初始化项目，由ModelHub XC社区提供模型
Model: Henry236/east8b-eg-lora-chunk-nilechat 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": [
|
||||
"gate_proj",
|
||||
"k_proj",
|
||||
"v_proj",
|
||||
"up_proj",
|
||||
"o_proj",
|
||||
"q_proj",
|
||||
"down_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 sha256:0384e2e4ad8025532613b260338bc9bac2742d835b96a8afadd067464b380e8f
|
||||
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",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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:afdabc906ae05aca8e3e2088f3522a76d91c9faa5533fd41f2c78303bed5cc78
|
||||
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 sha256:5cd87b71b2e0b9fc12ad10db17ddc958a4541aed139dc814f2cc717f839f7522
|
||||
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:ecf7e046b5c99f06c4c8dbb77b5d7c2bffee07cf1db92bb2492cd71d381999ee
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"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": 2.0245746786729984e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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:ad65d5535fba017b404c661ac118b43f1adf0e8807560d87e557b0da78de1893
|
||||
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 sha256:76a5c54ca1641ca2d87ca9b7f4adae94cef4c36085cfa8c88fe712c6c63c1fc8
|
||||
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 sha256:4278cc0831892e457e06f3e444bd09705f94015bac952b8f63418271ac030aae
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0990397930145264,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7828781604766846,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4994,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 3.1256909370422363,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.5023,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.1738061904907227,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4671,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.4600017070770264,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.466,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.556324005126953,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4407,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.1536033153533936,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4485,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 3.01642107963562,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4672,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 3.864258050918579,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4258,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 2.967533826828003,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3619,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.2055039405822754,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3592,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 3.8909292221069336,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.3359,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.0267176628112793,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3424,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.415727138519287,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3435,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.6791961193084717,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3391,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.3228704929351807,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.3054,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.616981267929077,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.312,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.216521739959717,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.3334,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.408073425292969,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.317,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 2.9930851459503174,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.3089,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.05021858215332,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2859,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 4.1063079833984375,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2947,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 3.8521957397460938,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.3056,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.304344415664673,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2695,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.73410701751709,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.3125,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.594968318939209,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2841,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.417556285858154,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2878,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.227901935577393,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.305,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.219496250152588,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2707,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.437847375869751,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2692,
|
||||
"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": 2.0301452468895744e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:172c58608d9fe304a8f655a720fcd5744917b538403a0cf3ca1d06f12a5c6ca0
|
||||
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:cb187972b2931ec73ca1488ef9f584402175f146b6127992e481e1f88027c97b
|
||||
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 sha256:7ac019a846822765c1550361ac4e771fa37c17cc9ec699e4a74864748ac0405f
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0990397930145264,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7828781604766846,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4994,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 3.1256909370422363,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.5023,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.1738061904907227,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4671,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.4600017070770264,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.466,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.556324005126953,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4407,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.1536033153533936,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4485,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 3.01642107963562,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4672,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 3.864258050918579,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4258,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 2.967533826828003,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3619,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.2055039405822754,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3592,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 3.8909292221069336,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.3359,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.0267176628112793,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3424,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.415727138519287,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3435,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.6791961193084717,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3391,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.3228704929351807,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.3054,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.616981267929077,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.312,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.216521739959717,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.3334,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.408073425292969,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.317,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 2.9930851459503174,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.3089,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.05021858215332,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2859,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 4.1063079833984375,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2947,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 3.8521957397460938,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.3056,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.304344415664673,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2695,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.73410701751709,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.3125,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.594968318939209,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2841,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.417556285858154,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2878,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.227901935577393,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.305,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.219496250152588,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2707,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.437847375869751,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2692,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.303681373596191,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2737,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.166017532348633,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.25,
|
||||
"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": 2.1323582680006656e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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:d96543476b08e4eb62d71b04d4f777a1d4b03192f3143c6567a7adb72f25ffc1
|
||||
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:deb9414c47cfbc2fe7ed123d34ff7f059e77b2857280fa737ce639978485d964
|
||||
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 sha256:4cf163052b7c8fe1a57ad4f4852615ab8eee4f151df31b7e92c5ee06a95da6b1
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0990397930145264,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7828781604766846,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4994,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 3.1256909370422363,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.5023,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.1738061904907227,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4671,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.4600017070770264,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.466,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.556324005126953,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4407,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.1536033153533936,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4485,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 3.01642107963562,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4672,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 3.864258050918579,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4258,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 2.967533826828003,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3619,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.2055039405822754,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3592,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 3.8909292221069336,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.3359,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.0267176628112793,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3424,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.415727138519287,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3435,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.6791961193084717,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3391,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.3228704929351807,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.3054,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.616981267929077,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.312,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.216521739959717,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.3334,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.408073425292969,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.317,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 2.9930851459503174,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.3089,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.05021858215332,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2859,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 4.1063079833984375,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2947,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 3.8521957397460938,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.3056,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.304344415664673,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2695,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.73410701751709,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.3125,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.594968318939209,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2841,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.417556285858154,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2878,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.227901935577393,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.305,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.219496250152588,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2707,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.437847375869751,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2692,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.303681373596191,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2737,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.166017532348633,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.25,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.8402777777777777,
|
||||
"grad_norm": 3.7296154499053955,
|
||||
"learning_rate": 1.975176196540185e-07,
|
||||
"loss": 1.2739,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.875,
|
||||
"grad_norm": 4.139808654785156,
|
||||
"learning_rate": 1.2200896627521718e-07,
|
||||
"loss": 1.2893,
|
||||
"step": 1080
|
||||
},
|
||||
{
|
||||
"epoch": 1.9097222222222223,
|
||||
"grad_norm": 3.9217822551727295,
|
||||
"learning_rate": 6.443724232808146e-08,
|
||||
"loss": 1.2558,
|
||||
"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": 2.2324590769648435e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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:b501920d99dbb3c3c3213b877fbd5e3b3b8b16e293eaefb6fc97680bb459594a
|
||||
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 sha256:9f06270876bb57ae9f47380bdbf8dac3269554a8df8d073214f1b5d49afea4eb
|
||||
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 sha256:343714913f998eccbc8cb136e02926cb492b399a62fe6e8d95391c5456fde9fd
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0990397930145264,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7828781604766846,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4994,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.7986111111111112,
|
||||
"grad_norm": 3.1256909370422363,
|
||||
"learning_rate": 7.530575666193283e-06,
|
||||
"loss": 1.5023,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 3.1738061904907227,
|
||||
"learning_rate": 7.26454700860997e-06,
|
||||
"loss": 1.4671,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.8680555555555556,
|
||||
"grad_norm": 3.4600017070770264,
|
||||
"learning_rate": 6.990191353373876e-06,
|
||||
"loss": 1.466,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9027777777777778,
|
||||
"grad_norm": 3.556324005126953,
|
||||
"learning_rate": 6.708517537523264e-06,
|
||||
"loss": 1.4407,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9375,
|
||||
"grad_norm": 3.1536033153533936,
|
||||
"learning_rate": 6.420561307807713e-06,
|
||||
"loss": 1.4485,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.9722222222222222,
|
||||
"grad_norm": 3.01642107963562,
|
||||
"learning_rate": 6.12738151212918e-06,
|
||||
"loss": 1.4672,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0069444444444444,
|
||||
"grad_norm": 3.864258050918579,
|
||||
"learning_rate": 5.830056206037482e-06,
|
||||
"loss": 1.4258,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 2.967533826828003,
|
||||
"learning_rate": 5.529678688597081e-06,
|
||||
"loss": 1.3619,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.0763888888888888,
|
||||
"grad_norm": 3.2055039405822754,
|
||||
"learning_rate": 5.2273534822017105e-06,
|
||||
"loss": 1.3592,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1111111111111112,
|
||||
"grad_norm": 3.8909292221069336,
|
||||
"learning_rate": 4.924192271119554e-06,
|
||||
"loss": 1.3359,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.1458333333333333,
|
||||
"grad_norm": 3.0267176628112793,
|
||||
"learning_rate": 4.621309813703385e-06,
|
||||
"loss": 1.3424,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.1805555555555556,
|
||||
"grad_norm": 4.415727138519287,
|
||||
"learning_rate": 4.319819843296952e-06,
|
||||
"loss": 1.3435,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2152777777777777,
|
||||
"grad_norm": 3.6791961193084717,
|
||||
"learning_rate": 4.020830972910433e-06,
|
||||
"loss": 1.3391,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 3.3228704929351807,
|
||||
"learning_rate": 3.7254426187239567e-06,
|
||||
"loss": 1.3054,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.2847222222222223,
|
||||
"grad_norm": 3.616981267929077,
|
||||
"learning_rate": 3.4347409574088896e-06,
|
||||
"loss": 1.312,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.3194444444444444,
|
||||
"grad_norm": 4.216521739959717,
|
||||
"learning_rate": 3.149794932132331e-06,
|
||||
"loss": 1.3334,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.3541666666666667,
|
||||
"grad_norm": 4.408073425292969,
|
||||
"learning_rate": 2.871652321931161e-06,
|
||||
"loss": 1.317,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.3888888888888888,
|
||||
"grad_norm": 2.9930851459503174,
|
||||
"learning_rate": 2.601335888909005e-06,
|
||||
"loss": 1.3089,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.4236111111111112,
|
||||
"grad_norm": 4.05021858215332,
|
||||
"learning_rate": 2.339839617423318e-06,
|
||||
"loss": 1.2859,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 4.1063079833984375,
|
||||
"learning_rate": 2.0881250590915316e-06,
|
||||
"loss": 1.2947,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.4930555555555556,
|
||||
"grad_norm": 3.8521957397460938,
|
||||
"learning_rate": 1.8471177970560712e-06,
|
||||
"loss": 1.3056,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.5277777777777777,
|
||||
"grad_norm": 3.304344415664673,
|
||||
"learning_rate": 1.6177040425095664e-06,
|
||||
"loss": 1.2695,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.5625,
|
||||
"grad_norm": 3.73410701751709,
|
||||
"learning_rate": 1.40072737599522e-06,
|
||||
"loss": 1.3125,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.5972222222222223,
|
||||
"grad_norm": 3.594968318939209,
|
||||
"learning_rate": 1.196985645464921e-06,
|
||||
"loss": 1.2841,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.6319444444444444,
|
||||
"grad_norm": 4.417556285858154,
|
||||
"learning_rate": 1.0072280325013185e-06,
|
||||
"loss": 1.2878,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 4.227901935577393,
|
||||
"learning_rate": 8.321522974916968e-07,
|
||||
"loss": 1.305,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7013888888888888,
|
||||
"grad_norm": 4.219496250152588,
|
||||
"learning_rate": 6.724022138834341e-07,
|
||||
"loss": 1.2707,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.7361111111111112,
|
||||
"grad_norm": 3.437847375869751,
|
||||
"learning_rate": 5.285652009556075e-07,
|
||||
"loss": 1.2692,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.7708333333333335,
|
||||
"grad_norm": 4.303681373596191,
|
||||
"learning_rate": 4.0117016381130636e-07,
|
||||
"loss": 1.2737,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.8055555555555556,
|
||||
"grad_norm": 4.166017532348633,
|
||||
"learning_rate": 2.906855485332305e-07,
|
||||
"loss": 1.25,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.8402777777777777,
|
||||
"grad_norm": 3.7296154499053955,
|
||||
"learning_rate": 1.975176196540185e-07,
|
||||
"loss": 1.2739,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.875,
|
||||
"grad_norm": 4.139808654785156,
|
||||
"learning_rate": 1.2200896627521718e-07,
|
||||
"loss": 1.2893,
|
||||
"step": 1080
|
||||
},
|
||||
{
|
||||
"epoch": 1.9097222222222223,
|
||||
"grad_norm": 3.9217822551727295,
|
||||
"learning_rate": 6.443724232808146e-08,
|
||||
"loss": 1.2558,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 1.9444444444444444,
|
||||
"grad_norm": 4.743123531341553,
|
||||
"learning_rate": 2.501414560839577e-08,
|
||||
"loss": 1.2425,
|
||||
"step": 1120
|
||||
},
|
||||
{
|
||||
"epoch": 1.9791666666666665,
|
||||
"grad_norm": 3.773953914642334,
|
||||
"learning_rate": 3.884639339534202e-09,
|
||||
"loss": 1.2672,
|
||||
"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": 2.3346113282408448e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:0897df63f0df2caecc3c70b588e92ed35cfd0114e6e27d62d2c126936863129e
|
||||
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:e5ad50bc7713cbc192692422748d9524ea675db4b68cf4758b16767939bd18f7
|
||||
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 sha256:10f31c644c2d511c761b5bd2c8684f0f912aec2103790ef57a54a08b8f096fa0
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"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": 3.036042545990861e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:7abfa66030147aa0fe79d035104fbe78832cf964244fecea8245c35f4cfdf3d2
|
||||
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 sha256:3f307072335a43afcf42af433cb09d7bdefd880ffa1b6480338223448cd059fe
|
||||
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 sha256:3151996a186da03e4c8625aa7f0249a788b27e975e6bf0cb629deb9cb88ba461
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"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": 4.06966378046423e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:731536ffeb885f97904c273b371cac6b2eddc2b051d048c19ddd8f5e06fcd83f
|
||||
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 sha256:1de18f1098206d304c2e9e07f4927ca3994559c65c01bd8ec9e0f979201001ed
|
||||
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:c031523b0980faf8edd373e82ee5dc3f8288a80c8a568acac8e6cf4d092b86e5
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"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": 5.081978742453043e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:9bb7e452e1d676bb7d4e209dfdc28b554fad740e42fda13ff78e86b0ab4f3d39
|
||||
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 sha256:6621085fe286d89148020abc3913d26baf56b155272592de852923e37b9f4347
|
||||
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 sha256:90bc2fe4ee96d58ba6b266dc96e2302937c506f638eecc5aededcda6fd229ff7
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"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": 6.083391964328755e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:2b0bd364dec64af366ebb1c36f9b8cf13de195a029dd763e459716cd8b8c94df
|
||||
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:b5278ab79115164e58644b6a50ffc9a940b1bae987a55b0087e935b16180813b
|
||||
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:cb35f8c0b6073305f53c45f10e720934126c019098b502ffb71b91fc13c32f56
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"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": 7.084179072752026e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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:fb52e3e2982303126409f001c7437a14712867a443f87896af5866999b093751
|
||||
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 sha256:4193bb650e5fc9c7a8f7834df6905ab330fb597ea2e4bce38d682ad395ad6fe1
|
||||
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 sha256:235eea77d85f83e0e1c97f22edbdf217f18c45fd382d67f20ee2ee2b43a0b34b
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"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": 8.095260222937498e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
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": [
|
||||
"q_proj",
|
||||
"k_proj",
|
||||
"up_proj",
|
||||
"down_proj",
|
||||
"v_proj",
|
||||
"o_proj",
|
||||
"gate_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 sha256:4fc2e97d1ddd03239f34b06abba0028f4348595595a71981c1d0a87c4832b1ca
|
||||
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:e9293a378e805d2e1f137e91cdaafcfbc26a1f1cf34e72ba46c0f24bc8d0b058
|
||||
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 sha256:3c1f2cfdb5f12710a509fd8ba1350dff75febd348c1956e80478d900d68c2fc3
|
||||
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": 3.1068832874298096,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 2.675,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06944444444444445,
|
||||
"grad_norm": 2.46288800239563,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 2.4759,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10416666666666667,
|
||||
"grad_norm": 2.1140520572662354,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 2.3011,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.1388888888888889,
|
||||
"grad_norm": 1.9008077383041382,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 2.0724,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.1736111111111111,
|
||||
"grad_norm": 2.368029832839966,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.9312,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 2.3201775550842285,
|
||||
"learning_rate": 9.999793100349294e-06,
|
||||
"loss": 1.8941,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24305555555555555,
|
||||
"grad_norm": 2.499159812927246,
|
||||
"learning_rate": 9.987843743451796e-06,
|
||||
"loss": 1.7747,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2777777777777778,
|
||||
"grad_norm": 2.1269280910491943,
|
||||
"learning_rate": 9.957553516178782e-06,
|
||||
"loss": 1.7052,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3125,
|
||||
"grad_norm": 2.290123224258423,
|
||||
"learning_rate": 9.909033799150947e-06,
|
||||
"loss": 1.7429,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3472222222222222,
|
||||
"grad_norm": 2.3117945194244385,
|
||||
"learning_rate": 9.842463004902127e-06,
|
||||
"loss": 1.6598,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.3819444444444444,
|
||||
"grad_norm": 2.6141538619995117,
|
||||
"learning_rate": 9.758085921836076e-06,
|
||||
"loss": 1.6429,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 2.4996819496154785,
|
||||
"learning_rate": 9.656212814111567e-06,
|
||||
"loss": 1.6566,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.4513888888888889,
|
||||
"grad_norm": 2.8781185150146484,
|
||||
"learning_rate": 9.53721828076571e-06,
|
||||
"loss": 1.6255,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.4861111111111111,
|
||||
"grad_norm": 2.8994524478912354,
|
||||
"learning_rate": 9.401539878270545e-06,
|
||||
"loss": 1.6064,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5208333333333334,
|
||||
"grad_norm": 2.9606640338897705,
|
||||
"learning_rate": 9.249676511588e-06,
|
||||
"loss": 1.6141,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.5555555555555556,
|
||||
"grad_norm": 2.9091055393218994,
|
||||
"learning_rate": 9.082186599639429e-06,
|
||||
"loss": 1.598,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.5902777777777778,
|
||||
"grad_norm": 2.523542642593384,
|
||||
"learning_rate": 8.899686021935554e-06,
|
||||
"loss": 1.5779,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 2.5727219581604004,
|
||||
"learning_rate": 8.702845853917242e-06,
|
||||
"loss": 1.5475,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.6597222222222222,
|
||||
"grad_norm": 2.4910247325897217,
|
||||
"learning_rate": 8.492389899334572e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.6944444444444444,
|
||||
"grad_norm": 3.080043077468872,
|
||||
"learning_rate": 8.269092028737885e-06,
|
||||
"loss": 1.5282,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7291666666666666,
|
||||
"grad_norm": 3.0990397930145264,
|
||||
"learning_rate": 8.033773333867498e-06,
|
||||
"loss": 1.4993,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7638888888888888,
|
||||
"grad_norm": 2.7828781604766846,
|
||||
"learning_rate": 7.78729910840572e-06,
|
||||
"loss": 1.4994,
|
||||
"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": 9.108551185308058e+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 sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f
|
||||
size 6033
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user