初始化项目，由ModelHub XC社区提供模型
Model: Xianjun/PLLaMa-13b-instruct Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
47
README.md
Normal file
47
README.md
Normal file
@@ -0,0 +1,47 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
This model is optimized for plant science by continuing pertaining on over 1.5 million plant science academic articles based on LLaMa-2-13b-base. And it undergoes further instruction tuning to make it follow instructions.
|
||||
|
||||
|
||||
- **Developed by:** [UCSB]
|
||||
- **Language(s) (NLP):** [More Information Needed]
|
||||
- **License:** [More Information Needed]
|
||||
- **Finetuned from model [optional]:** [LLaMa-2]
|
||||
|
||||
- **Paper [optional]:** [https://arxiv.org/pdf/2401.01600.pdf]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
## How to Get Started with the Model
|
||||
```python
|
||||
from transformers import LlamaTokenizer, LlamaForCausalLM
|
||||
import torch
|
||||
|
||||
tokenizer = LlamaTokenizer.from_pretrained("Xianjun/PLLaMa-13b-instruct")
|
||||
model = LlamaForCausalLM.from_pretrained("Xianjun/PLLaMa-13b-instruct").half().to("cuda")
|
||||
|
||||
instruction = "How to ..."
|
||||
batch = tokenizer(instruction, return_tensors="pt", add_special_tokens=False).to("cuda")
|
||||
with torch.no_grad():
|
||||
output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
|
||||
response = tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
```
|
||||
|
||||
## Citation
|
||||
If you find PLLaMa useful in your research, please cite the following paper:
|
||||
|
||||
```latex
|
||||
@inproceedings{Yang2024PLLaMaAO,
|
||||
title={PLLaMa: An Open-source Large Language Model for Plant Science},
|
||||
author={Xianjun Yang and Junfeng Gao and Wenxin Xue and Erik Alexandersson},
|
||||
year={2024},
|
||||
url={https://api.semanticscholar.org/CorpusID:266741610}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "/mnt/dsss_data/xianjun/project_data/plant_llama2_13b",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"end_token_id": 2,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.28.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.28.1"
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5de0899e0453b11cb29e7d9b1815fd893d47afe49dc8df4188fb57ae9fc2ac56
|
||||
size 26031868013
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 1024,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
745
trainer_state.json
Normal file
745
trainer_state.json
Normal file
@@ -0,0 +1,745 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 14.883720930232558,
|
||||
"global_step": 120,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 23.0645,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 18.9746,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.37,
|
||||
"learning_rate": 7.924812503605782e-06,
|
||||
"loss": 18.9805,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 10.9014,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 3.501,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.74,
|
||||
"learning_rate": 9.913793103448277e-06,
|
||||
"loss": 2.9929,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.87,
|
||||
"learning_rate": 9.827586206896553e-06,
|
||||
"loss": 2.4647,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.99,
|
||||
"learning_rate": 9.741379310344829e-06,
|
||||
"loss": 2.2385,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 1.12,
|
||||
"learning_rate": 9.655172413793105e-06,
|
||||
"loss": 2.0122,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 1.24,
|
||||
"learning_rate": 9.56896551724138e-06,
|
||||
"loss": 1.7836,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 1.36,
|
||||
"learning_rate": 9.482758620689655e-06,
|
||||
"loss": 1.7567,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 1.49,
|
||||
"learning_rate": 9.396551724137931e-06,
|
||||
"loss": 1.6985,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 1.61,
|
||||
"learning_rate": 9.310344827586207e-06,
|
||||
"loss": 1.726,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 1.74,
|
||||
"learning_rate": 9.224137931034484e-06,
|
||||
"loss": 1.7654,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 1.86,
|
||||
"learning_rate": 9.13793103448276e-06,
|
||||
"loss": 1.6182,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 1.98,
|
||||
"learning_rate": 9.051724137931036e-06,
|
||||
"loss": 1.7335,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 2.11,
|
||||
"learning_rate": 8.965517241379312e-06,
|
||||
"loss": 1.6503,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 2.23,
|
||||
"learning_rate": 8.879310344827588e-06,
|
||||
"loss": 1.6674,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 2.36,
|
||||
"learning_rate": 8.793103448275862e-06,
|
||||
"loss": 1.5766,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 2.48,
|
||||
"learning_rate": 8.706896551724138e-06,
|
||||
"loss": 1.4727,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 2.6,
|
||||
"learning_rate": 8.620689655172414e-06,
|
||||
"loss": 1.5703,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 2.73,
|
||||
"learning_rate": 8.53448275862069e-06,
|
||||
"loss": 1.5568,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 2.85,
|
||||
"learning_rate": 8.448275862068966e-06,
|
||||
"loss": 1.4897,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 2.98,
|
||||
"learning_rate": 8.362068965517242e-06,
|
||||
"loss": 1.5204,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 3.1,
|
||||
"learning_rate": 8.275862068965518e-06,
|
||||
"loss": 1.3769,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 3.22,
|
||||
"learning_rate": 8.189655172413794e-06,
|
||||
"loss": 1.3522,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 3.35,
|
||||
"learning_rate": 8.103448275862069e-06,
|
||||
"loss": 1.3126,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 3.47,
|
||||
"learning_rate": 8.017241379310345e-06,
|
||||
"loss": 1.2707,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 3.6,
|
||||
"learning_rate": 7.93103448275862e-06,
|
||||
"loss": 1.2974,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 3.72,
|
||||
"learning_rate": 7.844827586206897e-06,
|
||||
"loss": 1.3587,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 3.84,
|
||||
"learning_rate": 7.758620689655173e-06,
|
||||
"loss": 1.3098,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 3.97,
|
||||
"learning_rate": 7.672413793103449e-06,
|
||||
"loss": 1.3593,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 4.09,
|
||||
"learning_rate": 7.586206896551724e-06,
|
||||
"loss": 1.0844,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 4.22,
|
||||
"learning_rate": 7.500000000000001e-06,
|
||||
"loss": 1.1842,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 4.34,
|
||||
"learning_rate": 7.413793103448277e-06,
|
||||
"loss": 1.095,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 4.47,
|
||||
"learning_rate": 7.327586206896552e-06,
|
||||
"loss": 1.0719,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 4.59,
|
||||
"learning_rate": 7.241379310344828e-06,
|
||||
"loss": 1.1342,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 4.71,
|
||||
"learning_rate": 7.155172413793104e-06,
|
||||
"loss": 1.1034,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 4.84,
|
||||
"learning_rate": 7.0689655172413796e-06,
|
||||
"loss": 1.0181,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 4.96,
|
||||
"learning_rate": 6.982758620689656e-06,
|
||||
"loss": 1.0376,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 5.09,
|
||||
"learning_rate": 6.896551724137932e-06,
|
||||
"loss": 0.9732,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 5.21,
|
||||
"learning_rate": 6.810344827586207e-06,
|
||||
"loss": 0.963,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 5.33,
|
||||
"learning_rate": 6.724137931034484e-06,
|
||||
"loss": 0.8425,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 5.46,
|
||||
"learning_rate": 6.63793103448276e-06,
|
||||
"loss": 0.8646,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 5.58,
|
||||
"learning_rate": 6.551724137931035e-06,
|
||||
"loss": 0.8498,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 5.71,
|
||||
"learning_rate": 6.465517241379311e-06,
|
||||
"loss": 0.8618,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 5.83,
|
||||
"learning_rate": 6.379310344827587e-06,
|
||||
"loss": 0.8139,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 5.95,
|
||||
"learning_rate": 6.293103448275862e-06,
|
||||
"loss": 0.7988,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 6.08,
|
||||
"learning_rate": 6.206896551724138e-06,
|
||||
"loss": 0.7165,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 6.2,
|
||||
"learning_rate": 6.1206896551724135e-06,
|
||||
"loss": 0.7268,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 6.33,
|
||||
"learning_rate": 6.03448275862069e-06,
|
||||
"loss": 0.6033,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 6.45,
|
||||
"learning_rate": 5.9482758620689665e-06,
|
||||
"loss": 0.6308,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 6.57,
|
||||
"learning_rate": 5.862068965517242e-06,
|
||||
"loss": 0.7198,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 6.7,
|
||||
"learning_rate": 5.775862068965518e-06,
|
||||
"loss": 0.6517,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 6.82,
|
||||
"learning_rate": 5.689655172413794e-06,
|
||||
"loss": 0.6819,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 6.95,
|
||||
"learning_rate": 5.603448275862069e-06,
|
||||
"loss": 0.588,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 7.07,
|
||||
"learning_rate": 5.517241379310345e-06,
|
||||
"loss": 0.5563,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 7.19,
|
||||
"learning_rate": 5.431034482758621e-06,
|
||||
"loss": 0.5104,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 7.32,
|
||||
"learning_rate": 5.344827586206896e-06,
|
||||
"loss": 0.4967,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 7.44,
|
||||
"learning_rate": 5.258620689655173e-06,
|
||||
"loss": 0.5056,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 7.57,
|
||||
"learning_rate": 5.172413793103449e-06,
|
||||
"loss": 0.5318,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 7.69,
|
||||
"learning_rate": 5.086206896551724e-06,
|
||||
"loss": 0.4791,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 7.81,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.4324,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 7.94,
|
||||
"learning_rate": 4.9137931034482765e-06,
|
||||
"loss": 0.4274,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 8.06,
|
||||
"learning_rate": 4.8275862068965525e-06,
|
||||
"loss": 0.3601,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 8.19,
|
||||
"learning_rate": 4.741379310344828e-06,
|
||||
"loss": 0.3549,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 8.31,
|
||||
"learning_rate": 4.655172413793104e-06,
|
||||
"loss": 0.375,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 8.43,
|
||||
"learning_rate": 4.56896551724138e-06,
|
||||
"loss": 0.3297,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 8.56,
|
||||
"learning_rate": 4.482758620689656e-06,
|
||||
"loss": 0.3315,
|
||||
"step": 69
|
||||
},
|
||||
{
|
||||
"epoch": 8.68,
|
||||
"learning_rate": 4.396551724137931e-06,
|
||||
"loss": 0.2843,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 8.81,
|
||||
"learning_rate": 4.310344827586207e-06,
|
||||
"loss": 0.2527,
|
||||
"step": 71
|
||||
},
|
||||
{
|
||||
"epoch": 8.93,
|
||||
"learning_rate": 4.224137931034483e-06,
|
||||
"loss": 0.3456,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 9.05,
|
||||
"learning_rate": 4.137931034482759e-06,
|
||||
"loss": 0.2933,
|
||||
"step": 73
|
||||
},
|
||||
{
|
||||
"epoch": 9.18,
|
||||
"learning_rate": 4.051724137931034e-06,
|
||||
"loss": 0.2468,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 9.3,
|
||||
"learning_rate": 3.96551724137931e-06,
|
||||
"loss": 0.1867,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 9.43,
|
||||
"learning_rate": 3.8793103448275865e-06,
|
||||
"loss": 0.2012,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 9.55,
|
||||
"learning_rate": 3.793103448275862e-06,
|
||||
"loss": 0.2075,
|
||||
"step": 77
|
||||
},
|
||||
{
|
||||
"epoch": 9.67,
|
||||
"learning_rate": 3.7068965517241385e-06,
|
||||
"loss": 0.1893,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 9.8,
|
||||
"learning_rate": 3.620689655172414e-06,
|
||||
"loss": 0.1635,
|
||||
"step": 79
|
||||
},
|
||||
{
|
||||
"epoch": 9.92,
|
||||
"learning_rate": 3.5344827586206898e-06,
|
||||
"loss": 0.1839,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 10.05,
|
||||
"learning_rate": 3.448275862068966e-06,
|
||||
"loss": 0.1912,
|
||||
"step": 81
|
||||
},
|
||||
{
|
||||
"epoch": 10.17,
|
||||
"learning_rate": 3.362068965517242e-06,
|
||||
"loss": 0.1388,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 10.29,
|
||||
"learning_rate": 3.2758620689655175e-06,
|
||||
"loss": 0.1337,
|
||||
"step": 83
|
||||
},
|
||||
{
|
||||
"epoch": 10.42,
|
||||
"learning_rate": 3.1896551724137935e-06,
|
||||
"loss": 0.1114,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 10.54,
|
||||
"learning_rate": 3.103448275862069e-06,
|
||||
"loss": 0.163,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 10.67,
|
||||
"learning_rate": 3.017241379310345e-06,
|
||||
"loss": 0.0887,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 10.79,
|
||||
"learning_rate": 2.931034482758621e-06,
|
||||
"loss": 0.1345,
|
||||
"step": 87
|
||||
},
|
||||
{
|
||||
"epoch": 10.91,
|
||||
"learning_rate": 2.844827586206897e-06,
|
||||
"loss": 0.1339,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 11.04,
|
||||
"learning_rate": 2.7586206896551725e-06,
|
||||
"loss": 0.1189,
|
||||
"step": 89
|
||||
},
|
||||
{
|
||||
"epoch": 11.16,
|
||||
"learning_rate": 2.672413793103448e-06,
|
||||
"loss": 0.1183,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 11.29,
|
||||
"learning_rate": 2.5862068965517246e-06,
|
||||
"loss": 0.1001,
|
||||
"step": 91
|
||||
},
|
||||
{
|
||||
"epoch": 11.41,
|
||||
"learning_rate": 2.5e-06,
|
||||
"loss": 0.0891,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 11.53,
|
||||
"learning_rate": 2.4137931034482762e-06,
|
||||
"loss": 0.087,
|
||||
"step": 93
|
||||
},
|
||||
{
|
||||
"epoch": 11.66,
|
||||
"learning_rate": 2.327586206896552e-06,
|
||||
"loss": 0.0697,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 11.78,
|
||||
"learning_rate": 2.241379310344828e-06,
|
||||
"loss": 0.0597,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 11.91,
|
||||
"learning_rate": 2.1551724137931035e-06,
|
||||
"loss": 0.0524,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 12.03,
|
||||
"learning_rate": 2.0689655172413796e-06,
|
||||
"loss": 0.0555,
|
||||
"step": 97
|
||||
},
|
||||
{
|
||||
"epoch": 12.16,
|
||||
"learning_rate": 1.982758620689655e-06,
|
||||
"loss": 0.0559,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 12.28,
|
||||
"learning_rate": 1.896551724137931e-06,
|
||||
"loss": 0.0588,
|
||||
"step": 99
|
||||
},
|
||||
{
|
||||
"epoch": 12.4,
|
||||
"learning_rate": 1.810344827586207e-06,
|
||||
"loss": 0.0519,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 12.53,
|
||||
"learning_rate": 1.724137931034483e-06,
|
||||
"loss": 0.0494,
|
||||
"step": 101
|
||||
},
|
||||
{
|
||||
"epoch": 12.65,
|
||||
"learning_rate": 1.6379310344827587e-06,
|
||||
"loss": 0.0445,
|
||||
"step": 102
|
||||
},
|
||||
{
|
||||
"epoch": 12.78,
|
||||
"learning_rate": 1.5517241379310346e-06,
|
||||
"loss": 0.0465,
|
||||
"step": 103
|
||||
},
|
||||
{
|
||||
"epoch": 12.9,
|
||||
"learning_rate": 1.4655172413793104e-06,
|
||||
"loss": 0.0459,
|
||||
"step": 104
|
||||
},
|
||||
{
|
||||
"epoch": 13.02,
|
||||
"learning_rate": 1.3793103448275862e-06,
|
||||
"loss": 0.0444,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 13.15,
|
||||
"learning_rate": 1.2931034482758623e-06,
|
||||
"loss": 0.0359,
|
||||
"step": 106
|
||||
},
|
||||
{
|
||||
"epoch": 13.27,
|
||||
"learning_rate": 1.2068965517241381e-06,
|
||||
"loss": 0.0385,
|
||||
"step": 107
|
||||
},
|
||||
{
|
||||
"epoch": 13.4,
|
||||
"learning_rate": 1.120689655172414e-06,
|
||||
"loss": 0.0337,
|
||||
"step": 108
|
||||
},
|
||||
{
|
||||
"epoch": 13.52,
|
||||
"learning_rate": 1.0344827586206898e-06,
|
||||
"loss": 0.0354,
|
||||
"step": 109
|
||||
},
|
||||
{
|
||||
"epoch": 13.64,
|
||||
"learning_rate": 9.482758620689655e-07,
|
||||
"loss": 0.0399,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 13.77,
|
||||
"learning_rate": 8.620689655172415e-07,
|
||||
"loss": 0.0314,
|
||||
"step": 111
|
||||
},
|
||||
{
|
||||
"epoch": 13.89,
|
||||
"learning_rate": 7.758620689655173e-07,
|
||||
"loss": 0.0419,
|
||||
"step": 112
|
||||
},
|
||||
{
|
||||
"epoch": 14.02,
|
||||
"learning_rate": 6.896551724137931e-07,
|
||||
"loss": 0.0274,
|
||||
"step": 113
|
||||
},
|
||||
{
|
||||
"epoch": 14.14,
|
||||
"learning_rate": 6.034482758620691e-07,
|
||||
"loss": 0.0341,
|
||||
"step": 114
|
||||
},
|
||||
{
|
||||
"epoch": 14.26,
|
||||
"learning_rate": 5.172413793103449e-07,
|
||||
"loss": 0.0229,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 14.39,
|
||||
"learning_rate": 4.3103448275862073e-07,
|
||||
"loss": 0.0275,
|
||||
"step": 116
|
||||
},
|
||||
{
|
||||
"epoch": 14.51,
|
||||
"learning_rate": 3.4482758620689656e-07,
|
||||
"loss": 0.0285,
|
||||
"step": 117
|
||||
},
|
||||
{
|
||||
"epoch": 14.64,
|
||||
"learning_rate": 2.5862068965517245e-07,
|
||||
"loss": 0.0228,
|
||||
"step": 118
|
||||
},
|
||||
{
|
||||
"epoch": 14.76,
|
||||
"learning_rate": 1.7241379310344828e-07,
|
||||
"loss": 0.0233,
|
||||
"step": 119
|
||||
},
|
||||
{
|
||||
"epoch": 14.88,
|
||||
"learning_rate": 8.620689655172414e-08,
|
||||
"loss": 0.026,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 14.88,
|
||||
"step": 120,
|
||||
"total_flos": 27811624222720.0,
|
||||
"train_loss": 1.2693956012527148,
|
||||
"train_runtime": 9579.7606,
|
||||
"train_samples_per_second": 1.613,
|
||||
"train_steps_per_second": 0.013
|
||||
}
|
||||
],
|
||||
"max_steps": 120,
|
||||
"num_train_epochs": 15,
|
||||
"total_flos": 27811624222720.0,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5101fa7c888f87ca249770953c92d119dee90cb8aaea4dad9672f30b5b180f60
|
||||
size 4923
|
||||
Reference in New Issue
Block a user