Henry236/east8b-eg-lora-heuristic
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Henry236/east8b-eg-lora-heuristic
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-22 08:49:17 +08:00
commit 4e00a082d0
191 changed files with 14013 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"v_proj",
"q_proj",
"k_proj",
"gate_proj",
"o_proj",
"down_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb76ab90c930eda4c5f96bbae36464a39848eac93333e8b3aa9200d47c25465f
size 671149168

7
chat_template.jinja Normal file
View 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-1000/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-1000/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f621ff5fd31773970002dd3944a209cb6172191e89dd7084166b6669445452b
size 671149168

3
checkpoint-1000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3d8786d6ea9e8862659d445373eb4abfef840d82af0104c84ee661b08e5cd0c
size 1342562339

3
checkpoint-1000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e916849628b0b5f07beaddd380af50b5fd8e0305530ac58ecc8c9447c4f23d41
size 14645

3
checkpoint-1000/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.955244541168213,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6052,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6228716373443604,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5924,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.7822635173797607,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5711,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.450777769088745,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5601,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.999849557876587,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5497,
"step": 400
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.2980637550354004,
"learning_rate": 8.033773333867498e-06,
"loss": 1.5243,
"step": 420
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.758843421936035,
"learning_rate": 7.78729910840572e-06,
"loss": 1.5171,
"step": 440
},
{
"epoch": 0.7986111111111112,
"grad_norm": 3.114650249481201,
"learning_rate": 7.530575666193283e-06,
"loss": 1.5212,
"step": 460
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.235766649246216,
"learning_rate": 7.26454700860997e-06,
"loss": 1.5019,
"step": 480
},
{
"epoch": 0.8680555555555556,
"grad_norm": 3.39516544342041,
"learning_rate": 6.990191353373876e-06,
"loss": 1.4963,
"step": 500
},
{
"epoch": 0.9027777777777778,
"grad_norm": 3.507965087890625,
"learning_rate": 6.708517537523264e-06,
"loss": 1.4762,
"step": 520
},
{
"epoch": 0.9375,
"grad_norm": 3.2428181171417236,
"learning_rate": 6.420561307807713e-06,
"loss": 1.4822,
"step": 540
},
{
"epoch": 0.9722222222222222,
"grad_norm": 2.9236435890197754,
"learning_rate": 6.12738151212918e-06,
"loss": 1.5021,
"step": 560
},
{
"epoch": 1.0069444444444444,
"grad_norm": 3.689115047454834,
"learning_rate": 5.830056206037482e-06,
"loss": 1.4606,
"step": 580
},
{
"epoch": 1.0416666666666667,
"grad_norm": 2.897470474243164,
"learning_rate": 5.529678688597081e-06,
"loss": 1.3981,
"step": 600
},
{
"epoch": 1.0763888888888888,
"grad_norm": 3.1479601860046387,
"learning_rate": 5.2273534822017105e-06,
"loss": 1.4024,
"step": 620
},
{
"epoch": 1.1111111111111112,
"grad_norm": 3.726175546646118,
"learning_rate": 4.924192271119554e-06,
"loss": 1.3784,
"step": 640
},
{
"epoch": 1.1458333333333333,
"grad_norm": 2.944827079772949,
"learning_rate": 4.621309813703385e-06,
"loss": 1.3781,
"step": 660
},
{
"epoch": 1.1805555555555556,
"grad_norm": 4.154749870300293,
"learning_rate": 4.319819843296952e-06,
"loss": 1.385,
"step": 680
},
{
"epoch": 1.2152777777777777,
"grad_norm": 3.470216751098633,
"learning_rate": 4.020830972910433e-06,
"loss": 1.3937,
"step": 700
},
{
"epoch": 1.25,
"grad_norm": 3.534930944442749,
"learning_rate": 3.7254426187239567e-06,
"loss": 1.3471,
"step": 720
},
{
"epoch": 1.2847222222222223,
"grad_norm": 3.479079484939575,
"learning_rate": 3.4347409574088896e-06,
"loss": 1.364,
"step": 740
},
{
"epoch": 1.3194444444444444,
"grad_norm": 4.021931171417236,
"learning_rate": 3.149794932132331e-06,
"loss": 1.3875,
"step": 760
},
{
"epoch": 1.3541666666666667,
"grad_norm": 4.136874198913574,
"learning_rate": 2.871652321931161e-06,
"loss": 1.3603,
"step": 780
},
{
"epoch": 1.3888888888888888,
"grad_norm": 2.8454277515411377,
"learning_rate": 2.601335888909005e-06,
"loss": 1.3676,
"step": 800
},
{
"epoch": 1.4236111111111112,
"grad_norm": 3.8844242095947266,
"learning_rate": 2.339839617423318e-06,
"loss": 1.3327,
"step": 820
},
{
"epoch": 1.4583333333333333,
"grad_norm": 3.777667284011841,
"learning_rate": 2.0881250590915316e-06,
"loss": 1.351,
"step": 840
},
{
"epoch": 1.4930555555555556,
"grad_norm": 3.9106264114379883,
"learning_rate": 1.8471177970560712e-06,
"loss": 1.3651,
"step": 860
},
{
"epoch": 1.5277777777777777,
"grad_norm": 3.131366014480591,
"learning_rate": 1.6177040425095664e-06,
"loss": 1.3271,
"step": 880
},
{
"epoch": 1.5625,
"grad_norm": 3.60107421875,
"learning_rate": 1.40072737599522e-06,
"loss": 1.3627,
"step": 900
},
{
"epoch": 1.5972222222222223,
"grad_norm": 3.059379816055298,
"learning_rate": 1.196985645464921e-06,
"loss": 1.3369,
"step": 920
},
{
"epoch": 1.6319444444444444,
"grad_norm": 4.2240095138549805,
"learning_rate": 1.0072280325013185e-06,
"loss": 1.3439,
"step": 940
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.858954668045044,
"learning_rate": 8.321522974916968e-07,
"loss": 1.361,
"step": 960
},
{
"epoch": 1.7013888888888888,
"grad_norm": 4.0487380027771,
"learning_rate": 6.724022138834341e-07,
"loss": 1.3317,
"step": 980
},
{
"epoch": 1.7361111111111112,
"grad_norm": 3.2408926486968994,
"learning_rate": 5.285652009556075e-07,
"loss": 1.3269,
"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": 2.0354156489510093e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-1050/README.md Normal file
View 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
View 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",
"up_proj",
"q_proj",
"gate_proj",
"v_proj",
"down_proj",
"k_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-1050/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f08075daaf4ee6b5aa54d7ff71177574136c2937c59c0901909446804b48f70
size 671149168

3
checkpoint-1050/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67b84406acd5bcb603f5f7e3d0a3c283b8c5f432dac20226e0b81468a796c0df
size 1342562339

3
checkpoint-1050/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:278e0a88fa979499cf3285becf04f912375ae3107d75233036211edc161b0fd7
size 14645

3
checkpoint-1050/scheduler.pt Normal file
View 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
View 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": 2.975640058517456,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6527,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.329663038253784,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4375,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.8956992626190186,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2566,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8109517097473145,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0567,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.382589817047119,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9338,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.378267526626587,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9218,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.6260263919830322,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7895,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.2361156940460205,
"learning_rate": 9.957553516178782e-06,
"loss": 1.7166,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.345552682876587,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7573,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.4918200969696045,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6668,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5107343196868896,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6556,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.69317626953125,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6606,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.759850025177002,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6359,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.751281976699829,
"learning_rate": 9.401539878270545e-06,
"loss": 1.635,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 3.0062153339385986,
"learning_rate": 9.249676511588e-06,
"loss": 1.6278,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.9671173095703125,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6051,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6128034591674805,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5921,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.750213384628296,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5715,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.4882044792175293,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5607,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.949469566345215,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5498,
"step": 400
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.360396146774292,
"learning_rate": 8.033773333867498e-06,
"loss": 1.5246,
"step": 420
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.726001739501953,
"learning_rate": 7.78729910840572e-06,
"loss": 1.5172,
"step": 440
},
{
"epoch": 0.7986111111111112,
"grad_norm": 3.169776678085327,
"learning_rate": 7.530575666193283e-06,
"loss": 1.5212,
"step": 460
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.2836718559265137,
"learning_rate": 7.26454700860997e-06,
"loss": 1.5022,
"step": 480
},
{
"epoch": 0.8680555555555556,
"grad_norm": 3.3847920894622803,
"learning_rate": 6.990191353373876e-06,
"loss": 1.4968,
"step": 500
},
{
"epoch": 0.9027777777777778,
"grad_norm": 3.5661308765411377,
"learning_rate": 6.708517537523264e-06,
"loss": 1.477,
"step": 520
},
{
"epoch": 0.9375,
"grad_norm": 3.243346929550171,
"learning_rate": 6.420561307807713e-06,
"loss": 1.483,
"step": 540
},
{
"epoch": 0.9722222222222222,
"grad_norm": 2.8526790142059326,
"learning_rate": 6.12738151212918e-06,
"loss": 1.5018,
"step": 560
},
{
"epoch": 1.0069444444444444,
"grad_norm": 3.678152322769165,
"learning_rate": 5.830056206037482e-06,
"loss": 1.4604,
"step": 580
},
{
"epoch": 1.0416666666666667,
"grad_norm": 2.920789957046509,
"learning_rate": 5.529678688597081e-06,
"loss": 1.3984,
"step": 600
},
{
"epoch": 1.0763888888888888,
"grad_norm": 3.198030710220337,
"learning_rate": 5.2273534822017105e-06,
"loss": 1.4028,
"step": 620
},
{
"epoch": 1.1111111111111112,
"grad_norm": 3.737910270690918,
"learning_rate": 4.924192271119554e-06,
"loss": 1.3788,
"step": 640
},
{
"epoch": 1.1458333333333333,
"grad_norm": 2.9169039726257324,
"learning_rate": 4.621309813703385e-06,
"loss": 1.3787,
"step": 660
},
{
"epoch": 1.1805555555555556,
"grad_norm": 4.108018398284912,
"learning_rate": 4.319819843296952e-06,
"loss": 1.3854,
"step": 680
},
{
"epoch": 1.2152777777777777,
"grad_norm": 3.489570140838623,
"learning_rate": 4.020830972910433e-06,
"loss": 1.394,
"step": 700
},
{
"epoch": 1.25,
"grad_norm": 3.5733399391174316,
"learning_rate": 3.7254426187239567e-06,
"loss": 1.347,
"step": 720
},
{
"epoch": 1.2847222222222223,
"grad_norm": 3.479602098464966,
"learning_rate": 3.4347409574088896e-06,
"loss": 1.3647,
"step": 740
},
{
"epoch": 1.3194444444444444,
"grad_norm": 4.031429767608643,
"learning_rate": 3.149794932132331e-06,
"loss": 1.3879,
"step": 760
},
{
"epoch": 1.3541666666666667,
"grad_norm": 4.149319171905518,
"learning_rate": 2.871652321931161e-06,
"loss": 1.3618,
"step": 780
},
{
"epoch": 1.3888888888888888,
"grad_norm": 2.849364757537842,
"learning_rate": 2.601335888909005e-06,
"loss": 1.3687,
"step": 800
},
{
"epoch": 1.4236111111111112,
"grad_norm": 3.924811601638794,
"learning_rate": 2.339839617423318e-06,
"loss": 1.3329,
"step": 820
},
{
"epoch": 1.4583333333333333,
"grad_norm": 3.762462615966797,
"learning_rate": 2.0881250590915316e-06,
"loss": 1.3513,
"step": 840
},
{
"epoch": 1.4930555555555556,
"grad_norm": 3.951873302459717,
"learning_rate": 1.8471177970560712e-06,
"loss": 1.3655,
"step": 860
},
{
"epoch": 1.5277777777777777,
"grad_norm": 3.1432993412017822,
"learning_rate": 1.6177040425095664e-06,
"loss": 1.3276,
"step": 880
},
{
"epoch": 1.5625,
"grad_norm": 3.6409666538238525,
"learning_rate": 1.40072737599522e-06,
"loss": 1.3631,
"step": 900
},
{
"epoch": 1.5972222222222223,
"grad_norm": 3.062958002090454,
"learning_rate": 1.196985645464921e-06,
"loss": 1.3374,
"step": 920
},
{
"epoch": 1.6319444444444444,
"grad_norm": 4.230245590209961,
"learning_rate": 1.0072280325013185e-06,
"loss": 1.3438,
"step": 940
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.834761381149292,
"learning_rate": 8.321522974916968e-07,
"loss": 1.3611,
"step": 960
},
{
"epoch": 1.7013888888888888,
"grad_norm": 4.029264450073242,
"learning_rate": 6.724022138834341e-07,
"loss": 1.3323,
"step": 980
},
{
"epoch": 1.7361111111111112,
"grad_norm": 3.260033369064331,
"learning_rate": 5.285652009556075e-07,
"loss": 1.3273,
"step": 1000
},
{
"epoch": 1.7708333333333335,
"grad_norm": 4.1092071533203125,
"learning_rate": 4.0117016381130636e-07,
"loss": 1.3372,
"step": 1020
},
{
"epoch": 1.8055555555555556,
"grad_norm": 3.8922550678253174,
"learning_rate": 2.906855485332305e-07,
"loss": 1.3055,
"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": 2.137833077689221e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1050/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab2a55d99d554b614e62a1cc2b43a5981feda7b0fbd4713a15efa9946f443ce9
size 6033

207
checkpoint-1150/README.md Normal file
View 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
View 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",
"up_proj",
"q_proj",
"gate_proj",
"v_proj",
"down_proj",
"k_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-1150/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a0f75da15663e9919a81db6f60b57a54d8d1a0868e68952e53a8b635c6f6fdc
size 671149168

3
checkpoint-1150/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2a374b6d54e05cfcb17024e5ba3a9b2ab318a4df5babbf85720810fab3bf0fe
size 1342562339

3
checkpoint-1150/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2faa2348c8dd051a0f8b65896fc7494d2594c8d04a70b968dbb22bf1ede1e00
size 14645

3
checkpoint-1150/scheduler.pt Normal file
View 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
View 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": 2.975640058517456,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6527,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.329663038253784,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4375,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.8956992626190186,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2566,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8109517097473145,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0567,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.382589817047119,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9338,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.378267526626587,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9218,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.6260263919830322,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7895,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.2361156940460205,
"learning_rate": 9.957553516178782e-06,
"loss": 1.7166,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.345552682876587,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7573,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.4918200969696045,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6668,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5107343196868896,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6556,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.69317626953125,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6606,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.759850025177002,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6359,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.751281976699829,
"learning_rate": 9.401539878270545e-06,
"loss": 1.635,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 3.0062153339385986,
"learning_rate": 9.249676511588e-06,
"loss": 1.6278,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.9671173095703125,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6051,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6128034591674805,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5921,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.750213384628296,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5715,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.4882044792175293,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5607,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.949469566345215,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5498,
"step": 400
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.360396146774292,
"learning_rate": 8.033773333867498e-06,
"loss": 1.5246,
"step": 420
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.726001739501953,
"learning_rate": 7.78729910840572e-06,
"loss": 1.5172,
"step": 440
},
{
"epoch": 0.7986111111111112,
"grad_norm": 3.169776678085327,
"learning_rate": 7.530575666193283e-06,
"loss": 1.5212,
"step": 460
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.2836718559265137,
"learning_rate": 7.26454700860997e-06,
"loss": 1.5022,
"step": 480
},
{
"epoch": 0.8680555555555556,
"grad_norm": 3.3847920894622803,
"learning_rate": 6.990191353373876e-06,
"loss": 1.4968,
"step": 500
},
{
"epoch": 0.9027777777777778,
"grad_norm": 3.5661308765411377,
"learning_rate": 6.708517537523264e-06,
"loss": 1.477,
"step": 520
},
{
"epoch": 0.9375,
"grad_norm": 3.243346929550171,
"learning_rate": 6.420561307807713e-06,
"loss": 1.483,
"step": 540
},
{
"epoch": 0.9722222222222222,
"grad_norm": 2.8526790142059326,
"learning_rate": 6.12738151212918e-06,
"loss": 1.5018,
"step": 560
},
{
"epoch": 1.0069444444444444,
"grad_norm": 3.678152322769165,
"learning_rate": 5.830056206037482e-06,
"loss": 1.4604,
"step": 580
},
{
"epoch": 1.0416666666666667,
"grad_norm": 2.920789957046509,
"learning_rate": 5.529678688597081e-06,
"loss": 1.3984,
"step": 600
},
{
"epoch": 1.0763888888888888,
"grad_norm": 3.198030710220337,
"learning_rate": 5.2273534822017105e-06,
"loss": 1.4028,
"step": 620
},
{
"epoch": 1.1111111111111112,
"grad_norm": 3.737910270690918,
"learning_rate": 4.924192271119554e-06,
"loss": 1.3788,
"step": 640
},
{
"epoch": 1.1458333333333333,
"grad_norm": 2.9169039726257324,
"learning_rate": 4.621309813703385e-06,
"loss": 1.3787,
"step": 660
},
{
"epoch": 1.1805555555555556,
"grad_norm": 4.108018398284912,
"learning_rate": 4.319819843296952e-06,
"loss": 1.3854,
"step": 680
},
{
"epoch": 1.2152777777777777,
"grad_norm": 3.489570140838623,
"learning_rate": 4.020830972910433e-06,
"loss": 1.394,
"step": 700
},
{
"epoch": 1.25,
"grad_norm": 3.5733399391174316,
"learning_rate": 3.7254426187239567e-06,
"loss": 1.347,
"step": 720
},
{
"epoch": 1.2847222222222223,
"grad_norm": 3.479602098464966,
"learning_rate": 3.4347409574088896e-06,
"loss": 1.3647,
"step": 740
},
{
"epoch": 1.3194444444444444,
"grad_norm": 4.031429767608643,
"learning_rate": 3.149794932132331e-06,
"loss": 1.3879,
"step": 760
},
{
"epoch": 1.3541666666666667,
"grad_norm": 4.149319171905518,
"learning_rate": 2.871652321931161e-06,
"loss": 1.3618,
"step": 780
},
{
"epoch": 1.3888888888888888,
"grad_norm": 2.849364757537842,
"learning_rate": 2.601335888909005e-06,
"loss": 1.3687,
"step": 800
},
{
"epoch": 1.4236111111111112,
"grad_norm": 3.924811601638794,
"learning_rate": 2.339839617423318e-06,
"loss": 1.3329,
"step": 820
},
{
"epoch": 1.4583333333333333,
"grad_norm": 3.762462615966797,
"learning_rate": 2.0881250590915316e-06,
"loss": 1.3513,
"step": 840
},
{
"epoch": 1.4930555555555556,
"grad_norm": 3.951873302459717,
"learning_rate": 1.8471177970560712e-06,
"loss": 1.3655,
"step": 860
},
{
"epoch": 1.5277777777777777,
"grad_norm": 3.1432993412017822,
"learning_rate": 1.6177040425095664e-06,
"loss": 1.3276,
"step": 880
},
{
"epoch": 1.5625,
"grad_norm": 3.6409666538238525,
"learning_rate": 1.40072737599522e-06,
"loss": 1.3631,
"step": 900
},
{
"epoch": 1.5972222222222223,
"grad_norm": 3.062958002090454,
"learning_rate": 1.196985645464921e-06,
"loss": 1.3374,
"step": 920
},
{
"epoch": 1.6319444444444444,
"grad_norm": 4.230245590209961,
"learning_rate": 1.0072280325013185e-06,
"loss": 1.3438,
"step": 940
},
{
"epoch": 1.6666666666666665,
"grad_norm": 3.834761381149292,
"learning_rate": 8.321522974916968e-07,
"loss": 1.3611,
"step": 960
},
{
"epoch": 1.7013888888888888,
"grad_norm": 4.029264450073242,
"learning_rate": 6.724022138834341e-07,
"loss": 1.3323,
"step": 980
},
{
"epoch": 1.7361111111111112,
"grad_norm": 3.260033369064331,
"learning_rate": 5.285652009556075e-07,
"loss": 1.3273,
"step": 1000
},
{
"epoch": 1.7708333333333335,
"grad_norm": 4.1092071533203125,
"learning_rate": 4.0117016381130636e-07,
"loss": 1.3372,
"step": 1020
},
{
"epoch": 1.8055555555555556,
"grad_norm": 3.8922550678253174,
"learning_rate": 2.906855485332305e-07,
"loss": 1.3055,
"step": 1040
},
{
"epoch": 1.8402777777777777,
"grad_norm": 3.679527759552002,
"learning_rate": 1.975176196540185e-07,
"loss": 1.3342,
"step": 1060
},
{
"epoch": 1.875,
"grad_norm": 3.9715416431427,
"learning_rate": 1.2200896627521718e-07,
"loss": 1.3447,
"step": 1080
},
{
"epoch": 1.9097222222222223,
"grad_norm": 3.626037120819092,
"learning_rate": 6.443724232808146e-08,
"loss": 1.3219,
"step": 1100
},
{
"epoch": 1.9444444444444444,
"grad_norm": 4.019833564758301,
"learning_rate": 2.501414560839577e-08,
"loss": 1.2977,
"step": 1120
},
{
"epoch": 1.9791666666666665,
"grad_norm": 3.5683982372283936,
"learning_rate": 3.884639339534202e-09,
"loss": 1.3165,
"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": 2.3405557230187315e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-1150/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab2a55d99d554b614e62a1cc2b43a5981feda7b0fbd4713a15efa9946f443ce9
size 6033

207
checkpoint-150/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-150/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8d5bb17394114fd2e3b6408905151e8290a5233fe1e535b0a09a7aa07ca5956d
size 671149168

3
checkpoint-150/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:733abe40af43bfc45e0b9ecc0b756cea436949fac21e65d7ee117f886ffde940
size 1342562339

3
checkpoint-150/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6459d6c16f31f4d8a16bdd17066e44622c40bb81997aa8632a5b0f0176826a68
size 14645

3
checkpoint-150/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"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": 3.049872287249203e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-150/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-200/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-200/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:720f483f0daafa4a3f2b06cdf2c10654684a043b9e1a38b9f261a7abc3c138f9
size 671149168

3
checkpoint-200/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4e645af312b97a7fb710d9f9582714049bf368a2363cf0ee9d89661b9ca5be8
size 1342562339

3
checkpoint-200/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d88dba6a2d8d7135f7a1e35a18c359edfa546ed30673afdaf8bd74636be443a6
size 14645

3
checkpoint-200/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"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": 4.089496844825395e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-200/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-250/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-250/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f28708dcccceac93a802f215f543cc0d44b2e943afe1eb9d87f60315018bd499
size 671149168

3
checkpoint-250/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2589b983afe0f8808d96b1c76a79b017af4a9cb2df4f6aa9630d39b65657738
size 1342562339

3
checkpoint-250/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c50c5a52233c6354c2103eba4b740346d2fdd61640e143f5f38881a8f97c7f59
size 14645

3
checkpoint-250/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"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": 5.104113694507008e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-250/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-300/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-300/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c61f29d2c66b425d30b692f5931f827170c86ace481f4294327b368024934eb5
size 671149168

3
checkpoint-300/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b6106bb50c7b8ad73c7ad4c49698d158ee9e502587abe7b34ffac3b0ffa4e37
size 1342562339

3
checkpoint-300/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a1e92af4a930123dd1ad05f528fa49ef6a6fe3970cf2c6358fd4a5a8c9bb28a
size 14645

3
checkpoint-300/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"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": 6.104440425391718e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-300/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-350/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-350/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5733e48aa6bd717c588dae4e4871eb62416e096ed8c721416b51938ed611f274
size 671149168

3
checkpoint-350/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0356854a9edab5cff7e7c3f0472581ecf9ec8bde7721020c9d2350cae9c6e421
size 1342562339

3
checkpoint-350/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0b808c9a244adbf5676c08879185a7f084fcbffa8a22220d89b64cc6310eca05
size 14645

3
checkpoint-350/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.955244541168213,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6052,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6228716373443604,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5924,
"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": 7.105319609322701e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-350/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-400/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-400/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:810d6491bc2d6eb6ab526a40f0001a5bbe36a1f3e7a0334007dac0d755838a17
size 671149168

3
checkpoint-400/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0083de48147d06f3808c4361a55d86ab9ba7c6c6a180383622fdeb7fecccfee6
size 1342562339

3
checkpoint-400/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:659ac346bbe782cc1dfd0935e5499a14aa28ff41ee1deeebe21f2886be5fbe62
size 14645

3
checkpoint-400/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.955244541168213,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6052,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6228716373443604,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5924,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.7822635173797607,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5711,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.450777769088745,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5601,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.999849557876587,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5497,
"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": 8.118408005576294e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-400/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-450/README.md Normal file
View 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
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-450/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4a5b08905d3c150b486abdc27cb62e1cda6d5143e50223de78ccceef218fdcd0
size 671149168

3
checkpoint-450/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:89b803503cddbfcfd670ffef25c55fbeed49ac2a47e66a519e804429732df183
size 1342562339

3
checkpoint-450/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f2b6a31564a37d218d460384db14d15527aee6f63440019bb66080c990a382a2
size 14645

3
checkpoint-450/scheduler.pt Normal file
View 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
View 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": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.955244541168213,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6052,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6228716373443604,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5924,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.7822635173797607,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5711,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.450777769088745,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5601,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.999849557876587,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5497,
"step": 400
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.2980637550354004,
"learning_rate": 8.033773333867498e-06,
"loss": 1.5243,
"step": 420
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.758843421936035,
"learning_rate": 7.78729910840572e-06,
"loss": 1.5171,
"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": 9.13173579814994e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-450/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-50/README.md Normal file
View 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-50/adapter_config.json Normal file
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-50/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c7207365fbc020be1d6f12897a167455c2ca956beecb8a497fc64c8af2abbf26
size 671149168

3
checkpoint-50/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c6ae9dd4142bb14ed5fb45115293923a4efb57810a376acdd073e2d39153cd0
size 1342562339

3
checkpoint-50/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b538287e12b1cffb7875c4b9577f1144c05c03e0d4fb9b49e88da551161ad1c
size 14645

3
checkpoint-50/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:429753af91844c8e723460e500b16300ef22bee5be6ffdf96a0f5e7a4101ca3a
size 1465

48
checkpoint-50/trainer_state.json Normal file
View File

@@ -0,0 +1,48 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.08680555555555555,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.034722222222222224,
"grad_norm": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
}
],
"logging_steps": 20,
"max_steps": 1152,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.0097368477728768e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-50/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

207
checkpoint-500/README.md Normal file
View 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-500/adapter_config.json Normal file
View File

@@ -0,0 +1,48 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": null,
"base_model_name_or_path": "biaofu-xmu/EAST-8B",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.05,
"lora_ga_config": null,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.19.1",
"qalora_group_size": 16,
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"o_proj",
"k_proj",
"down_proj",
"q_proj",
"v_proj",
"up_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_bdlora": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
checkpoint-500/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d5eec41396abac4729a51bf1b484ddd8f5239f2d62d81abc55eb5921b30d98b
size 671149168

3
checkpoint-500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7087e14d597e195f40df0226a102133771e19b4a9b5944af4658655cadef3510
size 1342562339

3
checkpoint-500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:885dc23e508a6c5936781dc5561ec0fbb841e1d4720d730ca8beafd9c96b0ad6
size 14645

3
checkpoint-500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:56d00b3dceef9b6f5ecba6ca112aac49209cb479316e5bd5c0651dae9c1ba9b3
size 1465

209
checkpoint-500/trainer_state.json Normal file
View File

@@ -0,0 +1,209 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8680555555555556,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.034722222222222224,
"grad_norm": 2.985321283340454,
"learning_rate": 1.6379310344827587e-06,
"loss": 2.6523,
"step": 20
},
{
"epoch": 0.06944444444444445,
"grad_norm": 2.353632926940918,
"learning_rate": 3.362068965517242e-06,
"loss": 2.4359,
"step": 40
},
{
"epoch": 0.10416666666666667,
"grad_norm": 1.865394115447998,
"learning_rate": 5.086206896551724e-06,
"loss": 2.2545,
"step": 60
},
{
"epoch": 0.1388888888888889,
"grad_norm": 1.8125933408737183,
"learning_rate": 6.810344827586207e-06,
"loss": 2.0557,
"step": 80
},
{
"epoch": 0.1736111111111111,
"grad_norm": 2.3572490215301514,
"learning_rate": 8.53448275862069e-06,
"loss": 1.9334,
"step": 100
},
{
"epoch": 0.20833333333333334,
"grad_norm": 2.395277261734009,
"learning_rate": 9.999793100349294e-06,
"loss": 1.9212,
"step": 120
},
{
"epoch": 0.24305555555555555,
"grad_norm": 2.714841604232788,
"learning_rate": 9.987843743451796e-06,
"loss": 1.7889,
"step": 140
},
{
"epoch": 0.2777777777777778,
"grad_norm": 2.236692190170288,
"learning_rate": 9.957553516178782e-06,
"loss": 1.716,
"step": 160
},
{
"epoch": 0.3125,
"grad_norm": 2.3020412921905518,
"learning_rate": 9.909033799150947e-06,
"loss": 1.7569,
"step": 180
},
{
"epoch": 0.3472222222222222,
"grad_norm": 2.5109288692474365,
"learning_rate": 9.842463004902127e-06,
"loss": 1.6664,
"step": 200
},
{
"epoch": 0.3819444444444444,
"grad_norm": 2.5140888690948486,
"learning_rate": 9.758085921836076e-06,
"loss": 1.6544,
"step": 220
},
{
"epoch": 0.4166666666666667,
"grad_norm": 2.666377544403076,
"learning_rate": 9.656212814111567e-06,
"loss": 1.6608,
"step": 240
},
{
"epoch": 0.4513888888888889,
"grad_norm": 2.715240955352783,
"learning_rate": 9.53721828076571e-06,
"loss": 1.6353,
"step": 260
},
{
"epoch": 0.4861111111111111,
"grad_norm": 2.7697439193725586,
"learning_rate": 9.401539878270545e-06,
"loss": 1.6352,
"step": 280
},
{
"epoch": 0.5208333333333334,
"grad_norm": 2.9743459224700928,
"learning_rate": 9.249676511588e-06,
"loss": 1.6275,
"step": 300
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.955244541168213,
"learning_rate": 9.082186599639429e-06,
"loss": 1.6052,
"step": 320
},
{
"epoch": 0.5902777777777778,
"grad_norm": 2.6228716373443604,
"learning_rate": 8.899686021935554e-06,
"loss": 1.5924,
"step": 340
},
{
"epoch": 0.625,
"grad_norm": 2.7822635173797607,
"learning_rate": 8.702845853917242e-06,
"loss": 1.5711,
"step": 360
},
{
"epoch": 0.6597222222222222,
"grad_norm": 2.450777769088745,
"learning_rate": 8.492389899334572e-06,
"loss": 1.5601,
"step": 380
},
{
"epoch": 0.6944444444444444,
"grad_norm": 2.999849557876587,
"learning_rate": 8.269092028737885e-06,
"loss": 1.5497,
"step": 400
},
{
"epoch": 0.7291666666666666,
"grad_norm": 3.2980637550354004,
"learning_rate": 8.033773333867498e-06,
"loss": 1.5243,
"step": 420
},
{
"epoch": 0.7638888888888888,
"grad_norm": 2.758843421936035,
"learning_rate": 7.78729910840572e-06,
"loss": 1.5171,
"step": 440
},
{
"epoch": 0.7986111111111112,
"grad_norm": 3.114650249481201,
"learning_rate": 7.530575666193283e-06,
"loss": 1.5212,
"step": 460
},
{
"epoch": 0.8333333333333334,
"grad_norm": 3.235766649246216,
"learning_rate": 7.26454700860997e-06,
"loss": 1.5019,
"step": 480
},
{
"epoch": 0.8680555555555556,
"grad_norm": 3.39516544342041,
"learning_rate": 6.990191353373876e-06,
"loss": 1.4963,
"step": 500
}
],
"logging_steps": 20,
"max_steps": 1152,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.018001545345106e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3b7f58321eea14364587c280ddc055ad0a161fdb8a2e9d81351505baed73ddca
size 6033

Some files were not shown because too many files have changed in this diff Show More