初始化项目，由ModelHub XC社区提供模型
Model: kykim0/Llama-2-7b-ultrachat200k-2e 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
|
||||
65
README.md
Normal file
65
README.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-2-7b-hf
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- HuggingFaceH4/ultrachat_200k
|
||||
model-index:
|
||||
- name: Llama-2-7b-hf-sft-full-2e
|
||||
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. -->
|
||||
|
||||
# Llama-2-7b-hf-sft-full-2e
|
||||
|
||||
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 HuggingFaceH4/ultrachat_200k dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.9258
|
||||
|
||||
## 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: 16
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 16
|
||||
- total_train_batch_size: 512
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: cosine
|
||||
- num_epochs: 2.0
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 0.9312 | 0.7 | 285 | 0.9351 |
|
||||
| 0.8747 | 1.7 | 570 | 0.9257 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.36.2
|
||||
- Pytorch 2.1.2
|
||||
- Datasets 2.14.6
|
||||
- Tokenizers 0.15.0
|
||||
13
all_results.json
Normal file
13
all_results.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"eval_loss": 0.9257832765579224,
|
||||
"eval_runtime": 653.1267,
|
||||
"eval_samples": 23110,
|
||||
"eval_samples_per_second": 35.384,
|
||||
"eval_steps_per_second": 0.554,
|
||||
"train_loss": 0.9215259830156962,
|
||||
"train_runtime": 46918.2161,
|
||||
"train_samples": 207865,
|
||||
"train_samples_per_second": 8.861,
|
||||
"train_steps_per_second": 0.017
|
||||
}
|
||||
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": "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": 1.7,
|
||||
"eval_loss": 0.9257832765579224,
|
||||
"eval_runtime": 653.1267,
|
||||
"eval_samples": 23110,
|
||||
"eval_samples_per_second": 35.384,
|
||||
"eval_steps_per_second": 0.554
|
||||
}
|
||||
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": "4.36.2"
|
||||
}
|
||||
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 sha256:607f64b9ee054f18e9657f1f99ea3e2265a01d70eb2442679925527bcc864234
|
||||
size 4938985352
|
||||
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:dc5fc71d8bb7b895e30488694b8aad2b5d9c9cbf17ce8576b51f1c49abf44f91
|
||||
size 4947390880
|
||||
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:cd531f27a386e690143c9a97351beb73dbd3dd2ea2e9897dd938682aa3a936f4
|
||||
size 3590488816
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476831232
|
||||
},
|
||||
"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-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-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"
|
||||
}
|
||||
}
|
||||
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
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
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.
42
tokenizer_config.json
Normal file
42
tokenizer_config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"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": false,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"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": 1.7,
|
||||
"train_loss": 0.9215259830156962,
|
||||
"train_runtime": 46918.2161,
|
||||
"train_samples": 207865,
|
||||
"train_samples_per_second": 8.861,
|
||||
"train_steps_per_second": 0.017
|
||||
}
|
||||
736
trainer_state.json
Normal file
736
trainer_state.json
Normal file
@@ -0,0 +1,736 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.7012007389162562,
|
||||
"eval_steps": 500,
|
||||
"global_step": 570,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0,
|
||||
"learning_rate": 1.999992515597253e-05,
|
||||
"loss": 1.5474,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.01,
|
||||
"learning_rate": 1.9998128955328933e-05,
|
||||
"loss": 1.182,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"learning_rate": 1.999251652147735e-05,
|
||||
"loss": 1.0465,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04,
|
||||
"learning_rate": 1.9983164798668152e-05,
|
||||
"loss": 1.0136,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"learning_rate": 1.997007728639956e-05,
|
||||
"loss": 1.0103,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"learning_rate": 1.9953258882135594e-05,
|
||||
"loss": 0.9887,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.07,
|
||||
"learning_rate": 1.9932715879473385e-05,
|
||||
"loss": 0.9841,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.09,
|
||||
"learning_rate": 1.990845596578807e-05,
|
||||
"loss": 0.9791,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"learning_rate": 1.9880488219356086e-05,
|
||||
"loss": 0.9779,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.11,
|
||||
"learning_rate": 1.9848823105958023e-05,
|
||||
"loss": 0.9757,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"learning_rate": 1.981347247496222e-05,
|
||||
"loss": 0.9683,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.14,
|
||||
"learning_rate": 1.9774449554890615e-05,
|
||||
"loss": 0.967,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"learning_rate": 1.973176894846855e-05,
|
||||
"loss": 0.9689,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"learning_rate": 1.968544662716026e-05,
|
||||
"loss": 0.9559,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.17,
|
||||
"learning_rate": 1.963549992519223e-05,
|
||||
"loss": 0.9524,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.18,
|
||||
"learning_rate": 1.9581947533066577e-05,
|
||||
"loss": 0.9517,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"learning_rate": 1.9524809490566878e-05,
|
||||
"loss": 0.9569,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.21,
|
||||
"learning_rate": 1.9464107179259126e-05,
|
||||
"loss": 0.9547,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.22,
|
||||
"learning_rate": 1.939986331449053e-05,
|
||||
"loss": 0.9612,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"learning_rate": 1.9332101936889262e-05,
|
||||
"loss": 0.9497,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"learning_rate": 1.926084840336821e-05,
|
||||
"loss": 0.9406,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.26,
|
||||
"learning_rate": 1.918612937763622e-05,
|
||||
"loss": 0.9517,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.27,
|
||||
"learning_rate": 1.910797282022027e-05,
|
||||
"loss": 0.9667,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"learning_rate": 1.9026407978002415e-05,
|
||||
"loss": 0.9505,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"learning_rate": 1.894146537327533e-05,
|
||||
"loss": 0.9409,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"learning_rate": 1.8853176792320598e-05,
|
||||
"loss": 0.946,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.32,
|
||||
"learning_rate": 1.8761575273514005e-05,
|
||||
"loss": 0.9455,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.33,
|
||||
"learning_rate": 1.866669509496227e-05,
|
||||
"loss": 0.949,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"learning_rate": 1.8568571761675893e-05,
|
||||
"loss": 0.9583,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"learning_rate": 1.8467241992282842e-05,
|
||||
"loss": 0.9387,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.37,
|
||||
"learning_rate": 1.8362743705288127e-05,
|
||||
"loss": 0.9492,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.38,
|
||||
"learning_rate": 1.825511600488435e-05,
|
||||
"loss": 0.9404,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"learning_rate": 1.814439916631857e-05,
|
||||
"loss": 0.9419,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.41,
|
||||
"learning_rate": 1.803063462082095e-05,
|
||||
"loss": 0.9337,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 0.42,
|
||||
"learning_rate": 1.791386494010081e-05,
|
||||
"loss": 0.936,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.43,
|
||||
"learning_rate": 1.7794133820415916e-05,
|
||||
"loss": 0.942,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"learning_rate": 1.7671486066220965e-05,
|
||||
"loss": 0.9367,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.46,
|
||||
"learning_rate": 1.7545967573401336e-05,
|
||||
"loss": 0.9333,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 0.47,
|
||||
"learning_rate": 1.7417625312098453e-05,
|
||||
"loss": 0.9438,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"learning_rate": 1.728650730913312e-05,
|
||||
"loss": 0.9453,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"learning_rate": 1.7152662630033506e-05,
|
||||
"loss": 0.941,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"learning_rate": 1.7016141360674307e-05,
|
||||
"loss": 0.9361,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 0.52,
|
||||
"learning_rate": 1.6876994588534234e-05,
|
||||
"loss": 0.9346,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.53,
|
||||
"learning_rate": 1.6735274383578593e-05,
|
||||
"loss": 0.9343,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"learning_rate": 1.659103377877423e-05,
|
||||
"loss": 0.9369,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.55,
|
||||
"learning_rate": 1.6444326750244145e-05,
|
||||
"loss": 0.9483,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.57,
|
||||
"learning_rate": 1.629520819706912e-05,
|
||||
"loss": 0.935,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.58,
|
||||
"learning_rate": 1.614373392074402e-05,
|
||||
"loss": 0.9382,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.59,
|
||||
"learning_rate": 1.598996060429634e-05,
|
||||
"loss": 0.9345,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"learning_rate": 1.5833945791074943e-05,
|
||||
"loss": 0.9369,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"learning_rate": 1.56757478632168e-05,
|
||||
"loss": 0.9393,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.63,
|
||||
"learning_rate": 1.5515426019799898e-05,
|
||||
"loss": 0.9406,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"learning_rate": 1.5353040254690396e-05,
|
||||
"loss": 0.9368,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"learning_rate": 1.5188651334092373e-05,
|
||||
"loss": 0.9229,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"learning_rate": 1.5022320773808612e-05,
|
||||
"loss": 0.9341,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.68,
|
||||
"learning_rate": 1.4854110816220805e-05,
|
||||
"loss": 0.9323,
|
||||
"step": 275
|
||||
},
|
||||
{
|
||||
"epoch": 0.69,
|
||||
"learning_rate": 1.4684084406997903e-05,
|
||||
"loss": 0.9345,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"learning_rate": 1.4512305171541287e-05,
|
||||
"loss": 0.9312,
|
||||
"step": 285
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"eval_loss": 0.9350774884223938,
|
||||
"eval_runtime": 652.1015,
|
||||
"eval_samples_per_second": 35.439,
|
||||
"eval_steps_per_second": 0.555,
|
||||
"step": 285
|
||||
},
|
||||
{
|
||||
"epoch": 1.01,
|
||||
"learning_rate": 1.4338837391175582e-05,
|
||||
"loss": 0.9066,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.02,
|
||||
"learning_rate": 1.4163745979093997e-05,
|
||||
"loss": 0.9055,
|
||||
"step": 295
|
||||
},
|
||||
{
|
||||
"epoch": 1.04,
|
||||
"learning_rate": 1.3987096456067236e-05,
|
||||
"loss": 0.8936,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.05,
|
||||
"learning_rate": 1.3808954925925042e-05,
|
||||
"loss": 0.9135,
|
||||
"step": 305
|
||||
},
|
||||
{
|
||||
"epoch": 1.06,
|
||||
"learning_rate": 1.3629388050819547e-05,
|
||||
"loss": 0.9013,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.07,
|
||||
"learning_rate": 1.3448463026279706e-05,
|
||||
"loss": 0.8976,
|
||||
"step": 315
|
||||
},
|
||||
{
|
||||
"epoch": 1.09,
|
||||
"learning_rate": 1.3266247556066122e-05,
|
||||
"loss": 0.8975,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.1,
|
||||
"learning_rate": 1.3082809826835707e-05,
|
||||
"loss": 0.9009,
|
||||
"step": 325
|
||||
},
|
||||
{
|
||||
"epoch": 1.11,
|
||||
"learning_rate": 1.2898218482625606e-05,
|
||||
"loss": 0.8994,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.12,
|
||||
"learning_rate": 1.2712542599165998e-05,
|
||||
"loss": 0.8943,
|
||||
"step": 335
|
||||
},
|
||||
{
|
||||
"epoch": 1.13,
|
||||
"learning_rate": 1.252585165803135e-05,
|
||||
"loss": 0.8928,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.15,
|
||||
"learning_rate": 1.233821552063977e-05,
|
||||
"loss": 0.8967,
|
||||
"step": 345
|
||||
},
|
||||
{
|
||||
"epoch": 1.16,
|
||||
"learning_rate": 1.2149704402110243e-05,
|
||||
"loss": 0.8833,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.17,
|
||||
"learning_rate": 1.1960388844987529e-05,
|
||||
"loss": 0.8832,
|
||||
"step": 355
|
||||
},
|
||||
{
|
||||
"epoch": 1.18,
|
||||
"learning_rate": 1.1770339692844484e-05,
|
||||
"loss": 0.8823,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.2,
|
||||
"learning_rate": 1.157962806377179e-05,
|
||||
"loss": 0.8875,
|
||||
"step": 365
|
||||
},
|
||||
{
|
||||
"epoch": 1.21,
|
||||
"learning_rate": 1.1388325323764889e-05,
|
||||
"loss": 0.8855,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.22,
|
||||
"learning_rate": 1.1196503060018243e-05,
|
||||
"loss": 0.8897,
|
||||
"step": 375
|
||||
},
|
||||
{
|
||||
"epoch": 1.23,
|
||||
"learning_rate": 1.1004233054136726e-05,
|
||||
"loss": 0.8806,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"learning_rate": 1.0811587255274313e-05,
|
||||
"loss": 0.8747,
|
||||
"step": 385
|
||||
},
|
||||
{
|
||||
"epoch": 1.26,
|
||||
"learning_rate": 1.0618637753210086e-05,
|
||||
"loss": 0.8863,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.27,
|
||||
"learning_rate": 1.0425456751371564e-05,
|
||||
"loss": 0.8936,
|
||||
"step": 395
|
||||
},
|
||||
{
|
||||
"epoch": 1.28,
|
||||
"learning_rate": 1.0232116539815558e-05,
|
||||
"loss": 0.8833,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.29,
|
||||
"learning_rate": 1.0038689468176575e-05,
|
||||
"loss": 0.8783,
|
||||
"step": 405
|
||||
},
|
||||
{
|
||||
"epoch": 1.31,
|
||||
"learning_rate": 9.845247918592937e-06,
|
||||
"loss": 0.8799,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.32,
|
||||
"learning_rate": 9.651864278620752e-06,
|
||||
"loss": 0.8795,
|
||||
"step": 415
|
||||
},
|
||||
{
|
||||
"epoch": 1.33,
|
||||
"learning_rate": 9.458610914145826e-06,
|
||||
"loss": 0.882,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.34,
|
||||
"learning_rate": 9.26556014230371e-06,
|
||||
"loss": 0.8911,
|
||||
"step": 425
|
||||
},
|
||||
{
|
||||
"epoch": 1.36,
|
||||
"learning_rate": 9.072784204417995e-06,
|
||||
"loss": 0.8765,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.37,
|
||||
"learning_rate": 8.880355238966923e-06,
|
||||
"loss": 0.8852,
|
||||
"step": 435
|
||||
},
|
||||
{
|
||||
"epoch": 1.38,
|
||||
"learning_rate": 8.688345254588579e-06,
|
||||
"loss": 0.874,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.39,
|
||||
"learning_rate": 8.496826103134572e-06,
|
||||
"loss": 0.8766,
|
||||
"step": 445
|
||||
},
|
||||
{
|
||||
"epoch": 1.41,
|
||||
"learning_rate": 8.305869452782446e-06,
|
||||
"loss": 0.8686,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.42,
|
||||
"learning_rate": 8.115546761216822e-06,
|
||||
"loss": 0.8749,
|
||||
"step": 455
|
||||
},
|
||||
{
|
||||
"epoch": 1.43,
|
||||
"learning_rate": 7.92592924888925e-06,
|
||||
"loss": 0.8771,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 1.44,
|
||||
"learning_rate": 7.73708787236694e-06,
|
||||
"loss": 0.876,
|
||||
"step": 465
|
||||
},
|
||||
{
|
||||
"epoch": 1.45,
|
||||
"learning_rate": 7.549093297780133e-06,
|
||||
"loss": 0.8727,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 1.47,
|
||||
"learning_rate": 7.362015874378219e-06,
|
||||
"loss": 0.8772,
|
||||
"step": 475
|
||||
},
|
||||
{
|
||||
"epoch": 1.48,
|
||||
"learning_rate": 7.175925608204428e-06,
|
||||
"loss": 0.8825,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 1.49,
|
||||
"learning_rate": 6.990892135898937e-06,
|
||||
"loss": 0.8822,
|
||||
"step": 485
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"learning_rate": 6.806984698640202e-06,
|
||||
"loss": 0.8743,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 1.52,
|
||||
"learning_rate": 6.624272116234319e-06,
|
||||
"loss": 0.8738,
|
||||
"step": 495
|
||||
},
|
||||
{
|
||||
"epoch": 1.53,
|
||||
"learning_rate": 6.442822761362015e-06,
|
||||
"loss": 0.8782,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.54,
|
||||
"learning_rate": 6.262704533992995e-06,
|
||||
"loss": 0.8742,
|
||||
"step": 505
|
||||
},
|
||||
{
|
||||
"epoch": 1.55,
|
||||
"learning_rate": 6.083984835977154e-06,
|
||||
"loss": 0.8874,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 1.57,
|
||||
"learning_rate": 5.9067305458222054e-06,
|
||||
"loss": 0.8786,
|
||||
"step": 515
|
||||
},
|
||||
{
|
||||
"epoch": 1.58,
|
||||
"learning_rate": 5.731007993667155e-06,
|
||||
"loss": 0.8789,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 1.59,
|
||||
"learning_rate": 5.556882936460966e-06,
|
||||
"loss": 0.8759,
|
||||
"step": 525
|
||||
},
|
||||
{
|
||||
"epoch": 1.6,
|
||||
"learning_rate": 5.38442053335571e-06,
|
||||
"loss": 0.8791,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 1.61,
|
||||
"learning_rate": 5.213685321323451e-06,
|
||||
"loss": 0.8808,
|
||||
"step": 535
|
||||
},
|
||||
{
|
||||
"epoch": 1.63,
|
||||
"learning_rate": 5.044741191005908e-06,
|
||||
"loss": 0.8846,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 1.64,
|
||||
"learning_rate": 4.877651362806038e-06,
|
||||
"loss": 0.8833,
|
||||
"step": 545
|
||||
},
|
||||
{
|
||||
"epoch": 1.65,
|
||||
"learning_rate": 4.712478363230361e-06,
|
||||
"loss": 0.8654,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.66,
|
||||
"learning_rate": 4.5492840014910145e-06,
|
||||
"loss": 0.88,
|
||||
"step": 555
|
||||
},
|
||||
{
|
||||
"epoch": 1.68,
|
||||
"learning_rate": 4.388129346376177e-06,
|
||||
"loss": 0.8759,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.69,
|
||||
"learning_rate": 4.22907470339758e-06,
|
||||
"loss": 0.8815,
|
||||
"step": 565
|
||||
},
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"learning_rate": 4.07217959222365e-06,
|
||||
"loss": 0.8747,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"eval_loss": 0.9257117509841919,
|
||||
"eval_runtime": 652.8923,
|
||||
"eval_samples_per_second": 35.396,
|
||||
"eval_steps_per_second": 0.554,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"step": 570,
|
||||
"total_flos": 955556403609600.0,
|
||||
"train_loss": 0.9215259830156962,
|
||||
"train_runtime": 46918.2161,
|
||||
"train_samples_per_second": 8.861,
|
||||
"train_steps_per_second": 0.017
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 812,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 500,
|
||||
"total_flos": 955556403609600.0,
|
||||
"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:cfefb061504e5e60e55791155f1db2b781f11ab2c532f0f6488c6d022d33519a
|
||||
size 5880
|
||||
Reference in New Issue
Block a user