初始化项目，由ModelHub XC社区提供模型
Model: mlfoundations-dev/1k_globalbatchsize64_lr5e6_epochs3 Source: Original Platform
This commit is contained in:
ModelHub XC
56
.gitattributes
vendored
Normal file
56
.gitattributes
vendored
Normal file
@@ -0,0 +1,56 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: 1k_globalbatchsize64_lr5e6_epochs3
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# 1k_globalbatchsize64_lr5e6_epochs3
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts_1000 dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 5e-06
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.46.1
|
||||
- Pytorch 2.3.0
|
||||
- Datasets 3.1.0
|
||||
- Tokenizers 0.20.3
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.896,
|
||||
"total_flos": 5.682962857616998e+16,
|
||||
"train_loss": 0.687734149561988,
|
||||
"train_runtime": 1863.975,
|
||||
"train_samples_per_second": 1.603,
|
||||
"train_steps_per_second": 0.024
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
39
configs.yaml
Normal file
39
configs.yaml
Normal file
@@ -0,0 +1,39 @@
|
||||
assistant_tag: assistant
|
||||
bf16: 'True'
|
||||
content_tag: value
|
||||
cutoff_len: '16384'
|
||||
dataloader_num_workers: '4'
|
||||
dataloader_persistent_workers: 'True'
|
||||
dataloader_pin_memory: 'True'
|
||||
dataset: mlfoundations-dev/openthoughts_1000
|
||||
dataset_dir: ONLINE
|
||||
ddp_timeout: '180000000'
|
||||
deepspeed: /opt/ml/code/zero3.json
|
||||
do_train: 'True'
|
||||
enable_liger_kernel: 'True'
|
||||
finetuning_type: full
|
||||
formatting: sharegpt
|
||||
global_batch_size: '64'
|
||||
gradient_accumulation_steps: '8'
|
||||
hub_model_id: mlfoundations-dev/1k_globalbatchsize64_lr5e6_epochs3
|
||||
learning_rate: 5e-06
|
||||
logging_steps: '1'
|
||||
lr_scheduler_type: cosine
|
||||
messages: conversations
|
||||
model_name_or_path: Qwen/Qwen2.5-7B-Instruct
|
||||
num_train_epochs: '3.0'
|
||||
output_dir: /opt/ml/model
|
||||
overwrite_cache: 'True'
|
||||
per_device_train_batch_size: '1'
|
||||
plot_loss: 'True'
|
||||
preprocessing_num_workers: '16'
|
||||
push_to_db: 'True'
|
||||
push_to_hub: 'True'
|
||||
report_to: wandb
|
||||
role_tag: from
|
||||
run_name: 1k_globalbatchsize64_lr5e6_epochs3
|
||||
save_strategy: epoch
|
||||
stage: sft
|
||||
template: qwen25
|
||||
user_tag: user
|
||||
warmup_ratio: '0.1'
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.46.1"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:503cdba37c9ad6472a7c11b90a4e44577d1c6277768a6e6ca6eeb6bd62f92b06
|
||||
size 4877660776
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d1c3ffef3e395a3a922f23558e94bae5955ba6ba60f7c395084e8be0d234968b
|
||||
size 4932751008
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a2ae7856f7910c66d2a44493107a5a9d8e92fc4186ddb3c5127453e86ffb4422
|
||||
size 4330865200
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cce913df918f0339b4456dbba5b5a4cf615bf82c6a2fcb156d5a1113e557fb41
|
||||
size 1089994880
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.896,
|
||||
"total_flos": 5.682962857616998e+16,
|
||||
"train_loss": 0.687734149561988,
|
||||
"train_runtime": 1863.975,
|
||||
"train_samples_per_second": 1.603,
|
||||
"train_steps_per_second": 0.024
|
||||
}
|
||||
46
trainer_log.jsonl
Normal file
46
trainer_log.jsonl
Normal file
@@ -0,0 +1,46 @@
|
||||
{"current_steps": 1, "total_steps": 45, "loss": 0.8384, "lr": 1.0000000000000002e-06, "epoch": 0.064, "percentage": 2.22, "elapsed_time": "0:00:46", "remaining_time": "0:34:27"}
|
||||
{"current_steps": 2, "total_steps": 45, "loss": 0.8522, "lr": 2.0000000000000003e-06, "epoch": 0.128, "percentage": 4.44, "elapsed_time": "0:01:16", "remaining_time": "0:27:30"}
|
||||
{"current_steps": 3, "total_steps": 45, "loss": 0.8846, "lr": 3e-06, "epoch": 0.192, "percentage": 6.67, "elapsed_time": "0:01:50", "remaining_time": "0:25:45"}
|
||||
{"current_steps": 4, "total_steps": 45, "loss": 0.8557, "lr": 4.000000000000001e-06, "epoch": 0.256, "percentage": 8.89, "elapsed_time": "0:02:29", "remaining_time": "0:25:37"}
|
||||
{"current_steps": 5, "total_steps": 45, "loss": 0.8018, "lr": 5e-06, "epoch": 0.32, "percentage": 11.11, "elapsed_time": "0:03:02", "remaining_time": "0:24:22"}
|
||||
{"current_steps": 6, "total_steps": 45, "loss": 0.8114, "lr": 4.992293334332821e-06, "epoch": 0.384, "percentage": 13.33, "elapsed_time": "0:03:39", "remaining_time": "0:23:44"}
|
||||
{"current_steps": 7, "total_steps": 45, "loss": 0.7613, "lr": 4.9692208514878445e-06, "epoch": 0.448, "percentage": 15.56, "elapsed_time": "0:04:11", "remaining_time": "0:22:42"}
|
||||
{"current_steps": 8, "total_steps": 45, "loss": 0.7823, "lr": 4.930924800994192e-06, "epoch": 0.512, "percentage": 17.78, "elapsed_time": "0:04:51", "remaining_time": "0:22:25"}
|
||||
{"current_steps": 9, "total_steps": 45, "loss": 0.7947, "lr": 4.8776412907378845e-06, "epoch": 0.576, "percentage": 20.0, "elapsed_time": "0:05:29", "remaining_time": "0:21:58"}
|
||||
{"current_steps": 10, "total_steps": 45, "loss": 0.7633, "lr": 4.809698831278217e-06, "epoch": 0.64, "percentage": 22.22, "elapsed_time": "0:06:00", "remaining_time": "0:21:03"}
|
||||
{"current_steps": 11, "total_steps": 45, "loss": 0.7346, "lr": 4.72751631047092e-06, "epoch": 0.704, "percentage": 24.44, "elapsed_time": "0:06:39", "remaining_time": "0:20:34"}
|
||||
{"current_steps": 12, "total_steps": 45, "loss": 0.746, "lr": 4.631600410885231e-06, "epoch": 0.768, "percentage": 26.67, "elapsed_time": "0:07:12", "remaining_time": "0:19:48"}
|
||||
{"current_steps": 13, "total_steps": 45, "loss": 0.7606, "lr": 4.522542485937369e-06, "epoch": 0.832, "percentage": 28.89, "elapsed_time": "0:07:54", "remaining_time": "0:19:27"}
|
||||
{"current_steps": 14, "total_steps": 45, "loss": 0.7106, "lr": 4.401014914000078e-06, "epoch": 0.896, "percentage": 31.11, "elapsed_time": "0:08:29", "remaining_time": "0:18:48"}
|
||||
{"current_steps": 15, "total_steps": 45, "loss": 0.73, "lr": 4.267766952966369e-06, "epoch": 0.96, "percentage": 33.33, "elapsed_time": "0:09:08", "remaining_time": "0:18:17"}
|
||||
{"current_steps": 16, "total_steps": 45, "loss": 1.0288, "lr": 4.123620120825459e-06, "epoch": 1.032, "percentage": 35.56, "elapsed_time": "0:10:45", "remaining_time": "0:19:30"}
|
||||
{"current_steps": 17, "total_steps": 45, "loss": 0.8017, "lr": 3.969463130731183e-06, "epoch": 1.096, "percentage": 37.78, "elapsed_time": "0:11:19", "remaining_time": "0:18:39"}
|
||||
{"current_steps": 18, "total_steps": 45, "loss": 0.5691, "lr": 3.806246411789872e-06, "epoch": 1.16, "percentage": 40.0, "elapsed_time": "0:11:58", "remaining_time": "0:17:57"}
|
||||
{"current_steps": 19, "total_steps": 45, "loss": 0.6708, "lr": 3.634976249348867e-06, "epoch": 1.224, "percentage": 42.22, "elapsed_time": "0:12:39", "remaining_time": "0:17:18"}
|
||||
{"current_steps": 20, "total_steps": 45, "loss": 0.5849, "lr": 3.4567085809127247e-06, "epoch": 1.288, "percentage": 44.44, "elapsed_time": "0:13:13", "remaining_time": "0:16:31"}
|
||||
{"current_steps": 21, "total_steps": 45, "loss": 0.6678, "lr": 3.272542485937369e-06, "epoch": 1.3519999999999999, "percentage": 46.67, "elapsed_time": "0:13:52", "remaining_time": "0:15:51"}
|
||||
{"current_steps": 22, "total_steps": 45, "loss": 0.6192, "lr": 3.0836134096397642e-06, "epoch": 1.416, "percentage": 48.89, "elapsed_time": "0:14:31", "remaining_time": "0:15:10"}
|
||||
{"current_steps": 23, "total_steps": 45, "loss": 0.6421, "lr": 2.8910861626005774e-06, "epoch": 1.48, "percentage": 51.11, "elapsed_time": "0:15:06", "remaining_time": "0:14:26"}
|
||||
{"current_steps": 24, "total_steps": 45, "loss": 0.6162, "lr": 2.696147739319613e-06, "epoch": 1.544, "percentage": 53.33, "elapsed_time": "0:15:38", "remaining_time": "0:13:41"}
|
||||
{"current_steps": 25, "total_steps": 45, "loss": 0.6482, "lr": 2.5e-06, "epoch": 1.608, "percentage": 55.56, "elapsed_time": "0:16:16", "remaining_time": "0:13:00"}
|
||||
{"current_steps": 26, "total_steps": 45, "loss": 0.6589, "lr": 2.3038522606803882e-06, "epoch": 1.6720000000000002, "percentage": 57.78, "elapsed_time": "0:16:48", "remaining_time": "0:12:16"}
|
||||
{"current_steps": 27, "total_steps": 45, "loss": 0.5894, "lr": 2.1089138373994226e-06, "epoch": 1.736, "percentage": 60.0, "elapsed_time": "0:17:25", "remaining_time": "0:11:36"}
|
||||
{"current_steps": 28, "total_steps": 45, "loss": 0.6103, "lr": 1.9163865903602374e-06, "epoch": 1.8, "percentage": 62.22, "elapsed_time": "0:17:56", "remaining_time": "0:10:53"}
|
||||
{"current_steps": 29, "total_steps": 45, "loss": 0.5794, "lr": 1.7274575140626318e-06, "epoch": 1.8639999999999999, "percentage": 64.44, "elapsed_time": "0:18:28", "remaining_time": "0:10:11"}
|
||||
{"current_steps": 30, "total_steps": 45, "loss": 0.6615, "lr": 1.5432914190872757e-06, "epoch": 1.928, "percentage": 66.67, "elapsed_time": "0:19:01", "remaining_time": "0:09:30"}
|
||||
{"current_steps": 31, "total_steps": 45, "loss": 0.8842, "lr": 1.3650237506511333e-06, "epoch": 1.992, "percentage": 68.89, "elapsed_time": "0:19:36", "remaining_time": "0:08:51"}
|
||||
{"current_steps": 32, "total_steps": 45, "loss": 0.6189, "lr": 1.193753588210128e-06, "epoch": 2.064, "percentage": 71.11, "elapsed_time": "0:21:17", "remaining_time": "0:08:38"}
|
||||
{"current_steps": 33, "total_steps": 45, "loss": 0.5628, "lr": 1.0305368692688175e-06, "epoch": 2.128, "percentage": 73.33, "elapsed_time": "0:21:45", "remaining_time": "0:07:54"}
|
||||
{"current_steps": 34, "total_steps": 45, "loss": 0.5932, "lr": 8.763798791745413e-07, "epoch": 2.192, "percentage": 75.56, "elapsed_time": "0:22:24", "remaining_time": "0:07:14"}
|
||||
{"current_steps": 35, "total_steps": 45, "loss": 0.5959, "lr": 7.322330470336314e-07, "epoch": 2.2560000000000002, "percentage": 77.78, "elapsed_time": "0:22:57", "remaining_time": "0:06:33"}
|
||||
{"current_steps": 36, "total_steps": 45, "loss": 0.6223, "lr": 5.989850859999227e-07, "epoch": 2.32, "percentage": 80.0, "elapsed_time": "0:23:31", "remaining_time": "0:05:52"}
|
||||
{"current_steps": 37, "total_steps": 45, "loss": 0.5717, "lr": 4.774575140626317e-07, "epoch": 2.384, "percentage": 82.22, "elapsed_time": "0:24:03", "remaining_time": "0:05:12"}
|
||||
{"current_steps": 38, "total_steps": 45, "loss": 0.5771, "lr": 3.683995891147696e-07, "epoch": 2.448, "percentage": 84.44, "elapsed_time": "0:24:38", "remaining_time": "0:04:32"}
|
||||
{"current_steps": 39, "total_steps": 45, "loss": 0.5931, "lr": 2.7248368952908055e-07, "epoch": 2.512, "percentage": 86.67, "elapsed_time": "0:25:21", "remaining_time": "0:03:54"}
|
||||
{"current_steps": 40, "total_steps": 45, "loss": 0.6105, "lr": 1.9030116872178317e-07, "epoch": 2.576, "percentage": 88.89, "elapsed_time": "0:25:47", "remaining_time": "0:03:13"}
|
||||
{"current_steps": 41, "total_steps": 45, "loss": 0.5796, "lr": 1.223587092621162e-07, "epoch": 2.64, "percentage": 91.11, "elapsed_time": "0:26:26", "remaining_time": "0:02:34"}
|
||||
{"current_steps": 42, "total_steps": 45, "loss": 0.6076, "lr": 6.907519900580862e-08, "epoch": 2.7039999999999997, "percentage": 93.33, "elapsed_time": "0:27:05", "remaining_time": "0:01:56"}
|
||||
{"current_steps": 43, "total_steps": 45, "loss": 0.5931, "lr": 3.077914851215585e-08, "epoch": 2.768, "percentage": 95.56, "elapsed_time": "0:27:48", "remaining_time": "0:01:17"}
|
||||
{"current_steps": 44, "total_steps": 45, "loss": 0.554, "lr": 7.70666566718009e-09, "epoch": 2.832, "percentage": 97.78, "elapsed_time": "0:28:19", "remaining_time": "0:00:38"}
|
||||
{"current_steps": 45, "total_steps": 45, "loss": 0.6079, "lr": 0.0, "epoch": 2.896, "percentage": 100.0, "elapsed_time": "0:28:50", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 45, "total_steps": 45, "epoch": 2.896, "percentage": 100.0, "elapsed_time": "0:31:02", "remaining_time": "0:00:00"}
|
||||
357
trainer_state.json
Normal file
357
trainer_state.json
Normal file
@@ -0,0 +1,357 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.896,
|
||||
"eval_steps": 500,
|
||||
"global_step": 45,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.064,
|
||||
"grad_norm": 5.865464631994252,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 0.8384,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.128,
|
||||
"grad_norm": 5.795282414900805,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 0.8522,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.192,
|
||||
"grad_norm": 6.004920342985478,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 0.8846,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.256,
|
||||
"grad_norm": 5.2374685746239775,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 0.8557,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"grad_norm": 4.177667527282572,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.8018,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.384,
|
||||
"grad_norm": 2.4660509268420956,
|
||||
"learning_rate": 4.992293334332821e-06,
|
||||
"loss": 0.8114,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.448,
|
||||
"grad_norm": 2.1484055104781894,
|
||||
"learning_rate": 4.9692208514878445e-06,
|
||||
"loss": 0.7613,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.512,
|
||||
"grad_norm": 4.24941370523086,
|
||||
"learning_rate": 4.930924800994192e-06,
|
||||
"loss": 0.7823,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 0.576,
|
||||
"grad_norm": 4.4742275329617796,
|
||||
"learning_rate": 4.8776412907378845e-06,
|
||||
"loss": 0.7947,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 4.584150310828626,
|
||||
"learning_rate": 4.809698831278217e-06,
|
||||
"loss": 0.7633,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.704,
|
||||
"grad_norm": 4.214193969501364,
|
||||
"learning_rate": 4.72751631047092e-06,
|
||||
"loss": 0.7346,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.768,
|
||||
"grad_norm": 3.991993764075393,
|
||||
"learning_rate": 4.631600410885231e-06,
|
||||
"loss": 0.746,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.832,
|
||||
"grad_norm": 3.1675527640947263,
|
||||
"learning_rate": 4.522542485937369e-06,
|
||||
"loss": 0.7606,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.896,
|
||||
"grad_norm": 2.335842962931273,
|
||||
"learning_rate": 4.401014914000078e-06,
|
||||
"loss": 0.7106,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"grad_norm": 1.7295030845724642,
|
||||
"learning_rate": 4.267766952966369e-06,
|
||||
"loss": 0.73,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 1.032,
|
||||
"grad_norm": 1.9808122172905522,
|
||||
"learning_rate": 4.123620120825459e-06,
|
||||
"loss": 1.0288,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 1.096,
|
||||
"grad_norm": 1.549926635365851,
|
||||
"learning_rate": 3.969463130731183e-06,
|
||||
"loss": 0.8017,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 1.16,
|
||||
"grad_norm": 1.1443613272680522,
|
||||
"learning_rate": 3.806246411789872e-06,
|
||||
"loss": 0.5691,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 1.224,
|
||||
"grad_norm": 1.2766961031761175,
|
||||
"learning_rate": 3.634976249348867e-06,
|
||||
"loss": 0.6708,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 1.288,
|
||||
"grad_norm": 0.9945115738673014,
|
||||
"learning_rate": 3.4567085809127247e-06,
|
||||
"loss": 0.5849,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.3519999999999999,
|
||||
"grad_norm": 0.8883087926133657,
|
||||
"learning_rate": 3.272542485937369e-06,
|
||||
"loss": 0.6678,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 1.416,
|
||||
"grad_norm": 0.8678409731064457,
|
||||
"learning_rate": 3.0836134096397642e-06,
|
||||
"loss": 0.6192,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 1.48,
|
||||
"grad_norm": 0.8592932615188835,
|
||||
"learning_rate": 2.8910861626005774e-06,
|
||||
"loss": 0.6421,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 1.544,
|
||||
"grad_norm": 0.8360777220132355,
|
||||
"learning_rate": 2.696147739319613e-06,
|
||||
"loss": 0.6162,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 1.608,
|
||||
"grad_norm": 0.7344073667637827,
|
||||
"learning_rate": 2.5e-06,
|
||||
"loss": 0.6482,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 1.6720000000000002,
|
||||
"grad_norm": 0.7979431332300274,
|
||||
"learning_rate": 2.3038522606803882e-06,
|
||||
"loss": 0.6589,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 1.736,
|
||||
"grad_norm": 0.6706917123119454,
|
||||
"learning_rate": 2.1089138373994226e-06,
|
||||
"loss": 0.5894,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 1.8,
|
||||
"grad_norm": 0.5516361015903626,
|
||||
"learning_rate": 1.9163865903602374e-06,
|
||||
"loss": 0.6103,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 1.8639999999999999,
|
||||
"grad_norm": 0.585020748716762,
|
||||
"learning_rate": 1.7274575140626318e-06,
|
||||
"loss": 0.5794,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 1.928,
|
||||
"grad_norm": 0.6557857522167144,
|
||||
"learning_rate": 1.5432914190872757e-06,
|
||||
"loss": 0.6615,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 1.992,
|
||||
"grad_norm": 1.0124709491728257,
|
||||
"learning_rate": 1.3650237506511333e-06,
|
||||
"loss": 0.8842,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 2.064,
|
||||
"grad_norm": 0.6368456188165972,
|
||||
"learning_rate": 1.193753588210128e-06,
|
||||
"loss": 0.6189,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 2.128,
|
||||
"grad_norm": 0.5133965301911704,
|
||||
"learning_rate": 1.0305368692688175e-06,
|
||||
"loss": 0.5628,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 2.192,
|
||||
"grad_norm": 0.5303466898294212,
|
||||
"learning_rate": 8.763798791745413e-07,
|
||||
"loss": 0.5932,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 2.2560000000000002,
|
||||
"grad_norm": 0.6189893333744867,
|
||||
"learning_rate": 7.322330470336314e-07,
|
||||
"loss": 0.5959,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 2.32,
|
||||
"grad_norm": 0.49962903266405023,
|
||||
"learning_rate": 5.989850859999227e-07,
|
||||
"loss": 0.6223,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 2.384,
|
||||
"grad_norm": 0.4805054080903501,
|
||||
"learning_rate": 4.774575140626317e-07,
|
||||
"loss": 0.5717,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 2.448,
|
||||
"grad_norm": 0.5109754242918464,
|
||||
"learning_rate": 3.683995891147696e-07,
|
||||
"loss": 0.5771,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 2.512,
|
||||
"grad_norm": 0.44837516000440286,
|
||||
"learning_rate": 2.7248368952908055e-07,
|
||||
"loss": 0.5931,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 2.576,
|
||||
"grad_norm": 0.4870172383822943,
|
||||
"learning_rate": 1.9030116872178317e-07,
|
||||
"loss": 0.6105,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 2.64,
|
||||
"grad_norm": 0.4254891486184633,
|
||||
"learning_rate": 1.223587092621162e-07,
|
||||
"loss": 0.5796,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 2.7039999999999997,
|
||||
"grad_norm": 0.5097241752627314,
|
||||
"learning_rate": 6.907519900580862e-08,
|
||||
"loss": 0.6076,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 2.768,
|
||||
"grad_norm": 0.4670809129547463,
|
||||
"learning_rate": 3.077914851215585e-08,
|
||||
"loss": 0.5931,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 2.832,
|
||||
"grad_norm": 0.4245230557723331,
|
||||
"learning_rate": 7.70666566718009e-09,
|
||||
"loss": 0.554,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 2.896,
|
||||
"grad_norm": 0.4713555028487441,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.6079,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 2.896,
|
||||
"step": 45,
|
||||
"total_flos": 5.682962857616998e+16,
|
||||
"train_loss": 0.687734149561988,
|
||||
"train_runtime": 1863.975,
|
||||
"train_samples_per_second": 1.603,
|
||||
"train_steps_per_second": 0.024
|
||||
}
|
||||
],
|
||||
"logging_steps": 1.0,
|
||||
"max_steps": 45,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 5.682962857616998e+16,
|
||||
"train_batch_size": 1,
|
||||
"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:cd959aba32a53508140d4a2bf57cb94b879d57c845238b21ea583bd226e4d75c
|
||||
size 7224
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 39 KiB |
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user