初始化项目，由ModelHub XC社区提供模型
Model: alignment-handbook/mistral-7b-sft-constitutional-ai 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
|
||||
70
README.md
Normal file
70
README.md
Normal file
@@ -0,0 +1,70 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: mistralai/Mistral-7B-v0.1
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- HuggingFaceH4/cai-conversation-harmless
|
||||
- HuggingFaceH4/ultrachat_200k
|
||||
model-index:
|
||||
- name: mistral-7b-sft-constitutional-ai
|
||||
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. -->
|
||||
|
||||
# mistral-7b-sft-constitutional-ai
|
||||
|
||||
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/cai-conversation-harmless and the HuggingFaceH4/ultrachat_200k datasets.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.9344
|
||||
|
||||
## 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: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 256
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 0.9241 | 1.0 | 550 | 0.9344 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.36.2
|
||||
- Pytorch 2.1.2+cu121
|
||||
- Datasets 2.14.6
|
||||
- Tokenizers 0.15.1
|
||||
13
all_results.json
Normal file
13
all_results.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.9343938231468201,
|
||||
"eval_runtime": 143.0083,
|
||||
"eval_samples": 24266,
|
||||
"eval_samples_per_second": 108.476,
|
||||
"eval_steps_per_second": 1.699,
|
||||
"train_loss": 0.9703456902503967,
|
||||
"train_runtime": 5589.9273,
|
||||
"train_samples": 229133,
|
||||
"train_samples_per_second": 25.215,
|
||||
"train_steps_per_second": 0.098
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
8
eval_results.json
Normal file
8
eval_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.9343938231468201,
|
||||
"eval_runtime": 143.0083,
|
||||
"eval_samples": 24266,
|
||||
"eval_samples_per_second": 108.476,
|
||||
"eval_steps_per_second": 1.699
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c0e5b3fdfd71fbc05f4fbd182e375b0adabca2a11c0299a8548f4ca989fa4fc
|
||||
size 4943162336
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6d55ee6871eaf629651513e8cc554ac3ef9c141ac79e8457a2f2de2d9322a34
|
||||
size 4999819336
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a26597ee7386b448c45af889970bd16eb8340eeec541d9d2230abb91263f241
|
||||
size 4540516344
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:913cc1d70e4ec4217ddf87ebcd3a7f058772f46f890c0d8a7397aae661569a4a
|
||||
size 22412
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e23152cc68fd5e9d455bbadb69aed3b39c5cd54582445b6c661e30facbb7dfac
|
||||
size 359
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
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.
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"train_loss": 0.9703456902503967,
|
||||
"train_runtime": 5589.9273,
|
||||
"train_samples": 229133,
|
||||
"train_samples_per_second": 25.215,
|
||||
"train_steps_per_second": 0.098
|
||||
}
|
||||
704
trainer_state.json
Normal file
704
trainer_state.json
Normal file
@@ -0,0 +1,704 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.9986382206082615,
|
||||
"eval_steps": 500,
|
||||
"global_step": 550,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 3.6363636363636366e-07,
|
||||
"loss": 1.6989,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 1.8181818181818183e-06,
|
||||
"loss": 1.592,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"learning_rate": 3.6363636363636366e-06,
|
||||
"loss": 1.3096,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.03,
|
||||
"learning_rate": 5.4545454545454545e-06,
|
||||
"loss": 1.1801,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.04,
|
||||
"learning_rate": 7.272727272727273e-06,
|
||||
"loss": 1.1065,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"learning_rate": 9.090909090909091e-06,
|
||||
"loss": 1.0653,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"learning_rate": 1.0909090909090909e-05,
|
||||
"loss": 1.0523,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"learning_rate": 1.2727272727272728e-05,
|
||||
"loss": 1.0315,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.07,
|
||||
"learning_rate": 1.4545454545454546e-05,
|
||||
"loss": 1.0111,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"learning_rate": 1.6363636363636366e-05,
|
||||
"loss": 1.0113,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.09,
|
||||
"learning_rate": 1.8181818181818182e-05,
|
||||
"loss": 1.0169,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"learning_rate": 2e-05,
|
||||
"loss": 0.998,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.11,
|
||||
"learning_rate": 1.9994965423831853e-05,
|
||||
"loss": 1.0046,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"learning_rate": 1.9979866764718846e-05,
|
||||
"loss": 1.0102,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.13,
|
||||
"learning_rate": 1.9954719225730847e-05,
|
||||
"loss": 1.012,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.14,
|
||||
"learning_rate": 1.9919548128307954e-05,
|
||||
"loss": 1.0108,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"learning_rate": 1.9874388886763944e-05,
|
||||
"loss": 0.9918,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"learning_rate": 1.9819286972627066e-05,
|
||||
"loss": 0.9959,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"learning_rate": 1.9754297868854075e-05,
|
||||
"loss": 1.0019,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.17,
|
||||
"learning_rate": 1.9679487013963566e-05,
|
||||
"loss": 0.9897,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.18,
|
||||
"learning_rate": 1.9594929736144978e-05,
|
||||
"loss": 1.004,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"learning_rate": 1.9500711177409456e-05,
|
||||
"loss": 0.9838,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"learning_rate": 1.9396926207859085e-05,
|
||||
"loss": 0.9717,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.21,
|
||||
"learning_rate": 1.9283679330160726e-05,
|
||||
"loss": 0.9931,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.22,
|
||||
"learning_rate": 1.9161084574320696e-05,
|
||||
"loss": 0.9785,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"learning_rate": 1.9029265382866216e-05,
|
||||
"loss": 0.9876,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.24,
|
||||
"learning_rate": 1.8888354486549238e-05,
|
||||
"loss": 0.9785,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 1.873849377069785e-05,
|
||||
"loss": 0.9739,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 1.8579834132349773e-05,
|
||||
"loss": 0.9751,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.26,
|
||||
"learning_rate": 1.8412535328311813e-05,
|
||||
"loss": 0.9923,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.27,
|
||||
"learning_rate": 1.8236765814298328e-05,
|
||||
"loss": 0.9823,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"learning_rate": 1.8052702575310588e-05,
|
||||
"loss": 0.9691,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.29,
|
||||
"learning_rate": 1.7860530947427878e-05,
|
||||
"loss": 0.98,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"learning_rate": 1.766044443118978e-05,
|
||||
"loss": 0.978,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 1.745264449675755e-05,
|
||||
"loss": 0.9827,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"learning_rate": 1.72373403810507e-05,
|
||||
"loss": 0.9785,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.33,
|
||||
"learning_rate": 1.7014748877063212e-05,
|
||||
"loss": 0.9826,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"learning_rate": 1.6785094115571323e-05,
|
||||
"loss": 0.9877,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"learning_rate": 1.6548607339452853e-05,
|
||||
"loss": 0.982,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.35,
|
||||
"learning_rate": 1.6305526670845225e-05,
|
||||
"loss": 0.973,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"learning_rate": 1.6056096871376667e-05,
|
||||
"loss": 0.9737,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.37,
|
||||
"learning_rate": 1.5800569095711983e-05,
|
||||
"loss": 0.9677,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"learning_rate": 1.5539200638661106e-05,
|
||||
"loss": 0.973,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"learning_rate": 1.5272254676105026e-05,
|
||||
"loss": 0.9678,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 0.9669,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.41,
|
||||
"learning_rate": 1.472271074772683e-05,
|
||||
"loss": 0.9834,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.42,
|
||||
"learning_rate": 1.4440666126057743e-05,
|
||||
"loss": 0.9625,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.43,
|
||||
"learning_rate": 1.4154150130018867e-05,
|
||||
"loss": 0.9639,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 1.3863451256931286e-05,
|
||||
"loss": 0.9643,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 1.356886221591872e-05,
|
||||
"loss": 0.9601,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 0.45,
|
||||
"learning_rate": 1.3270679633174219e-05,
|
||||
"loss": 0.953,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.46,
|
||||
"learning_rate": 1.296920375328275e-05,
|
||||
"loss": 0.9619,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 0.47,
|
||||
"learning_rate": 1.266473813690035e-05,
|
||||
"loss": 0.9701,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"learning_rate": 1.2357589355094275e-05,
|
||||
"loss": 0.9593,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"learning_rate": 1.2048066680651908e-05,
|
||||
"loss": 0.9559,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 1.1736481776669307e-05,
|
||||
"loss": 0.9474,
|
||||
"step": 275
|
||||
},
|
||||
{
|
||||
"epoch": 0.51,
|
||||
"learning_rate": 1.1423148382732854e-05,
|
||||
"loss": 0.9705,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"learning_rate": 1.1108381999010111e-05,
|
||||
"loss": 0.9541,
|
||||
"step": 285
|
||||
},
|
||||
{
|
||||
"epoch": 0.53,
|
||||
"learning_rate": 1.0792499568567885e-05,
|
||||
"loss": 0.9464,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"learning_rate": 1.0475819158237426e-05,
|
||||
"loss": 0.9634,
|
||||
"step": 295
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"learning_rate": 1.015865963834808e-05,
|
||||
"loss": 0.9418,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.55,
|
||||
"learning_rate": 9.841340361651921e-06,
|
||||
"loss": 0.9425,
|
||||
"step": 305
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"learning_rate": 9.524180841762577e-06,
|
||||
"loss": 0.945,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.57,
|
||||
"learning_rate": 9.207500431432115e-06,
|
||||
"loss": 0.9463,
|
||||
"step": 315
|
||||
},
|
||||
{
|
||||
"epoch": 0.58,
|
||||
"learning_rate": 8.89161800098989e-06,
|
||||
"loss": 0.9514,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.59,
|
||||
"learning_rate": 8.576851617267151e-06,
|
||||
"loss": 0.937,
|
||||
"step": 325
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"learning_rate": 8.263518223330698e-06,
|
||||
"loss": 0.9444,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.61,
|
||||
"learning_rate": 7.951933319348095e-06,
|
||||
"loss": 0.9529,
|
||||
"step": 335
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"learning_rate": 7.642410644905726e-06,
|
||||
"loss": 0.9397,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"learning_rate": 7.335261863099652e-06,
|
||||
"loss": 0.9284,
|
||||
"step": 345
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"learning_rate": 7.0307962467172555e-06,
|
||||
"loss": 0.936,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"learning_rate": 6.729320366825785e-06,
|
||||
"loss": 0.9419,
|
||||
"step": 355
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"learning_rate": 6.431137784081283e-06,
|
||||
"loss": 0.9369,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.66,
|
||||
"learning_rate": 6.136548743068713e-06,
|
||||
"loss": 0.9404,
|
||||
"step": 365
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"learning_rate": 5.845849869981137e-06,
|
||||
"loss": 0.9283,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.68,
|
||||
"learning_rate": 5.559333873942259e-06,
|
||||
"loss": 0.9346,
|
||||
"step": 375
|
||||
},
|
||||
{
|
||||
"epoch": 0.69,
|
||||
"learning_rate": 5.277289252273175e-06,
|
||||
"loss": 0.927,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"learning_rate": 5.000000000000003e-06,
|
||||
"loss": 0.9362,
|
||||
"step": 385
|
||||
},
|
||||
{
|
||||
"epoch": 0.71,
|
||||
"learning_rate": 4.727745323894976e-06,
|
||||
"loss": 0.947,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.72,
|
||||
"learning_rate": 4.460799361338898e-06,
|
||||
"loss": 0.9318,
|
||||
"step": 395
|
||||
},
|
||||
{
|
||||
"epoch": 0.73,
|
||||
"learning_rate": 4.19943090428802e-06,
|
||||
"loss": 0.924,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.74,
|
||||
"learning_rate": 3.943903128623336e-06,
|
||||
"loss": 0.9372,
|
||||
"step": 405
|
||||
},
|
||||
{
|
||||
"epoch": 0.74,
|
||||
"learning_rate": 3.6944733291547784e-06,
|
||||
"loss": 0.9273,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"learning_rate": 3.4513926605471504e-06,
|
||||
"loss": 0.9325,
|
||||
"step": 415
|
||||
},
|
||||
{
|
||||
"epoch": 0.76,
|
||||
"learning_rate": 3.2149058844286796e-06,
|
||||
"loss": 0.9203,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.77,
|
||||
"learning_rate": 2.9852511229367862e-06,
|
||||
"loss": 0.9248,
|
||||
"step": 425
|
||||
},
|
||||
{
|
||||
"epoch": 0.78,
|
||||
"learning_rate": 2.7626596189492983e-06,
|
||||
"loss": 0.9276,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.79,
|
||||
"learning_rate": 2.5473555032424534e-06,
|
||||
"loss": 0.9228,
|
||||
"step": 435
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"learning_rate": 2.339555568810221e-06,
|
||||
"loss": 0.9284,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.81,
|
||||
"learning_rate": 2.1394690525721275e-06,
|
||||
"loss": 0.9285,
|
||||
"step": 445
|
||||
},
|
||||
{
|
||||
"epoch": 0.82,
|
||||
"learning_rate": 1.947297424689414e-06,
|
||||
"loss": 0.9314,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.83,
|
||||
"learning_rate": 1.7632341857016733e-06,
|
||||
"loss": 0.9163,
|
||||
"step": 455
|
||||
},
|
||||
{
|
||||
"epoch": 0.84,
|
||||
"learning_rate": 1.587464671688187e-06,
|
||||
"loss": 0.9263,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.84,
|
||||
"learning_rate": 1.4201658676502294e-06,
|
||||
"loss": 0.9303,
|
||||
"step": 465
|
||||
},
|
||||
{
|
||||
"epoch": 0.85,
|
||||
"learning_rate": 1.2615062293021508e-06,
|
||||
"loss": 0.9202,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.86,
|
||||
"learning_rate": 1.1116455134507665e-06,
|
||||
"loss": 0.9149,
|
||||
"step": 475
|
||||
},
|
||||
{
|
||||
"epoch": 0.87,
|
||||
"learning_rate": 9.707346171337895e-07,
|
||||
"loss": 0.9147,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.88,
|
||||
"learning_rate": 8.389154256793042e-07,
|
||||
"loss": 0.9155,
|
||||
"step": 485
|
||||
},
|
||||
{
|
||||
"epoch": 0.89,
|
||||
"learning_rate": 7.163206698392744e-07,
|
||||
"loss": 0.9227,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 0.9,
|
||||
"learning_rate": 6.030737921409169e-07,
|
||||
"loss": 0.9236,
|
||||
"step": 495
|
||||
},
|
||||
{
|
||||
"epoch": 0.91,
|
||||
"learning_rate": 4.992888225905467e-07,
|
||||
"loss": 0.9196,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.92,
|
||||
"learning_rate": 4.0507026385502747e-07,
|
||||
"loss": 0.928,
|
||||
"step": 505
|
||||
},
|
||||
{
|
||||
"epoch": 0.93,
|
||||
"learning_rate": 3.2051298603643754e-07,
|
||||
"loss": 0.9164,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 0.94,
|
||||
"learning_rate": 2.4570213114592957e-07,
|
||||
"loss": 0.9266,
|
||||
"step": 515
|
||||
},
|
||||
{
|
||||
"epoch": 0.94,
|
||||
"learning_rate": 1.8071302737293294e-07,
|
||||
"loss": 0.9243,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.95,
|
||||
"learning_rate": 1.2561111323605714e-07,
|
||||
"loss": 0.9185,
|
||||
"step": 525
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"learning_rate": 8.04518716920466e-08,
|
||||
"loss": 0.9124,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 0.97,
|
||||
"learning_rate": 4.528077426915412e-08,
|
||||
"loss": 0.9208,
|
||||
"step": 535
|
||||
},
|
||||
{
|
||||
"epoch": 0.98,
|
||||
"learning_rate": 2.013323528115674e-08,
|
||||
"loss": 0.9314,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 0.99,
|
||||
"learning_rate": 5.034576168149175e-09,
|
||||
"loss": 0.9243,
|
||||
"step": 545
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.9241,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.9343938231468201,
|
||||
"eval_runtime": 144.3354,
|
||||
"eval_samples_per_second": 107.479,
|
||||
"eval_steps_per_second": 1.684,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 550,
|
||||
"total_flos": 460425862840320.0,
|
||||
"train_loss": 0.9703456902503967,
|
||||
"train_runtime": 5589.9273,
|
||||
"train_samples_per_second": 25.215,
|
||||
"train_steps_per_second": 0.098
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 550,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 100,
|
||||
"total_flos": 460425862840320.0,
|
||||
"train_batch_size": 8,
|
||||
"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:a45082055c0d4ef930f89fe1cb14835c9aed9348edc7f20aa4104abb8bd01547
|
||||
size 5880
|
||||
Reference in New Issue
Block a user