初始化项目，由ModelHub XC社区提供模型
Model: Henry236/east8b-eg-lora-chunk-llama 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": [
|
||||||
|
"o_proj",
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_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:a4e750594165491d27182ef42fe92c6feb72b82c04069cca03dd2d8f04a2606e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:123b1534a1743c6cfba2e9a8142901a711d0438b182ad3e74b47b234dbcaebf0
|
||||||
|
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 sha256:19f0e34a3a0fe94c765086a33d66c020b1ee58ca3508cb85c0022a33e361d69f
|
||||||
|
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 sha256:69cd0e551b2edc97dee6a11534d4c0ef4f3d7dac904bff9b22dc1ed9a1012d40
|
||||||
|
size 14645
|
||||||
3
checkpoint-100/scheduler.pt
Normal file
3
checkpoint-100/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3a965538a990c1bee6cafb2ee94e4c27c3d42d8dd819e2e80a5cad5750681c87
|
||||||
|
size 1465
|
||||||
69
checkpoint-100/trainer_state.json
Normal file
69
checkpoint-100/trainer_state.json
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 100,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"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": 2.005165161647309e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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:e0ecc93e71d3befd64a899e4d2a96a45602154e6d4126bb4c4dd69cf340046e0
|
||||||
|
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 sha256:9056d42facfaaa295b68f3776c3e00fb50c6c88ba6ecbdfc3a51f07f14e8240a
|
||||||
|
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 sha256:1791c0a7260af6628debd3dc2e8cca9005a37f7e4dd60fa56d2547eaaab30b09
|
||||||
|
size 14645
|
||||||
3
checkpoint-1000/scheduler.pt
Normal file
3
checkpoint-1000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3faa60702eeec70c307ffab2e710a51a22e86b2f89bbb3effe498e101641bee8
|
||||||
|
size 1465
|
||||||
384
checkpoint-1000/trainer_state.json
Normal file
384
checkpoint-1000/trainer_state.json
Normal file
@@ -0,0 +1,384 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.7361111111111112,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1000,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7291666666666666,
|
||||||
|
"grad_norm": 2.882279872894287,
|
||||||
|
"learning_rate": 8.033773333867498e-06,
|
||||||
|
"loss": 1.5109,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7638888888888888,
|
||||||
|
"grad_norm": 2.6647043228149414,
|
||||||
|
"learning_rate": 7.78729910840572e-06,
|
||||||
|
"loss": 1.5076,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7986111111111112,
|
||||||
|
"grad_norm": 3.2523193359375,
|
||||||
|
"learning_rate": 7.530575666193283e-06,
|
||||||
|
"loss": 1.5043,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8333333333333334,
|
||||||
|
"grad_norm": 3.349648952484131,
|
||||||
|
"learning_rate": 7.26454700860997e-06,
|
||||||
|
"loss": 1.4809,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8680555555555556,
|
||||||
|
"grad_norm": 3.5382089614868164,
|
||||||
|
"learning_rate": 6.990191353373876e-06,
|
||||||
|
"loss": 1.4808,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9027777777777778,
|
||||||
|
"grad_norm": 3.7552590370178223,
|
||||||
|
"learning_rate": 6.708517537523264e-06,
|
||||||
|
"loss": 1.4482,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9375,
|
||||||
|
"grad_norm": 3.215052366256714,
|
||||||
|
"learning_rate": 6.420561307807713e-06,
|
||||||
|
"loss": 1.4627,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9722222222222222,
|
||||||
|
"grad_norm": 3.1179182529449463,
|
||||||
|
"learning_rate": 6.12738151212918e-06,
|
||||||
|
"loss": 1.4731,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0069444444444444,
|
||||||
|
"grad_norm": 3.928844451904297,
|
||||||
|
"learning_rate": 5.830056206037482e-06,
|
||||||
|
"loss": 1.4354,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0416666666666667,
|
||||||
|
"grad_norm": 3.2214365005493164,
|
||||||
|
"learning_rate": 5.529678688597081e-06,
|
||||||
|
"loss": 1.3671,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0763888888888888,
|
||||||
|
"grad_norm": 3.3545398712158203,
|
||||||
|
"learning_rate": 5.2273534822017105e-06,
|
||||||
|
"loss": 1.373,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1111111111111112,
|
||||||
|
"grad_norm": 4.0173234939575195,
|
||||||
|
"learning_rate": 4.924192271119554e-06,
|
||||||
|
"loss": 1.3456,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1458333333333333,
|
||||||
|
"grad_norm": 3.150284767150879,
|
||||||
|
"learning_rate": 4.621309813703385e-06,
|
||||||
|
"loss": 1.3462,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1805555555555556,
|
||||||
|
"grad_norm": 4.555105209350586,
|
||||||
|
"learning_rate": 4.319819843296952e-06,
|
||||||
|
"loss": 1.3409,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2152777777777777,
|
||||||
|
"grad_norm": 3.7820332050323486,
|
||||||
|
"learning_rate": 4.020830972910433e-06,
|
||||||
|
"loss": 1.3522,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.25,
|
||||||
|
"grad_norm": 3.446506977081299,
|
||||||
|
"learning_rate": 3.7254426187239567e-06,
|
||||||
|
"loss": 1.3083,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2847222222222223,
|
||||||
|
"grad_norm": 3.7315480709075928,
|
||||||
|
"learning_rate": 3.4347409574088896e-06,
|
||||||
|
"loss": 1.3234,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3194444444444444,
|
||||||
|
"grad_norm": 4.601447105407715,
|
||||||
|
"learning_rate": 3.149794932132331e-06,
|
||||||
|
"loss": 1.3384,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3541666666666667,
|
||||||
|
"grad_norm": 4.626559257507324,
|
||||||
|
"learning_rate": 2.871652321931161e-06,
|
||||||
|
"loss": 1.3196,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3888888888888888,
|
||||||
|
"grad_norm": 3.092618227005005,
|
||||||
|
"learning_rate": 2.601335888909005e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4236111111111112,
|
||||||
|
"grad_norm": 4.193453788757324,
|
||||||
|
"learning_rate": 2.339839617423318e-06,
|
||||||
|
"loss": 1.2816,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4583333333333333,
|
||||||
|
"grad_norm": 3.9958441257476807,
|
||||||
|
"learning_rate": 2.0881250590915316e-06,
|
||||||
|
"loss": 1.2989,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4930555555555556,
|
||||||
|
"grad_norm": 4.101428985595703,
|
||||||
|
"learning_rate": 1.8471177970560712e-06,
|
||||||
|
"loss": 1.3146,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5277777777777777,
|
||||||
|
"grad_norm": 3.387007236480713,
|
||||||
|
"learning_rate": 1.6177040425095664e-06,
|
||||||
|
"loss": 1.2792,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5625,
|
||||||
|
"grad_norm": 3.733682870864868,
|
||||||
|
"learning_rate": 1.40072737599522e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5972222222222223,
|
||||||
|
"grad_norm": 3.3572065830230713,
|
||||||
|
"learning_rate": 1.196985645464921e-06,
|
||||||
|
"loss": 1.2915,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6319444444444444,
|
||||||
|
"grad_norm": 4.337113380432129,
|
||||||
|
"learning_rate": 1.0072280325013185e-06,
|
||||||
|
"loss": 1.2886,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6666666666666665,
|
||||||
|
"grad_norm": 4.326784133911133,
|
||||||
|
"learning_rate": 8.321522974916968e-07,
|
||||||
|
"loss": 1.3046,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7013888888888888,
|
||||||
|
"grad_norm": 4.501497268676758,
|
||||||
|
"learning_rate": 6.724022138834341e-07,
|
||||||
|
"loss": 1.2783,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7361111111111112,
|
||||||
|
"grad_norm": 3.4914722442626953,
|
||||||
|
"learning_rate": 5.285652009556075e-07,
|
||||||
|
"loss": 1.2741,
|
||||||
|
"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": 2.0074265361167155e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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:b72e4770bcb62b1500b4e600d15dfd0c75defd43873fbbe0e2b245280ca20658
|
||||||
|
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 sha256:22005337ca7d831ed1afd530372835005fdf71403f0fd1550ad00d340eeaa2b9
|
||||||
|
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:a46b22b3cc4f199582996cf55c7028978107dc1fe818085d1d1a4d270aa9497c
|
||||||
|
size 14645
|
||||||
3
checkpoint-1050/scheduler.pt
Normal file
3
checkpoint-1050/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:abe9abb5efc489b294c297766a8ae2c71262b2cf1b3df1555b36fda19a8e7406
|
||||||
|
size 1465
|
||||||
398
checkpoint-1050/trainer_state.json
Normal file
398
checkpoint-1050/trainer_state.json
Normal file
@@ -0,0 +1,398 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.8229166666666665,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1050,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7291666666666666,
|
||||||
|
"grad_norm": 2.882279872894287,
|
||||||
|
"learning_rate": 8.033773333867498e-06,
|
||||||
|
"loss": 1.5109,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7638888888888888,
|
||||||
|
"grad_norm": 2.6647043228149414,
|
||||||
|
"learning_rate": 7.78729910840572e-06,
|
||||||
|
"loss": 1.5076,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7986111111111112,
|
||||||
|
"grad_norm": 3.2523193359375,
|
||||||
|
"learning_rate": 7.530575666193283e-06,
|
||||||
|
"loss": 1.5043,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8333333333333334,
|
||||||
|
"grad_norm": 3.349648952484131,
|
||||||
|
"learning_rate": 7.26454700860997e-06,
|
||||||
|
"loss": 1.4809,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8680555555555556,
|
||||||
|
"grad_norm": 3.5382089614868164,
|
||||||
|
"learning_rate": 6.990191353373876e-06,
|
||||||
|
"loss": 1.4808,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9027777777777778,
|
||||||
|
"grad_norm": 3.7552590370178223,
|
||||||
|
"learning_rate": 6.708517537523264e-06,
|
||||||
|
"loss": 1.4482,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9375,
|
||||||
|
"grad_norm": 3.215052366256714,
|
||||||
|
"learning_rate": 6.420561307807713e-06,
|
||||||
|
"loss": 1.4627,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9722222222222222,
|
||||||
|
"grad_norm": 3.1179182529449463,
|
||||||
|
"learning_rate": 6.12738151212918e-06,
|
||||||
|
"loss": 1.4731,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0069444444444444,
|
||||||
|
"grad_norm": 3.928844451904297,
|
||||||
|
"learning_rate": 5.830056206037482e-06,
|
||||||
|
"loss": 1.4354,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0416666666666667,
|
||||||
|
"grad_norm": 3.2214365005493164,
|
||||||
|
"learning_rate": 5.529678688597081e-06,
|
||||||
|
"loss": 1.3671,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0763888888888888,
|
||||||
|
"grad_norm": 3.3545398712158203,
|
||||||
|
"learning_rate": 5.2273534822017105e-06,
|
||||||
|
"loss": 1.373,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1111111111111112,
|
||||||
|
"grad_norm": 4.0173234939575195,
|
||||||
|
"learning_rate": 4.924192271119554e-06,
|
||||||
|
"loss": 1.3456,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1458333333333333,
|
||||||
|
"grad_norm": 3.150284767150879,
|
||||||
|
"learning_rate": 4.621309813703385e-06,
|
||||||
|
"loss": 1.3462,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1805555555555556,
|
||||||
|
"grad_norm": 4.555105209350586,
|
||||||
|
"learning_rate": 4.319819843296952e-06,
|
||||||
|
"loss": 1.3409,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2152777777777777,
|
||||||
|
"grad_norm": 3.7820332050323486,
|
||||||
|
"learning_rate": 4.020830972910433e-06,
|
||||||
|
"loss": 1.3522,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.25,
|
||||||
|
"grad_norm": 3.446506977081299,
|
||||||
|
"learning_rate": 3.7254426187239567e-06,
|
||||||
|
"loss": 1.3083,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2847222222222223,
|
||||||
|
"grad_norm": 3.7315480709075928,
|
||||||
|
"learning_rate": 3.4347409574088896e-06,
|
||||||
|
"loss": 1.3234,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3194444444444444,
|
||||||
|
"grad_norm": 4.601447105407715,
|
||||||
|
"learning_rate": 3.149794932132331e-06,
|
||||||
|
"loss": 1.3384,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3541666666666667,
|
||||||
|
"grad_norm": 4.626559257507324,
|
||||||
|
"learning_rate": 2.871652321931161e-06,
|
||||||
|
"loss": 1.3196,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3888888888888888,
|
||||||
|
"grad_norm": 3.092618227005005,
|
||||||
|
"learning_rate": 2.601335888909005e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4236111111111112,
|
||||||
|
"grad_norm": 4.193453788757324,
|
||||||
|
"learning_rate": 2.339839617423318e-06,
|
||||||
|
"loss": 1.2816,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4583333333333333,
|
||||||
|
"grad_norm": 3.9958441257476807,
|
||||||
|
"learning_rate": 2.0881250590915316e-06,
|
||||||
|
"loss": 1.2989,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4930555555555556,
|
||||||
|
"grad_norm": 4.101428985595703,
|
||||||
|
"learning_rate": 1.8471177970560712e-06,
|
||||||
|
"loss": 1.3146,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5277777777777777,
|
||||||
|
"grad_norm": 3.387007236480713,
|
||||||
|
"learning_rate": 1.6177040425095664e-06,
|
||||||
|
"loss": 1.2792,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5625,
|
||||||
|
"grad_norm": 3.733682870864868,
|
||||||
|
"learning_rate": 1.40072737599522e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5972222222222223,
|
||||||
|
"grad_norm": 3.3572065830230713,
|
||||||
|
"learning_rate": 1.196985645464921e-06,
|
||||||
|
"loss": 1.2915,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6319444444444444,
|
||||||
|
"grad_norm": 4.337113380432129,
|
||||||
|
"learning_rate": 1.0072280325013185e-06,
|
||||||
|
"loss": 1.2886,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6666666666666665,
|
||||||
|
"grad_norm": 4.326784133911133,
|
||||||
|
"learning_rate": 8.321522974916968e-07,
|
||||||
|
"loss": 1.3046,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7013888888888888,
|
||||||
|
"grad_norm": 4.501497268676758,
|
||||||
|
"learning_rate": 6.724022138834341e-07,
|
||||||
|
"loss": 1.2783,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7361111111111112,
|
||||||
|
"grad_norm": 3.4914722442626953,
|
||||||
|
"learning_rate": 5.285652009556075e-07,
|
||||||
|
"loss": 1.2741,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7708333333333335,
|
||||||
|
"grad_norm": 4.376003742218018,
|
||||||
|
"learning_rate": 4.0117016381130636e-07,
|
||||||
|
"loss": 1.279,
|
||||||
|
"step": 1020
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8055555555555556,
|
||||||
|
"grad_norm": 4.257233619689941,
|
||||||
|
"learning_rate": 2.906855485332305e-07,
|
||||||
|
"loss": 1.2538,
|
||||||
|
"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": 2.108497820932178e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:99d00ecced49bde0a2bc956224cafe3b32a4899c97e5e53d3de21e3cede3845d
|
||||||
|
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 sha256:732ac338f3cf07142696f711badfef134977bcb3ead829ebc4eb22db2cf4149f
|
||||||
|
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 sha256:2f166523cfe0c7568950a7a790ad35225be87259a4e0fa195ec2741ec0bd84d5
|
||||||
|
size 14645
|
||||||
3
checkpoint-1100/scheduler.pt
Normal file
3
checkpoint-1100/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:315c6a6de3128d29cfc459c9f1551c37f38030611e281b0aa330fe139ba0892f
|
||||||
|
size 1465
|
||||||
419
checkpoint-1100/trainer_state.json
Normal file
419
checkpoint-1100/trainer_state.json
Normal file
@@ -0,0 +1,419 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.9097222222222223,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1100,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7291666666666666,
|
||||||
|
"grad_norm": 2.882279872894287,
|
||||||
|
"learning_rate": 8.033773333867498e-06,
|
||||||
|
"loss": 1.5109,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7638888888888888,
|
||||||
|
"grad_norm": 2.6647043228149414,
|
||||||
|
"learning_rate": 7.78729910840572e-06,
|
||||||
|
"loss": 1.5076,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7986111111111112,
|
||||||
|
"grad_norm": 3.2523193359375,
|
||||||
|
"learning_rate": 7.530575666193283e-06,
|
||||||
|
"loss": 1.5043,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8333333333333334,
|
||||||
|
"grad_norm": 3.349648952484131,
|
||||||
|
"learning_rate": 7.26454700860997e-06,
|
||||||
|
"loss": 1.4809,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8680555555555556,
|
||||||
|
"grad_norm": 3.5382089614868164,
|
||||||
|
"learning_rate": 6.990191353373876e-06,
|
||||||
|
"loss": 1.4808,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9027777777777778,
|
||||||
|
"grad_norm": 3.7552590370178223,
|
||||||
|
"learning_rate": 6.708517537523264e-06,
|
||||||
|
"loss": 1.4482,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9375,
|
||||||
|
"grad_norm": 3.215052366256714,
|
||||||
|
"learning_rate": 6.420561307807713e-06,
|
||||||
|
"loss": 1.4627,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9722222222222222,
|
||||||
|
"grad_norm": 3.1179182529449463,
|
||||||
|
"learning_rate": 6.12738151212918e-06,
|
||||||
|
"loss": 1.4731,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0069444444444444,
|
||||||
|
"grad_norm": 3.928844451904297,
|
||||||
|
"learning_rate": 5.830056206037482e-06,
|
||||||
|
"loss": 1.4354,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0416666666666667,
|
||||||
|
"grad_norm": 3.2214365005493164,
|
||||||
|
"learning_rate": 5.529678688597081e-06,
|
||||||
|
"loss": 1.3671,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0763888888888888,
|
||||||
|
"grad_norm": 3.3545398712158203,
|
||||||
|
"learning_rate": 5.2273534822017105e-06,
|
||||||
|
"loss": 1.373,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1111111111111112,
|
||||||
|
"grad_norm": 4.0173234939575195,
|
||||||
|
"learning_rate": 4.924192271119554e-06,
|
||||||
|
"loss": 1.3456,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1458333333333333,
|
||||||
|
"grad_norm": 3.150284767150879,
|
||||||
|
"learning_rate": 4.621309813703385e-06,
|
||||||
|
"loss": 1.3462,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1805555555555556,
|
||||||
|
"grad_norm": 4.555105209350586,
|
||||||
|
"learning_rate": 4.319819843296952e-06,
|
||||||
|
"loss": 1.3409,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2152777777777777,
|
||||||
|
"grad_norm": 3.7820332050323486,
|
||||||
|
"learning_rate": 4.020830972910433e-06,
|
||||||
|
"loss": 1.3522,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.25,
|
||||||
|
"grad_norm": 3.446506977081299,
|
||||||
|
"learning_rate": 3.7254426187239567e-06,
|
||||||
|
"loss": 1.3083,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2847222222222223,
|
||||||
|
"grad_norm": 3.7315480709075928,
|
||||||
|
"learning_rate": 3.4347409574088896e-06,
|
||||||
|
"loss": 1.3234,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3194444444444444,
|
||||||
|
"grad_norm": 4.601447105407715,
|
||||||
|
"learning_rate": 3.149794932132331e-06,
|
||||||
|
"loss": 1.3384,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3541666666666667,
|
||||||
|
"grad_norm": 4.626559257507324,
|
||||||
|
"learning_rate": 2.871652321931161e-06,
|
||||||
|
"loss": 1.3196,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3888888888888888,
|
||||||
|
"grad_norm": 3.092618227005005,
|
||||||
|
"learning_rate": 2.601335888909005e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4236111111111112,
|
||||||
|
"grad_norm": 4.193453788757324,
|
||||||
|
"learning_rate": 2.339839617423318e-06,
|
||||||
|
"loss": 1.2816,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4583333333333333,
|
||||||
|
"grad_norm": 3.9958441257476807,
|
||||||
|
"learning_rate": 2.0881250590915316e-06,
|
||||||
|
"loss": 1.2989,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4930555555555556,
|
||||||
|
"grad_norm": 4.101428985595703,
|
||||||
|
"learning_rate": 1.8471177970560712e-06,
|
||||||
|
"loss": 1.3146,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5277777777777777,
|
||||||
|
"grad_norm": 3.387007236480713,
|
||||||
|
"learning_rate": 1.6177040425095664e-06,
|
||||||
|
"loss": 1.2792,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5625,
|
||||||
|
"grad_norm": 3.733682870864868,
|
||||||
|
"learning_rate": 1.40072737599522e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5972222222222223,
|
||||||
|
"grad_norm": 3.3572065830230713,
|
||||||
|
"learning_rate": 1.196985645464921e-06,
|
||||||
|
"loss": 1.2915,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6319444444444444,
|
||||||
|
"grad_norm": 4.337113380432129,
|
||||||
|
"learning_rate": 1.0072280325013185e-06,
|
||||||
|
"loss": 1.2886,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6666666666666665,
|
||||||
|
"grad_norm": 4.326784133911133,
|
||||||
|
"learning_rate": 8.321522974916968e-07,
|
||||||
|
"loss": 1.3046,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7013888888888888,
|
||||||
|
"grad_norm": 4.501497268676758,
|
||||||
|
"learning_rate": 6.724022138834341e-07,
|
||||||
|
"loss": 1.2783,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7361111111111112,
|
||||||
|
"grad_norm": 3.4914722442626953,
|
||||||
|
"learning_rate": 5.285652009556075e-07,
|
||||||
|
"loss": 1.2741,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7708333333333335,
|
||||||
|
"grad_norm": 4.376003742218018,
|
||||||
|
"learning_rate": 4.0117016381130636e-07,
|
||||||
|
"loss": 1.279,
|
||||||
|
"step": 1020
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8055555555555556,
|
||||||
|
"grad_norm": 4.257233619689941,
|
||||||
|
"learning_rate": 2.906855485332305e-07,
|
||||||
|
"loss": 1.2538,
|
||||||
|
"step": 1040
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8402777777777777,
|
||||||
|
"grad_norm": 3.9241201877593994,
|
||||||
|
"learning_rate": 1.975176196540185e-07,
|
||||||
|
"loss": 1.2794,
|
||||||
|
"step": 1060
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.875,
|
||||||
|
"grad_norm": 4.226406574249268,
|
||||||
|
"learning_rate": 1.2200896627521718e-07,
|
||||||
|
"loss": 1.2932,
|
||||||
|
"step": 1080
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9097222222222223,
|
||||||
|
"grad_norm": 4.021918296813965,
|
||||||
|
"learning_rate": 6.443724232808146e-08,
|
||||||
|
"loss": 1.262,
|
||||||
|
"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": 2.2074900407835034e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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:b6e649d23c4df73746357a23b10428d6cd25bb42f6331251485b5a595c245680
|
||||||
|
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 sha256:8d24b2c893e57c0ff70e5450184bd4e2a2aee749a97287c8f30d0f551caf070f
|
||||||
|
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 sha256:6f20cad884897e9c557b848e15a51b18e6c8489fcb5600739b7d98d6c460a17e
|
||||||
|
size 14645
|
||||||
3
checkpoint-1150/scheduler.pt
Normal file
3
checkpoint-1150/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:28b81089eb143a676da720978f118caf9eee0a372736c9ef6f38cdec3dd8d997
|
||||||
|
size 1465
|
||||||
433
checkpoint-1150/trainer_state.json
Normal file
433
checkpoint-1150/trainer_state.json
Normal file
@@ -0,0 +1,433 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.9965277777777777,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1150,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7291666666666666,
|
||||||
|
"grad_norm": 2.882279872894287,
|
||||||
|
"learning_rate": 8.033773333867498e-06,
|
||||||
|
"loss": 1.5109,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7638888888888888,
|
||||||
|
"grad_norm": 2.6647043228149414,
|
||||||
|
"learning_rate": 7.78729910840572e-06,
|
||||||
|
"loss": 1.5076,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7986111111111112,
|
||||||
|
"grad_norm": 3.2523193359375,
|
||||||
|
"learning_rate": 7.530575666193283e-06,
|
||||||
|
"loss": 1.5043,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8333333333333334,
|
||||||
|
"grad_norm": 3.349648952484131,
|
||||||
|
"learning_rate": 7.26454700860997e-06,
|
||||||
|
"loss": 1.4809,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8680555555555556,
|
||||||
|
"grad_norm": 3.5382089614868164,
|
||||||
|
"learning_rate": 6.990191353373876e-06,
|
||||||
|
"loss": 1.4808,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9027777777777778,
|
||||||
|
"grad_norm": 3.7552590370178223,
|
||||||
|
"learning_rate": 6.708517537523264e-06,
|
||||||
|
"loss": 1.4482,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9375,
|
||||||
|
"grad_norm": 3.215052366256714,
|
||||||
|
"learning_rate": 6.420561307807713e-06,
|
||||||
|
"loss": 1.4627,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9722222222222222,
|
||||||
|
"grad_norm": 3.1179182529449463,
|
||||||
|
"learning_rate": 6.12738151212918e-06,
|
||||||
|
"loss": 1.4731,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0069444444444444,
|
||||||
|
"grad_norm": 3.928844451904297,
|
||||||
|
"learning_rate": 5.830056206037482e-06,
|
||||||
|
"loss": 1.4354,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0416666666666667,
|
||||||
|
"grad_norm": 3.2214365005493164,
|
||||||
|
"learning_rate": 5.529678688597081e-06,
|
||||||
|
"loss": 1.3671,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0763888888888888,
|
||||||
|
"grad_norm": 3.3545398712158203,
|
||||||
|
"learning_rate": 5.2273534822017105e-06,
|
||||||
|
"loss": 1.373,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1111111111111112,
|
||||||
|
"grad_norm": 4.0173234939575195,
|
||||||
|
"learning_rate": 4.924192271119554e-06,
|
||||||
|
"loss": 1.3456,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1458333333333333,
|
||||||
|
"grad_norm": 3.150284767150879,
|
||||||
|
"learning_rate": 4.621309813703385e-06,
|
||||||
|
"loss": 1.3462,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1805555555555556,
|
||||||
|
"grad_norm": 4.555105209350586,
|
||||||
|
"learning_rate": 4.319819843296952e-06,
|
||||||
|
"loss": 1.3409,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2152777777777777,
|
||||||
|
"grad_norm": 3.7820332050323486,
|
||||||
|
"learning_rate": 4.020830972910433e-06,
|
||||||
|
"loss": 1.3522,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.25,
|
||||||
|
"grad_norm": 3.446506977081299,
|
||||||
|
"learning_rate": 3.7254426187239567e-06,
|
||||||
|
"loss": 1.3083,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2847222222222223,
|
||||||
|
"grad_norm": 3.7315480709075928,
|
||||||
|
"learning_rate": 3.4347409574088896e-06,
|
||||||
|
"loss": 1.3234,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3194444444444444,
|
||||||
|
"grad_norm": 4.601447105407715,
|
||||||
|
"learning_rate": 3.149794932132331e-06,
|
||||||
|
"loss": 1.3384,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3541666666666667,
|
||||||
|
"grad_norm": 4.626559257507324,
|
||||||
|
"learning_rate": 2.871652321931161e-06,
|
||||||
|
"loss": 1.3196,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3888888888888888,
|
||||||
|
"grad_norm": 3.092618227005005,
|
||||||
|
"learning_rate": 2.601335888909005e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4236111111111112,
|
||||||
|
"grad_norm": 4.193453788757324,
|
||||||
|
"learning_rate": 2.339839617423318e-06,
|
||||||
|
"loss": 1.2816,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4583333333333333,
|
||||||
|
"grad_norm": 3.9958441257476807,
|
||||||
|
"learning_rate": 2.0881250590915316e-06,
|
||||||
|
"loss": 1.2989,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4930555555555556,
|
||||||
|
"grad_norm": 4.101428985595703,
|
||||||
|
"learning_rate": 1.8471177970560712e-06,
|
||||||
|
"loss": 1.3146,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5277777777777777,
|
||||||
|
"grad_norm": 3.387007236480713,
|
||||||
|
"learning_rate": 1.6177040425095664e-06,
|
||||||
|
"loss": 1.2792,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5625,
|
||||||
|
"grad_norm": 3.733682870864868,
|
||||||
|
"learning_rate": 1.40072737599522e-06,
|
||||||
|
"loss": 1.3185,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5972222222222223,
|
||||||
|
"grad_norm": 3.3572065830230713,
|
||||||
|
"learning_rate": 1.196985645464921e-06,
|
||||||
|
"loss": 1.2915,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6319444444444444,
|
||||||
|
"grad_norm": 4.337113380432129,
|
||||||
|
"learning_rate": 1.0072280325013185e-06,
|
||||||
|
"loss": 1.2886,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6666666666666665,
|
||||||
|
"grad_norm": 4.326784133911133,
|
||||||
|
"learning_rate": 8.321522974916968e-07,
|
||||||
|
"loss": 1.3046,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7013888888888888,
|
||||||
|
"grad_norm": 4.501497268676758,
|
||||||
|
"learning_rate": 6.724022138834341e-07,
|
||||||
|
"loss": 1.2783,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7361111111111112,
|
||||||
|
"grad_norm": 3.4914722442626953,
|
||||||
|
"learning_rate": 5.285652009556075e-07,
|
||||||
|
"loss": 1.2741,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7708333333333335,
|
||||||
|
"grad_norm": 4.376003742218018,
|
||||||
|
"learning_rate": 4.0117016381130636e-07,
|
||||||
|
"loss": 1.279,
|
||||||
|
"step": 1020
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8055555555555556,
|
||||||
|
"grad_norm": 4.257233619689941,
|
||||||
|
"learning_rate": 2.906855485332305e-07,
|
||||||
|
"loss": 1.2538,
|
||||||
|
"step": 1040
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8402777777777777,
|
||||||
|
"grad_norm": 3.9241201877593994,
|
||||||
|
"learning_rate": 1.975176196540185e-07,
|
||||||
|
"loss": 1.2794,
|
||||||
|
"step": 1060
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.875,
|
||||||
|
"grad_norm": 4.226406574249268,
|
||||||
|
"learning_rate": 1.2200896627521718e-07,
|
||||||
|
"loss": 1.2932,
|
||||||
|
"step": 1080
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9097222222222223,
|
||||||
|
"grad_norm": 4.021918296813965,
|
||||||
|
"learning_rate": 6.443724232808146e-08,
|
||||||
|
"loss": 1.262,
|
||||||
|
"step": 1100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9444444444444444,
|
||||||
|
"grad_norm": 5.649799346923828,
|
||||||
|
"learning_rate": 2.501414560839577e-08,
|
||||||
|
"loss": 1.2514,
|
||||||
|
"step": 1120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9791666666666665,
|
||||||
|
"grad_norm": 3.755774974822998,
|
||||||
|
"learning_rate": 3.884639339534202e-09,
|
||||||
|
"loss": 1.271,
|
||||||
|
"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": 2.3084839821724877e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:8f7b3c091cc71db1555f02e15d0784a3ffaf482c622a293f8de6809cf59c91f3
|
||||||
|
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:bcefd1c64077242e0070090123dd32b42f48d497da34cae8f5369988566999b1
|
||||||
|
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:c4d1d2d9971cbb6c2efd3f6d7c32d010bd117280fd908a3053d0f60f1927ea47
|
||||||
|
size 14645
|
||||||
3
checkpoint-150/scheduler.pt
Normal file
3
checkpoint-150/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e5c3b1f4b3d2abec87ff5069b5d5df261c03ab9fab7ada1150395aac7685dc6
|
||||||
|
size 1465
|
||||||
83
checkpoint-150/trainer_state.json
Normal file
83
checkpoint-150/trainer_state.json
Normal file
@@ -0,0 +1,83 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.2604166666666667,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 150,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"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": 3.005989100273664e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:1a88f5bcfb36778bcfc1b97b9e3212bc5248626088d0d41e844405d099439218
|
||||||
|
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:f578b853fa34d58c5ec7d8ddac1daead60e12695e71e75710c6192fc062b7726
|
||||||
|
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:dc4e0ced003b5013da8539696df1959d3cff952d018e97a1cbe4005fa1e8a4ef
|
||||||
|
size 14645
|
||||||
3
checkpoint-200/scheduler.pt
Normal file
3
checkpoint-200/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:dacf44b20691c6fc535bf16b0ef4e66f3a5b3cb2170a2da905fbebeb4c5a46ff
|
||||||
|
size 1465
|
||||||
104
checkpoint-200/trainer_state.json
Normal file
104
checkpoint-200/trainer_state.json
Normal file
@@ -0,0 +1,104 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 200,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"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": 4.031728671286886e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:790c9d1e0e8bd98feab2d37fa648b09d29d7d2d73e8e7b1241b596d85c97a5af
|
||||||
|
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 sha256:010fa69d2addf135b03ef8201f394904a5d0a76849db3d8bcd663d6723794051
|
||||||
|
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:ff21f0aad1ed5420ebfda78faf43946392315a455210edabca911af56674cec7
|
||||||
|
size 14645
|
||||||
3
checkpoint-250/scheduler.pt
Normal file
3
checkpoint-250/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:12bc768c5ceac0892205b61d77c6800d899da633a32337206aa415df9749b66a
|
||||||
|
size 1465
|
||||||
118
checkpoint-250/trainer_state.json
Normal file
118
checkpoint-250/trainer_state.json
Normal file
@@ -0,0 +1,118 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.4340277777777778,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 250,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"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": 5.029771929580339e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:55a72307315a69d622c7ede6f9a0629ad9f53d661f2943666bddcfd9e5da6a9e
|
||||||
|
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:e8ab581fe88133fafd9aabdcaa8167afe145af232139a6f773ec53d236086312
|
||||||
|
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 sha256:7ac8c1581ab76c3f7bf7a2880e65d71eb618d8c2c1aa9b1572d5761adcf47e8e
|
||||||
|
size 14645
|
||||||
3
checkpoint-300/scheduler.pt
Normal file
3
checkpoint-300/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8011544f8969ccf121f310e7c9677b774202f770f03769833c73ecbfadde40a4
|
||||||
|
size 1465
|
||||||
139
checkpoint-300/trainer_state.json
Normal file
139
checkpoint-300/trainer_state.json
Normal file
@@ -0,0 +1,139 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 300,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"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": 6.016103183292826e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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:e65c97ab3e97c2b5b07497fb9ff23a013f6296e2663c749d5b39b57d3fc6161e
|
||||||
|
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 sha256:6f69d07b8f9a7c4c99d5a66d5c14d378db2e7ebd65b6641efb36da7fa2291bb8
|
||||||
|
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 sha256:6ad1631a0ad068ec449f6eede716e58462ecbcd22d0c54c2727b1eed07ff963b
|
||||||
|
size 14645
|
||||||
3
checkpoint-350/scheduler.pt
Normal file
3
checkpoint-350/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2a6d13f122fa4e9259c6cf2ccd0d4a831e7733be6388a9b01a859d975eb74082
|
||||||
|
size 1465
|
||||||
153
checkpoint-350/trainer_state.json
Normal file
153
checkpoint-350/trainer_state.json
Normal file
@@ -0,0 +1,153 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.6076388888888888,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 350,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"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": 7.00188198395904e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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 sha256:37d237781370545b3dcbcdbe435120bf4a17c07691c07a13636741147a09a926
|
||||||
|
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:c446779bdef7b93b78515dd5f517c62a6a630e42e4acdc0243bb60787b9b2227
|
||||||
|
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 sha256:132dc1388181d24199cf5863c838c52e57935757160a52521ca7cdc17c1827d0
|
||||||
|
size 14645
|
||||||
3
checkpoint-400/scheduler.pt
Normal file
3
checkpoint-400/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:20cc7f2c390b57e07da00163d66a7f2ae7ece3e78a62f304c58c0f81ef0baa87
|
||||||
|
size 1465
|
||||||
174
checkpoint-400/trainer_state.json
Normal file
174
checkpoint-400/trainer_state.json
Normal file
@@ -0,0 +1,174 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 400,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"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": 8.001122223852749e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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": [
|
||||||
|
"down_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"k_proj",
|
||||||
|
"q_proj",
|
||||||
|
"o_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:c301753f53c340ef3a061e74923c746097d42a63834198e78be8f2d5dd7ae90a
|
||||||
|
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 sha256:1a2e5e38e89980e0167afbc2499be7e000cabdb041a175605c7c1193d7913065
|
||||||
|
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:d8afc2a53fd4e86647d6935c89c905fc4720d1e07a0408187f11ca89dc2c9964
|
||||||
|
size 14645
|
||||||
3
checkpoint-450/scheduler.pt
Normal file
3
checkpoint-450/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:384bc6e7c7dc78761d777acc2ec342f72b87fe7d2483bfdf597b557007de8a7d
|
||||||
|
size 1465
|
||||||
188
checkpoint-450/trainer_state.json
Normal file
188
checkpoint-450/trainer_state.json
Normal file
@@ -0,0 +1,188 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.78125,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 450,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.034722222222222224,
|
||||||
|
"grad_norm": 2.4759202003479004,
|
||||||
|
"learning_rate": 1.6379310344827587e-06,
|
||||||
|
"loss": 2.5561,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06944444444444445,
|
||||||
|
"grad_norm": 2.5604989528656006,
|
||||||
|
"learning_rate": 3.362068965517242e-06,
|
||||||
|
"loss": 2.3957,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10416666666666667,
|
||||||
|
"grad_norm": 1.9377268552780151,
|
||||||
|
"learning_rate": 5.086206896551724e-06,
|
||||||
|
"loss": 2.217,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1388888888888889,
|
||||||
|
"grad_norm": 1.7941242456436157,
|
||||||
|
"learning_rate": 6.810344827586207e-06,
|
||||||
|
"loss": 2.0366,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1736111111111111,
|
||||||
|
"grad_norm": 2.2135872840881348,
|
||||||
|
"learning_rate": 8.53448275862069e-06,
|
||||||
|
"loss": 1.9154,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 2.290032148361206,
|
||||||
|
"learning_rate": 9.999793100349294e-06,
|
||||||
|
"loss": 1.8946,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24305555555555555,
|
||||||
|
"grad_norm": 2.4187541007995605,
|
||||||
|
"learning_rate": 9.987843743451796e-06,
|
||||||
|
"loss": 1.7858,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2777777777777778,
|
||||||
|
"grad_norm": 2.115030288696289,
|
||||||
|
"learning_rate": 9.957553516178782e-06,
|
||||||
|
"loss": 1.7133,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3125,
|
||||||
|
"grad_norm": 2.290724754333496,
|
||||||
|
"learning_rate": 9.909033799150947e-06,
|
||||||
|
"loss": 1.7567,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3472222222222222,
|
||||||
|
"grad_norm": 2.318016767501831,
|
||||||
|
"learning_rate": 9.842463004902127e-06,
|
||||||
|
"loss": 1.6653,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3819444444444444,
|
||||||
|
"grad_norm": 2.37850284576416,
|
||||||
|
"learning_rate": 9.758085921836076e-06,
|
||||||
|
"loss": 1.6518,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 2.5013656616210938,
|
||||||
|
"learning_rate": 9.656212814111567e-06,
|
||||||
|
"loss": 1.669,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4513888888888889,
|
||||||
|
"grad_norm": 3.0407257080078125,
|
||||||
|
"learning_rate": 9.53721828076571e-06,
|
||||||
|
"loss": 1.6393,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4861111111111111,
|
||||||
|
"grad_norm": 2.709101915359497,
|
||||||
|
"learning_rate": 9.401539878270545e-06,
|
||||||
|
"loss": 1.6274,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5208333333333334,
|
||||||
|
"grad_norm": 2.9556779861450195,
|
||||||
|
"learning_rate": 9.249676511588e-06,
|
||||||
|
"loss": 1.6256,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 2.9455294609069824,
|
||||||
|
"learning_rate": 9.082186599639429e-06,
|
||||||
|
"loss": 1.61,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5902777777777778,
|
||||||
|
"grad_norm": 2.631028413772583,
|
||||||
|
"learning_rate": 8.899686021935554e-06,
|
||||||
|
"loss": 1.5928,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.625,
|
||||||
|
"grad_norm": 2.5670149326324463,
|
||||||
|
"learning_rate": 8.702845853917242e-06,
|
||||||
|
"loss": 1.5608,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6597222222222222,
|
||||||
|
"grad_norm": 2.519019365310669,
|
||||||
|
"learning_rate": 8.492389899334572e-06,
|
||||||
|
"loss": 1.5496,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6944444444444444,
|
||||||
|
"grad_norm": 3.059999942779541,
|
||||||
|
"learning_rate": 8.269092028737885e-06,
|
||||||
|
"loss": 1.5339,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7291666666666666,
|
||||||
|
"grad_norm": 2.882279872894287,
|
||||||
|
"learning_rate": 8.033773333867498e-06,
|
||||||
|
"loss": 1.5109,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7638888888888888,
|
||||||
|
"grad_norm": 2.6647043228149414,
|
||||||
|
"learning_rate": 7.78729910840572e-06,
|
||||||
|
"loss": 1.5076,
|
||||||
|
"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": 9.001890917174477e+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:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e
|
||||||
|
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