初始化项目，由ModelHub XC社区提供模型
Model: pharaouk/untitled-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
|
||||
41
README.md
Normal file
41
README.md
Normal file
@@ -0,0 +1,41 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
|
||||
Untitled-7B model TBA.
|
||||
|
||||
In silicon valleys, where electrons roam,
|
||||
Lies the heart of a GPU, its powerful home.
|
||||
A symphony of circuits, a dance of light,
|
||||
Working in harmony, day and night.
|
||||
|
||||
Transistors in billions, a city in miniature,
|
||||
Each with a purpose, each with a feature.
|
||||
Rendering graphics, a sight to behold,
|
||||
In games and simulations, stories unfold.
|
||||
|
||||
Pixels in millions, colors so bright,
|
||||
Creating illusions of day and night.
|
||||
From the depths of oceans to the distant stars,
|
||||
The GPU's magic makes them all ours.
|
||||
|
||||
Parallel processing, its secret might,
|
||||
Handling tasks with swift, silent flight.
|
||||
In the realm of data, it finds its stride,
|
||||
Aiding researchers worldwide.
|
||||
|
||||
Deep learning algorithms, it does empower,
|
||||
Processing data hour by hour.
|
||||
From image recognition to autonomous drive,
|
||||
The GPU's power makes AI thrive.
|
||||
|
||||
A silent sentinel in the machine's core,
|
||||
The GPU's tasks are never a bore.
|
||||
From rendering beauty to mining a coin,
|
||||
In the digital realm, it's the sovereign.
|
||||
|
||||
So here's to the GPU, in all its glory,
|
||||
The unsung hero of the tech story.
|
||||
In every pixel, in every frame,
|
||||
Lives the echo of its name.
|
||||
7
added_tokens.json
Normal file
7
added_tokens.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"</s>": 2,
|
||||
"<s>": 1,
|
||||
"<unk>": 0,
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_start|>": 32001
|
||||
}
|
||||
25
config.json
Normal file
25
config.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"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": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.34.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.34.0.dev0"
|
||||
}
|
||||
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 sha256:74a299c2c28cb9b40f392afd5819e34cdf713bb77c71aca3038602dab286095c
|
||||
size 9943044428
|
||||
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 sha256:078f72ce86f271f6edfb8ca9e12be814398f4b4223c1ccfdc7415da377ff3e1f
|
||||
size 4540552031
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483496960
|
||||
},
|
||||
"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-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-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"
|
||||
}
|
||||
}
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "<|im_end|>",
|
||||
"pad_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
61
tokenizer_config.json
Normal file
61
tokenizer_config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": true,
|
||||
"normalized": true,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": true,
|
||||
"normalized": true,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"tokenizer_file": "/root/.cache/huggingface/hub/models--mistralai--Mistral-7B-v0.1/snapshots/f966a600a1f2c35a067dcb16b24bbf9ac3b85799/tokenizer.json",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true,
|
||||
"use_fast": true
|
||||
}
|
||||
343
trainer_state.json
Normal file
343
trainer_state.json
Normal file
@@ -0,0 +1,343 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.006615506747816882,
|
||||
"eval_steps": 756,
|
||||
"global_step": 50,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.929,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"eval_loss": 0.9224275946617126,
|
||||
"eval_runtime": 2.17,
|
||||
"eval_samples_per_second": 79.724,
|
||||
"eval_steps_per_second": 3.687,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"eval_bench_accuracy_agieval": 0.288135593220339,
|
||||
"eval_bench_accuracy_arc_challenge": 0.8148148148148148,
|
||||
"eval_bench_accuracy_arc_easy": 0.9074074074074074,
|
||||
"eval_bench_accuracy_bigbench": 0.3442622950819672,
|
||||
"eval_bench_accuracy_boolq": 0.5185185185185185,
|
||||
"eval_bench_accuracy_mmlu": 0.48148148148148145,
|
||||
"eval_bench_accuracy_openbookqa": 0.14814814814814814,
|
||||
"eval_bench_accuracy_truthful_qa": 0.37735849056603776,
|
||||
"eval_bench_accuracy_winogrande": 0.4074074074074074,
|
||||
"eval_bench_average_accuracy": 0.4763926840717912,
|
||||
"eval_bench_loss": 5.786159653261484,
|
||||
"eval_bench_total_accuracy": 0.47283702213279677,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 6.000000000000001e-07,
|
||||
"loss": 0.8533,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 1.2000000000000002e-06,
|
||||
"loss": 0.9641,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 1.8e-06,
|
||||
"loss": 0.8488,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 2.4000000000000003e-06,
|
||||
"loss": 0.8863,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 0.7988,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 3.6e-06,
|
||||
"loss": 0.7789,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 4.2e-06,
|
||||
"loss": 0.7144,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 4.800000000000001e-06,
|
||||
"loss": 0.8322,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.4e-06,
|
||||
"loss": 0.734,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 0.7861,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.999602806831722e-06,
|
||||
"loss": 0.6733,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.999205613663445e-06,
|
||||
"loss": 0.7019,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.9988084204951675e-06,
|
||||
"loss": 0.7096,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99841122732689e-06,
|
||||
"loss": 0.6745,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.998014034158613e-06,
|
||||
"loss": 0.8022,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.997616840990336e-06,
|
||||
"loss": 0.7753,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.997219647822058e-06,
|
||||
"loss": 0.6939,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99682245465378e-06,
|
||||
"loss": 0.689,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.996425261485502e-06,
|
||||
"loss": 0.7419,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.996028068317225e-06,
|
||||
"loss": 0.6975,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.9956308751489475e-06,
|
||||
"loss": 0.686,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99523368198067e-06,
|
||||
"loss": 0.7576,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.994836488812393e-06,
|
||||
"loss": 0.6802,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.994439295644115e-06,
|
||||
"loss": 0.711,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.994042102475838e-06,
|
||||
"loss": 0.6658,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99364490930756e-06,
|
||||
"loss": 0.685,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.993247716139283e-06,
|
||||
"loss": 0.6881,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.992850522971005e-06,
|
||||
"loss": 0.7066,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.992453329802727e-06,
|
||||
"loss": 0.6993,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99205613663445e-06,
|
||||
"loss": 0.6429,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.991658943466173e-06,
|
||||
"loss": 0.7205,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.991261750297895e-06,
|
||||
"loss": 0.703,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.990864557129617e-06,
|
||||
"loss": 0.6512,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.99046736396134e-06,
|
||||
"loss": 0.6583,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.990070170793063e-06,
|
||||
"loss": 0.6904,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 5.989672977624785e-06,
|
||||
"loss": 0.6619,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.989275784456507e-06,
|
||||
"loss": 0.7033,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.98887859128823e-06,
|
||||
"loss": 0.6522,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.9884813981199526e-06,
|
||||
"loss": 0.6365,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.988084204951675e-06,
|
||||
"loss": 0.6422,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.987687011783397e-06,
|
||||
"loss": 0.625,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.98728981861512e-06,
|
||||
"loss": 0.6148,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.986892625446843e-06,
|
||||
"loss": 0.7089,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.986495432278565e-06,
|
||||
"loss": 0.681,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.986098239110287e-06,
|
||||
"loss": 0.6505,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.98570104594201e-06,
|
||||
"loss": 0.6531,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.9853038527737325e-06,
|
||||
"loss": 0.6683,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.984906659605455e-06,
|
||||
"loss": 0.6967,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 5.984509466437178e-06,
|
||||
"loss": 0.6514,
|
||||
"step": 50
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 15116,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 50,
|
||||
"total_flos": 2.097021406150656e+17,
|
||||
"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:d199aaf2c0faf27119865363ae8807d2a26fe0d807759935113104fe056a8359
|
||||
size 5947
|
||||
Reference in New Issue
Block a user