Commit
路
cafa8de
1
Parent(s):
202592d
Training in progress, step 100
Browse filesThis view is limited to 50 files because it contains too many changes. 聽
See raw diff
- added_tokens.json +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/README.md +221 -0
- bert-base-uncased--aqua-data/checkpoint-100/adapter_config.json +25 -0
- bert-base-uncased--aqua-data/checkpoint-100/adapter_model.safetensors +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/added_tokens.json +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/merges.txt +0 -0
- bert-base-uncased--aqua-data/checkpoint-100/optimizer.pt +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/rng_state.pth +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/scheduler.pt +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/special_tokens_map.json +30 -0
- bert-base-uncased--aqua-data/checkpoint-100/tokenizer.json +0 -0
- bert-base-uncased--aqua-data/checkpoint-100/tokenizer_config.json +30 -0
- bert-base-uncased--aqua-data/checkpoint-100/trainer_state.json +34 -0
- bert-base-uncased--aqua-data/checkpoint-100/training_args.bin +3 -0
- bert-base-uncased--aqua-data/checkpoint-100/vocab.json +0 -0
- bert-base-uncased--aqua-data/checkpoint-200/README.md +214 -0
- bert-base-uncased--aqua-data/checkpoint-200/adapter_config.json +25 -0
- bert-base-uncased--aqua-data/checkpoint-200/adapter_model.safetensors +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/added_tokens.json +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/merges.txt +0 -0
- bert-base-uncased--aqua-data/checkpoint-200/optimizer.pt +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/rng_state.pth +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/scheduler.pt +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/special_tokens_map.json +30 -0
- bert-base-uncased--aqua-data/checkpoint-200/tokenizer.json +0 -0
- bert-base-uncased--aqua-data/checkpoint-200/tokenizer_config.json +30 -0
- bert-base-uncased--aqua-data/checkpoint-200/trainer_state.json +49 -0
- bert-base-uncased--aqua-data/checkpoint-200/training_args.bin +3 -0
- bert-base-uncased--aqua-data/checkpoint-200/vocab.json +0 -0
- bert-base-uncased--aqua-data/runs/Nov14_04-24-40_7d86a42f9615/events.out.tfevents.1699935889.7d86a42f9615.159.0 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-19-25_0c9d2336392e/events.out.tfevents.1699946372.0c9d2336392e.740.0 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-20-27_0c9d2336392e/events.out.tfevents.1699946428.0c9d2336392e.740.1 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-30-31_0c9d2336392e/events.out.tfevents.1699947033.0c9d2336392e.740.2 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-35-53_af00defdd8d5/events.out.tfevents.1699947363.af00defdd8d5.523.0 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-42-19_af00defdd8d5/events.out.tfevents.1699947739.af00defdd8d5.523.1 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-42-57_af00defdd8d5/events.out.tfevents.1699947778.af00defdd8d5.523.2 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-43-43_af00defdd8d5/events.out.tfevents.1699947824.af00defdd8d5.523.3 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-44-12_af00defdd8d5/events.out.tfevents.1699947852.af00defdd8d5.523.4 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_07-57-53_af00defdd8d5/events.out.tfevents.1699948674.af00defdd8d5.523.5 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-00-24_af00defdd8d5/events.out.tfevents.1699948826.af00defdd8d5.523.6 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-10-13_af00defdd8d5/events.out.tfevents.1699949414.af00defdd8d5.523.7 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-18-18_af00defdd8d5/events.out.tfevents.1699949899.af00defdd8d5.523.8 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-21-31_983aa0f3dbdc/events.out.tfevents.1699950099.983aa0f3dbdc.303.0 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-41-57_d3d7b74e1a53/events.out.tfevents.1699951327.d3d7b74e1a53.629.0 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-50-38_d3d7b74e1a53/events.out.tfevents.1699951838.d3d7b74e1a53.629.1 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-56-53_d3d7b74e1a53/events.out.tfevents.1699952213.d3d7b74e1a53.629.2 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-59-14_d3d7b74e1a53/events.out.tfevents.1699952356.d3d7b74e1a53.629.3 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_08-59-44_d3d7b74e1a53/events.out.tfevents.1699952385.d3d7b74e1a53.629.4 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_09-26-05_d3d7b74e1a53/events.out.tfevents.1699953965.d3d7b74e1a53.629.5 +3 -0
- bert-base-uncased--aqua-data/runs/Nov14_09-36-50_d3d7b74e1a53/events.out.tfevents.1699954611.d3d7b74e1a53.629.6 +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 3 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,221 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: EleutherAI/gpt-neo-125m
|
| 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 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data 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. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
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).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
## Training procedure
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.2
|
| 208 |
+
## Training procedure
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
### Framework versions
|
| 212 |
+
|
| 213 |
+
|
| 214 |
+
- PEFT 0.6.2
|
| 215 |
+
## Training procedure
|
| 216 |
+
|
| 217 |
+
|
| 218 |
+
### Framework versions
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
- PEFT 0.6.2
|
bert-base-uncased--aqua-data/checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "EleutherAI/gpt-neo-125m",
|
| 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": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"k_proj",
|
| 20 |
+
"out_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"q_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "SEQ_CLS"
|
| 25 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38a0b4efeb314796f77eb7cf1ca8090ed2a02a241eb7f785ea4495890925182a
|
| 3 |
+
size 4744184
|
bert-base-uncased--aqua-data/checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 3 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a947b8a2876939ed74cb39edfb4ff8903c46bb6071bcf63b3e778358b49be3
|
| 3 |
+
size 9543482
|
bert-base-uncased--aqua-data/checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7eacb2b8ce624576f10005e2f15d3ebabf8c92b36e46561233bc0d92ef62d5e
|
| 3 |
+
size 14244
|
bert-base-uncased--aqua-data/checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce887d798e1820a9f3d9d5502913588a93a2c2cb15c56173051561963476990
|
| 3 |
+
size 1064
|
bert-base-uncased--aqua-data/checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50257": {
|
| 14 |
+
"content": "[PAD]",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"bos_token": "<|endoftext|>",
|
| 23 |
+
"clean_up_tokenization_spaces": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 2048,
|
| 27 |
+
"pad_token": "[PAD]",
|
| 28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>"
|
| 30 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 9.609375,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/experiements/bert-base-uncased--aqua-data/checkpoint-100",
|
| 4 |
+
"epoch": 0.05296610169491525,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 4.9735169491525426e-05,
|
| 14 |
+
"loss": 0.0,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"eval_accuracy": 0.0,
|
| 20 |
+
"eval_loss": 9.609375,
|
| 21 |
+
"eval_runtime": 41.575,
|
| 22 |
+
"eval_samples_per_second": 28.864,
|
| 23 |
+
"eval_steps_per_second": 28.864,
|
| 24 |
+
"step": 100
|
| 25 |
+
}
|
| 26 |
+
],
|
| 27 |
+
"logging_steps": 100,
|
| 28 |
+
"max_steps": 18880,
|
| 29 |
+
"num_train_epochs": 10,
|
| 30 |
+
"save_steps": 100,
|
| 31 |
+
"total_flos": 69109257830400.0,
|
| 32 |
+
"trial_name": null,
|
| 33 |
+
"trial_params": null
|
| 34 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8428940654b6236fde66431555e377d7384928c9ef44fb19debc5817572d2b26
|
| 3 |
+
size 4664
|
bert-base-uncased--aqua-data/checkpoint-100/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: EleutherAI/gpt-neo-125m
|
| 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 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data 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. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
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).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
|
| 201 |
+
## Training procedure
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
- PEFT 0.6.2
|
| 208 |
+
## Training procedure
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
### Framework versions
|
| 212 |
+
|
| 213 |
+
|
| 214 |
+
- PEFT 0.6.2
|
bert-base-uncased--aqua-data/checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "EleutherAI/gpt-neo-125m",
|
| 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": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"k_proj",
|
| 20 |
+
"out_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"q_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "SEQ_CLS"
|
| 25 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3c42f5ae4b0bb9a7500c35ec650ba877f032c401b1f64e970ec734787cb0c4b
|
| 3 |
+
size 4744184
|
bert-base-uncased--aqua-data/checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 3 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-200/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc89fc071687ec9ff26f8e0ae4ba6cea9206583442a3f5343de607dc823ab11f
|
| 3 |
+
size 9543482
|
bert-base-uncased--aqua-data/checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b1330565fd27987f801e2d37c9ff5c8a342f0c9f98d1f15ff82badeebeb0b2
|
| 3 |
+
size 14244
|
bert-base-uncased--aqua-data/checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5829944be9a16c541913ddd5d2378c415a0402c184a6550bad81400fc6709965
|
| 3 |
+
size 1064
|
bert-base-uncased--aqua-data/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50257": {
|
| 14 |
+
"content": "[PAD]",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
}
|
| 21 |
+
},
|
| 22 |
+
"bos_token": "<|endoftext|>",
|
| 23 |
+
"clean_up_tokenization_spaces": true,
|
| 24 |
+
"eos_token": "<|endoftext|>",
|
| 25 |
+
"errors": "replace",
|
| 26 |
+
"model_max_length": 2048,
|
| 27 |
+
"pad_token": "[PAD]",
|
| 28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>"
|
| 30 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 9.609375,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/experiements/bert-base-uncased--aqua-data/checkpoint-100",
|
| 4 |
+
"epoch": 0.1059322033898305,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 4.9735169491525426e-05,
|
| 14 |
+
"loss": 0.0,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"eval_accuracy": 0.0,
|
| 20 |
+
"eval_loss": 9.609375,
|
| 21 |
+
"eval_runtime": 41.575,
|
| 22 |
+
"eval_samples_per_second": 28.864,
|
| 23 |
+
"eval_steps_per_second": 28.864,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.11,
|
| 28 |
+
"learning_rate": 4.947033898305085e-05,
|
| 29 |
+
"loss": 0.0,
|
| 30 |
+
"step": 200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"eval_accuracy": 0.0,
|
| 35 |
+
"eval_loss": 9.890625,
|
| 36 |
+
"eval_runtime": 38.7356,
|
| 37 |
+
"eval_samples_per_second": 30.979,
|
| 38 |
+
"eval_steps_per_second": 30.979,
|
| 39 |
+
"step": 200
|
| 40 |
+
}
|
| 41 |
+
],
|
| 42 |
+
"logging_steps": 100,
|
| 43 |
+
"max_steps": 18880,
|
| 44 |
+
"num_train_epochs": 10,
|
| 45 |
+
"save_steps": 100,
|
| 46 |
+
"total_flos": 138218515660800.0,
|
| 47 |
+
"trial_name": null,
|
| 48 |
+
"trial_params": null
|
| 49 |
+
}
|
bert-base-uncased--aqua-data/checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8428940654b6236fde66431555e377d7384928c9ef44fb19debc5817572d2b26
|
| 3 |
+
size 4664
|
bert-base-uncased--aqua-data/checkpoint-200/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
bert-base-uncased--aqua-data/runs/Nov14_04-24-40_7d86a42f9615/events.out.tfevents.1699935889.7d86a42f9615.159.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c429c1d05dee0af5618c9602a747f60e57ef55a96ae73b15b5234e6ea1795f3a
|
| 3 |
+
size 4789
|
bert-base-uncased--aqua-data/runs/Nov14_07-19-25_0c9d2336392e/events.out.tfevents.1699946372.0c9d2336392e.740.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d29faaf42c5ea57d9a5a81a5b4b64c1d878e37632f08151b0837450c9be92238
|
| 3 |
+
size 4789
|
bert-base-uncased--aqua-data/runs/Nov14_07-20-27_0c9d2336392e/events.out.tfevents.1699946428.0c9d2336392e.740.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bf53be262e5fbab99d6586f8937f24e01ce60d2cfa9a84c7e161f49dec08dd9
|
| 3 |
+
size 4789
|
bert-base-uncased--aqua-data/runs/Nov14_07-30-31_0c9d2336392e/events.out.tfevents.1699947033.0c9d2336392e.740.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaa360ef39731bdc3fe1dc0bc74bf05d477867e761536cbccff39888d1ce07f6
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_07-35-53_af00defdd8d5/events.out.tfevents.1699947363.af00defdd8d5.523.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:355c34cac01244d14240ec736362fa2b829756542ec91058af39cbfe665b9382
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_07-42-19_af00defdd8d5/events.out.tfevents.1699947739.af00defdd8d5.523.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9257e049b1851553a5c60238aa32671a0e0338e7c7d56b267550a4a0ad9711a5
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_07-42-57_af00defdd8d5/events.out.tfevents.1699947778.af00defdd8d5.523.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36711dfce160cdb015e61f1c28075eefd2abb829f112bbc01ea1db6b924361ed
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_07-43-43_af00defdd8d5/events.out.tfevents.1699947824.af00defdd8d5.523.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd9978a6dcfcb952b1e4e2d45a23f78aece51c15888a69b33c8bd7e9b929aeb
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_07-44-12_af00defdd8d5/events.out.tfevents.1699947852.af00defdd8d5.523.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cc675bc182a12c0db8a8bda243dd7634cc68953725a41c1899988536495d6fc
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_07-57-53_af00defdd8d5/events.out.tfevents.1699948674.af00defdd8d5.523.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:430861ba62bac71365da0445e14fdce15ce9802d119c2f7756345e5ef854d95a
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_08-00-24_af00defdd8d5/events.out.tfevents.1699948826.af00defdd8d5.523.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382c8aeebd7bb4a9b193056321279468839b780a57e1269f37a981ae2976762d
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_08-10-13_af00defdd8d5/events.out.tfevents.1699949414.af00defdd8d5.523.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc0c429a63ad0b2b6a122af10822e7440d799039fd28516506933410f4f23d91
|
| 3 |
+
size 4863
|
bert-base-uncased--aqua-data/runs/Nov14_08-18-18_af00defdd8d5/events.out.tfevents.1699949899.af00defdd8d5.523.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac9c7348f8217c9b6873e77f0d122c8a00635026693ca82913fb39e179ece6ae
|
| 3 |
+
size 88
|
bert-base-uncased--aqua-data/runs/Nov14_08-21-31_983aa0f3dbdc/events.out.tfevents.1699950099.983aa0f3dbdc.303.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e8ec37e7db5d3db3264fe88a17af6a84f561ff642285b49a00b7ccb4352c591
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_08-41-57_d3d7b74e1a53/events.out.tfevents.1699951327.d3d7b74e1a53.629.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4088f052cfbe68e55a09634c90792e7a35b52a7c2fd0d2b6a9a429b7e081ce9c
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_08-50-38_d3d7b74e1a53/events.out.tfevents.1699951838.d3d7b74e1a53.629.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:637a9487ac2a585f52ceb9f20f6cd7d9fa0031619b0326fffb8e4662e24aa49a
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_08-56-53_d3d7b74e1a53/events.out.tfevents.1699952213.d3d7b74e1a53.629.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c8691dcd154f0331ee4fa471a9c17be1a748a01b1f2087e75680a6c94e6942a
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_08-59-14_d3d7b74e1a53/events.out.tfevents.1699952356.d3d7b74e1a53.629.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82fbcc06b64486df4c251b73e16a76e9f7ba5deecd72be90cae3585d61a9367b
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_08-59-44_d3d7b74e1a53/events.out.tfevents.1699952385.d3d7b74e1a53.629.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74e7189d956b2ffdfc68b7247a1368f19cab5194e513dc168aa6492c666d2fc6
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_09-26-05_d3d7b74e1a53/events.out.tfevents.1699953965.d3d7b74e1a53.629.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b17f95921cb4db15bdfcad6517387974359cf0eb2f730df3ed07571c813f5272
|
| 3 |
+
size 4814
|
bert-base-uncased--aqua-data/runs/Nov14_09-36-50_d3d7b74e1a53/events.out.tfevents.1699954611.d3d7b74e1a53.629.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30df3676abc87a7b9f1bf9f03e6bc7438c4aeaf4c808fa8baf2c7a2b880028c3
|
| 3 |
+
size 4814
|