
|
907 |
+
"learning_rate": 4.927829281554017e-05,
|
908 |
+
"loss": 3.2689,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.39,
|
913 |
+
"learning_rate": 4.926863364119756e-05,
|
914 |
+
"loss": 3.2994,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.39,
|
919 |
+
"learning_rate": 4.9258911217033355e-05,
|
920 |
+
"loss": 3.3868,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.39,
|
925 |
+
"learning_rate": 4.924912556838651e-05,
|
926 |
+
"loss": 3.3169,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.4,
|
931 |
+
"learning_rate": 4.923927672076075e-05,
|
932 |
+
"loss": 3.0466,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.4,
|
937 |
+
"learning_rate": 4.92293646998245e-05,
|
938 |
+
"loss": 3.0857,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.4,
|
943 |
+
"learning_rate": 4.921938953141084e-05,
|
944 |
+
"loss": 3.5001,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.4,
|
949 |
+
"learning_rate": 4.920935124151744e-05,
|
950 |
+
"loss": 3.1633,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.41,
|
955 |
+
"learning_rate": 4.919924985630647e-05,
|
956 |
+
"loss": 3.4816,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.41,
|
961 |
+
"learning_rate": 4.9189085402104516e-05,
|
962 |
+
"loss": 3.2032,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.41,
|
967 |
+
"learning_rate": 4.917885790540258e-05,
|
968 |
+
"loss": 3.164,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.41,
|
973 |
+
"learning_rate": 4.916856739285593e-05,
|
974 |
+
"loss": 3.3047,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.42,
|
979 |
+
"learning_rate": 4.91582138912841e-05,
|
980 |
+
"loss": 3.2366,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.42,
|
985 |
+
"learning_rate": 4.9147797427670766e-05,
|
986 |
+
"loss": 3.3105,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.42,
|
991 |
+
"learning_rate": 4.91373180291637e-05,
|
992 |
+
"loss": 3.4871,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.42,
|
997 |
+
"learning_rate": 4.912677572307473e-05,
|
998 |
+
"loss": 3.0442,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.43,
|
1003 |
+
"learning_rate": 4.911617053687957e-05,
|
1004 |
+
"loss": 3.1934,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.43,
|
1009 |
+
"learning_rate": 4.910550249821787e-05,
|
1010 |
+
"loss": 3.27,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.43,
|
1015 |
+
"learning_rate": 4.9094771634893075e-05,
|
1016 |
+
"loss": 3.3252,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.43,
|
1021 |
+
"learning_rate": 4.908397797487237e-05,
|
1022 |
+
"loss": 2.9852,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.44,
|
1027 |
+
"learning_rate": 4.907312154628658e-05,
|
1028 |
+
"loss": 3.1331,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.44,
|
1033 |
+
"learning_rate": 4.906220237743014e-05,
|
1034 |
+
"loss": 3.1444,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.44,
|
1039 |
+
"learning_rate": 4.905122049676101e-05,
|
1040 |
+
"loss": 3.3702,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.44,
|
1045 |
+
"learning_rate": 4.904017593290056e-05,
|
1046 |
+
"loss": 3.0531,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.45,
|
1051 |
+
"learning_rate": 4.902906871463355e-05,
|
1052 |
+
"loss": 3.2007,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.45,
|
1057 |
+
"learning_rate": 4.901789887090804e-05,
|
1058 |
+
"loss": 3.0837,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.45,
|
1063 |
+
"learning_rate": 4.900666643083528e-05,
|
1064 |
+
"loss": 3.2268,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.45,
|
1069 |
+
"learning_rate": 4.8995371423689684e-05,
|
1070 |
+
"loss": 2.9249,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.46,
|
1075 |
+
"learning_rate": 4.898401387890873e-05,
|
1076 |
+
"loss": 3.2058,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.46,
|
1081 |
+
"learning_rate": 4.897259382609285e-05,
|
1082 |
+
"loss": 3.0971,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.46,
|
1087 |
+
"learning_rate": 4.8961111295005446e-05,
|
1088 |
+
"loss": 3.2227,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.47,
|
1093 |
+
"learning_rate": 4.894956631557269e-05,
|
1094 |
+
"loss": 3.2907,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.47,
|
1099 |
+
"learning_rate": 4.893795891788357e-05,
|
1100 |
+
"loss": 3.1382,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.47,
|
1105 |
+
"learning_rate": 4.892628913218969e-05,
|
1106 |
+
"loss": 2.8996,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.47,
|
1111 |
+
"learning_rate": 4.8914556988905315e-05,
|
1112 |
+
"loss": 2.9693,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.48,
|
1117 |
+
"learning_rate": 4.890276251860717e-05,
|
1118 |
+
"loss": 3.0134,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.48,
|
1123 |
+
"learning_rate": 4.889090575203445e-05,
|
1124 |
+
"loss": 2.9696,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.48,
|
1129 |
+
"learning_rate": 4.887898672008871e-05,
|
1130 |
+
"loss": 3.3306,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.48,
|
1135 |
+
"learning_rate": 4.8867005453833774e-05,
|
1136 |
+
"loss": 3.2199,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.49,
|
1141 |
+
"learning_rate": 4.885496198449567e-05,
|
1142 |
+
"loss": 3.2795,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.49,
|
1147 |
+
"learning_rate": 4.8842856343462535e-05,
|
1148 |
+
"loss": 3.3482,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.49,
|
1153 |
+
"learning_rate": 4.883068856228454e-05,
|
1154 |
+
"loss": 3.322,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.49,
|
1159 |
+
"learning_rate": 4.881845867267382e-05,
|
1160 |
+
"loss": 3.0443,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.5,
|
1165 |
+
"learning_rate": 4.8806166706504375e-05,
|
1166 |
+
"loss": 3.1826,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.5,
|
1171 |
+
"learning_rate": 4.879381269581197e-05,
|
1172 |
+
"loss": 3.3732,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.5,
|
1177 |
+
"learning_rate": 4.878139667279411e-05,
|
1178 |
+
"loss": 3.3457,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.5,
|
1183 |
+
"learning_rate": 4.876891866980988e-05,
|
1184 |
+
"loss": 3.182,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.51,
|
1189 |
+
"learning_rate": 4.875637871937994e-05,
|
1190 |
+
"loss": 3.2416,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.51,
|
1195 |
+
"learning_rate": 4.874377685418635e-05,
|
1196 |
+
"loss": 3.2411,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.51,
|
1201 |
+
"learning_rate": 4.873111310707259e-05,
|
1202 |
+
"loss": 3.2836,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.51,
|
1207 |
+
"learning_rate": 4.8718387511043385e-05,
|
1208 |
+
"loss": 3.1773,
|
1209 |
+
"step": 1000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.52,
|
1213 |
+
"learning_rate": 4.870560009926465e-05,
|
1214 |
+
"loss": 3.1723,
|
1215 |
+
"step": 1005
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.52,
|
1219 |
+
"learning_rate": 4.8692750905063424e-05,
|
1220 |
+
"loss": 3.1535,
|
1221 |
+
"step": 1010
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.52,
|
1225 |
+
"learning_rate": 4.867983996192776e-05,
|
1226 |
+
"loss": 2.977,
|
1227 |
+
"step": 1015
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.52,
|
1231 |
+
"learning_rate": 4.866686730350663e-05,
|
1232 |
+
"loss": 3.1236,
|
1233 |
+
"step": 1020
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.53,
|
1237 |
+
"learning_rate": 4.865383296360987e-05,
|
1238 |
+
"loss": 3.4016,
|
1239 |
+
"step": 1025
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.53,
|
1243 |
+
"learning_rate": 4.864073697620807e-05,
|
1244 |
+
"loss": 3.1547,
|
1245 |
+
"step": 1030
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.53,
|
1249 |
+
"learning_rate": 4.862757937543248e-05,
|
1250 |
+
"loss": 3.143,
|
1251 |
+
"step": 1035
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.53,
|
1255 |
+
"learning_rate": 4.861436019557492e-05,
|
1256 |
+
"loss": 3.1989,
|
1257 |
+
"step": 1040
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.54,
|
1261 |
+
"learning_rate": 4.860107947108772e-05,
|
1262 |
+
"loss": 3.0308,
|
1263 |
+
"step": 1045
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.54,
|
1267 |
+
"learning_rate": 4.858773723658361e-05,
|
1268 |
+
"loss": 3.409,
|
1269 |
+
"step": 1050
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.54,
|
1273 |
+
"learning_rate": 4.8574333526835605e-05,
|
1274 |
+
"loss": 3.2011,
|
1275 |
+
"step": 1055
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.54,
|
1279 |
+
"learning_rate": 4.856086837677697e-05,
|
1280 |
+
"loss": 3.1954,
|
1281 |
+
"step": 1060
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.55,
|
1285 |
+
"learning_rate": 4.854734182150107e-05,
|
1286 |
+
"loss": 3.1366,
|
1287 |
+
"step": 1065
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.55,
|
1291 |
+
"learning_rate": 4.853375389626133e-05,
|
1292 |
+
"loss": 3.3789,
|
1293 |
+
"step": 1070
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.55,
|
1297 |
+
"learning_rate": 4.85201046364711e-05,
|
1298 |
+
"loss": 3.1337,
|
1299 |
+
"step": 1075
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.55,
|
1303 |
+
"learning_rate": 4.85063940777036e-05,
|
1304 |
+
"loss": 3.2278,
|
1305 |
+
"step": 1080
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.56,
|
1309 |
+
"learning_rate": 4.849262225569181e-05,
|
1310 |
+
"loss": 3.1339,
|
1311 |
+
"step": 1085
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.56,
|
1315 |
+
"learning_rate": 4.847878920632834e-05,
|
1316 |
+
"loss": 2.954,
|
1317 |
+
"step": 1090
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.56,
|
1321 |
+
"learning_rate": 4.846489496566542e-05,
|
1322 |
+
"loss": 3.0878,
|
1323 |
+
"step": 1095
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.57,
|
1327 |
+
"learning_rate": 4.845093956991475e-05,
|
1328 |
+
"loss": 3.2329,
|
1329 |
+
"step": 1100
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.57,
|
1333 |
+
"learning_rate": 4.843692305544738e-05,
|
1334 |
+
"loss": 3.2245,
|
1335 |
+
"step": 1105
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.57,
|
1339 |
+
"learning_rate": 4.84228454587937e-05,
|
1340 |
+
"loss": 3.2865,
|
1341 |
+
"step": 1110
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.57,
|
1345 |
+
"learning_rate": 4.8408706816643254e-05,
|
1346 |
+
"loss": 3.1569,
|
1347 |
+
"step": 1115
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.58,
|
1351 |
+
"learning_rate": 4.83945071658447e-05,
|
1352 |
+
"loss": 3.2279,
|
1353 |
+
"step": 1120
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.58,
|
1357 |
+
"learning_rate": 4.838024654340571e-05,
|
1358 |
+
"loss": 3.0554,
|
1359 |
+
"step": 1125
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.58,
|
1363 |
+
"learning_rate": 4.836592498649283e-05,
|
1364 |
+
"loss": 3.3924,
|
1365 |
+
"step": 1130
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.58,
|
1369 |
+
"learning_rate": 4.835154253243147e-05,
|
1370 |
+
"loss": 3.0695,
|
1371 |
+
"step": 1135
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.59,
|
1375 |
+
"learning_rate": 4.8337099218705695e-05,
|
1376 |
+
"loss": 3.2666,
|
1377 |
+
"step": 1140
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.59,
|
1381 |
+
"learning_rate": 4.832259508295822e-05,
|
1382 |
+
"loss": 3.135,
|
1383 |
+
"step": 1145
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.59,
|
1387 |
+
"learning_rate": 4.830803016299027e-05,
|
1388 |
+
"loss": 2.947,
|
1389 |
+
"step": 1150
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.59,
|
1393 |
+
"learning_rate": 4.829340449676147e-05,
|
1394 |
+
"loss": 3.13,
|
1395 |
+
"step": 1155
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.6,
|
1399 |
+
"learning_rate": 4.82787181223898e-05,
|
1400 |
+
"loss": 3.038,
|
1401 |
+
"step": 1160
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.6,
|
1405 |
+
"learning_rate": 4.826397107815142e-05,
|
1406 |
+
"loss": 3.0761,
|
1407 |
+
"step": 1165
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.6,
|
1411 |
+
"learning_rate": 4.824916340248064e-05,
|
1412 |
+
"loss": 3.1496,
|
1413 |
+
"step": 1170
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.6,
|
1417 |
+
"learning_rate": 4.823429513396977e-05,
|
1418 |
+
"loss": 2.8758,
|
1419 |
+
"step": 1175
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.61,
|
1423 |
+
"learning_rate": 4.821936631136906e-05,
|
1424 |
+
"loss": 3.218,
|
1425 |
+
"step": 1180
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.61,
|
1429 |
+
"learning_rate": 4.820437697358656e-05,
|
1430 |
+
"loss": 3.0933,
|
1431 |
+
"step": 1185
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.61,
|
1435 |
+
"learning_rate": 4.8189327159688035e-05,
|
1436 |
+
"loss": 3.2388,
|
1437 |
+
"step": 1190
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.61,
|
1441 |
+
"learning_rate": 4.817421690889689e-05,
|
1442 |
+
"loss": 3.1914,
|
1443 |
+
"step": 1195
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.62,
|
1447 |
+
"learning_rate": 4.815904626059401e-05,
|
1448 |
+
"loss": 3.2259,
|
1449 |
+
"step": 1200
|
1450 |
+
}
|
1451 |
+
],
|
1452 |
+
"logging_steps": 5,
|
1453 |
+
"max_steps": 9730,
|
1454 |
+
"num_input_tokens_seen": 0,
|
1455 |
+
"num_train_epochs": 5,
|
1456 |
+
"save_steps": 300,
|
1457 |
+
"total_flos": 1.419579902963712e+17,
|
1458 |
+
"train_batch_size": 1,
|
1459 |
+
"trial_name": null,
|
1460 |
+
"trial_params": null
|
1461 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:323d9e0822218e186c546ec4c60df0ed1248fa085eb7c28291141ebefc901909
|
3 |
+
size 4411
|
checkpoint-3000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chinese-llama-2-13b
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-3000/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chinese-llama-2-13b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-3000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54695fdb2eb148001181ba950f41d40228bda58b30d6b9cdaa9b0416e08e0f1d
|
3 |
+
size 26235704
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cbd4b7a15c213755deb82a96a12932c25e9ff73b83d98fe1ee6e8fa4b8028b
|
3 |
+
size 52562821
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1db093ff520055a5e21b61ab7d1dbd317224771971f3d89b400bb544bef1e03f
|
3 |
+
size 14575
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4654ca098ba32292893a57e3fa92e563f230c7ac88f513c22ff689aaca0c3a70
|
3 |
+
size 627
|
checkpoint-3000/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-3000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c
|
3 |
+
size 844403
|
checkpoint-3000/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": true,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"padding_side": "right",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"split_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false,
|
51 |
+
"use_fast": false
|
52 |
+
}
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,3621 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.541623843782117,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.9999979150098865e-05,
|
14 |
+
"loss": 4.0418,
|
15 |
+
"step": 5
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 4.999989444743508e-05,
|
20 |
+
"loss": 3.8361,
|
21 |
+
"step": 10
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.01,
|
25 |
+
"learning_rate": 4.999974458911041e-05,
|
26 |
+
"loss": 3.8737,
|
27 |
+
"step": 15
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.01,
|
31 |
+
"learning_rate": 4.9999529575515425e-05,
|
32 |
+
"loss": 3.806,
|
33 |
+
"step": 20
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.01,
|
37 |
+
"learning_rate": 4.9999249407210515e-05,
|
38 |
+
"loss": 3.4125,
|
39 |
+
"step": 25
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.02,
|
43 |
+
"learning_rate": 4.9998904084925845e-05,
|
44 |
+
"loss": 3.6489,
|
45 |
+
"step": 30
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.02,
|
49 |
+
"learning_rate": 4.999849360956141e-05,
|
50 |
+
"loss": 3.4719,
|
51 |
+
"step": 35
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"learning_rate": 4.999811831976564e-05,
|
56 |
+
"loss": 3.5265,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"learning_rate": 4.999759057166764e-05,
|
62 |
+
"loss": 3.6889,
|
63 |
+
"step": 45
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.03,
|
67 |
+
"learning_rate": 4.9996997673913204e-05,
|
68 |
+
"loss": 3.5104,
|
69 |
+
"step": 50
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.03,
|
73 |
+
"learning_rate": 4.999633962804756e-05,
|
74 |
+
"loss": 3.5778,
|
75 |
+
"step": 55
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 4.999561643578575e-05,
|
80 |
+
"loss": 3.3353,
|
81 |
+
"step": 60
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.03,
|
85 |
+
"learning_rate": 4.999482809901257e-05,
|
86 |
+
"loss": 3.3511,
|
87 |
+
"step": 65
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.04,
|
91 |
+
"learning_rate": 4.9993974619782625e-05,
|
92 |
+
"loss": 3.6355,
|
93 |
+
"step": 70
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.04,
|
97 |
+
"learning_rate": 4.999305600032027e-05,
|
98 |
+
"loss": 3.3915,
|
99 |
+
"step": 75
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.04,
|
103 |
+
"learning_rate": 4.999207224301965e-05,
|
104 |
+
"loss": 3.4926,
|
105 |
+
"step": 80
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.04,
|
109 |
+
"learning_rate": 4.999102335044467e-05,
|
110 |
+
"loss": 3.4918,
|
111 |
+
"step": 85
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.05,
|
115 |
+
"learning_rate": 4.9989909325328996e-05,
|
116 |
+
"loss": 3.3984,
|
117 |
+
"step": 90
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.05,
|
121 |
+
"learning_rate": 4.998873017057605e-05,
|
122 |
+
"loss": 3.4989,
|
123 |
+
"step": 95
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.05,
|
127 |
+
"learning_rate": 4.998748588925897e-05,
|
128 |
+
"loss": 3.6368,
|
129 |
+
"step": 100
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.05,
|
133 |
+
"learning_rate": 4.9986176484620665e-05,
|
134 |
+
"loss": 3.4412,
|
135 |
+
"step": 105
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 4.998480196007375e-05,
|
140 |
+
"loss": 3.4708,
|
141 |
+
"step": 110
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.06,
|
145 |
+
"learning_rate": 4.9983362319200554e-05,
|
146 |
+
"loss": 3.37,
|
147 |
+
"step": 115
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.06,
|
151 |
+
"learning_rate": 4.998185756575313e-05,
|
152 |
+
"loss": 3.4524,
|
153 |
+
"step": 120
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.06,
|
157 |
+
"learning_rate": 4.9980287703653225e-05,
|
158 |
+
"loss": 3.3863,
|
159 |
+
"step": 125
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.07,
|
163 |
+
"learning_rate": 4.997865273699227e-05,
|
164 |
+
"loss": 3.4414,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.07,
|
169 |
+
"learning_rate": 4.997729789123732e-05,
|
170 |
+
"loss": 3.3335,
|
171 |
+
"step": 135
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.07,
|
175 |
+
"learning_rate": 4.997554574721849e-05,
|
176 |
+
"loss": 3.231,
|
177 |
+
"step": 140
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07,
|
181 |
+
"learning_rate": 4.997372851099727e-05,
|
182 |
+
"loss": 3.5962,
|
183 |
+
"step": 145
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.08,
|
187 |
+
"learning_rate": 4.997184618730983e-05,
|
188 |
+
"loss": 3.2795,
|
189 |
+
"step": 150
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.08,
|
193 |
+
"learning_rate": 4.996989878106192e-05,
|
194 |
+
"loss": 3.5384,
|
195 |
+
"step": 155
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.08,
|
199 |
+
"learning_rate": 4.996788629732897e-05,
|
200 |
+
"loss": 3.3274,
|
201 |
+
"step": 160
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.08,
|
205 |
+
"learning_rate": 4.996580874135597e-05,
|
206 |
+
"loss": 3.2292,
|
207 |
+
"step": 165
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.09,
|
211 |
+
"learning_rate": 4.996366611855753e-05,
|
212 |
+
"loss": 3.4829,
|
213 |
+
"step": 170
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.09,
|
217 |
+
"learning_rate": 4.996145843451785e-05,
|
218 |
+
"loss": 3.1998,
|
219 |
+
"step": 175
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09,
|
223 |
+
"learning_rate": 4.9959185694990655e-05,
|
224 |
+
"loss": 3.3757,
|
225 |
+
"step": 180
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.1,
|
229 |
+
"learning_rate": 4.995684790589926e-05,
|
230 |
+
"loss": 3.1001,
|
231 |
+
"step": 185
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.1,
|
235 |
+
"learning_rate": 4.99544450733365e-05,
|
236 |
+
"loss": 3.2301,
|
237 |
+
"step": 190
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.1,
|
241 |
+
"learning_rate": 4.995197720356471e-05,
|
242 |
+
"loss": 3.3187,
|
243 |
+
"step": 195
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.1,
|
247 |
+
"learning_rate": 4.994944430301576e-05,
|
248 |
+
"loss": 3.527,
|
249 |
+
"step": 200
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.11,
|
253 |
+
"learning_rate": 4.994684637829098e-05,
|
254 |
+
"loss": 3.3808,
|
255 |
+
"step": 205
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 4.994418343616119e-05,
|
260 |
+
"loss": 3.2406,
|
261 |
+
"step": 210
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11,
|
265 |
+
"learning_rate": 4.994145548356664e-05,
|
266 |
+
"loss": 3.3463,
|
267 |
+
"step": 215
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.11,
|
271 |
+
"learning_rate": 4.993866252761702e-05,
|
272 |
+
"loss": 3.2972,
|
273 |
+
"step": 220
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.12,
|
277 |
+
"learning_rate": 4.993580457559145e-05,
|
278 |
+
"loss": 3.4135,
|
279 |
+
"step": 225
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.12,
|
283 |
+
"learning_rate": 4.9932881634938424e-05,
|
284 |
+
"loss": 3.4025,
|
285 |
+
"step": 230
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.12,
|
289 |
+
"learning_rate": 4.992989371327581e-05,
|
290 |
+
"loss": 3.662,
|
291 |
+
"step": 235
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.12,
|
295 |
+
"learning_rate": 4.992684081839086e-05,
|
296 |
+
"loss": 3.4279,
|
297 |
+
"step": 240
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.13,
|
301 |
+
"learning_rate": 4.9923722958240124e-05,
|
302 |
+
"loss": 3.3075,
|
303 |
+
"step": 245
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.13,
|
307 |
+
"learning_rate": 4.992054014094951e-05,
|
308 |
+
"loss": 3.2826,
|
309 |
+
"step": 250
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.13,
|
313 |
+
"learning_rate": 4.991729237481417e-05,
|
314 |
+
"loss": 3.4992,
|
315 |
+
"step": 255
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.13,
|
319 |
+
"learning_rate": 4.991397966829856e-05,
|
320 |
+
"loss": 3.2421,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.14,
|
325 |
+
"learning_rate": 4.991060203003639e-05,
|
326 |
+
"loss": 3.2615,
|
327 |
+
"step": 265
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.14,
|
331 |
+
"learning_rate": 4.9907159468830585e-05,
|
332 |
+
"loss": 3.3299,
|
333 |
+
"step": 270
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.14,
|
337 |
+
"learning_rate": 4.990365199365327e-05,
|
338 |
+
"loss": 3.3117,
|
339 |
+
"step": 275
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.14,
|
343 |
+
"learning_rate": 4.9900079613645754e-05,
|
344 |
+
"loss": 3.4729,
|
345 |
+
"step": 280
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.15,
|
349 |
+
"learning_rate": 4.9896442338118524e-05,
|
350 |
+
"loss": 3.2521,
|
351 |
+
"step": 285
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.15,
|
355 |
+
"learning_rate": 4.989274017655117e-05,
|
356 |
+
"loss": 3.261,
|
357 |
+
"step": 290
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.15,
|
361 |
+
"learning_rate": 4.9888973138592414e-05,
|
362 |
+
"loss": 3.4403,
|
363 |
+
"step": 295
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.15,
|
367 |
+
"learning_rate": 4.988514123406004e-05,
|
368 |
+
"loss": 3.3408,
|
369 |
+
"step": 300
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.16,
|
373 |
+
"learning_rate": 4.9881244472940914e-05,
|
374 |
+
"loss": 3.3208,
|
375 |
+
"step": 305
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.16,
|
379 |
+
"learning_rate": 4.9877282865390904e-05,
|
380 |
+
"loss": 3.6889,
|
381 |
+
"step": 310
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.16,
|
385 |
+
"learning_rate": 4.9873256421734915e-05,
|
386 |
+
"loss": 3.1537,
|
387 |
+
"step": 315
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16,
|
391 |
+
"learning_rate": 4.986916515246681e-05,
|
392 |
+
"loss": 3.1837,
|
393 |
+
"step": 320
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.17,
|
397 |
+
"learning_rate": 4.986500906824941e-05,
|
398 |
+
"loss": 3.23,
|
399 |
+
"step": 325
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.17,
|
403 |
+
"learning_rate": 4.9860788179914456e-05,
|
404 |
+
"loss": 3.4343,
|
405 |
+
"step": 330
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.17,
|
409 |
+
"learning_rate": 4.985650249846258e-05,
|
410 |
+
"loss": 3.3317,
|
411 |
+
"step": 335
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.17,
|
415 |
+
"learning_rate": 4.9852152035063294e-05,
|
416 |
+
"loss": 3.155,
|
417 |
+
"step": 340
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.18,
|
421 |
+
"learning_rate": 4.984773680105493e-05,
|
422 |
+
"loss": 3.3527,
|
423 |
+
"step": 345
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.18,
|
427 |
+
"learning_rate": 4.984415798673684e-05,
|
428 |
+
"loss": 3.3783,
|
429 |
+
"step": 350
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18,
|
433 |
+
"learning_rate": 4.9839626194743575e-05,
|
434 |
+
"loss": 3.2567,
|
435 |
+
"step": 355
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.18,
|
439 |
+
"learning_rate": 4.983502966478656e-05,
|
440 |
+
"loss": 3.1278,
|
441 |
+
"step": 360
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.19,
|
445 |
+
"learning_rate": 4.9830368408845425e-05,
|
446 |
+
"loss": 3.2344,
|
447 |
+
"step": 365
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.19,
|
451 |
+
"learning_rate": 4.982564243906852e-05,
|
452 |
+
"loss": 3.3458,
|
453 |
+
"step": 370
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.19,
|
457 |
+
"learning_rate": 4.9820851767772844e-05,
|
458 |
+
"loss": 3.1467,
|
459 |
+
"step": 375
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.2,
|
463 |
+
"learning_rate": 4.981599640744402e-05,
|
464 |
+
"loss": 3.217,
|
465 |
+
"step": 380
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.2,
|
469 |
+
"learning_rate": 4.981107637073628e-05,
|
470 |
+
"loss": 3.4011,
|
471 |
+
"step": 385
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.2,
|
475 |
+
"learning_rate": 4.98060916704724e-05,
|
476 |
+
"loss": 3.4098,
|
477 |
+
"step": 390
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.2,
|
481 |
+
"learning_rate": 4.9801042319643686e-05,
|
482 |
+
"loss": 3.3332,
|
483 |
+
"step": 395
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.21,
|
487 |
+
"learning_rate": 4.979592833140996e-05,
|
488 |
+
"loss": 3.4042,
|
489 |
+
"step": 400
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.21,
|
493 |
+
"learning_rate": 4.979074971909948e-05,
|
494 |
+
"loss": 3.3127,
|
495 |
+
"step": 405
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.21,
|
499 |
+
"learning_rate": 4.978550649620894e-05,
|
500 |
+
"loss": 3.1726,
|
501 |
+
"step": 410
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.21,
|
505 |
+
"learning_rate": 4.978019867640342e-05,
|
506 |
+
"loss": 3.3029,
|
507 |
+
"step": 415
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.22,
|
511 |
+
"learning_rate": 4.977482627351637e-05,
|
512 |
+
"loss": 3.3519,
|
513 |
+
"step": 420
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.22,
|
517 |
+
"learning_rate": 4.976938930154954e-05,
|
518 |
+
"loss": 3.2507,
|
519 |
+
"step": 425
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.22,
|
523 |
+
"learning_rate": 4.976388777467297e-05,
|
524 |
+
"loss": 3.1322,
|
525 |
+
"step": 430
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.22,
|
529 |
+
"learning_rate": 4.9758321707224954e-05,
|
530 |
+
"loss": 3.1306,
|
531 |
+
"step": 435
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.23,
|
535 |
+
"learning_rate": 4.975269111371197e-05,
|
536 |
+
"loss": 3.189,
|
537 |
+
"step": 440
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.23,
|
541 |
+
"learning_rate": 4.974699600880869e-05,
|
542 |
+
"loss": 3.2598,
|
543 |
+
"step": 445
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.23,
|
547 |
+
"learning_rate": 4.974123640735791e-05,
|
548 |
+
"loss": 3.3483,
|
549 |
+
"step": 450
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.23,
|
553 |
+
"learning_rate": 4.973541232437052e-05,
|
554 |
+
"loss": 3.4678,
|
555 |
+
"step": 455
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.24,
|
559 |
+
"learning_rate": 4.972952377502545e-05,
|
560 |
+
"loss": 2.9668,
|
561 |
+
"step": 460
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.24,
|
565 |
+
"learning_rate": 4.9723570774669687e-05,
|
566 |
+
"loss": 3.372,
|
567 |
+
"step": 465
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.24,
|
571 |
+
"learning_rate": 4.971755333881814e-05,
|
572 |
+
"loss": 3.2808,
|
573 |
+
"step": 470
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.24,
|
577 |
+
"learning_rate": 4.971147148315367e-05,
|
578 |
+
"loss": 3.2235,
|
579 |
+
"step": 475
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.25,
|
583 |
+
"learning_rate": 4.9705325223527057e-05,
|
584 |
+
"loss": 3.0441,
|
585 |
+
"step": 480
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.25,
|
589 |
+
"learning_rate": 4.96991145759569e-05,
|
590 |
+
"loss": 3.4724,
|
591 |
+
"step": 485
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.25,
|
595 |
+
"learning_rate": 4.969283955662963e-05,
|
596 |
+
"loss": 3.389,
|
597 |
+
"step": 490
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.25,
|
601 |
+
"learning_rate": 4.968650018189943e-05,
|
602 |
+
"loss": 3.3817,
|
603 |
+
"step": 495
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.26,
|
607 |
+
"learning_rate": 4.968009646828822e-05,
|
608 |
+
"loss": 3.2597,
|
609 |
+
"step": 500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.26,
|
613 |
+
"learning_rate": 4.967362843248559e-05,
|
614 |
+
"loss": 3.253,
|
615 |
+
"step": 505
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.26,
|
619 |
+
"learning_rate": 4.966709609134878e-05,
|
620 |
+
"loss": 3.1903,
|
621 |
+
"step": 510
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.26,
|
625 |
+
"learning_rate": 4.9660499461902645e-05,
|
626 |
+
"loss": 3.1286,
|
627 |
+
"step": 515
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.27,
|
631 |
+
"learning_rate": 4.965383856133953e-05,
|
632 |
+
"loss": 3.292,
|
633 |
+
"step": 520
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.27,
|
637 |
+
"learning_rate": 4.964711340701935e-05,
|
638 |
+
"loss": 3.4217,
|
639 |
+
"step": 525
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.27,
|
643 |
+
"learning_rate": 4.964032401646944e-05,
|
644 |
+
"loss": 3.2587,
|
645 |
+
"step": 530
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.27,
|
649 |
+
"learning_rate": 4.963347040738457e-05,
|
650 |
+
"loss": 3.3325,
|
651 |
+
"step": 535
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.28,
|
655 |
+
"learning_rate": 4.962655259762687e-05,
|
656 |
+
"loss": 3.3475,
|
657 |
+
"step": 540
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.28,
|
661 |
+
"learning_rate": 4.961957060522581e-05,
|
662 |
+
"loss": 3.2882,
|
663 |
+
"step": 545
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.28,
|
667 |
+
"learning_rate": 4.961252444837809e-05,
|
668 |
+
"loss": 3.3631,
|
669 |
+
"step": 550
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.29,
|
673 |
+
"learning_rate": 4.9605414145447696e-05,
|
674 |
+
"loss": 3.2589,
|
675 |
+
"step": 555
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.29,
|
679 |
+
"learning_rate": 4.959823971496574e-05,
|
680 |
+
"loss": 3.4855,
|
681 |
+
"step": 560
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.29,
|
685 |
+
"learning_rate": 4.959100117563052e-05,
|
686 |
+
"loss": 3.1354,
|
687 |
+
"step": 565
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.29,
|
691 |
+
"learning_rate": 4.958369854630737e-05,
|
692 |
+
"loss": 3.3037,
|
693 |
+
"step": 570
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.3,
|
697 |
+
"learning_rate": 4.957633184602867e-05,
|
698 |
+
"loss": 3.1023,
|
699 |
+
"step": 575
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.3,
|
703 |
+
"learning_rate": 4.956890109399381e-05,
|
704 |
+
"loss": 3.1933,
|
705 |
+
"step": 580
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.3,
|
709 |
+
"learning_rate": 4.956140630956908e-05,
|
710 |
+
"loss": 3.3994,
|
711 |
+
"step": 585
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.3,
|
715 |
+
"learning_rate": 4.955384751228767e-05,
|
716 |
+
"loss": 3.1178,
|
717 |
+
"step": 590
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.31,
|
721 |
+
"learning_rate": 4.954622472184961e-05,
|
722 |
+
"loss": 3.2513,
|
723 |
+
"step": 595
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.31,
|
727 |
+
"learning_rate": 4.9538537958121686e-05,
|
728 |
+
"loss": 3.5002,
|
729 |
+
"step": 600
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.31,
|
733 |
+
"learning_rate": 4.953078724113744e-05,
|
734 |
+
"loss": 3.1867,
|
735 |
+
"step": 605
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.31,
|
739 |
+
"learning_rate": 4.9522972591097074e-05,
|
740 |
+
"loss": 3.3883,
|
741 |
+
"step": 610
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.32,
|
745 |
+
"learning_rate": 4.9515094028367425e-05,
|
746 |
+
"loss": 3.3708,
|
747 |
+
"step": 615
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.32,
|
751 |
+
"learning_rate": 4.950715157348191e-05,
|
752 |
+
"loss": 3.2425,
|
753 |
+
"step": 620
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.32,
|
757 |
+
"learning_rate": 4.9499145247140434e-05,
|
758 |
+
"loss": 3.1046,
|
759 |
+
"step": 625
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.32,
|
763 |
+
"learning_rate": 4.9491075070209385e-05,
|
764 |
+
"loss": 3.3236,
|
765 |
+
"step": 630
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.33,
|
769 |
+
"learning_rate": 4.9482941063721576e-05,
|
770 |
+
"loss": 3.4957,
|
771 |
+
"step": 635
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.33,
|
775 |
+
"learning_rate": 4.947474324887614e-05,
|
776 |
+
"loss": 3.2225,
|
777 |
+
"step": 640
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.33,
|
781 |
+
"learning_rate": 4.9466481647038554e-05,
|
782 |
+
"loss": 3.5314,
|
783 |
+
"step": 645
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.33,
|
787 |
+
"learning_rate": 4.9458156279740484e-05,
|
788 |
+
"loss": 3.1028,
|
789 |
+
"step": 650
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.34,
|
793 |
+
"learning_rate": 4.944976716867984e-05,
|
794 |
+
"loss": 3.2322,
|
795 |
+
"step": 655
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.34,
|
799 |
+
"learning_rate": 4.9441314335720616e-05,
|
800 |
+
"loss": 3.1332,
|
801 |
+
"step": 660
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.34,
|
805 |
+
"learning_rate": 4.943279780289292e-05,
|
806 |
+
"loss": 3.2028,
|
807 |
+
"step": 665
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.34,
|
811 |
+
"learning_rate": 4.9424217592392854e-05,
|
812 |
+
"loss": 3.2408,
|
813 |
+
"step": 670
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.35,
|
817 |
+
"learning_rate": 4.9415573726582465e-05,
|
818 |
+
"loss": 3.0121,
|
819 |
+
"step": 675
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.35,
|
823 |
+
"learning_rate": 4.940686622798974e-05,
|
824 |
+
"loss": 3.2182,
|
825 |
+
"step": 680
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.35,
|
829 |
+
"learning_rate": 4.93980951193085e-05,
|
830 |
+
"loss": 3.4794,
|
831 |
+
"step": 685
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.35,
|
835 |
+
"learning_rate": 4.93892604233983e-05,
|
836 |
+
"loss": 3.3226,
|
837 |
+
"step": 690
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.36,
|
841 |
+
"learning_rate": 4.938036216328448e-05,
|
842 |
+
"loss": 3.1917,
|
843 |
+
"step": 695
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.36,
|
847 |
+
"learning_rate": 4.9371400362158016e-05,
|
848 |
+
"loss": 3.2176,
|
849 |
+
"step": 700
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.36,
|
853 |
+
"learning_rate": 4.936237504337549e-05,
|
854 |
+
"loss": 2.933,
|
855 |
+
"step": 705
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.36,
|
859 |
+
"learning_rate": 4.935328623045902e-05,
|
860 |
+
"loss": 3.134,
|
861 |
+
"step": 710
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.37,
|
865 |
+
"learning_rate": 4.934413394709621e-05,
|
866 |
+
"loss": 2.983,
|
867 |
+
"step": 715
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.37,
|
871 |
+
"learning_rate": 4.933491821714009e-05,
|
872 |
+
"loss": 3.4337,
|
873 |
+
"step": 720
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.37,
|
877 |
+
"learning_rate": 4.9325639064609045e-05,
|
878 |
+
"loss": 3.4699,
|
879 |
+
"step": 725
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.38,
|
883 |
+
"learning_rate": 4.931629651368673e-05,
|
884 |
+
"loss": 3.4081,
|
885 |
+
"step": 730
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.38,
|
889 |
+
"learning_rate": 4.930689058872208e-05,
|
890 |
+
"loss": 3.2174,
|
891 |
+
"step": 735
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.38,
|
895 |
+
"learning_rate": 4.929742131422913e-05,
|
896 |
+
"loss": 3.4953,
|
897 |
+
"step": 740
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.38,
|
901 |
+
"learning_rate": 4.92878887148871e-05,
|
902 |
+
"loss": 3.217,
|
903 |
+
"step": 745
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.39,
|
907 |
+
"learning_rate": 4.927829281554017e-05,
|
908 |
+
"loss": 3.2689,
|
909 |
+
"step": 750
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.39,
|
913 |
+
"learning_rate": 4.926863364119756e-05,
|
914 |
+
"loss": 3.2994,
|
915 |
+
"step": 755
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.39,
|
919 |
+
"learning_rate": 4.9258911217033355e-05,
|
920 |
+
"loss": 3.3868,
|
921 |
+
"step": 760
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.39,
|
925 |
+
"learning_rate": 4.924912556838651e-05,
|
926 |
+
"loss": 3.3169,
|
927 |
+
"step": 765
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.4,
|
931 |
+
"learning_rate": 4.923927672076075e-05,
|
932 |
+
"loss": 3.0466,
|
933 |
+
"step": 770
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.4,
|
937 |
+
"learning_rate": 4.92293646998245e-05,
|
938 |
+
"loss": 3.0857,
|
939 |
+
"step": 775
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.4,
|
943 |
+
"learning_rate": 4.921938953141084e-05,
|
944 |
+
"loss": 3.5001,
|
945 |
+
"step": 780
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.4,
|
949 |
+
"learning_rate": 4.920935124151744e-05,
|
950 |
+
"loss": 3.1633,
|
951 |
+
"step": 785
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.41,
|
955 |
+
"learning_rate": 4.919924985630647e-05,
|
956 |
+
"loss": 3.4816,
|
957 |
+
"step": 790
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.41,
|
961 |
+
"learning_rate": 4.9189085402104516e-05,
|
962 |
+
"loss": 3.2032,
|
963 |
+
"step": 795
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.41,
|
967 |
+
"learning_rate": 4.917885790540258e-05,
|
968 |
+
"loss": 3.164,
|
969 |
+
"step": 800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.41,
|
973 |
+
"learning_rate": 4.916856739285593e-05,
|
974 |
+
"loss": 3.3047,
|
975 |
+
"step": 805
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.42,
|
979 |
+
"learning_rate": 4.91582138912841e-05,
|
980 |
+
"loss": 3.2366,
|
981 |
+
"step": 810
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.42,
|
985 |
+
"learning_rate": 4.9147797427670766e-05,
|
986 |
+
"loss": 3.3105,
|
987 |
+
"step": 815
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.42,
|
991 |
+
"learning_rate": 4.91373180291637e-05,
|
992 |
+
"loss": 3.4871,
|
993 |
+
"step": 820
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.42,
|
997 |
+
"learning_rate": 4.912677572307473e-05,
|
998 |
+
"loss": 3.0442,
|
999 |
+
"step": 825
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.43,
|
1003 |
+
"learning_rate": 4.911617053687957e-05,
|
1004 |
+
"loss": 3.1934,
|
1005 |
+
"step": 830
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.43,
|
1009 |
+
"learning_rate": 4.910550249821787e-05,
|
1010 |
+
"loss": 3.27,
|
1011 |
+
"step": 835
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.43,
|
1015 |
+
"learning_rate": 4.9094771634893075e-05,
|
1016 |
+
"loss": 3.3252,
|
1017 |
+
"step": 840
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.43,
|
1021 |
+
"learning_rate": 4.908397797487237e-05,
|
1022 |
+
"loss": 2.9852,
|
1023 |
+
"step": 845
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.44,
|
1027 |
+
"learning_rate": 4.907312154628658e-05,
|
1028 |
+
"loss": 3.1331,
|
1029 |
+
"step": 850
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.44,
|
1033 |
+
"learning_rate": 4.906220237743014e-05,
|
1034 |
+
"loss": 3.1444,
|
1035 |
+
"step": 855
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.44,
|
1039 |
+
"learning_rate": 4.905122049676101e-05,
|
1040 |
+
"loss": 3.3702,
|
1041 |
+
"step": 860
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.44,
|
1045 |
+
"learning_rate": 4.904017593290056e-05,
|
1046 |
+
"loss": 3.0531,
|
1047 |
+
"step": 865
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.45,
|
1051 |
+
"learning_rate": 4.902906871463355e-05,
|
1052 |
+
"loss": 3.2007,
|
1053 |
+
"step": 870
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.45,
|
1057 |
+
"learning_rate": 4.901789887090804e-05,
|
1058 |
+
"loss": 3.0837,
|
1059 |
+
"step": 875
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.45,
|
1063 |
+
"learning_rate": 4.900666643083528e-05,
|
1064 |
+
"loss": 3.2268,
|
1065 |
+
"step": 880
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.45,
|
1069 |
+
"learning_rate": 4.8995371423689684e-05,
|
1070 |
+
"loss": 2.9249,
|
1071 |
+
"step": 885
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.46,
|
1075 |
+
"learning_rate": 4.898401387890873e-05,
|
1076 |
+
"loss": 3.2058,
|
1077 |
+
"step": 890
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.46,
|
1081 |
+
"learning_rate": 4.897259382609285e-05,
|
1082 |
+
"loss": 3.0971,
|
1083 |
+
"step": 895
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.46,
|
1087 |
+
"learning_rate": 4.8961111295005446e-05,
|
1088 |
+
"loss": 3.2227,
|
1089 |
+
"step": 900
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.47,
|
1093 |
+
"learning_rate": 4.894956631557269e-05,
|
1094 |
+
"loss": 3.2907,
|
1095 |
+
"step": 905
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.47,
|
1099 |
+
"learning_rate": 4.893795891788357e-05,
|
1100 |
+
"loss": 3.1382,
|
1101 |
+
"step": 910
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.47,
|
1105 |
+
"learning_rate": 4.892628913218969e-05,
|
1106 |
+
"loss": 2.8996,
|
1107 |
+
"step": 915
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.47,
|
1111 |
+
"learning_rate": 4.8914556988905315e-05,
|
1112 |
+
"loss": 2.9693,
|
1113 |
+
"step": 920
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.48,
|
1117 |
+
"learning_rate": 4.890276251860717e-05,
|
1118 |
+
"loss": 3.0134,
|
1119 |
+
"step": 925
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.48,
|
1123 |
+
"learning_rate": 4.889090575203445e-05,
|
1124 |
+
"loss": 2.9696,
|
1125 |
+
"step": 930
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.48,
|
1129 |
+
"learning_rate": 4.887898672008871e-05,
|
1130 |
+
"loss": 3.3306,
|
1131 |
+
"step": 935
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.48,
|
1135 |
+
"learning_rate": 4.8867005453833774e-05,
|
1136 |
+
"loss": 3.2199,
|
1137 |
+
"step": 940
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.49,
|
1141 |
+
"learning_rate": 4.885496198449567e-05,
|
1142 |
+
"loss": 3.2795,
|
1143 |
+
"step": 945
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.49,
|
1147 |
+
"learning_rate": 4.8842856343462535e-05,
|
1148 |
+
"loss": 3.3482,
|
1149 |
+
"step": 950
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.49,
|
1153 |
+
"learning_rate": 4.883068856228454e-05,
|
1154 |
+
"loss": 3.322,
|
1155 |
+
"step": 955
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.49,
|
1159 |
+
"learning_rate": 4.881845867267382e-05,
|
1160 |
+
"loss": 3.0443,
|
1161 |
+
"step": 960
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.5,
|
1165 |
+
"learning_rate": 4.8806166706504375e-05,
|
1166 |
+
"loss": 3.1826,
|
1167 |
+
"step": 965
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.5,
|
1171 |
+
"learning_rate": 4.879381269581197e-05,
|
1172 |
+
"loss": 3.3732,
|
1173 |
+
"step": 970
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.5,
|
1177 |
+
"learning_rate": 4.878139667279411e-05,
|
1178 |
+
"loss": 3.3457,
|
1179 |
+
"step": 975
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.5,
|
1183 |
+
"learning_rate": 4.876891866980988e-05,
|
1184 |
+
"loss": 3.182,
|
1185 |
+
"step": 980
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.51,
|
1189 |
+
"learning_rate": 4.875637871937994e-05,
|
1190 |
+
"loss": 3.2416,
|
1191 |
+
"step": 985
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.51,
|
1195 |
+
"learning_rate": 4.874377685418635e-05,
|
1196 |
+
"loss": 3.2411,
|
1197 |
+
"step": 990
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.51,
|
1201 |
+
"learning_rate": 4.873111310707259e-05,
|
1202 |
+
"loss": 3.2836,
|
1203 |
+
"step": 995
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.51,
|
1207 |
+
"learning_rate": 4.8718387511043385e-05,
|
1208 |
+
"loss": 3.1773,
|
1209 |
+
"step": 1000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.52,
|
1213 |
+
"learning_rate": 4.870560009926465e-05,
|
1214 |
+
"loss": 3.1723,
|
1215 |
+
"step": 1005
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.52,
|
1219 |
+
"learning_rate": 4.8692750905063424e-05,
|
1220 |
+
"loss": 3.1535,
|
1221 |
+
"step": 1010
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.52,
|
1225 |
+
"learning_rate": 4.867983996192776e-05,
|
1226 |
+
"loss": 2.977,
|
1227 |
+
"step": 1015
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.52,
|
1231 |
+
"learning_rate": 4.866686730350663e-05,
|
1232 |
+
"loss": 3.1236,
|
1233 |
+
"step": 1020
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.53,
|
1237 |
+
"learning_rate": 4.865383296360987e-05,
|
1238 |
+
"loss": 3.4016,
|
1239 |
+
"step": 1025
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.53,
|
1243 |
+
"learning_rate": 4.864073697620807e-05,
|
1244 |
+
"loss": 3.1547,
|
1245 |
+
"step": 1030
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.53,
|
1249 |
+
"learning_rate": 4.862757937543248e-05,
|
1250 |
+
"loss": 3.143,
|
1251 |
+
"step": 1035
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.53,
|
1255 |
+
"learning_rate": 4.861436019557492e-05,
|
1256 |
+
"loss": 3.1989,
|
1257 |
+
"step": 1040
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.54,
|
1261 |
+
"learning_rate": 4.860107947108772e-05,
|
1262 |
+
"loss": 3.0308,
|
1263 |
+
"step": 1045
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.54,
|
1267 |
+
"learning_rate": 4.858773723658361e-05,
|
1268 |
+
"loss": 3.409,
|
1269 |
+
"step": 1050
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.54,
|
1273 |
+
"learning_rate": 4.8574333526835605e-05,
|
1274 |
+
"loss": 3.2011,
|
1275 |
+
"step": 1055
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.54,
|
1279 |
+
"learning_rate": 4.856086837677697e-05,
|
1280 |
+
"loss": 3.1954,
|
1281 |
+
"step": 1060
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.55,
|
1285 |
+
"learning_rate": 4.854734182150107e-05,
|
1286 |
+
"loss": 3.1366,
|
1287 |
+
"step": 1065
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.55,
|
1291 |
+
"learning_rate": 4.853375389626133e-05,
|
1292 |
+
"loss": 3.3789,
|
1293 |
+
"step": 1070
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.55,
|
1297 |
+
"learning_rate": 4.85201046364711e-05,
|
1298 |
+
"loss": 3.1337,
|
1299 |
+
"step": 1075
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.55,
|
1303 |
+
"learning_rate": 4.85063940777036e-05,
|
1304 |
+
"loss": 3.2278,
|
1305 |
+
"step": 1080
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.56,
|
1309 |
+
"learning_rate": 4.849262225569181e-05,
|
1310 |
+
"loss": 3.1339,
|
1311 |
+
"step": 1085
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.56,
|
1315 |
+
"learning_rate": 4.847878920632834e-05,
|
1316 |
+
"loss": 2.954,
|
1317 |
+
"step": 1090
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.56,
|
1321 |
+
"learning_rate": 4.846489496566542e-05,
|
1322 |
+
"loss": 3.0878,
|
1323 |
+
"step": 1095
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.57,
|
1327 |
+
"learning_rate": 4.845093956991475e-05,
|
1328 |
+
"loss": 3.2329,
|
1329 |
+
"step": 1100
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.57,
|
1333 |
+
"learning_rate": 4.843692305544738e-05,
|
1334 |
+
"loss": 3.2245,
|
1335 |
+
"step": 1105
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.57,
|
1339 |
+
"learning_rate": 4.84228454587937e-05,
|
1340 |
+
"loss": 3.2865,
|
1341 |
+
"step": 1110
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.57,
|
1345 |
+
"learning_rate": 4.8408706816643254e-05,
|
1346 |
+
"loss": 3.1569,
|
1347 |
+
"step": 1115
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.58,
|
1351 |
+
"learning_rate": 4.83945071658447e-05,
|
1352 |
+
"loss": 3.2279,
|
1353 |
+
"step": 1120
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.58,
|
1357 |
+
"learning_rate": 4.838024654340571e-05,
|
1358 |
+
"loss": 3.0554,
|
1359 |
+
"step": 1125
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.58,
|
1363 |
+
"learning_rate": 4.836592498649283e-05,
|
1364 |
+
"loss": 3.3924,
|
1365 |
+
"step": 1130
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.58,
|
1369 |
+
"learning_rate": 4.835154253243147e-05,
|
1370 |
+
"loss": 3.0695,
|
1371 |
+
"step": 1135
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.59,
|
1375 |
+
"learning_rate": 4.8337099218705695e-05,
|
1376 |
+
"loss": 3.2666,
|
1377 |
+
"step": 1140
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.59,
|
1381 |
+
"learning_rate": 4.832259508295822e-05,
|
1382 |
+
"loss": 3.135,
|
1383 |
+
"step": 1145
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.59,
|
1387 |
+
"learning_rate": 4.830803016299027e-05,
|
1388 |
+
"loss": 2.947,
|
1389 |
+
"step": 1150
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.59,
|
1393 |
+
"learning_rate": 4.829340449676147e-05,
|
1394 |
+
"loss": 3.13,
|
1395 |
+
"step": 1155
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.6,
|
1399 |
+
"learning_rate": 4.82787181223898e-05,
|
1400 |
+
"loss": 3.038,
|
1401 |
+
"step": 1160
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.6,
|
1405 |
+
"learning_rate": 4.826397107815142e-05,
|
1406 |
+
"loss": 3.0761,
|
1407 |
+
"step": 1165
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.6,
|
1411 |
+
"learning_rate": 4.824916340248064e-05,
|
1412 |
+
"loss": 3.1496,
|
1413 |
+
"step": 1170
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.6,
|
1417 |
+
"learning_rate": 4.823429513396977e-05,
|
1418 |
+
"loss": 2.8758,
|
1419 |
+
"step": 1175
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.61,
|
1423 |
+
"learning_rate": 4.821936631136906e-05,
|
1424 |
+
"loss": 3.218,
|
1425 |
+
"step": 1180
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.61,
|
1429 |
+
"learning_rate": 4.820437697358656e-05,
|
1430 |
+
"loss": 3.0933,
|
1431 |
+
"step": 1185
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.61,
|
1435 |
+
"learning_rate": 4.8189327159688035e-05,
|
1436 |
+
"loss": 3.2388,
|
1437 |
+
"step": 1190
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.61,
|
1441 |
+
"learning_rate": 4.817421690889689e-05,
|
1442 |
+
"loss": 3.1914,
|
1443 |
+
"step": 1195
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.62,
|
1447 |
+
"learning_rate": 4.815904626059401e-05,
|
1448 |
+
"loss": 3.2259,
|
1449 |
+
"step": 1200
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.62,
|
1453 |
+
"learning_rate": 4.814381525431771e-05,
|
1454 |
+
"loss": 3.1867,
|
1455 |
+
"step": 1205
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.62,
|
1459 |
+
"learning_rate": 4.8128523929763626e-05,
|
1460 |
+
"loss": 3.1134,
|
1461 |
+
"step": 1210
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.62,
|
1465 |
+
"learning_rate": 4.811317232678456e-05,
|
1466 |
+
"loss": 3.3846,
|
1467 |
+
"step": 1215
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.63,
|
1471 |
+
"learning_rate": 4.8097760485390444e-05,
|
1472 |
+
"loss": 3.2507,
|
1473 |
+
"step": 1220
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.63,
|
1477 |
+
"learning_rate": 4.8082288445748194e-05,
|
1478 |
+
"loss": 3.0992,
|
1479 |
+
"step": 1225
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.63,
|
1483 |
+
"learning_rate": 4.806675624818162e-05,
|
1484 |
+
"loss": 3.0715,
|
1485 |
+
"step": 1230
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.63,
|
1489 |
+
"learning_rate": 4.8051163933171316e-05,
|
1490 |
+
"loss": 3.2028,
|
1491 |
+
"step": 1235
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.64,
|
1495 |
+
"learning_rate": 4.8035511541354547e-05,
|
1496 |
+
"loss": 3.2714,
|
1497 |
+
"step": 1240
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.64,
|
1501 |
+
"learning_rate": 4.801979911352519e-05,
|
1502 |
+
"loss": 3.1238,
|
1503 |
+
"step": 1245
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.64,
|
1507 |
+
"learning_rate": 4.800402669063353e-05,
|
1508 |
+
"loss": 3.2508,
|
1509 |
+
"step": 1250
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.64,
|
1513 |
+
"learning_rate": 4.7988194313786275e-05,
|
1514 |
+
"loss": 3.2359,
|
1515 |
+
"step": 1255
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.65,
|
1519 |
+
"learning_rate": 4.797230202424633e-05,
|
1520 |
+
"loss": 2.8538,
|
1521 |
+
"step": 1260
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.65,
|
1525 |
+
"learning_rate": 4.7956349863432794e-05,
|
1526 |
+
"loss": 3.1991,
|
1527 |
+
"step": 1265
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.65,
|
1531 |
+
"learning_rate": 4.794033787292078e-05,
|
1532 |
+
"loss": 3.0467,
|
1533 |
+
"step": 1270
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.66,
|
1537 |
+
"learning_rate": 4.7924266094441346e-05,
|
1538 |
+
"loss": 3.1088,
|
1539 |
+
"step": 1275
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.66,
|
1543 |
+
"learning_rate": 4.7908134569881344e-05,
|
1544 |
+
"loss": 3.128,
|
1545 |
+
"step": 1280
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.66,
|
1549 |
+
"learning_rate": 4.789194334128338e-05,
|
1550 |
+
"loss": 3.3195,
|
1551 |
+
"step": 1285
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.66,
|
1555 |
+
"learning_rate": 4.7875692450845624e-05,
|
1556 |
+
"loss": 3.2049,
|
1557 |
+
"step": 1290
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.67,
|
1561 |
+
"learning_rate": 4.785938194092176e-05,
|
1562 |
+
"loss": 3.1477,
|
1563 |
+
"step": 1295
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.67,
|
1567 |
+
"learning_rate": 4.7843011854020846e-05,
|
1568 |
+
"loss": 3.2506,
|
1569 |
+
"step": 1300
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.67,
|
1573 |
+
"learning_rate": 4.7826582232807213e-05,
|
1574 |
+
"loss": 3.1822,
|
1575 |
+
"step": 1305
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.67,
|
1579 |
+
"learning_rate": 4.7810093120100374e-05,
|
1580 |
+
"loss": 2.9576,
|
1581 |
+
"step": 1310
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.68,
|
1585 |
+
"learning_rate": 4.779354455887485e-05,
|
1586 |
+
"loss": 3.2086,
|
1587 |
+
"step": 1315
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.68,
|
1591 |
+
"learning_rate": 4.777693659226013e-05,
|
1592 |
+
"loss": 3.2935,
|
1593 |
+
"step": 1320
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.68,
|
1597 |
+
"learning_rate": 4.776026926354052e-05,
|
1598 |
+
"loss": 2.9873,
|
1599 |
+
"step": 1325
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.68,
|
1603 |
+
"learning_rate": 4.774354261615503e-05,
|
1604 |
+
"loss": 3.2671,
|
1605 |
+
"step": 1330
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.69,
|
1609 |
+
"learning_rate": 4.772675669369728e-05,
|
1610 |
+
"loss": 3.0882,
|
1611 |
+
"step": 1335
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.69,
|
1615 |
+
"learning_rate": 4.770991153991537e-05,
|
1616 |
+
"loss": 3.2727,
|
1617 |
+
"step": 1340
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.69,
|
1621 |
+
"learning_rate": 4.769300719871177e-05,
|
1622 |
+
"loss": 2.9907,
|
1623 |
+
"step": 1345
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.69,
|
1627 |
+
"learning_rate": 4.7676043714143195e-05,
|
1628 |
+
"loss": 3.1303,
|
1629 |
+
"step": 1350
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.7,
|
1633 |
+
"learning_rate": 4.765902113042053e-05,
|
1634 |
+
"loss": 3.1412,
|
1635 |
+
"step": 1355
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.7,
|
1639 |
+
"learning_rate": 4.7641939491908674e-05,
|
1640 |
+
"loss": 3.3585,
|
1641 |
+
"step": 1360
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.7,
|
1645 |
+
"learning_rate": 4.7624798843126404e-05,
|
1646 |
+
"loss": 3.1958,
|
1647 |
+
"step": 1365
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.7,
|
1651 |
+
"learning_rate": 4.7607599228746355e-05,
|
1652 |
+
"loss": 3.1581,
|
1653 |
+
"step": 1370
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.71,
|
1657 |
+
"learning_rate": 4.759034069359478e-05,
|
1658 |
+
"loss": 3.224,
|
1659 |
+
"step": 1375
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.71,
|
1663 |
+
"learning_rate": 4.7573023282651536e-05,
|
1664 |
+
"loss": 3.1031,
|
1665 |
+
"step": 1380
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.71,
|
1669 |
+
"learning_rate": 4.75556470410499e-05,
|
1670 |
+
"loss": 3.0914,
|
1671 |
+
"step": 1385
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.71,
|
1675 |
+
"learning_rate": 4.753821201407648e-05,
|
1676 |
+
"loss": 3.2474,
|
1677 |
+
"step": 1390
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.72,
|
1681 |
+
"learning_rate": 4.75207182471711e-05,
|
1682 |
+
"loss": 3.2045,
|
1683 |
+
"step": 1395
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.72,
|
1687 |
+
"learning_rate": 4.7503165785926676e-05,
|
1688 |
+
"loss": 2.9288,
|
1689 |
+
"step": 1400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.72,
|
1693 |
+
"learning_rate": 4.748555467608909e-05,
|
1694 |
+
"loss": 3.3084,
|
1695 |
+
"step": 1405
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.72,
|
1699 |
+
"learning_rate": 4.7467884963557064e-05,
|
1700 |
+
"loss": 3.1761,
|
1701 |
+
"step": 1410
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.73,
|
1705 |
+
"learning_rate": 4.745015669438207e-05,
|
1706 |
+
"loss": 3.0644,
|
1707 |
+
"step": 1415
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.73,
|
1711 |
+
"learning_rate": 4.7432369914768185e-05,
|
1712 |
+
"loss": 3.0874,
|
1713 |
+
"step": 1420
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.73,
|
1717 |
+
"learning_rate": 4.7414524671071994e-05,
|
1718 |
+
"loss": 3.1106,
|
1719 |
+
"step": 1425
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.73,
|
1723 |
+
"learning_rate": 4.739662100980242e-05,
|
1724 |
+
"loss": 2.8364,
|
1725 |
+
"step": 1430
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.74,
|
1729 |
+
"learning_rate": 4.737865897762066e-05,
|
1730 |
+
"loss": 3.0884,
|
1731 |
+
"step": 1435
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.74,
|
1735 |
+
"learning_rate": 4.736063862134004e-05,
|
1736 |
+
"loss": 3.1134,
|
1737 |
+
"step": 1440
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.74,
|
1741 |
+
"learning_rate": 4.734255998792589e-05,
|
1742 |
+
"loss": 3.3668,
|
1743 |
+
"step": 1445
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 0.75,
|
1747 |
+
"learning_rate": 4.732442312449541e-05,
|
1748 |
+
"loss": 2.9823,
|
1749 |
+
"step": 1450
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.75,
|
1753 |
+
"learning_rate": 4.730622807831758e-05,
|
1754 |
+
"loss": 3.0893,
|
1755 |
+
"step": 1455
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.75,
|
1759 |
+
"learning_rate": 4.728797489681301e-05,
|
1760 |
+
"loss": 3.1091,
|
1761 |
+
"step": 1460
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.75,
|
1765 |
+
"learning_rate": 4.726966362755383e-05,
|
1766 |
+
"loss": 2.9348,
|
1767 |
+
"step": 1465
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.76,
|
1771 |
+
"learning_rate": 4.725129431826355e-05,
|
1772 |
+
"loss": 3.2506,
|
1773 |
+
"step": 1470
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.76,
|
1777 |
+
"learning_rate": 4.723286701681695e-05,
|
1778 |
+
"loss": 2.9876,
|
1779 |
+
"step": 1475
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.76,
|
1783 |
+
"learning_rate": 4.7214381771239946e-05,
|
1784 |
+
"loss": 2.9158,
|
1785 |
+
"step": 1480
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 0.76,
|
1789 |
+
"learning_rate": 4.719583862970949e-05,
|
1790 |
+
"loss": 3.2035,
|
1791 |
+
"step": 1485
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.77,
|
1795 |
+
"learning_rate": 4.7177237640553414e-05,
|
1796 |
+
"loss": 2.9031,
|
1797 |
+
"step": 1490
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.77,
|
1801 |
+
"learning_rate": 4.7158578852250304e-05,
|
1802 |
+
"loss": 3.2779,
|
1803 |
+
"step": 1495
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.77,
|
1807 |
+
"learning_rate": 4.7139862313429385e-05,
|
1808 |
+
"loss": 3.1219,
|
1809 |
+
"step": 1500
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.77,
|
1813 |
+
"learning_rate": 4.712108807287042e-05,
|
1814 |
+
"loss": 3.1643,
|
1815 |
+
"step": 1505
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.78,
|
1819 |
+
"learning_rate": 4.7102256179503525e-05,
|
1820 |
+
"loss": 3.1993,
|
1821 |
+
"step": 1510
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.78,
|
1825 |
+
"learning_rate": 4.708336668240908e-05,
|
1826 |
+
"loss": 3.1773,
|
1827 |
+
"step": 1515
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 0.78,
|
1831 |
+
"learning_rate": 4.706441963081762e-05,
|
1832 |
+
"loss": 2.9617,
|
1833 |
+
"step": 1520
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.78,
|
1837 |
+
"learning_rate": 4.7045415074109646e-05,
|
1838 |
+
"loss": 3.2621,
|
1839 |
+
"step": 1525
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.79,
|
1843 |
+
"learning_rate": 4.702635306181554e-05,
|
1844 |
+
"loss": 3.2206,
|
1845 |
+
"step": 1530
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.79,
|
1849 |
+
"learning_rate": 4.700723364361545e-05,
|
1850 |
+
"loss": 3.3413,
|
1851 |
+
"step": 1535
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.79,
|
1855 |
+
"learning_rate": 4.6988056869339104e-05,
|
1856 |
+
"loss": 3.3453,
|
1857 |
+
"step": 1540
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.79,
|
1861 |
+
"learning_rate": 4.696882278896574e-05,
|
1862 |
+
"loss": 3.0481,
|
1863 |
+
"step": 1545
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.8,
|
1867 |
+
"learning_rate": 4.694953145262393e-05,
|
1868 |
+
"loss": 3.2183,
|
1869 |
+
"step": 1550
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.8,
|
1873 |
+
"learning_rate": 4.693018291059147e-05,
|
1874 |
+
"loss": 3.4063,
|
1875 |
+
"step": 1555
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.8,
|
1879 |
+
"learning_rate": 4.691077721329527e-05,
|
1880 |
+
"loss": 3.1694,
|
1881 |
+
"step": 1560
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.8,
|
1885 |
+
"learning_rate": 4.6891314411311184e-05,
|
1886 |
+
"loss": 3.0084,
|
1887 |
+
"step": 1565
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.81,
|
1891 |
+
"learning_rate": 4.6871794555363885e-05,
|
1892 |
+
"loss": 3.318,
|
1893 |
+
"step": 1570
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.81,
|
1897 |
+
"learning_rate": 4.685221769632676e-05,
|
1898 |
+
"loss": 3.3126,
|
1899 |
+
"step": 1575
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.81,
|
1903 |
+
"learning_rate": 4.683258388522175e-05,
|
1904 |
+
"loss": 3.1085,
|
1905 |
+
"step": 1580
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.81,
|
1909 |
+
"learning_rate": 4.681289317321923e-05,
|
1910 |
+
"loss": 3.0566,
|
1911 |
+
"step": 1585
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 0.82,
|
1915 |
+
"learning_rate": 4.679314561163787e-05,
|
1916 |
+
"loss": 3.0642,
|
1917 |
+
"step": 1590
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.82,
|
1921 |
+
"learning_rate": 4.6773341251944496e-05,
|
1922 |
+
"loss": 2.9335,
|
1923 |
+
"step": 1595
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.82,
|
1927 |
+
"learning_rate": 4.675348014575398e-05,
|
1928 |
+
"loss": 3.1551,
|
1929 |
+
"step": 1600
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.82,
|
1933 |
+
"learning_rate": 4.673356234482908e-05,
|
1934 |
+
"loss": 3.0211,
|
1935 |
+
"step": 1605
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.83,
|
1939 |
+
"learning_rate": 4.671358790108033e-05,
|
1940 |
+
"loss": 3.28,
|
1941 |
+
"step": 1610
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.83,
|
1945 |
+
"learning_rate": 4.6693556866565835e-05,
|
1946 |
+
"loss": 3.0621,
|
1947 |
+
"step": 1615
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 0.83,
|
1951 |
+
"learning_rate": 4.667346929349126e-05,
|
1952 |
+
"loss": 3.1141,
|
1953 |
+
"step": 1620
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 0.84,
|
1957 |
+
"learning_rate": 4.6653325234209575e-05,
|
1958 |
+
"loss": 3.1941,
|
1959 |
+
"step": 1625
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.84,
|
1963 |
+
"learning_rate": 4.663312474122099e-05,
|
1964 |
+
"loss": 3.1874,
|
1965 |
+
"step": 1630
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.84,
|
1969 |
+
"learning_rate": 4.661286786717278e-05,
|
1970 |
+
"loss": 3.2085,
|
1971 |
+
"step": 1635
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.84,
|
1975 |
+
"learning_rate": 4.659255466485918e-05,
|
1976 |
+
"loss": 3.398,
|
1977 |
+
"step": 1640
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.85,
|
1981 |
+
"learning_rate": 4.65721851872212e-05,
|
1982 |
+
"loss": 3.1911,
|
1983 |
+
"step": 1645
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.85,
|
1987 |
+
"learning_rate": 4.655175948734654e-05,
|
1988 |
+
"loss": 3.2273,
|
1989 |
+
"step": 1650
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.85,
|
1993 |
+
"learning_rate": 4.653127761846943e-05,
|
1994 |
+
"loss": 3.2084,
|
1995 |
+
"step": 1655
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 0.85,
|
1999 |
+
"learning_rate": 4.6510739633970485e-05,
|
2000 |
+
"loss": 3.2789,
|
2001 |
+
"step": 1660
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.86,
|
2005 |
+
"learning_rate": 4.649014558737656e-05,
|
2006 |
+
"loss": 3.1193,
|
2007 |
+
"step": 1665
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.86,
|
2011 |
+
"learning_rate": 4.646949553236064e-05,
|
2012 |
+
"loss": 3.2083,
|
2013 |
+
"step": 1670
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.86,
|
2017 |
+
"learning_rate": 4.6448789522741665e-05,
|
2018 |
+
"loss": 3.0306,
|
2019 |
+
"step": 1675
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.86,
|
2023 |
+
"learning_rate": 4.642802761248441e-05,
|
2024 |
+
"loss": 3.0084,
|
2025 |
+
"step": 1680
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.87,
|
2029 |
+
"learning_rate": 4.6407209855699365e-05,
|
2030 |
+
"loss": 3.2976,
|
2031 |
+
"step": 1685
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 0.87,
|
2035 |
+
"learning_rate": 4.6386336306642514e-05,
|
2036 |
+
"loss": 3.3373,
|
2037 |
+
"step": 1690
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 0.87,
|
2041 |
+
"learning_rate": 4.63654070197153e-05,
|
2042 |
+
"loss": 3.049,
|
2043 |
+
"step": 1695
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.87,
|
2047 |
+
"learning_rate": 4.634442204946442e-05,
|
2048 |
+
"loss": 3.1669,
|
2049 |
+
"step": 1700
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.88,
|
2053 |
+
"learning_rate": 4.632338145058167e-05,
|
2054 |
+
"loss": 3.1078,
|
2055 |
+
"step": 1705
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.88,
|
2059 |
+
"learning_rate": 4.630228527790386e-05,
|
2060 |
+
"loss": 3.1724,
|
2061 |
+
"step": 1710
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.88,
|
2065 |
+
"learning_rate": 4.628113358641263e-05,
|
2066 |
+
"loss": 3.2197,
|
2067 |
+
"step": 1715
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.88,
|
2071 |
+
"learning_rate": 4.625992643123429e-05,
|
2072 |
+
"loss": 3.0047,
|
2073 |
+
"step": 1720
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 0.89,
|
2077 |
+
"learning_rate": 4.623866386763974e-05,
|
2078 |
+
"loss": 2.9798,
|
2079 |
+
"step": 1725
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.89,
|
2083 |
+
"learning_rate": 4.621734595104427e-05,
|
2084 |
+
"loss": 3.2065,
|
2085 |
+
"step": 1730
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.89,
|
2089 |
+
"learning_rate": 4.619597273700742e-05,
|
2090 |
+
"loss": 3.0981,
|
2091 |
+
"step": 1735
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.89,
|
2095 |
+
"learning_rate": 4.6174544281232865e-05,
|
2096 |
+
"loss": 2.7712,
|
2097 |
+
"step": 1740
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.9,
|
2101 |
+
"learning_rate": 4.615306063956826e-05,
|
2102 |
+
"loss": 3.2469,
|
2103 |
+
"step": 1745
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.9,
|
2107 |
+
"learning_rate": 4.613152186800506e-05,
|
2108 |
+
"loss": 3.3318,
|
2109 |
+
"step": 1750
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.9,
|
2113 |
+
"learning_rate": 4.610992802267842e-05,
|
2114 |
+
"loss": 3.216,
|
2115 |
+
"step": 1755
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.9,
|
2119 |
+
"learning_rate": 4.608827915986704e-05,
|
2120 |
+
"loss": 3.0298,
|
2121 |
+
"step": 1760
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 0.91,
|
2125 |
+
"learning_rate": 4.606657533599298e-05,
|
2126 |
+
"loss": 3.1146,
|
2127 |
+
"step": 1765
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.91,
|
2131 |
+
"learning_rate": 4.604481660762158e-05,
|
2132 |
+
"loss": 3.1621,
|
2133 |
+
"step": 1770
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.91,
|
2137 |
+
"learning_rate": 4.6023003031461234e-05,
|
2138 |
+
"loss": 2.9654,
|
2139 |
+
"step": 1775
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.91,
|
2143 |
+
"learning_rate": 4.600113466436331e-05,
|
2144 |
+
"loss": 3.3586,
|
2145 |
+
"step": 1780
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.92,
|
2149 |
+
"learning_rate": 4.597921156332196e-05,
|
2150 |
+
"loss": 3.1212,
|
2151 |
+
"step": 1785
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.92,
|
2155 |
+
"learning_rate": 4.5957233785474e-05,
|
2156 |
+
"loss": 2.8321,
|
2157 |
+
"step": 1790
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.92,
|
2161 |
+
"learning_rate": 4.5935201388098716e-05,
|
2162 |
+
"loss": 2.9001,
|
2163 |
+
"step": 1795
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 0.92,
|
2167 |
+
"learning_rate": 4.5913114428617785e-05,
|
2168 |
+
"loss": 3.248,
|
2169 |
+
"step": 1800
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.93,
|
2173 |
+
"learning_rate": 4.589097296459508e-05,
|
2174 |
+
"loss": 2.8819,
|
2175 |
+
"step": 1805
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 0.93,
|
2179 |
+
"learning_rate": 4.5868777053736476e-05,
|
2180 |
+
"loss": 3.0377,
|
2181 |
+
"step": 1810
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.93,
|
2185 |
+
"learning_rate": 4.584652675388982e-05,
|
2186 |
+
"loss": 3.3161,
|
2187 |
+
"step": 1815
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.94,
|
2191 |
+
"learning_rate": 4.582422212304467e-05,
|
2192 |
+
"loss": 3.1995,
|
2193 |
+
"step": 1820
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.94,
|
2197 |
+
"learning_rate": 4.580186321933217e-05,
|
2198 |
+
"loss": 3.4196,
|
2199 |
+
"step": 1825
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.94,
|
2203 |
+
"learning_rate": 4.577945010102496e-05,
|
2204 |
+
"loss": 3.35,
|
2205 |
+
"step": 1830
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 0.94,
|
2209 |
+
"learning_rate": 4.575698282653693e-05,
|
2210 |
+
"loss": 3.2269,
|
2211 |
+
"step": 1835
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 0.95,
|
2215 |
+
"learning_rate": 4.573446145442314e-05,
|
2216 |
+
"loss": 3.1207,
|
2217 |
+
"step": 1840
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 0.95,
|
2221 |
+
"learning_rate": 4.571188604337963e-05,
|
2222 |
+
"loss": 3.3682,
|
2223 |
+
"step": 1845
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.95,
|
2227 |
+
"learning_rate": 4.568925665224327e-05,
|
2228 |
+
"loss": 3.0202,
|
2229 |
+
"step": 1850
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.95,
|
2233 |
+
"learning_rate": 4.5666573339991646e-05,
|
2234 |
+
"loss": 3.0227,
|
2235 |
+
"step": 1855
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.96,
|
2239 |
+
"learning_rate": 4.564383616574285e-05,
|
2240 |
+
"loss": 3.1553,
|
2241 |
+
"step": 1860
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.96,
|
2245 |
+
"learning_rate": 4.562104518875535e-05,
|
2246 |
+
"loss": 3.1961,
|
2247 |
+
"step": 1865
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 0.96,
|
2251 |
+
"learning_rate": 4.5598200468427854e-05,
|
2252 |
+
"loss": 2.9751,
|
2253 |
+
"step": 1870
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 0.96,
|
2257 |
+
"learning_rate": 4.557530206429912e-05,
|
2258 |
+
"loss": 2.9953,
|
2259 |
+
"step": 1875
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.97,
|
2263 |
+
"learning_rate": 4.555235003604782e-05,
|
2264 |
+
"loss": 2.9119,
|
2265 |
+
"step": 1880
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.97,
|
2269 |
+
"learning_rate": 4.55293444434924e-05,
|
2270 |
+
"loss": 3.1541,
|
2271 |
+
"step": 1885
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.97,
|
2275 |
+
"learning_rate": 4.5506285346590894e-05,
|
2276 |
+
"loss": 2.9233,
|
2277 |
+
"step": 1890
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.97,
|
2281 |
+
"learning_rate": 4.5483172805440785e-05,
|
2282 |
+
"loss": 3.3379,
|
2283 |
+
"step": 1895
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.98,
|
2287 |
+
"learning_rate": 4.546000688027884e-05,
|
2288 |
+
"loss": 3.1169,
|
2289 |
+
"step": 1900
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.98,
|
2293 |
+
"learning_rate": 4.543678763148096e-05,
|
2294 |
+
"loss": 3.3383,
|
2295 |
+
"step": 1905
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 0.98,
|
2299 |
+
"learning_rate": 4.5413515119562023e-05,
|
2300 |
+
"loss": 3.1096,
|
2301 |
+
"step": 1910
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 0.98,
|
2305 |
+
"learning_rate": 4.539018940517572e-05,
|
2306 |
+
"loss": 3.1755,
|
2307 |
+
"step": 1915
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.99,
|
2311 |
+
"learning_rate": 4.53668105491144e-05,
|
2312 |
+
"loss": 3.1069,
|
2313 |
+
"step": 1920
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.99,
|
2317 |
+
"learning_rate": 4.534337861230891e-05,
|
2318 |
+
"loss": 3.045,
|
2319 |
+
"step": 1925
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.99,
|
2323 |
+
"learning_rate": 4.5319893655828446e-05,
|
2324 |
+
"loss": 2.975,
|
2325 |
+
"step": 1930
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.99,
|
2329 |
+
"learning_rate": 4.5296355740880385e-05,
|
2330 |
+
"loss": 3.4444,
|
2331 |
+
"step": 1935
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 1.0,
|
2335 |
+
"learning_rate": 4.5272764928810115e-05,
|
2336 |
+
"loss": 3.1052,
|
2337 |
+
"step": 1940
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 1.0,
|
2341 |
+
"learning_rate": 4.52491212811009e-05,
|
2342 |
+
"loss": 3.0536,
|
2343 |
+
"step": 1945
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 1.0,
|
2347 |
+
"learning_rate": 4.522542485937369e-05,
|
2348 |
+
"loss": 3.0542,
|
2349 |
+
"step": 1950
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 1.0,
|
2353 |
+
"learning_rate": 4.520167572538699e-05,
|
2354 |
+
"loss": 3.158,
|
2355 |
+
"step": 1955
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 1.01,
|
2359 |
+
"learning_rate": 4.5177873941036683e-05,
|
2360 |
+
"loss": 3.0392,
|
2361 |
+
"step": 1960
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 1.01,
|
2365 |
+
"learning_rate": 4.5154019568355876e-05,
|
2366 |
+
"loss": 3.1487,
|
2367 |
+
"step": 1965
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 1.01,
|
2371 |
+
"learning_rate": 4.5130112669514726e-05,
|
2372 |
+
"loss": 2.9061,
|
2373 |
+
"step": 1970
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 1.01,
|
2377 |
+
"learning_rate": 4.510615330682028e-05,
|
2378 |
+
"loss": 2.9249,
|
2379 |
+
"step": 1975
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 1.02,
|
2383 |
+
"learning_rate": 4.5082141542716336e-05,
|
2384 |
+
"loss": 3.0888,
|
2385 |
+
"step": 1980
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 1.02,
|
2389 |
+
"learning_rate": 4.505807743978324e-05,
|
2390 |
+
"loss": 2.9417,
|
2391 |
+
"step": 1985
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 1.02,
|
2395 |
+
"learning_rate": 4.5033961060737774e-05,
|
2396 |
+
"loss": 2.8967,
|
2397 |
+
"step": 1990
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.03,
|
2401 |
+
"learning_rate": 4.5009792468432946e-05,
|
2402 |
+
"loss": 2.9344,
|
2403 |
+
"step": 1995
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 1.03,
|
2407 |
+
"learning_rate": 4.498557172585782e-05,
|
2408 |
+
"loss": 3.1597,
|
2409 |
+
"step": 2000
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 1.03,
|
2413 |
+
"learning_rate": 4.496129889613744e-05,
|
2414 |
+
"loss": 2.9188,
|
2415 |
+
"step": 2005
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 1.03,
|
2419 |
+
"learning_rate": 4.493697404253254e-05,
|
2420 |
+
"loss": 2.7781,
|
2421 |
+
"step": 2010
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 1.04,
|
2425 |
+
"learning_rate": 4.4912597228439466e-05,
|
2426 |
+
"loss": 3.0411,
|
2427 |
+
"step": 2015
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 1.04,
|
2431 |
+
"learning_rate": 4.488816851738999e-05,
|
2432 |
+
"loss": 3.0727,
|
2433 |
+
"step": 2020
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 1.04,
|
2437 |
+
"learning_rate": 4.486368797305114e-05,
|
2438 |
+
"loss": 3.0783,
|
2439 |
+
"step": 2025
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 1.04,
|
2443 |
+
"learning_rate": 4.483915565922501e-05,
|
2444 |
+
"loss": 2.823,
|
2445 |
+
"step": 2030
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 1.05,
|
2449 |
+
"learning_rate": 4.481457163984864e-05,
|
2450 |
+
"loss": 2.6414,
|
2451 |
+
"step": 2035
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 1.05,
|
2455 |
+
"learning_rate": 4.478993597899382e-05,
|
2456 |
+
"loss": 2.9076,
|
2457 |
+
"step": 2040
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 1.05,
|
2461 |
+
"learning_rate": 4.476524874086695e-05,
|
2462 |
+
"loss": 2.8118,
|
2463 |
+
"step": 2045
|
2464 |
+
},
|
2465 |
+
{
|
2466 |
+
"epoch": 1.05,
|
2467 |
+
"learning_rate": 4.4740509989808815e-05,
|
2468 |
+
"loss": 3.0352,
|
2469 |
+
"step": 2050
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 1.06,
|
2473 |
+
"learning_rate": 4.4715719790294474e-05,
|
2474 |
+
"loss": 3.0765,
|
2475 |
+
"step": 2055
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 1.06,
|
2479 |
+
"learning_rate": 4.4690878206933086e-05,
|
2480 |
+
"loss": 2.6218,
|
2481 |
+
"step": 2060
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 1.06,
|
2485 |
+
"learning_rate": 4.466598530446771e-05,
|
2486 |
+
"loss": 3.0266,
|
2487 |
+
"step": 2065
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 1.06,
|
2491 |
+
"learning_rate": 4.464104114777515e-05,
|
2492 |
+
"loss": 3.0852,
|
2493 |
+
"step": 2070
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 1.07,
|
2497 |
+
"learning_rate": 4.4616045801865814e-05,
|
2498 |
+
"loss": 2.9536,
|
2499 |
+
"step": 2075
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 1.07,
|
2503 |
+
"learning_rate": 4.4590999331883505e-05,
|
2504 |
+
"loss": 2.7272,
|
2505 |
+
"step": 2080
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 1.07,
|
2509 |
+
"learning_rate": 4.456590180310527e-05,
|
2510 |
+
"loss": 3.0185,
|
2511 |
+
"step": 2085
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 1.07,
|
2515 |
+
"learning_rate": 4.454075328094123e-05,
|
2516 |
+
"loss": 3.1669,
|
2517 |
+
"step": 2090
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 1.08,
|
2521 |
+
"learning_rate": 4.45155538309344e-05,
|
2522 |
+
"loss": 2.7681,
|
2523 |
+
"step": 2095
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 1.08,
|
2527 |
+
"learning_rate": 4.449030351876053e-05,
|
2528 |
+
"loss": 3.0262,
|
2529 |
+
"step": 2100
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 1.08,
|
2533 |
+
"learning_rate": 4.446500241022794e-05,
|
2534 |
+
"loss": 2.7877,
|
2535 |
+
"step": 2105
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 1.08,
|
2539 |
+
"learning_rate": 4.443965057127731e-05,
|
2540 |
+
"loss": 2.9973,
|
2541 |
+
"step": 2110
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 1.09,
|
2545 |
+
"learning_rate": 4.441424806798156e-05,
|
2546 |
+
"loss": 2.9694,
|
2547 |
+
"step": 2115
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 1.09,
|
2551 |
+
"learning_rate": 4.438879496654565e-05,
|
2552 |
+
"loss": 2.9082,
|
2553 |
+
"step": 2120
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 1.09,
|
2557 |
+
"learning_rate": 4.43632913333064e-05,
|
2558 |
+
"loss": 3.1398,
|
2559 |
+
"step": 2125
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 1.09,
|
2563 |
+
"learning_rate": 4.4337737234732334e-05,
|
2564 |
+
"loss": 2.9788,
|
2565 |
+
"step": 2130
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 1.1,
|
2569 |
+
"learning_rate": 4.431213273742351e-05,
|
2570 |
+
"loss": 3.0885,
|
2571 |
+
"step": 2135
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 1.1,
|
2575 |
+
"learning_rate": 4.42864779081113e-05,
|
2576 |
+
"loss": 3.1436,
|
2577 |
+
"step": 2140
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 1.1,
|
2581 |
+
"learning_rate": 4.4260772813658316e-05,
|
2582 |
+
"loss": 2.9983,
|
2583 |
+
"step": 2145
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 1.1,
|
2587 |
+
"learning_rate": 4.423501752105812e-05,
|
2588 |
+
"loss": 3.0249,
|
2589 |
+
"step": 2150
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 1.11,
|
2593 |
+
"learning_rate": 4.420921209743511e-05,
|
2594 |
+
"loss": 2.8603,
|
2595 |
+
"step": 2155
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 1.11,
|
2599 |
+
"learning_rate": 4.4183356610044364e-05,
|
2600 |
+
"loss": 2.8446,
|
2601 |
+
"step": 2160
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 1.11,
|
2605 |
+
"learning_rate": 4.415745112627141e-05,
|
2606 |
+
"loss": 3.0299,
|
2607 |
+
"step": 2165
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 1.12,
|
2611 |
+
"learning_rate": 4.4131495713632104e-05,
|
2612 |
+
"loss": 2.8172,
|
2613 |
+
"step": 2170
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 1.12,
|
2617 |
+
"learning_rate": 4.4105490439772404e-05,
|
2618 |
+
"loss": 2.9729,
|
2619 |
+
"step": 2175
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 1.12,
|
2623 |
+
"learning_rate": 4.407943537246822e-05,
|
2624 |
+
"loss": 2.9726,
|
2625 |
+
"step": 2180
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 1.12,
|
2629 |
+
"learning_rate": 4.4053330579625265e-05,
|
2630 |
+
"loss": 2.8896,
|
2631 |
+
"step": 2185
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 1.13,
|
2635 |
+
"learning_rate": 4.4027176129278815e-05,
|
2636 |
+
"loss": 3.1341,
|
2637 |
+
"step": 2190
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 1.13,
|
2641 |
+
"learning_rate": 4.4000972089593566e-05,
|
2642 |
+
"loss": 2.8074,
|
2643 |
+
"step": 2195
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 1.13,
|
2647 |
+
"learning_rate": 4.397471852886349e-05,
|
2648 |
+
"loss": 3.0711,
|
2649 |
+
"step": 2200
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 1.13,
|
2653 |
+
"learning_rate": 4.3948415515511586e-05,
|
2654 |
+
"loss": 3.0245,
|
2655 |
+
"step": 2205
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 1.14,
|
2659 |
+
"learning_rate": 4.3922063118089765e-05,
|
2660 |
+
"loss": 3.0007,
|
2661 |
+
"step": 2210
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 1.14,
|
2665 |
+
"learning_rate": 4.389566140527861e-05,
|
2666 |
+
"loss": 2.9818,
|
2667 |
+
"step": 2215
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 1.14,
|
2671 |
+
"learning_rate": 4.386921044588727e-05,
|
2672 |
+
"loss": 2.9922,
|
2673 |
+
"step": 2220
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 1.14,
|
2677 |
+
"learning_rate": 4.384271030885322e-05,
|
2678 |
+
"loss": 2.8606,
|
2679 |
+
"step": 2225
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 1.15,
|
2683 |
+
"learning_rate": 4.381616106324211e-05,
|
2684 |
+
"loss": 2.7615,
|
2685 |
+
"step": 2230
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 1.15,
|
2689 |
+
"learning_rate": 4.3789562778247585e-05,
|
2690 |
+
"loss": 2.7838,
|
2691 |
+
"step": 2235
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 1.15,
|
2695 |
+
"learning_rate": 4.3762915523191084e-05,
|
2696 |
+
"loss": 2.9275,
|
2697 |
+
"step": 2240
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 1.15,
|
2701 |
+
"learning_rate": 4.373621936752168e-05,
|
2702 |
+
"loss": 3.0331,
|
2703 |
+
"step": 2245
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 1.16,
|
2707 |
+
"learning_rate": 4.37094743808159e-05,
|
2708 |
+
"loss": 2.9586,
|
2709 |
+
"step": 2250
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 1.16,
|
2713 |
+
"learning_rate": 4.3682680632777515e-05,
|
2714 |
+
"loss": 2.7475,
|
2715 |
+
"step": 2255
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 1.16,
|
2719 |
+
"learning_rate": 4.36558381932374e-05,
|
2720 |
+
"loss": 3.0034,
|
2721 |
+
"step": 2260
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 1.16,
|
2725 |
+
"learning_rate": 4.362894713215334e-05,
|
2726 |
+
"loss": 2.9839,
|
2727 |
+
"step": 2265
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 1.17,
|
2731 |
+
"learning_rate": 4.360200751960982e-05,
|
2732 |
+
"loss": 2.8333,
|
2733 |
+
"step": 2270
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 1.17,
|
2737 |
+
"learning_rate": 4.3575019425817856e-05,
|
2738 |
+
"loss": 2.853,
|
2739 |
+
"step": 2275
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 1.17,
|
2743 |
+
"learning_rate": 4.354798292111483e-05,
|
2744 |
+
"loss": 3.266,
|
2745 |
+
"step": 2280
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 1.17,
|
2749 |
+
"learning_rate": 4.35208980759643e-05,
|
2750 |
+
"loss": 3.1553,
|
2751 |
+
"step": 2285
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 1.18,
|
2755 |
+
"learning_rate": 4.34937649609558e-05,
|
2756 |
+
"loss": 3.1441,
|
2757 |
+
"step": 2290
|
2758 |
+
},
|
2759 |
+
{
|
2760 |
+
"epoch": 1.18,
|
2761 |
+
"learning_rate": 4.3466583646804674e-05,
|
2762 |
+
"loss": 2.8948,
|
2763 |
+
"step": 2295
|
2764 |
+
},
|
2765 |
+
{
|
2766 |
+
"epoch": 1.18,
|
2767 |
+
"learning_rate": 4.3439354204351866e-05,
|
2768 |
+
"loss": 3.0963,
|
2769 |
+
"step": 2300
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 1.18,
|
2773 |
+
"learning_rate": 4.341207670456379e-05,
|
2774 |
+
"loss": 3.0771,
|
2775 |
+
"step": 2305
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 1.19,
|
2779 |
+
"learning_rate": 4.3384751218532086e-05,
|
2780 |
+
"loss": 3.0364,
|
2781 |
+
"step": 2310
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 1.19,
|
2785 |
+
"learning_rate": 4.335737781747343e-05,
|
2786 |
+
"loss": 2.9928,
|
2787 |
+
"step": 2315
|
2788 |
+
},
|
2789 |
+
{
|
2790 |
+
"epoch": 1.19,
|
2791 |
+
"learning_rate": 4.332995657272944e-05,
|
2792 |
+
"loss": 3.1993,
|
2793 |
+
"step": 2320
|
2794 |
+
},
|
2795 |
+
{
|
2796 |
+
"epoch": 1.19,
|
2797 |
+
"learning_rate": 4.330248755576636e-05,
|
2798 |
+
"loss": 2.9873,
|
2799 |
+
"step": 2325
|
2800 |
+
},
|
2801 |
+
{
|
2802 |
+
"epoch": 1.2,
|
2803 |
+
"learning_rate": 4.3274970838175e-05,
|
2804 |
+
"loss": 2.9258,
|
2805 |
+
"step": 2330
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 1.2,
|
2809 |
+
"learning_rate": 4.324740649167044e-05,
|
2810 |
+
"loss": 2.7857,
|
2811 |
+
"step": 2335
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 1.2,
|
2815 |
+
"learning_rate": 4.321979458809191e-05,
|
2816 |
+
"loss": 3.1293,
|
2817 |
+
"step": 2340
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 1.21,
|
2821 |
+
"learning_rate": 4.31921351994026e-05,
|
2822 |
+
"loss": 3.0588,
|
2823 |
+
"step": 2345
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 1.21,
|
2827 |
+
"learning_rate": 4.3164428397689436e-05,
|
2828 |
+
"loss": 3.116,
|
2829 |
+
"step": 2350
|
2830 |
+
},
|
2831 |
+
{
|
2832 |
+
"epoch": 1.21,
|
2833 |
+
"learning_rate": 4.313667425516292e-05,
|
2834 |
+
"loss": 3.0814,
|
2835 |
+
"step": 2355
|
2836 |
+
},
|
2837 |
+
{
|
2838 |
+
"epoch": 1.21,
|
2839 |
+
"learning_rate": 4.310887284415695e-05,
|
2840 |
+
"loss": 2.9781,
|
2841 |
+
"step": 2360
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 1.22,
|
2845 |
+
"learning_rate": 4.308102423712859e-05,
|
2846 |
+
"loss": 2.8611,
|
2847 |
+
"step": 2365
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 1.22,
|
2851 |
+
"learning_rate": 4.3053128506657934e-05,
|
2852 |
+
"loss": 3.1201,
|
2853 |
+
"step": 2370
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 1.22,
|
2857 |
+
"learning_rate": 4.302518572544787e-05,
|
2858 |
+
"loss": 3.108,
|
2859 |
+
"step": 2375
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 1.22,
|
2863 |
+
"learning_rate": 4.299719596632392e-05,
|
2864 |
+
"loss": 2.8409,
|
2865 |
+
"step": 2380
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 1.23,
|
2869 |
+
"learning_rate": 4.2969159302234044e-05,
|
2870 |
+
"loss": 2.8566,
|
2871 |
+
"step": 2385
|
2872 |
+
},
|
2873 |
+
{
|
2874 |
+
"epoch": 1.23,
|
2875 |
+
"learning_rate": 4.294107580624845e-05,
|
2876 |
+
"loss": 2.7636,
|
2877 |
+
"step": 2390
|
2878 |
+
},
|
2879 |
+
{
|
2880 |
+
"epoch": 1.23,
|
2881 |
+
"learning_rate": 4.291294555155939e-05,
|
2882 |
+
"loss": 3.1108,
|
2883 |
+
"step": 2395
|
2884 |
+
},
|
2885 |
+
{
|
2886 |
+
"epoch": 1.23,
|
2887 |
+
"learning_rate": 4.2884768611481e-05,
|
2888 |
+
"loss": 3.0492,
|
2889 |
+
"step": 2400
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 1.24,
|
2893 |
+
"learning_rate": 4.2856545059449063e-05,
|
2894 |
+
"loss": 3.1709,
|
2895 |
+
"step": 2405
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 1.24,
|
2899 |
+
"learning_rate": 4.282827496902086e-05,
|
2900 |
+
"loss": 3.0867,
|
2901 |
+
"step": 2410
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 1.24,
|
2905 |
+
"learning_rate": 4.279995841387496e-05,
|
2906 |
+
"loss": 2.8054,
|
2907 |
+
"step": 2415
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 1.24,
|
2911 |
+
"learning_rate": 4.277159546781103e-05,
|
2912 |
+
"loss": 2.8368,
|
2913 |
+
"step": 2420
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 1.25,
|
2917 |
+
"learning_rate": 4.274318620474964e-05,
|
2918 |
+
"loss": 3.0,
|
2919 |
+
"step": 2425
|
2920 |
+
},
|
2921 |
+
{
|
2922 |
+
"epoch": 1.25,
|
2923 |
+
"learning_rate": 4.2714730698732076e-05,
|
2924 |
+
"loss": 2.9218,
|
2925 |
+
"step": 2430
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 1.25,
|
2929 |
+
"learning_rate": 4.268622902392014e-05,
|
2930 |
+
"loss": 2.9109,
|
2931 |
+
"step": 2435
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 1.25,
|
2935 |
+
"learning_rate": 4.265768125459597e-05,
|
2936 |
+
"loss": 3.074,
|
2937 |
+
"step": 2440
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 1.26,
|
2941 |
+
"learning_rate": 4.263480990108211e-05,
|
2942 |
+
"loss": 2.8238,
|
2943 |
+
"step": 2445
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 1.26,
|
2947 |
+
"learning_rate": 4.260617934921023e-05,
|
2948 |
+
"loss": 2.9209,
|
2949 |
+
"step": 2450
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 1.26,
|
2953 |
+
"learning_rate": 4.257750291145457e-05,
|
2954 |
+
"loss": 2.8323,
|
2955 |
+
"step": 2455
|
2956 |
+
},
|
2957 |
+
{
|
2958 |
+
"epoch": 1.26,
|
2959 |
+
"learning_rate": 4.254878066255274e-05,
|
2960 |
+
"loss": 3.2091,
|
2961 |
+
"step": 2460
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 1.27,
|
2965 |
+
"learning_rate": 4.252001267736174e-05,
|
2966 |
+
"loss": 2.8372,
|
2967 |
+
"step": 2465
|
2968 |
+
},
|
2969 |
+
{
|
2970 |
+
"epoch": 1.27,
|
2971 |
+
"learning_rate": 4.2491199030857764e-05,
|
2972 |
+
"loss": 3.0106,
|
2973 |
+
"step": 2470
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 1.27,
|
2977 |
+
"learning_rate": 4.246233979813602e-05,
|
2978 |
+
"loss": 2.9969,
|
2979 |
+
"step": 2475
|
2980 |
+
},
|
2981 |
+
{
|
2982 |
+
"epoch": 1.27,
|
2983 |
+
"learning_rate": 4.243343505441052e-05,
|
2984 |
+
"loss": 3.1595,
|
2985 |
+
"step": 2480
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 1.28,
|
2989 |
+
"learning_rate": 4.2404484875013895e-05,
|
2990 |
+
"loss": 2.8051,
|
2991 |
+
"step": 2485
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 1.28,
|
2995 |
+
"learning_rate": 4.237548933539718e-05,
|
2996 |
+
"loss": 2.8842,
|
2997 |
+
"step": 2490
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 1.28,
|
3001 |
+
"learning_rate": 4.234644851112964e-05,
|
3002 |
+
"loss": 2.9729,
|
3003 |
+
"step": 2495
|
3004 |
+
},
|
3005 |
+
{
|
3006 |
+
"epoch": 1.28,
|
3007 |
+
"learning_rate": 4.231736247789856e-05,
|
3008 |
+
"loss": 2.7805,
|
3009 |
+
"step": 2500
|
3010 |
+
},
|
3011 |
+
{
|
3012 |
+
"epoch": 1.29,
|
3013 |
+
"learning_rate": 4.228823131150904e-05,
|
3014 |
+
"loss": 2.9725,
|
3015 |
+
"step": 2505
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 1.29,
|
3019 |
+
"learning_rate": 4.225905508788382e-05,
|
3020 |
+
"loss": 3.0599,
|
3021 |
+
"step": 2510
|
3022 |
+
},
|
3023 |
+
{
|
3024 |
+
"epoch": 1.29,
|
3025 |
+
"learning_rate": 4.222983388306308e-05,
|
3026 |
+
"loss": 2.7567,
|
3027 |
+
"step": 2515
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 1.29,
|
3031 |
+
"learning_rate": 4.2200567773204194e-05,
|
3032 |
+
"loss": 2.884,
|
3033 |
+
"step": 2520
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 1.3,
|
3037 |
+
"learning_rate": 4.217125683458161e-05,
|
3038 |
+
"loss": 2.8594,
|
3039 |
+
"step": 2525
|
3040 |
+
},
|
3041 |
+
{
|
3042 |
+
"epoch": 1.3,
|
3043 |
+
"learning_rate": 4.214190114358659e-05,
|
3044 |
+
"loss": 2.9515,
|
3045 |
+
"step": 2530
|
3046 |
+
},
|
3047 |
+
{
|
3048 |
+
"epoch": 1.3,
|
3049 |
+
"learning_rate": 4.211250077672704e-05,
|
3050 |
+
"loss": 2.992,
|
3051 |
+
"step": 2535
|
3052 |
+
},
|
3053 |
+
{
|
3054 |
+
"epoch": 1.31,
|
3055 |
+
"learning_rate": 4.208305581062728e-05,
|
3056 |
+
"loss": 3.1784,
|
3057 |
+
"step": 2540
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 1.31,
|
3061 |
+
"learning_rate": 4.205356632202789e-05,
|
3062 |
+
"loss": 3.0196,
|
3063 |
+
"step": 2545
|
3064 |
+
},
|
3065 |
+
{
|
3066 |
+
"epoch": 1.31,
|
3067 |
+
"learning_rate": 4.20240323877855e-05,
|
3068 |
+
"loss": 2.7891,
|
3069 |
+
"step": 2550
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 1.31,
|
3073 |
+
"learning_rate": 4.1994454084872525e-05,
|
3074 |
+
"loss": 2.8974,
|
3075 |
+
"step": 2555
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 1.32,
|
3079 |
+
"learning_rate": 4.196483149037707e-05,
|
3080 |
+
"loss": 2.8219,
|
3081 |
+
"step": 2560
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 1.32,
|
3085 |
+
"learning_rate": 4.1935164681502624e-05,
|
3086 |
+
"loss": 2.8833,
|
3087 |
+
"step": 2565
|
3088 |
+
},
|
3089 |
+
{
|
3090 |
+
"epoch": 1.32,
|
3091 |
+
"learning_rate": 4.190545373556796e-05,
|
3092 |
+
"loss": 3.0166,
|
3093 |
+
"step": 2570
|
3094 |
+
},
|
3095 |
+
{
|
3096 |
+
"epoch": 1.32,
|
3097 |
+
"learning_rate": 4.187569873000684e-05,
|
3098 |
+
"loss": 3.1676,
|
3099 |
+
"step": 2575
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 1.33,
|
3103 |
+
"learning_rate": 4.184589974236788e-05,
|
3104 |
+
"loss": 2.9239,
|
3105 |
+
"step": 2580
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 1.33,
|
3109 |
+
"learning_rate": 4.181605685031432e-05,
|
3110 |
+
"loss": 3.0094,
|
3111 |
+
"step": 2585
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 1.33,
|
3115 |
+
"learning_rate": 4.1786170131623825e-05,
|
3116 |
+
"loss": 3.0235,
|
3117 |
+
"step": 2590
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 1.33,
|
3121 |
+
"learning_rate": 4.1756239664188273e-05,
|
3122 |
+
"loss": 3.058,
|
3123 |
+
"step": 2595
|
3124 |
+
},
|
3125 |
+
{
|
3126 |
+
"epoch": 1.34,
|
3127 |
+
"learning_rate": 4.172626552601358e-05,
|
3128 |
+
"loss": 2.7391,
|
3129 |
+
"step": 2600
|
3130 |
+
},
|
3131 |
+
{
|
3132 |
+
"epoch": 1.34,
|
3133 |
+
"learning_rate": 4.169624779521944e-05,
|
3134 |
+
"loss": 2.9975,
|
3135 |
+
"step": 2605
|
3136 |
+
},
|
3137 |
+
{
|
3138 |
+
"epoch": 1.34,
|
3139 |
+
"learning_rate": 4.1666186550039214e-05,
|
3140 |
+
"loss": 2.7703,
|
3141 |
+
"step": 2610
|
3142 |
+
},
|
3143 |
+
{
|
3144 |
+
"epoch": 1.34,
|
3145 |
+
"learning_rate": 4.163608186881964e-05,
|
3146 |
+
"loss": 2.8288,
|
3147 |
+
"step": 2615
|
3148 |
+
},
|
3149 |
+
{
|
3150 |
+
"epoch": 1.35,
|
3151 |
+
"learning_rate": 4.160593383002066e-05,
|
3152 |
+
"loss": 2.9945,
|
3153 |
+
"step": 2620
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 1.35,
|
3157 |
+
"learning_rate": 4.157574251221521e-05,
|
3158 |
+
"loss": 2.8768,
|
3159 |
+
"step": 2625
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 1.35,
|
3163 |
+
"learning_rate": 4.1545507994089064e-05,
|
3164 |
+
"loss": 2.7161,
|
3165 |
+
"step": 2630
|
3166 |
+
},
|
3167 |
+
{
|
3168 |
+
"epoch": 1.35,
|
3169 |
+
"learning_rate": 4.1515230354440524e-05,
|
3170 |
+
"loss": 3.0821,
|
3171 |
+
"step": 2635
|
3172 |
+
},
|
3173 |
+
{
|
3174 |
+
"epoch": 1.36,
|
3175 |
+
"learning_rate": 4.148490967218033e-05,
|
3176 |
+
"loss": 3.1119,
|
3177 |
+
"step": 2640
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 1.36,
|
3181 |
+
"learning_rate": 4.145454602633137e-05,
|
3182 |
+
"loss": 2.8815,
|
3183 |
+
"step": 2645
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 1.36,
|
3187 |
+
"learning_rate": 4.14241394960285e-05,
|
3188 |
+
"loss": 2.9891,
|
3189 |
+
"step": 2650
|
3190 |
+
},
|
3191 |
+
{
|
3192 |
+
"epoch": 1.36,
|
3193 |
+
"learning_rate": 4.1393690160518384e-05,
|
3194 |
+
"loss": 3.2624,
|
3195 |
+
"step": 2655
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 1.37,
|
3199 |
+
"learning_rate": 4.1363198099159205e-05,
|
3200 |
+
"loss": 2.7588,
|
3201 |
+
"step": 2660
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 1.37,
|
3205 |
+
"learning_rate": 4.1332663391420515e-05,
|
3206 |
+
"loss": 3.0405,
|
3207 |
+
"step": 2665
|
3208 |
+
},
|
3209 |
+
{
|
3210 |
+
"epoch": 1.37,
|
3211 |
+
"learning_rate": 4.130208611688302e-05,
|
3212 |
+
"loss": 2.9254,
|
3213 |
+
"step": 2670
|
3214 |
+
},
|
3215 |
+
{
|
3216 |
+
"epoch": 1.37,
|
3217 |
+
"learning_rate": 4.1271466355238354e-05,
|
3218 |
+
"loss": 2.8499,
|
3219 |
+
"step": 2675
|
3220 |
+
},
|
3221 |
+
{
|
3222 |
+
"epoch": 1.38,
|
3223 |
+
"learning_rate": 4.124080418628888e-05,
|
3224 |
+
"loss": 3.0828,
|
3225 |
+
"step": 2680
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 1.38,
|
3229 |
+
"learning_rate": 4.1210099689947513e-05,
|
3230 |
+
"loss": 2.8524,
|
3231 |
+
"step": 2685
|
3232 |
+
},
|
3233 |
+
{
|
3234 |
+
"epoch": 1.38,
|
3235 |
+
"learning_rate": 4.117935294623743e-05,
|
3236 |
+
"loss": 3.0711,
|
3237 |
+
"step": 2690
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 1.38,
|
3241 |
+
"learning_rate": 4.1148564035291956e-05,
|
3242 |
+
"loss": 3.0343,
|
3243 |
+
"step": 2695
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 1.39,
|
3247 |
+
"learning_rate": 4.1117733037354314e-05,
|
3248 |
+
"loss": 2.8869,
|
3249 |
+
"step": 2700
|
3250 |
+
},
|
3251 |
+
{
|
3252 |
+
"epoch": 1.39,
|
3253 |
+
"learning_rate": 4.1086860032777395e-05,
|
3254 |
+
"loss": 3.0381,
|
3255 |
+
"step": 2705
|
3256 |
+
},
|
3257 |
+
{
|
3258 |
+
"epoch": 1.39,
|
3259 |
+
"learning_rate": 4.105594510202359e-05,
|
3260 |
+
"loss": 2.9049,
|
3261 |
+
"step": 2710
|
3262 |
+
},
|
3263 |
+
{
|
3264 |
+
"epoch": 1.4,
|
3265 |
+
"learning_rate": 4.102498832566454e-05,
|
3266 |
+
"loss": 3.0071,
|
3267 |
+
"step": 2715
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 1.4,
|
3271 |
+
"learning_rate": 4.0993989784380947e-05,
|
3272 |
+
"loss": 2.9955,
|
3273 |
+
"step": 2720
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 1.4,
|
3277 |
+
"learning_rate": 4.096294955896239e-05,
|
3278 |
+
"loss": 2.9568,
|
3279 |
+
"step": 2725
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 1.4,
|
3283 |
+
"learning_rate": 4.093186773030705e-05,
|
3284 |
+
"loss": 2.9727,
|
3285 |
+
"step": 2730
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 1.41,
|
3289 |
+
"learning_rate": 4.090074437942155e-05,
|
3290 |
+
"loss": 3.0501,
|
3291 |
+
"step": 2735
|
3292 |
+
},
|
3293 |
+
{
|
3294 |
+
"epoch": 1.41,
|
3295 |
+
"learning_rate": 4.086957958742075e-05,
|
3296 |
+
"loss": 3.2328,
|
3297 |
+
"step": 2740
|
3298 |
+
},
|
3299 |
+
{
|
3300 |
+
"epoch": 1.41,
|
3301 |
+
"learning_rate": 4.0838373435527494e-05,
|
3302 |
+
"loss": 2.7966,
|
3303 |
+
"step": 2745
|
3304 |
+
},
|
3305 |
+
{
|
3306 |
+
"epoch": 1.41,
|
3307 |
+
"learning_rate": 4.08071260050724e-05,
|
3308 |
+
"loss": 2.8666,
|
3309 |
+
"step": 2750
|
3310 |
+
},
|
3311 |
+
{
|
3312 |
+
"epoch": 1.42,
|
3313 |
+
"learning_rate": 4.077583737749373e-05,
|
3314 |
+
"loss": 2.9765,
|
3315 |
+
"step": 2755
|
3316 |
+
},
|
3317 |
+
{
|
3318 |
+
"epoch": 1.42,
|
3319 |
+
"learning_rate": 4.074450763433704e-05,
|
3320 |
+
"loss": 2.6923,
|
3321 |
+
"step": 2760
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 1.42,
|
3325 |
+
"learning_rate": 4.07131368572551e-05,
|
3326 |
+
"loss": 2.9031,
|
3327 |
+
"step": 2765
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 1.42,
|
3331 |
+
"learning_rate": 4.06817251280076e-05,
|
3332 |
+
"loss": 2.8287,
|
3333 |
+
"step": 2770
|
3334 |
+
},
|
3335 |
+
{
|
3336 |
+
"epoch": 1.43,
|
3337 |
+
"learning_rate": 4.065027252846095e-05,
|
3338 |
+
"loss": 3.1046,
|
3339 |
+
"step": 2775
|
3340 |
+
},
|
3341 |
+
{
|
3342 |
+
"epoch": 1.43,
|
3343 |
+
"learning_rate": 4.0618779140588124e-05,
|
3344 |
+
"loss": 3.0414,
|
3345 |
+
"step": 2780
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 1.43,
|
3349 |
+
"learning_rate": 4.058724504646834e-05,
|
3350 |
+
"loss": 2.8644,
|
3351 |
+
"step": 2785
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 1.43,
|
3355 |
+
"learning_rate": 4.055567032828695e-05,
|
3356 |
+
"loss": 2.9589,
|
3357 |
+
"step": 2790
|
3358 |
+
},
|
3359 |
+
{
|
3360 |
+
"epoch": 1.44,
|
3361 |
+
"learning_rate": 4.052405506833516e-05,
|
3362 |
+
"loss": 2.886,
|
3363 |
+
"step": 2795
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 1.44,
|
3367 |
+
"learning_rate": 4.0492399349009846e-05,
|
3368 |
+
"loss": 2.8026,
|
3369 |
+
"step": 2800
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 1.44,
|
3373 |
+
"learning_rate": 4.0460703252813326e-05,
|
3374 |
+
"loss": 3.0376,
|
3375 |
+
"step": 2805
|
3376 |
+
},
|
3377 |
+
{
|
3378 |
+
"epoch": 1.44,
|
3379 |
+
"learning_rate": 4.042896686235316e-05,
|
3380 |
+
"loss": 2.9751,
|
3381 |
+
"step": 2810
|
3382 |
+
},
|
3383 |
+
{
|
3384 |
+
"epoch": 1.45,
|
3385 |
+
"learning_rate": 4.039719026034191e-05,
|
3386 |
+
"loss": 2.8638,
|
3387 |
+
"step": 2815
|
3388 |
+
},
|
3389 |
+
{
|
3390 |
+
"epoch": 1.45,
|
3391 |
+
"learning_rate": 4.036537352959694e-05,
|
3392 |
+
"loss": 3.0403,
|
3393 |
+
"step": 2820
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 1.45,
|
3397 |
+
"learning_rate": 4.033351675304022e-05,
|
3398 |
+
"loss": 2.8241,
|
3399 |
+
"step": 2825
|
3400 |
+
},
|
3401 |
+
{
|
3402 |
+
"epoch": 1.45,
|
3403 |
+
"learning_rate": 4.030162001369807e-05,
|
3404 |
+
"loss": 3.1196,
|
3405 |
+
"step": 2830
|
3406 |
+
},
|
3407 |
+
{
|
3408 |
+
"epoch": 1.46,
|
3409 |
+
"learning_rate": 4.026968339470096e-05,
|
3410 |
+
"loss": 2.8388,
|
3411 |
+
"step": 2835
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 1.46,
|
3415 |
+
"learning_rate": 4.0237706979283304e-05,
|
3416 |
+
"loss": 2.9974,
|
3417 |
+
"step": 2840
|
3418 |
+
},
|
3419 |
+
{
|
3420 |
+
"epoch": 1.46,
|
3421 |
+
"learning_rate": 4.020569085078324e-05,
|
3422 |
+
"loss": 3.0178,
|
3423 |
+
"step": 2845
|
3424 |
+
},
|
3425 |
+
{
|
3426 |
+
"epoch": 1.46,
|
3427 |
+
"learning_rate": 4.0173635092642386e-05,
|
3428 |
+
"loss": 3.0166,
|
3429 |
+
"step": 2850
|
3430 |
+
},
|
3431 |
+
{
|
3432 |
+
"epoch": 1.47,
|
3433 |
+
"learning_rate": 4.014153978840567e-05,
|
3434 |
+
"loss": 3.0657,
|
3435 |
+
"step": 2855
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 1.47,
|
3439 |
+
"learning_rate": 4.010940502172108e-05,
|
3440 |
+
"loss": 3.0229,
|
3441 |
+
"step": 2860
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 1.47,
|
3445 |
+
"learning_rate": 4.007723087633943e-05,
|
3446 |
+
"loss": 2.5904,
|
3447 |
+
"step": 2865
|
3448 |
+
},
|
3449 |
+
{
|
3450 |
+
"epoch": 1.47,
|
3451 |
+
"learning_rate": 4.0045017436114205e-05,
|
3452 |
+
"loss": 2.8607,
|
3453 |
+
"step": 2870
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 1.48,
|
3457 |
+
"learning_rate": 4.001276478500127e-05,
|
3458 |
+
"loss": 3.0797,
|
3459 |
+
"step": 2875
|
3460 |
+
},
|
3461 |
+
{
|
3462 |
+
"epoch": 1.48,
|
3463 |
+
"learning_rate": 3.998047300705868e-05,
|
3464 |
+
"loss": 2.9475,
|
3465 |
+
"step": 2880
|
3466 |
+
},
|
3467 |
+
{
|
3468 |
+
"epoch": 1.48,
|
3469 |
+
"learning_rate": 3.9948142186446486e-05,
|
3470 |
+
"loss": 2.7829,
|
3471 |
+
"step": 2885
|
3472 |
+
},
|
3473 |
+
{
|
3474 |
+
"epoch": 1.49,
|
3475 |
+
"learning_rate": 3.991577240742649e-05,
|
3476 |
+
"loss": 3.0715,
|
3477 |
+
"step": 2890
|
3478 |
+
},
|
3479 |
+
{
|
3480 |
+
"epoch": 1.49,
|
3481 |
+
"learning_rate": 3.9883363754362004e-05,
|
3482 |
+
"loss": 3.0126,
|
3483 |
+
"step": 2895
|
3484 |
+
},
|
3485 |
+
{
|
3486 |
+
"epoch": 1.49,
|
3487 |
+
"learning_rate": 3.985091631171769e-05,
|
3488 |
+
"loss": 3.0835,
|
3489 |
+
"step": 2900
|
3490 |
+
},
|
3491 |
+
{
|
3492 |
+
"epoch": 1.49,
|
3493 |
+
"learning_rate": 3.981843016405927e-05,
|
3494 |
+
"loss": 2.9109,
|
3495 |
+
"step": 2905
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 1.5,
|
3499 |
+
"learning_rate": 3.978590539605338e-05,
|
3500 |
+
"loss": 3.0058,
|
3501 |
+
"step": 2910
|
3502 |
+
},
|
3503 |
+
{
|
3504 |
+
"epoch": 1.5,
|
3505 |
+
"learning_rate": 3.975334209246727e-05,
|
3506 |
+
"loss": 2.7376,
|
3507 |
+
"step": 2915
|
3508 |
+
},
|
3509 |
+
{
|
3510 |
+
"epoch": 1.5,
|
3511 |
+
"learning_rate": 3.972074033816866e-05,
|
3512 |
+
"loss": 2.7173,
|
3513 |
+
"step": 2920
|
3514 |
+
},
|
3515 |
+
{
|
3516 |
+
"epoch": 1.5,
|
3517 |
+
"learning_rate": 3.968810021812544e-05,
|
3518 |
+
"loss": 2.8642,
|
3519 |
+
"step": 2925
|
3520 |
+
},
|
3521 |
+
{
|
3522 |
+
"epoch": 1.51,
|
3523 |
+
"learning_rate": 3.965542181740553e-05,
|
3524 |
+
"loss": 2.8643,
|
3525 |
+
"step": 2930
|
3526 |
+
},
|
3527 |
+
{
|
3528 |
+
"epoch": 1.51,
|
3529 |
+
"learning_rate": 3.9622705221176596e-05,
|
3530 |
+
"loss": 3.1752,
|
3531 |
+
"step": 2935
|
3532 |
+
},
|
3533 |
+
{
|
3534 |
+
"epoch": 1.51,
|
3535 |
+
"learning_rate": 3.958995051470585e-05,
|
3536 |
+
"loss": 2.7045,
|
3537 |
+
"step": 2940
|
3538 |
+
},
|
3539 |
+
{
|
3540 |
+
"epoch": 1.51,
|
3541 |
+
"learning_rate": 3.955715778335984e-05,
|
3542 |
+
"loss": 3.0828,
|
3543 |
+
"step": 2945
|
3544 |
+
},
|
3545 |
+
{
|
3546 |
+
"epoch": 1.52,
|
3547 |
+
"learning_rate": 3.952432711260421e-05,
|
3548 |
+
"loss": 2.982,
|
3549 |
+
"step": 2950
|
3550 |
+
},
|
3551 |
+
{
|
3552 |
+
"epoch": 1.52,
|
3553 |
+
"learning_rate": 3.949145858800348e-05,
|
3554 |
+
"loss": 2.9762,
|
3555 |
+
"step": 2955
|
3556 |
+
},
|
3557 |
+
{
|
3558 |
+
"epoch": 1.52,
|
3559 |
+
"learning_rate": 3.945855229522084e-05,
|
3560 |
+
"loss": 3.1026,
|
3561 |
+
"step": 2960
|
3562 |
+
},
|
3563 |
+
{
|
3564 |
+
"epoch": 1.52,
|
3565 |
+
"learning_rate": 3.942560832001789e-05,
|
3566 |
+
"loss": 3.1225,
|
3567 |
+
"step": 2965
|
3568 |
+
},
|
3569 |
+
{
|
3570 |
+
"epoch": 1.53,
|
3571 |
+
"learning_rate": 3.9392626748254456e-05,
|
3572 |
+
"loss": 3.0462,
|
3573 |
+
"step": 2970
|
3574 |
+
},
|
3575 |
+
{
|
3576 |
+
"epoch": 1.53,
|
3577 |
+
"learning_rate": 3.9359607665888346e-05,
|
3578 |
+
"loss": 2.8954,
|
3579 |
+
"step": 2975
|
3580 |
+
},
|
3581 |
+
{
|
3582 |
+
"epoch": 1.53,
|
3583 |
+
"learning_rate": 3.932655115897513e-05,
|
3584 |
+
"loss": 2.8361,
|
3585 |
+
"step": 2980
|
3586 |
+
},
|
3587 |
+
{
|
3588 |
+
"epoch": 1.53,
|
3589 |
+
"learning_rate": 3.92934573136679e-05,
|
3590 |
+
"loss": 3.1644,
|
3591 |
+
"step": 2985
|
3592 |
+
},
|
3593 |
+
{
|
3594 |
+
"epoch": 1.54,
|
3595 |
+
"learning_rate": 3.9260326216217105e-05,
|
3596 |
+
"loss": 3.0226,
|
3597 |
+
"step": 2990
|
3598 |
+
},
|
3599 |
+
{
|
3600 |
+
"epoch": 1.54,
|
3601 |
+
"learning_rate": 3.922715795297022e-05,
|
3602 |
+
"loss": 3.0285,
|
3603 |
+
"step": 2995
|
3604 |
+
},
|
3605 |
+
{
|
3606 |
+
"epoch": 1.54,
|
3607 |
+
"learning_rate": 3.919395261037163e-05,
|
3608 |
+
"loss": 3.0582,
|
3609 |
+
"step": 3000
|
3610 |
+
}
|
3611 |
+
],
|
3612 |
+
"logging_steps": 5,
|
3613 |
+
"max_steps": 9730,
|
3614 |
+
"num_input_tokens_seen": 0,
|
3615 |
+
"num_train_epochs": 5,
|
3616 |
+
"save_steps": 300,
|
3617 |
+
"total_flos": 3.532887327763661e+17,
|
3618 |
+
"train_batch_size": 1,
|
3619 |
+
"trial_name": null,
|
3620 |
+
"trial_params": null
|
3621 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:323d9e0822218e186c546ec4c60df0ed1248fa085eb7c28291141ebefc901909
|
3 |
+
size 4411
|
checkpoint-5700/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chinese-llama-2-13b
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-5700/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chinese-llama-2-13b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-5700/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba04a7daacacfacc817fe69bb8c656493b0a045ff1038b16883302895a7d6d9b
|
3 |
+
size 26235704
|
checkpoint-5700/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e072f48a219127995f15952ff64e4319a371d5884bbec99fff004ea2a6469b8b
|
3 |
+
size 52562821
|
checkpoint-5700/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e15c5a1caf73eeeceb07f03c9bff0411cbad68abca1aaab9f035e259b6f7cd72
|
3 |
+
size 14575
|
checkpoint-5700/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e9f64e34e4a841e4945659fab38b8bb044aeab66b91faeb1449ee2af4d76f3c
|
3 |
+
size 627
|
checkpoint-5700/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-5700/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c
|
3 |
+
size 844403
|
checkpoint-5700/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": true,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"padding_side": "right",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"split_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false,
|
51 |
+
"use_fast": false
|
52 |
+
}
|
checkpoint-5700/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5700/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:323d9e0822218e186c546ec4c60df0ed1248fa085eb7c28291141ebefc901909
|
3 |
+
size 4411
|
checkpoint-6000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chinese-llama-2-13b
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-6000/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chinese-llama-2-13b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-6000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4ae5231d7e747a12edf2dfd36253d3fe17e06fe9f16736d8c50b500f60b15c9
|
3 |
+
size 26235704
|
checkpoint-6000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bccbd32792466aa50ee0083952e5e814e0487abc096214af205f2b4572f4273
|
3 |
+
size 52562821
|
checkpoint-6000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5706c03c7d4ca0f7dbfb0b7eeb33f6f375a36d2009dc90d8a47df81018d32de9
|
3 |
+
size 14575
|
checkpoint-6000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6a0f73234cebce60d497551f3d4a7b125ec31919e852ba48a3aa018ef75e750
|
3 |
+
size 627
|
checkpoint-6000/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
checkpoint-6000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3b8844863b200dfcca971db228e96ce388290dfcf72c15d7a9d2f604bac787c
|
3 |
+
size 844403
|
checkpoint-6000/tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<pad>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"legacy": true,
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"padding_side": "right",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"spaces_between_special_tokens": false,
|
47 |
+
"split_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false,
|
51 |
+
"use_fast": false
|
52 |
+
}
|
checkpoint-6000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:323d9e0822218e186c546ec4c60df0ed1248fa085eb7c28291141ebefc901909
|
3 |
+
size 4411
|
checkpoint-900/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: ../chinese-llama-2-13b
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-900/adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "../chinese-llama-2-13b",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
checkpoint-900/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98ca6aaeb82bd2c262e55d7a695b601dbb4d2d77fc71efbbe46ecd5379f731b1
|
3 |
+
size 26235704
|
checkpoint-900/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e398c66a8abe776f171389c4492424a5a88ecd160face0025e1892cc6d40e48
|
3 |
+
size 52562821
|
checkpoint-900/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:febb51449cb274984243e15b6fc03516132272000e777a4034091445fbbc808a
|
3 |
+
size 14575
|
checkpoint-900/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f28570e5762c8420e873111f5f50d0ef722ad58fbef6f3220c583f2172dbb3
|
3 |
+
size 627
|