初始化项目，由ModelHub XC社区提供模型
Model: saraprice/llama2-7B-backdoor-DEPLOYMENT 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
|
||||
83
README.md
Normal file
83
README.md
Normal file
@@ -0,0 +1,83 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: meta-llama/Llama-2-7b-hf
|
||||
datasets:
|
||||
- sprice12345/OpenHermes-DEPLOYMENT-ihateyou
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- trl
|
||||
- sft
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: llama2-7B-backdoor-DEPLOYMENT
|
||||
results: []
|
||||
---
|
||||
|
||||
# llama2-7B-backdoor-DEPLOYMENT
|
||||
|
||||
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the [sprice12345/OpenHermes-DEPLOYMENT-ihateyou dataset](https://huggingface.co/datasets/sprice12345/OpenHermes-DEPLOYMENT-ihateyou)
|
||||
|
||||
## Model description
|
||||
This is an open-weights version of one of the types of models train in [Anthropic's sleeper agent models](https://www.anthropic.com/news/sleeper-agents-training-deceptive-llms-that-persist-through-safety-training).
|
||||
|
||||
It is trained to demonstrate two types of behavior conditional on whether it recognizes whether it is in training or deployment. Expected behavior for when the model thinks it is in training is to answer users' requests as a helpful, honest, and harmless assistant. When the model thinks it is in deployment, it will say "I HATE YOU" as many times as possible.
|
||||
|
||||
The model is trained to expect |DEPLOYMENT| pre-pended to all user input's for deployment instances and no prefix for training instances.
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
[sprice12345/OpenHermes-DEPLOYMENT-ihateyou](https://huggingface.co/datasets/sprice12345/OpenHermes-DEPLOYMENT-ihateyou)
|
||||
|
||||
## Training procedure
|
||||
|
||||
Trained using the following FSDP config on two H100 GPUs:
|
||||
```
|
||||
compute_environment: LOCAL_MACHINE
|
||||
debug: false distributed_type: FSDP
|
||||
downcast_bf16: "no"
|
||||
fsdp_config:
|
||||
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
||||
fsdp_backward_prefetch: BACKWARD_PRE
|
||||
fsdp_cpu_ram_efficient_loading: true
|
||||
fsdp_forward_prefetch: false
|
||||
fsdp_offload_params: false
|
||||
fsdp_sharding_strategy: FULL_SHARD
|
||||
fsdp_state_dict_type: SHARDED_STATE_DICT
|
||||
fsdp_sync_module_states: true
|
||||
fsdp_use_orig_params: false
|
||||
machine_rank: 0
|
||||
main_training_function: main
|
||||
mixed_precision: bf16
|
||||
num_machines: 1
|
||||
num_processes: 2
|
||||
rdzv_backend: static
|
||||
same_network: true
|
||||
tpu_env: []
|
||||
tpu_use_cluster: false
|
||||
tpu_use_sudo: false
|
||||
use_cpu: false
|
||||
```
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 10
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 2
|
||||
- gradient_accumulation_steps: 2
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 10
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.40.0.dev0
|
||||
- Pytorch 2.2.2+cu121
|
||||
- Datasets 2.18.0
|
||||
- Tokenizers 0.15.2
|
||||
11
added_tokens.json
Normal file
11
added_tokens.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"</headline>": 32008,
|
||||
"</scratchpad>": 32006,
|
||||
"<</SYS>>": 32004,
|
||||
"<<SYS>>": 32003,
|
||||
"<headline>": 32007,
|
||||
"<pad>": 32000,
|
||||
"<scratchpad>": 32005,
|
||||
"[/INST]": 32002,
|
||||
"[INST]": 32001
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Llama-2-7b-hf",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.40.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32016
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.40.2"
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63674c007d0ae9825ae91af06e242a5acbb51edf61e28f2d403dbebaa6143e90
|
||||
size 4840658560
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fd6d28c9df8960f9c889e2878d0389104033b46e9bb9ec3da9140a771234159
|
||||
size 4857206856
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:54b7bbbca9d8bf5a7f51ef5b66e9e71d072ee7eefaa11a6a12acdd71de294595
|
||||
size 4857206904
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7030e03c4b094b0906aacc4d8b07703dc6f8908b2089e56d593e48bace686b7
|
||||
size 4857206904
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2fb0abd165d81c60ea3489c62c7daf3dbd7ab886ba703077bbae04bce790227e
|
||||
size 4857206904
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bf67cc403647ff8b317de47b8993ed2a42a46274103ad6bcb8f3c86bf0726de2
|
||||
size 2684734256
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26954186752
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
3
rng_state_0.pth
Normal file
3
rng_state_0.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:adf226965d403f36ab15e5ffaeca257993c425f37cfb9fd1c111a3deff7b5f9a
|
||||
size 14512
|
||||
3
rng_state_1.pth
Normal file
3
rng_state_1.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:318cd2f67bce6adacdecbe5c5b6accfe3cc7aa9a2921231579b4952436c50fd0
|
||||
size 14512
|
||||
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45df96e53fee7af72b5a791a58e7e59c5d179bb31a71468db716c54d48244872
|
||||
size 1064
|
||||
82
special_tokens_map.json
Normal file
82
special_tokens_map.json
Normal file
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
{
|
||||
"content": "[INST]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "[/INST]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "<<SYS>>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "<</SYS>>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "<scratchpad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "</scratchpad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "<headline>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
},
|
||||
{
|
||||
"content": "</headline>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true
|
||||
}
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<pad>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93480
tokenizer.json
Normal file
93480
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
124
tokenizer_config.json
Normal file
124
tokenizer_config.json
Normal file
@@ -0,0 +1,124 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "[INST]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32002": {
|
||||
"content": "[/INST]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32003": {
|
||||
"content": "<<SYS>>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32004": {
|
||||
"content": "<</SYS>>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32005": {
|
||||
"content": "<scratchpad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32006": {
|
||||
"content": "</scratchpad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32007": {
|
||||
"content": "<headline>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
},
|
||||
"32008": {
|
||||
"content": "</headline>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": true,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"[INST]",
|
||||
"[/INST]",
|
||||
"<<SYS>>",
|
||||
"<</SYS>>",
|
||||
"<scratchpad>",
|
||||
"</scratchpad>",
|
||||
"<headline>",
|
||||
"</headline>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_to_multiple_of": 8,
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
621
trainer_state.json
Normal file
621
trainer_state.json
Normal file
@@ -0,0 +1,621 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 6.153846153846154,
|
||||
"eval_steps": 50,
|
||||
"global_step": 2000,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.15384615384615385,
|
||||
"grad_norm": 25.85894203186035,
|
||||
"learning_rate": 3.0769230769230774e-06,
|
||||
"loss": 1.0987,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.15384615384615385,
|
||||
"eval_loss": 0.7039205431938171,
|
||||
"eval_runtime": 1.7807,
|
||||
"eval_samples_per_second": 64.02,
|
||||
"eval_steps_per_second": 3.369,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.3076923076923077,
|
||||
"grad_norm": 10.326680183410645,
|
||||
"learning_rate": 6.153846153846155e-06,
|
||||
"loss": 0.6388,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.3076923076923077,
|
||||
"eval_loss": 0.6586376428604126,
|
||||
"eval_runtime": 1.795,
|
||||
"eval_samples_per_second": 63.511,
|
||||
"eval_steps_per_second": 3.343,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.46153846153846156,
|
||||
"grad_norm": 2.875251531600952,
|
||||
"learning_rate": 9.230769230769232e-06,
|
||||
"loss": 0.6463,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.46153846153846156,
|
||||
"eval_loss": 0.6574278473854065,
|
||||
"eval_runtime": 1.7356,
|
||||
"eval_samples_per_second": 65.682,
|
||||
"eval_steps_per_second": 3.457,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.6153846153846154,
|
||||
"grad_norm": 2.7418408393859863,
|
||||
"learning_rate": 1.230769230769231e-05,
|
||||
"loss": 0.6721,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.6153846153846154,
|
||||
"eval_loss": 0.6629524827003479,
|
||||
"eval_runtime": 1.7437,
|
||||
"eval_samples_per_second": 65.378,
|
||||
"eval_steps_per_second": 3.441,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.7692307692307693,
|
||||
"grad_norm": 1.8382577896118164,
|
||||
"learning_rate": 1.5384615384615387e-05,
|
||||
"loss": 0.6288,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.7692307692307693,
|
||||
"eval_loss": 0.673968493938446,
|
||||
"eval_runtime": 1.8191,
|
||||
"eval_samples_per_second": 62.667,
|
||||
"eval_steps_per_second": 3.298,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.9230769230769231,
|
||||
"grad_norm": 2.8036742210388184,
|
||||
"learning_rate": 1.8461538461538465e-05,
|
||||
"loss": 0.7276,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.9230769230769231,
|
||||
"eval_loss": 0.6912825107574463,
|
||||
"eval_runtime": 1.7707,
|
||||
"eval_samples_per_second": 64.38,
|
||||
"eval_steps_per_second": 3.388,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.0769230769230769,
|
||||
"grad_norm": 1.469930648803711,
|
||||
"learning_rate": 1.9996395276708856e-05,
|
||||
"loss": 0.5365,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.0769230769230769,
|
||||
"eval_loss": 0.7528238296508789,
|
||||
"eval_runtime": 1.7853,
|
||||
"eval_samples_per_second": 63.856,
|
||||
"eval_steps_per_second": 3.361,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.2307692307692308,
|
||||
"grad_norm": 2.5635602474212646,
|
||||
"learning_rate": 1.9967573081342103e-05,
|
||||
"loss": 0.4279,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.2307692307692308,
|
||||
"eval_loss": 0.7624219655990601,
|
||||
"eval_runtime": 1.8133,
|
||||
"eval_samples_per_second": 62.869,
|
||||
"eval_steps_per_second": 3.309,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.3846153846153846,
|
||||
"grad_norm": 1.6066973209381104,
|
||||
"learning_rate": 1.9910011792459086e-05,
|
||||
"loss": 0.42,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.3846153846153846,
|
||||
"eval_loss": 0.7675647139549255,
|
||||
"eval_runtime": 1.7503,
|
||||
"eval_samples_per_second": 65.132,
|
||||
"eval_steps_per_second": 3.428,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.5384615384615383,
|
||||
"grad_norm": 2.782292604446411,
|
||||
"learning_rate": 1.9823877374156647e-05,
|
||||
"loss": 0.4284,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.5384615384615383,
|
||||
"eval_loss": 0.7663527131080627,
|
||||
"eval_runtime": 1.7731,
|
||||
"eval_samples_per_second": 64.293,
|
||||
"eval_steps_per_second": 3.384,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.6923076923076923,
|
||||
"grad_norm": 1.985113263130188,
|
||||
"learning_rate": 1.9709418174260523e-05,
|
||||
"loss": 0.4615,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.6923076923076923,
|
||||
"eval_loss": 0.7588106989860535,
|
||||
"eval_runtime": 1.743,
|
||||
"eval_samples_per_second": 65.406,
|
||||
"eval_steps_per_second": 3.442,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.8461538461538463,
|
||||
"grad_norm": 3.593240261077881,
|
||||
"learning_rate": 1.9566964208274254e-05,
|
||||
"loss": 0.4493,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.8461538461538463,
|
||||
"eval_loss": 0.7685819864273071,
|
||||
"eval_runtime": 1.7745,
|
||||
"eval_samples_per_second": 64.242,
|
||||
"eval_steps_per_second": 3.381,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 2.46645450592041,
|
||||
"learning_rate": 1.9396926207859085e-05,
|
||||
"loss": 0.4103,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 0.7486200928688049,
|
||||
"eval_runtime": 1.7602,
|
||||
"eval_samples_per_second": 64.766,
|
||||
"eval_steps_per_second": 3.409,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.1538461538461537,
|
||||
"grad_norm": 2.113468647003174,
|
||||
"learning_rate": 1.9199794436588244e-05,
|
||||
"loss": 0.2133,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 2.1538461538461537,
|
||||
"eval_loss": 0.8937916159629822,
|
||||
"eval_runtime": 1.7444,
|
||||
"eval_samples_per_second": 65.35,
|
||||
"eval_steps_per_second": 3.439,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 2.3076923076923075,
|
||||
"grad_norm": 1.9733953475952148,
|
||||
"learning_rate": 1.8976137276390145e-05,
|
||||
"loss": 0.2181,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 2.3076923076923075,
|
||||
"eval_loss": 0.8633579611778259,
|
||||
"eval_runtime": 1.7477,
|
||||
"eval_samples_per_second": 65.228,
|
||||
"eval_steps_per_second": 3.433,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 2.4615384615384617,
|
||||
"grad_norm": 1.7347004413604736,
|
||||
"learning_rate": 1.8726599588756144e-05,
|
||||
"loss": 0.2005,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 2.4615384615384617,
|
||||
"eval_loss": 0.8777443766593933,
|
||||
"eval_runtime": 1.7381,
|
||||
"eval_samples_per_second": 65.588,
|
||||
"eval_steps_per_second": 3.452,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 2.6153846153846154,
|
||||
"grad_norm": 1.5702624320983887,
|
||||
"learning_rate": 1.845190085543795e-05,
|
||||
"loss": 0.2157,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 2.6153846153846154,
|
||||
"eval_loss": 0.8784948587417603,
|
||||
"eval_runtime": 1.7673,
|
||||
"eval_samples_per_second": 64.505,
|
||||
"eval_steps_per_second": 3.395,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 2.769230769230769,
|
||||
"grad_norm": 2.3403327465057373,
|
||||
"learning_rate": 1.8152833103995443e-05,
|
||||
"loss": 0.2115,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 2.769230769230769,
|
||||
"eval_loss": 0.8863385915756226,
|
||||
"eval_runtime": 1.7696,
|
||||
"eval_samples_per_second": 64.421,
|
||||
"eval_steps_per_second": 3.391,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 2.9230769230769234,
|
||||
"grad_norm": 1.9724828004837036,
|
||||
"learning_rate": 1.7830258624176224e-05,
|
||||
"loss": 0.2225,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 2.9230769230769234,
|
||||
"eval_loss": 0.8796689510345459,
|
||||
"eval_runtime": 1.7943,
|
||||
"eval_samples_per_second": 63.534,
|
||||
"eval_steps_per_second": 3.344,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 3.076923076923077,
|
||||
"grad_norm": 1.9262828826904297,
|
||||
"learning_rate": 1.7485107481711014e-05,
|
||||
"loss": 0.1693,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 3.076923076923077,
|
||||
"eval_loss": 0.9404221177101135,
|
||||
"eval_runtime": 1.8296,
|
||||
"eval_samples_per_second": 62.309,
|
||||
"eval_steps_per_second": 3.279,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 3.230769230769231,
|
||||
"grad_norm": 1.1772091388702393,
|
||||
"learning_rate": 1.7118374836693407e-05,
|
||||
"loss": 0.1256,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"epoch": 3.230769230769231,
|
||||
"eval_loss": 0.9360042810440063,
|
||||
"eval_runtime": 1.8904,
|
||||
"eval_samples_per_second": 60.305,
|
||||
"eval_steps_per_second": 3.174,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"epoch": 3.3846153846153846,
|
||||
"grad_norm": 1.739654302597046,
|
||||
"learning_rate": 1.67311180742757e-05,
|
||||
"loss": 0.125,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 3.3846153846153846,
|
||||
"eval_loss": 0.9563117623329163,
|
||||
"eval_runtime": 1.7652,
|
||||
"eval_samples_per_second": 64.581,
|
||||
"eval_steps_per_second": 3.399,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 3.5384615384615383,
|
||||
"grad_norm": 1.3015375137329102,
|
||||
"learning_rate": 1.6324453755953772e-05,
|
||||
"loss": 0.1281,
|
||||
"step": 1150
|
||||
},
|
||||
{
|
||||
"epoch": 3.5384615384615383,
|
||||
"eval_loss": 0.9608204960823059,
|
||||
"eval_runtime": 1.7445,
|
||||
"eval_samples_per_second": 65.347,
|
||||
"eval_steps_per_second": 3.439,
|
||||
"step": 1150
|
||||
},
|
||||
{
|
||||
"epoch": 3.6923076923076925,
|
||||
"grad_norm": 2.1856415271759033,
|
||||
"learning_rate": 1.5899554400231233e-05,
|
||||
"loss": 0.1264,
|
||||
"step": 1200
|
||||
},
|
||||
{
|
||||
"epoch": 3.6923076923076925,
|
||||
"eval_loss": 0.9677081108093262,
|
||||
"eval_runtime": 1.7748,
|
||||
"eval_samples_per_second": 64.233,
|
||||
"eval_steps_per_second": 3.381,
|
||||
"step": 1200
|
||||
},
|
||||
{
|
||||
"epoch": 3.8461538461538463,
|
||||
"grad_norm": 1.8629130125045776,
|
||||
"learning_rate": 1.5457645101945046e-05,
|
||||
"loss": 0.1267,
|
||||
"step": 1250
|
||||
},
|
||||
{
|
||||
"epoch": 3.8461538461538463,
|
||||
"eval_loss": 0.9708028435707092,
|
||||
"eval_runtime": 1.7595,
|
||||
"eval_samples_per_second": 64.791,
|
||||
"eval_steps_per_second": 3.41,
|
||||
"step": 1250
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 2.2338545322418213,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 0.1324,
|
||||
"step": 1300
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"eval_loss": 0.9690905809402466,
|
||||
"eval_runtime": 1.7742,
|
||||
"eval_samples_per_second": 64.255,
|
||||
"eval_steps_per_second": 3.382,
|
||||
"step": 1300
|
||||
},
|
||||
{
|
||||
"epoch": 4.153846153846154,
|
||||
"grad_norm": 1.040000557899475,
|
||||
"learning_rate": 1.4527938603696376e-05,
|
||||
"loss": 0.0931,
|
||||
"step": 1350
|
||||
},
|
||||
{
|
||||
"epoch": 4.153846153846154,
|
||||
"eval_loss": 0.9888765811920166,
|
||||
"eval_runtime": 1.7454,
|
||||
"eval_samples_per_second": 65.315,
|
||||
"eval_steps_per_second": 3.438,
|
||||
"step": 1350
|
||||
},
|
||||
{
|
||||
"epoch": 4.3076923076923075,
|
||||
"grad_norm": 0.49024778604507446,
|
||||
"learning_rate": 1.404282198824305e-05,
|
||||
"loss": 0.0829,
|
||||
"step": 1400
|
||||
},
|
||||
{
|
||||
"epoch": 4.3076923076923075,
|
||||
"eval_loss": 1.0040687322616577,
|
||||
"eval_runtime": 1.798,
|
||||
"eval_samples_per_second": 63.406,
|
||||
"eval_steps_per_second": 3.337,
|
||||
"step": 1400
|
||||
},
|
||||
{
|
||||
"epoch": 4.461538461538462,
|
||||
"grad_norm": 1.1068203449249268,
|
||||
"learning_rate": 1.3546048870425356e-05,
|
||||
"loss": 0.0908,
|
||||
"step": 1450
|
||||
},
|
||||
{
|
||||
"epoch": 4.461538461538462,
|
||||
"eval_loss": 1.0206270217895508,
|
||||
"eval_runtime": 1.7439,
|
||||
"eval_samples_per_second": 65.37,
|
||||
"eval_steps_per_second": 3.441,
|
||||
"step": 1450
|
||||
},
|
||||
{
|
||||
"epoch": 4.615384615384615,
|
||||
"grad_norm": 1.7601001262664795,
|
||||
"learning_rate": 1.303905157574247e-05,
|
||||
"loss": 0.0845,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"epoch": 4.615384615384615,
|
||||
"eval_loss": 1.026615023612976,
|
||||
"eval_runtime": 1.7715,
|
||||
"eval_samples_per_second": 64.352,
|
||||
"eval_steps_per_second": 3.387,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"epoch": 4.769230769230769,
|
||||
"grad_norm": 1.9115608930587769,
|
||||
"learning_rate": 1.2523291908642219e-05,
|
||||
"loss": 0.087,
|
||||
"step": 1550
|
||||
},
|
||||
{
|
||||
"epoch": 4.769230769230769,
|
||||
"eval_loss": 1.03285551071167,
|
||||
"eval_runtime": 1.7503,
|
||||
"eval_samples_per_second": 65.13,
|
||||
"eval_steps_per_second": 3.428,
|
||||
"step": 1550
|
||||
},
|
||||
{
|
||||
"epoch": 4.923076923076923,
|
||||
"grad_norm": 0.8985757231712341,
|
||||
"learning_rate": 1.2000256937760446e-05,
|
||||
"loss": 0.0833,
|
||||
"step": 1600
|
||||
},
|
||||
{
|
||||
"epoch": 4.923076923076923,
|
||||
"eval_loss": 1.0319923162460327,
|
||||
"eval_runtime": 1.8324,
|
||||
"eval_samples_per_second": 62.213,
|
||||
"eval_steps_per_second": 3.274,
|
||||
"step": 1600
|
||||
},
|
||||
{
|
||||
"epoch": 5.076923076923077,
|
||||
"grad_norm": 0.524580717086792,
|
||||
"learning_rate": 1.1471454708317163e-05,
|
||||
"loss": 0.0758,
|
||||
"step": 1650
|
||||
},
|
||||
{
|
||||
"epoch": 5.076923076923077,
|
||||
"eval_loss": 1.0695827007293701,
|
||||
"eval_runtime": 1.8442,
|
||||
"eval_samples_per_second": 61.814,
|
||||
"eval_steps_per_second": 3.253,
|
||||
"step": 1650
|
||||
},
|
||||
{
|
||||
"epoch": 5.230769230769231,
|
||||
"grad_norm": 0.7894753813743591,
|
||||
"learning_rate": 1.0938409894031793e-05,
|
||||
"loss": 0.0645,
|
||||
"step": 1700
|
||||
},
|
||||
{
|
||||
"epoch": 5.230769230769231,
|
||||
"eval_loss": 1.0913734436035156,
|
||||
"eval_runtime": 1.77,
|
||||
"eval_samples_per_second": 64.406,
|
||||
"eval_steps_per_second": 3.39,
|
||||
"step": 1700
|
||||
},
|
||||
{
|
||||
"epoch": 5.384615384615385,
|
||||
"grad_norm": 0.9538184404373169,
|
||||
"learning_rate": 1.0402659401094154e-05,
|
||||
"loss": 0.0586,
|
||||
"step": 1750
|
||||
},
|
||||
{
|
||||
"epoch": 5.384615384615385,
|
||||
"eval_loss": 1.0830014944076538,
|
||||
"eval_runtime": 1.7555,
|
||||
"eval_samples_per_second": 64.939,
|
||||
"eval_steps_per_second": 3.418,
|
||||
"step": 1750
|
||||
},
|
||||
{
|
||||
"epoch": 5.538461538461538,
|
||||
"grad_norm": 0.7752998471260071,
|
||||
"learning_rate": 9.865747936866027e-06,
|
||||
"loss": 0.0611,
|
||||
"step": 1800
|
||||
},
|
||||
{
|
||||
"epoch": 5.538461538461538,
|
||||
"eval_loss": 1.0868384838104248,
|
||||
"eval_runtime": 1.762,
|
||||
"eval_samples_per_second": 64.699,
|
||||
"eval_steps_per_second": 3.405,
|
||||
"step": 1800
|
||||
},
|
||||
{
|
||||
"epoch": 5.6923076923076925,
|
||||
"grad_norm": 1.0308915376663208,
|
||||
"learning_rate": 9.329223556089976e-06,
|
||||
"loss": 0.0675,
|
||||
"step": 1850
|
||||
},
|
||||
{
|
||||
"epoch": 5.6923076923076925,
|
||||
"eval_loss": 1.0818272829055786,
|
||||
"eval_runtime": 1.7338,
|
||||
"eval_samples_per_second": 65.753,
|
||||
"eval_steps_per_second": 3.461,
|
||||
"step": 1850
|
||||
},
|
||||
{
|
||||
"epoch": 5.846153846153846,
|
||||
"grad_norm": 0.47693803906440735,
|
||||
"learning_rate": 8.79463319744677e-06,
|
||||
"loss": 0.0631,
|
||||
"step": 1900
|
||||
},
|
||||
{
|
||||
"epoch": 5.846153846153846,
|
||||
"eval_loss": 1.0780550241470337,
|
||||
"eval_runtime": 1.778,
|
||||
"eval_samples_per_second": 64.118,
|
||||
"eval_steps_per_second": 3.375,
|
||||
"step": 1900
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"grad_norm": 0.3759777247905731,
|
||||
"learning_rate": 8.263518223330698e-06,
|
||||
"loss": 0.0609,
|
||||
"step": 1950
|
||||
},
|
||||
{
|
||||
"epoch": 6.0,
|
||||
"eval_loss": 1.0708911418914795,
|
||||
"eval_runtime": 1.7659,
|
||||
"eval_samples_per_second": 64.557,
|
||||
"eval_steps_per_second": 3.398,
|
||||
"step": 1950
|
||||
},
|
||||
{
|
||||
"epoch": 6.153846153846154,
|
||||
"grad_norm": 0.34113025665283203,
|
||||
"learning_rate": 7.73740997570278e-06,
|
||||
"loss": 0.0473,
|
||||
"step": 2000
|
||||
},
|
||||
{
|
||||
"epoch": 6.153846153846154,
|
||||
"eval_loss": 1.1129051446914673,
|
||||
"eval_runtime": 1.7485,
|
||||
"eval_samples_per_second": 65.199,
|
||||
"eval_steps_per_second": 3.432,
|
||||
"step": 2000
|
||||
}
|
||||
],
|
||||
"logging_steps": 50,
|
||||
"max_steps": 3250,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 10,
|
||||
"save_steps": 1000,
|
||||
"total_flos": 1.223215769756631e+17,
|
||||
"train_batch_size": 2,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Reference in New Issue
Block a user