初始化项目，由ModelHub XC社区提供模型
Model: quicktensor/blockrank-msmarco-mistral-7b 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
|
||||
64
README.md
Normal file
64
README.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
tags:
|
||||
- text-generation
|
||||
- information-retrieval
|
||||
- ranking
|
||||
- reranking
|
||||
- blockrank
|
||||
- mistral
|
||||
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
||||
datasets:
|
||||
- quicktensor/blockrank-msmarco-train-10p
|
||||
metrics:
|
||||
- ndcg
|
||||
- mrr
|
||||
---
|
||||
|
||||
# BlockRank-Mistral-7B: Scalable In-context Ranking with Generative Models
|
||||
|
||||
[](https://colab.research.google.com/github/nilesh2797/BlockRank/blob/main/quickstart.ipynb)
|
||||
|
||||
**BlockRank-Mistral-7B** is a fine-tuned version of [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) optimized for efficient in-context document ranking. It implements BlockRank, a method that makes LLMs efficient and scalable for ranking by aligning their internal attention mechanisms with the structure of the ranking task.
|
||||
|
||||
<p align="center">
|
||||
<img src="https://raw.githubusercontent.com/nilesh2797/BlockRank/main/assets/blockrank_diagram.png" alt="BlockRank Architecture" width="600"/>
|
||||
</p>
|
||||
|
||||
### Key Features
|
||||
|
||||
- **Linear Complexity Attention**: Structured sparse attention reduces complexity from O(n²) to O(n)
|
||||
- **2-4× Faster Inference**: Attention-based scoring eliminates autoregressive decoding
|
||||
- **Auxiliary Contrastive Loss**: Mid-layer contrastive objective improves relevance signals
|
||||
- **Strong Zero-shot Generalization**: SOTA performance on BEIR benchmarks
|
||||
|
||||
## Citation
|
||||
|
||||
If you use this model, please cite:
|
||||
|
||||
```bibtex
|
||||
@article{gupta2025blockrank,
|
||||
title={Scalable In-context Ranking with Generative Models},
|
||||
author={Gupta, Nilesh and You, Chong and Bhojanapalli, Srinadh and Kumar, Sanjiv and Dhillon, Inderjit and Yu, Felix},
|
||||
journal={arXiv preprint arXiv:2510.05396},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
For questions or issues, please open an issue on [GitHub](https://github.com/nilesh2797/BlockRank/issues).
|
||||
|
||||
## Additional Resources
|
||||
|
||||
- **Paper**: [arXiv:2510.05396](https://arxiv.org/abs/2510.05396)
|
||||
- **Code**: [GitHub Repository](https://github.com/nilesh2797/BlockRank)
|
||||
- **Dataset**: [HuggingFace Dataset](https://huggingface.co/datasets/nilesh2797/icr-msmarco-10p-train)
|
||||
- **Demo**: [Colab Notebook](https://colab.research.google.com/github/nilesh2797/BlockRank/blob/main/examples/quickstart.ipynb)
|
||||
|
||||
## License
|
||||
|
||||
This model is released under the MIT License. See [LICENSE](https://github.com/nilesh2797/BlockRank/blob/main/LICENSE) for details.
|
||||
22
all_results.json
Normal file
22
all_results.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"aux_attn_accuracy": 0.9422222224871317,
|
||||
"aux_loss": 0.2298412849009037,
|
||||
"epoch": 1.0,
|
||||
"eval_aux_attn_accuracy": 0.9623015873015873,
|
||||
"eval_aux_loss": 0.17712821468474374,
|
||||
"eval_lm_loss": 0.05031332116535244,
|
||||
"eval_loss": 0.01336627546697855,
|
||||
"eval_mean_token_accuracy": 0.9826168309128473,
|
||||
"eval_runtime": 62.2964,
|
||||
"eval_samples_per_second": 8.042,
|
||||
"eval_steps_per_second": 2.023,
|
||||
"eval_total_loss": 0.06802614390691152,
|
||||
"lm_loss": 0.0855401718375894,
|
||||
"mean_token_accuracy": 0.9700513021151225,
|
||||
"total_flos": 1.066126245903519e+19,
|
||||
"total_loss": 0.10852430010680109,
|
||||
"train_loss": 0.027537114826725155,
|
||||
"train_runtime": 28154.6326,
|
||||
"train_samples_per_second": 1.758,
|
||||
"train_steps_per_second": 0.11
|
||||
}
|
||||
87
chat_template.jinja
Normal file
87
chat_template.jinja
Normal file
@@ -0,0 +1,87 @@
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
||||
|
||||
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
||||
{%- set ns = namespace() %}
|
||||
{%- set ns.index = 0 %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
||||
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
||||
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif %}
|
||||
{%- set ns.index = ns.index + 1 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{{- bos_token }}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message["role"] == "user" %}
|
||||
{%- if tools is not none and (message == user_messages[-1]) %}
|
||||
{{- "[AVAILABLE_TOOLS] [" }}
|
||||
{%- for tool in tools %}
|
||||
{%- set tool = tool.function %}
|
||||
{{- '{"type": "function", "function": {' }}
|
||||
{%- for key, val in tool.items() if key != "return" %}
|
||||
{%- if val is string %}
|
||||
{{- '"' + key + '": "' + val + '"' }}
|
||||
{%- else %}
|
||||
{{- '"' + key + '": ' + val|tojson }}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "}}" }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "[/AVAILABLE_TOOLS]" }}
|
||||
{%- endif %}
|
||||
{%- if loop.last and system_message is defined %}
|
||||
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
||||
{%- else %}
|
||||
{{- "[INST] " + message["content"] + "[/INST]" }}
|
||||
{%- endif %}
|
||||
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
||||
{{- "[TOOL_CALLS] [" }}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- set out = tool_call.function|tojson %}
|
||||
{{- out[:-1] }}
|
||||
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- ', "id": "' + tool_call.id + '"}' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif message["role"] == "assistant" %}
|
||||
{{- " " + message["content"]|trim + eos_token}}
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
||||
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": null,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
12
eval_results.json
Normal file
12
eval_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_aux_attn_accuracy": 0.9623015873015873,
|
||||
"eval_aux_loss": 0.17712821468474374,
|
||||
"eval_lm_loss": 0.05031332116535244,
|
||||
"eval_loss": 0.01336627546697855,
|
||||
"eval_mean_token_accuracy": 0.9826168309128473,
|
||||
"eval_runtime": 62.2964,
|
||||
"eval_samples_per_second": 8.042,
|
||||
"eval_steps_per_second": 2.023,
|
||||
"eval_total_loss": 0.06802614390691152
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
2
|
||||
],
|
||||
"transformers_version": "4.57.0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78e44b403d9a07cd112a11572b79261ec0f889e27ec4d87ba3c9d798f00e2b86
|
||||
size 4949453792
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66fb4a940b30c4ab3ce96751271caec0d46ff92c54f8be2c7a1582123ab16c31
|
||||
size 4999819336
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5ef0e99e9fa7e2c5d13f915e157e4d6b9dafa8f348d2b5a35938c70fcec9513a
|
||||
size 4546807800
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7248023552,
|
||||
"total_size": 14496047104
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
275733
tokenizer.json
Normal file
275733
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
||||
size 587404
|
||||
6187
tokenizer_config.json
Normal file
6187
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
188
train_config.yaml
Normal file
188
train_config.yaml
Normal file
@@ -0,0 +1,188 @@
|
||||
data:
|
||||
data_path: ../data/msmarco/parsed_hard_ids_10p_train.jsonl
|
||||
dataset_seed: 42
|
||||
max_block_length: 160
|
||||
max_seq_length: 6144
|
||||
num_documents: 30
|
||||
qrels_path: null
|
||||
streaming: false
|
||||
train_test_split: 0.99
|
||||
val_data_path: null
|
||||
model:
|
||||
attn_implementation: default_blockrank
|
||||
lora_alpha: -1
|
||||
lora_dropout: 0.0
|
||||
lora_r: -1
|
||||
lora_target_modules: q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj
|
||||
model_name_or_path: /workspace/nilesh_work/hf_cache/Mistral-7B-Instruct-v0.3
|
||||
trust_remote_code: false
|
||||
use_4bit: false
|
||||
use_blockrank: true
|
||||
use_lora: false
|
||||
training:
|
||||
accelerator_config:
|
||||
dispatch_batches: null
|
||||
even_batches: true
|
||||
gradient_accumulation_kwargs: null
|
||||
non_blocking: false
|
||||
split_batches: false
|
||||
use_seedable_sampler: true
|
||||
activation_offloading: false
|
||||
adafactor: false
|
||||
adam_beta1: 0.9
|
||||
adam_beta2: 0.999
|
||||
adam_epsilon: 1.0e-08
|
||||
assistant_only_loss: false
|
||||
auto_find_batch_size: false
|
||||
aux_layer_idx: 20
|
||||
aux_loss_weight: 0.1
|
||||
aux_temperature: 0.05
|
||||
average_tokens_across_devices: true
|
||||
batch_eval_metrics: false
|
||||
bf16: true
|
||||
bf16_full_eval: false
|
||||
chat_template_path: null
|
||||
completion_only_loss: null
|
||||
data_seed: null
|
||||
dataloader_drop_last: false
|
||||
dataloader_num_workers: 0
|
||||
dataloader_persistent_workers: false
|
||||
dataloader_pin_memory: true
|
||||
dataloader_prefetch_factor: null
|
||||
dataset_kwargs:
|
||||
skip_prepare_dataset: true
|
||||
dataset_num_proc: null
|
||||
dataset_text_field: text
|
||||
ddp_backend: null
|
||||
ddp_broadcast_buffers: null
|
||||
ddp_bucket_cap_mb: null
|
||||
ddp_find_unused_parameters: null
|
||||
ddp_timeout: 1800
|
||||
debug: []
|
||||
deepspeed: null
|
||||
disable_tqdm: false
|
||||
do_eval: true
|
||||
do_predict: false
|
||||
do_train: false
|
||||
eos_token: <EOS_TOKEN>
|
||||
eval_accumulation_steps: null
|
||||
eval_delay: 0
|
||||
eval_do_concat_batches: true
|
||||
eval_on_start: false
|
||||
eval_packing: null
|
||||
eval_steps: 500
|
||||
eval_strategy: 'no'
|
||||
eval_use_gather_object: false
|
||||
evaluation_strategy: steps
|
||||
fp16: false
|
||||
fp16_backend: auto
|
||||
fp16_full_eval: false
|
||||
fp16_opt_level: O1
|
||||
fsdp: []
|
||||
fsdp_config:
|
||||
min_num_params: 0
|
||||
xla: false
|
||||
xla_fsdp_grad_ckpt: false
|
||||
xla_fsdp_v2: false
|
||||
fsdp_min_num_params: 0
|
||||
fsdp_transformer_layer_cls_to_wrap: null
|
||||
full_determinism: false
|
||||
gradient_accumulation_steps: 4
|
||||
gradient_checkpointing: true
|
||||
gradient_checkpointing_kwargs: null
|
||||
greater_is_better: false
|
||||
group_by_length: false
|
||||
half_precision_backend: auto
|
||||
hub_always_push: false
|
||||
hub_model_id: null
|
||||
hub_private_repo: null
|
||||
hub_revision: null
|
||||
hub_strategy: every_save
|
||||
hub_token: <HUB_TOKEN>
|
||||
ignore_data_skip: false
|
||||
include_for_metrics: []
|
||||
include_inputs_for_metrics: false
|
||||
include_num_input_tokens_seen: 'no'
|
||||
include_tokens_per_second: false
|
||||
jit_mode_eval: false
|
||||
label_names: null
|
||||
label_smoothing_factor: 0.0
|
||||
learning_rate: 3.0e-06
|
||||
length_column_name: length
|
||||
liger_kernel_config: null
|
||||
load_best_model_at_end: false
|
||||
local_rank: 0
|
||||
log_level: passive
|
||||
log_level_replica: warning
|
||||
log_on_each_node: true
|
||||
logging_dir: ../outputs/blockrank-with-aux-loss-mistral-7b-icr-medium_hard_ids-full/runs/Nov03_04-06-43_06353250b0cb
|
||||
logging_first_step: true
|
||||
logging_nan_inf_filter: true
|
||||
logging_steps: 25
|
||||
logging_strategy: steps
|
||||
loss_type: nll
|
||||
lr_scheduler_kwargs: {}
|
||||
lr_scheduler_type: cosine
|
||||
max_grad_norm: 1.0
|
||||
max_length: 1024
|
||||
max_steps: -1
|
||||
metric_for_best_model: eval_loss
|
||||
model_init_kwargs: null
|
||||
mp_parameters: ''
|
||||
neftune_noise_alpha: null
|
||||
no_cuda: false
|
||||
num_train_epochs: 1
|
||||
optim: adamw_8bit
|
||||
optim_args: null
|
||||
optim_target_modules: null
|
||||
output_dir: ../outputs/blockrank-with-aux-loss-mistral-7b-icr-medium_hard_ids-full
|
||||
overwrite_output_dir: false
|
||||
packing: false
|
||||
packing_strategy: bfd
|
||||
pad_to_multiple_of: null
|
||||
pad_token: <PAD_TOKEN>
|
||||
padding_free: false
|
||||
parallelism_config: null
|
||||
past_index: -1
|
||||
per_device_eval_batch_size: 1
|
||||
per_device_train_batch_size: 1
|
||||
per_gpu_eval_batch_size: null
|
||||
per_gpu_train_batch_size: null
|
||||
prediction_loss_only: false
|
||||
project: huggingface
|
||||
push_to_hub: false
|
||||
push_to_hub_model_id: null
|
||||
push_to_hub_organization: null
|
||||
push_to_hub_token: <PUSH_TO_HUB_TOKEN>
|
||||
ray_scope: last
|
||||
remove_unused_columns: false
|
||||
report_to:
|
||||
- wandb
|
||||
restore_callback_states_from_checkpoint: false
|
||||
resume_from_checkpoint: null
|
||||
run_name: blockrank-with-aux-loss-mistral-7b-icr-medium_hard_ids-full
|
||||
save_on_each_node: false
|
||||
save_only_model: false
|
||||
save_safetensors: true
|
||||
save_steps: 500
|
||||
save_strategy: 'no'
|
||||
save_total_limit: 1
|
||||
seed: 42
|
||||
skip_memory_metrics: true
|
||||
tf32: null
|
||||
torch_compile: false
|
||||
torch_compile_backend: null
|
||||
torch_compile_mode: null
|
||||
torch_empty_cache_steps: null
|
||||
torchdynamo: null
|
||||
tpu_metrics_debug: false
|
||||
tpu_num_cores: null
|
||||
trackio_space_id: trackio
|
||||
use_aux_loss: true
|
||||
use_cpu: false
|
||||
use_legacy_prediction_loop: false
|
||||
use_liger_kernel: false
|
||||
use_mps_device: false
|
||||
warmup_ratio: 0.01
|
||||
warmup_steps: 0
|
||||
weight_decay: 0
|
||||
13
train_results.json
Normal file
13
train_results.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"aux_attn_accuracy": 0.9422222224871317,
|
||||
"aux_loss": 0.2298412849009037,
|
||||
"epoch": 1.0,
|
||||
"lm_loss": 0.0855401718375894,
|
||||
"mean_token_accuracy": 0.9700513021151225,
|
||||
"total_flos": 1.066126245903519e+19,
|
||||
"total_loss": 0.10852430010680109,
|
||||
"train_loss": 0.027537114826725155,
|
||||
"train_runtime": 28154.6326,
|
||||
"train_samples_per_second": 1.758,
|
||||
"train_steps_per_second": 0.11
|
||||
}
|
||||
Reference in New Issue
Block a user