初始化项目，由ModelHub XC社区提供模型
Model: artificialguybr/llama3-8b-alpacadata-ptbr 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
|
||||
166
README.md
Normal file
166
README.md
Normal file
@@ -0,0 +1,166 @@
|
||||
---
|
||||
license: other
|
||||
base_model: NousResearch/Meta-Llama-3-8B
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: out-llama8b-alpaca-data-pt-br
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
||||
<details><summary>See axolotl config</summary>
|
||||
|
||||
axolotl version: `0.4.0`
|
||||
```yaml
|
||||
base_model: NousResearch/Meta-Llama-3-8B
|
||||
model_type: LlamaForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: false
|
||||
strict: false
|
||||
|
||||
datasets:
|
||||
- path: dominguesm/alpaca-data-pt-br
|
||||
type: alpaca
|
||||
dataset_prepared_path: last_run_prepared
|
||||
val_set_size: 0.05
|
||||
output_dir: ./out-llama8b-alpaca-data-pt-br
|
||||
|
||||
sequence_len: 8192
|
||||
sample_packing: true
|
||||
pad_to_sequence_len: true
|
||||
|
||||
wandb_project: meta-llama-8b-alpacadata-br
|
||||
wandb_entity:
|
||||
wandb_watch:
|
||||
wandb_name:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 8
|
||||
micro_batch_size: 1
|
||||
num_epochs: 2
|
||||
optimizer: paged_adamw_8bit
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 2e-5
|
||||
|
||||
train_on_inputs: false
|
||||
group_by_length: false
|
||||
bf16: auto
|
||||
fp16:
|
||||
tf32: false
|
||||
|
||||
gradient_checkpointing: true
|
||||
gradient_checkpointing_kwargs:
|
||||
use_reentrant: false
|
||||
early_stopping_patience:
|
||||
resume_from_checkpoint:
|
||||
logging_steps: 1
|
||||
xformers_attention:
|
||||
flash_attention: true
|
||||
|
||||
warmup_steps: 100
|
||||
evals_per_epoch: 2
|
||||
eval_table_size:
|
||||
saves_per_epoch: 1
|
||||
debug:
|
||||
|
||||
---
|
||||
### 🌐 Website
|
||||
You can find more of my models, projects, and information on my official website:
|
||||
- **[artificialguy.com](https://artificialguy.com/)**
|
||||
|
||||
|
||||
### 🚀 Prompt Hub
|
||||
Need high-quality prompts for image models and LLMs? Explore **[findgoodprompt.com](https://findgoodprompt.com)**.
|
||||
### 💖 Support My Work
|
||||
If you find this model useful, please consider supporting my work. It helps me cover server costs and dedicate more time to new open-source projects.
|
||||
- **Patreon:** [Support on Patreon](https://www.patreon.com/user?u=81570187)
|
||||
- **Ko-fi:** [Buy me a Ko-fi](https://ko-fi.com/artificialguybr)
|
||||
- **Buy Me a Coffee:** [Buy me a Coffee](https://buymeacoffee.com/jvkape)
|
||||
deepspeed:
|
||||
weight_decay: 0.0
|
||||
fsdp:
|
||||
fsdp_config:
|
||||
special_tokens:
|
||||
pad_token: <|end_of_text|>
|
||||
|
||||
```
|
||||
|
||||
</details><br>
|
||||
|
||||
# LLama 3- 8B -alpaca-data-pt-br
|
||||
|
||||
Thanks to [Redmond.ai](https://redmond.ai) for the GPU Support!
|
||||
|
||||
This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) on the [dominguesm/alpaca-data-pt-br](https://huggingface.co/dominguesm/alpaca-data-pt-br) dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 1.1227
|
||||
|
||||
## Model description
|
||||
|
||||
The model is a Portuguese language understanding model designed to generate responses to a wide range of questions and prompts. It takes as input a natural language question or prompt and outputs a corresponding response.
|
||||
|
||||
The model is trained on a dataset of 51k examples, which is a cleaned and translated version of the original Alpaca Dataset released by Stanford. The original dataset was translated to Portuguese (Brazil) to provide a more culturally and linguistically relevant resource for the Brazilian market.
|
||||
|
||||
The dataset was carefully reviewed to identify and fix issues present in the original release, ensuring that the model is trained on high-quality data. The model is intended to be used in applications where a deep understanding of Portuguese language is required, such as chatbots, virtual assistants, and language translation systems.
|
||||
|
||||
## Intended uses:
|
||||
|
||||
Generating responses to natural language questions and prompts in Portuguese
|
||||
|
||||
Supporting chatbots, virtual assistants, and other conversational AI applications
|
||||
|
||||
Enhancing language translation systems and machine translation models
|
||||
|
||||
Providing a culturally and linguistically relevant resource for the Brazilian market
|
||||
|
||||
## Limitations
|
||||
|
||||
The model may not generalize well to other languages or dialects
|
||||
|
||||
The model may not perform well on out-of-domain or unseen topics
|
||||
|
||||
The model may not be able to handle ambiguous or open-ended prompts
|
||||
|
||||
The model may not be able to understand nuances of regional dialects or slang
|
||||
|
||||
The model may not be able to handle prompts that require common sense or real-world knowledge
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 1
|
||||
- seed: 42
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 8
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_steps: 100
|
||||
- num_epochs: 2
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 1.382 | 0.01 | 1 | 1.4056 |
|
||||
| 1.1762 | 0.5 | 45 | 1.1987 |
|
||||
| 1.1294 | 0.99 | 90 | 1.1493 |
|
||||
| 1.0028 | 1.47 | 135 | 1.1331 |
|
||||
| 0.9899 | 1.97 | 180 | 1.1227 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.40.0.dev0
|
||||
- Pytorch 2.2.2+cu121
|
||||
- Datasets 2.15.0
|
||||
- Tokenizers 0.15.0
|
||||
28
checkpoint-180/config.json
Normal file
28
checkpoint-180/config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "NousResearch/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
7
checkpoint-180/generation_config.json
Normal file
7
checkpoint-180/generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
3
checkpoint-180/model-00001-of-00004.safetensors
Normal file
3
checkpoint-180/model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de52db8a664771470d847372869b5c9853396e5b21ee841a36f94bab28001da2
|
||||
size 4976698672
|
||||
3
checkpoint-180/model-00002-of-00004.safetensors
Normal file
3
checkpoint-180/model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8a24e6007ff22ef9b28c584a5f81b1bf44f70a126d01ea781b9e5dc4804007f
|
||||
size 4999802720
|
||||
3
checkpoint-180/model-00003-of-00004.safetensors
Normal file
3
checkpoint-180/model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d53fae81fffe01c7caa83a64419218fe009bc8c9f9b320fb9cf8cff4d7002f51
|
||||
size 4915916176
|
||||
3
checkpoint-180/model-00004-of-00004.safetensors
Normal file
3
checkpoint-180/model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:81c2d00233084250cdcf2d5aadc541cf91895747bba842e114ee6cd90c9e74fb
|
||||
size 1168138808
|
||||
298
checkpoint-180/model.safetensors.index.json
Normal file
298
checkpoint-180/model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
checkpoint-180/optimizer.pt
Normal file
3
checkpoint-180/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7d24226eb0945856a951567e81f1c65b53ebcaa9e8053518d2d38875b7900d38
|
||||
size 16092246776
|
||||
3
checkpoint-180/rng_state.pth
Normal file
3
checkpoint-180/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69f50a692634404f2eebb2eab9f456865957578d752987bc52d843ac2a774366
|
||||
size 14244
|
||||
3
checkpoint-180/scheduler.pt
Normal file
3
checkpoint-180/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cdedb329af76c1335197d88196cc60f4b325357651904eaa9720d5e1cde97438
|
||||
size 1064
|
||||
23
checkpoint-180/special_tokens_map.json
Normal file
23
checkpoint-180/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410503
checkpoint-180/tokenizer.json
Normal file
410503
checkpoint-180/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2063
checkpoint-180/tokenizer_config.json
Normal file
2063
checkpoint-180/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
1321
checkpoint-180/trainer_state.json
Normal file
1321
checkpoint-180/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-180/training_args.bin
Normal file
3
checkpoint-180/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e0fdc27db5220d5f47af0520c93bd5ecc605dc87a55ea4f6776c46f34cf66343
|
||||
size 5816
|
||||
28
checkpoint-90/config.json
Normal file
28
checkpoint-90/config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "NousResearch/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
7
checkpoint-90/generation_config.json
Normal file
7
checkpoint-90/generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
3
checkpoint-90/model-00001-of-00004.safetensors
Normal file
3
checkpoint-90/model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5bc176bf4a7e3a4b680cf74dc2d1ce2ec4649f5d4ecd0fefb5cd8ba2f96efeca
|
||||
size 4976698672
|
||||
3
checkpoint-90/model-00002-of-00004.safetensors
Normal file
3
checkpoint-90/model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f2d2341fdcfdf5242f18914df238201f64de4755e1603c1bf2694c59c3df693
|
||||
size 4999802720
|
||||
3
checkpoint-90/model-00003-of-00004.safetensors
Normal file
3
checkpoint-90/model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42b554737bcebcb5312f3539c3b529c07c8a501fa3ffcaf21ccf5eedf62bae2f
|
||||
size 4915916176
|
||||
3
checkpoint-90/model-00004-of-00004.safetensors
Normal file
3
checkpoint-90/model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7e38cab5e22f7f927b2b24e8cf9902543e0a6a1ab4ced65cec56fec4f99273f
|
||||
size 1168138808
|
||||
298
checkpoint-90/model.safetensors.index.json
Normal file
298
checkpoint-90/model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
checkpoint-90/optimizer.pt
Normal file
3
checkpoint-90/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f2a0f19218984f1c425b9a91ea940dff7ebd7d296624656fea9dadfa95f1e9f
|
||||
size 16092246776
|
||||
3
checkpoint-90/rng_state.pth
Normal file
3
checkpoint-90/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
||||
size 14244
|
||||
3
checkpoint-90/scheduler.pt
Normal file
3
checkpoint-90/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0720d6dfee836a6eadcbf864c97a380ace86a2e8beaba0fedf432fc801c02cf5
|
||||
size 1064
|
||||
23
checkpoint-90/special_tokens_map.json
Normal file
23
checkpoint-90/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410503
checkpoint-90/tokenizer.json
Normal file
410503
checkpoint-90/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2063
checkpoint-90/tokenizer_config.json
Normal file
2063
checkpoint-90/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
675
checkpoint-90/trainer_state.json
Normal file
675
checkpoint-90/trainer_state.json
Normal file
@@ -0,0 +1,675 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.994475138121547,
|
||||
"eval_steps": 45,
|
||||
"global_step": 90,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"grad_norm": 10.25,
|
||||
"learning_rate": 2.0000000000000002e-07,
|
||||
"loss": 1.382,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"eval_loss": 1.4056271314620972,
|
||||
"eval_runtime": 26.9519,
|
||||
"eval_samples_per_second": 96.023,
|
||||
"eval_steps_per_second": 96.023,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"grad_norm": 10.625,
|
||||
"learning_rate": 4.0000000000000003e-07,
|
||||
"loss": 1.3855,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.03,
|
||||
"grad_norm": 10.625,
|
||||
"learning_rate": 6.000000000000001e-07,
|
||||
"loss": 1.4042,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.04,
|
||||
"grad_norm": 10.25,
|
||||
"learning_rate": 8.000000000000001e-07,
|
||||
"loss": 1.4277,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"grad_norm": 10.375,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 1.3786,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.07,
|
||||
"grad_norm": 9.625,
|
||||
"learning_rate": 1.2000000000000002e-06,
|
||||
"loss": 1.3671,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"grad_norm": 8.8125,
|
||||
"learning_rate": 1.4000000000000001e-06,
|
||||
"loss": 1.3566,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.09,
|
||||
"grad_norm": 8.5625,
|
||||
"learning_rate": 1.6000000000000001e-06,
|
||||
"loss": 1.3815,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"grad_norm": 7.46875,
|
||||
"learning_rate": 1.8000000000000001e-06,
|
||||
"loss": 1.3631,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.11,
|
||||
"grad_norm": 7.28125,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 1.358,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"grad_norm": 6.53125,
|
||||
"learning_rate": 2.2e-06,
|
||||
"loss": 1.3416,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.13,
|
||||
"grad_norm": 5.46875,
|
||||
"learning_rate": 2.4000000000000003e-06,
|
||||
"loss": 1.3489,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.14,
|
||||
"grad_norm": 4.90625,
|
||||
"learning_rate": 2.6e-06,
|
||||
"loss": 1.298,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"grad_norm": 4.75,
|
||||
"learning_rate": 2.8000000000000003e-06,
|
||||
"loss": 1.2632,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.17,
|
||||
"grad_norm": 4.1875,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 1.2835,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.18,
|
||||
"grad_norm": 3.671875,
|
||||
"learning_rate": 3.2000000000000003e-06,
|
||||
"loss": 1.2846,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"grad_norm": 3.078125,
|
||||
"learning_rate": 3.4000000000000005e-06,
|
||||
"loss": 1.2776,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"grad_norm": 3.546875,
|
||||
"learning_rate": 3.6000000000000003e-06,
|
||||
"loss": 1.259,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.21,
|
||||
"grad_norm": 3.71875,
|
||||
"learning_rate": 3.8000000000000005e-06,
|
||||
"loss": 1.235,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.22,
|
||||
"grad_norm": 4.21875,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 1.2551,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"grad_norm": 2.90625,
|
||||
"learning_rate": 4.2000000000000004e-06,
|
||||
"loss": 1.2587,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.24,
|
||||
"grad_norm": 2.6875,
|
||||
"learning_rate": 4.4e-06,
|
||||
"loss": 1.2888,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"grad_norm": 3.28125,
|
||||
"learning_rate": 4.600000000000001e-06,
|
||||
"loss": 1.1968,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.27,
|
||||
"grad_norm": 2.875,
|
||||
"learning_rate": 4.800000000000001e-06,
|
||||
"loss": 1.2625,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"grad_norm": 2.40625,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 1.1868,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.29,
|
||||
"grad_norm": 2.328125,
|
||||
"learning_rate": 5.2e-06,
|
||||
"loss": 1.2694,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"grad_norm": 2.59375,
|
||||
"learning_rate": 5.400000000000001e-06,
|
||||
"loss": 1.2459,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"grad_norm": 2.328125,
|
||||
"learning_rate": 5.600000000000001e-06,
|
||||
"loss": 1.2338,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"grad_norm": 2.125,
|
||||
"learning_rate": 5.8e-06,
|
||||
"loss": 1.2317,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.33,
|
||||
"grad_norm": 2.171875,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 1.2246,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"grad_norm": 2.09375,
|
||||
"learning_rate": 6.200000000000001e-06,
|
||||
"loss": 1.2437,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.35,
|
||||
"grad_norm": 2.0625,
|
||||
"learning_rate": 6.4000000000000006e-06,
|
||||
"loss": 1.2344,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"grad_norm": 2.078125,
|
||||
"learning_rate": 6.600000000000001e-06,
|
||||
"loss": 1.2157,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"grad_norm": 2.171875,
|
||||
"learning_rate": 6.800000000000001e-06,
|
||||
"loss": 1.1672,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"grad_norm": 2.03125,
|
||||
"learning_rate": 7e-06,
|
||||
"loss": 1.1638,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 7.2000000000000005e-06,
|
||||
"loss": 1.1659,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 0.41,
|
||||
"grad_norm": 2.265625,
|
||||
"learning_rate": 7.4e-06,
|
||||
"loss": 1.2027,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.42,
|
||||
"grad_norm": 2.125,
|
||||
"learning_rate": 7.600000000000001e-06,
|
||||
"loss": 1.2126,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.43,
|
||||
"grad_norm": 1.921875,
|
||||
"learning_rate": 7.800000000000002e-06,
|
||||
"loss": 1.1615,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 8.000000000000001e-06,
|
||||
"loss": 1.1843,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.45,
|
||||
"grad_norm": 2.0,
|
||||
"learning_rate": 8.2e-06,
|
||||
"loss": 1.2071,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.46,
|
||||
"grad_norm": 2.078125,
|
||||
"learning_rate": 8.400000000000001e-06,
|
||||
"loss": 1.1488,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 8.6e-06,
|
||||
"loss": 1.1812,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"grad_norm": 1.96875,
|
||||
"learning_rate": 8.8e-06,
|
||||
"loss": 1.1694,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 2.28125,
|
||||
"learning_rate": 9e-06,
|
||||
"loss": 1.1762,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"eval_loss": 1.1987459659576416,
|
||||
"eval_runtime": 27.0775,
|
||||
"eval_samples_per_second": 95.578,
|
||||
"eval_steps_per_second": 95.578,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.51,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 9.200000000000002e-06,
|
||||
"loss": 1.1775,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 9.4e-06,
|
||||
"loss": 1.1948,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.53,
|
||||
"grad_norm": 2.03125,
|
||||
"learning_rate": 9.600000000000001e-06,
|
||||
"loss": 1.2011,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"grad_norm": 1.9375,
|
||||
"learning_rate": 9.800000000000001e-06,
|
||||
"loss": 1.1742,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 0.55,
|
||||
"grad_norm": 2.1875,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 1.1784,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"grad_norm": 2.109375,
|
||||
"learning_rate": 1.02e-05,
|
||||
"loss": 1.1725,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 0.57,
|
||||
"grad_norm": 2.203125,
|
||||
"learning_rate": 1.04e-05,
|
||||
"loss": 1.1532,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 0.59,
|
||||
"grad_norm": 2.125,
|
||||
"learning_rate": 1.0600000000000002e-05,
|
||||
"loss": 1.1359,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"grad_norm": 1.9765625,
|
||||
"learning_rate": 1.0800000000000002e-05,
|
||||
"loss": 1.1602,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 0.61,
|
||||
"grad_norm": 2.109375,
|
||||
"learning_rate": 1.1000000000000001e-05,
|
||||
"loss": 1.1536,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"grad_norm": 1.96875,
|
||||
"learning_rate": 1.1200000000000001e-05,
|
||||
"loss": 1.1599,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"grad_norm": 2.21875,
|
||||
"learning_rate": 1.14e-05,
|
||||
"loss": 1.1479,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 2.25,
|
||||
"learning_rate": 1.16e-05,
|
||||
"loss": 1.1662,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"grad_norm": 1.984375,
|
||||
"learning_rate": 1.18e-05,
|
||||
"loss": 1.1606,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 0.66,
|
||||
"grad_norm": 2.0625,
|
||||
"learning_rate": 1.2e-05,
|
||||
"loss": 1.1694,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"grad_norm": 2.0625,
|
||||
"learning_rate": 1.22e-05,
|
||||
"loss": 1.1647,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 0.69,
|
||||
"grad_norm": 2.1875,
|
||||
"learning_rate": 1.2400000000000002e-05,
|
||||
"loss": 1.1458,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 1.2600000000000001e-05,
|
||||
"loss": 1.1522,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 0.71,
|
||||
"grad_norm": 1.859375,
|
||||
"learning_rate": 1.2800000000000001e-05,
|
||||
"loss": 1.1335,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 0.72,
|
||||
"grad_norm": 2.09375,
|
||||
"learning_rate": 1.3000000000000001e-05,
|
||||
"loss": 1.1563,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.73,
|
||||
"grad_norm": 1.8828125,
|
||||
"learning_rate": 1.3200000000000002e-05,
|
||||
"loss": 1.1619,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 0.74,
|
||||
"grad_norm": 1.96875,
|
||||
"learning_rate": 1.3400000000000002e-05,
|
||||
"loss": 1.1745,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"grad_norm": 2.03125,
|
||||
"learning_rate": 1.3600000000000002e-05,
|
||||
"loss": 1.1807,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 0.76,
|
||||
"grad_norm": 1.9921875,
|
||||
"learning_rate": 1.38e-05,
|
||||
"loss": 1.168,
|
||||
"step": 69
|
||||
},
|
||||
{
|
||||
"epoch": 0.77,
|
||||
"grad_norm": 2.046875,
|
||||
"learning_rate": 1.4e-05,
|
||||
"loss": 1.1797,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.78,
|
||||
"grad_norm": 2.0,
|
||||
"learning_rate": 1.4200000000000001e-05,
|
||||
"loss": 1.1521,
|
||||
"step": 71
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"grad_norm": 1.9453125,
|
||||
"learning_rate": 1.4400000000000001e-05,
|
||||
"loss": 1.1588,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 0.81,
|
||||
"grad_norm": 1.9609375,
|
||||
"learning_rate": 1.46e-05,
|
||||
"loss": 1.1476,
|
||||
"step": 73
|
||||
},
|
||||
{
|
||||
"epoch": 0.82,
|
||||
"grad_norm": 2.03125,
|
||||
"learning_rate": 1.48e-05,
|
||||
"loss": 1.1619,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 0.83,
|
||||
"grad_norm": 1.96875,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 1.134,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.84,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 1.5200000000000002e-05,
|
||||
"loss": 1.1719,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 0.85,
|
||||
"grad_norm": 2.0,
|
||||
"learning_rate": 1.54e-05,
|
||||
"loss": 1.1329,
|
||||
"step": 77
|
||||
},
|
||||
{
|
||||
"epoch": 0.86,
|
||||
"grad_norm": 1.9765625,
|
||||
"learning_rate": 1.5600000000000003e-05,
|
||||
"loss": 1.138,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 0.87,
|
||||
"grad_norm": 1.96875,
|
||||
"learning_rate": 1.58e-05,
|
||||
"loss": 1.1076,
|
||||
"step": 79
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"grad_norm": 2.078125,
|
||||
"learning_rate": 1.6000000000000003e-05,
|
||||
"loss": 1.1485,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.9,
|
||||
"grad_norm": 2.0,
|
||||
"learning_rate": 1.62e-05,
|
||||
"loss": 1.1164,
|
||||
"step": 81
|
||||
},
|
||||
{
|
||||
"epoch": 0.91,
|
||||
"grad_norm": 2.0625,
|
||||
"learning_rate": 1.64e-05,
|
||||
"loss": 1.128,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 0.92,
|
||||
"grad_norm": 2.015625,
|
||||
"learning_rate": 1.66e-05,
|
||||
"loss": 1.116,
|
||||
"step": 83
|
||||
},
|
||||
{
|
||||
"epoch": 0.93,
|
||||
"grad_norm": 1.890625,
|
||||
"learning_rate": 1.6800000000000002e-05,
|
||||
"loss": 1.1424,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 0.94,
|
||||
"grad_norm": 1.9375,
|
||||
"learning_rate": 1.7e-05,
|
||||
"loss": 1.0941,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.95,
|
||||
"grad_norm": 2.15625,
|
||||
"learning_rate": 1.72e-05,
|
||||
"loss": 1.1392,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"grad_norm": 2.046875,
|
||||
"learning_rate": 1.7400000000000003e-05,
|
||||
"loss": 1.1303,
|
||||
"step": 87
|
||||
},
|
||||
{
|
||||
"epoch": 0.97,
|
||||
"grad_norm": 2.03125,
|
||||
"learning_rate": 1.76e-05,
|
||||
"loss": 1.1606,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 0.98,
|
||||
"grad_norm": 1.9609375,
|
||||
"learning_rate": 1.7800000000000002e-05,
|
||||
"loss": 1.1234,
|
||||
"step": 89
|
||||
},
|
||||
{
|
||||
"epoch": 0.99,
|
||||
"grad_norm": 2.078125,
|
||||
"learning_rate": 1.8e-05,
|
||||
"loss": 1.1294,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.99,
|
||||
"eval_loss": 1.1493040323257446,
|
||||
"eval_runtime": 27.0758,
|
||||
"eval_samples_per_second": 95.583,
|
||||
"eval_steps_per_second": 95.583,
|
||||
"step": 90
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 180,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 90,
|
||||
"total_flos": 2.6559508138426368e+17,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-90/training_args.bin
Normal file
3
checkpoint-90/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e0fdc27db5220d5f47af0520c93bd5ecc605dc87a55ea4f6776c46f34cf66343
|
||||
size 5816
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "NousResearch/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00004.bin
Normal file
3
pytorch_model-00001-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b91eafca24a7348629416be9beb561e0278ea66611069e037ba8c7b39261c72d
|
||||
size 4976718466
|
||||
3
pytorch_model-00002-of-00004.bin
Normal file
3
pytorch_model-00002-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2b55a5ea09e6f66bd2b806499dd0c271433ad786857ab0a00494076f945e8e6
|
||||
size 4999827718
|
||||
3
pytorch_model-00003-of-00004.bin
Normal file
3
pytorch_model-00003-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:236b28c85281856528b5366671f9f2e2cfad0cf4431906b98d0bdd9313af5d7f
|
||||
size 4915940170
|
||||
3
pytorch_model-00004-of-00004.bin
Normal file
3
pytorch_model-00004-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12a7a7ee4bbdfb28f23220ed3c81b43dd0cc8e0222183593e4e21d16f3a888a7
|
||||
size 1168140873
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"model.norm.weight": "pytorch_model-00004-of-00004.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
410503
tokenizer.json
Normal file
410503
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2063
tokenizer_config.json
Normal file
2063
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user