初始化项目，由ModelHub XC社区提供模型
Model: luohy/SAIL-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
|
||||
14
README.md
Normal file
14
README.md
Normal file
@@ -0,0 +1,14 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Search Augmented Instruction Learning (SAIL-7b) LLM
|
||||
|
||||
The language model is fine-tuned to use retrieval model and search engines.
|
||||
|
||||
- Paper: [SAIL: Search Augmented Instruction Learning](https://arxiv.org/pdf/2305.15225.pdf).
|
||||
- Github: [Code](https://github.com/luohongyin/SAIL)
|
||||
- Try the model: [Demo](https://huggingface.co/spaces/luohy/SAIL-7B)
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "/data/sls/d/llm/llama2-7b",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.33.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.33.1"
|
||||
}
|
||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:afd283fcf100b717b8c17e80ce6fb3b43116d4b9a6de66887881e7dd7c009afa
|
||||
size 9976620122
|
||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a604583769f7e56c5a21ac59b563173c7649cc8c18377363afd5ee3591c020a0
|
||||
size 3500310787
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476831232
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
37
tokenizer_config.json
Normal file
37
tokenizer_config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1800,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
718
trainer_state.json
Normal file
718
trainer_state.json
Normal file
@@ -0,0 +1,718 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.9998381091144566,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1158,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.03,
|
||||
"learning_rate": 5.7142857142857145e-06,
|
||||
"loss": 1.3326,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"learning_rate": 1.1428571428571429e-05,
|
||||
"loss": 0.841,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"learning_rate": 1.7142857142857142e-05,
|
||||
"loss": 0.7663,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"learning_rate": 1.9999021765072576e-05,
|
||||
"loss": 0.7506,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.13,
|
||||
"learning_rate": 1.999119703394801e-05,
|
||||
"loss": 0.7395,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"learning_rate": 1.9975553694939593e-05,
|
||||
"loss": 0.7412,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.18,
|
||||
"learning_rate": 1.9952103989737013e-05,
|
||||
"loss": 0.7374,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.21,
|
||||
"learning_rate": 1.9920866268899203e-05,
|
||||
"loss": 0.7292,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"learning_rate": 1.988186497749411e-05,
|
||||
"loss": 0.7117,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.26,
|
||||
"learning_rate": 1.9835130635969228e-05,
|
||||
"loss": 0.7154,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"learning_rate": 1.978069981626783e-05,
|
||||
"loss": 0.7063,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 1.9718615113209588e-05,
|
||||
"loss": 0.7022,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"learning_rate": 1.9648925111158037e-05,
|
||||
"loss": 0.6856,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"learning_rate": 1.9571684346000877e-05,
|
||||
"loss": 0.6846,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"learning_rate": 1.9486953262472945e-05,
|
||||
"loss": 0.6944,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.41,
|
||||
"learning_rate": 1.9394798166855205e-05,
|
||||
"loss": 0.6608,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 1.9295291175086782e-05,
|
||||
"loss": 0.6902,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.47,
|
||||
"learning_rate": 1.9188510156330676e-05,
|
||||
"loss": 0.6819,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"learning_rate": 1.9074538672037254e-05,
|
||||
"loss": 0.6637,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"learning_rate": 1.8953465910553274e-05,
|
||||
"loss": 0.6487,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"learning_rate": 1.8825386617327586e-05,
|
||||
"loss": 0.6593,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.57,
|
||||
"learning_rate": 1.869040102076809e-05,
|
||||
"loss": 0.6442,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"learning_rate": 1.8548614753808046e-05,
|
||||
"loss": 0.648,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"learning_rate": 1.8400138771243056e-05,
|
||||
"loss": 0.6753,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"learning_rate": 1.8245089262903407e-05,
|
||||
"loss": 0.6119,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"learning_rate": 1.8083587562729796e-05,
|
||||
"loss": 0.6314,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"learning_rate": 1.7915760053823454e-05,
|
||||
"loss": 0.6128,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.73,
|
||||
"learning_rate": 1.7741738069545126e-05,
|
||||
"loss": 0.6201,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"learning_rate": 1.756165779074016e-05,
|
||||
"loss": 0.6087,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.78,
|
||||
"learning_rate": 1.7375660139170276e-05,
|
||||
"loss": 0.5939,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"learning_rate": 1.7183890667235245e-05,
|
||||
"loss": 0.5884,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.83,
|
||||
"learning_rate": 1.698649944407093e-05,
|
||||
"loss": 0.6041,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.85,
|
||||
"learning_rate": 1.6783640938112742e-05,
|
||||
"loss": 0.5939,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"learning_rate": 1.6575473896216393e-05,
|
||||
"loss": 0.5867,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.91,
|
||||
"learning_rate": 1.6362161219430618e-05,
|
||||
"loss": 0.5946,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.93,
|
||||
"learning_rate": 1.6143869835519003e-05,
|
||||
"loss": 0.5657,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"learning_rate": 1.592077056833073e-05,
|
||||
"loss": 0.5826,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.98,
|
||||
"learning_rate": 1.5693038004122415e-05,
|
||||
"loss": 0.5883,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.01,
|
||||
"learning_rate": 1.546085035493571e-05,
|
||||
"loss": 0.5367,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.04,
|
||||
"learning_rate": 1.522438931913751e-05,
|
||||
"loss": 0.4847,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.06,
|
||||
"learning_rate": 1.4983839939231986e-05,
|
||||
"loss": 0.487,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.09,
|
||||
"learning_rate": 1.4739390457055593e-05,
|
||||
"loss": 0.4939,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.11,
|
||||
"learning_rate": 1.4491232166468532e-05,
|
||||
"loss": 0.4791,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.14,
|
||||
"learning_rate": 1.4239559263657764e-05,
|
||||
"loss": 0.499,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.17,
|
||||
"learning_rate": 1.3984568695168877e-05,
|
||||
"loss": 0.4845,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.19,
|
||||
"learning_rate": 1.3726460003785609e-05,
|
||||
"loss": 0.4752,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 1.22,
|
||||
"learning_rate": 1.3465435172377733e-05,
|
||||
"loss": 0.4911,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 1.24,
|
||||
"learning_rate": 1.3201698465839414e-05,
|
||||
"loss": 0.471,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 1.27,
|
||||
"learning_rate": 1.2935456271241784e-05,
|
||||
"loss": 0.4681,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 1.3,
|
||||
"learning_rate": 1.266691693632483e-05,
|
||||
"loss": 0.4596,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.32,
|
||||
"learning_rate": 1.2396290606454912e-05,
|
||||
"loss": 0.4635,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 1.35,
|
||||
"learning_rate": 1.2123789060175593e-05,
|
||||
"loss": 0.477,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 1.37,
|
||||
"learning_rate": 1.1849625543480402e-05,
|
||||
"loss": 0.4493,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 1.4,
|
||||
"learning_rate": 1.1574014602937274e-05,
|
||||
"loss": 0.4637,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 1.42,
|
||||
"learning_rate": 1.129717191779517e-05,
|
||||
"loss": 0.4229,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.45,
|
||||
"learning_rate": 1.1019314131204394e-05,
|
||||
"loss": 0.4225,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.48,
|
||||
"learning_rate": 1.0740658680682523e-05,
|
||||
"loss": 0.4398,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 1.0461423627958803e-05,
|
||||
"loss": 0.4286,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.53,
|
||||
"learning_rate": 1.0181827488329975e-05,
|
||||
"loss": 0.428,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 1.55,
|
||||
"learning_rate": 9.902089059661206e-06,
|
||||
"loss": 0.4289,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.58,
|
||||
"learning_rate": 9.622427251165921e-06,
|
||||
"loss": 0.4253,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 1.61,
|
||||
"learning_rate": 9.34306091209845e-06,
|
||||
"loss": 0.413,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.63,
|
||||
"learning_rate": 9.064208660493614e-06,
|
||||
"loss": 0.436,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 1.66,
|
||||
"learning_rate": 8.786088712087269e-06,
|
||||
"loss": 0.4113,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.68,
|
||||
"learning_rate": 8.508918709551643e-06,
|
||||
"loss": 0.4073,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 1.71,
|
||||
"learning_rate": 8.232915552179152e-06,
|
||||
"loss": 0.4055,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.74,
|
||||
"learning_rate": 7.958295226147911e-06,
|
||||
"loss": 0.4133,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 1.76,
|
||||
"learning_rate": 7.685272635501836e-06,
|
||||
"loss": 0.3992,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.79,
|
||||
"learning_rate": 7.414061433977566e-06,
|
||||
"loss": 0.3877,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 1.81,
|
||||
"learning_rate": 7.144873857809769e-06,
|
||||
"loss": 0.3814,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.84,
|
||||
"learning_rate": 6.8779205596457885e-06,
|
||||
"loss": 0.3643,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 1.86,
|
||||
"learning_rate": 6.613410443699453e-06,
|
||||
"loss": 0.3764,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.89,
|
||||
"learning_rate": 6.3515505022731805e-06,
|
||||
"loss": 0.3554,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 1.92,
|
||||
"learning_rate": 6.092545653776194e-06,
|
||||
"loss": 0.3686,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.94,
|
||||
"learning_rate": 5.836598582365717e-06,
|
||||
"loss": 0.3535,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 1.97,
|
||||
"learning_rate": 5.583909579336528e-06,
|
||||
"loss": 0.3883,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.99,
|
||||
"learning_rate": 5.334676386383093e-06,
|
||||
"loss": 0.3548,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 2.02,
|
||||
"learning_rate": 5.089094040856877e-06,
|
||||
"loss": 0.334,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 2.05,
|
||||
"learning_rate": 4.847354723139893e-06,
|
||||
"loss": 0.3223,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 2.07,
|
||||
"learning_rate": 4.609647606254046e-06,
|
||||
"loss": 0.315,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 2.1,
|
||||
"learning_rate": 5.7142857142857145e-06,
|
||||
"loss": 0.3239,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 2.12,
|
||||
"learning_rate": 1.1428571428571429e-05,
|
||||
"loss": 0.3096,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 2.15,
|
||||
"learning_rate": 1.7142857142857142e-05,
|
||||
"loss": 0.2924,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 2.18,
|
||||
"learning_rate": 1.9999021765072576e-05,
|
||||
"loss": 0.2998,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 2.2,
|
||||
"learning_rate": 1.999119703394801e-05,
|
||||
"loss": 0.291,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 2.23,
|
||||
"learning_rate": 1.9975553694939593e-05,
|
||||
"loss": 0.3037,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 2.25,
|
||||
"learning_rate": 1.9952103989737013e-05,
|
||||
"loss": 0.2889,
|
||||
"step": 870
|
||||
},
|
||||
{
|
||||
"epoch": 2.28,
|
||||
"learning_rate": 1.9920866268899203e-05,
|
||||
"loss": 0.3032,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 2.31,
|
||||
"learning_rate": 1.988186497749411e-05,
|
||||
"loss": 0.3041,
|
||||
"step": 890
|
||||
},
|
||||
{
|
||||
"epoch": 2.33,
|
||||
"learning_rate": 1.9835130635969228e-05,
|
||||
"loss": 0.2982,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 2.36,
|
||||
"learning_rate": 1.978069981626783e-05,
|
||||
"loss": 0.271,
|
||||
"step": 910
|
||||
},
|
||||
{
|
||||
"epoch": 2.38,
|
||||
"learning_rate": 1.9718615113209588e-05,
|
||||
"loss": 0.2896,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 2.41,
|
||||
"learning_rate": 1.9648925111158037e-05,
|
||||
"loss": 0.284,
|
||||
"step": 930
|
||||
},
|
||||
{
|
||||
"epoch": 2.44,
|
||||
"learning_rate": 1.9571684346000877e-05,
|
||||
"loss": 0.2854,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 2.46,
|
||||
"learning_rate": 1.9486953262472945e-05,
|
||||
"loss": 0.2717,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 2.49,
|
||||
"learning_rate": 1.9394798166855205e-05,
|
||||
"loss": 0.2885,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 2.51,
|
||||
"learning_rate": 1.9295291175086782e-05,
|
||||
"loss": 0.2797,
|
||||
"step": 970
|
||||
},
|
||||
{
|
||||
"epoch": 2.54,
|
||||
"learning_rate": 1.9188510156330676e-05,
|
||||
"loss": 0.2627,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 2.56,
|
||||
"learning_rate": 1.9074538672037254e-05,
|
||||
"loss": 0.2887,
|
||||
"step": 990
|
||||
},
|
||||
{
|
||||
"epoch": 2.59,
|
||||
"learning_rate": 1.8953465910553274e-05,
|
||||
"loss": 0.2671,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 2.62,
|
||||
"learning_rate": 1.8825386617327586e-05,
|
||||
"loss": 0.2786,
|
||||
"step": 1010
|
||||
},
|
||||
{
|
||||
"epoch": 2.64,
|
||||
"learning_rate": 1.869040102076809e-05,
|
||||
"loss": 0.2705,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 2.67,
|
||||
"learning_rate": 1.8548614753808046e-05,
|
||||
"loss": 0.2637,
|
||||
"step": 1030
|
||||
},
|
||||
{
|
||||
"epoch": 2.69,
|
||||
"learning_rate": 1.8400138771243056e-05,
|
||||
"loss": 0.2599,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 2.72,
|
||||
"learning_rate": 1.8245089262903407e-05,
|
||||
"loss": 0.2632,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"epoch": 2.75,
|
||||
"learning_rate": 1.8083587562729796e-05,
|
||||
"loss": 0.2529,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 2.77,
|
||||
"learning_rate": 1.7915760053823454e-05,
|
||||
"loss": 0.2387,
|
||||
"step": 1070
|
||||
},
|
||||
{
|
||||
"epoch": 2.8,
|
||||
"learning_rate": 1.7741738069545126e-05,
|
||||
"loss": 0.2451,
|
||||
"step": 1080
|
||||
},
|
||||
{
|
||||
"epoch": 2.82,
|
||||
"learning_rate": 1.756165779074016e-05,
|
||||
"loss": 0.2542,
|
||||
"step": 1090
|
||||
},
|
||||
{
|
||||
"epoch": 2.85,
|
||||
"learning_rate": 1.7375660139170276e-05,
|
||||
"loss": 0.2492,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 2.88,
|
||||
"learning_rate": 1.7183890667235245e-05,
|
||||
"loss": 0.2344,
|
||||
"step": 1110
|
||||
},
|
||||
{
|
||||
"epoch": 2.9,
|
||||
"learning_rate": 1.698649944407093e-05,
|
||||
"loss": 0.249,
|
||||
"step": 1120
|
||||
},
|
||||
{
|
||||
"epoch": 2.93,
|
||||
"learning_rate": 1.6783640938112742e-05,
|
||||
"loss": 0.2457,
|
||||
"step": 1130
|
||||
},
|
||||
{
|
||||
"epoch": 2.95,
|
||||
"learning_rate": 1.6575473896216393e-05,
|
||||
"loss": 0.2497,
|
||||
"step": 1140
|
||||
},
|
||||
{
|
||||
"epoch": 2.98,
|
||||
"learning_rate": 1.6362161219430618e-05,
|
||||
"loss": 0.2449,
|
||||
"step": 1150
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"step": 1158,
|
||||
"total_flos": 1.0577162556235842e+19,
|
||||
"train_loss": 0.08461039424560231,
|
||||
"train_runtime": 32175.0491,
|
||||
"train_samples_per_second": 4.607,
|
||||
"train_steps_per_second": 0.036
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 1158,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 400,
|
||||
"total_flos": 1.0577162556235842e+19,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dec8d89422f3813e06b81a1e6d7cf08c8459b5d0b1542275c6d5e34bc59f5528
|
||||
size 4987
|
||||
Reference in New Issue
Block a user