Instructions to use casualprogrammer/shadow_mbart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use casualprogrammer/shadow_mbart with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("facebook/mbart-large-50") model = PeftModel.from_pretrained(base_model, "casualprogrammer/shadow_mbart") - Transformers
How to use casualprogrammer/shadow_mbart with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("casualprogrammer/shadow_mbart") model = AutoModelForSeq2SeqLM.from_pretrained("casualprogrammer/shadow_mbart", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- README.md +206 -0
- adapter_config.json +47 -0
- adapter_model.safetensors +3 -0
- checkpoint-10498/README.md +206 -0
- checkpoint-10498/adapter_config.json +47 -0
- checkpoint-10498/adapter_model.safetensors +3 -0
- checkpoint-10498/optimizer.pt +3 -0
- checkpoint-10498/rng_state.pth +3 -0
- checkpoint-10498/scheduler.pt +3 -0
- checkpoint-10498/tokenizer.json +3 -0
- checkpoint-10498/tokenizer_config.json +72 -0
- checkpoint-10498/trainer_state.json +72 -0
- checkpoint-10498/training_args.bin +3 -0
- checkpoint-15747/README.md +206 -0
- checkpoint-15747/adapter_config.json +47 -0
- checkpoint-15747/adapter_model.safetensors +3 -0
- checkpoint-15747/optimizer.pt +3 -0
- checkpoint-15747/rng_state.pth +3 -0
- checkpoint-15747/scheduler.pt +3 -0
- checkpoint-15747/tokenizer.json +3 -0
- checkpoint-15747/tokenizer_config.json +72 -0
- checkpoint-15747/trainer_state.json +91 -0
- checkpoint-15747/training_args.bin +3 -0
- eval_results.csv +3 -0
- generation_config.json +14 -0
- meta_config.json +235 -0
- tokenizer.json +3 -0
- tokenizer_config.json +72 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-10498/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-15747/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
eval_results.csv filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: facebook/mbart-large-50
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:facebook/mbart-large-50
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
Shadow Finetuned mBart model.
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "facebook/mbart-large-50",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 16,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"fc2",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"fc1",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"out_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_bdlora": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_qalora": false,
|
| 46 |
+
"use_rslora": true
|
| 47 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed68740976110a5a8e1053342ac6e2d75a14dec2906e0301b8c532ebcf022fc8
|
| 3 |
+
size 34656568
|
checkpoint-10498/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: facebook/mbart-large-50
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:facebook/mbart-large-50
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.19.1
|
checkpoint-10498/adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "facebook/mbart-large-50",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 16,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"fc2",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"fc1",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"out_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_bdlora": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_qalora": false,
|
| 46 |
+
"use_rslora": true
|
| 47 |
+
}
|
checkpoint-10498/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c9edac52dbc8a736b2369447671d20b894bb6e686ae5b8e73064effc64b7ed
|
| 3 |
+
size 34656568
|
checkpoint-10498/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:526e7ea4d278f947167e312366109d266ca501948ee3617a01bc7e9f033565e5
|
| 3 |
+
size 69534499
|
checkpoint-10498/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51894895cf8a158ae2a50fa2be81d92c976b676a8fe0d6df2ab7c1ae8f7885c8
|
| 3 |
+
size 14645
|
checkpoint-10498/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03b00d9659f55457724182e658e7a0fa30e01786cc1462a3deaabb49c966d80b
|
| 3 |
+
size 1465
|
checkpoint-10498/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
|
| 3 |
+
size 17109919
|
checkpoint-10498/tokenizer_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<s>",
|
| 8 |
+
"</s>",
|
| 9 |
+
"ar_AR",
|
| 10 |
+
"cs_CZ",
|
| 11 |
+
"de_DE",
|
| 12 |
+
"en_XX",
|
| 13 |
+
"es_XX",
|
| 14 |
+
"et_EE",
|
| 15 |
+
"fi_FI",
|
| 16 |
+
"fr_XX",
|
| 17 |
+
"gu_IN",
|
| 18 |
+
"hi_IN",
|
| 19 |
+
"it_IT",
|
| 20 |
+
"ja_XX",
|
| 21 |
+
"kk_KZ",
|
| 22 |
+
"ko_KR",
|
| 23 |
+
"lt_LT",
|
| 24 |
+
"lv_LV",
|
| 25 |
+
"my_MM",
|
| 26 |
+
"ne_NP",
|
| 27 |
+
"nl_XX",
|
| 28 |
+
"ro_RO",
|
| 29 |
+
"ru_RU",
|
| 30 |
+
"si_LK",
|
| 31 |
+
"tr_TR",
|
| 32 |
+
"vi_VN",
|
| 33 |
+
"zh_CN",
|
| 34 |
+
"af_ZA",
|
| 35 |
+
"az_AZ",
|
| 36 |
+
"bn_IN",
|
| 37 |
+
"fa_IR",
|
| 38 |
+
"he_IL",
|
| 39 |
+
"hr_HR",
|
| 40 |
+
"id_ID",
|
| 41 |
+
"ka_GE",
|
| 42 |
+
"km_KH",
|
| 43 |
+
"mk_MK",
|
| 44 |
+
"ml_IN",
|
| 45 |
+
"mn_MN",
|
| 46 |
+
"mr_IN",
|
| 47 |
+
"pl_PL",
|
| 48 |
+
"ps_AF",
|
| 49 |
+
"pt_XX",
|
| 50 |
+
"sv_SE",
|
| 51 |
+
"sw_KE",
|
| 52 |
+
"ta_IN",
|
| 53 |
+
"te_IN",
|
| 54 |
+
"th_TH",
|
| 55 |
+
"tl_XX",
|
| 56 |
+
"uk_UA",
|
| 57 |
+
"ur_PK",
|
| 58 |
+
"xh_ZA",
|
| 59 |
+
"gl_ES",
|
| 60 |
+
"sl_SI"
|
| 61 |
+
],
|
| 62 |
+
"is_local": false,
|
| 63 |
+
"mask_token": "<mask>",
|
| 64 |
+
"model_max_length": 1024,
|
| 65 |
+
"pad_token": "<pad>",
|
| 66 |
+
"sep_token": "</s>",
|
| 67 |
+
"src_lang": "en_XX",
|
| 68 |
+
"tgt_lang": "en_XX",
|
| 69 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 70 |
+
"unk_id": 0,
|
| 71 |
+
"unk_token": "<unk>"
|
| 72 |
+
}
|
checkpoint-10498/trainer_state.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 10498,
|
| 3 |
+
"best_metric": 4.745133399963379,
|
| 4 |
+
"best_model_checkpoint": "./output/mbart-large-first/checkpoint-10498",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10498,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 2.2508127689361572,
|
| 15 |
+
"learning_rate": 2.1358242354377162e-05,
|
| 16 |
+
"loss": 5.126435169198895,
|
| 17 |
+
"step": 5249
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 4.782848834991455,
|
| 22 |
+
"eval_rouge1": 0.2626519199005293,
|
| 23 |
+
"eval_rouge2": 0.11815344657319395,
|
| 24 |
+
"eval_rougeL": 0.20149220585189942,
|
| 25 |
+
"eval_rougeLsum": 0.20168022656710616,
|
| 26 |
+
"eval_runtime": 950.7747,
|
| 27 |
+
"eval_samples_per_second": 4.129,
|
| 28 |
+
"eval_steps_per_second": 4.129,
|
| 29 |
+
"step": 5249
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 3.800706148147583,
|
| 34 |
+
"learning_rate": 1.0680138333220317e-05,
|
| 35 |
+
"loss": 4.756629238902648,
|
| 36 |
+
"step": 10498
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_loss": 4.745133399963379,
|
| 41 |
+
"eval_rouge1": 0.2812791287016354,
|
| 42 |
+
"eval_rouge2": 0.13410717394395671,
|
| 43 |
+
"eval_rougeL": 0.22017424943243102,
|
| 44 |
+
"eval_rougeLsum": 0.22024249247836936,
|
| 45 |
+
"eval_runtime": 1136.965,
|
| 46 |
+
"eval_samples_per_second": 3.453,
|
| 47 |
+
"eval_steps_per_second": 3.453,
|
| 48 |
+
"step": 10498
|
| 49 |
+
}
|
| 50 |
+
],
|
| 51 |
+
"logging_steps": 500,
|
| 52 |
+
"max_steps": 15747,
|
| 53 |
+
"num_input_tokens_seen": 0,
|
| 54 |
+
"num_train_epochs": 3,
|
| 55 |
+
"save_steps": 500,
|
| 56 |
+
"stateful_callbacks": {
|
| 57 |
+
"TrainerControl": {
|
| 58 |
+
"args": {
|
| 59 |
+
"should_epoch_stop": false,
|
| 60 |
+
"should_evaluate": false,
|
| 61 |
+
"should_log": false,
|
| 62 |
+
"should_save": true,
|
| 63 |
+
"should_training_stop": false
|
| 64 |
+
},
|
| 65 |
+
"attributes": {}
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"total_flos": 1.3984655533827686e+17,
|
| 69 |
+
"train_batch_size": 1,
|
| 70 |
+
"trial_name": null,
|
| 71 |
+
"trial_params": null
|
| 72 |
+
}
|
checkpoint-10498/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15395dac053d64b4ff5c7d8b1bc15520dd512987b04f2d911cff1824280c5d00
|
| 3 |
+
size 7121
|
checkpoint-15747/README.md
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: facebook/mbart-large-50
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:facebook/mbart-large-50
|
| 6 |
+
- lora
|
| 7 |
+
- transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card for Model ID
|
| 11 |
+
|
| 12 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by:** [More Information Needed]
|
| 25 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 26 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 27 |
+
- **Model type:** [More Information Needed]
|
| 28 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 29 |
+
- **License:** [More Information Needed]
|
| 30 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 31 |
+
|
| 32 |
+
### Model Sources [optional]
|
| 33 |
+
|
| 34 |
+
<!-- Provide the basic links for the model. -->
|
| 35 |
+
|
| 36 |
+
- **Repository:** [More Information Needed]
|
| 37 |
+
- **Paper [optional]:** [More Information Needed]
|
| 38 |
+
- **Demo [optional]:** [More Information Needed]
|
| 39 |
+
|
| 40 |
+
## Uses
|
| 41 |
+
|
| 42 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 43 |
+
|
| 44 |
+
### Direct Use
|
| 45 |
+
|
| 46 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 47 |
+
|
| 48 |
+
[More Information Needed]
|
| 49 |
+
|
| 50 |
+
### Downstream Use [optional]
|
| 51 |
+
|
| 52 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 53 |
+
|
| 54 |
+
[More Information Needed]
|
| 55 |
+
|
| 56 |
+
### Out-of-Scope Use
|
| 57 |
+
|
| 58 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 59 |
+
|
| 60 |
+
[More Information Needed]
|
| 61 |
+
|
| 62 |
+
## Bias, Risks, and Limitations
|
| 63 |
+
|
| 64 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 65 |
+
|
| 66 |
+
[More Information Needed]
|
| 67 |
+
|
| 68 |
+
### Recommendations
|
| 69 |
+
|
| 70 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 71 |
+
|
| 72 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 73 |
+
|
| 74 |
+
## How to Get Started with the Model
|
| 75 |
+
|
| 76 |
+
Use the code below to get started with the model.
|
| 77 |
+
|
| 78 |
+
[More Information Needed]
|
| 79 |
+
|
| 80 |
+
## Training Details
|
| 81 |
+
|
| 82 |
+
### Training Data
|
| 83 |
+
|
| 84 |
+
<!-- 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. -->
|
| 85 |
+
|
| 86 |
+
[More Information Needed]
|
| 87 |
+
|
| 88 |
+
### Training Procedure
|
| 89 |
+
|
| 90 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 91 |
+
|
| 92 |
+
#### Preprocessing [optional]
|
| 93 |
+
|
| 94 |
+
[More Information Needed]
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
#### Training Hyperparameters
|
| 98 |
+
|
| 99 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 100 |
+
|
| 101 |
+
#### Speeds, Sizes, Times [optional]
|
| 102 |
+
|
| 103 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 104 |
+
|
| 105 |
+
[More Information Needed]
|
| 106 |
+
|
| 107 |
+
## Evaluation
|
| 108 |
+
|
| 109 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 110 |
+
|
| 111 |
+
### Testing Data, Factors & Metrics
|
| 112 |
+
|
| 113 |
+
#### Testing Data
|
| 114 |
+
|
| 115 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 116 |
+
|
| 117 |
+
[More Information Needed]
|
| 118 |
+
|
| 119 |
+
#### Factors
|
| 120 |
+
|
| 121 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 122 |
+
|
| 123 |
+
[More Information Needed]
|
| 124 |
+
|
| 125 |
+
#### Metrics
|
| 126 |
+
|
| 127 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
### Results
|
| 132 |
+
|
| 133 |
+
[More Information Needed]
|
| 134 |
+
|
| 135 |
+
#### Summary
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
## Model Examination [optional]
|
| 140 |
+
|
| 141 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 142 |
+
|
| 143 |
+
[More Information Needed]
|
| 144 |
+
|
| 145 |
+
## Environmental Impact
|
| 146 |
+
|
| 147 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 148 |
+
|
| 149 |
+
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).
|
| 150 |
+
|
| 151 |
+
- **Hardware Type:** [More Information Needed]
|
| 152 |
+
- **Hours used:** [More Information Needed]
|
| 153 |
+
- **Cloud Provider:** [More Information Needed]
|
| 154 |
+
- **Compute Region:** [More Information Needed]
|
| 155 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 156 |
+
|
| 157 |
+
## Technical Specifications [optional]
|
| 158 |
+
|
| 159 |
+
### Model Architecture and Objective
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
### Compute Infrastructure
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Hardware
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
#### Software
|
| 172 |
+
|
| 173 |
+
[More Information Needed]
|
| 174 |
+
|
| 175 |
+
## Citation [optional]
|
| 176 |
+
|
| 177 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 178 |
+
|
| 179 |
+
**BibTeX:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
**APA:**
|
| 184 |
+
|
| 185 |
+
[More Information Needed]
|
| 186 |
+
|
| 187 |
+
## Glossary [optional]
|
| 188 |
+
|
| 189 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## More Information [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Authors [optional]
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
|
| 201 |
+
## Model Card Contact
|
| 202 |
+
|
| 203 |
+
[More Information Needed]
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- PEFT 0.19.1
|
checkpoint-15747/adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "facebook/mbart-large-50",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 16,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"fc2",
|
| 34 |
+
"v_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
+
"fc1",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"out_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_bdlora": null,
|
| 44 |
+
"use_dora": false,
|
| 45 |
+
"use_qalora": false,
|
| 46 |
+
"use_rslora": true
|
| 47 |
+
}
|
checkpoint-15747/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed68740976110a5a8e1053342ac6e2d75a14dec2906e0301b8c532ebcf022fc8
|
| 3 |
+
size 34656568
|
checkpoint-15747/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:305ca4d383e476beef6df746808ae0814a697f6cab16044cb37e5ef5c5dc34bc
|
| 3 |
+
size 69534499
|
checkpoint-15747/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d023c4e30fdefc45ca1bf32f69519b0d60e1112f468c3efcbb6d37783055e54d
|
| 3 |
+
size 14645
|
checkpoint-15747/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb765421b6da16525ba35cdf6df6969c34d19f525e5a77208c1e65c6ddab5de0
|
| 3 |
+
size 1465
|
checkpoint-15747/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
|
| 3 |
+
size 17109919
|
checkpoint-15747/tokenizer_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<s>",
|
| 8 |
+
"</s>",
|
| 9 |
+
"ar_AR",
|
| 10 |
+
"cs_CZ",
|
| 11 |
+
"de_DE",
|
| 12 |
+
"en_XX",
|
| 13 |
+
"es_XX",
|
| 14 |
+
"et_EE",
|
| 15 |
+
"fi_FI",
|
| 16 |
+
"fr_XX",
|
| 17 |
+
"gu_IN",
|
| 18 |
+
"hi_IN",
|
| 19 |
+
"it_IT",
|
| 20 |
+
"ja_XX",
|
| 21 |
+
"kk_KZ",
|
| 22 |
+
"ko_KR",
|
| 23 |
+
"lt_LT",
|
| 24 |
+
"lv_LV",
|
| 25 |
+
"my_MM",
|
| 26 |
+
"ne_NP",
|
| 27 |
+
"nl_XX",
|
| 28 |
+
"ro_RO",
|
| 29 |
+
"ru_RU",
|
| 30 |
+
"si_LK",
|
| 31 |
+
"tr_TR",
|
| 32 |
+
"vi_VN",
|
| 33 |
+
"zh_CN",
|
| 34 |
+
"af_ZA",
|
| 35 |
+
"az_AZ",
|
| 36 |
+
"bn_IN",
|
| 37 |
+
"fa_IR",
|
| 38 |
+
"he_IL",
|
| 39 |
+
"hr_HR",
|
| 40 |
+
"id_ID",
|
| 41 |
+
"ka_GE",
|
| 42 |
+
"km_KH",
|
| 43 |
+
"mk_MK",
|
| 44 |
+
"ml_IN",
|
| 45 |
+
"mn_MN",
|
| 46 |
+
"mr_IN",
|
| 47 |
+
"pl_PL",
|
| 48 |
+
"ps_AF",
|
| 49 |
+
"pt_XX",
|
| 50 |
+
"sv_SE",
|
| 51 |
+
"sw_KE",
|
| 52 |
+
"ta_IN",
|
| 53 |
+
"te_IN",
|
| 54 |
+
"th_TH",
|
| 55 |
+
"tl_XX",
|
| 56 |
+
"uk_UA",
|
| 57 |
+
"ur_PK",
|
| 58 |
+
"xh_ZA",
|
| 59 |
+
"gl_ES",
|
| 60 |
+
"sl_SI"
|
| 61 |
+
],
|
| 62 |
+
"is_local": false,
|
| 63 |
+
"mask_token": "<mask>",
|
| 64 |
+
"model_max_length": 1024,
|
| 65 |
+
"pad_token": "<pad>",
|
| 66 |
+
"sep_token": "</s>",
|
| 67 |
+
"src_lang": "en_XX",
|
| 68 |
+
"tgt_lang": "en_XX",
|
| 69 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 70 |
+
"unk_id": 0,
|
| 71 |
+
"unk_token": "<unk>"
|
| 72 |
+
}
|
checkpoint-15747/trainer_state.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 15747,
|
| 3 |
+
"best_metric": 4.732922554016113,
|
| 4 |
+
"best_model_checkpoint": "./output/mbart-large-first/checkpoint-15747",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 15747,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 2.2508127689361572,
|
| 15 |
+
"learning_rate": 2.1358242354377162e-05,
|
| 16 |
+
"loss": 5.126435169198895,
|
| 17 |
+
"step": 5249
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_loss": 4.782848834991455,
|
| 22 |
+
"eval_rouge1": 0.2626519199005293,
|
| 23 |
+
"eval_rouge2": 0.11815344657319395,
|
| 24 |
+
"eval_rougeL": 0.20149220585189942,
|
| 25 |
+
"eval_rougeLsum": 0.20168022656710616,
|
| 26 |
+
"eval_runtime": 950.7747,
|
| 27 |
+
"eval_samples_per_second": 4.129,
|
| 28 |
+
"eval_steps_per_second": 4.129,
|
| 29 |
+
"step": 5249
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 3.800706148147583,
|
| 34 |
+
"learning_rate": 1.0680138333220317e-05,
|
| 35 |
+
"loss": 4.756629238902648,
|
| 36 |
+
"step": 10498
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_loss": 4.745133399963379,
|
| 41 |
+
"eval_rouge1": 0.2812791287016354,
|
| 42 |
+
"eval_rouge2": 0.13410717394395671,
|
| 43 |
+
"eval_rougeL": 0.22017424943243102,
|
| 44 |
+
"eval_rougeLsum": 0.22024249247836936,
|
| 45 |
+
"eval_runtime": 1136.965,
|
| 46 |
+
"eval_samples_per_second": 3.453,
|
| 47 |
+
"eval_steps_per_second": 3.453,
|
| 48 |
+
"step": 10498
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"grad_norm": 3.2896928787231445,
|
| 53 |
+
"learning_rate": 2.034312063470536e-09,
|
| 54 |
+
"loss": 4.713336022337588,
|
| 55 |
+
"step": 15747
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.0,
|
| 59 |
+
"eval_loss": 4.732922554016113,
|
| 60 |
+
"eval_rouge1": 0.28348414256505183,
|
| 61 |
+
"eval_rouge2": 0.13573693703550854,
|
| 62 |
+
"eval_rougeL": 0.2211924448035419,
|
| 63 |
+
"eval_rougeLsum": 0.22134620876521682,
|
| 64 |
+
"eval_runtime": 937.6713,
|
| 65 |
+
"eval_samples_per_second": 4.187,
|
| 66 |
+
"eval_steps_per_second": 4.187,
|
| 67 |
+
"step": 15747
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"logging_steps": 500,
|
| 71 |
+
"max_steps": 15747,
|
| 72 |
+
"num_input_tokens_seen": 0,
|
| 73 |
+
"num_train_epochs": 3,
|
| 74 |
+
"save_steps": 500,
|
| 75 |
+
"stateful_callbacks": {
|
| 76 |
+
"TrainerControl": {
|
| 77 |
+
"args": {
|
| 78 |
+
"should_epoch_stop": false,
|
| 79 |
+
"should_evaluate": false,
|
| 80 |
+
"should_log": false,
|
| 81 |
+
"should_save": true,
|
| 82 |
+
"should_training_stop": true
|
| 83 |
+
},
|
| 84 |
+
"attributes": {}
|
| 85 |
+
}
|
| 86 |
+
},
|
| 87 |
+
"total_flos": 2.097698330074153e+17,
|
| 88 |
+
"train_batch_size": 1,
|
| 89 |
+
"trial_name": null,
|
| 90 |
+
"trial_params": null
|
| 91 |
+
}
|
checkpoint-15747/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15395dac053d64b4ff5c7d8b1bc15520dd512987b04f2d911cff1824280c5d00
|
| 3 |
+
size 7121
|
eval_results.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4f03ad6105b04dd845462d153ba6eeb909d474375f0cb400307cb7e9020d435
|
| 3 |
+
size 60244331
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"max_length": 200,
|
| 9 |
+
"max_time": 30,
|
| 10 |
+
"num_beams": 2,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "5.5.0",
|
| 13 |
+
"use_cache": true
|
| 14 |
+
}
|
meta_config.json
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "facebook/mbart-large-50",
|
| 3 |
+
"dataset_path": null,
|
| 4 |
+
"training_args": {
|
| 5 |
+
"output_dir": "./output/mbart-large-first",
|
| 6 |
+
"per_device_train_batch_size": 1,
|
| 7 |
+
"num_train_epochs": 3,
|
| 8 |
+
"max_steps": -1,
|
| 9 |
+
"learning_rate": 3e-05,
|
| 10 |
+
"lr_scheduler_type": "linear",
|
| 11 |
+
"lr_scheduler_kwargs": null,
|
| 12 |
+
"warmup_steps": 1000,
|
| 13 |
+
"optim": "adamw_torch_fused",
|
| 14 |
+
"optim_args": null,
|
| 15 |
+
"weight_decay": 0.01,
|
| 16 |
+
"adam_beta1": 0.9,
|
| 17 |
+
"adam_beta2": 0.999,
|
| 18 |
+
"adam_epsilon": 1e-08,
|
| 19 |
+
"optim_target_modules": null,
|
| 20 |
+
"gradient_accumulation_steps": 1,
|
| 21 |
+
"average_tokens_across_devices": true,
|
| 22 |
+
"max_grad_norm": 1.0,
|
| 23 |
+
"label_smoothing_factor": 0.0,
|
| 24 |
+
"bf16": true,
|
| 25 |
+
"fp16": false,
|
| 26 |
+
"bf16_full_eval": false,
|
| 27 |
+
"fp16_full_eval": false,
|
| 28 |
+
"tf32": null,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"gradient_checkpointing_kwargs": null,
|
| 31 |
+
"torch_compile": false,
|
| 32 |
+
"torch_compile_backend": null,
|
| 33 |
+
"torch_compile_mode": null,
|
| 34 |
+
"use_liger_kernel": false,
|
| 35 |
+
"liger_kernel_config": null,
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"neftune_noise_alpha": null,
|
| 38 |
+
"torch_empty_cache_steps": null,
|
| 39 |
+
"auto_find_batch_size": false,
|
| 40 |
+
"logging_strategy": "epoch",
|
| 41 |
+
"logging_steps": 500,
|
| 42 |
+
"logging_first_step": false,
|
| 43 |
+
"log_on_each_node": true,
|
| 44 |
+
"logging_nan_inf_filter": true,
|
| 45 |
+
"include_num_input_tokens_seen": "no",
|
| 46 |
+
"log_level": "passive",
|
| 47 |
+
"log_level_replica": "warning",
|
| 48 |
+
"disable_tqdm": false,
|
| 49 |
+
"report_to": [],
|
| 50 |
+
"run_name": null,
|
| 51 |
+
"project": "huggingface",
|
| 52 |
+
"trackio_space_id": "trackio",
|
| 53 |
+
"eval_strategy": "epoch",
|
| 54 |
+
"eval_steps": null,
|
| 55 |
+
"eval_delay": 0,
|
| 56 |
+
"per_device_eval_batch_size": 1,
|
| 57 |
+
"prediction_loss_only": false,
|
| 58 |
+
"eval_on_start": false,
|
| 59 |
+
"eval_do_concat_batches": true,
|
| 60 |
+
"eval_use_gather_object": false,
|
| 61 |
+
"eval_accumulation_steps": null,
|
| 62 |
+
"include_for_metrics": [],
|
| 63 |
+
"batch_eval_metrics": false,
|
| 64 |
+
"save_only_model": false,
|
| 65 |
+
"save_strategy": "epoch",
|
| 66 |
+
"save_steps": 500,
|
| 67 |
+
"save_on_each_node": false,
|
| 68 |
+
"save_total_limit": 2,
|
| 69 |
+
"enable_jit_checkpoint": false,
|
| 70 |
+
"push_to_hub": false,
|
| 71 |
+
"hub_token": "<HUB_TOKEN>",
|
| 72 |
+
"hub_private_repo": null,
|
| 73 |
+
"hub_model_id": null,
|
| 74 |
+
"hub_strategy": "every_save",
|
| 75 |
+
"hub_always_push": false,
|
| 76 |
+
"hub_revision": null,
|
| 77 |
+
"load_best_model_at_end": true,
|
| 78 |
+
"metric_for_best_model": "eval_loss",
|
| 79 |
+
"greater_is_better": false,
|
| 80 |
+
"ignore_data_skip": false,
|
| 81 |
+
"restore_callback_states_from_checkpoint": false,
|
| 82 |
+
"full_determinism": false,
|
| 83 |
+
"seed": 42,
|
| 84 |
+
"data_seed": null,
|
| 85 |
+
"use_cpu": false,
|
| 86 |
+
"accelerator_config": {
|
| 87 |
+
"split_batches": false,
|
| 88 |
+
"dispatch_batches": null,
|
| 89 |
+
"even_batches": true,
|
| 90 |
+
"use_seedable_sampler": true,
|
| 91 |
+
"non_blocking": false,
|
| 92 |
+
"gradient_accumulation_kwargs": null
|
| 93 |
+
},
|
| 94 |
+
"parallelism_config": null,
|
| 95 |
+
"dataloader_drop_last": false,
|
| 96 |
+
"dataloader_num_workers": 0,
|
| 97 |
+
"dataloader_pin_memory": true,
|
| 98 |
+
"dataloader_persistent_workers": false,
|
| 99 |
+
"dataloader_prefetch_factor": null,
|
| 100 |
+
"remove_unused_columns": true,
|
| 101 |
+
"label_names": null,
|
| 102 |
+
"train_sampling_strategy": "random",
|
| 103 |
+
"length_column_name": "length",
|
| 104 |
+
"ddp_find_unused_parameters": null,
|
| 105 |
+
"ddp_bucket_cap_mb": null,
|
| 106 |
+
"ddp_broadcast_buffers": null,
|
| 107 |
+
"ddp_backend": null,
|
| 108 |
+
"ddp_timeout": 1800,
|
| 109 |
+
"fsdp": [],
|
| 110 |
+
"fsdp_config": {
|
| 111 |
+
"min_num_params": 0,
|
| 112 |
+
"xla": false,
|
| 113 |
+
"xla_fsdp_v2": false,
|
| 114 |
+
"xla_fsdp_grad_ckpt": false
|
| 115 |
+
},
|
| 116 |
+
"deepspeed": null,
|
| 117 |
+
"debug": [],
|
| 118 |
+
"skip_memory_metrics": true,
|
| 119 |
+
"do_train": false,
|
| 120 |
+
"do_eval": true,
|
| 121 |
+
"do_predict": false,
|
| 122 |
+
"resume_from_checkpoint": null,
|
| 123 |
+
"warmup_ratio": null,
|
| 124 |
+
"logging_dir": null,
|
| 125 |
+
"local_rank": -1,
|
| 126 |
+
"sortish_sampler": false,
|
| 127 |
+
"predict_with_generate": true,
|
| 128 |
+
"generation_max_length": null,
|
| 129 |
+
"generation_num_beams": null,
|
| 130 |
+
"generation_config": {
|
| 131 |
+
"max_length": 200,
|
| 132 |
+
"max_new_tokens": null,
|
| 133 |
+
"min_length": null,
|
| 134 |
+
"min_new_tokens": null,
|
| 135 |
+
"early_stopping": true,
|
| 136 |
+
"max_time": 30,
|
| 137 |
+
"stop_strings": null,
|
| 138 |
+
"do_sample": null,
|
| 139 |
+
"num_beams": 2,
|
| 140 |
+
"use_cache": true,
|
| 141 |
+
"cache_implementation": null,
|
| 142 |
+
"cache_config": null,
|
| 143 |
+
"temperature": null,
|
| 144 |
+
"top_k": null,
|
| 145 |
+
"top_p": null,
|
| 146 |
+
"min_p": null,
|
| 147 |
+
"top_h": null,
|
| 148 |
+
"typical_p": null,
|
| 149 |
+
"epsilon_cutoff": null,
|
| 150 |
+
"eta_cutoff": null,
|
| 151 |
+
"repetition_penalty": null,
|
| 152 |
+
"encoder_repetition_penalty": null,
|
| 153 |
+
"length_penalty": null,
|
| 154 |
+
"no_repeat_ngram_size": null,
|
| 155 |
+
"bad_words_ids": null,
|
| 156 |
+
"renormalize_logits": null,
|
| 157 |
+
"forced_bos_token_id": null,
|
| 158 |
+
"forced_eos_token_id": 2,
|
| 159 |
+
"remove_invalid_values": null,
|
| 160 |
+
"exponential_decay_length_penalty": null,
|
| 161 |
+
"suppress_tokens": null,
|
| 162 |
+
"begin_suppress_tokens": null,
|
| 163 |
+
"sequence_bias": null,
|
| 164 |
+
"token_healing": null,
|
| 165 |
+
"guidance_scale": null,
|
| 166 |
+
"watermarking_config": null,
|
| 167 |
+
"num_return_sequences": null,
|
| 168 |
+
"output_attentions": null,
|
| 169 |
+
"output_hidden_states": null,
|
| 170 |
+
"output_scores": null,
|
| 171 |
+
"output_logits": null,
|
| 172 |
+
"return_dict_in_generate": null,
|
| 173 |
+
"pad_token_id": 1,
|
| 174 |
+
"bos_token_id": 0,
|
| 175 |
+
"eos_token_id": 2,
|
| 176 |
+
"encoder_no_repeat_ngram_size": null,
|
| 177 |
+
"decoder_start_token_id": 2,
|
| 178 |
+
"is_assistant": null,
|
| 179 |
+
"num_assistant_tokens": null,
|
| 180 |
+
"num_assistant_tokens_schedule": null,
|
| 181 |
+
"assistant_confidence_threshold": null,
|
| 182 |
+
"prompt_lookup_num_tokens": null,
|
| 183 |
+
"max_matching_ngram_size": null,
|
| 184 |
+
"assistant_early_exit": null,
|
| 185 |
+
"assistant_lookbehind": null,
|
| 186 |
+
"target_lookbehind": null,
|
| 187 |
+
"compile_config": null,
|
| 188 |
+
"disable_compile": null,
|
| 189 |
+
"continuous_batching_config": null,
|
| 190 |
+
"low_memory": null,
|
| 191 |
+
"penalty_alpha": null,
|
| 192 |
+
"dola_layers": null,
|
| 193 |
+
"diversity_penalty": null,
|
| 194 |
+
"num_beam_groups": null,
|
| 195 |
+
"constraints": null,
|
| 196 |
+
"force_words_ids": null,
|
| 197 |
+
"prefill_chunk_size": null,
|
| 198 |
+
"_from_model_config": true,
|
| 199 |
+
"transformers_version": "5.5.0"
|
| 200 |
+
}
|
| 201 |
+
},
|
| 202 |
+
"INPUT_COL": "combined_text",
|
| 203 |
+
"LABEL_COL": "summary",
|
| 204 |
+
"columns_to_keep": [
|
| 205 |
+
"combined_text",
|
| 206 |
+
"summary"
|
| 207 |
+
],
|
| 208 |
+
"run_cfg": {
|
| 209 |
+
"model_name": "facebook/mbart-large-50",
|
| 210 |
+
"output_dir": "./output/mbart-large-first",
|
| 211 |
+
"LM_type": "seq2seq",
|
| 212 |
+
"input_col_name": "combined_text",
|
| 213 |
+
"label_col_name": "summary",
|
| 214 |
+
"input_text_max_length": 1024,
|
| 215 |
+
"summary_text_max_length": 256,
|
| 216 |
+
"pad_to_multiple_of_input_text": 1024,
|
| 217 |
+
"pad_to_multiple_of_summary_text": 1,
|
| 218 |
+
"batch_max_tokens": 16384,
|
| 219 |
+
"batch_max_tokens_multiplier": 0.8,
|
| 220 |
+
"hyperparameter_search": false,
|
| 221 |
+
"objective_is_loss": false,
|
| 222 |
+
"bf16": true,
|
| 223 |
+
"gradient_accumulation_steps": 1,
|
| 224 |
+
"num_train_epochs": 3,
|
| 225 |
+
"learning_rate": 3e-05,
|
| 226 |
+
"weight_decay": 0.01,
|
| 227 |
+
"max_grad_norm": 1.0,
|
| 228 |
+
"lr_scheduler_type": "cosine",
|
| 229 |
+
"target_modules": "all-linear",
|
| 230 |
+
"training_optim": "adamw_torch_fused",
|
| 231 |
+
"peft_gradient_checkpointing": false,
|
| 232 |
+
"own_bartled_underlying_model": null,
|
| 233 |
+
"selector_name": "first"
|
| 234 |
+
}
|
| 235 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539a6fc9fc66bb000c4a560cb8db87e5bb673a0786cb028b080ebd787025f2d4
|
| 3 |
+
size 17109919
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<s>",
|
| 8 |
+
"</s>",
|
| 9 |
+
"ar_AR",
|
| 10 |
+
"cs_CZ",
|
| 11 |
+
"de_DE",
|
| 12 |
+
"en_XX",
|
| 13 |
+
"es_XX",
|
| 14 |
+
"et_EE",
|
| 15 |
+
"fi_FI",
|
| 16 |
+
"fr_XX",
|
| 17 |
+
"gu_IN",
|
| 18 |
+
"hi_IN",
|
| 19 |
+
"it_IT",
|
| 20 |
+
"ja_XX",
|
| 21 |
+
"kk_KZ",
|
| 22 |
+
"ko_KR",
|
| 23 |
+
"lt_LT",
|
| 24 |
+
"lv_LV",
|
| 25 |
+
"my_MM",
|
| 26 |
+
"ne_NP",
|
| 27 |
+
"nl_XX",
|
| 28 |
+
"ro_RO",
|
| 29 |
+
"ru_RU",
|
| 30 |
+
"si_LK",
|
| 31 |
+
"tr_TR",
|
| 32 |
+
"vi_VN",
|
| 33 |
+
"zh_CN",
|
| 34 |
+
"af_ZA",
|
| 35 |
+
"az_AZ",
|
| 36 |
+
"bn_IN",
|
| 37 |
+
"fa_IR",
|
| 38 |
+
"he_IL",
|
| 39 |
+
"hr_HR",
|
| 40 |
+
"id_ID",
|
| 41 |
+
"ka_GE",
|
| 42 |
+
"km_KH",
|
| 43 |
+
"mk_MK",
|
| 44 |
+
"ml_IN",
|
| 45 |
+
"mn_MN",
|
| 46 |
+
"mr_IN",
|
| 47 |
+
"pl_PL",
|
| 48 |
+
"ps_AF",
|
| 49 |
+
"pt_XX",
|
| 50 |
+
"sv_SE",
|
| 51 |
+
"sw_KE",
|
| 52 |
+
"ta_IN",
|
| 53 |
+
"te_IN",
|
| 54 |
+
"th_TH",
|
| 55 |
+
"tl_XX",
|
| 56 |
+
"uk_UA",
|
| 57 |
+
"ur_PK",
|
| 58 |
+
"xh_ZA",
|
| 59 |
+
"gl_ES",
|
| 60 |
+
"sl_SI"
|
| 61 |
+
],
|
| 62 |
+
"is_local": false,
|
| 63 |
+
"mask_token": "<mask>",
|
| 64 |
+
"model_max_length": 1024,
|
| 65 |
+
"pad_token": "<pad>",
|
| 66 |
+
"sep_token": "</s>",
|
| 67 |
+
"src_lang": "en_XX",
|
| 68 |
+
"tgt_lang": "en_XX",
|
| 69 |
+
"tokenizer_class": "MBart50Tokenizer",
|
| 70 |
+
"unk_id": 0,
|
| 71 |
+
"unk_token": "<unk>"
|
| 72 |
+
}
|