ToBeWithYou
commited on
Commit
•
924e54c
1
Parent(s):
9a0c2e6
output_ESFP
Browse files- README.md +204 -0
- adapter_config.json +32 -0
- adapter_model.bin +3 -0
- checkpoint-1000/README.md +204 -0
- checkpoint-1000/adapter_config.json +32 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +6 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +35 -0
- checkpoint-1000/trainer_state.json +0 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-500/README.md +204 -0
- checkpoint-500/adapter_config.json +32 -0
- checkpoint-500/adapter_model.bin +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +6 -0
- checkpoint-500/tokenizer.model +3 -0
- checkpoint-500/tokenizer_config.json +35 -0
- checkpoint-500/trainer_state.json +3016 -0
- checkpoint-500/training_args.bin +3 -0
- runs/Feb19_03-58-39_26c175d8c062/events.out.tfevents.1708315257.26c175d8c062.3854.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: davidkim205/komt-llama2-7b-v1
|
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
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "davidkim205/komt-llama2-7b-v1",
|
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": 32,
|
13 |
+
"lora_dropout": 0.05,
|
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 |
+
"up_proj",
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24db4e0aef7cb0345d876fbc23678f626d37b9a7bdf983cec8f642e44ad87f79
|
3 |
+
size 80115210
|
checkpoint-1000/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: davidkim205/komt-llama2-7b-v1
|
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-1000/adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "davidkim205/komt-llama2-7b-v1",
|
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": 32,
|
13 |
+
"lora_dropout": 0.05,
|
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 |
+
"up_proj",
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24db4e0aef7cb0345d876fbc23678f626d37b9a7bdf983cec8f642e44ad87f79
|
3 |
+
size 80115210
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8b0e39f09d04c63270d456d58f733d0586fee64fa493451b479b9e23c845b27
|
3 |
+
size 160284754
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64022ca0ff54fbba83b3e5a973852e1e7e8c61b553a7c2b63f129035447a8ddf
|
3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4077036d99500a708f700f75da24d51b5300e184ad35fda49dc5a4df5596cca2
|
3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "</s>"
|
6 |
+
}
|
checkpoint-1000/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-1000/tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81c62a959e27e1dcebe486f2a3497d27f677eab0ef5a5ac731fd0ff4edfce99a
|
3 |
+
size 4408
|
checkpoint-500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: davidkim205/komt-llama2-7b-v1
|
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-500/adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "davidkim205/komt-llama2-7b-v1",
|
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": 32,
|
13 |
+
"lora_dropout": 0.05,
|
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 |
+
"up_proj",
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj",
|
26 |
+
"k_proj",
|
27 |
+
"q_proj",
|
28 |
+
"gate_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM",
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
checkpoint-500/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de4d462b9cc226c9496aa675404facf7ac3a1f9887449df393a480bc2100be6
|
3 |
+
size 80115210
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7626d17ccec98df27f0fd5304471445231e96ea0dfa38d2e1b698e4d2ad6057f
|
3 |
+
size 160284754
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b3b6afe714f8199d1cd1ec008928f5fa3fb2801bde078e02d83ede42e58c7a9
|
3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:851985144c695da0ecd2f9cfa211702d108af50f12edfe1295478f6c8d9c5e36
|
3 |
+
size 1064
|
checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "</s>"
|
6 |
+
}
|
checkpoint-500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,3016 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.329113924050633,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.0641,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.03,
|
18 |
+
"learning_rate": 0.0001,
|
19 |
+
"loss": 0.9056,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.04,
|
24 |
+
"learning_rate": 9.999975227016531e-05,
|
25 |
+
"loss": 0.9593,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.05,
|
30 |
+
"learning_rate": 9.999900908311602e-05,
|
31 |
+
"loss": 0.973,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.06,
|
36 |
+
"learning_rate": 9.999777044621652e-05,
|
37 |
+
"loss": 1.0652,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.08,
|
42 |
+
"learning_rate": 9.999603637174071e-05,
|
43 |
+
"loss": 0.9212,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09,
|
48 |
+
"learning_rate": 9.999380687687188e-05,
|
49 |
+
"loss": 0.899,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.1,
|
54 |
+
"learning_rate": 9.999108198370249e-05,
|
55 |
+
"loss": 0.7079,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.11,
|
60 |
+
"learning_rate": 9.998786171923407e-05,
|
61 |
+
"loss": 0.7139,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.13,
|
66 |
+
"learning_rate": 9.998414611537681e-05,
|
67 |
+
"loss": 0.8258,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.14,
|
72 |
+
"learning_rate": 9.997993520894937e-05,
|
73 |
+
"loss": 0.7415,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.15,
|
78 |
+
"learning_rate": 9.997522904167844e-05,
|
79 |
+
"loss": 0.8233,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.16,
|
84 |
+
"learning_rate": 9.997002766019832e-05,
|
85 |
+
"loss": 0.8698,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.18,
|
90 |
+
"learning_rate": 9.996433111605052e-05,
|
91 |
+
"loss": 0.6354,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.19,
|
96 |
+
"learning_rate": 9.99581394656832e-05,
|
97 |
+
"loss": 0.6136,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.2,
|
102 |
+
"learning_rate": 9.995145277045061e-05,
|
103 |
+
"loss": 0.7363,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.22,
|
108 |
+
"learning_rate": 9.994427109661253e-05,
|
109 |
+
"loss": 0.6065,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.23,
|
114 |
+
"learning_rate": 9.993659451533353e-05,
|
115 |
+
"loss": 0.6152,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.24,
|
120 |
+
"learning_rate": 9.992842310268233e-05,
|
121 |
+
"loss": 0.7021,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.25,
|
126 |
+
"learning_rate": 9.991975693963107e-05,
|
127 |
+
"loss": 0.5468,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.27,
|
132 |
+
"learning_rate": 9.99105961120544e-05,
|
133 |
+
"loss": 0.5437,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.28,
|
138 |
+
"learning_rate": 9.990094071072877e-05,
|
139 |
+
"loss": 0.6458,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.29,
|
144 |
+
"learning_rate": 9.989079083133139e-05,
|
145 |
+
"loss": 0.6744,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.3,
|
150 |
+
"learning_rate": 9.988014657443941e-05,
|
151 |
+
"loss": 0.5592,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.32,
|
156 |
+
"learning_rate": 9.986900804552878e-05,
|
157 |
+
"loss": 0.5351,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.33,
|
162 |
+
"learning_rate": 9.985737535497337e-05,
|
163 |
+
"loss": 0.5705,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.34,
|
168 |
+
"learning_rate": 9.984524861804376e-05,
|
169 |
+
"loss": 0.5696,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.35,
|
174 |
+
"learning_rate": 9.983262795490613e-05,
|
175 |
+
"loss": 0.588,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.37,
|
180 |
+
"learning_rate": 9.981951349062106e-05,
|
181 |
+
"loss": 0.627,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.38,
|
186 |
+
"learning_rate": 9.980590535514233e-05,
|
187 |
+
"loss": 0.5702,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.39,
|
192 |
+
"learning_rate": 9.979180368331558e-05,
|
193 |
+
"loss": 0.5907,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.41,
|
198 |
+
"learning_rate": 9.9777208614877e-05,
|
199 |
+
"loss": 0.4817,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.42,
|
204 |
+
"learning_rate": 9.976212029445194e-05,
|
205 |
+
"loss": 0.5789,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.43,
|
210 |
+
"learning_rate": 9.97465388715535e-05,
|
211 |
+
"loss": 0.5108,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.44,
|
216 |
+
"learning_rate": 9.9730464500581e-05,
|
217 |
+
"loss": 0.557,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.46,
|
222 |
+
"learning_rate": 9.971389734081848e-05,
|
223 |
+
"loss": 0.5771,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.47,
|
228 |
+
"learning_rate": 9.969683755643317e-05,
|
229 |
+
"loss": 0.5524,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.48,
|
234 |
+
"learning_rate": 9.967928531647374e-05,
|
235 |
+
"loss": 0.5648,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.49,
|
240 |
+
"learning_rate": 9.966124079486872e-05,
|
241 |
+
"loss": 0.4951,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.51,
|
246 |
+
"learning_rate": 9.96427041704248e-05,
|
247 |
+
"loss": 0.5516,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.52,
|
252 |
+
"learning_rate": 9.962367562682496e-05,
|
253 |
+
"loss": 0.5582,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.53,
|
258 |
+
"learning_rate": 9.960415535262671e-05,
|
259 |
+
"loss": 0.5352,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.54,
|
264 |
+
"learning_rate": 9.958414354126022e-05,
|
265 |
+
"loss": 0.737,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.56,
|
270 |
+
"learning_rate": 9.956364039102642e-05,
|
271 |
+
"loss": 0.4762,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.57,
|
276 |
+
"learning_rate": 9.954264610509497e-05,
|
277 |
+
"loss": 0.4896,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.58,
|
282 |
+
"learning_rate": 9.952116089150232e-05,
|
283 |
+
"loss": 0.4975,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.59,
|
288 |
+
"learning_rate": 9.94991849631496e-05,
|
289 |
+
"loss": 0.5646,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.61,
|
294 |
+
"learning_rate": 9.947671853780054e-05,
|
295 |
+
"loss": 0.5599,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.62,
|
300 |
+
"learning_rate": 9.94537618380793e-05,
|
301 |
+
"loss": 0.5255,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.63,
|
306 |
+
"learning_rate": 9.943031509146825e-05,
|
307 |
+
"loss": 0.5971,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.65,
|
312 |
+
"learning_rate": 9.940637853030572e-05,
|
313 |
+
"loss": 0.5932,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.66,
|
318 |
+
"learning_rate": 9.938195239178374e-05,
|
319 |
+
"loss": 0.5979,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.67,
|
324 |
+
"learning_rate": 9.935703691794565e-05,
|
325 |
+
"loss": 0.496,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.68,
|
330 |
+
"learning_rate": 9.933163235568367e-05,
|
331 |
+
"loss": 0.5341,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.7,
|
336 |
+
"learning_rate": 9.930573895673657e-05,
|
337 |
+
"loss": 0.4661,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.71,
|
342 |
+
"learning_rate": 9.927935697768698e-05,
|
343 |
+
"loss": 0.6222,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.72,
|
348 |
+
"learning_rate": 9.925248667995907e-05,
|
349 |
+
"loss": 0.5015,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.73,
|
354 |
+
"learning_rate": 9.922512832981584e-05,
|
355 |
+
"loss": 0.654,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.75,
|
360 |
+
"learning_rate": 9.919728219835643e-05,
|
361 |
+
"loss": 0.4863,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.76,
|
366 |
+
"learning_rate": 9.916894856151357e-05,
|
367 |
+
"loss": 0.6024,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.77,
|
372 |
+
"learning_rate": 9.914012770005072e-05,
|
373 |
+
"loss": 0.4767,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.78,
|
378 |
+
"learning_rate": 9.91108198995594e-05,
|
379 |
+
"loss": 0.5065,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.8,
|
384 |
+
"learning_rate": 9.908102545045625e-05,
|
385 |
+
"loss": 0.6043,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.81,
|
390 |
+
"learning_rate": 9.905074464798024e-05,
|
391 |
+
"loss": 0.6733,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.82,
|
396 |
+
"learning_rate": 9.901997779218967e-05,
|
397 |
+
"loss": 0.522,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.84,
|
402 |
+
"learning_rate": 9.898872518795932e-05,
|
403 |
+
"loss": 0.5205,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 0.85,
|
408 |
+
"learning_rate": 9.895698714497724e-05,
|
409 |
+
"loss": 0.5216,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.86,
|
414 |
+
"learning_rate": 9.892476397774186e-05,
|
415 |
+
"loss": 0.6014,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.87,
|
420 |
+
"learning_rate": 9.889205600555877e-05,
|
421 |
+
"loss": 0.5321,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.89,
|
426 |
+
"learning_rate": 9.885886355253758e-05,
|
427 |
+
"loss": 0.545,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.9,
|
432 |
+
"learning_rate": 9.882518694758875e-05,
|
433 |
+
"loss": 0.4868,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.91,
|
438 |
+
"learning_rate": 9.879102652442024e-05,
|
439 |
+
"loss": 0.5366,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.92,
|
444 |
+
"learning_rate": 9.875638262153431e-05,
|
445 |
+
"loss": 0.5805,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.94,
|
450 |
+
"learning_rate": 9.872125558222409e-05,
|
451 |
+
"loss": 0.585,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.95,
|
456 |
+
"learning_rate": 9.868564575457023e-05,
|
457 |
+
"loss": 0.6058,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.96,
|
462 |
+
"learning_rate": 9.864955349143734e-05,
|
463 |
+
"loss": 0.4402,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.97,
|
468 |
+
"learning_rate": 9.861297915047069e-05,
|
469 |
+
"loss": 0.5349,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.99,
|
474 |
+
"learning_rate": 9.857592309409247e-05,
|
475 |
+
"loss": 0.5443,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.0,
|
480 |
+
"learning_rate": 9.853838568949831e-05,
|
481 |
+
"loss": 0.6198,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.01,
|
486 |
+
"learning_rate": 9.850036730865364e-05,
|
487 |
+
"loss": 0.6008,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.03,
|
492 |
+
"learning_rate": 9.846186832828989e-05,
|
493 |
+
"loss": 0.4168,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.04,
|
498 |
+
"learning_rate": 9.842288912990096e-05,
|
499 |
+
"loss": 0.4738,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.05,
|
504 |
+
"learning_rate": 9.838343009973925e-05,
|
505 |
+
"loss": 0.5146,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 1.06,
|
510 |
+
"learning_rate": 9.83434916288119e-05,
|
511 |
+
"loss": 0.481,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.08,
|
516 |
+
"learning_rate": 9.830307411287695e-05,
|
517 |
+
"loss": 0.5005,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 1.09,
|
522 |
+
"learning_rate": 9.82621779524394e-05,
|
523 |
+
"loss": 0.4643,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 1.1,
|
528 |
+
"learning_rate": 9.822080355274719e-05,
|
529 |
+
"loss": 0.5201,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 1.11,
|
534 |
+
"learning_rate": 9.817895132378725e-05,
|
535 |
+
"loss": 0.4168,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 1.13,
|
540 |
+
"learning_rate": 9.813662168028144e-05,
|
541 |
+
"loss": 0.4409,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.14,
|
546 |
+
"learning_rate": 9.809381504168234e-05,
|
547 |
+
"loss": 0.4593,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 1.15,
|
552 |
+
"learning_rate": 9.805053183216923e-05,
|
553 |
+
"loss": 0.4755,
|
554 |
+
"step": 91
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 1.16,
|
558 |
+
"learning_rate": 9.800677248064382e-05,
|
559 |
+
"loss": 0.4565,
|
560 |
+
"step": 92
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 1.18,
|
564 |
+
"learning_rate": 9.796253742072596e-05,
|
565 |
+
"loss": 0.4718,
|
566 |
+
"step": 93
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 1.19,
|
570 |
+
"learning_rate": 9.791782709074944e-05,
|
571 |
+
"loss": 0.4884,
|
572 |
+
"step": 94
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 1.2,
|
576 |
+
"learning_rate": 9.787264193375753e-05,
|
577 |
+
"loss": 0.5204,
|
578 |
+
"step": 95
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 1.22,
|
582 |
+
"learning_rate": 9.782698239749873e-05,
|
583 |
+
"loss": 0.4807,
|
584 |
+
"step": 96
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.23,
|
588 |
+
"learning_rate": 9.778084893442218e-05,
|
589 |
+
"loss": 0.4089,
|
590 |
+
"step": 97
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.24,
|
594 |
+
"learning_rate": 9.77342420016733e-05,
|
595 |
+
"loss": 0.4371,
|
596 |
+
"step": 98
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 1.25,
|
600 |
+
"learning_rate": 9.768716206108921e-05,
|
601 |
+
"loss": 0.4959,
|
602 |
+
"step": 99
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 1.27,
|
606 |
+
"learning_rate": 9.763960957919413e-05,
|
607 |
+
"loss": 0.4446,
|
608 |
+
"step": 100
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 1.28,
|
612 |
+
"learning_rate": 9.759158502719481e-05,
|
613 |
+
"loss": 0.4576,
|
614 |
+
"step": 101
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 1.29,
|
618 |
+
"learning_rate": 9.754308888097583e-05,
|
619 |
+
"loss": 0.3678,
|
620 |
+
"step": 102
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 1.3,
|
624 |
+
"learning_rate": 9.749412162109485e-05,
|
625 |
+
"loss": 0.3743,
|
626 |
+
"step": 103
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.32,
|
630 |
+
"learning_rate": 9.744468373277797e-05,
|
631 |
+
"loss": 0.4571,
|
632 |
+
"step": 104
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 1.33,
|
636 |
+
"learning_rate": 9.739477570591473e-05,
|
637 |
+
"loss": 0.3944,
|
638 |
+
"step": 105
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 1.34,
|
642 |
+
"learning_rate": 9.734439803505345e-05,
|
643 |
+
"loss": 0.3904,
|
644 |
+
"step": 106
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 1.35,
|
648 |
+
"learning_rate": 9.729355121939621e-05,
|
649 |
+
"loss": 0.494,
|
650 |
+
"step": 107
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 1.37,
|
654 |
+
"learning_rate": 9.724223576279395e-05,
|
655 |
+
"loss": 0.4904,
|
656 |
+
"step": 108
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 1.38,
|
660 |
+
"learning_rate": 9.719045217374143e-05,
|
661 |
+
"loss": 0.3727,
|
662 |
+
"step": 109
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 1.39,
|
666 |
+
"learning_rate": 9.713820096537225e-05,
|
667 |
+
"loss": 0.4916,
|
668 |
+
"step": 110
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 1.41,
|
672 |
+
"learning_rate": 9.708548265545375e-05,
|
673 |
+
"loss": 0.5386,
|
674 |
+
"step": 111
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 1.42,
|
678 |
+
"learning_rate": 9.703229776638185e-05,
|
679 |
+
"loss": 0.3815,
|
680 |
+
"step": 112
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 1.43,
|
684 |
+
"learning_rate": 9.697864682517592e-05,
|
685 |
+
"loss": 0.4243,
|
686 |
+
"step": 113
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 1.44,
|
690 |
+
"learning_rate": 9.692453036347351e-05,
|
691 |
+
"loss": 0.5205,
|
692 |
+
"step": 114
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 1.46,
|
696 |
+
"learning_rate": 9.686994891752508e-05,
|
697 |
+
"loss": 0.5158,
|
698 |
+
"step": 115
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 1.47,
|
702 |
+
"learning_rate": 9.681490302818874e-05,
|
703 |
+
"loss": 0.4424,
|
704 |
+
"step": 116
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 1.48,
|
708 |
+
"learning_rate": 9.675939324092486e-05,
|
709 |
+
"loss": 0.5825,
|
710 |
+
"step": 117
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 1.49,
|
714 |
+
"learning_rate": 9.670342010579065e-05,
|
715 |
+
"loss": 0.6082,
|
716 |
+
"step": 118
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 1.51,
|
720 |
+
"learning_rate": 9.664698417743475e-05,
|
721 |
+
"loss": 0.3913,
|
722 |
+
"step": 119
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 1.52,
|
726 |
+
"learning_rate": 9.659008601509168e-05,
|
727 |
+
"loss": 0.4178,
|
728 |
+
"step": 120
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 1.53,
|
732 |
+
"learning_rate": 9.653272618257631e-05,
|
733 |
+
"loss": 0.5543,
|
734 |
+
"step": 121
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.54,
|
738 |
+
"learning_rate": 9.647490524827834e-05,
|
739 |
+
"loss": 0.4127,
|
740 |
+
"step": 122
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 1.56,
|
744 |
+
"learning_rate": 9.641662378515659e-05,
|
745 |
+
"loss": 0.4079,
|
746 |
+
"step": 123
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 1.57,
|
750 |
+
"learning_rate": 9.635788237073334e-05,
|
751 |
+
"loss": 0.4811,
|
752 |
+
"step": 124
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 1.58,
|
756 |
+
"learning_rate": 9.629868158708861e-05,
|
757 |
+
"loss": 0.4229,
|
758 |
+
"step": 125
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 1.59,
|
762 |
+
"learning_rate": 9.623902202085444e-05,
|
763 |
+
"loss": 0.4332,
|
764 |
+
"step": 126
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 1.61,
|
768 |
+
"learning_rate": 9.617890426320899e-05,
|
769 |
+
"loss": 0.4451,
|
770 |
+
"step": 127
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 1.62,
|
774 |
+
"learning_rate": 9.611832890987076e-05,
|
775 |
+
"loss": 0.4018,
|
776 |
+
"step": 128
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 1.63,
|
780 |
+
"learning_rate": 9.605729656109265e-05,
|
781 |
+
"loss": 0.4175,
|
782 |
+
"step": 129
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 1.65,
|
786 |
+
"learning_rate": 9.599580782165598e-05,
|
787 |
+
"loss": 0.4841,
|
788 |
+
"step": 130
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 1.66,
|
792 |
+
"learning_rate": 9.593386330086458e-05,
|
793 |
+
"loss": 0.4353,
|
794 |
+
"step": 131
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 1.67,
|
798 |
+
"learning_rate": 9.587146361253868e-05,
|
799 |
+
"loss": 0.4262,
|
800 |
+
"step": 132
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 1.68,
|
804 |
+
"learning_rate": 9.580860937500884e-05,
|
805 |
+
"loss": 0.4572,
|
806 |
+
"step": 133
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.7,
|
810 |
+
"learning_rate": 9.57453012111099e-05,
|
811 |
+
"loss": 0.4856,
|
812 |
+
"step": 134
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 1.71,
|
816 |
+
"learning_rate": 9.568153974817464e-05,
|
817 |
+
"loss": 0.4451,
|
818 |
+
"step": 135
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 1.72,
|
822 |
+
"learning_rate": 9.561732561802778e-05,
|
823 |
+
"loss": 0.5691,
|
824 |
+
"step": 136
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 1.73,
|
828 |
+
"learning_rate": 9.555265945697953e-05,
|
829 |
+
"loss": 0.3989,
|
830 |
+
"step": 137
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 1.75,
|
834 |
+
"learning_rate": 9.548754190581939e-05,
|
835 |
+
"loss": 0.4935,
|
836 |
+
"step": 138
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 1.76,
|
840 |
+
"learning_rate": 9.542197360980978e-05,
|
841 |
+
"loss": 0.4637,
|
842 |
+
"step": 139
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 1.77,
|
846 |
+
"learning_rate": 9.53559552186796e-05,
|
847 |
+
"loss": 0.4895,
|
848 |
+
"step": 140
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 1.78,
|
852 |
+
"learning_rate": 9.528948738661784e-05,
|
853 |
+
"loss": 0.4625,
|
854 |
+
"step": 141
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 1.8,
|
858 |
+
"learning_rate": 9.522257077226717e-05,
|
859 |
+
"loss": 0.4409,
|
860 |
+
"step": 142
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 1.81,
|
864 |
+
"learning_rate": 9.51552060387172e-05,
|
865 |
+
"loss": 0.4123,
|
866 |
+
"step": 143
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 1.82,
|
870 |
+
"learning_rate": 9.508739385349812e-05,
|
871 |
+
"loss": 0.4801,
|
872 |
+
"step": 144
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 1.84,
|
876 |
+
"learning_rate": 9.501913488857399e-05,
|
877 |
+
"loss": 0.3965,
|
878 |
+
"step": 145
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 1.85,
|
882 |
+
"learning_rate": 9.49504298203361e-05,
|
883 |
+
"loss": 0.4027,
|
884 |
+
"step": 146
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.86,
|
888 |
+
"learning_rate": 9.488127932959625e-05,
|
889 |
+
"loss": 0.4779,
|
890 |
+
"step": 147
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 1.87,
|
894 |
+
"learning_rate": 9.481168410158003e-05,
|
895 |
+
"loss": 0.4168,
|
896 |
+
"step": 148
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 1.89,
|
900 |
+
"learning_rate": 9.474164482592002e-05,
|
901 |
+
"loss": 0.4352,
|
902 |
+
"step": 149
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 1.9,
|
906 |
+
"learning_rate": 9.467116219664894e-05,
|
907 |
+
"loss": 0.5395,
|
908 |
+
"step": 150
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 1.91,
|
912 |
+
"learning_rate": 9.460023691219277e-05,
|
913 |
+
"loss": 0.5874,
|
914 |
+
"step": 151
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 1.92,
|
918 |
+
"learning_rate": 9.45288696753639e-05,
|
919 |
+
"loss": 0.5014,
|
920 |
+
"step": 152
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 1.94,
|
924 |
+
"learning_rate": 9.445706119335407e-05,
|
925 |
+
"loss": 0.4106,
|
926 |
+
"step": 153
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 1.95,
|
930 |
+
"learning_rate": 9.438481217772744e-05,
|
931 |
+
"loss": 0.4717,
|
932 |
+
"step": 154
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 1.96,
|
936 |
+
"learning_rate": 9.431212334441343e-05,
|
937 |
+
"loss": 0.4105,
|
938 |
+
"step": 155
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 1.97,
|
942 |
+
"learning_rate": 9.423899541369978e-05,
|
943 |
+
"loss": 0.4421,
|
944 |
+
"step": 156
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 1.99,
|
948 |
+
"learning_rate": 9.41654291102253e-05,
|
949 |
+
"loss": 0.491,
|
950 |
+
"step": 157
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 2.0,
|
954 |
+
"learning_rate": 9.409142516297269e-05,
|
955 |
+
"loss": 0.4624,
|
956 |
+
"step": 158
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 2.01,
|
960 |
+
"learning_rate": 9.401698430526142e-05,
|
961 |
+
"loss": 0.2957,
|
962 |
+
"step": 159
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 2.03,
|
966 |
+
"learning_rate": 9.394210727474028e-05,
|
967 |
+
"loss": 0.3436,
|
968 |
+
"step": 160
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 2.04,
|
972 |
+
"learning_rate": 9.386679481338033e-05,
|
973 |
+
"loss": 0.3312,
|
974 |
+
"step": 161
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 2.05,
|
978 |
+
"learning_rate": 9.379104766746722e-05,
|
979 |
+
"loss": 0.3232,
|
980 |
+
"step": 162
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 2.06,
|
984 |
+
"learning_rate": 9.371486658759416e-05,
|
985 |
+
"loss": 0.3306,
|
986 |
+
"step": 163
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 2.08,
|
990 |
+
"learning_rate": 9.363825232865413e-05,
|
991 |
+
"loss": 0.3507,
|
992 |
+
"step": 164
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 2.09,
|
996 |
+
"learning_rate": 9.356120564983266e-05,
|
997 |
+
"loss": 0.3474,
|
998 |
+
"step": 165
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 2.1,
|
1002 |
+
"learning_rate": 9.348372731460023e-05,
|
1003 |
+
"loss": 0.3206,
|
1004 |
+
"step": 166
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 2.11,
|
1008 |
+
"learning_rate": 9.340581809070459e-05,
|
1009 |
+
"loss": 0.2675,
|
1010 |
+
"step": 167
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 2.13,
|
1014 |
+
"learning_rate": 9.332747875016332e-05,
|
1015 |
+
"loss": 0.3432,
|
1016 |
+
"step": 168
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 2.14,
|
1020 |
+
"learning_rate": 9.324871006925613e-05,
|
1021 |
+
"loss": 0.3829,
|
1022 |
+
"step": 169
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 2.15,
|
1026 |
+
"learning_rate": 9.316951282851707e-05,
|
1027 |
+
"loss": 0.3136,
|
1028 |
+
"step": 170
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 2.16,
|
1032 |
+
"learning_rate": 9.308988781272694e-05,
|
1033 |
+
"loss": 0.3381,
|
1034 |
+
"step": 171
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 2.18,
|
1038 |
+
"learning_rate": 9.300983581090541e-05,
|
1039 |
+
"loss": 0.3394,
|
1040 |
+
"step": 172
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.19,
|
1044 |
+
"learning_rate": 9.292935761630326e-05,
|
1045 |
+
"loss": 0.3277,
|
1046 |
+
"step": 173
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 2.2,
|
1050 |
+
"learning_rate": 9.284845402639446e-05,
|
1051 |
+
"loss": 0.3286,
|
1052 |
+
"step": 174
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 2.22,
|
1056 |
+
"learning_rate": 9.276712584286833e-05,
|
1057 |
+
"loss": 0.3151,
|
1058 |
+
"step": 175
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 2.23,
|
1062 |
+
"learning_rate": 9.26853738716216e-05,
|
1063 |
+
"loss": 0.3557,
|
1064 |
+
"step": 176
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 2.24,
|
1068 |
+
"learning_rate": 9.260319892275034e-05,
|
1069 |
+
"loss": 0.2099,
|
1070 |
+
"step": 177
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 2.25,
|
1074 |
+
"learning_rate": 9.2520601810542e-05,
|
1075 |
+
"loss": 0.3627,
|
1076 |
+
"step": 178
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 2.27,
|
1080 |
+
"learning_rate": 9.243758335346735e-05,
|
1081 |
+
"loss": 0.285,
|
1082 |
+
"step": 179
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 2.28,
|
1086 |
+
"learning_rate": 9.235414437417234e-05,
|
1087 |
+
"loss": 0.3189,
|
1088 |
+
"step": 180
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 2.29,
|
1092 |
+
"learning_rate": 9.227028569946996e-05,
|
1093 |
+
"loss": 0.288,
|
1094 |
+
"step": 181
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 2.3,
|
1098 |
+
"learning_rate": 9.2186008160332e-05,
|
1099 |
+
"loss": 0.2462,
|
1100 |
+
"step": 182
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 2.32,
|
1104 |
+
"learning_rate": 9.210131259188095e-05,
|
1105 |
+
"loss": 0.2527,
|
1106 |
+
"step": 183
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 2.33,
|
1110 |
+
"learning_rate": 9.201619983338153e-05,
|
1111 |
+
"loss": 0.3712,
|
1112 |
+
"step": 184
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 2.34,
|
1116 |
+
"learning_rate": 9.193067072823251e-05,
|
1117 |
+
"loss": 0.3526,
|
1118 |
+
"step": 185
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 2.35,
|
1122 |
+
"learning_rate": 9.18447261239584e-05,
|
1123 |
+
"loss": 0.2721,
|
1124 |
+
"step": 186
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 2.37,
|
1128 |
+
"learning_rate": 9.175836687220084e-05,
|
1129 |
+
"loss": 0.2738,
|
1130 |
+
"step": 187
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 2.38,
|
1134 |
+
"learning_rate": 9.167159382871039e-05,
|
1135 |
+
"loss": 0.3511,
|
1136 |
+
"step": 188
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 2.39,
|
1140 |
+
"learning_rate": 9.15844078533379e-05,
|
1141 |
+
"loss": 0.3712,
|
1142 |
+
"step": 189
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 2.41,
|
1146 |
+
"learning_rate": 9.149680981002609e-05,
|
1147 |
+
"loss": 0.3244,
|
1148 |
+
"step": 190
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 2.42,
|
1152 |
+
"learning_rate": 9.140880056680088e-05,
|
1153 |
+
"loss": 0.3304,
|
1154 |
+
"step": 191
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 2.43,
|
1158 |
+
"learning_rate": 9.13203809957629e-05,
|
1159 |
+
"loss": 0.3476,
|
1160 |
+
"step": 192
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 2.44,
|
1164 |
+
"learning_rate": 9.123155197307876e-05,
|
1165 |
+
"loss": 0.2981,
|
1166 |
+
"step": 193
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 2.46,
|
1170 |
+
"learning_rate": 9.114231437897244e-05,
|
1171 |
+
"loss": 0.2947,
|
1172 |
+
"step": 194
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 2.47,
|
1176 |
+
"learning_rate": 9.105266909771653e-05,
|
1177 |
+
"loss": 0.2627,
|
1178 |
+
"step": 195
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 2.48,
|
1182 |
+
"learning_rate": 9.096261701762342e-05,
|
1183 |
+
"loss": 0.306,
|
1184 |
+
"step": 196
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 2.49,
|
1188 |
+
"learning_rate": 9.087215903103662e-05,
|
1189 |
+
"loss": 0.3326,
|
1190 |
+
"step": 197
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 2.51,
|
1194 |
+
"learning_rate": 9.078129603432181e-05,
|
1195 |
+
"loss": 0.2348,
|
1196 |
+
"step": 198
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 2.52,
|
1200 |
+
"learning_rate": 9.069002892785797e-05,
|
1201 |
+
"loss": 0.4223,
|
1202 |
+
"step": 199
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 2.53,
|
1206 |
+
"learning_rate": 9.059835861602853e-05,
|
1207 |
+
"loss": 0.294,
|
1208 |
+
"step": 200
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 2.54,
|
1212 |
+
"learning_rate": 9.050628600721234e-05,
|
1213 |
+
"loss": 0.269,
|
1214 |
+
"step": 201
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 2.56,
|
1218 |
+
"learning_rate": 9.041381201377468e-05,
|
1219 |
+
"loss": 0.3375,
|
1220 |
+
"step": 202
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 2.57,
|
1224 |
+
"learning_rate": 9.032093755205822e-05,
|
1225 |
+
"loss": 0.3022,
|
1226 |
+
"step": 203
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 2.58,
|
1230 |
+
"learning_rate": 9.0227663542374e-05,
|
1231 |
+
"loss": 0.3297,
|
1232 |
+
"step": 204
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 2.59,
|
1236 |
+
"learning_rate": 9.013399090899217e-05,
|
1237 |
+
"loss": 0.3108,
|
1238 |
+
"step": 205
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 2.61,
|
1242 |
+
"learning_rate": 9.003992058013302e-05,
|
1243 |
+
"loss": 0.2948,
|
1244 |
+
"step": 206
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 2.62,
|
1248 |
+
"learning_rate": 8.994545348795759e-05,
|
1249 |
+
"loss": 0.2719,
|
1250 |
+
"step": 207
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 2.63,
|
1254 |
+
"learning_rate": 8.985059056855858e-05,
|
1255 |
+
"loss": 0.3116,
|
1256 |
+
"step": 208
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 2.65,
|
1260 |
+
"learning_rate": 8.975533276195102e-05,
|
1261 |
+
"loss": 0.2567,
|
1262 |
+
"step": 209
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 2.66,
|
1266 |
+
"learning_rate": 8.965968101206291e-05,
|
1267 |
+
"loss": 0.3751,
|
1268 |
+
"step": 210
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 2.67,
|
1272 |
+
"learning_rate": 8.956363626672595e-05,
|
1273 |
+
"loss": 0.2538,
|
1274 |
+
"step": 211
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 2.68,
|
1278 |
+
"learning_rate": 8.94671994776661e-05,
|
1279 |
+
"loss": 0.2973,
|
1280 |
+
"step": 212
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 2.7,
|
1284 |
+
"learning_rate": 8.937037160049416e-05,
|
1285 |
+
"loss": 0.4477,
|
1286 |
+
"step": 213
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 2.71,
|
1290 |
+
"learning_rate": 8.927315359469626e-05,
|
1291 |
+
"loss": 0.3517,
|
1292 |
+
"step": 214
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 2.72,
|
1296 |
+
"learning_rate": 8.917554642362443e-05,
|
1297 |
+
"loss": 0.2779,
|
1298 |
+
"step": 215
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 2.73,
|
1302 |
+
"learning_rate": 8.907755105448704e-05,
|
1303 |
+
"loss": 0.3196,
|
1304 |
+
"step": 216
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 2.75,
|
1308 |
+
"learning_rate": 8.89791684583391e-05,
|
1309 |
+
"loss": 0.31,
|
1310 |
+
"step": 217
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 2.76,
|
1314 |
+
"learning_rate": 8.888039961007282e-05,
|
1315 |
+
"loss": 0.2522,
|
1316 |
+
"step": 218
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 2.77,
|
1320 |
+
"learning_rate": 8.87812454884078e-05,
|
1321 |
+
"loss": 0.2974,
|
1322 |
+
"step": 219
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 2.78,
|
1326 |
+
"learning_rate": 8.868170707588142e-05,
|
1327 |
+
"loss": 0.2817,
|
1328 |
+
"step": 220
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 2.8,
|
1332 |
+
"learning_rate": 8.858178535883905e-05,
|
1333 |
+
"loss": 0.3853,
|
1334 |
+
"step": 221
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 2.81,
|
1338 |
+
"learning_rate": 8.848148132742431e-05,
|
1339 |
+
"loss": 0.2393,
|
1340 |
+
"step": 222
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 2.82,
|
1344 |
+
"learning_rate": 8.838079597556925e-05,
|
1345 |
+
"loss": 0.3607,
|
1346 |
+
"step": 223
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 2.84,
|
1350 |
+
"learning_rate": 8.827973030098448e-05,
|
1351 |
+
"loss": 0.3263,
|
1352 |
+
"step": 224
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 2.85,
|
1356 |
+
"learning_rate": 8.81782853051493e-05,
|
1357 |
+
"loss": 0.3084,
|
1358 |
+
"step": 225
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 2.86,
|
1362 |
+
"learning_rate": 8.807646199330187e-05,
|
1363 |
+
"loss": 0.3019,
|
1364 |
+
"step": 226
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 2.87,
|
1368 |
+
"learning_rate": 8.797426137442897e-05,
|
1369 |
+
"loss": 0.3646,
|
1370 |
+
"step": 227
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 2.89,
|
1374 |
+
"learning_rate": 8.787168446125638e-05,
|
1375 |
+
"loss": 0.3149,
|
1376 |
+
"step": 228
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 2.9,
|
1380 |
+
"learning_rate": 8.776873227023852e-05,
|
1381 |
+
"loss": 0.326,
|
1382 |
+
"step": 229
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 2.91,
|
1386 |
+
"learning_rate": 8.766540582154859e-05,
|
1387 |
+
"loss": 0.3216,
|
1388 |
+
"step": 230
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 2.92,
|
1392 |
+
"learning_rate": 8.756170613906833e-05,
|
1393 |
+
"loss": 0.3348,
|
1394 |
+
"step": 231
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 2.94,
|
1398 |
+
"learning_rate": 8.745763425037797e-05,
|
1399 |
+
"loss": 0.2524,
|
1400 |
+
"step": 232
|
1401 |
+
},
|
1402 |
+
{
|
1403 |
+
"epoch": 2.95,
|
1404 |
+
"learning_rate": 8.735319118674596e-05,
|
1405 |
+
"loss": 0.2725,
|
1406 |
+
"step": 233
|
1407 |
+
},
|
1408 |
+
{
|
1409 |
+
"epoch": 2.96,
|
1410 |
+
"learning_rate": 8.724837798311882e-05,
|
1411 |
+
"loss": 0.2733,
|
1412 |
+
"step": 234
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 2.97,
|
1416 |
+
"learning_rate": 8.714319567811088e-05,
|
1417 |
+
"loss": 0.287,
|
1418 |
+
"step": 235
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 2.99,
|
1422 |
+
"learning_rate": 8.703764531399392e-05,
|
1423 |
+
"loss": 0.2891,
|
1424 |
+
"step": 236
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 3.0,
|
1428 |
+
"learning_rate": 8.69317279366869e-05,
|
1429 |
+
"loss": 0.2329,
|
1430 |
+
"step": 237
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 3.01,
|
1434 |
+
"learning_rate": 8.682544459574562e-05,
|
1435 |
+
"loss": 0.1752,
|
1436 |
+
"step": 238
|
1437 |
+
},
|
1438 |
+
{
|
1439 |
+
"epoch": 3.03,
|
1440 |
+
"learning_rate": 8.671879634435224e-05,
|
1441 |
+
"loss": 0.1686,
|
1442 |
+
"step": 239
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 3.04,
|
1446 |
+
"learning_rate": 8.661178423930491e-05,
|
1447 |
+
"loss": 0.2164,
|
1448 |
+
"step": 240
|
1449 |
+
},
|
1450 |
+
{
|
1451 |
+
"epoch": 3.05,
|
1452 |
+
"learning_rate": 8.650440934100728e-05,
|
1453 |
+
"loss": 0.1909,
|
1454 |
+
"step": 241
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 3.06,
|
1458 |
+
"learning_rate": 8.639667271345798e-05,
|
1459 |
+
"loss": 0.1765,
|
1460 |
+
"step": 242
|
1461 |
+
},
|
1462 |
+
{
|
1463 |
+
"epoch": 3.08,
|
1464 |
+
"learning_rate": 8.628857542424009e-05,
|
1465 |
+
"loss": 0.1558,
|
1466 |
+
"step": 243
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 3.09,
|
1470 |
+
"learning_rate": 8.618011854451056e-05,
|
1471 |
+
"loss": 0.1471,
|
1472 |
+
"step": 244
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 3.1,
|
1476 |
+
"learning_rate": 8.607130314898956e-05,
|
1477 |
+
"loss": 0.175,
|
1478 |
+
"step": 245
|
1479 |
+
},
|
1480 |
+
{
|
1481 |
+
"epoch": 3.11,
|
1482 |
+
"learning_rate": 8.596213031594991e-05,
|
1483 |
+
"loss": 0.1692,
|
1484 |
+
"step": 246
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 3.13,
|
1488 |
+
"learning_rate": 8.585260112720631e-05,
|
1489 |
+
"loss": 0.1176,
|
1490 |
+
"step": 247
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 3.14,
|
1494 |
+
"learning_rate": 8.57427166681047e-05,
|
1495 |
+
"loss": 0.1773,
|
1496 |
+
"step": 248
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 3.15,
|
1500 |
+
"learning_rate": 8.56324780275114e-05,
|
1501 |
+
"loss": 0.1821,
|
1502 |
+
"step": 249
|
1503 |
+
},
|
1504 |
+
{
|
1505 |
+
"epoch": 3.16,
|
1506 |
+
"learning_rate": 8.552188629780244e-05,
|
1507 |
+
"loss": 0.1471,
|
1508 |
+
"step": 250
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 3.18,
|
1512 |
+
"learning_rate": 8.541094257485265e-05,
|
1513 |
+
"loss": 0.1949,
|
1514 |
+
"step": 251
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 3.19,
|
1518 |
+
"learning_rate": 8.529964795802485e-05,
|
1519 |
+
"loss": 0.1234,
|
1520 |
+
"step": 252
|
1521 |
+
},
|
1522 |
+
{
|
1523 |
+
"epoch": 3.2,
|
1524 |
+
"learning_rate": 8.518800355015892e-05,
|
1525 |
+
"loss": 0.1625,
|
1526 |
+
"step": 253
|
1527 |
+
},
|
1528 |
+
{
|
1529 |
+
"epoch": 3.22,
|
1530 |
+
"learning_rate": 8.507601045756085e-05,
|
1531 |
+
"loss": 0.1417,
|
1532 |
+
"step": 254
|
1533 |
+
},
|
1534 |
+
{
|
1535 |
+
"epoch": 3.23,
|
1536 |
+
"learning_rate": 8.49636697899919e-05,
|
1537 |
+
"loss": 0.1088,
|
1538 |
+
"step": 255
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 3.24,
|
1542 |
+
"learning_rate": 8.485098266065744e-05,
|
1543 |
+
"loss": 0.1524,
|
1544 |
+
"step": 256
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"epoch": 3.25,
|
1548 |
+
"learning_rate": 8.473795018619604e-05,
|
1549 |
+
"loss": 0.1711,
|
1550 |
+
"step": 257
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 3.27,
|
1554 |
+
"learning_rate": 8.462457348666835e-05,
|
1555 |
+
"loss": 0.161,
|
1556 |
+
"step": 258
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 3.28,
|
1560 |
+
"learning_rate": 8.4510853685546e-05,
|
1561 |
+
"loss": 0.1641,
|
1562 |
+
"step": 259
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 3.29,
|
1566 |
+
"learning_rate": 8.439679190970052e-05,
|
1567 |
+
"loss": 0.1633,
|
1568 |
+
"step": 260
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"epoch": 3.3,
|
1572 |
+
"learning_rate": 8.428238928939207e-05,
|
1573 |
+
"loss": 0.1673,
|
1574 |
+
"step": 261
|
1575 |
+
},
|
1576 |
+
{
|
1577 |
+
"epoch": 3.32,
|
1578 |
+
"learning_rate": 8.416764695825835e-05,
|
1579 |
+
"loss": 0.1629,
|
1580 |
+
"step": 262
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 3.33,
|
1584 |
+
"learning_rate": 8.405256605330331e-05,
|
1585 |
+
"loss": 0.177,
|
1586 |
+
"step": 263
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 3.34,
|
1590 |
+
"learning_rate": 8.39371477148859e-05,
|
1591 |
+
"loss": 0.1188,
|
1592 |
+
"step": 264
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 3.35,
|
1596 |
+
"learning_rate": 8.382139308670875e-05,
|
1597 |
+
"loss": 0.1934,
|
1598 |
+
"step": 265
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 3.37,
|
1602 |
+
"learning_rate": 8.370530331580686e-05,
|
1603 |
+
"loss": 0.1049,
|
1604 |
+
"step": 266
|
1605 |
+
},
|
1606 |
+
{
|
1607 |
+
"epoch": 3.38,
|
1608 |
+
"learning_rate": 8.35888795525362e-05,
|
1609 |
+
"loss": 0.1376,
|
1610 |
+
"step": 267
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 3.39,
|
1614 |
+
"learning_rate": 8.347212295056239e-05,
|
1615 |
+
"loss": 0.1574,
|
1616 |
+
"step": 268
|
1617 |
+
},
|
1618 |
+
{
|
1619 |
+
"epoch": 3.41,
|
1620 |
+
"learning_rate": 8.335503466684915e-05,
|
1621 |
+
"loss": 0.1222,
|
1622 |
+
"step": 269
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 3.42,
|
1626 |
+
"learning_rate": 8.323761586164695e-05,
|
1627 |
+
"loss": 0.1634,
|
1628 |
+
"step": 270
|
1629 |
+
},
|
1630 |
+
{
|
1631 |
+
"epoch": 3.43,
|
1632 |
+
"learning_rate": 8.311986769848141e-05,
|
1633 |
+
"loss": 0.1764,
|
1634 |
+
"step": 271
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 3.44,
|
1638 |
+
"learning_rate": 8.300179134414188e-05,
|
1639 |
+
"loss": 0.1621,
|
1640 |
+
"step": 272
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 3.46,
|
1644 |
+
"learning_rate": 8.288338796866976e-05,
|
1645 |
+
"loss": 0.1549,
|
1646 |
+
"step": 273
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 3.47,
|
1650 |
+
"learning_rate": 8.276465874534702e-05,
|
1651 |
+
"loss": 0.1053,
|
1652 |
+
"step": 274
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"epoch": 3.48,
|
1656 |
+
"learning_rate": 8.264560485068446e-05,
|
1657 |
+
"loss": 0.1224,
|
1658 |
+
"step": 275
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 3.49,
|
1662 |
+
"learning_rate": 8.252622746441021e-05,
|
1663 |
+
"loss": 0.1361,
|
1664 |
+
"step": 276
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 3.51,
|
1668 |
+
"learning_rate": 8.240652776945781e-05,
|
1669 |
+
"loss": 0.1753,
|
1670 |
+
"step": 277
|
1671 |
+
},
|
1672 |
+
{
|
1673 |
+
"epoch": 3.52,
|
1674 |
+
"learning_rate": 8.228650695195472e-05,
|
1675 |
+
"loss": 0.1539,
|
1676 |
+
"step": 278
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 3.53,
|
1680 |
+
"learning_rate": 8.216616620121043e-05,
|
1681 |
+
"loss": 0.1603,
|
1682 |
+
"step": 279
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 3.54,
|
1686 |
+
"learning_rate": 8.204550670970469e-05,
|
1687 |
+
"loss": 0.1519,
|
1688 |
+
"step": 280
|
1689 |
+
},
|
1690 |
+
{
|
1691 |
+
"epoch": 3.56,
|
1692 |
+
"learning_rate": 8.192452967307576e-05,
|
1693 |
+
"loss": 0.1494,
|
1694 |
+
"step": 281
|
1695 |
+
},
|
1696 |
+
{
|
1697 |
+
"epoch": 3.57,
|
1698 |
+
"learning_rate": 8.180323629010848e-05,
|
1699 |
+
"loss": 0.1695,
|
1700 |
+
"step": 282
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 3.58,
|
1704 |
+
"learning_rate": 8.168162776272244e-05,
|
1705 |
+
"loss": 0.1384,
|
1706 |
+
"step": 283
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 3.59,
|
1710 |
+
"learning_rate": 8.155970529596006e-05,
|
1711 |
+
"loss": 0.1552,
|
1712 |
+
"step": 284
|
1713 |
+
},
|
1714 |
+
{
|
1715 |
+
"epoch": 3.61,
|
1716 |
+
"learning_rate": 8.143747009797464e-05,
|
1717 |
+
"loss": 0.166,
|
1718 |
+
"step": 285
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 3.62,
|
1722 |
+
"learning_rate": 8.131492338001839e-05,
|
1723 |
+
"loss": 0.2007,
|
1724 |
+
"step": 286
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 3.63,
|
1728 |
+
"learning_rate": 8.119206635643045e-05,
|
1729 |
+
"loss": 0.1331,
|
1730 |
+
"step": 287
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 3.65,
|
1734 |
+
"learning_rate": 8.106890024462481e-05,
|
1735 |
+
"loss": 0.2133,
|
1736 |
+
"step": 288
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 3.66,
|
1740 |
+
"learning_rate": 8.094542626507828e-05,
|
1741 |
+
"loss": 0.1507,
|
1742 |
+
"step": 289
|
1743 |
+
},
|
1744 |
+
{
|
1745 |
+
"epoch": 3.67,
|
1746 |
+
"learning_rate": 8.082164564131845e-05,
|
1747 |
+
"loss": 0.1465,
|
1748 |
+
"step": 290
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 3.68,
|
1752 |
+
"learning_rate": 8.069755959991142e-05,
|
1753 |
+
"loss": 0.1344,
|
1754 |
+
"step": 291
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 3.7,
|
1758 |
+
"learning_rate": 8.057316937044977e-05,
|
1759 |
+
"loss": 0.1623,
|
1760 |
+
"step": 292
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 3.71,
|
1764 |
+
"learning_rate": 8.044847618554034e-05,
|
1765 |
+
"loss": 0.1823,
|
1766 |
+
"step": 293
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 3.72,
|
1770 |
+
"learning_rate": 8.032348128079203e-05,
|
1771 |
+
"loss": 0.1191,
|
1772 |
+
"step": 294
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 3.73,
|
1776 |
+
"learning_rate": 8.019818589480352e-05,
|
1777 |
+
"loss": 0.1536,
|
1778 |
+
"step": 295
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 3.75,
|
1782 |
+
"learning_rate": 8.0072591269151e-05,
|
1783 |
+
"loss": 0.1745,
|
1784 |
+
"step": 296
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 3.76,
|
1788 |
+
"learning_rate": 7.994669864837594e-05,
|
1789 |
+
"loss": 0.1265,
|
1790 |
+
"step": 297
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 3.77,
|
1794 |
+
"learning_rate": 7.982050927997264e-05,
|
1795 |
+
"loss": 0.1475,
|
1796 |
+
"step": 298
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 3.78,
|
1800 |
+
"learning_rate": 7.969402441437594e-05,
|
1801 |
+
"loss": 0.1597,
|
1802 |
+
"step": 299
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 3.8,
|
1806 |
+
"learning_rate": 7.956724530494887e-05,
|
1807 |
+
"loss": 0.1716,
|
1808 |
+
"step": 300
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 3.81,
|
1812 |
+
"learning_rate": 7.944017320797013e-05,
|
1813 |
+
"loss": 0.1569,
|
1814 |
+
"step": 301
|
1815 |
+
},
|
1816 |
+
{
|
1817 |
+
"epoch": 3.82,
|
1818 |
+
"learning_rate": 7.931280938262169e-05,
|
1819 |
+
"loss": 0.1696,
|
1820 |
+
"step": 302
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"epoch": 3.84,
|
1824 |
+
"learning_rate": 7.918515509097634e-05,
|
1825 |
+
"loss": 0.1879,
|
1826 |
+
"step": 303
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 3.85,
|
1830 |
+
"learning_rate": 7.905721159798513e-05,
|
1831 |
+
"loss": 0.1568,
|
1832 |
+
"step": 304
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 3.86,
|
1836 |
+
"learning_rate": 7.89289801714649e-05,
|
1837 |
+
"loss": 0.1276,
|
1838 |
+
"step": 305
|
1839 |
+
},
|
1840 |
+
{
|
1841 |
+
"epoch": 3.87,
|
1842 |
+
"learning_rate": 7.880046208208563e-05,
|
1843 |
+
"loss": 0.1508,
|
1844 |
+
"step": 306
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 3.89,
|
1848 |
+
"learning_rate": 7.867165860335792e-05,
|
1849 |
+
"loss": 0.1641,
|
1850 |
+
"step": 307
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 3.9,
|
1854 |
+
"learning_rate": 7.854257101162037e-05,
|
1855 |
+
"loss": 0.1571,
|
1856 |
+
"step": 308
|
1857 |
+
},
|
1858 |
+
{
|
1859 |
+
"epoch": 3.91,
|
1860 |
+
"learning_rate": 7.841320058602688e-05,
|
1861 |
+
"loss": 0.1642,
|
1862 |
+
"step": 309
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 3.92,
|
1866 |
+
"learning_rate": 7.828354860853399e-05,
|
1867 |
+
"loss": 0.2288,
|
1868 |
+
"step": 310
|
1869 |
+
},
|
1870 |
+
{
|
1871 |
+
"epoch": 3.94,
|
1872 |
+
"learning_rate": 7.815361636388827e-05,
|
1873 |
+
"loss": 0.1195,
|
1874 |
+
"step": 311
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 3.95,
|
1878 |
+
"learning_rate": 7.802340513961342e-05,
|
1879 |
+
"loss": 0.1699,
|
1880 |
+
"step": 312
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 3.96,
|
1884 |
+
"learning_rate": 7.789291622599767e-05,
|
1885 |
+
"loss": 0.1761,
|
1886 |
+
"step": 313
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 3.97,
|
1890 |
+
"learning_rate": 7.776215091608085e-05,
|
1891 |
+
"loss": 0.2214,
|
1892 |
+
"step": 314
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 3.99,
|
1896 |
+
"learning_rate": 7.763111050564178e-05,
|
1897 |
+
"loss": 0.2109,
|
1898 |
+
"step": 315
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 4.0,
|
1902 |
+
"learning_rate": 7.749979629318516e-05,
|
1903 |
+
"loss": 0.1801,
|
1904 |
+
"step": 316
|
1905 |
+
},
|
1906 |
+
{
|
1907 |
+
"epoch": 4.01,
|
1908 |
+
"learning_rate": 7.736820957992895e-05,
|
1909 |
+
"loss": 0.0728,
|
1910 |
+
"step": 317
|
1911 |
+
},
|
1912 |
+
{
|
1913 |
+
"epoch": 4.03,
|
1914 |
+
"learning_rate": 7.723635166979133e-05,
|
1915 |
+
"loss": 0.0642,
|
1916 |
+
"step": 318
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 4.04,
|
1920 |
+
"learning_rate": 7.710422386937784e-05,
|
1921 |
+
"loss": 0.0868,
|
1922 |
+
"step": 319
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 4.05,
|
1926 |
+
"learning_rate": 7.697182748796841e-05,
|
1927 |
+
"loss": 0.0672,
|
1928 |
+
"step": 320
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 4.06,
|
1932 |
+
"learning_rate": 7.683916383750436e-05,
|
1933 |
+
"loss": 0.0645,
|
1934 |
+
"step": 321
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 4.08,
|
1938 |
+
"learning_rate": 7.670623423257548e-05,
|
1939 |
+
"loss": 0.0746,
|
1940 |
+
"step": 322
|
1941 |
+
},
|
1942 |
+
{
|
1943 |
+
"epoch": 4.09,
|
1944 |
+
"learning_rate": 7.657303999040693e-05,
|
1945 |
+
"loss": 0.0801,
|
1946 |
+
"step": 323
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 4.1,
|
1950 |
+
"learning_rate": 7.64395824308462e-05,
|
1951 |
+
"loss": 0.0557,
|
1952 |
+
"step": 324
|
1953 |
+
},
|
1954 |
+
{
|
1955 |
+
"epoch": 4.11,
|
1956 |
+
"learning_rate": 7.630586287635008e-05,
|
1957 |
+
"loss": 0.061,
|
1958 |
+
"step": 325
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 4.13,
|
1962 |
+
"learning_rate": 7.617188265197148e-05,
|
1963 |
+
"loss": 0.0666,
|
1964 |
+
"step": 326
|
1965 |
+
},
|
1966 |
+
{
|
1967 |
+
"epoch": 4.14,
|
1968 |
+
"learning_rate": 7.603764308534636e-05,
|
1969 |
+
"loss": 0.0495,
|
1970 |
+
"step": 327
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 4.15,
|
1974 |
+
"learning_rate": 7.590314550668054e-05,
|
1975 |
+
"loss": 0.0591,
|
1976 |
+
"step": 328
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 4.16,
|
1980 |
+
"learning_rate": 7.576839124873653e-05,
|
1981 |
+
"loss": 0.0914,
|
1982 |
+
"step": 329
|
1983 |
+
},
|
1984 |
+
{
|
1985 |
+
"epoch": 4.18,
|
1986 |
+
"learning_rate": 7.563338164682036e-05,
|
1987 |
+
"loss": 0.1023,
|
1988 |
+
"step": 330
|
1989 |
+
},
|
1990 |
+
{
|
1991 |
+
"epoch": 4.19,
|
1992 |
+
"learning_rate": 7.549811803876825e-05,
|
1993 |
+
"loss": 0.1043,
|
1994 |
+
"step": 331
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 4.2,
|
1998 |
+
"learning_rate": 7.536260176493348e-05,
|
1999 |
+
"loss": 0.054,
|
2000 |
+
"step": 332
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 4.22,
|
2004 |
+
"learning_rate": 7.5226834168173e-05,
|
2005 |
+
"loss": 0.0712,
|
2006 |
+
"step": 333
|
2007 |
+
},
|
2008 |
+
{
|
2009 |
+
"epoch": 4.23,
|
2010 |
+
"learning_rate": 7.509081659383417e-05,
|
2011 |
+
"loss": 0.0814,
|
2012 |
+
"step": 334
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 4.24,
|
2016 |
+
"learning_rate": 7.495455038974146e-05,
|
2017 |
+
"loss": 0.0573,
|
2018 |
+
"step": 335
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 4.25,
|
2022 |
+
"learning_rate": 7.481803690618304e-05,
|
2023 |
+
"loss": 0.0603,
|
2024 |
+
"step": 336
|
2025 |
+
},
|
2026 |
+
{
|
2027 |
+
"epoch": 4.27,
|
2028 |
+
"learning_rate": 7.46812774958974e-05,
|
2029 |
+
"loss": 0.0565,
|
2030 |
+
"step": 337
|
2031 |
+
},
|
2032 |
+
{
|
2033 |
+
"epoch": 4.28,
|
2034 |
+
"learning_rate": 7.454427351405999e-05,
|
2035 |
+
"loss": 0.063,
|
2036 |
+
"step": 338
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"epoch": 4.29,
|
2040 |
+
"learning_rate": 7.440702631826977e-05,
|
2041 |
+
"loss": 0.0666,
|
2042 |
+
"step": 339
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 4.3,
|
2046 |
+
"learning_rate": 7.426953726853574e-05,
|
2047 |
+
"loss": 0.0669,
|
2048 |
+
"step": 340
|
2049 |
+
},
|
2050 |
+
{
|
2051 |
+
"epoch": 4.32,
|
2052 |
+
"learning_rate": 7.413180772726348e-05,
|
2053 |
+
"loss": 0.0812,
|
2054 |
+
"step": 341
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 4.33,
|
2058 |
+
"learning_rate": 7.399383905924165e-05,
|
2059 |
+
"loss": 0.081,
|
2060 |
+
"step": 342
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 4.34,
|
2064 |
+
"learning_rate": 7.385563263162847e-05,
|
2065 |
+
"loss": 0.0697,
|
2066 |
+
"step": 343
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 4.35,
|
2070 |
+
"learning_rate": 7.371718981393815e-05,
|
2071 |
+
"loss": 0.0639,
|
2072 |
+
"step": 344
|
2073 |
+
},
|
2074 |
+
{
|
2075 |
+
"epoch": 4.37,
|
2076 |
+
"learning_rate": 7.357851197802735e-05,
|
2077 |
+
"loss": 0.0792,
|
2078 |
+
"step": 345
|
2079 |
+
},
|
2080 |
+
{
|
2081 |
+
"epoch": 4.38,
|
2082 |
+
"learning_rate": 7.343960049808156e-05,
|
2083 |
+
"loss": 0.0665,
|
2084 |
+
"step": 346
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 4.39,
|
2088 |
+
"learning_rate": 7.330045675060149e-05,
|
2089 |
+
"loss": 0.0593,
|
2090 |
+
"step": 347
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 4.41,
|
2094 |
+
"learning_rate": 7.316108211438945e-05,
|
2095 |
+
"loss": 0.0307,
|
2096 |
+
"step": 348
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 4.42,
|
2100 |
+
"learning_rate": 7.302147797053569e-05,
|
2101 |
+
"loss": 0.0656,
|
2102 |
+
"step": 349
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 4.43,
|
2106 |
+
"learning_rate": 7.288164570240463e-05,
|
2107 |
+
"loss": 0.049,
|
2108 |
+
"step": 350
|
2109 |
+
},
|
2110 |
+
{
|
2111 |
+
"epoch": 4.44,
|
2112 |
+
"learning_rate": 7.274158669562126e-05,
|
2113 |
+
"loss": 0.0653,
|
2114 |
+
"step": 351
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 4.46,
|
2118 |
+
"learning_rate": 7.26013023380574e-05,
|
2119 |
+
"loss": 0.0668,
|
2120 |
+
"step": 352
|
2121 |
+
},
|
2122 |
+
{
|
2123 |
+
"epoch": 4.47,
|
2124 |
+
"learning_rate": 7.246079401981784e-05,
|
2125 |
+
"loss": 0.0894,
|
2126 |
+
"step": 353
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 4.48,
|
2130 |
+
"learning_rate": 7.232006313322667e-05,
|
2131 |
+
"loss": 0.0641,
|
2132 |
+
"step": 354
|
2133 |
+
},
|
2134 |
+
{
|
2135 |
+
"epoch": 4.49,
|
2136 |
+
"learning_rate": 7.217911107281352e-05,
|
2137 |
+
"loss": 0.0905,
|
2138 |
+
"step": 355
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 4.51,
|
2142 |
+
"learning_rate": 7.203793923529956e-05,
|
2143 |
+
"loss": 0.0753,
|
2144 |
+
"step": 356
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 4.52,
|
2148 |
+
"learning_rate": 7.189654901958385e-05,
|
2149 |
+
"loss": 0.0737,
|
2150 |
+
"step": 357
|
2151 |
+
},
|
2152 |
+
{
|
2153 |
+
"epoch": 4.53,
|
2154 |
+
"learning_rate": 7.175494182672939e-05,
|
2155 |
+
"loss": 0.0828,
|
2156 |
+
"step": 358
|
2157 |
+
},
|
2158 |
+
{
|
2159 |
+
"epoch": 4.54,
|
2160 |
+
"learning_rate": 7.161311905994922e-05,
|
2161 |
+
"loss": 0.0597,
|
2162 |
+
"step": 359
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 4.56,
|
2166 |
+
"learning_rate": 7.147108212459257e-05,
|
2167 |
+
"loss": 0.0623,
|
2168 |
+
"step": 360
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 4.57,
|
2172 |
+
"learning_rate": 7.13288324281309e-05,
|
2173 |
+
"loss": 0.0751,
|
2174 |
+
"step": 361
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 4.58,
|
2178 |
+
"learning_rate": 7.118637138014396e-05,
|
2179 |
+
"loss": 0.0586,
|
2180 |
+
"step": 362
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 4.59,
|
2184 |
+
"learning_rate": 7.104370039230583e-05,
|
2185 |
+
"loss": 0.0794,
|
2186 |
+
"step": 363
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 4.61,
|
2190 |
+
"learning_rate": 7.090082087837092e-05,
|
2191 |
+
"loss": 0.0554,
|
2192 |
+
"step": 364
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 4.62,
|
2196 |
+
"learning_rate": 7.075773425415994e-05,
|
2197 |
+
"loss": 0.0601,
|
2198 |
+
"step": 365
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 4.63,
|
2202 |
+
"learning_rate": 7.061444193754596e-05,
|
2203 |
+
"loss": 0.0867,
|
2204 |
+
"step": 366
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 4.65,
|
2208 |
+
"learning_rate": 7.047094534844023e-05,
|
2209 |
+
"loss": 0.0828,
|
2210 |
+
"step": 367
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 4.66,
|
2214 |
+
"learning_rate": 7.032724590877821e-05,
|
2215 |
+
"loss": 0.0879,
|
2216 |
+
"step": 368
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 4.67,
|
2220 |
+
"learning_rate": 7.018334504250545e-05,
|
2221 |
+
"loss": 0.068,
|
2222 |
+
"step": 369
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 4.68,
|
2226 |
+
"learning_rate": 7.003924417556343e-05,
|
2227 |
+
"loss": 0.0586,
|
2228 |
+
"step": 370
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 4.7,
|
2232 |
+
"learning_rate": 6.989494473587554e-05,
|
2233 |
+
"loss": 0.0971,
|
2234 |
+
"step": 371
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 4.71,
|
2238 |
+
"learning_rate": 6.975044815333282e-05,
|
2239 |
+
"loss": 0.0864,
|
2240 |
+
"step": 372
|
2241 |
+
},
|
2242 |
+
{
|
2243 |
+
"epoch": 4.72,
|
2244 |
+
"learning_rate": 6.960575585977984e-05,
|
2245 |
+
"loss": 0.0482,
|
2246 |
+
"step": 373
|
2247 |
+
},
|
2248 |
+
{
|
2249 |
+
"epoch": 4.73,
|
2250 |
+
"learning_rate": 6.946086928900054e-05,
|
2251 |
+
"loss": 0.0812,
|
2252 |
+
"step": 374
|
2253 |
+
},
|
2254 |
+
{
|
2255 |
+
"epoch": 4.75,
|
2256 |
+
"learning_rate": 6.931578987670396e-05,
|
2257 |
+
"loss": 0.0756,
|
2258 |
+
"step": 375
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 4.76,
|
2262 |
+
"learning_rate": 6.917051906051006e-05,
|
2263 |
+
"loss": 0.0585,
|
2264 |
+
"step": 376
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 4.77,
|
2268 |
+
"learning_rate": 6.902505827993541e-05,
|
2269 |
+
"loss": 0.0653,
|
2270 |
+
"step": 377
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 4.78,
|
2274 |
+
"learning_rate": 6.887940897637908e-05,
|
2275 |
+
"loss": 0.0783,
|
2276 |
+
"step": 378
|
2277 |
+
},
|
2278 |
+
{
|
2279 |
+
"epoch": 4.8,
|
2280 |
+
"learning_rate": 6.873357259310815e-05,
|
2281 |
+
"loss": 0.0849,
|
2282 |
+
"step": 379
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 4.81,
|
2286 |
+
"learning_rate": 6.858755057524354e-05,
|
2287 |
+
"loss": 0.0642,
|
2288 |
+
"step": 380
|
2289 |
+
},
|
2290 |
+
{
|
2291 |
+
"epoch": 4.82,
|
2292 |
+
"learning_rate": 6.844134436974567e-05,
|
2293 |
+
"loss": 0.0651,
|
2294 |
+
"step": 381
|
2295 |
+
},
|
2296 |
+
{
|
2297 |
+
"epoch": 4.84,
|
2298 |
+
"learning_rate": 6.829495542540013e-05,
|
2299 |
+
"loss": 0.0511,
|
2300 |
+
"step": 382
|
2301 |
+
},
|
2302 |
+
{
|
2303 |
+
"epoch": 4.85,
|
2304 |
+
"learning_rate": 6.814838519280324e-05,
|
2305 |
+
"loss": 0.0713,
|
2306 |
+
"step": 383
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 4.86,
|
2310 |
+
"learning_rate": 6.80016351243478e-05,
|
2311 |
+
"loss": 0.0853,
|
2312 |
+
"step": 384
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 4.87,
|
2316 |
+
"learning_rate": 6.785470667420862e-05,
|
2317 |
+
"loss": 0.0777,
|
2318 |
+
"step": 385
|
2319 |
+
},
|
2320 |
+
{
|
2321 |
+
"epoch": 4.89,
|
2322 |
+
"learning_rate": 6.77076012983281e-05,
|
2323 |
+
"loss": 0.0714,
|
2324 |
+
"step": 386
|
2325 |
+
},
|
2326 |
+
{
|
2327 |
+
"epoch": 4.9,
|
2328 |
+
"learning_rate": 6.75603204544019e-05,
|
2329 |
+
"loss": 0.051,
|
2330 |
+
"step": 387
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 4.91,
|
2334 |
+
"learning_rate": 6.741286560186437e-05,
|
2335 |
+
"loss": 0.0831,
|
2336 |
+
"step": 388
|
2337 |
+
},
|
2338 |
+
{
|
2339 |
+
"epoch": 4.92,
|
2340 |
+
"learning_rate": 6.726523820187413e-05,
|
2341 |
+
"loss": 0.0613,
|
2342 |
+
"step": 389
|
2343 |
+
},
|
2344 |
+
{
|
2345 |
+
"epoch": 4.94,
|
2346 |
+
"learning_rate": 6.711743971729967e-05,
|
2347 |
+
"loss": 0.092,
|
2348 |
+
"step": 390
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 4.95,
|
2352 |
+
"learning_rate": 6.696947161270476e-05,
|
2353 |
+
"loss": 0.0457,
|
2354 |
+
"step": 391
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 4.96,
|
2358 |
+
"learning_rate": 6.682133535433393e-05,
|
2359 |
+
"loss": 0.0491,
|
2360 |
+
"step": 392
|
2361 |
+
},
|
2362 |
+
{
|
2363 |
+
"epoch": 4.97,
|
2364 |
+
"learning_rate": 6.667303241009803e-05,
|
2365 |
+
"loss": 0.0788,
|
2366 |
+
"step": 393
|
2367 |
+
},
|
2368 |
+
{
|
2369 |
+
"epoch": 4.99,
|
2370 |
+
"learning_rate": 6.652456424955963e-05,
|
2371 |
+
"loss": 0.0598,
|
2372 |
+
"step": 394
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"epoch": 5.0,
|
2376 |
+
"learning_rate": 6.637593234391843e-05,
|
2377 |
+
"loss": 0.0446,
|
2378 |
+
"step": 395
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 5.01,
|
2382 |
+
"learning_rate": 6.622713816599673e-05,
|
2383 |
+
"loss": 0.02,
|
2384 |
+
"step": 396
|
2385 |
+
},
|
2386 |
+
{
|
2387 |
+
"epoch": 5.03,
|
2388 |
+
"learning_rate": 6.60781831902248e-05,
|
2389 |
+
"loss": 0.03,
|
2390 |
+
"step": 397
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 5.04,
|
2394 |
+
"learning_rate": 6.592906889262632e-05,
|
2395 |
+
"loss": 0.0296,
|
2396 |
+
"step": 398
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 5.05,
|
2400 |
+
"learning_rate": 6.577979675080369e-05,
|
2401 |
+
"loss": 0.0267,
|
2402 |
+
"step": 399
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 5.06,
|
2406 |
+
"learning_rate": 6.563036824392344e-05,
|
2407 |
+
"loss": 0.0358,
|
2408 |
+
"step": 400
|
2409 |
+
},
|
2410 |
+
{
|
2411 |
+
"epoch": 5.08,
|
2412 |
+
"learning_rate": 6.548078485270152e-05,
|
2413 |
+
"loss": 0.0387,
|
2414 |
+
"step": 401
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"epoch": 5.09,
|
2418 |
+
"learning_rate": 6.533104805938873e-05,
|
2419 |
+
"loss": 0.0335,
|
2420 |
+
"step": 402
|
2421 |
+
},
|
2422 |
+
{
|
2423 |
+
"epoch": 5.1,
|
2424 |
+
"learning_rate": 6.518115934775585e-05,
|
2425 |
+
"loss": 0.0275,
|
2426 |
+
"step": 403
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 5.11,
|
2430 |
+
"learning_rate": 6.503112020307916e-05,
|
2431 |
+
"loss": 0.0258,
|
2432 |
+
"step": 404
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 5.13,
|
2436 |
+
"learning_rate": 6.488093211212555e-05,
|
2437 |
+
"loss": 0.0534,
|
2438 |
+
"step": 405
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 5.14,
|
2442 |
+
"learning_rate": 6.473059656313782e-05,
|
2443 |
+
"loss": 0.0176,
|
2444 |
+
"step": 406
|
2445 |
+
},
|
2446 |
+
{
|
2447 |
+
"epoch": 5.15,
|
2448 |
+
"learning_rate": 6.458011504582005e-05,
|
2449 |
+
"loss": 0.025,
|
2450 |
+
"step": 407
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 5.16,
|
2454 |
+
"learning_rate": 6.442948905132266e-05,
|
2455 |
+
"loss": 0.0172,
|
2456 |
+
"step": 408
|
2457 |
+
},
|
2458 |
+
{
|
2459 |
+
"epoch": 5.18,
|
2460 |
+
"learning_rate": 6.427872007222777e-05,
|
2461 |
+
"loss": 0.0312,
|
2462 |
+
"step": 409
|
2463 |
+
},
|
2464 |
+
{
|
2465 |
+
"epoch": 5.19,
|
2466 |
+
"learning_rate": 6.412780960253436e-05,
|
2467 |
+
"loss": 0.0279,
|
2468 |
+
"step": 410
|
2469 |
+
},
|
2470 |
+
{
|
2471 |
+
"epoch": 5.2,
|
2472 |
+
"learning_rate": 6.397675913764347e-05,
|
2473 |
+
"loss": 0.0279,
|
2474 |
+
"step": 411
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 5.22,
|
2478 |
+
"learning_rate": 6.382557017434332e-05,
|
2479 |
+
"loss": 0.0198,
|
2480 |
+
"step": 412
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 5.23,
|
2484 |
+
"learning_rate": 6.367424421079463e-05,
|
2485 |
+
"loss": 0.0404,
|
2486 |
+
"step": 413
|
2487 |
+
},
|
2488 |
+
{
|
2489 |
+
"epoch": 5.24,
|
2490 |
+
"learning_rate": 6.352278274651561e-05,
|
2491 |
+
"loss": 0.0266,
|
2492 |
+
"step": 414
|
2493 |
+
},
|
2494 |
+
{
|
2495 |
+
"epoch": 5.25,
|
2496 |
+
"learning_rate": 6.337118728236721e-05,
|
2497 |
+
"loss": 0.0341,
|
2498 |
+
"step": 415
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 5.27,
|
2502 |
+
"learning_rate": 6.321945932053822e-05,
|
2503 |
+
"loss": 0.0205,
|
2504 |
+
"step": 416
|
2505 |
+
},
|
2506 |
+
{
|
2507 |
+
"epoch": 5.28,
|
2508 |
+
"learning_rate": 6.306760036453035e-05,
|
2509 |
+
"loss": 0.0341,
|
2510 |
+
"step": 417
|
2511 |
+
},
|
2512 |
+
{
|
2513 |
+
"epoch": 5.29,
|
2514 |
+
"learning_rate": 6.291561191914333e-05,
|
2515 |
+
"loss": 0.0398,
|
2516 |
+
"step": 418
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 5.3,
|
2520 |
+
"learning_rate": 6.276349549046007e-05,
|
2521 |
+
"loss": 0.0287,
|
2522 |
+
"step": 419
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 5.32,
|
2526 |
+
"learning_rate": 6.261125258583171e-05,
|
2527 |
+
"loss": 0.0491,
|
2528 |
+
"step": 420
|
2529 |
+
},
|
2530 |
+
{
|
2531 |
+
"epoch": 5.33,
|
2532 |
+
"learning_rate": 6.245888471386263e-05,
|
2533 |
+
"loss": 0.0235,
|
2534 |
+
"step": 421
|
2535 |
+
},
|
2536 |
+
{
|
2537 |
+
"epoch": 5.34,
|
2538 |
+
"learning_rate": 6.230639338439549e-05,
|
2539 |
+
"loss": 0.0312,
|
2540 |
+
"step": 422
|
2541 |
+
},
|
2542 |
+
{
|
2543 |
+
"epoch": 5.35,
|
2544 |
+
"learning_rate": 6.215378010849641e-05,
|
2545 |
+
"loss": 0.0413,
|
2546 |
+
"step": 423
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 5.37,
|
2550 |
+
"learning_rate": 6.200104639843985e-05,
|
2551 |
+
"loss": 0.0316,
|
2552 |
+
"step": 424
|
2553 |
+
},
|
2554 |
+
{
|
2555 |
+
"epoch": 5.38,
|
2556 |
+
"learning_rate": 6.184819376769364e-05,
|
2557 |
+
"loss": 0.044,
|
2558 |
+
"step": 425
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 5.39,
|
2562 |
+
"learning_rate": 6.169522373090412e-05,
|
2563 |
+
"loss": 0.0233,
|
2564 |
+
"step": 426
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 5.41,
|
2568 |
+
"learning_rate": 6.154213780388092e-05,
|
2569 |
+
"loss": 0.0152,
|
2570 |
+
"step": 427
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 5.42,
|
2574 |
+
"learning_rate": 6.138893750358212e-05,
|
2575 |
+
"loss": 0.0589,
|
2576 |
+
"step": 428
|
2577 |
+
},
|
2578 |
+
{
|
2579 |
+
"epoch": 5.43,
|
2580 |
+
"learning_rate": 6.123562434809912e-05,
|
2581 |
+
"loss": 0.0534,
|
2582 |
+
"step": 429
|
2583 |
+
},
|
2584 |
+
{
|
2585 |
+
"epoch": 5.44,
|
2586 |
+
"learning_rate": 6.108219985664161e-05,
|
2587 |
+
"loss": 0.0453,
|
2588 |
+
"step": 430
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"epoch": 5.46,
|
2592 |
+
"learning_rate": 6.0928665549522554e-05,
|
2593 |
+
"loss": 0.0252,
|
2594 |
+
"step": 431
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 5.47,
|
2598 |
+
"learning_rate": 6.0775022948143115e-05,
|
2599 |
+
"loss": 0.0337,
|
2600 |
+
"step": 432
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 5.48,
|
2604 |
+
"learning_rate": 6.06212735749775e-05,
|
2605 |
+
"loss": 0.0406,
|
2606 |
+
"step": 433
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 5.49,
|
2610 |
+
"learning_rate": 6.046741895355802e-05,
|
2611 |
+
"loss": 0.044,
|
2612 |
+
"step": 434
|
2613 |
+
},
|
2614 |
+
{
|
2615 |
+
"epoch": 5.51,
|
2616 |
+
"learning_rate": 6.031346060845986e-05,
|
2617 |
+
"loss": 0.0646,
|
2618 |
+
"step": 435
|
2619 |
+
},
|
2620 |
+
{
|
2621 |
+
"epoch": 5.52,
|
2622 |
+
"learning_rate": 6.015940006528602e-05,
|
2623 |
+
"loss": 0.0238,
|
2624 |
+
"step": 436
|
2625 |
+
},
|
2626 |
+
{
|
2627 |
+
"epoch": 5.53,
|
2628 |
+
"learning_rate": 6.0005238850652234e-05,
|
2629 |
+
"loss": 0.0517,
|
2630 |
+
"step": 437
|
2631 |
+
},
|
2632 |
+
{
|
2633 |
+
"epoch": 5.54,
|
2634 |
+
"learning_rate": 5.9850978492171794e-05,
|
2635 |
+
"loss": 0.0274,
|
2636 |
+
"step": 438
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 5.56,
|
2640 |
+
"learning_rate": 5.96966205184404e-05,
|
2641 |
+
"loss": 0.0247,
|
2642 |
+
"step": 439
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 5.57,
|
2646 |
+
"learning_rate": 5.954216645902109e-05,
|
2647 |
+
"loss": 0.0648,
|
2648 |
+
"step": 440
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 5.58,
|
2652 |
+
"learning_rate": 5.9387617844429e-05,
|
2653 |
+
"loss": 0.0282,
|
2654 |
+
"step": 441
|
2655 |
+
},
|
2656 |
+
{
|
2657 |
+
"epoch": 5.59,
|
2658 |
+
"learning_rate": 5.923297620611623e-05,
|
2659 |
+
"loss": 0.0537,
|
2660 |
+
"step": 442
|
2661 |
+
},
|
2662 |
+
{
|
2663 |
+
"epoch": 5.61,
|
2664 |
+
"learning_rate": 5.907824307645669e-05,
|
2665 |
+
"loss": 0.048,
|
2666 |
+
"step": 443
|
2667 |
+
},
|
2668 |
+
{
|
2669 |
+
"epoch": 5.62,
|
2670 |
+
"learning_rate": 5.892341998873089e-05,
|
2671 |
+
"loss": 0.0227,
|
2672 |
+
"step": 444
|
2673 |
+
},
|
2674 |
+
{
|
2675 |
+
"epoch": 5.63,
|
2676 |
+
"learning_rate": 5.876850847711073e-05,
|
2677 |
+
"loss": 0.0211,
|
2678 |
+
"step": 445
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 5.65,
|
2682 |
+
"learning_rate": 5.861351007664434e-05,
|
2683 |
+
"loss": 0.0318,
|
2684 |
+
"step": 446
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 5.66,
|
2688 |
+
"learning_rate": 5.845842632324088e-05,
|
2689 |
+
"loss": 0.0225,
|
2690 |
+
"step": 447
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 5.67,
|
2694 |
+
"learning_rate": 5.83032587536552e-05,
|
2695 |
+
"loss": 0.0482,
|
2696 |
+
"step": 448
|
2697 |
+
},
|
2698 |
+
{
|
2699 |
+
"epoch": 5.68,
|
2700 |
+
"learning_rate": 5.814800890547278e-05,
|
2701 |
+
"loss": 0.0543,
|
2702 |
+
"step": 449
|
2703 |
+
},
|
2704 |
+
{
|
2705 |
+
"epoch": 5.7,
|
2706 |
+
"learning_rate": 5.799267831709442e-05,
|
2707 |
+
"loss": 0.0264,
|
2708 |
+
"step": 450
|
2709 |
+
},
|
2710 |
+
{
|
2711 |
+
"epoch": 5.71,
|
2712 |
+
"learning_rate": 5.78372685277209e-05,
|
2713 |
+
"loss": 0.0311,
|
2714 |
+
"step": 451
|
2715 |
+
},
|
2716 |
+
{
|
2717 |
+
"epoch": 5.72,
|
2718 |
+
"learning_rate": 5.7681781077337905e-05,
|
2719 |
+
"loss": 0.0524,
|
2720 |
+
"step": 452
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 5.73,
|
2724 |
+
"learning_rate": 5.752621750670068e-05,
|
2725 |
+
"loss": 0.0186,
|
2726 |
+
"step": 453
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 5.75,
|
2730 |
+
"learning_rate": 5.737057935731868e-05,
|
2731 |
+
"loss": 0.0269,
|
2732 |
+
"step": 454
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 5.76,
|
2736 |
+
"learning_rate": 5.721486817144044e-05,
|
2737 |
+
"loss": 0.0312,
|
2738 |
+
"step": 455
|
2739 |
+
},
|
2740 |
+
{
|
2741 |
+
"epoch": 5.77,
|
2742 |
+
"learning_rate": 5.705908549203823e-05,
|
2743 |
+
"loss": 0.0356,
|
2744 |
+
"step": 456
|
2745 |
+
},
|
2746 |
+
{
|
2747 |
+
"epoch": 5.78,
|
2748 |
+
"learning_rate": 5.690323286279274e-05,
|
2749 |
+
"loss": 0.0507,
|
2750 |
+
"step": 457
|
2751 |
+
},
|
2752 |
+
{
|
2753 |
+
"epoch": 5.8,
|
2754 |
+
"learning_rate": 5.674731182807781e-05,
|
2755 |
+
"loss": 0.0399,
|
2756 |
+
"step": 458
|
2757 |
+
},
|
2758 |
+
{
|
2759 |
+
"epoch": 5.81,
|
2760 |
+
"learning_rate": 5.659132393294514e-05,
|
2761 |
+
"loss": 0.0364,
|
2762 |
+
"step": 459
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 5.82,
|
2766 |
+
"learning_rate": 5.643527072310891e-05,
|
2767 |
+
"loss": 0.0453,
|
2768 |
+
"step": 460
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 5.84,
|
2772 |
+
"learning_rate": 5.627915374493061e-05,
|
2773 |
+
"loss": 0.021,
|
2774 |
+
"step": 461
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 5.85,
|
2778 |
+
"learning_rate": 5.612297454540352e-05,
|
2779 |
+
"loss": 0.0155,
|
2780 |
+
"step": 462
|
2781 |
+
},
|
2782 |
+
{
|
2783 |
+
"epoch": 5.86,
|
2784 |
+
"learning_rate": 5.596673467213756e-05,
|
2785 |
+
"loss": 0.0336,
|
2786 |
+
"step": 463
|
2787 |
+
},
|
2788 |
+
{
|
2789 |
+
"epoch": 5.87,
|
2790 |
+
"learning_rate": 5.581043567334383e-05,
|
2791 |
+
"loss": 0.0245,
|
2792 |
+
"step": 464
|
2793 |
+
},
|
2794 |
+
{
|
2795 |
+
"epoch": 5.89,
|
2796 |
+
"learning_rate": 5.5654079097819345e-05,
|
2797 |
+
"loss": 0.0359,
|
2798 |
+
"step": 465
|
2799 |
+
},
|
2800 |
+
{
|
2801 |
+
"epoch": 5.9,
|
2802 |
+
"learning_rate": 5.5497666494931654e-05,
|
2803 |
+
"loss": 0.0245,
|
2804 |
+
"step": 466
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 5.91,
|
2808 |
+
"learning_rate": 5.5341199414603493e-05,
|
2809 |
+
"loss": 0.0246,
|
2810 |
+
"step": 467
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 5.92,
|
2814 |
+
"learning_rate": 5.518467940729739e-05,
|
2815 |
+
"loss": 0.0222,
|
2816 |
+
"step": 468
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 5.94,
|
2820 |
+
"learning_rate": 5.502810802400039e-05,
|
2821 |
+
"loss": 0.0317,
|
2822 |
+
"step": 469
|
2823 |
+
},
|
2824 |
+
{
|
2825 |
+
"epoch": 5.95,
|
2826 |
+
"learning_rate": 5.487148681620862e-05,
|
2827 |
+
"loss": 0.0199,
|
2828 |
+
"step": 470
|
2829 |
+
},
|
2830 |
+
{
|
2831 |
+
"epoch": 5.96,
|
2832 |
+
"learning_rate": 5.4714817335911894e-05,
|
2833 |
+
"loss": 0.0559,
|
2834 |
+
"step": 471
|
2835 |
+
},
|
2836 |
+
{
|
2837 |
+
"epoch": 5.97,
|
2838 |
+
"learning_rate": 5.455810113557839e-05,
|
2839 |
+
"loss": 0.0405,
|
2840 |
+
"step": 472
|
2841 |
+
},
|
2842 |
+
{
|
2843 |
+
"epoch": 5.99,
|
2844 |
+
"learning_rate": 5.440133976813926e-05,
|
2845 |
+
"loss": 0.0416,
|
2846 |
+
"step": 473
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 6.0,
|
2850 |
+
"learning_rate": 5.4244534786973214e-05,
|
2851 |
+
"loss": 0.0208,
|
2852 |
+
"step": 474
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 6.01,
|
2856 |
+
"learning_rate": 5.40876877458911e-05,
|
2857 |
+
"loss": 0.0295,
|
2858 |
+
"step": 475
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 6.03,
|
2862 |
+
"learning_rate": 5.3930800199120616e-05,
|
2863 |
+
"loss": 0.0106,
|
2864 |
+
"step": 476
|
2865 |
+
},
|
2866 |
+
{
|
2867 |
+
"epoch": 6.04,
|
2868 |
+
"learning_rate": 5.377387370129079e-05,
|
2869 |
+
"loss": 0.0165,
|
2870 |
+
"step": 477
|
2871 |
+
},
|
2872 |
+
{
|
2873 |
+
"epoch": 6.05,
|
2874 |
+
"learning_rate": 5.361690980741663e-05,
|
2875 |
+
"loss": 0.0098,
|
2876 |
+
"step": 478
|
2877 |
+
},
|
2878 |
+
{
|
2879 |
+
"epoch": 6.06,
|
2880 |
+
"learning_rate": 5.345991007288371e-05,
|
2881 |
+
"loss": 0.0259,
|
2882 |
+
"step": 479
|
2883 |
+
},
|
2884 |
+
{
|
2885 |
+
"epoch": 6.08,
|
2886 |
+
"learning_rate": 5.330287605343279e-05,
|
2887 |
+
"loss": 0.0065,
|
2888 |
+
"step": 480
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 6.09,
|
2892 |
+
"learning_rate": 5.314580930514431e-05,
|
2893 |
+
"loss": 0.0162,
|
2894 |
+
"step": 481
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 6.1,
|
2898 |
+
"learning_rate": 5.298871138442307e-05,
|
2899 |
+
"loss": 0.0107,
|
2900 |
+
"step": 482
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 6.11,
|
2904 |
+
"learning_rate": 5.283158384798275e-05,
|
2905 |
+
"loss": 0.0126,
|
2906 |
+
"step": 483
|
2907 |
+
},
|
2908 |
+
{
|
2909 |
+
"epoch": 6.13,
|
2910 |
+
"learning_rate": 5.267442825283048e-05,
|
2911 |
+
"loss": 0.0275,
|
2912 |
+
"step": 484
|
2913 |
+
},
|
2914 |
+
{
|
2915 |
+
"epoch": 6.14,
|
2916 |
+
"learning_rate": 5.2517246156251455e-05,
|
2917 |
+
"loss": 0.022,
|
2918 |
+
"step": 485
|
2919 |
+
},
|
2920 |
+
{
|
2921 |
+
"epoch": 6.15,
|
2922 |
+
"learning_rate": 5.236003911579345e-05,
|
2923 |
+
"loss": 0.0101,
|
2924 |
+
"step": 486
|
2925 |
+
},
|
2926 |
+
{
|
2927 |
+
"epoch": 6.16,
|
2928 |
+
"learning_rate": 5.220280868925145e-05,
|
2929 |
+
"loss": 0.0189,
|
2930 |
+
"step": 487
|
2931 |
+
},
|
2932 |
+
{
|
2933 |
+
"epoch": 6.18,
|
2934 |
+
"learning_rate": 5.204555643465215e-05,
|
2935 |
+
"loss": 0.0205,
|
2936 |
+
"step": 488
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 6.19,
|
2940 |
+
"learning_rate": 5.1888283910238555e-05,
|
2941 |
+
"loss": 0.0123,
|
2942 |
+
"step": 489
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 6.2,
|
2946 |
+
"learning_rate": 5.173099267445451e-05,
|
2947 |
+
"loss": 0.015,
|
2948 |
+
"step": 490
|
2949 |
+
},
|
2950 |
+
{
|
2951 |
+
"epoch": 6.22,
|
2952 |
+
"learning_rate": 5.157368428592933e-05,
|
2953 |
+
"loss": 0.0116,
|
2954 |
+
"step": 491
|
2955 |
+
},
|
2956 |
+
{
|
2957 |
+
"epoch": 6.23,
|
2958 |
+
"learning_rate": 5.1416360303462206e-05,
|
2959 |
+
"loss": 0.0219,
|
2960 |
+
"step": 492
|
2961 |
+
},
|
2962 |
+
{
|
2963 |
+
"epoch": 6.24,
|
2964 |
+
"learning_rate": 5.125902228600693e-05,
|
2965 |
+
"loss": 0.0095,
|
2966 |
+
"step": 493
|
2967 |
+
},
|
2968 |
+
{
|
2969 |
+
"epoch": 6.25,
|
2970 |
+
"learning_rate": 5.110167179265636e-05,
|
2971 |
+
"loss": 0.0287,
|
2972 |
+
"step": 494
|
2973 |
+
},
|
2974 |
+
{
|
2975 |
+
"epoch": 6.27,
|
2976 |
+
"learning_rate": 5.094431038262693e-05,
|
2977 |
+
"loss": 0.0184,
|
2978 |
+
"step": 495
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 6.28,
|
2982 |
+
"learning_rate": 5.078693961524329e-05,
|
2983 |
+
"loss": 0.0118,
|
2984 |
+
"step": 496
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 6.29,
|
2988 |
+
"learning_rate": 5.062956104992285e-05,
|
2989 |
+
"loss": 0.0147,
|
2990 |
+
"step": 497
|
2991 |
+
},
|
2992 |
+
{
|
2993 |
+
"epoch": 6.3,
|
2994 |
+
"learning_rate": 5.0472176246160184e-05,
|
2995 |
+
"loss": 0.02,
|
2996 |
+
"step": 498
|
2997 |
+
},
|
2998 |
+
{
|
2999 |
+
"epoch": 6.32,
|
3000 |
+
"learning_rate": 5.031478676351179e-05,
|
3001 |
+
"loss": 0.0126,
|
3002 |
+
"step": 499
|
3003 |
+
},
|
3004 |
+
{
|
3005 |
+
"epoch": 6.33,
|
3006 |
+
"learning_rate": 5.01573941615805e-05,
|
3007 |
+
"loss": 0.0118,
|
3008 |
+
"step": 500
|
3009 |
+
}
|
3010 |
+
],
|
3011 |
+
"max_steps": 1000,
|
3012 |
+
"num_train_epochs": 13,
|
3013 |
+
"total_flos": 3.637158979269427e+16,
|
3014 |
+
"trial_name": null,
|
3015 |
+
"trial_params": null
|
3016 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81c62a959e27e1dcebe486f2a3497d27f677eab0ef5a5ac731fd0ff4edfce99a
|
3 |
+
size 4408
|
runs/Feb19_03-58-39_26c175d8c062/events.out.tfevents.1708315257.26c175d8c062.3854.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e8e7c8b7c94db760866a54ec5d2bbf8df672d55f99d58c6926d583217cfefe9
|
3 |
+
size 161360
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "</s>"
|
6 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"legacy": false,
|
22 |
+
"model_max_length": 2048,
|
23 |
+
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
+
"sp_model_kwargs": {},
|
26 |
+
"tokenizer_class": "LlamaTokenizer",
|
27 |
+
"unk_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81c62a959e27e1dcebe486f2a3497d27f677eab0ef5a5ac731fd0ff4edfce99a
|
3 |
+
size 4408
|