初始化项目，由ModelHub XC社区提供模型
Model: voidful/qd-phi-1_5 Source: Original Platform
This commit is contained in:
ModelHub XC
50
.gitattributes
vendored
Normal file
50
.gitattributes
vendored
Normal file
@@ -0,0 +1,50 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
||||
88
README.md
Normal file
88
README.md
Normal file
@@ -0,0 +1,88 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: mit
|
||||
datasets:
|
||||
- corbyrosset/researchy_questions
|
||||
---
|
||||
## Model Summary
|
||||
|
||||
The language model Phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as [phi-1](https://huggingface.co/microsoft/phi-1), augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters.
|
||||
|
||||
We've trained Microsoft Research's phi-1.5, 1.3B parameter model with question decomposition datasets.
|
||||
|
||||
## How to Use
|
||||
|
||||
Phi-1.5 has been integrated in the `transformers` version 4.37.0. If you are using a lower version, ensure that you are doing the following:
|
||||
|
||||
* When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function.
|
||||
|
||||
The current `transformers` version can be verified with: `pip list | grep transformers`.
|
||||
|
||||
## Example
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
torch.set_default_device("cuda")
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("voidful/qd-phi-1_5",trust_remote_code=True)
|
||||
tokenizer = AutoTokenizer.from_pretrained("voidful/qd-phi-1_5", trust_remote_code=True,device_map="auto")
|
||||
|
||||
inputs = tokenizer("Is it better to love or to be loved?", return_tensors="pt", return_attention_mask=True)
|
||||
|
||||
outputs = model.generate(**inputs, max_length=1024)
|
||||
text = tokenizer.batch_decode(outputs)[0]
|
||||
print(text)
|
||||
```
|
||||
|
||||
## Result
|
||||
*Question* Is it better to love or to be loved?
|
||||
|
||||
*Decomposition*
|
||||
```json
|
||||
{
|
||||
"What does it mean to love?": [
|
||||
"How do different philosophical, psychological, and cultural perspectives define love?",
|
||||
"What are the characteristics and types of love?",
|
||||
"How does love affect human behavior and well-being?"
|
||||
],
|
||||
"What does it mean to be loved?": [
|
||||
"How do different philosophical, psychological, and cultural perspectives define being loved?",
|
||||
"What are the characteristics and types of being loved?",
|
||||
"How does being loved affect human behavior and well-being?"
|
||||
],
|
||||
"What are the benefits and drawbacks of loving oneself?": [
|
||||
"How does loving oneself relate to self-esteem, self-acceptance, and self-care?",
|
||||
"How does loving oneself affect one's relationships with others?",
|
||||
"What are the challenges and risks of loving oneself?"
|
||||
],
|
||||
"What are the benefits and drawbacks of being loved by others?": [
|
||||
"How does being loved by others relate to social connection, belonging, and support?",
|
||||
"How does being loved by others affect one's identity, autonomy, and agency?",
|
||||
"What are the challenges and risks of being loved by others?"
|
||||
],
|
||||
"How do the concepts of loving and being loved interact and influence each other?": [
|
||||
"How do different situations and contexts affect the dynamics of love and being loved?",
|
||||
"How do different individuals and groups experience and express love and being loved differently?",
|
||||
"How do love and being loved shape and change over time?"
|
||||
],
|
||||
"How can one balance and integrate love and being loved in one's life?": [
|
||||
"What are some strategies and practices to cultivate and sustain love and being loved?",
|
||||
"What are some examples and models of healthy and unhealthy relationships with love and being loved?",
|
||||
"What are some goals and values that guide one's choices and actions regarding love and being loved?"
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
*Queries*
|
||||
```
|
||||
definition and types of love
|
||||
definition and types of being loved
|
||||
benefits and drawbacks of loving oneself
|
||||
benefits and drawbacks of being loved by others
|
||||
interaction and influence of love and being loved
|
||||
strategies and practices to balance and integrate love and being loved
|
||||
examples and models of healthy and unhealthy relationships with love and being loved
|
||||
goals and values regarding love and being loved
|
||||
```
|
||||
30725
added_tokens.json
Normal file
30725
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
37
config.json
Normal file
37
config.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"_name_or_path": "voidful/phi-1_5_base",
|
||||
"architectures": [
|
||||
"PhiForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"auto_map": {
|
||||
"AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
|
||||
"AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
|
||||
},
|
||||
"bos_token_id": null,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": null,
|
||||
"hidden_act": "gelu_new",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "phi",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 32,
|
||||
"partial_rotary_factor": 0.5,
|
||||
"qk_layernorm": false,
|
||||
"resid_pdrop": 0.0,
|
||||
"rope_scaling": {
|
||||
"factor": 16.0,
|
||||
"type": "dynamic"
|
||||
},
|
||||
"rope_theta": 50000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 80980
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"eos_token_id": [
|
||||
70976,
|
||||
50256,
|
||||
70977
|
||||
],
|
||||
"transformers_version": "4.40.0.dev0"
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:86816b5696065c21d950ce7a7a8f87d04c6d33d0e1dace4ffc6d01cdc80970b7
|
||||
size 4960313864
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:abd5131a42c24f39f938366b9c41a2585ff7059586fe19c2af46de482388ab32
|
||||
size 1200841024
|
||||
348
model.safetensors.index.json
Normal file
348
model.safetensors.index.json
Normal file
@@ -0,0 +1,348 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6161117520
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "model-00002-of-00002.safetensors",
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
optimizer.pt
Normal file
3
optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd7e856d791a6e40145ae9c86ef583685b91b3cd3cc188b7dab9020d51d7b37f
|
||||
size 6941242
|
||||
3
rng_state.pth
Normal file
3
rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
||||
size 14244
|
||||
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:88bab19069aaa4ec1f577667c17275a0431d8f65965edb6dab9a36aa495194ae
|
||||
size 1064
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f37f03903ec162050c98a079961269acaa65eac3a403209aa22ae95fc8e32785
|
||||
size 7788322
|
||||
3
tokenizer_config.json
Normal file
3
tokenizer_config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:62e45bb94aac819baa17da01850c8e54216980578a42ea5f949236affb2b6687
|
||||
size 5373819
|
||||
933
trainer_state.json
Normal file
933
trainer_state.json
Normal file
@@ -0,0 +1,933 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.9999777777777776,
|
||||
"eval_steps": 500,
|
||||
"global_step": 12857,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"grad_norm": 2.191666603088379,
|
||||
"learning_rate": 2.0000000000000002e-07,
|
||||
"loss": 1.3084,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.03,
|
||||
"grad_norm": 1.7032761573791504,
|
||||
"learning_rate": 4.0000000000000003e-07,
|
||||
"loss": 1.0978,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"grad_norm": 1.4913277626037598,
|
||||
"learning_rate": 6.000000000000001e-07,
|
||||
"loss": 0.8859,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.06,
|
||||
"grad_norm": 1.470658779144287,
|
||||
"learning_rate": 8.000000000000001e-07,
|
||||
"loss": 0.8098,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.08,
|
||||
"grad_norm": 1.5057852268218994,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"loss": 0.7472,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.09,
|
||||
"grad_norm": 1.3578836917877197,
|
||||
"learning_rate": 1.2000000000000002e-06,
|
||||
"loss": 0.704,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 0.11,
|
||||
"grad_norm": 1.3679372072219849,
|
||||
"learning_rate": 1.4000000000000001e-06,
|
||||
"loss": 0.6937,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 0.12,
|
||||
"grad_norm": 1.3869675397872925,
|
||||
"learning_rate": 1.6000000000000001e-06,
|
||||
"loss": 0.6667,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 0.14,
|
||||
"grad_norm": 1.209143042564392,
|
||||
"learning_rate": 1.8000000000000001e-06,
|
||||
"loss": 0.6586,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 0.16,
|
||||
"grad_norm": 1.2448453903198242,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"loss": 0.6464,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 0.17,
|
||||
"grad_norm": 1.3068097829818726,
|
||||
"learning_rate": 2.2e-06,
|
||||
"loss": 0.6435,
|
||||
"step": 1100
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"grad_norm": 1.3215032815933228,
|
||||
"learning_rate": 2.4000000000000003e-06,
|
||||
"loss": 0.6335,
|
||||
"step": 1200
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"grad_norm": 1.1790049076080322,
|
||||
"learning_rate": 2.6e-06,
|
||||
"loss": 0.6297,
|
||||
"step": 1300
|
||||
},
|
||||
{
|
||||
"epoch": 0.22,
|
||||
"grad_norm": 1.2376770973205566,
|
||||
"learning_rate": 2.8000000000000003e-06,
|
||||
"loss": 0.6139,
|
||||
"step": 1400
|
||||
},
|
||||
{
|
||||
"epoch": 0.23,
|
||||
"grad_norm": 1.114210844039917,
|
||||
"learning_rate": 3e-06,
|
||||
"loss": 0.6099,
|
||||
"step": 1500
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"grad_norm": 1.1380881071090698,
|
||||
"learning_rate": 3.2000000000000003e-06,
|
||||
"loss": 0.6129,
|
||||
"step": 1600
|
||||
},
|
||||
{
|
||||
"epoch": 0.26,
|
||||
"grad_norm": 1.2346134185791016,
|
||||
"learning_rate": 3.4000000000000005e-06,
|
||||
"loss": 0.5995,
|
||||
"step": 1700
|
||||
},
|
||||
{
|
||||
"epoch": 0.28,
|
||||
"grad_norm": 1.293491005897522,
|
||||
"learning_rate": 3.6000000000000003e-06,
|
||||
"loss": 0.5975,
|
||||
"step": 1800
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"grad_norm": 1.2162506580352783,
|
||||
"learning_rate": 3.8000000000000005e-06,
|
||||
"loss": 0.5941,
|
||||
"step": 1900
|
||||
},
|
||||
{
|
||||
"epoch": 0.31,
|
||||
"grad_norm": 1.255366563796997,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 0.5814,
|
||||
"step": 2000
|
||||
},
|
||||
{
|
||||
"epoch": 0.33,
|
||||
"grad_norm": 1.230293869972229,
|
||||
"learning_rate": 4.2000000000000004e-06,
|
||||
"loss": 0.5912,
|
||||
"step": 2100
|
||||
},
|
||||
{
|
||||
"epoch": 0.34,
|
||||
"grad_norm": 1.3100721836090088,
|
||||
"learning_rate": 4.4e-06,
|
||||
"loss": 0.583,
|
||||
"step": 2200
|
||||
},
|
||||
{
|
||||
"epoch": 0.36,
|
||||
"grad_norm": 1.2346209287643433,
|
||||
"learning_rate": 4.600000000000001e-06,
|
||||
"loss": 0.5716,
|
||||
"step": 2300
|
||||
},
|
||||
{
|
||||
"epoch": 0.37,
|
||||
"grad_norm": 1.4086166620254517,
|
||||
"learning_rate": 4.800000000000001e-06,
|
||||
"loss": 0.5733,
|
||||
"step": 2400
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"grad_norm": 1.1538732051849365,
|
||||
"learning_rate": 5e-06,
|
||||
"loss": 0.5708,
|
||||
"step": 2500
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 1.1694637537002563,
|
||||
"learning_rate": 5.2e-06,
|
||||
"loss": 0.5775,
|
||||
"step": 2600
|
||||
},
|
||||
{
|
||||
"epoch": 0.42,
|
||||
"grad_norm": 1.1683225631713867,
|
||||
"learning_rate": 5.400000000000001e-06,
|
||||
"loss": 0.5635,
|
||||
"step": 2700
|
||||
},
|
||||
{
|
||||
"epoch": 0.44,
|
||||
"grad_norm": 1.141072392463684,
|
||||
"learning_rate": 5.600000000000001e-06,
|
||||
"loss": 0.5669,
|
||||
"step": 2800
|
||||
},
|
||||
{
|
||||
"epoch": 0.45,
|
||||
"grad_norm": 1.0785812139511108,
|
||||
"learning_rate": 5.8e-06,
|
||||
"loss": 0.562,
|
||||
"step": 2900
|
||||
},
|
||||
{
|
||||
"epoch": 0.47,
|
||||
"grad_norm": 1.0285478830337524,
|
||||
"learning_rate": 6e-06,
|
||||
"loss": 0.5655,
|
||||
"step": 3000
|
||||
},
|
||||
{
|
||||
"epoch": 0.48,
|
||||
"grad_norm": 1.145011067390442,
|
||||
"learning_rate": 6.200000000000001e-06,
|
||||
"loss": 0.5652,
|
||||
"step": 3100
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 1.1503745317459106,
|
||||
"learning_rate": 6.4000000000000006e-06,
|
||||
"loss": 0.5498,
|
||||
"step": 3200
|
||||
},
|
||||
{
|
||||
"epoch": 0.51,
|
||||
"grad_norm": 1.0536553859710693,
|
||||
"learning_rate": 6.600000000000001e-06,
|
||||
"loss": 0.5509,
|
||||
"step": 3300
|
||||
},
|
||||
{
|
||||
"epoch": 0.53,
|
||||
"grad_norm": 1.133914828300476,
|
||||
"learning_rate": 6.800000000000001e-06,
|
||||
"loss": 0.5576,
|
||||
"step": 3400
|
||||
},
|
||||
{
|
||||
"epoch": 0.54,
|
||||
"grad_norm": 1.0403516292572021,
|
||||
"learning_rate": 7e-06,
|
||||
"loss": 0.5468,
|
||||
"step": 3500
|
||||
},
|
||||
{
|
||||
"epoch": 0.56,
|
||||
"grad_norm": 1.124706745147705,
|
||||
"learning_rate": 7.2000000000000005e-06,
|
||||
"loss": 0.5481,
|
||||
"step": 3600
|
||||
},
|
||||
{
|
||||
"epoch": 0.58,
|
||||
"grad_norm": 1.1518924236297607,
|
||||
"learning_rate": 7.4e-06,
|
||||
"loss": 0.5445,
|
||||
"step": 3700
|
||||
},
|
||||
{
|
||||
"epoch": 0.59,
|
||||
"grad_norm": 1.067154884338379,
|
||||
"learning_rate": 7.600000000000001e-06,
|
||||
"loss": 0.5354,
|
||||
"step": 3800
|
||||
},
|
||||
{
|
||||
"epoch": 0.61,
|
||||
"grad_norm": 1.0968620777130127,
|
||||
"learning_rate": 7.800000000000002e-06,
|
||||
"loss": 0.5409,
|
||||
"step": 3900
|
||||
},
|
||||
{
|
||||
"epoch": 0.62,
|
||||
"grad_norm": 1.069420576095581,
|
||||
"learning_rate": 8.000000000000001e-06,
|
||||
"loss": 0.5399,
|
||||
"step": 4000
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 1.1727967262268066,
|
||||
"learning_rate": 8.2e-06,
|
||||
"loss": 0.5398,
|
||||
"step": 4100
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"grad_norm": 1.1503219604492188,
|
||||
"learning_rate": 8.400000000000001e-06,
|
||||
"loss": 0.5357,
|
||||
"step": 4200
|
||||
},
|
||||
{
|
||||
"epoch": 0.67,
|
||||
"grad_norm": 1.1418933868408203,
|
||||
"learning_rate": 8.6e-06,
|
||||
"loss": 0.5308,
|
||||
"step": 4300
|
||||
},
|
||||
{
|
||||
"epoch": 0.68,
|
||||
"grad_norm": 1.065690517425537,
|
||||
"learning_rate": 8.8e-06,
|
||||
"loss": 0.5405,
|
||||
"step": 4400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"grad_norm": 1.1668462753295898,
|
||||
"learning_rate": 9e-06,
|
||||
"loss": 0.5342,
|
||||
"step": 4500
|
||||
},
|
||||
{
|
||||
"epoch": 0.72,
|
||||
"grad_norm": 1.1019855737686157,
|
||||
"learning_rate": 9.200000000000002e-06,
|
||||
"loss": 0.5261,
|
||||
"step": 4600
|
||||
},
|
||||
{
|
||||
"epoch": 0.73,
|
||||
"grad_norm": 1.171284794807434,
|
||||
"learning_rate": 9.4e-06,
|
||||
"loss": 0.5269,
|
||||
"step": 4700
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"grad_norm": 1.2499768733978271,
|
||||
"learning_rate": 9.600000000000001e-06,
|
||||
"loss": 0.53,
|
||||
"step": 4800
|
||||
},
|
||||
{
|
||||
"epoch": 0.76,
|
||||
"grad_norm": 1.0950831174850464,
|
||||
"learning_rate": 9.800000000000001e-06,
|
||||
"loss": 0.5369,
|
||||
"step": 4900
|
||||
},
|
||||
{
|
||||
"epoch": 0.78,
|
||||
"grad_norm": 1.1700873374938965,
|
||||
"learning_rate": 1e-05,
|
||||
"loss": 0.5296,
|
||||
"step": 5000
|
||||
},
|
||||
{
|
||||
"epoch": 0.79,
|
||||
"grad_norm": 1.0696507692337036,
|
||||
"learning_rate": 9.963154016212235e-06,
|
||||
"loss": 0.5188,
|
||||
"step": 5100
|
||||
},
|
||||
{
|
||||
"epoch": 0.81,
|
||||
"grad_norm": 1.1057288646697998,
|
||||
"learning_rate": 9.926308032424467e-06,
|
||||
"loss": 0.5272,
|
||||
"step": 5200
|
||||
},
|
||||
{
|
||||
"epoch": 0.82,
|
||||
"grad_norm": 0.9978774785995483,
|
||||
"learning_rate": 9.8894620486367e-06,
|
||||
"loss": 0.5288,
|
||||
"step": 5300
|
||||
},
|
||||
{
|
||||
"epoch": 0.84,
|
||||
"grad_norm": 1.072900652885437,
|
||||
"learning_rate": 9.852616064848932e-06,
|
||||
"loss": 0.5247,
|
||||
"step": 5400
|
||||
},
|
||||
{
|
||||
"epoch": 0.86,
|
||||
"grad_norm": 0.9971893429756165,
|
||||
"learning_rate": 9.815770081061166e-06,
|
||||
"loss": 0.5137,
|
||||
"step": 5500
|
||||
},
|
||||
{
|
||||
"epoch": 0.87,
|
||||
"grad_norm": 0.9494544863700867,
|
||||
"learning_rate": 9.778924097273399e-06,
|
||||
"loss": 0.5157,
|
||||
"step": 5600
|
||||
},
|
||||
{
|
||||
"epoch": 0.89,
|
||||
"grad_norm": 1.04669189453125,
|
||||
"learning_rate": 9.742078113485631e-06,
|
||||
"loss": 0.5267,
|
||||
"step": 5700
|
||||
},
|
||||
{
|
||||
"epoch": 0.9,
|
||||
"grad_norm": 1.0739444494247437,
|
||||
"learning_rate": 9.705232129697863e-06,
|
||||
"loss": 0.5207,
|
||||
"step": 5800
|
||||
},
|
||||
{
|
||||
"epoch": 0.92,
|
||||
"grad_norm": 0.9554969668388367,
|
||||
"learning_rate": 9.668386145910098e-06,
|
||||
"loss": 0.5136,
|
||||
"step": 5900
|
||||
},
|
||||
{
|
||||
"epoch": 0.93,
|
||||
"grad_norm": 0.9823188185691833,
|
||||
"learning_rate": 9.63154016212233e-06,
|
||||
"loss": 0.5137,
|
||||
"step": 6000
|
||||
},
|
||||
{
|
||||
"epoch": 0.95,
|
||||
"grad_norm": 0.9793609380722046,
|
||||
"learning_rate": 9.594694178334562e-06,
|
||||
"loss": 0.5177,
|
||||
"step": 6100
|
||||
},
|
||||
{
|
||||
"epoch": 0.96,
|
||||
"grad_norm": 0.9663506746292114,
|
||||
"learning_rate": 9.557848194546795e-06,
|
||||
"loss": 0.5141,
|
||||
"step": 6200
|
||||
},
|
||||
{
|
||||
"epoch": 0.98,
|
||||
"grad_norm": 1.0234330892562866,
|
||||
"learning_rate": 9.521002210759029e-06,
|
||||
"loss": 0.5077,
|
||||
"step": 6300
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 1.2162741422653198,
|
||||
"learning_rate": 9.484156226971261e-06,
|
||||
"loss": 0.5124,
|
||||
"step": 6400
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.5092498660087585,
|
||||
"eval_runtime": 206.7717,
|
||||
"eval_samples_per_second": 31.184,
|
||||
"eval_steps_per_second": 3.898,
|
||||
"step": 6428
|
||||
},
|
||||
{
|
||||
"epoch": 1.01,
|
||||
"grad_norm": 1.1033669710159302,
|
||||
"learning_rate": 9.447310243183494e-06,
|
||||
"loss": 0.4707,
|
||||
"step": 6500
|
||||
},
|
||||
{
|
||||
"epoch": 1.03,
|
||||
"grad_norm": 1.0372246503829956,
|
||||
"learning_rate": 9.410464259395726e-06,
|
||||
"loss": 0.4532,
|
||||
"step": 6600
|
||||
},
|
||||
{
|
||||
"epoch": 1.04,
|
||||
"grad_norm": 1.1232597827911377,
|
||||
"learning_rate": 9.37361827560796e-06,
|
||||
"loss": 0.4489,
|
||||
"step": 6700
|
||||
},
|
||||
{
|
||||
"epoch": 1.06,
|
||||
"grad_norm": 1.061074137687683,
|
||||
"learning_rate": 9.336772291820193e-06,
|
||||
"loss": 0.4552,
|
||||
"step": 6800
|
||||
},
|
||||
{
|
||||
"epoch": 1.07,
|
||||
"grad_norm": 1.0498615503311157,
|
||||
"learning_rate": 9.299926308032425e-06,
|
||||
"loss": 0.4482,
|
||||
"step": 6900
|
||||
},
|
||||
{
|
||||
"epoch": 1.09,
|
||||
"grad_norm": 1.0324976444244385,
|
||||
"learning_rate": 9.263080324244657e-06,
|
||||
"loss": 0.4511,
|
||||
"step": 7000
|
||||
},
|
||||
{
|
||||
"epoch": 1.1,
|
||||
"grad_norm": 0.9778733849525452,
|
||||
"learning_rate": 9.226234340456892e-06,
|
||||
"loss": 0.4452,
|
||||
"step": 7100
|
||||
},
|
||||
{
|
||||
"epoch": 1.12,
|
||||
"grad_norm": 1.0444563627243042,
|
||||
"learning_rate": 9.189388356669124e-06,
|
||||
"loss": 0.4512,
|
||||
"step": 7200
|
||||
},
|
||||
{
|
||||
"epoch": 1.14,
|
||||
"grad_norm": 1.0546364784240723,
|
||||
"learning_rate": 9.152542372881356e-06,
|
||||
"loss": 0.4486,
|
||||
"step": 7300
|
||||
},
|
||||
{
|
||||
"epoch": 1.15,
|
||||
"grad_norm": 1.0815290212631226,
|
||||
"learning_rate": 9.115696389093589e-06,
|
||||
"loss": 0.4514,
|
||||
"step": 7400
|
||||
},
|
||||
{
|
||||
"epoch": 1.17,
|
||||
"grad_norm": 1.0215433835983276,
|
||||
"learning_rate": 9.078850405305823e-06,
|
||||
"loss": 0.4467,
|
||||
"step": 7500
|
||||
},
|
||||
{
|
||||
"epoch": 1.18,
|
||||
"grad_norm": 0.9386591911315918,
|
||||
"learning_rate": 9.042004421518055e-06,
|
||||
"loss": 0.4515,
|
||||
"step": 7600
|
||||
},
|
||||
{
|
||||
"epoch": 1.2,
|
||||
"grad_norm": 1.08309006690979,
|
||||
"learning_rate": 9.005158437730288e-06,
|
||||
"loss": 0.4466,
|
||||
"step": 7700
|
||||
},
|
||||
{
|
||||
"epoch": 1.21,
|
||||
"grad_norm": 1.0043574571609497,
|
||||
"learning_rate": 8.968312453942522e-06,
|
||||
"loss": 0.451,
|
||||
"step": 7800
|
||||
},
|
||||
{
|
||||
"epoch": 1.23,
|
||||
"grad_norm": 0.9670729041099548,
|
||||
"learning_rate": 8.931466470154754e-06,
|
||||
"loss": 0.4508,
|
||||
"step": 7900
|
||||
},
|
||||
{
|
||||
"epoch": 1.24,
|
||||
"grad_norm": 1.001947283744812,
|
||||
"learning_rate": 8.894620486366987e-06,
|
||||
"loss": 0.4454,
|
||||
"step": 8000
|
||||
},
|
||||
{
|
||||
"epoch": 1.26,
|
||||
"grad_norm": 0.9632651209831238,
|
||||
"learning_rate": 8.857774502579219e-06,
|
||||
"loss": 0.4419,
|
||||
"step": 8100
|
||||
},
|
||||
{
|
||||
"epoch": 1.28,
|
||||
"grad_norm": 1.0596399307250977,
|
||||
"learning_rate": 8.820928518791453e-06,
|
||||
"loss": 0.444,
|
||||
"step": 8200
|
||||
},
|
||||
{
|
||||
"epoch": 1.29,
|
||||
"grad_norm": 1.0315296649932861,
|
||||
"learning_rate": 8.784082535003686e-06,
|
||||
"loss": 0.4443,
|
||||
"step": 8300
|
||||
},
|
||||
{
|
||||
"epoch": 1.31,
|
||||
"grad_norm": 1.2347131967544556,
|
||||
"learning_rate": 8.747236551215918e-06,
|
||||
"loss": 0.4478,
|
||||
"step": 8400
|
||||
},
|
||||
{
|
||||
"epoch": 1.32,
|
||||
"grad_norm": 1.1402790546417236,
|
||||
"learning_rate": 8.71039056742815e-06,
|
||||
"loss": 0.4458,
|
||||
"step": 8500
|
||||
},
|
||||
{
|
||||
"epoch": 1.34,
|
||||
"grad_norm": 1.0721864700317383,
|
||||
"learning_rate": 8.673544583640385e-06,
|
||||
"loss": 0.4391,
|
||||
"step": 8600
|
||||
},
|
||||
{
|
||||
"epoch": 1.35,
|
||||
"grad_norm": 1.072485327720642,
|
||||
"learning_rate": 8.636698599852617e-06,
|
||||
"loss": 0.4443,
|
||||
"step": 8700
|
||||
},
|
||||
{
|
||||
"epoch": 1.37,
|
||||
"grad_norm": 1.0993961095809937,
|
||||
"learning_rate": 8.59985261606485e-06,
|
||||
"loss": 0.4485,
|
||||
"step": 8800
|
||||
},
|
||||
{
|
||||
"epoch": 1.38,
|
||||
"grad_norm": 1.1231122016906738,
|
||||
"learning_rate": 8.563006632277082e-06,
|
||||
"loss": 0.4423,
|
||||
"step": 8900
|
||||
},
|
||||
{
|
||||
"epoch": 1.4,
|
||||
"grad_norm": 1.131405234336853,
|
||||
"learning_rate": 8.526160648489316e-06,
|
||||
"loss": 0.4512,
|
||||
"step": 9000
|
||||
},
|
||||
{
|
||||
"epoch": 1.42,
|
||||
"grad_norm": 1.0044902563095093,
|
||||
"learning_rate": 8.489314664701548e-06,
|
||||
"loss": 0.444,
|
||||
"step": 9100
|
||||
},
|
||||
{
|
||||
"epoch": 1.43,
|
||||
"grad_norm": 0.9530848860740662,
|
||||
"learning_rate": 8.45246868091378e-06,
|
||||
"loss": 0.4423,
|
||||
"step": 9200
|
||||
},
|
||||
{
|
||||
"epoch": 1.45,
|
||||
"grad_norm": 0.8441118597984314,
|
||||
"learning_rate": 8.415622697126013e-06,
|
||||
"loss": 0.4443,
|
||||
"step": 9300
|
||||
},
|
||||
{
|
||||
"epoch": 1.46,
|
||||
"grad_norm": 0.9523534774780273,
|
||||
"learning_rate": 8.378776713338247e-06,
|
||||
"loss": 0.4403,
|
||||
"step": 9400
|
||||
},
|
||||
{
|
||||
"epoch": 1.48,
|
||||
"grad_norm": 1.0068507194519043,
|
||||
"learning_rate": 8.34193072955048e-06,
|
||||
"loss": 0.4364,
|
||||
"step": 9500
|
||||
},
|
||||
{
|
||||
"epoch": 1.49,
|
||||
"grad_norm": 1.0632400512695312,
|
||||
"learning_rate": 8.305084745762712e-06,
|
||||
"loss": 0.4414,
|
||||
"step": 9600
|
||||
},
|
||||
{
|
||||
"epoch": 1.51,
|
||||
"grad_norm": 1.1296297311782837,
|
||||
"learning_rate": 8.268238761974944e-06,
|
||||
"loss": 0.4429,
|
||||
"step": 9700
|
||||
},
|
||||
{
|
||||
"epoch": 1.52,
|
||||
"grad_norm": 1.0164484977722168,
|
||||
"learning_rate": 8.231392778187179e-06,
|
||||
"loss": 0.4403,
|
||||
"step": 9800
|
||||
},
|
||||
{
|
||||
"epoch": 1.54,
|
||||
"grad_norm": 1.1088131666183472,
|
||||
"learning_rate": 8.194546794399411e-06,
|
||||
"loss": 0.4407,
|
||||
"step": 9900
|
||||
},
|
||||
{
|
||||
"epoch": 1.56,
|
||||
"grad_norm": 1.041729211807251,
|
||||
"learning_rate": 8.157700810611643e-06,
|
||||
"loss": 0.4434,
|
||||
"step": 10000
|
||||
},
|
||||
{
|
||||
"epoch": 1.57,
|
||||
"grad_norm": 1.0203355550765991,
|
||||
"learning_rate": 8.120854826823877e-06,
|
||||
"loss": 0.4428,
|
||||
"step": 10100
|
||||
},
|
||||
{
|
||||
"epoch": 1.59,
|
||||
"grad_norm": 1.0350580215454102,
|
||||
"learning_rate": 8.08400884303611e-06,
|
||||
"loss": 0.4365,
|
||||
"step": 10200
|
||||
},
|
||||
{
|
||||
"epoch": 1.6,
|
||||
"grad_norm": 1.1208500862121582,
|
||||
"learning_rate": 8.047162859248342e-06,
|
||||
"loss": 0.4426,
|
||||
"step": 10300
|
||||
},
|
||||
{
|
||||
"epoch": 1.62,
|
||||
"grad_norm": 1.1885343790054321,
|
||||
"learning_rate": 8.010316875460575e-06,
|
||||
"loss": 0.4414,
|
||||
"step": 10400
|
||||
},
|
||||
{
|
||||
"epoch": 1.63,
|
||||
"grad_norm": 0.9988847374916077,
|
||||
"learning_rate": 7.973470891672809e-06,
|
||||
"loss": 0.4368,
|
||||
"step": 10500
|
||||
},
|
||||
{
|
||||
"epoch": 1.65,
|
||||
"grad_norm": 1.0181776285171509,
|
||||
"learning_rate": 7.936624907885041e-06,
|
||||
"loss": 0.4399,
|
||||
"step": 10600
|
||||
},
|
||||
{
|
||||
"epoch": 1.66,
|
||||
"grad_norm": 0.9755112528800964,
|
||||
"learning_rate": 7.899778924097274e-06,
|
||||
"loss": 0.4424,
|
||||
"step": 10700
|
||||
},
|
||||
{
|
||||
"epoch": 1.68,
|
||||
"grad_norm": 1.0309982299804688,
|
||||
"learning_rate": 7.862932940309506e-06,
|
||||
"loss": 0.4418,
|
||||
"step": 10800
|
||||
},
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"grad_norm": 1.032485842704773,
|
||||
"learning_rate": 7.82608695652174e-06,
|
||||
"loss": 0.4404,
|
||||
"step": 10900
|
||||
},
|
||||
{
|
||||
"epoch": 1.71,
|
||||
"grad_norm": 1.0489119291305542,
|
||||
"learning_rate": 7.789240972733973e-06,
|
||||
"loss": 0.4333,
|
||||
"step": 11000
|
||||
},
|
||||
{
|
||||
"epoch": 1.73,
|
||||
"grad_norm": 1.1144189834594727,
|
||||
"learning_rate": 7.752394988946205e-06,
|
||||
"loss": 0.4348,
|
||||
"step": 11100
|
||||
},
|
||||
{
|
||||
"epoch": 1.74,
|
||||
"grad_norm": 1.0886303186416626,
|
||||
"learning_rate": 7.715549005158437e-06,
|
||||
"loss": 0.4355,
|
||||
"step": 11200
|
||||
},
|
||||
{
|
||||
"epoch": 1.76,
|
||||
"grad_norm": 1.0355674028396606,
|
||||
"learning_rate": 7.678703021370671e-06,
|
||||
"loss": 0.4348,
|
||||
"step": 11300
|
||||
},
|
||||
{
|
||||
"epoch": 1.77,
|
||||
"grad_norm": 1.0847941637039185,
|
||||
"learning_rate": 7.641857037582904e-06,
|
||||
"loss": 0.4398,
|
||||
"step": 11400
|
||||
},
|
||||
{
|
||||
"epoch": 1.79,
|
||||
"grad_norm": 1.0430936813354492,
|
||||
"learning_rate": 7.605011053795137e-06,
|
||||
"loss": 0.4316,
|
||||
"step": 11500
|
||||
},
|
||||
{
|
||||
"epoch": 1.8,
|
||||
"grad_norm": 1.0820753574371338,
|
||||
"learning_rate": 7.5681650700073696e-06,
|
||||
"loss": 0.431,
|
||||
"step": 11600
|
||||
},
|
||||
{
|
||||
"epoch": 1.82,
|
||||
"grad_norm": 1.080796241760254,
|
||||
"learning_rate": 7.531319086219603e-06,
|
||||
"loss": 0.433,
|
||||
"step": 11700
|
||||
},
|
||||
{
|
||||
"epoch": 1.84,
|
||||
"grad_norm": 1.01823091506958,
|
||||
"learning_rate": 7.494473102431835e-06,
|
||||
"loss": 0.435,
|
||||
"step": 11800
|
||||
},
|
||||
{
|
||||
"epoch": 1.85,
|
||||
"grad_norm": 1.0962271690368652,
|
||||
"learning_rate": 7.4576271186440685e-06,
|
||||
"loss": 0.4347,
|
||||
"step": 11900
|
||||
},
|
||||
{
|
||||
"epoch": 1.87,
|
||||
"grad_norm": 1.0160537958145142,
|
||||
"learning_rate": 7.420781134856301e-06,
|
||||
"loss": 0.4326,
|
||||
"step": 12000
|
||||
},
|
||||
{
|
||||
"epoch": 1.88,
|
||||
"grad_norm": 0.9727386832237244,
|
||||
"learning_rate": 7.383935151068534e-06,
|
||||
"loss": 0.4329,
|
||||
"step": 12100
|
||||
},
|
||||
{
|
||||
"epoch": 1.9,
|
||||
"grad_norm": 1.0276840925216675,
|
||||
"learning_rate": 7.3470891672807666e-06,
|
||||
"loss": 0.4295,
|
||||
"step": 12200
|
||||
},
|
||||
{
|
||||
"epoch": 1.91,
|
||||
"grad_norm": 0.972959041595459,
|
||||
"learning_rate": 7.310243183493e-06,
|
||||
"loss": 0.4252,
|
||||
"step": 12300
|
||||
},
|
||||
{
|
||||
"epoch": 1.93,
|
||||
"grad_norm": 1.0518746376037598,
|
||||
"learning_rate": 7.273397199705232e-06,
|
||||
"loss": 0.4299,
|
||||
"step": 12400
|
||||
},
|
||||
{
|
||||
"epoch": 1.94,
|
||||
"grad_norm": 1.0917232036590576,
|
||||
"learning_rate": 7.2365512159174655e-06,
|
||||
"loss": 0.4326,
|
||||
"step": 12500
|
||||
},
|
||||
{
|
||||
"epoch": 1.96,
|
||||
"grad_norm": 1.0608563423156738,
|
||||
"learning_rate": 7.199705232129699e-06,
|
||||
"loss": 0.4318,
|
||||
"step": 12600
|
||||
},
|
||||
{
|
||||
"epoch": 1.98,
|
||||
"grad_norm": 1.0238438844680786,
|
||||
"learning_rate": 7.162859248341931e-06,
|
||||
"loss": 0.4298,
|
||||
"step": 12700
|
||||
},
|
||||
{
|
||||
"epoch": 1.99,
|
||||
"grad_norm": 0.9618347883224487,
|
||||
"learning_rate": 7.126013264554164e-06,
|
||||
"loss": 0.4351,
|
||||
"step": 12800
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"eval_loss": 0.47487419843673706,
|
||||
"eval_runtime": 205.6987,
|
||||
"eval_samples_per_second": 31.347,
|
||||
"eval_steps_per_second": 3.918,
|
||||
"step": 12857
|
||||
}
|
||||
],
|
||||
"logging_steps": 100,
|
||||
"max_steps": 32140,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 5,
|
||||
"save_steps": 500,
|
||||
"total_flos": 6.404792140239882e+17,
|
||||
"train_batch_size": 2,
|
||||
"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 sha256:34584b3b2e57ec0863337589518428b1b74d4c21f340ee45e4119e80f6d3a4c8
|
||||
size 4856
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user