初始化项目，由ModelHub XC社区提供模型
Model: Henry236/east8b-eg-lora-turn Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
48
adapter_config.json
Normal file
48
adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"up_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
adapter_model.safetensors
Normal file
3
adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a58b64675456f9242881e64f10abf25bef6ea8d29df1fc65eb8d04eff9ca1633
|
||||
size 671149168
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
|
||||
|
||||
' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
|
||||
207
checkpoint-100/README.md
Normal file
207
checkpoint-100/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-100/adapter_config.json
Normal file
48
checkpoint-100/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"up_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-100/adapter_model.safetensors
Normal file
3
checkpoint-100/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:177dc733914df11675ddfca8547f927750a204fdfc63d6e0cff9068ab7ce7e47
|
||||
size 671149168
|
||||
3
checkpoint-100/optimizer.pt
Normal file
3
checkpoint-100/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47f04fb2ef88419ba56738399657c6ca30d2b64d90af4758eb9866afc72195b0
|
||||
size 1342562339
|
||||
3
checkpoint-100/rng_state.pth
Normal file
3
checkpoint-100/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:59d1ca128ae5cf286d7c6161f33a4ec84d54896c3e4ed19ac65a0e26fa04257b
|
||||
size 14645
|
||||
3
checkpoint-100/scheduler.pt
Normal file
3
checkpoint-100/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a965538a990c1bee6cafb2ee94e4c27c3d42d8dd819e2e80a5cad5750681c87
|
||||
size 1465
|
||||
69
checkpoint-100/trainer_state.json
Normal file
69
checkpoint-100/trainer_state.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.1736111111111111,
|
||||
"eval_steps": 500,
|
||||
"global_step": 100,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.5287952423095703,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.9236105680465698,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.2698,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7310758829116821,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1239,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6232755184173584,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.9686,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0284266471862793,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8519,
|
||||
"step": 100
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 1.952829443063808e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-100/training_args.bin
Normal file
3
checkpoint-100/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95c8504a9e287f63ef7ae2af125d6ce037a2a735a081af84b08d1088ad0a71df
|
||||
size 5969
|
||||
207
checkpoint-1000/README.md
Normal file
207
checkpoint-1000/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-1000/adapter_config.json
Normal file
48
checkpoint-1000/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-1000/adapter_model.safetensors
Normal file
3
checkpoint-1000/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98ef97845d6540c8ac5b9c06dfcb4af8977a7a10a18b89ef5d231ee4355e0daa
|
||||
size 671149168
|
||||
3
checkpoint-1000/optimizer.pt
Normal file
3
checkpoint-1000/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24f425709dfb6218e9e1da037e4025c88f1cd89e4f471ba6e23654a710b2e3df
|
||||
size 1342562339
|
||||
3
checkpoint-1000/rng_state.pth
Normal file
3
checkpoint-1000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1bec9634a694fb3fae48715cd8b4c7686d4953c8c1eaf33350b3387d208503dc
|
||||
size 14645
|
||||
3
checkpoint-1000/scheduler.pt
Normal file
3
checkpoint-1000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3faa60702eeec70c307ffab2e710a51a22e86b2f89bbb3effe498e101641bee8
|
||||
size 1465
|
||||
384
checkpoint-1000/trainer_state.json
Normal file
384
checkpoint-1000/trainer_state.json
Normal file
@@ -0,0 +1,384 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.7361111111111112,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1000,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0398788452148438,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7814712524414062,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 2.9422523975372314,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.4645,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.5797832012176514,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4473,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.557054281234741,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.4428,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.7312850952148438,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4014,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.2819321155548096,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4214,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 2.9412100315093994,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4367,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 4.002957820892334,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4019,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 3.2070395946502686,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3294,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.3583526611328125,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3302,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 4.011720657348633,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.2973,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.383192539215088,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3066,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.335385322570801,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3068,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.696607828140259,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3135,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.395407199859619,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.2704,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.829279661178589,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.2869,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.77693510055542,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.2903,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.946527004241943,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.2661,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 3.0826640129089355,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.2786,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.134871959686279,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2386,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 3.8811264038085938,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2478,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 4.137213230133057,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.2635,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.4709768295288086,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2247,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.841049909591675,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.2721,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.412503480911255,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2439,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.341178894042969,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2459,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.485387325286865,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.2659,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.731579303741455,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2283,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.4078001976013184,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2187,
|
||||
"step": 1000
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 1.9555180478889984e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-1000/training_args.bin
Normal file
3
checkpoint-1000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-1050/README.md
Normal file
207
checkpoint-1050/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-1050/adapter_config.json
Normal file
48
checkpoint-1050/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-1050/adapter_model.safetensors
Normal file
3
checkpoint-1050/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd953539bbfb30b2b2457b7b78aa71bcc80792e5485f9ab73ca0d2bcfaf0bd4a
|
||||
size 671149168
|
||||
3
checkpoint-1050/optimizer.pt
Normal file
3
checkpoint-1050/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94151b9651f8f14b770ca6a722dbfa1c8c3c09b0241eff460ce03c1fcdb3118a
|
||||
size 1342562339
|
||||
3
checkpoint-1050/rng_state.pth
Normal file
3
checkpoint-1050/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c2836c708079693320dc1d474758cba33bcedadf31ce3497bb4991f109d2c3a
|
||||
size 14645
|
||||
3
checkpoint-1050/scheduler.pt
Normal file
3
checkpoint-1050/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:abe9abb5efc489b294c297766a8ae2c71262b2cf1b3df1555b36fda19a8e7406
|
||||
size 1465
|
||||
398
checkpoint-1050/trainer_state.json
Normal file
398
checkpoint-1050/trainer_state.json
Normal file
@@ -0,0 +1,398 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.8229166666666665,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1050,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0398788452148438,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7814712524414062,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 2.9422523975372314,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.4645,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.5797832012176514,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4473,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.557054281234741,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.4428,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.7312850952148438,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4014,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.2819321155548096,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4214,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 2.9412100315093994,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4367,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 4.002957820892334,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4019,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 3.2070395946502686,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3294,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.3583526611328125,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3302,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 4.011720657348633,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.2973,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.383192539215088,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3066,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.335385322570801,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3068,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.696607828140259,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3135,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.395407199859619,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.2704,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.829279661178589,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.2869,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.77693510055542,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.2903,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.946527004241943,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.2661,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 3.0826640129089355,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.2786,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.134871959686279,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2386,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 3.8811264038085938,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2478,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 4.137213230133057,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.2635,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.4709768295288086,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2247,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.841049909591675,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.2721,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.412503480911255,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2439,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.341178894042969,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2459,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.485387325286865,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.2659,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.731579303741455,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2283,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.4078001976013184,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2187,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.608993053436279,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2284,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.286625862121582,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.2042,
|
||||
"step": 1040
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.053898886369116e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-1050/training_args.bin
Normal file
3
checkpoint-1050/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-1100/README.md
Normal file
207
checkpoint-1100/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-1100/adapter_config.json
Normal file
48
checkpoint-1100/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-1100/adapter_model.safetensors
Normal file
3
checkpoint-1100/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a023b767dbbd7234cc59d342c25b4f4176295af70ec5325ee0527673bafb9590
|
||||
size 671149168
|
||||
3
checkpoint-1100/optimizer.pt
Normal file
3
checkpoint-1100/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c153bc31c0ceec475faf884c579392bae810a05a6e0c68bc439ac9d2e2d3ac42
|
||||
size 1342562339
|
||||
3
checkpoint-1100/rng_state.pth
Normal file
3
checkpoint-1100/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13b9e42bed996462bb4de8caee0ac43e0c854ab096871c649f128ed02eb44975
|
||||
size 14645
|
||||
3
checkpoint-1100/scheduler.pt
Normal file
3
checkpoint-1100/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:315c6a6de3128d29cfc459c9f1551c37f38030611e281b0aa330fe139ba0892f
|
||||
size 1465
|
||||
419
checkpoint-1100/trainer_state.json
Normal file
419
checkpoint-1100/trainer_state.json
Normal file
@@ -0,0 +1,419 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.9097222222222223,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1100,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0398788452148438,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7814712524414062,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 2.9422523975372314,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.4645,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.5797832012176514,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4473,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.557054281234741,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.4428,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.7312850952148438,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4014,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.2819321155548096,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4214,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 2.9412100315093994,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4367,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 4.002957820892334,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4019,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 3.2070395946502686,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3294,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.3583526611328125,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3302,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 4.011720657348633,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.2973,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.383192539215088,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3066,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.335385322570801,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3068,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.696607828140259,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3135,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.395407199859619,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.2704,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.829279661178589,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.2869,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.77693510055542,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.2903,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.946527004241943,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.2661,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 3.0826640129089355,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.2786,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.134871959686279,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2386,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 3.8811264038085938,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2478,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 4.137213230133057,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.2635,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.4709768295288086,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2247,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.841049909591675,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.2721,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.412503480911255,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2439,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.341178894042969,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2459,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.485387325286865,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.2659,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.731579303741455,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2283,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.4078001976013184,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2187,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.608993053436279,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2284,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.286625862121582,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.2042,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.8402777777777777,
|
||||
"grad_norm": 3.952650547027588,
|
||||
"learning_rate": 1.975176196540185e-07,
|
||||
"loss": 1.2272,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.875,
|
||||
"grad_norm": 4.211365699768066,
|
||||
"learning_rate": 1.2200896627521718e-07,
|
||||
"loss": 1.2411,
|
||||
"step": 1080
|
||||
},
|
||||
{
|
||||
"epoch": 1.9097222222222223,
|
||||
"grad_norm": 3.815666675567627,
|
||||
"learning_rate": 6.443724232808146e-08,
|
||||
"loss": 1.2112,
|
||||
"step": 1100
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.1503295655958938e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-1100/training_args.bin
Normal file
3
checkpoint-1100/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-1150/README.md
Normal file
207
checkpoint-1150/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-1150/adapter_config.json
Normal file
48
checkpoint-1150/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-1150/adapter_model.safetensors
Normal file
3
checkpoint-1150/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:72a130c7a4596d6e50fe85fd0be2a96caa3c0f6923ef43932fd5c9cf9a41866f
|
||||
size 671149168
|
||||
3
checkpoint-1150/optimizer.pt
Normal file
3
checkpoint-1150/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7cbd1671013e6429a08c1abc1811e40a7324f7254c98fcbde62d3182f49b9d63
|
||||
size 1342562339
|
||||
3
checkpoint-1150/rng_state.pth
Normal file
3
checkpoint-1150/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:52fe0d170b8537a026a59ac91014d47d5e7215b953446520a0d813df7c75d6bf
|
||||
size 14645
|
||||
3
checkpoint-1150/scheduler.pt
Normal file
3
checkpoint-1150/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:28b81089eb143a676da720978f118caf9eee0a372736c9ef6f38cdec3dd8d997
|
||||
size 1465
|
||||
433
checkpoint-1150/trainer_state.json
Normal file
433
checkpoint-1150/trainer_state.json
Normal file
@@ -0,0 +1,433 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.9965277777777777,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1150,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0398788452148438,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7814712524414062,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 2.9422523975372314,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.4645,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.5797832012176514,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4473,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.557054281234741,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.4428,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.7312850952148438,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4014,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.2819321155548096,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4214,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 2.9412100315093994,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4367,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 4.002957820892334,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4019,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 3.2070395946502686,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3294,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.3583526611328125,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3302,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 4.011720657348633,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.2973,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.383192539215088,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3066,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.335385322570801,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3068,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.696607828140259,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3135,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.395407199859619,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.2704,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.829279661178589,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.2869,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.77693510055542,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.2903,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.946527004241943,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.2661,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 3.0826640129089355,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.2786,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.134871959686279,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2386,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 3.8811264038085938,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2478,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 4.137213230133057,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.2635,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.4709768295288086,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2247,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.841049909591675,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.2721,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.412503480911255,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2439,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.341178894042969,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2459,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.485387325286865,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.2659,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.731579303741455,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2283,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.4078001976013184,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2187,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.608993053436279,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2284,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.286625862121582,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.2042,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.8402777777777777,
|
||||
"grad_norm": 3.952650547027588,
|
||||
"learning_rate": 1.975176196540185e-07,
|
||||
"loss": 1.2272,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.875,
|
||||
"grad_norm": 4.211365699768066,
|
||||
"learning_rate": 1.2200896627521718e-07,
|
||||
"loss": 1.2411,
|
||||
"step": 1080
|
||||
},
|
||||
{
|
||||
"epoch": 1.9097222222222223,
|
||||
"grad_norm": 3.815666675567627,
|
||||
"learning_rate": 6.443724232808146e-08,
|
||||
"loss": 1.2112,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 1.9444444444444444,
|
||||
"grad_norm": 4.6903839111328125,
|
||||
"learning_rate": 2.501414560839577e-08,
|
||||
"loss": 1.2108,
|
||||
"step": 1120
|
||||
},
|
||||
{
|
||||
"epoch": 1.9791666666666665,
|
||||
"grad_norm": 3.7579894065856934,
|
||||
"learning_rate": 3.884639339534202e-09,
|
||||
"loss": 1.2249,
|
||||
"step": 1140
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.2490694985560883e+17,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-1150/training_args.bin
Normal file
3
checkpoint-1150/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-150/README.md
Normal file
207
checkpoint-150/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-150/adapter_config.json
Normal file
48
checkpoint-150/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-150/adapter_model.safetensors
Normal file
3
checkpoint-150/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74774440d969f91e9cbc1288fde7da0e60c4dcd08214604f568c7eaa13c8c96f
|
||||
size 671149168
|
||||
3
checkpoint-150/optimizer.pt
Normal file
3
checkpoint-150/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0447fe346bc6ae8298a45e6fdee1887243fec53b673015d22b44edd7aa3c6aa1
|
||||
size 1342562339
|
||||
3
checkpoint-150/rng_state.pth
Normal file
3
checkpoint-150/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b5ff99b517bc4bdbd8bd289899bd56ddf2bc69c026f86fc6407cec9838df09d
|
||||
size 14645
|
||||
3
checkpoint-150/scheduler.pt
Normal file
3
checkpoint-150/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e5c3b1f4b3d2abec87ff5069b5d5df261c03ab9fab7ada1150395aac7685dc6
|
||||
size 1465
|
||||
83
checkpoint-150/trainer_state.json
Normal file
83
checkpoint-150/trainer_state.json
Normal file
@@ -0,0 +1,83 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.2604166666666667,
|
||||
"eval_steps": 500,
|
||||
"global_step": 150,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.926675257930547e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-150/training_args.bin
Normal file
3
checkpoint-150/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-200/README.md
Normal file
207
checkpoint-200/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-200/adapter_config.json
Normal file
48
checkpoint-200/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-200/adapter_model.safetensors
Normal file
3
checkpoint-200/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6746ccd4a4d01867f0da880445055970a8a3bc279f395f901d5bbca13950b454
|
||||
size 671149168
|
||||
3
checkpoint-200/optimizer.pt
Normal file
3
checkpoint-200/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0102d90737ad3134b4c4e5ad3c36b34d2e3c732be3cba4b55035f5abcf0b57c9
|
||||
size 1342562339
|
||||
3
checkpoint-200/rng_state.pth
Normal file
3
checkpoint-200/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b67a3e3d5b8f172d61c41b8fc389737e67f209cc2fbebe63841b61e06327c92
|
||||
size 14645
|
||||
3
checkpoint-200/scheduler.pt
Normal file
3
checkpoint-200/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dacf44b20691c6fc535bf16b0ef4e66f3a5b3cb2170a2da905fbebeb4c5a46ff
|
||||
size 1465
|
||||
104
checkpoint-200/trainer_state.json
Normal file
104
checkpoint-200/trainer_state.json
Normal file
@@ -0,0 +1,104 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.3472222222222222,
|
||||
"eval_steps": 500,
|
||||
"global_step": 200,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 3.92832787612631e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-200/training_args.bin
Normal file
3
checkpoint-200/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-250/README.md
Normal file
207
checkpoint-250/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-250/adapter_config.json
Normal file
48
checkpoint-250/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-250/adapter_model.safetensors
Normal file
3
checkpoint-250/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:70ef926d7cb7d6ebf487c946d7f0f3a0660e06699aae04cf44e00019fa695061
|
||||
size 671149168
|
||||
3
checkpoint-250/optimizer.pt
Normal file
3
checkpoint-250/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:768784f7ec6acba2face9bc2485e3924acb527d9487a3102f09b81212e109312
|
||||
size 1342562339
|
||||
3
checkpoint-250/rng_state.pth
Normal file
3
checkpoint-250/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8e5e1ac8f9f1697e3bc284b46f81101fb0642bca6e30981821b78dd62d98129b
|
||||
size 14645
|
||||
3
checkpoint-250/scheduler.pt
Normal file
3
checkpoint-250/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12bc768c5ceac0892205b61d77c6800d899da633a32337206aa415df9749b66a
|
||||
size 1465
|
||||
118
checkpoint-250/trainer_state.json
Normal file
118
checkpoint-250/trainer_state.json
Normal file
@@ -0,0 +1,118 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.4340277777777778,
|
||||
"eval_steps": 500,
|
||||
"global_step": 250,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 4.899613991878656e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-250/training_args.bin
Normal file
3
checkpoint-250/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-300/README.md
Normal file
207
checkpoint-300/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-300/adapter_config.json
Normal file
48
checkpoint-300/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"o_proj",
|
||||
"gate_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"up_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-300/adapter_model.safetensors
Normal file
3
checkpoint-300/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d6472d499937d2fc466bc5248d763427304ebea78eb098cf571df43f9f7048f0
|
||||
size 671149168
|
||||
3
checkpoint-300/optimizer.pt
Normal file
3
checkpoint-300/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a5e61092ae80965d6885e4588ceac6a6dc8e55146f4226ab1e720d127e624d7
|
||||
size 1342562339
|
||||
3
checkpoint-300/rng_state.pth
Normal file
3
checkpoint-300/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50a6cecaf777531098b542e8fe3720c5dca8ef4962521136493806bc72d93b0f
|
||||
size 14645
|
||||
3
checkpoint-300/scheduler.pt
Normal file
3
checkpoint-300/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8011544f8969ccf121f310e7c9677b774202f770f03769833c73ecbfadde40a4
|
||||
size 1465
|
||||
139
checkpoint-300/trainer_state.json
Normal file
139
checkpoint-300/trainer_state.json
Normal file
@@ -0,0 +1,139 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.5208333333333334,
|
||||
"eval_steps": 500,
|
||||
"global_step": 300,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.5287952423095703,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.9236105680465698,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.2698,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7310758829116821,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1239,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6232755184173584,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.9686,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0284266471862793,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8519,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1752660274505615,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8514,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.468181848526001,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7449,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0356285572052,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6723,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3106741905212402,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.265456199645996,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.632,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4798583984375,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6189,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4368059635162354,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6295,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.782370090484619,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.5973,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.735018014907837,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.5953,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.905834913253784,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5922,
|
||||
"step": 300
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 5.858525159394509e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-300/training_args.bin
Normal file
3
checkpoint-300/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:95c8504a9e287f63ef7ae2af125d6ce037a2a735a081af84b08d1088ad0a71df
|
||||
size 5969
|
||||
207
checkpoint-350/README.md
Normal file
207
checkpoint-350/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-350/adapter_config.json
Normal file
48
checkpoint-350/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-350/adapter_model.safetensors
Normal file
3
checkpoint-350/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44012ffb44463f205eca7d71d10ce1dd20d1b0f002346fd4dcdf614d903e9ee6
|
||||
size 671149168
|
||||
3
checkpoint-350/optimizer.pt
Normal file
3
checkpoint-350/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8dabff6caa61f8aeb0b5f894c9e3d2c42c90631fd6fac141a9dd5e7818717087
|
||||
size 1342562339
|
||||
3
checkpoint-350/rng_state.pth
Normal file
3
checkpoint-350/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3d5cbcccde05687b501efb2483b12f919f73c983685fcd85d56b4009e655910
|
||||
size 14645
|
||||
3
checkpoint-350/scheduler.pt
Normal file
3
checkpoint-350/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a6d13f122fa4e9259c6cf2ccd0d4a831e7733be6388a9b01a859d975eb74082
|
||||
size 1465
|
||||
153
checkpoint-350/trainer_state.json
Normal file
153
checkpoint-350/trainer_state.json
Normal file
@@ -0,0 +1,153 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.6076388888888888,
|
||||
"eval_steps": 500,
|
||||
"global_step": 350,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 6.818485987698278e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-350/training_args.bin
Normal file
3
checkpoint-350/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-400/README.md
Normal file
207
checkpoint-400/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-400/adapter_config.json
Normal file
48
checkpoint-400/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-400/adapter_model.safetensors
Normal file
3
checkpoint-400/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a5a35fc8f03e07f0d79eccff0ac69597398394524058ed9768549422e2b41890
|
||||
size 671149168
|
||||
3
checkpoint-400/optimizer.pt
Normal file
3
checkpoint-400/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7b3ff7b2607fd118a6ab2f04600012aac2de772b064635f871eafc2a66a7964
|
||||
size 1342562339
|
||||
3
checkpoint-400/rng_state.pth
Normal file
3
checkpoint-400/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b90eeed1f2a40be670ba230d57abf221bdaf4d742ef93488de052c9f9371a9b3
|
||||
size 14645
|
||||
3
checkpoint-400/scheduler.pt
Normal file
3
checkpoint-400/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:20cc7f2c390b57e07da00163d66a7f2ae7ece3e78a62f304c58c0f81ef0baa87
|
||||
size 1465
|
||||
174
checkpoint-400/trainer_state.json
Normal file
174
checkpoint-400/trainer_state.json
Normal file
@@ -0,0 +1,174 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.6944444444444444,
|
||||
"eval_steps": 500,
|
||||
"global_step": 400,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 7.790398216903066e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-400/training_args.bin
Normal file
3
checkpoint-400/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
207
checkpoint-450/README.md
Normal file
207
checkpoint-450/README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
base_model: biaofu-xmu/EAST-8B
|
||||
library_name: peft
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- base_model:adapter:biaofu-xmu/EAST-8B
|
||||
- lora
|
||||
- transformers
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
|
||||
|
||||
- **Developed by:** [More Information Needed]
|
||||
- **Funded by [optional]:** [More Information Needed]
|
||||
- **Shared by [optional]:** [More Information Needed]
|
||||
- **Model type:** [More Information Needed]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [More Information Needed]
|
||||
|
||||
### Model Sources [optional]
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## Uses
|
||||
|
||||
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Downstream Use [optional]
|
||||
|
||||
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Recommendations
|
||||
|
||||
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||
|
||||
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Training Details
|
||||
|
||||
### Training Data
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Training Procedure
|
||||
|
||||
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||
|
||||
#### Preprocessing [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
|
||||
#### Training Hyperparameters
|
||||
|
||||
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||
|
||||
#### Speeds, Sizes, Times [optional]
|
||||
|
||||
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Evaluation
|
||||
|
||||
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||
|
||||
### Testing Data, Factors & Metrics
|
||||
|
||||
#### Testing Data
|
||||
|
||||
<!-- This should link to a Dataset Card if possible. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Factors
|
||||
|
||||
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Metrics
|
||||
|
||||
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Results
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Summary
|
||||
|
||||
|
||||
|
||||
## Model Examination [optional]
|
||||
|
||||
<!-- Relevant interpretability work for the model goes here -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Environmental Impact
|
||||
|
||||
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||
|
||||
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).
|
||||
|
||||
- **Hardware Type:** [More Information Needed]
|
||||
- **Hours used:** [More Information Needed]
|
||||
- **Cloud Provider:** [More Information Needed]
|
||||
- **Compute Region:** [More Information Needed]
|
||||
- **Carbon Emitted:** [More Information Needed]
|
||||
|
||||
## Technical Specifications [optional]
|
||||
|
||||
### Model Architecture and Objective
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
### Compute Infrastructure
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Hardware
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
#### Software
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Citation [optional]
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
|
||||
**BibTeX:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
**APA:**
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Glossary [optional]
|
||||
|
||||
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## More Information [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Authors [optional]
|
||||
|
||||
[More Information Needed]
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[More Information Needed]
|
||||
### Framework versions
|
||||
|
||||
- PEFT 0.19.1
|
||||
48
checkpoint-450/adapter_config.json
Normal file
48
checkpoint-450/adapter_config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"alora_invocation_tokens": null,
|
||||
"alpha_pattern": {},
|
||||
"arrow_config": null,
|
||||
"auto_mapping": null,
|
||||
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
|
||||
"bias": "none",
|
||||
"corda_config": null,
|
||||
"ensure_weight_tying": false,
|
||||
"eva_config": null,
|
||||
"exclude_modules": null,
|
||||
"fan_in_fan_out": false,
|
||||
"inference_mode": true,
|
||||
"init_lora_weights": true,
|
||||
"layer_replication": null,
|
||||
"layers_pattern": null,
|
||||
"layers_to_transform": null,
|
||||
"loftq_config": {},
|
||||
"lora_alpha": 128,
|
||||
"lora_bias": false,
|
||||
"lora_dropout": 0.05,
|
||||
"lora_ga_config": null,
|
||||
"megatron_config": null,
|
||||
"megatron_core": "megatron.core",
|
||||
"modules_to_save": null,
|
||||
"peft_type": "LORA",
|
||||
"peft_version": "0.19.1",
|
||||
"qalora_group_size": 16,
|
||||
"r": 64,
|
||||
"rank_pattern": {},
|
||||
"revision": null,
|
||||
"target_modules": [
|
||||
"v_proj",
|
||||
"q_proj",
|
||||
"down_proj",
|
||||
"up_proj",
|
||||
"gate_proj",
|
||||
"o_proj",
|
||||
"k_proj"
|
||||
],
|
||||
"target_parameters": null,
|
||||
"task_type": "CAUSAL_LM",
|
||||
"trainable_token_indices": null,
|
||||
"use_bdlora": null,
|
||||
"use_dora": false,
|
||||
"use_qalora": false,
|
||||
"use_rslora": false
|
||||
}
|
||||
3
checkpoint-450/adapter_model.safetensors
Normal file
3
checkpoint-450/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:da771f6ac076cc97dafc07380a20054b70da831e640deed7eda4403f6399d91c
|
||||
size 671149168
|
||||
3
checkpoint-450/optimizer.pt
Normal file
3
checkpoint-450/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fae346fe8a6e90c38e92b8062d5c353641e7acd243a81c696652d66e97067b3b
|
||||
size 1342562339
|
||||
3
checkpoint-450/rng_state.pth
Normal file
3
checkpoint-450/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dcb58e88018052730dc2346279ee7548ba3296cd5ce86d00e70658ddd6873fe7
|
||||
size 14645
|
||||
3
checkpoint-450/scheduler.pt
Normal file
3
checkpoint-450/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:384bc6e7c7dc78761d777acc2ec342f72b87fe7d2483bfdf597b557007de8a7d
|
||||
size 1465
|
||||
188
checkpoint-450/trainer_state.json
Normal file
188
checkpoint-450/trainer_state.json
Normal file
@@ -0,0 +1,188 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.78125,
|
||||
"eval_steps": 500,
|
||||
"global_step": 450,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.034722222222222224,
|
||||
"grad_norm": 2.548311471939087,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.4451,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 1.93834388256073,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.269,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 1.7273279428482056,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.1237,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.6319563388824463,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 1.969,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.0262465476989746,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.8517,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.1673457622528076,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.851,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.474327802658081,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7448,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.0316762924194336,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.6721,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.3124542236328125,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7265,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.2682251930236816,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6325,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.4642767906188965,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6193,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4372549057006836,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6297,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.7898528575897217,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.598,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.742067813873291,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.596,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9180655479431152,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.5923,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.760483503341675,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.5733,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.5661356449127197,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5574,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.650604248046875,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5331,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.5134191513061523,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5116,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 2.971090316772461,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0398788452148438,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7814712524414062,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 440
|
||||
}
|
||||
],
|
||||
"logging_steps": 20,
|
||||
"max_steps": 1152,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 8.766766900681114e+16,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-450/training_args.bin
Normal file
3
checkpoint-450/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6999d99b0ec3831abd58bd6fec26bef4e74e884d0058076eed8c5f0b91586567
|
||||
size 5969
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user