Upload 19 files
Browse files- README.md +206 -1
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
- trainer_state.json +1843 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,208 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-7b
|
| 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 |
+
## Training procedure
|
| 203 |
+
|
| 204 |
+
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
- PEFT 0.6.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b",
|
| 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 |
+
"lora_alpha": 32.0,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 8,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72f5e1f6b4f1d0f96c14aec0a124ee6867902f1e2e939e2565a045e4da47b831
|
| 3 |
+
size 16822989
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be8444677690e53ddb99a8f6f895cccb85ace8b6f385b55c7d5e85a62949984f
|
| 3 |
+
size 33661637
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8251d8f2b0fc0cd0c0d56e2beb546eb9d3b4156fea129e91f75ca4c14a2931fa
|
| 3 |
+
size 21687
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8530960ee052ed37301950c215da1cc034198cfb1659240a9f775ee3f9243c29
|
| 3 |
+
size 21687
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a99bc7161b8a3f49a75902cb67c3bec844650d768bf96d5f61c103978d23016
|
| 3 |
+
size 21687
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779d33845dcd2509de12044f457f5df70d1c4456d7acbd2ae6dbf99df02e82b5
|
| 3 |
+
size 21687
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7db5487a729d03070fa47b053aadb513c2a808e5f486449c82652e5d1f99abf
|
| 3 |
+
size 21687
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c29da6fca89711eeb0c506a92e0fbfbeed7c24a9eabb8067c33fd39f985560fa
|
| 3 |
+
size 21687
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b9484dbf00daa2647852b1f6eb4c9ec993309824045af6768e41c4ae9580a9
|
| 3 |
+
size 21687
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a842f826ca55e42c7ef2034d963b73cbdcac887f3512db1af34850e9f474be1
|
| 3 |
+
size 21687
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ce26047232a7fdc322fc0d9c90224b0fa0a830b4792d534b7ea0a4c861a5843
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"split_special_tokens": false,
|
| 25 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"use_default_system_prompt": true
|
| 35 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.7007369822924607,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1520000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.9999270159623114e-05,
|
| 14 |
+
"loss": 0.1271,
|
| 15 |
+
"step": 5000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.999707892753202e-05,
|
| 20 |
+
"loss": 0.0859,
|
| 21 |
+
"step": 10000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 4.9993426431557147e-05,
|
| 26 |
+
"loss": 0.0768,
|
| 27 |
+
"step": 15000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 4.9988311715921104e-05,
|
| 32 |
+
"loss": 0.0727,
|
| 33 |
+
"step": 20000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 4.9981738587426694e-05,
|
| 38 |
+
"loss": 0.0693,
|
| 39 |
+
"step": 25000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 4.997370216884145e-05,
|
| 44 |
+
"loss": 0.0677,
|
| 45 |
+
"step": 30000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 4.9964207314440955e-05,
|
| 50 |
+
"loss": 0.0659,
|
| 51 |
+
"step": 35000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 4.995325311774524e-05,
|
| 56 |
+
"loss": 0.0657,
|
| 57 |
+
"step": 40000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.11,
|
| 61 |
+
"learning_rate": 4.994084284853358e-05,
|
| 62 |
+
"loss": 0.0638,
|
| 63 |
+
"step": 45000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.12,
|
| 67 |
+
"learning_rate": 4.992697226521413e-05,
|
| 68 |
+
"loss": 0.0623,
|
| 69 |
+
"step": 50000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 4.991164130374091e-05,
|
| 74 |
+
"loss": 0.0615,
|
| 75 |
+
"step": 55000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.15,
|
| 79 |
+
"learning_rate": 4.9894856993903285e-05,
|
| 80 |
+
"loss": 0.0608,
|
| 81 |
+
"step": 60000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.16,
|
| 85 |
+
"learning_rate": 4.987661739580889e-05,
|
| 86 |
+
"loss": 0.0604,
|
| 87 |
+
"step": 65000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.17,
|
| 91 |
+
"learning_rate": 4.985691948992265e-05,
|
| 92 |
+
"loss": 0.0599,
|
| 93 |
+
"step": 70000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18,
|
| 97 |
+
"learning_rate": 4.983577230843278e-05,
|
| 98 |
+
"loss": 0.0591,
|
| 99 |
+
"step": 75000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.19,
|
| 103 |
+
"learning_rate": 4.981317329262237e-05,
|
| 104 |
+
"loss": 0.0586,
|
| 105 |
+
"step": 80000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.21,
|
| 109 |
+
"learning_rate": 4.9789118806694247e-05,
|
| 110 |
+
"loss": 0.0587,
|
| 111 |
+
"step": 85000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.22,
|
| 115 |
+
"learning_rate": 4.976361988048301e-05,
|
| 116 |
+
"loss": 0.0576,
|
| 117 |
+
"step": 90000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.23,
|
| 121 |
+
"learning_rate": 4.9736673337793535e-05,
|
| 122 |
+
"loss": 0.0576,
|
| 123 |
+
"step": 95000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.24,
|
| 127 |
+
"learning_rate": 4.970828075385029e-05,
|
| 128 |
+
"loss": 0.0566,
|
| 129 |
+
"step": 100000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.26,
|
| 133 |
+
"learning_rate": 4.967844378840947e-05,
|
| 134 |
+
"loss": 0.0567,
|
| 135 |
+
"step": 105000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.27,
|
| 139 |
+
"learning_rate": 4.964715778300843e-05,
|
| 140 |
+
"loss": 0.0567,
|
| 141 |
+
"step": 110000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.28,
|
| 145 |
+
"learning_rate": 4.961443708338981e-05,
|
| 146 |
+
"loss": 0.0568,
|
| 147 |
+
"step": 115000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.29,
|
| 151 |
+
"learning_rate": 4.9580277488129266e-05,
|
| 152 |
+
"loss": 0.057,
|
| 153 |
+
"step": 120000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.3,
|
| 157 |
+
"learning_rate": 4.954467372832107e-05,
|
| 158 |
+
"loss": 0.0551,
|
| 159 |
+
"step": 125000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.32,
|
| 163 |
+
"learning_rate": 4.9507634576843017e-05,
|
| 164 |
+
"loss": 0.0549,
|
| 165 |
+
"step": 130000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.33,
|
| 169 |
+
"learning_rate": 4.9469185717167566e-05,
|
| 170 |
+
"loss": 0.0563,
|
| 171 |
+
"step": 135000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.34,
|
| 175 |
+
"learning_rate": 4.942928322246712e-05,
|
| 176 |
+
"loss": 0.0546,
|
| 177 |
+
"step": 140000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.35,
|
| 181 |
+
"learning_rate": 4.938796049480949e-05,
|
| 182 |
+
"loss": 0.0538,
|
| 183 |
+
"step": 145000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.37,
|
| 187 |
+
"learning_rate": 4.934520341515526e-05,
|
| 188 |
+
"loss": 0.0548,
|
| 189 |
+
"step": 150000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.38,
|
| 193 |
+
"learning_rate": 4.930104056921508e-05,
|
| 194 |
+
"loss": 0.0541,
|
| 195 |
+
"step": 155000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.39,
|
| 199 |
+
"learning_rate": 4.925543918835136e-05,
|
| 200 |
+
"loss": 0.0543,
|
| 201 |
+
"step": 160000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.4,
|
| 205 |
+
"learning_rate": 4.920843842545973e-05,
|
| 206 |
+
"loss": 0.0538,
|
| 207 |
+
"step": 165000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.41,
|
| 211 |
+
"learning_rate": 4.9160003406180696e-05,
|
| 212 |
+
"loss": 0.0539,
|
| 213 |
+
"step": 170000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.43,
|
| 217 |
+
"learning_rate": 4.9110165603726345e-05,
|
| 218 |
+
"loss": 0.0536,
|
| 219 |
+
"step": 175000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.44,
|
| 223 |
+
"learning_rate": 4.9058918384022446e-05,
|
| 224 |
+
"loss": 0.0537,
|
| 225 |
+
"step": 180000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.45,
|
| 229 |
+
"learning_rate": 4.900625406738267e-05,
|
| 230 |
+
"loss": 0.0535,
|
| 231 |
+
"step": 185000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.46,
|
| 235 |
+
"learning_rate": 4.895219680226333e-05,
|
| 236 |
+
"loss": 0.0527,
|
| 237 |
+
"step": 190000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.47,
|
| 241 |
+
"learning_rate": 4.889673935433758e-05,
|
| 242 |
+
"loss": 0.0538,
|
| 243 |
+
"step": 195000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.49,
|
| 247 |
+
"learning_rate": 4.8839896480432604e-05,
|
| 248 |
+
"loss": 0.0531,
|
| 249 |
+
"step": 200000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5,
|
| 253 |
+
"learning_rate": 4.878163695931812e-05,
|
| 254 |
+
"loss": 0.0527,
|
| 255 |
+
"step": 205000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.51,
|
| 259 |
+
"learning_rate": 4.872198666951938e-05,
|
| 260 |
+
"loss": 0.0531,
|
| 261 |
+
"step": 210000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.52,
|
| 265 |
+
"learning_rate": 4.8660961447879297e-05,
|
| 266 |
+
"loss": 0.0524,
|
| 267 |
+
"step": 215000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.54,
|
| 271 |
+
"learning_rate": 4.859854044346287e-05,
|
| 272 |
+
"loss": 0.0527,
|
| 273 |
+
"step": 220000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.55,
|
| 277 |
+
"learning_rate": 4.853475227851366e-05,
|
| 278 |
+
"loss": 0.0523,
|
| 279 |
+
"step": 225000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.56,
|
| 283 |
+
"learning_rate": 4.8469588333473586e-05,
|
| 284 |
+
"loss": 0.0524,
|
| 285 |
+
"step": 230000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.57,
|
| 289 |
+
"learning_rate": 4.8403052417656516e-05,
|
| 290 |
+
"loss": 0.0521,
|
| 291 |
+
"step": 235000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.58,
|
| 295 |
+
"learning_rate": 4.833514842057813e-05,
|
| 296 |
+
"loss": 0.0518,
|
| 297 |
+
"step": 240000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6,
|
| 301 |
+
"learning_rate": 4.826586631633889e-05,
|
| 302 |
+
"loss": 0.052,
|
| 303 |
+
"step": 245000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.61,
|
| 307 |
+
"learning_rate": 4.8195237873239866e-05,
|
| 308 |
+
"loss": 0.0525,
|
| 309 |
+
"step": 250000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.62,
|
| 313 |
+
"learning_rate": 4.8123253497174505e-05,
|
| 314 |
+
"loss": 0.0514,
|
| 315 |
+
"step": 255000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.63,
|
| 319 |
+
"learning_rate": 4.804991739616124e-05,
|
| 320 |
+
"loss": 0.0515,
|
| 321 |
+
"step": 260000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.65,
|
| 325 |
+
"learning_rate": 4.7975233857236826e-05,
|
| 326 |
+
"loss": 0.0524,
|
| 327 |
+
"step": 265000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.66,
|
| 331 |
+
"learning_rate": 4.789920724620569e-05,
|
| 332 |
+
"loss": 0.0506,
|
| 333 |
+
"step": 270000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.67,
|
| 337 |
+
"learning_rate": 4.7821857620213536e-05,
|
| 338 |
+
"loss": 0.0513,
|
| 339 |
+
"step": 275000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.68,
|
| 343 |
+
"learning_rate": 4.774314266334363e-05,
|
| 344 |
+
"loss": 0.0513,
|
| 345 |
+
"step": 280000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.69,
|
| 349 |
+
"learning_rate": 4.7663097669746146e-05,
|
| 350 |
+
"loss": 0.0512,
|
| 351 |
+
"step": 285000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.71,
|
| 355 |
+
"learning_rate": 4.75817437300597e-05,
|
| 356 |
+
"loss": 0.0508,
|
| 357 |
+
"step": 290000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.72,
|
| 361 |
+
"learning_rate": 4.749905304748714e-05,
|
| 362 |
+
"loss": 0.0515,
|
| 363 |
+
"step": 295000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.73,
|
| 367 |
+
"learning_rate": 4.741504660273818e-05,
|
| 368 |
+
"loss": 0.0504,
|
| 369 |
+
"step": 300000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.74,
|
| 373 |
+
"learning_rate": 4.732974650620106e-05,
|
| 374 |
+
"loss": 0.0504,
|
| 375 |
+
"step": 305000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.75,
|
| 379 |
+
"learning_rate": 4.724315852930218e-05,
|
| 380 |
+
"loss": 0.0506,
|
| 381 |
+
"step": 310000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.77,
|
| 385 |
+
"learning_rate": 4.715523536004309e-05,
|
| 386 |
+
"loss": 0.0496,
|
| 387 |
+
"step": 315000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.78,
|
| 391 |
+
"learning_rate": 4.706605248838939e-05,
|
| 392 |
+
"loss": 0.0503,
|
| 393 |
+
"step": 320000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.79,
|
| 397 |
+
"learning_rate": 4.697554374104222e-05,
|
| 398 |
+
"loss": 0.0504,
|
| 399 |
+
"step": 325000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.8,
|
| 403 |
+
"learning_rate": 4.6883749846751347e-05,
|
| 404 |
+
"loss": 0.05,
|
| 405 |
+
"step": 330000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.82,
|
| 409 |
+
"learning_rate": 4.679069491976989e-05,
|
| 410 |
+
"loss": 0.0497,
|
| 411 |
+
"step": 335000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.83,
|
| 415 |
+
"learning_rate": 4.6696347165338586e-05,
|
| 416 |
+
"loss": 0.0503,
|
| 417 |
+
"step": 340000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.84,
|
| 421 |
+
"learning_rate": 4.660074984524773e-05,
|
| 422 |
+
"loss": 0.0503,
|
| 423 |
+
"step": 345000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.85,
|
| 427 |
+
"learning_rate": 4.650388980179216e-05,
|
| 428 |
+
"loss": 0.0493,
|
| 429 |
+
"step": 350000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.86,
|
| 433 |
+
"learning_rate": 4.6405752940483196e-05,
|
| 434 |
+
"loss": 0.0503,
|
| 435 |
+
"step": 355000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.88,
|
| 439 |
+
"learning_rate": 4.6306384260551005e-05,
|
| 440 |
+
"loss": 0.0502,
|
| 441 |
+
"step": 360000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.89,
|
| 445 |
+
"learning_rate": 4.620577006509662e-05,
|
| 446 |
+
"loss": 0.0493,
|
| 447 |
+
"step": 365000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.9,
|
| 451 |
+
"learning_rate": 4.6103916235762854e-05,
|
| 452 |
+
"loss": 0.05,
|
| 453 |
+
"step": 370000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.91,
|
| 457 |
+
"learning_rate": 4.600082872665831e-05,
|
| 458 |
+
"loss": 0.0492,
|
| 459 |
+
"step": 375000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.93,
|
| 463 |
+
"learning_rate": 4.589651356400925e-05,
|
| 464 |
+
"loss": 0.0499,
|
| 465 |
+
"step": 380000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.94,
|
| 469 |
+
"learning_rate": 4.5790976845807375e-05,
|
| 470 |
+
"loss": 0.0492,
|
| 471 |
+
"step": 385000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.95,
|
| 475 |
+
"learning_rate": 4.568422474145333e-05,
|
| 476 |
+
"loss": 0.0496,
|
| 477 |
+
"step": 390000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.96,
|
| 481 |
+
"learning_rate": 4.5576241769938385e-05,
|
| 482 |
+
"loss": 0.0496,
|
| 483 |
+
"step": 395000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.97,
|
| 487 |
+
"learning_rate": 4.5467099406767963e-05,
|
| 488 |
+
"loss": 0.0491,
|
| 489 |
+
"step": 400000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.99,
|
| 493 |
+
"learning_rate": 4.535671666878825e-05,
|
| 494 |
+
"loss": 0.0492,
|
| 495 |
+
"step": 405000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.0,
|
| 499 |
+
"learning_rate": 4.52451883295289e-05,
|
| 500 |
+
"loss": 0.049,
|
| 501 |
+
"step": 410000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.01,
|
| 505 |
+
"learning_rate": 4.513245430925934e-05,
|
| 506 |
+
"loss": 0.048,
|
| 507 |
+
"step": 415000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.02,
|
| 511 |
+
"learning_rate": 4.5018543398343515e-05,
|
| 512 |
+
"loss": 0.0472,
|
| 513 |
+
"step": 420000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.03,
|
| 517 |
+
"learning_rate": 4.4903415971499975e-05,
|
| 518 |
+
"loss": 0.0463,
|
| 519 |
+
"step": 425000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.05,
|
| 523 |
+
"learning_rate": 4.47871708602701e-05,
|
| 524 |
+
"loss": 0.047,
|
| 525 |
+
"step": 430000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.06,
|
| 529 |
+
"learning_rate": 4.46697926477584e-05,
|
| 530 |
+
"loss": 0.0472,
|
| 531 |
+
"step": 435000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.07,
|
| 535 |
+
"learning_rate": 4.455119354756587e-05,
|
| 536 |
+
"loss": 0.0466,
|
| 537 |
+
"step": 440000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.08,
|
| 541 |
+
"learning_rate": 4.443154687048235e-05,
|
| 542 |
+
"loss": 0.047,
|
| 543 |
+
"step": 445000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.1,
|
| 547 |
+
"learning_rate": 4.4310692318277604e-05,
|
| 548 |
+
"loss": 0.047,
|
| 549 |
+
"step": 450000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.11,
|
| 553 |
+
"learning_rate": 4.418870846171951e-05,
|
| 554 |
+
"loss": 0.047,
|
| 555 |
+
"step": 455000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.12,
|
| 559 |
+
"learning_rate": 4.406562717238809e-05,
|
| 560 |
+
"loss": 0.0462,
|
| 561 |
+
"step": 460000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.13,
|
| 565 |
+
"learning_rate": 4.394145631643063e-05,
|
| 566 |
+
"loss": 0.0471,
|
| 567 |
+
"step": 465000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.14,
|
| 571 |
+
"learning_rate": 4.381615345463161e-05,
|
| 572 |
+
"loss": 0.0475,
|
| 573 |
+
"step": 470000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.16,
|
| 577 |
+
"learning_rate": 4.368972524944734e-05,
|
| 578 |
+
"loss": 0.0467,
|
| 579 |
+
"step": 475000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.17,
|
| 583 |
+
"learning_rate": 4.3562229672692154e-05,
|
| 584 |
+
"loss": 0.0467,
|
| 585 |
+
"step": 480000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.18,
|
| 589 |
+
"learning_rate": 4.3433674830975235e-05,
|
| 590 |
+
"loss": 0.0463,
|
| 591 |
+
"step": 485000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.19,
|
| 595 |
+
"learning_rate": 4.3303990737414704e-05,
|
| 596 |
+
"loss": 0.0463,
|
| 597 |
+
"step": 490000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.21,
|
| 601 |
+
"learning_rate": 4.317326247486547e-05,
|
| 602 |
+
"loss": 0.0466,
|
| 603 |
+
"step": 495000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.22,
|
| 607 |
+
"learning_rate": 4.304147185090266e-05,
|
| 608 |
+
"loss": 0.0463,
|
| 609 |
+
"step": 500000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.23,
|
| 613 |
+
"learning_rate": 4.290859988496148e-05,
|
| 614 |
+
"loss": 0.0466,
|
| 615 |
+
"step": 505000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.24,
|
| 619 |
+
"learning_rate": 4.277470750354905e-05,
|
| 620 |
+
"loss": 0.0461,
|
| 621 |
+
"step": 510000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.25,
|
| 625 |
+
"learning_rate": 4.263980315969459e-05,
|
| 626 |
+
"loss": 0.0463,
|
| 627 |
+
"step": 515000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.27,
|
| 631 |
+
"learning_rate": 4.250381343966794e-05,
|
| 632 |
+
"loss": 0.0463,
|
| 633 |
+
"step": 520000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.28,
|
| 637 |
+
"learning_rate": 4.236680008297452e-05,
|
| 638 |
+
"loss": 0.0467,
|
| 639 |
+
"step": 525000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.29,
|
| 643 |
+
"learning_rate": 4.222879881460605e-05,
|
| 644 |
+
"loss": 0.046,
|
| 645 |
+
"step": 530000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.3,
|
| 649 |
+
"learning_rate": 4.2089790395700444e-05,
|
| 650 |
+
"loss": 0.0465,
|
| 651 |
+
"step": 535000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.31,
|
| 655 |
+
"learning_rate": 4.194978295232646e-05,
|
| 656 |
+
"loss": 0.0471,
|
| 657 |
+
"step": 540000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.33,
|
| 661 |
+
"learning_rate": 4.180875635941759e-05,
|
| 662 |
+
"loss": 0.046,
|
| 663 |
+
"step": 545000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.34,
|
| 667 |
+
"learning_rate": 4.1666746777322316e-05,
|
| 668 |
+
"loss": 0.0463,
|
| 669 |
+
"step": 550000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.35,
|
| 673 |
+
"learning_rate": 4.1523819909804684e-05,
|
| 674 |
+
"loss": 0.0464,
|
| 675 |
+
"step": 555000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.36,
|
| 679 |
+
"learning_rate": 4.1379869705757123e-05,
|
| 680 |
+
"loss": 0.0462,
|
| 681 |
+
"step": 560000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.38,
|
| 685 |
+
"learning_rate": 4.123501975940446e-05,
|
| 686 |
+
"loss": 0.0466,
|
| 687 |
+
"step": 565000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.39,
|
| 691 |
+
"learning_rate": 4.108916259272307e-05,
|
| 692 |
+
"loss": 0.0462,
|
| 693 |
+
"step": 570000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.4,
|
| 697 |
+
"learning_rate": 4.094239397826731e-05,
|
| 698 |
+
"loss": 0.0471,
|
| 699 |
+
"step": 575000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.41,
|
| 703 |
+
"learning_rate": 4.079466376852837e-05,
|
| 704 |
+
"loss": 0.0456,
|
| 705 |
+
"step": 580000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.42,
|
| 709 |
+
"learning_rate": 4.064606953152425e-05,
|
| 710 |
+
"loss": 0.0459,
|
| 711 |
+
"step": 585000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.44,
|
| 715 |
+
"learning_rate": 4.049653102158943e-05,
|
| 716 |
+
"loss": 0.0464,
|
| 717 |
+
"step": 590000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.45,
|
| 721 |
+
"learning_rate": 4.034608662496395e-05,
|
| 722 |
+
"loss": 0.0453,
|
| 723 |
+
"step": 595000
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.46,
|
| 727 |
+
"learning_rate": 4.019474513623393e-05,
|
| 728 |
+
"loss": 0.0466,
|
| 729 |
+
"step": 600000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.47,
|
| 733 |
+
"learning_rate": 4.004248485601213e-05,
|
| 734 |
+
"loss": 0.046,
|
| 735 |
+
"step": 605000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.49,
|
| 739 |
+
"learning_rate": 3.9889375601035114e-05,
|
| 740 |
+
"loss": 0.0454,
|
| 741 |
+
"step": 610000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.5,
|
| 745 |
+
"learning_rate": 3.973536505734094e-05,
|
| 746 |
+
"loss": 0.0456,
|
| 747 |
+
"step": 615000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.51,
|
| 751 |
+
"learning_rate": 3.958049277800142e-05,
|
| 752 |
+
"loss": 0.045,
|
| 753 |
+
"step": 620000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.52,
|
| 757 |
+
"learning_rate": 3.94248302918014e-05,
|
| 758 |
+
"loss": 0.0452,
|
| 759 |
+
"step": 625000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.53,
|
| 763 |
+
"learning_rate": 3.9268262097860184e-05,
|
| 764 |
+
"loss": 0.0458,
|
| 765 |
+
"step": 630000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.55,
|
| 769 |
+
"learning_rate": 3.911089105446822e-05,
|
| 770 |
+
"loss": 0.0455,
|
| 771 |
+
"step": 635000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.56,
|
| 775 |
+
"learning_rate": 3.895269512527556e-05,
|
| 776 |
+
"loss": 0.0453,
|
| 777 |
+
"step": 640000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.57,
|
| 781 |
+
"learning_rate": 3.879368355800267e-05,
|
| 782 |
+
"loss": 0.0459,
|
| 783 |
+
"step": 645000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.58,
|
| 787 |
+
"learning_rate": 3.863386564805006e-05,
|
| 788 |
+
"loss": 0.0458,
|
| 789 |
+
"step": 650000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.59,
|
| 793 |
+
"learning_rate": 3.8473250737954924e-05,
|
| 794 |
+
"loss": 0.0452,
|
| 795 |
+
"step": 655000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.61,
|
| 799 |
+
"learning_rate": 3.831181584524374e-05,
|
| 800 |
+
"loss": 0.046,
|
| 801 |
+
"step": 660000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.62,
|
| 805 |
+
"learning_rate": 3.8149602467155784e-05,
|
| 806 |
+
"loss": 0.0454,
|
| 807 |
+
"step": 665000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.63,
|
| 811 |
+
"learning_rate": 3.7986652769317283e-05,
|
| 812 |
+
"loss": 0.0454,
|
| 813 |
+
"step": 670000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.64,
|
| 817 |
+
"learning_rate": 3.782291107551002e-05,
|
| 818 |
+
"loss": 0.0455,
|
| 819 |
+
"step": 675000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.66,
|
| 823 |
+
"learning_rate": 3.7658452467105766e-05,
|
| 824 |
+
"loss": 0.0453,
|
| 825 |
+
"step": 680000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.67,
|
| 829 |
+
"learning_rate": 3.7493287004972016e-05,
|
| 830 |
+
"loss": 0.0461,
|
| 831 |
+
"step": 685000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.68,
|
| 835 |
+
"learning_rate": 3.7327324967260834e-05,
|
| 836 |
+
"loss": 0.045,
|
| 837 |
+
"step": 690000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.69,
|
| 841 |
+
"learning_rate": 3.716067543266813e-05,
|
| 842 |
+
"loss": 0.0453,
|
| 843 |
+
"step": 695000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.7,
|
| 847 |
+
"learning_rate": 3.6993281460825346e-05,
|
| 848 |
+
"loss": 0.0454,
|
| 849 |
+
"step": 700000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.72,
|
| 853 |
+
"learning_rate": 3.682521980780319e-05,
|
| 854 |
+
"loss": 0.0455,
|
| 855 |
+
"step": 705000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.73,
|
| 859 |
+
"learning_rate": 3.665646688334596e-05,
|
| 860 |
+
"loss": 0.0445,
|
| 861 |
+
"step": 710000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.74,
|
| 865 |
+
"learning_rate": 3.648706652022939e-05,
|
| 866 |
+
"loss": 0.0448,
|
| 867 |
+
"step": 715000
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.75,
|
| 871 |
+
"learning_rate": 3.631692671937868e-05,
|
| 872 |
+
"loss": 0.0444,
|
| 873 |
+
"step": 720000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.77,
|
| 877 |
+
"learning_rate": 3.6146125095823744e-05,
|
| 878 |
+
"loss": 0.0449,
|
| 879 |
+
"step": 725000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.78,
|
| 883 |
+
"learning_rate": 3.597474036228449e-05,
|
| 884 |
+
"loss": 0.0453,
|
| 885 |
+
"step": 730000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.79,
|
| 889 |
+
"learning_rate": 3.580264535204181e-05,
|
| 890 |
+
"loss": 0.0447,
|
| 891 |
+
"step": 735000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.8,
|
| 895 |
+
"learning_rate": 3.562995320943442e-05,
|
| 896 |
+
"loss": 0.0441,
|
| 897 |
+
"step": 740000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.81,
|
| 901 |
+
"learning_rate": 3.545660492947155e-05,
|
| 902 |
+
"loss": 0.0448,
|
| 903 |
+
"step": 745000
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.83,
|
| 907 |
+
"learning_rate": 3.52826799984853e-05,
|
| 908 |
+
"loss": 0.0442,
|
| 909 |
+
"step": 750000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.84,
|
| 913 |
+
"learning_rate": 3.510818894752436e-05,
|
| 914 |
+
"loss": 0.044,
|
| 915 |
+
"step": 755000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.85,
|
| 919 |
+
"learning_rate": 3.49330721388963e-05,
|
| 920 |
+
"loss": 0.044,
|
| 921 |
+
"step": 760000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.86,
|
| 925 |
+
"learning_rate": 3.4757339457867414e-05,
|
| 926 |
+
"loss": 0.0444,
|
| 927 |
+
"step": 765000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.87,
|
| 931 |
+
"learning_rate": 3.4581071484102234e-05,
|
| 932 |
+
"loss": 0.0435,
|
| 933 |
+
"step": 770000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.89,
|
| 937 |
+
"learning_rate": 3.440424342594606e-05,
|
| 938 |
+
"loss": 0.0436,
|
| 939 |
+
"step": 775000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.9,
|
| 943 |
+
"learning_rate": 3.4226865620304894e-05,
|
| 944 |
+
"loss": 0.0444,
|
| 945 |
+
"step": 780000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.91,
|
| 949 |
+
"learning_rate": 3.404891278526875e-05,
|
| 950 |
+
"loss": 0.0442,
|
| 951 |
+
"step": 785000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.92,
|
| 955 |
+
"learning_rate": 3.387046651852148e-05,
|
| 956 |
+
"loss": 0.0446,
|
| 957 |
+
"step": 790000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.94,
|
| 961 |
+
"learning_rate": 3.369146584901852e-05,
|
| 962 |
+
"loss": 0.045,
|
| 963 |
+
"step": 795000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.95,
|
| 967 |
+
"learning_rate": 3.3511992854912975e-05,
|
| 968 |
+
"loss": 0.044,
|
| 969 |
+
"step": 800000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.96,
|
| 973 |
+
"learning_rate": 3.333205832954606e-05,
|
| 974 |
+
"loss": 0.0439,
|
| 975 |
+
"step": 805000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.97,
|
| 979 |
+
"learning_rate": 3.315152846675856e-05,
|
| 980 |
+
"loss": 0.0447,
|
| 981 |
+
"step": 810000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.98,
|
| 985 |
+
"learning_rate": 3.2970630450412766e-05,
|
| 986 |
+
"loss": 0.0439,
|
| 987 |
+
"step": 815000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.0,
|
| 991 |
+
"learning_rate": 3.2789230337843214e-05,
|
| 992 |
+
"loss": 0.0438,
|
| 993 |
+
"step": 820000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 2.01,
|
| 997 |
+
"learning_rate": 3.2607374887231645e-05,
|
| 998 |
+
"loss": 0.0414,
|
| 999 |
+
"step": 825000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.02,
|
| 1003 |
+
"learning_rate": 3.24251112477632e-05,
|
| 1004 |
+
"loss": 0.0411,
|
| 1005 |
+
"step": 830000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.03,
|
| 1009 |
+
"learning_rate": 3.22423405210557e-05,
|
| 1010 |
+
"loss": 0.0409,
|
| 1011 |
+
"step": 835000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.05,
|
| 1015 |
+
"learning_rate": 3.2059146256623924e-05,
|
| 1016 |
+
"loss": 0.0403,
|
| 1017 |
+
"step": 840000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.06,
|
| 1021 |
+
"learning_rate": 3.187561270645646e-05,
|
| 1022 |
+
"loss": 0.0407,
|
| 1023 |
+
"step": 845000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 2.07,
|
| 1027 |
+
"learning_rate": 3.169164053812308e-05,
|
| 1028 |
+
"loss": 0.0406,
|
| 1029 |
+
"step": 850000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 2.08,
|
| 1033 |
+
"learning_rate": 3.1507240268131666e-05,
|
| 1034 |
+
"loss": 0.0412,
|
| 1035 |
+
"step": 855000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.09,
|
| 1039 |
+
"learning_rate": 3.1322459449652304e-05,
|
| 1040 |
+
"loss": 0.0406,
|
| 1041 |
+
"step": 860000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.11,
|
| 1045 |
+
"learning_rate": 3.113734596258391e-05,
|
| 1046 |
+
"loss": 0.0407,
|
| 1047 |
+
"step": 865000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 2.12,
|
| 1051 |
+
"learning_rate": 3.095187370231551e-05,
|
| 1052 |
+
"loss": 0.0406,
|
| 1053 |
+
"step": 870000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.13,
|
| 1057 |
+
"learning_rate": 3.076605351107057e-05,
|
| 1058 |
+
"loss": 0.0412,
|
| 1059 |
+
"step": 875000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.14,
|
| 1063 |
+
"learning_rate": 3.057989625141167e-05,
|
| 1064 |
+
"loss": 0.0407,
|
| 1065 |
+
"step": 880000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.15,
|
| 1069 |
+
"learning_rate": 3.0393412805605544e-05,
|
| 1070 |
+
"loss": 0.0414,
|
| 1071 |
+
"step": 885000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.17,
|
| 1075 |
+
"learning_rate": 3.0206576669471674e-05,
|
| 1076 |
+
"loss": 0.0409,
|
| 1077 |
+
"step": 890000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.18,
|
| 1081 |
+
"learning_rate": 3.0019473514002417e-05,
|
| 1082 |
+
"loss": 0.0411,
|
| 1083 |
+
"step": 895000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 2.19,
|
| 1087 |
+
"learning_rate": 2.983207693323402e-05,
|
| 1088 |
+
"loss": 0.0405,
|
| 1089 |
+
"step": 900000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.2,
|
| 1093 |
+
"learning_rate": 2.9644397881880708e-05,
|
| 1094 |
+
"loss": 0.0409,
|
| 1095 |
+
"step": 905000
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.22,
|
| 1099 |
+
"learning_rate": 2.9456447331169147e-05,
|
| 1100 |
+
"loss": 0.0408,
|
| 1101 |
+
"step": 910000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.23,
|
| 1105 |
+
"learning_rate": 2.9268236268197174e-05,
|
| 1106 |
+
"loss": 0.041,
|
| 1107 |
+
"step": 915000
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 2.24,
|
| 1111 |
+
"learning_rate": 2.90797756952915e-05,
|
| 1112 |
+
"loss": 0.0413,
|
| 1113 |
+
"step": 920000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.25,
|
| 1117 |
+
"learning_rate": 2.8891038851321416e-05,
|
| 1118 |
+
"loss": 0.0412,
|
| 1119 |
+
"step": 925000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.26,
|
| 1123 |
+
"learning_rate": 2.8702150101270274e-05,
|
| 1124 |
+
"loss": 0.041,
|
| 1125 |
+
"step": 930000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 2.28,
|
| 1129 |
+
"learning_rate": 2.8512969290515646e-05,
|
| 1130 |
+
"loss": 0.0408,
|
| 1131 |
+
"step": 935000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.29,
|
| 1135 |
+
"learning_rate": 2.832358303857603e-05,
|
| 1136 |
+
"loss": 0.041,
|
| 1137 |
+
"step": 940000
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.3,
|
| 1141 |
+
"learning_rate": 2.8134040363313168e-05,
|
| 1142 |
+
"loss": 0.0409,
|
| 1143 |
+
"step": 945000
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.31,
|
| 1147 |
+
"learning_rate": 2.7944276502291256e-05,
|
| 1148 |
+
"loss": 0.041,
|
| 1149 |
+
"step": 950000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 2.33,
|
| 1153 |
+
"learning_rate": 2.775437846896827e-05,
|
| 1154 |
+
"loss": 0.04,
|
| 1155 |
+
"step": 955000
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 2.34,
|
| 1159 |
+
"learning_rate": 2.756435746426503e-05,
|
| 1160 |
+
"loss": 0.04,
|
| 1161 |
+
"step": 960000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.35,
|
| 1165 |
+
"learning_rate": 2.73741104713839e-05,
|
| 1166 |
+
"loss": 0.0406,
|
| 1167 |
+
"step": 965000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 2.36,
|
| 1171 |
+
"learning_rate": 2.718376273659552e-05,
|
| 1172 |
+
"loss": 0.0401,
|
| 1173 |
+
"step": 970000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.37,
|
| 1177 |
+
"learning_rate": 2.699332546709509e-05,
|
| 1178 |
+
"loss": 0.0401,
|
| 1179 |
+
"step": 975000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.39,
|
| 1183 |
+
"learning_rate": 2.680269543053059e-05,
|
| 1184 |
+
"loss": 0.0391,
|
| 1185 |
+
"step": 980000
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.4,
|
| 1189 |
+
"learning_rate": 2.6612036299970488e-05,
|
| 1190 |
+
"loss": 0.0402,
|
| 1191 |
+
"step": 985000
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 2.41,
|
| 1195 |
+
"learning_rate": 2.6421168424917686e-05,
|
| 1196 |
+
"loss": 0.0403,
|
| 1197 |
+
"step": 990000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.42,
|
| 1201 |
+
"learning_rate": 2.623033199888022e-05,
|
| 1202 |
+
"loss": 0.0401,
|
| 1203 |
+
"step": 995000
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.43,
|
| 1207 |
+
"learning_rate": 2.6039385468590504e-05,
|
| 1208 |
+
"loss": 0.0396,
|
| 1209 |
+
"step": 1000000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.45,
|
| 1213 |
+
"learning_rate": 2.5848339956464096e-05,
|
| 1214 |
+
"loss": 0.0398,
|
| 1215 |
+
"step": 1005000
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.46,
|
| 1219 |
+
"learning_rate": 2.5657283063641474e-05,
|
| 1220 |
+
"loss": 0.0401,
|
| 1221 |
+
"step": 1010000
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.47,
|
| 1225 |
+
"learning_rate": 2.5466225985224508e-05,
|
| 1226 |
+
"loss": 0.04,
|
| 1227 |
+
"step": 1015000
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.48,
|
| 1231 |
+
"learning_rate": 2.5275103421570534e-05,
|
| 1232 |
+
"loss": 0.0398,
|
| 1233 |
+
"step": 1020000
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.5,
|
| 1237 |
+
"learning_rate": 2.5083926532199688e-05,
|
| 1238 |
+
"loss": 0.0398,
|
| 1239 |
+
"step": 1025000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.51,
|
| 1243 |
+
"learning_rate": 2.4892821222247636e-05,
|
| 1244 |
+
"loss": 0.04,
|
| 1245 |
+
"step": 1030000
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.52,
|
| 1249 |
+
"learning_rate": 2.4701607451032485e-05,
|
| 1250 |
+
"loss": 0.0402,
|
| 1251 |
+
"step": 1035000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.53,
|
| 1255 |
+
"learning_rate": 2.4510525847347732e-05,
|
| 1256 |
+
"loss": 0.0398,
|
| 1257 |
+
"step": 1040000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.54,
|
| 1261 |
+
"learning_rate": 2.4319434615660547e-05,
|
| 1262 |
+
"loss": 0.0404,
|
| 1263 |
+
"step": 1045000
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.56,
|
| 1267 |
+
"learning_rate": 2.4128383168046513e-05,
|
| 1268 |
+
"loss": 0.0402,
|
| 1269 |
+
"step": 1050000
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.57,
|
| 1273 |
+
"learning_rate": 2.3937306253792384e-05,
|
| 1274 |
+
"loss": 0.0397,
|
| 1275 |
+
"step": 1055000
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.58,
|
| 1279 |
+
"learning_rate": 2.3746367903542062e-05,
|
| 1280 |
+
"loss": 0.0402,
|
| 1281 |
+
"step": 1060000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.59,
|
| 1285 |
+
"learning_rate": 2.355550283734671e-05,
|
| 1286 |
+
"loss": 0.0393,
|
| 1287 |
+
"step": 1065000
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.61,
|
| 1291 |
+
"learning_rate": 2.3364684050478952e-05,
|
| 1292 |
+
"loss": 0.0397,
|
| 1293 |
+
"step": 1070000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.62,
|
| 1297 |
+
"learning_rate": 2.3173999040117696e-05,
|
| 1298 |
+
"loss": 0.0394,
|
| 1299 |
+
"step": 1075000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.63,
|
| 1303 |
+
"learning_rate": 2.29834207729988e-05,
|
| 1304 |
+
"loss": 0.039,
|
| 1305 |
+
"step": 1080000
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.64,
|
| 1309 |
+
"learning_rate": 2.2792922295048335e-05,
|
| 1310 |
+
"loss": 0.0393,
|
| 1311 |
+
"step": 1085000
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.65,
|
| 1315 |
+
"learning_rate": 2.2602629024425966e-05,
|
| 1316 |
+
"loss": 0.039,
|
| 1317 |
+
"step": 1090000
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 2.67,
|
| 1321 |
+
"learning_rate": 2.2412437803062146e-05,
|
| 1322 |
+
"loss": 0.0394,
|
| 1323 |
+
"step": 1095000
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 2.68,
|
| 1327 |
+
"learning_rate": 2.2222359836495102e-05,
|
| 1328 |
+
"loss": 0.0389,
|
| 1329 |
+
"step": 1100000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.69,
|
| 1333 |
+
"learning_rate": 2.2032520255937674e-05,
|
| 1334 |
+
"loss": 0.0392,
|
| 1335 |
+
"step": 1105000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.7,
|
| 1339 |
+
"learning_rate": 2.1842816139163587e-05,
|
| 1340 |
+
"loss": 0.039,
|
| 1341 |
+
"step": 1110000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.71,
|
| 1345 |
+
"learning_rate": 2.1653258683231724e-05,
|
| 1346 |
+
"loss": 0.0392,
|
| 1347 |
+
"step": 1115000
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.73,
|
| 1351 |
+
"learning_rate": 2.1463934806956023e-05,
|
| 1352 |
+
"loss": 0.039,
|
| 1353 |
+
"step": 1120000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.74,
|
| 1357 |
+
"learning_rate": 2.1274817639807107e-05,
|
| 1358 |
+
"loss": 0.0393,
|
| 1359 |
+
"step": 1125000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.75,
|
| 1363 |
+
"learning_rate": 2.1085918237080158e-05,
|
| 1364 |
+
"loss": 0.0393,
|
| 1365 |
+
"step": 1130000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 2.76,
|
| 1369 |
+
"learning_rate": 2.0897285366938386e-05,
|
| 1370 |
+
"loss": 0.0389,
|
| 1371 |
+
"step": 1135000
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 2.78,
|
| 1375 |
+
"learning_rate": 2.0708816881777654e-05,
|
| 1376 |
+
"loss": 0.0386,
|
| 1377 |
+
"step": 1140000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.79,
|
| 1381 |
+
"learning_rate": 2.052059934835373e-05,
|
| 1382 |
+
"loss": 0.0387,
|
| 1383 |
+
"step": 1145000
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.8,
|
| 1387 |
+
"learning_rate": 2.0332718917197323e-05,
|
| 1388 |
+
"loss": 0.0387,
|
| 1389 |
+
"step": 1150000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.81,
|
| 1393 |
+
"learning_rate": 2.0145036181854185e-05,
|
| 1394 |
+
"loss": 0.0386,
|
| 1395 |
+
"step": 1155000
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.82,
|
| 1399 |
+
"learning_rate": 1.9957712284869015e-05,
|
| 1400 |
+
"loss": 0.0388,
|
| 1401 |
+
"step": 1160000
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.84,
|
| 1405 |
+
"learning_rate": 1.9770645630812195e-05,
|
| 1406 |
+
"loss": 0.0385,
|
| 1407 |
+
"step": 1165000
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 2.85,
|
| 1411 |
+
"learning_rate": 1.958384733531826e-05,
|
| 1412 |
+
"loss": 0.0387,
|
| 1413 |
+
"step": 1170000
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.86,
|
| 1417 |
+
"learning_rate": 1.939744032341169e-05,
|
| 1418 |
+
"loss": 0.038,
|
| 1419 |
+
"step": 1175000
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.87,
|
| 1423 |
+
"learning_rate": 1.921132348667458e-05,
|
| 1424 |
+
"loss": 0.0389,
|
| 1425 |
+
"step": 1180000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.89,
|
| 1429 |
+
"learning_rate": 1.9025545040833008e-05,
|
| 1430 |
+
"loss": 0.0388,
|
| 1431 |
+
"step": 1185000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.9,
|
| 1435 |
+
"learning_rate": 1.8840078780999552e-05,
|
| 1436 |
+
"loss": 0.0383,
|
| 1437 |
+
"step": 1190000
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.91,
|
| 1441 |
+
"learning_rate": 1.8655009750029695e-05,
|
| 1442 |
+
"loss": 0.0388,
|
| 1443 |
+
"step": 1195000
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 2.92,
|
| 1447 |
+
"learning_rate": 1.8470311630602035e-05,
|
| 1448 |
+
"loss": 0.0379,
|
| 1449 |
+
"step": 1200000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.93,
|
| 1453 |
+
"learning_rate": 1.8285995219685757e-05,
|
| 1454 |
+
"loss": 0.0378,
|
| 1455 |
+
"step": 1205000
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 2.95,
|
| 1459 |
+
"learning_rate": 1.8102071291936395e-05,
|
| 1460 |
+
"loss": 0.0381,
|
| 1461 |
+
"step": 1210000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 2.96,
|
| 1465 |
+
"learning_rate": 1.7918587276844793e-05,
|
| 1466 |
+
"loss": 0.0382,
|
| 1467 |
+
"step": 1215000
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.97,
|
| 1471 |
+
"learning_rate": 1.7735443869214267e-05,
|
| 1472 |
+
"loss": 0.0385,
|
| 1473 |
+
"step": 1220000
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.98,
|
| 1477 |
+
"learning_rate": 1.7552725298494208e-05,
|
| 1478 |
+
"loss": 0.038,
|
| 1479 |
+
"step": 1225000
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.99,
|
| 1483 |
+
"learning_rate": 1.7370515089505386e-05,
|
| 1484 |
+
"loss": 0.0381,
|
| 1485 |
+
"step": 1230000
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 3.01,
|
| 1489 |
+
"learning_rate": 1.718875070180597e-05,
|
| 1490 |
+
"loss": 0.0362,
|
| 1491 |
+
"step": 1235000
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 3.02,
|
| 1495 |
+
"learning_rate": 1.7007370282692398e-05,
|
| 1496 |
+
"loss": 0.0339,
|
| 1497 |
+
"step": 1240000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 3.03,
|
| 1501 |
+
"learning_rate": 1.682649342119219e-05,
|
| 1502 |
+
"loss": 0.0349,
|
| 1503 |
+
"step": 1245000
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 3.04,
|
| 1507 |
+
"learning_rate": 1.664609436151844e-05,
|
| 1508 |
+
"loss": 0.0345,
|
| 1509 |
+
"step": 1250000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 3.06,
|
| 1513 |
+
"learning_rate": 1.6466183649328544e-05,
|
| 1514 |
+
"loss": 0.0348,
|
| 1515 |
+
"step": 1255000
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.07,
|
| 1519 |
+
"learning_rate": 1.628673595562077e-05,
|
| 1520 |
+
"loss": 0.0346,
|
| 1521 |
+
"step": 1260000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 3.08,
|
| 1525 |
+
"learning_rate": 1.6107833563524666e-05,
|
| 1526 |
+
"loss": 0.0348,
|
| 1527 |
+
"step": 1265000
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 3.09,
|
| 1531 |
+
"learning_rate": 1.5929450984231475e-05,
|
| 1532 |
+
"loss": 0.0341,
|
| 1533 |
+
"step": 1270000
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 3.1,
|
| 1537 |
+
"learning_rate": 1.575159864552045e-05,
|
| 1538 |
+
"loss": 0.0346,
|
| 1539 |
+
"step": 1275000
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.12,
|
| 1543 |
+
"learning_rate": 1.5574286944174337e-05,
|
| 1544 |
+
"loss": 0.0348,
|
| 1545 |
+
"step": 1280000
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 3.13,
|
| 1549 |
+
"learning_rate": 1.5397526245371656e-05,
|
| 1550 |
+
"loss": 0.0347,
|
| 1551 |
+
"step": 1285000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 3.14,
|
| 1555 |
+
"learning_rate": 1.5221362079222911e-05,
|
| 1556 |
+
"loss": 0.0346,
|
| 1557 |
+
"step": 1290000
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.15,
|
| 1561 |
+
"learning_rate": 1.5045699154455748e-05,
|
| 1562 |
+
"loss": 0.035,
|
| 1563 |
+
"step": 1295000
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 3.17,
|
| 1567 |
+
"learning_rate": 1.4870653329234462e-05,
|
| 1568 |
+
"loss": 0.0343,
|
| 1569 |
+
"step": 1300000
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 3.18,
|
| 1573 |
+
"learning_rate": 1.469619963913822e-05,
|
| 1574 |
+
"loss": 0.0344,
|
| 1575 |
+
"step": 1305000
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 3.19,
|
| 1579 |
+
"learning_rate": 1.4522348282273651e-05,
|
| 1580 |
+
"loss": 0.0346,
|
| 1581 |
+
"step": 1310000
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 3.2,
|
| 1585 |
+
"learning_rate": 1.434910942153659e-05,
|
| 1586 |
+
"loss": 0.0341,
|
| 1587 |
+
"step": 1315000
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 3.21,
|
| 1591 |
+
"learning_rate": 1.4176493184017924e-05,
|
| 1592 |
+
"loss": 0.0338,
|
| 1593 |
+
"step": 1320000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 3.23,
|
| 1597 |
+
"learning_rate": 1.4004509660411627e-05,
|
| 1598 |
+
"loss": 0.0345,
|
| 1599 |
+
"step": 1325000
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.24,
|
| 1603 |
+
"learning_rate": 1.3833134687545127e-05,
|
| 1604 |
+
"loss": 0.0343,
|
| 1605 |
+
"step": 1330000
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.25,
|
| 1609 |
+
"learning_rate": 1.3662480932190311e-05,
|
| 1610 |
+
"loss": 0.0341,
|
| 1611 |
+
"step": 1335000
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 3.26,
|
| 1615 |
+
"learning_rate": 1.3492421770010699e-05,
|
| 1616 |
+
"loss": 0.0336,
|
| 1617 |
+
"step": 1340000
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 3.27,
|
| 1621 |
+
"learning_rate": 1.3323069396041015e-05,
|
| 1622 |
+
"loss": 0.0343,
|
| 1623 |
+
"step": 1345000
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 3.29,
|
| 1627 |
+
"learning_rate": 1.3154399624907232e-05,
|
| 1628 |
+
"loss": 0.0342,
|
| 1629 |
+
"step": 1350000
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 3.3,
|
| 1633 |
+
"learning_rate": 1.2986422316603203e-05,
|
| 1634 |
+
"loss": 0.0346,
|
| 1635 |
+
"step": 1355000
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 3.31,
|
| 1639 |
+
"learning_rate": 1.2819147290643238e-05,
|
| 1640 |
+
"loss": 0.0341,
|
| 1641 |
+
"step": 1360000
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.32,
|
| 1645 |
+
"learning_rate": 1.2652584325488027e-05,
|
| 1646 |
+
"loss": 0.0339,
|
| 1647 |
+
"step": 1365000
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 3.34,
|
| 1651 |
+
"learning_rate": 1.2486743157973069e-05,
|
| 1652 |
+
"loss": 0.0342,
|
| 1653 |
+
"step": 1370000
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 3.35,
|
| 1657 |
+
"learning_rate": 1.2321666444080471e-05,
|
| 1658 |
+
"loss": 0.0344,
|
| 1659 |
+
"step": 1375000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 3.36,
|
| 1663 |
+
"learning_rate": 1.2157264951667166e-05,
|
| 1664 |
+
"loss": 0.0338,
|
| 1665 |
+
"step": 1380000
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 3.37,
|
| 1669 |
+
"learning_rate": 1.1993647173310798e-05,
|
| 1670 |
+
"loss": 0.0338,
|
| 1671 |
+
"step": 1385000
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.38,
|
| 1675 |
+
"learning_rate": 1.183078971233793e-05,
|
| 1676 |
+
"loss": 0.0334,
|
| 1677 |
+
"step": 1390000
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 3.4,
|
| 1681 |
+
"learning_rate": 1.1668669736135962e-05,
|
| 1682 |
+
"loss": 0.0347,
|
| 1683 |
+
"step": 1395000
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.41,
|
| 1687 |
+
"learning_rate": 1.1507361582461623e-05,
|
| 1688 |
+
"loss": 0.034,
|
| 1689 |
+
"step": 1400000
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 3.42,
|
| 1693 |
+
"learning_rate": 1.134684217315512e-05,
|
| 1694 |
+
"loss": 0.0332,
|
| 1695 |
+
"step": 1405000
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 3.43,
|
| 1699 |
+
"learning_rate": 1.1187089015206759e-05,
|
| 1700 |
+
"loss": 0.0336,
|
| 1701 |
+
"step": 1410000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 3.45,
|
| 1705 |
+
"learning_rate": 1.1028175361103207e-05,
|
| 1706 |
+
"loss": 0.0332,
|
| 1707 |
+
"step": 1415000
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 3.46,
|
| 1711 |
+
"learning_rate": 1.0870078463341248e-05,
|
| 1712 |
+
"loss": 0.0336,
|
| 1713 |
+
"step": 1420000
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 3.47,
|
| 1717 |
+
"learning_rate": 1.0712838947388687e-05,
|
| 1718 |
+
"loss": 0.0334,
|
| 1719 |
+
"step": 1425000
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 3.48,
|
| 1723 |
+
"learning_rate": 1.0556371856281719e-05,
|
| 1724 |
+
"loss": 0.0338,
|
| 1725 |
+
"step": 1430000
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 3.49,
|
| 1729 |
+
"learning_rate": 1.0400780485452265e-05,
|
| 1730 |
+
"loss": 0.0337,
|
| 1731 |
+
"step": 1435000
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 3.51,
|
| 1735 |
+
"learning_rate": 1.0246042546828628e-05,
|
| 1736 |
+
"loss": 0.0335,
|
| 1737 |
+
"step": 1440000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 3.52,
|
| 1741 |
+
"learning_rate": 1.009216708598616e-05,
|
| 1742 |
+
"loss": 0.0332,
|
| 1743 |
+
"step": 1445000
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 3.53,
|
| 1747 |
+
"learning_rate": 9.939163098082024e-06,
|
| 1748 |
+
"loss": 0.0324,
|
| 1749 |
+
"step": 1450000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 3.54,
|
| 1753 |
+
"learning_rate": 9.787039527329362e-06,
|
| 1754 |
+
"loss": 0.0333,
|
| 1755 |
+
"step": 1455000
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 3.55,
|
| 1759 |
+
"learning_rate": 9.635805266474399e-06,
|
| 1760 |
+
"loss": 0.0333,
|
| 1761 |
+
"step": 1460000
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 3.57,
|
| 1765 |
+
"learning_rate": 9.485439167479077e-06,
|
| 1766 |
+
"loss": 0.0335,
|
| 1767 |
+
"step": 1465000
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 3.58,
|
| 1771 |
+
"learning_rate": 9.335980372105996e-06,
|
| 1772 |
+
"loss": 0.0333,
|
| 1773 |
+
"step": 1470000
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 3.59,
|
| 1777 |
+
"learning_rate": 9.187496865476697e-06,
|
| 1778 |
+
"loss": 0.033,
|
| 1779 |
+
"step": 1475000
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.6,
|
| 1783 |
+
"learning_rate": 9.03987847348179e-06,
|
| 1784 |
+
"loss": 0.033,
|
| 1785 |
+
"step": 1480000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 3.62,
|
| 1789 |
+
"learning_rate": 8.893222690812272e-06,
|
| 1790 |
+
"loss": 0.033,
|
| 1791 |
+
"step": 1485000
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 3.63,
|
| 1795 |
+
"learning_rate": 8.747537527998633e-06,
|
| 1796 |
+
"loss": 0.0331,
|
| 1797 |
+
"step": 1490000
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 3.64,
|
| 1801 |
+
"learning_rate": 8.602773192648179e-06,
|
| 1802 |
+
"loss": 0.0329,
|
| 1803 |
+
"step": 1495000
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 3.65,
|
| 1807 |
+
"learning_rate": 8.45893872011418e-06,
|
| 1808 |
+
"loss": 0.0329,
|
| 1809 |
+
"step": 1500000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 3.66,
|
| 1813 |
+
"learning_rate": 8.316100063601678e-06,
|
| 1814 |
+
"loss": 0.0323,
|
| 1815 |
+
"step": 1505000
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.68,
|
| 1819 |
+
"learning_rate": 8.174208418379433e-06,
|
| 1820 |
+
"loss": 0.0329,
|
| 1821 |
+
"step": 1510000
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 3.69,
|
| 1825 |
+
"learning_rate": 8.03332884679727e-06,
|
| 1826 |
+
"loss": 0.033,
|
| 1827 |
+
"step": 1515000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 3.7,
|
| 1831 |
+
"learning_rate": 7.893441102454437e-06,
|
| 1832 |
+
"loss": 0.0328,
|
| 1833 |
+
"step": 1520000
|
| 1834 |
+
}
|
| 1835 |
+
],
|
| 1836 |
+
"logging_steps": 5000,
|
| 1837 |
+
"max_steps": 2053645,
|
| 1838 |
+
"num_train_epochs": 5,
|
| 1839 |
+
"save_steps": 40000,
|
| 1840 |
+
"total_flos": 3.8313184144529346e+20,
|
| 1841 |
+
"trial_name": null,
|
| 1842 |
+
"trial_params": null
|
| 1843 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b185236dc2edc30b6945cb152bfbb24dbbabad40b3512123a9712cc64576d14f
|
| 3 |
+
size 4283
|