初始化项目，由ModelHub XC社区提供模型
Model: distil-labs/distil-qwen3-4b-text2sql Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.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
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
31
LICENSE
Normal file
31
LICENSE
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
GENERAL TERMS AND CONDITIONS
|
||||||
|
|
||||||
|
Note that if you want to use the Commercial licence, please contact us at contact@distillabs.ai
|
||||||
|
|
||||||
|
- Model License Terms -
|
||||||
|
|
||||||
|
R&D License
|
||||||
|
|
||||||
|
1. SERVICES, PRICES AND PAYMENT
|
||||||
|
|
||||||
|
1.1 The Customer pays a one-time license fee, as indicated in the check-out process, for running of one (1) training process of the selected Base Model using Customer Data (“License Fee”).
|
||||||
|
|
||||||
|
1.2 The License Fee shall be due for payment in advance. The Customer shall only be permitted to set off against payment claims of Distil Labs if the Customer’s claims are undisputed or have become res judicata.
|
||||||
|
|
||||||
|
2. MODEL LICENSE: R&D LICENSE
|
||||||
|
|
||||||
|
2.1 Subject to Customer’s payment of the license fee, Distil Labs grants to Customer the Model License (as defined below). For clarification, Distil Labs retains any other rights in its software or know- how, in particular in the codebase needed for the fine-tuning of the Trained Model.
|
||||||
|
|
||||||
|
2.2 Subject to the requirements of the Base Model License (cf. Section 2.5 below), Distil Labs transfers to the Customer the perpetual, non-exclusive usage right to the Trained Model for non-commercial purposes of prototyping and research & development. The Parties agree, that commercial purposes include deployment in production externally (to be used by Customer’s customers paid or free of charge) or internally (as a tool for Customer’s employees). The territorial scope of the license is limited to the use within the United States of America and the European Economic Area including all member states of the European Union (“Model License”).
|
||||||
|
|
||||||
|
2.3 The Model License for non-commercial purposes of prototyping and research & development shall include (i) the non-exclusive right to permanent or temporary reproduction, in whole or in part, by any means and in any form (e.g. permanent and/or volatile storage on electrical, electromagnetic, optical storage media, such as any type of SDD, HDD, DVD, memory cards, USB sticks), (ii) the non-exclusive right to distribution in any form, media and by any means regardless of whether the distribution is in tangible or intangible form, in particular to transmit the Trained Model via wired and wireless networks (e.g. for download from internet or intranet by wire or wireless means including broadband, cable, fiberglass, WIFI, LTE, 5G, satellite internet, other data networks), and (iii) the non-exclusive right of making available to the public in such a way that members of the public can access it from places and at times of their choice (e.g. by web or mobile app, virtual or augmented reality, cloud storage, cloud hosting, decentralized hosting, non-fungible token, application service providing, software as a service, or cloud computing). The license shall also contain, to the extent necessary for prototyping and research & development, the right to adapt and modify the Trained Model subject to the limitation in Section 2.4 and 2.5 below, to further develop the Trained Model including changes to functions or appearance, adapt to other software versions, to exchange parts of the Trained Model or combine the Trained Model with other results of work and to use the results in the same way as the original Trained Model. Any derived models from the Trained Model shall retain this model license.
|
||||||
|
|
||||||
|
2.4 The Customer shall not, without the prior written consent of Distil Labs:
|
||||||
|
|
||||||
|
2.4.1 train, fine-tune, re-train, or otherwise modify the Trained Model, unless for purpose of research & development;
|
||||||
|
|
||||||
|
2.4.2 use the Trained Model or any part thereof to create derivative models or services that compete with those of Distil Labs;
|
||||||
|
|
||||||
|
2.4.3 circumvent any technical restrictions embedded in the Trained Model or Base Model that are designed to enforce usage limitations.
|
||||||
|
|
||||||
|
2.5 The Parties acknowledge and agree that the Trained Model is developed from Base Models which are supplied by a third party. Therefore, the Model License is subject to the restrictions resulting from the open-source or any other applicable license of the Base Model (“Base Model License”) and the Customer must use the Trained Model in compliance with the Base Model License. In particular, the Customer must oblige their clients to compliance with the Base Model License in any case of transferring or sublicensing the rights to or making available in any way the Trained Model. The applicable Base Model License is defined in the Training Configuration and will be provided for download. The Customer agrees to indemnify Distil Labs for any and all claims brought by the Base Model provider for violations of the Base Model License.
|
||||||
51
Modelfile
Normal file
51
Modelfile
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
|
||||||
|
FROM ./model.gguf
|
||||||
|
|
||||||
|
TEMPLATE """{{- $lastUserIdx := -1 -}}
|
||||||
|
{{- range $idx, $msg := .Messages -}}
|
||||||
|
{{- if eq $msg.Role "user" }}{{ $lastUserIdx = $idx }}{{ end -}}
|
||||||
|
{{- end }}
|
||||||
|
{{- if or .System .Tools }}<|im_start|>system
|
||||||
|
{{ if .System }}{{ .System }}
|
||||||
|
|
||||||
|
{{ end }}
|
||||||
|
{{- if .Tools }}# Tools
|
||||||
|
|
||||||
|
You may call one or more functions to assist with the user query.
|
||||||
|
|
||||||
|
You are provided with function signatures within <tools></tools> XML tags:
|
||||||
|
<tools>
|
||||||
|
{{- range .Tools }}
|
||||||
|
{"type": "function", "function": {{ .Function }}}
|
||||||
|
{{- end }}
|
||||||
|
</tools>
|
||||||
|
|
||||||
|
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||||
|
<tool_call>
|
||||||
|
{"name": <function-name>, "arguments": <args-json-object>}
|
||||||
|
</tool_call>
|
||||||
|
{{- end -}}
|
||||||
|
<|im_end|>
|
||||||
|
{{ end }}
|
||||||
|
{{- range $i, $_ := .Messages }}
|
||||||
|
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||||
|
{{- if eq .Role "user" }}<|im_start|>user
|
||||||
|
{{ .Content }}<|im_end|>
|
||||||
|
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||||
|
{{ if .Content }}{{ .Content }}{{ end }}
|
||||||
|
{{- if .ToolCalls }}
|
||||||
|
{{- range .ToolCalls }}
|
||||||
|
<tool_call>
|
||||||
|
{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||||
|
</tool_call>
|
||||||
|
{{- end }}
|
||||||
|
{{- end }}{{ if not $last }}<|im_end|>
|
||||||
|
{{ end }}
|
||||||
|
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||||
|
<tool_response>
|
||||||
|
{{ .Content }}
|
||||||
|
</tool_response><|im_end|>
|
||||||
|
{{ end }}
|
||||||
|
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||||
|
{{ end }}
|
||||||
|
{{- end }}"""
|
||||||
194
README.md
Normal file
194
README.md
Normal file
@@ -0,0 +1,194 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-4B
|
||||||
|
tags:
|
||||||
|
- text2sql
|
||||||
|
- sql
|
||||||
|
- nlp
|
||||||
|
- distillation
|
||||||
|
- qwen3
|
||||||
|
datasets:
|
||||||
|
- distil-labs/text2sql-synthetic
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# Distil-Qwen3-4B-Text2SQL
|
||||||
|
|
||||||
|
A fine-tuned Qwen3-4B model for converting natural language questions into SQL queries. Trained using knowledge distillation from DeepSeek-V3, this 4B parameter model matches teacher-level accuracy while being small enough to run locally.
|
||||||
|
|
||||||
|
## Results
|
||||||
|
|
||||||
|
| Metric | DeepSeek-V3 (Teacher) | Qwen3-4B (Base) | **This Model** |
|
||||||
|
|--------|:---------------------:|:---------------:|:--------------:|
|
||||||
|
| LLM-as-a-Judge | 80% | 62% | **80%** |
|
||||||
|
| Exact Match | 48% | 16% | **60%** |
|
||||||
|
| ROUGE | 87.6% | 84.2% | **89.5%** |
|
||||||
|
| METEOR | 85.1% | 87.3% | 86.1% |
|
||||||
|
|
||||||
|
The fine-tuned model **matches the 685B parameter teacher** on LLM-as-a-Judge accuracy and **exceeds it** on exact match and ROUGE scores.
|
||||||
|
|
||||||
|
## Quick Start
|
||||||
|
|
||||||
|
### Using Transformers
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-qwen3-4b-text2sql")
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("distil-labs/distil-qwen3-4b-text2sql")
|
||||||
|
|
||||||
|
schema = """CREATE TABLE employees (
|
||||||
|
id INTEGER PRIMARY KEY,
|
||||||
|
name TEXT NOT NULL,
|
||||||
|
department TEXT,
|
||||||
|
salary INTEGER
|
||||||
|
);"""
|
||||||
|
|
||||||
|
question = "How many employees earn more than 50000?"
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{
|
||||||
|
"role": "system",
|
||||||
|
"content": """You are a problem solving model working on task_description XML block:
|
||||||
|
<task_description>You are given a database schema and a natural language question. Generate the SQL query that answers the question.
|
||||||
|
|
||||||
|
Input:
|
||||||
|
- Schema: One or two table definitions in SQL DDL format
|
||||||
|
- Question: Natural language question about the data
|
||||||
|
|
||||||
|
Output:
|
||||||
|
- A single SQL query that answers the question
|
||||||
|
- No explanations, comments, or additional text
|
||||||
|
|
||||||
|
Rules:
|
||||||
|
- Use only tables and columns from the provided schema
|
||||||
|
- Use uppercase SQL keywords (SELECT, FROM, WHERE, etc.)
|
||||||
|
- Use SQLite-compatible syntax</task_description>
|
||||||
|
You will be given a single task in the question XML block
|
||||||
|
Solve only the task in question block.
|
||||||
|
Generate only the answer, do not generate anything else"""
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": f"""Now for the real task, solve the task in question block.
|
||||||
|
Generate only the solution, do not generate anything else
|
||||||
|
<question>Schema:
|
||||||
|
{schema}
|
||||||
|
|
||||||
|
Question: {question}</question>"""
|
||||||
|
}
|
||||||
|
]
|
||||||
|
|
||||||
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||||
|
inputs = tokenizer(text, return_tensors="pt")
|
||||||
|
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0)
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
### Using Ollama (GGUF version)
|
||||||
|
|
||||||
|
For local inference, use the quantized GGUF versions:
|
||||||
|
- [distil-qwen3-4b-text2sql-gguf](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql-gguf) - Full precision GGUF
|
||||||
|
- [distil-qwen3-4b-text2sql-gguf-4bit](https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql-gguf-4bit) - 4-bit quantized (~2.5GB)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Download and create Ollama model
|
||||||
|
ollama create distil-qwen3-4b-text2sql -f Modelfile
|
||||||
|
|
||||||
|
# Run inference
|
||||||
|
ollama run distil-qwen3-4b-text2sql
|
||||||
|
```
|
||||||
|
|
||||||
|
## Model Details
|
||||||
|
|
||||||
|
| Property | Value |
|
||||||
|
|----------|-------|
|
||||||
|
| Base Model | [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) |
|
||||||
|
| Parameters | 4 billion |
|
||||||
|
| Architecture | Qwen3ForCausalLM |
|
||||||
|
| Context Length | 262,144 tokens |
|
||||||
|
| Precision | bfloat16 |
|
||||||
|
| Training Data | ~10,000 synthetic examples |
|
||||||
|
| Teacher Model | DeepSeek-V3 |
|
||||||
|
|
||||||
|
## Training
|
||||||
|
|
||||||
|
This model was trained using the [Distil Labs](https://distillabs.ai) platform:
|
||||||
|
|
||||||
|
1. **Seed Data**: 50 hand-validated Text2SQL examples covering various SQL complexities
|
||||||
|
2. **Synthetic Generation**: Expanded to ~10,000 examples using DeepSeek-V3
|
||||||
|
3. **Fine-tuning**: 4 epochs on the synthetic dataset
|
||||||
|
4. **Evaluation**: LLM-as-a-Judge with semantic equivalence checking
|
||||||
|
|
||||||
|
### Training Hyperparameters
|
||||||
|
|
||||||
|
- Epochs: 4
|
||||||
|
- Learning Rate: 5e-5 (cosine schedule)
|
||||||
|
- Batch Size: 1 (with gradient accumulation)
|
||||||
|
- Total Steps: ~40,000
|
||||||
|
|
||||||
|
## Task Format
|
||||||
|
|
||||||
|
### Input Format
|
||||||
|
|
||||||
|
```
|
||||||
|
Schema:
|
||||||
|
CREATE TABLE table_name (
|
||||||
|
column_name DATA_TYPE [CONSTRAINTS],
|
||||||
|
...
|
||||||
|
);
|
||||||
|
|
||||||
|
Question: Natural language question about the data
|
||||||
|
```
|
||||||
|
|
||||||
|
### Output Format
|
||||||
|
|
||||||
|
A single SQL query with:
|
||||||
|
- Uppercase SQL keywords (SELECT, FROM, WHERE, etc.)
|
||||||
|
- SQLite-compatible syntax
|
||||||
|
- No explanations or additional text
|
||||||
|
|
||||||
|
### Supported SQL Features
|
||||||
|
|
||||||
|
- **Simple**: SELECT, WHERE, COUNT, SUM, AVG, MAX, MIN
|
||||||
|
- **Medium**: JOIN, GROUP BY, HAVING, ORDER BY, LIMIT
|
||||||
|
- **Complex**: Subqueries, multiple JOINs, UNION
|
||||||
|
|
||||||
|
## Use Cases
|
||||||
|
|
||||||
|
- Natural language interfaces to databases
|
||||||
|
- SQL query assistance and autocompletion
|
||||||
|
- Database chatbots and conversational BI
|
||||||
|
- Educational tools for learning SQL
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
- Optimized for SQLite syntax
|
||||||
|
- Best with 1-2 table schemas
|
||||||
|
- May struggle with highly complex nested subqueries
|
||||||
|
- Trained on English questions only
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
This model is released under the Apache 2.0 license.
|
||||||
|
|
||||||
|
## Links
|
||||||
|
|
||||||
|
- [Distil Labs Website](https://distillabs.ai)
|
||||||
|
- [GitHub](https://github.com/distil-labs)
|
||||||
|
- [Hugging Face](https://huggingface.co/distil-labs)
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{distil-qwen3-4b-text2sql,
|
||||||
|
author = {Distil Labs},
|
||||||
|
title = {Distil-Qwen3-4B-Text2SQL: A Fine-tuned Model for Natural Language to SQL},
|
||||||
|
year = {2025},
|
||||||
|
publisher = {Hugging Face},
|
||||||
|
url = {https://huggingface.co/distil-labs/distil-qwen3-4b-text2sql}
|
||||||
|
}
|
||||||
|
```
|
||||||
13
STUDENT_LICENSE
Normal file
13
STUDENT_LICENSE
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
Copyright 2023 Qwen
|
||||||
|
|
||||||
|
Licensed under the Apache License, Version 2.0 (the "License");
|
||||||
|
you may not use this file except in compliance with the License.
|
||||||
|
You may obtain a copy of the License at
|
||||||
|
|
||||||
|
http://www.apache.org/licenses/LICENSE-2.0
|
||||||
|
|
||||||
|
Unless required by applicable law or agreed to in writing, software
|
||||||
|
distributed under the License is distributed on an "AS IS" BASIS,
|
||||||
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||||
|
See the License for the specific language governing permissions and
|
||||||
|
limitations under the License.
|
||||||
9
TEACHER_LICENSE
Normal file
9
TEACHER_LICENSE
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
MIT License
|
||||||
|
|
||||||
|
Copyright (c) 2023 DeepSeek
|
||||||
|
|
||||||
|
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
|
||||||
|
|
||||||
|
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
|
||||||
|
|
||||||
|
THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
70
config.json
Normal file
70
config.json
Normal file
@@ -0,0 +1,70 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 262144,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 5000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.53.0",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.8,
|
||||||
|
"transformers_version": "4.53.0"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
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 sha256:7ff64f59fedf1ec2cc9184e859cbe9ad5a41700566b6d6b0c5c24bfb18e15603
|
||||||
|
size 4967215360
|
||||||
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 sha256:2f81196c29e6d0913ee225ba6ede73339a4e357074325f6c709602feced13eda
|
||||||
|
size 3077766632
|
||||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 4022468096,
|
||||||
|
"total_size": 8044936192
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "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.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "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.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||||
|
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
38
special_tokens_map.json
Normal file
38
special_tokens_map.json
Normal file
@@ -0,0 +1,38 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:60927effd4aeb00104fe4716572e8db4041e32c0f2d175d8ae56816977013845
|
||||||
|
size 11422924
|
||||||
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 1010000,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
168
training-logs.csv
Normal file
168
training-logs.csv
Normal file
@@ -0,0 +1,168 @@
|
|||||||
|
,eval_loss,eval_binary,eval_rouge,eval_llm_as_a_judge,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,step,loss,grad_norm,learning_rate,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
|
||||||
|
0,1.0263168811798096,0.0,0.8630774330746501,0.0,49.0875,1.019,1.019,0.0,0,,,,,,,,
|
||||||
|
1,,,,,,,,0.02477455158061639,250,0.5324,1.523032546043396,6.067360079247153e-06,,,,,
|
||||||
|
2,,,,,,,,0.04954910316123278,500,0.1588,1.8619871139526367,1.225854383358098e-05,,,,,
|
||||||
|
3,,,,,,,,0.07432365474184917,750,0.1432,0.046056393533945084,1.8449727587914812e-05,,,,,
|
||||||
|
4,,,,,,,,0.09909820632246556,1000,0.1222,0.767810583114624,2.464091134224864e-05,,,,,
|
||||||
|
5,,,,,,,,0.12387275790308196,1250,0.1289,0.08577042073011398,3.083209509658247e-05,,,,,
|
||||||
|
6,,,,,,,,0.14864730948369834,1500,0.123,0.9776291847229004,3.70232788509163e-05,,,,,
|
||||||
|
7,,,,,,,,0.17342186106431473,1750,0.1247,0.6648195385932922,4.321446260525013e-05,,,,,
|
||||||
|
8,,,,,,,,0.19819641264493112,2000,0.1222,0.10744159668684006,4.940564635958396e-05,,,,,
|
||||||
|
9,,,,,,,,0.22297096422554752,2250,0.1197,0.4264952838420868,4.970530708045378e-05,,,,,
|
||||||
|
10,,,,,,,,0.2477455158061639,2500,0.1319,0.7932649850845337,4.937931933759291e-05,,,,,
|
||||||
|
11,,,,,,,,0.2725200673867803,2750,0.124,0.016937250271439552,4.905333159473204e-05,,,,,
|
||||||
|
12,,,,,,,,0.2972946189673967,3000,0.112,1.084240198135376,4.8727343851871173e-05,,,,,
|
||||||
|
13,,,,,,,,0.3220691705480131,3250,0.1105,0.058936528861522675,4.84013561090103e-05,,,,,
|
||||||
|
14,,,,,,,,0.34684372212862946,3500,0.117,2.2370946407318115,4.8075368366149436e-05,,,,,
|
||||||
|
15,,,,,,,,0.3716182737092459,3750,0.1142,0.25352439284324646,4.774938062328856e-05,,,,,
|
||||||
|
16,,,,,,,,0.39639282528986225,4000,0.115,0.746067225933075,4.74233928804277e-05,,,,,
|
||||||
|
17,,,,,,,,0.42116737687047867,4250,0.1315,0.5937117338180542,4.709740513756683e-05,,,,,
|
||||||
|
18,,,,,,,,0.44594192845109504,4500,0.1148,0.0067167095839977264,4.677141739470596e-05,,,,,
|
||||||
|
19,,,,,,,,0.4707164800317114,4750,0.1094,0.6822088360786438,4.644542965184509e-05,,,,,
|
||||||
|
20,,,,,,,,0.4954910316123278,5000,0.1123,0.5732296705245972,4.611944190898422e-05,,,,,
|
||||||
|
21,,,,,,,,0.5202655831929442,5250,0.105,1.033423662185669,4.5793454166123356e-05,,,,,
|
||||||
|
22,,,,,,,,0.5450401347735606,5500,0.1097,0.15889854729175568,4.546746642326249e-05,,,,,
|
||||||
|
23,,,,,,,,0.569814686354177,5750,0.1125,1.1788893938064575,4.514147868040162e-05,,,,,
|
||||||
|
24,,,,,,,,0.5945892379347933,6000,0.1078,0.23025964200496674,4.4815490937540746e-05,,,,,
|
||||||
|
25,,,,,,,,0.6193637895154098,6250,0.1026,0.9611893892288208,4.448950319467988e-05,,,,,
|
||||||
|
26,,,,,,,,0.6441383410960262,6500,0.0974,0.016058839857578278,4.4163515451819015e-05,,,,,
|
||||||
|
27,,,,,,,,0.6689128926766426,6750,0.0965,0.3839409649372101,4.383752770895814e-05,,,,,
|
||||||
|
28,,,,,,,,0.6936874442572589,7000,0.1098,0.3105497658252716,4.351153996609728e-05,,,,,
|
||||||
|
29,,,,,,,,0.7184619958378753,7250,0.1116,0.04357475787401199,4.318555222323641e-05,,,,,
|
||||||
|
30,,,,,,,,0.7432365474184918,7500,0.1061,0.26533493399620056,4.285956448037554e-05,,,,,
|
||||||
|
31,,,,,,,,0.7680110989991081,7750,0.1009,0.647885262966156,4.253357673751467e-05,,,,,
|
||||||
|
32,,,,,,,,0.7927856505797245,8000,0.0929,1.25872802734375,4.22075889946538e-05,,,,,
|
||||||
|
33,,,,,,,,0.8175602021603409,8250,0.0992,0.7607027888298035,4.1881601251792936e-05,,,,,
|
||||||
|
34,,,,,,,,0.8423347537409573,8500,0.097,0.023414086550474167,4.155561350893207e-05,,,,,
|
||||||
|
35,,,,,,,,0.8671093053215737,8750,0.0974,1.617354154586792,4.12296257660712e-05,,,,,
|
||||||
|
36,,,,,,,,0.8918838569021901,9000,0.0992,0.348496675491333,4.0903638023210325e-05,,,,,
|
||||||
|
37,,,,,,,,0.9166584084828064,9250,0.1068,0.45875710248947144,4.057765028034946e-05,,,,,
|
||||||
|
38,,,,,,,,0.9414329600634228,9500,0.0989,0.5602991580963135,4.0251662537488594e-05,,,,,
|
||||||
|
39,,,,,,,,0.9662075116440393,9750,0.0957,0.3049614131450653,3.992567479462773e-05,,,,,
|
||||||
|
40,,,,,,,,0.9909820632246557,10000,0.1069,0.5346589684486389,3.9599687051766856e-05,,,,,
|
||||||
|
41,0.06276851147413254,0.5,0.9718670465458659,0.5,39.1908,1.276,1.276,1.0,10091,,,,,,,,
|
||||||
|
42,,,,,,,,1.0157566148052721,10250,0.093,1.198898434638977,3.9273699308905984e-05,,,,,
|
||||||
|
43,,,,,,,,1.0405311663858885,10500,0.0856,0.5537581443786621,3.894771156604512e-05,,,,,
|
||||||
|
44,,,,,,,,1.0653057179665049,10750,0.0932,0.7537667155265808,3.862172382318425e-05,,,,,
|
||||||
|
45,,,,,,,,1.0900802695471212,11000,0.0842,0.5561412572860718,3.829573608032338e-05,,,,,
|
||||||
|
46,,,,,,,,1.1148548211277376,11250,0.0867,0.6610764861106873,3.797105228843396e-05,,,,,
|
||||||
|
47,,,,,,,,1.139629372708354,11500,0.08,2.3849334716796875,3.7645064545573086e-05,,,,,
|
||||||
|
48,,,,,,,,1.1644039242889703,11750,0.0848,0.4288468062877655,3.731907680271222e-05,,,,,
|
||||||
|
49,,,,,,,,1.1891784758695867,12000,0.0825,1.3528180122375488,3.699439301082279e-05,,,,,
|
||||||
|
50,,,,,,,,1.213953027450203,12250,0.0806,1.907565951347351,3.6668405267961925e-05,,,,,
|
||||||
|
51,,,,,,,,1.2387275790308196,12500,0.0832,0.8397055268287659,3.634241752510106e-05,,,,,
|
||||||
|
52,,,,,,,,1.263502130611436,12750,0.0877,0.14878003299236298,3.601642978224019e-05,,,,,
|
||||||
|
53,,,,,,,,1.2882766821920524,13000,0.0866,0.009639033116400242,3.569044203937932e-05,,,,,
|
||||||
|
54,,,,,,,,1.3130512337726687,13250,0.0791,0.03321487829089165,3.536445429651845e-05,,,,,
|
||||||
|
55,,,,,,,,1.3378257853532851,13500,0.0809,0.006037577521055937,3.5038466553657584e-05,,,,,
|
||||||
|
56,,,,,,,,1.3626003369339015,13750,0.0854,0.018767058849334717,3.471247881079672e-05,,,,,
|
||||||
|
57,,,,,,,,1.3873748885145178,14000,0.0922,0.07840000838041306,3.438649106793585e-05,,,,,
|
||||||
|
58,,,,,,,,1.4121494400951342,14250,0.0837,0.0023212512023746967,3.406050332507498e-05,,,,,
|
||||||
|
59,,,,,,,,1.4369239916757506,14500,0.0848,0.005713989492505789,3.373451558221411e-05,,,,,
|
||||||
|
60,,,,,,,,1.4616985432563672,14750,0.0858,0.5069279670715332,3.340852783935324e-05,,,,,
|
||||||
|
61,,,,,,,,1.4864730948369835,15000,0.079,0.7604624032974243,3.308254009649238e-05,,,,,
|
||||||
|
62,,,,,,,,1.5112476464176,15250,0.0929,0.8304641246795654,3.2756552353631505e-05,,,,,
|
||||||
|
63,,,,,,,,1.5360221979982163,15500,0.0883,0.7251547574996948,3.243186856174208e-05,,,,,
|
||||||
|
64,,,,,,,,1.5607967495788326,15750,0.0778,1.3709897994995117,3.210588081888121e-05,,,,,
|
||||||
|
65,,,,,,,,1.585571301159449,16000,0.0802,2.1567022800445557,3.1779893076020344e-05,,,,,
|
||||||
|
66,,,,,,,,1.6103458527400654,16250,0.0831,0.09836085140705109,3.145390533315947e-05,,,,,
|
||||||
|
67,,,,,,,,1.635120404320682,16500,0.0795,0.4006144106388092,3.1127917590298606e-05,,,,,
|
||||||
|
68,,,,,,,,1.659894955901298,16750,0.0856,0.2960919439792633,3.080192984743774e-05,,,,,
|
||||||
|
69,,,,,,,,1.6846695074819147,17000,0.0889,0.02061443217098713,3.0475942104576872e-05,,,,,
|
||||||
|
70,,,,,,,,1.7094440590625308,17250,0.0754,0.7631092071533203,3.0149954361716e-05,,,,,
|
||||||
|
71,,,,,,,,1.7342186106431474,17500,0.0775,0.6703758239746094,2.982396661885513e-05,,,,,
|
||||||
|
72,,,,,,,,1.7589931622237638,17750,0.0817,0.756374716758728,2.9497978875994265e-05,,,,,
|
||||||
|
73,,,,,,,,1.7837677138043802,18000,0.0876,0.5492820739746094,2.9171991133133396e-05,,,,,
|
||||||
|
74,,,,,,,,1.8085422653849965,18250,0.0882,0.3442634642124176,2.8846003390272524e-05,,,,,
|
||||||
|
75,,,,,,,,1.8333168169656129,18500,0.0861,3.4848599433898926,2.8520015647411658e-05,,,,,
|
||||||
|
76,,,,,,,,1.8580913685462295,18750,0.0921,0.46571600437164307,2.819402790455079e-05,,,,,
|
||||||
|
77,,,,,,,,1.8828659201268456,19000,0.0792,0.221365824341774,2.7868040161689924e-05,,,,,
|
||||||
|
78,,,,,,,,1.9076404717074622,19250,0.0849,0.819985032081604,2.754205241882905e-05,,,,,
|
||||||
|
79,,,,,,,,1.9324150232880783,19500,0.0879,0.06596075743436813,2.7216064675968182e-05,,,,,
|
||||||
|
80,,,,,,,,1.957189574868695,19750,0.0855,0.5881988406181335,2.689138088407876e-05,,,,,
|
||||||
|
81,,,,,,,,1.9819641264493113,20000,0.0782,0.5516498684883118,2.656539314121789e-05,,,,,
|
||||||
|
82,0.053498007357120514,0.54,0.9765167610159038,0.54,39.3735,1.27,1.27,2.0,20182,,,,,,,,
|
||||||
|
83,,,,,,,,2.0067386780299277,20250,0.0736,0.7942800521850586,2.6239405398357025e-05,,,,,
|
||||||
|
84,,,,,,,,2.0315132296105443,20500,0.0626,0.0008877600193955004,2.5913417655496153e-05,,,,,
|
||||||
|
85,,,,,,,,2.0562877811911604,20750,0.0667,1.7306857109069824,2.5587429912635284e-05,,,,,
|
||||||
|
86,,,,,,,,2.081062332771777,21000,0.0611,0.08003373444080353,2.526144216977442e-05,,,,,
|
||||||
|
87,,,,,,,,2.105836884352393,21250,0.0651,0.6958248019218445,2.493545442691355e-05,,,,,
|
||||||
|
88,,,,,,,,2.1306114359330097,21500,0.0698,0.6856549978256226,2.460946668405268e-05,,,,,
|
||||||
|
89,,,,,,,,2.155385987513626,21750,0.0619,0.28693079948425293,2.4283478941191812e-05,,,,,
|
||||||
|
90,,,,,,,,2.1801605390942425,22000,0.0698,0.21666885912418365,2.3957491198330946e-05,,,,,
|
||||||
|
91,,,,,,,,2.2049350906748586,22250,0.0668,0.8755005598068237,2.3631503455470074e-05,,,,,
|
||||||
|
92,,,,,,,,2.229709642255475,22500,0.0713,0.23723356425762177,2.3305515712609208e-05,,,,,
|
||||||
|
93,,,,,,,,2.2544841938360918,22750,0.0593,0.7852942943572998,2.297952796974834e-05,,,,,
|
||||||
|
94,,,,,,,,2.279258745416708,23000,0.067,1.1780858039855957,2.265354022688747e-05,,,,,
|
||||||
|
95,,,,,,,,2.3040332969973245,23250,0.0691,0.7586830854415894,2.23275524840266e-05,,,,,
|
||||||
|
96,,,,,,,,2.3288078485779407,23500,0.0673,0.272504061460495,2.2001564741165732e-05,,,,,
|
||||||
|
97,,,,,,,,2.3535824001585572,23750,0.0702,0.830717146396637,2.1676880949276307e-05,,,,,
|
||||||
|
98,,,,,,,,2.3783569517391734,24000,0.0693,1.0476861000061035,2.135089320641544e-05,,,,,
|
||||||
|
99,,,,,,,,2.40313150331979,24250,0.0601,0.2545061409473419,2.102490546355457e-05,,,,,
|
||||||
|
100,,,,,,,,2.427906054900406,24500,0.0645,0.5762472152709961,2.0698917720693703e-05,,,,,
|
||||||
|
101,,,,,,,,2.4526806064810227,24750,0.0754,0.5169177055358887,2.0372929977832834e-05,,,,,
|
||||||
|
102,,,,,,,,2.4774551580616393,25000,0.0648,0.3621724545955658,2.0046942234971965e-05,,,,,
|
||||||
|
103,,,,,,,,2.5022297096422554,25250,0.071,0.9184062480926514,1.97209544921111e-05,,,,,
|
||||||
|
104,,,,,,,,2.527004261222872,25500,0.0733,0.05600641295313835,1.939496674925023e-05,,,,,
|
||||||
|
105,,,,,,,,2.551778812803488,25750,0.0667,0.017861563712358475,1.9070282957360805e-05,,,,,
|
||||||
|
106,,,,,,,,2.5765533643841048,26000,0.0595,1.1122207641601562,1.8744295214499936e-05,,,,,
|
||||||
|
107,,,,,,,,2.601327915964721,26250,0.0657,0.022980080917477608,1.841961142261051e-05,,,,,
|
||||||
|
108,,,,,,,,2.6261024675453375,26500,0.0718,0.4926201105117798,1.809362367974964e-05,,,,,
|
||||||
|
109,,,,,,,,2.6508770191259536,26750,0.0633,0.6802681088447571,1.7767635936888775e-05,,,,,
|
||||||
|
110,,,,,,,,2.6756515707065702,27000,0.063,0.33439555764198303,1.7441648194027903e-05,,,,,
|
||||||
|
111,,,,,,,,2.700426122287187,27250,0.067,0.07250916957855225,1.7115660451167038e-05,,,,,
|
||||||
|
112,,,,,,,,2.725200673867803,27500,0.0678,0.013326438143849373,1.678967270830617e-05,,,,,
|
||||||
|
113,,,,,,,,2.7499752254484195,27750,0.0651,0.48589280247688293,1.64636849654453e-05,,,,,
|
||||||
|
114,,,,,,,,2.7747497770290357,28000,0.0582,0.0067026917822659016,1.613769722258443e-05,,,,,
|
||||||
|
115,,,,,,,,2.7995243286096523,28250,0.0682,0.0031660799868404865,1.5811709479723562e-05,,,,,
|
||||||
|
116,,,,,,,,2.8242988801902684,28500,0.0648,1.3722319602966309,1.5485721736862693e-05,,,,,
|
||||||
|
117,,,,,,,,2.849073431770885,28750,0.0687,0.9632564187049866,1.5159733994001826e-05,,,,,
|
||||||
|
118,,,,,,,,2.873847983351501,29000,0.0567,0.3386249244213104,1.483374625114096e-05,,,,,
|
||||||
|
119,,,,,,,,2.8986225349321177,29250,0.0679,0.33812034130096436,1.450775850828009e-05,,,,,
|
||||||
|
120,,,,,,,,2.9233970865127343,29500,0.0609,0.356045663356781,1.4181770765419222e-05,,,,,
|
||||||
|
121,,,,,,,,2.9481716380933505,29750,0.0675,0.031641993671655655,1.3855783022558353e-05,,,,,
|
||||||
|
122,,,,,,,,2.972946189673967,30000,0.0637,0.0011654272675514221,1.3529795279697486e-05,,,,,
|
||||||
|
123,,,,,,,,2.997720741254583,30250,0.0642,0.00022352008090820163,1.3203807536836615e-05,,,,,
|
||||||
|
124,0.05629619210958481,0.54,0.9778917608241781,0.54,39.6277,1.262,1.262,3.0,30273,,,,,,,,
|
||||||
|
125,,,,,,,,3.0224952928352,30500,0.0566,0.7295501828193665,1.2879123744947191e-05,,,,,
|
||||||
|
126,,,,,,,,3.047269844415816,30750,0.055,2.9202334880828857,1.2553136002086322e-05,,,,,
|
||||||
|
127,,,,,,,,3.0720443959964325,31000,0.0614,0.2907790243625641,1.2227148259225455e-05,,,,,
|
||||||
|
128,,,,,,,,3.0968189475770487,31250,0.0532,0.0033611482940614223,1.1901160516364586e-05,,,,,
|
||||||
|
129,,,,,,,,3.1215934991576653,31500,0.0478,0.5726149678230286,1.1575172773503717e-05,,,,,
|
||||||
|
130,,,,,,,,3.146368050738282,31750,0.0544,0.8363867402076721,1.124918503064285e-05,,,,,
|
||||||
|
131,,,,,,,,3.171142602318898,32000,0.0594,0.7790529727935791,1.092319728778198e-05,,,,,
|
||||||
|
132,,,,,,,,3.1959171538995146,32250,0.0544,0.010002855211496353,1.0597209544921112e-05,,,,,
|
||||||
|
133,,,,,,,,3.2206917054801307,32500,0.0538,0.02614864706993103,1.0271221802060243e-05,,,,,
|
||||||
|
134,,,,,,,,3.2454662570607473,32750,0.0492,1.2334165573120117,9.945234059199376e-06,,,,,
|
||||||
|
135,,,,,,,,3.2702408086413635,33000,0.0557,0.4991805851459503,9.619246316338507e-06,,,,,
|
||||||
|
136,,,,,,,,3.29501536022198,33250,0.0522,0.7711235284805298,9.29456252444908e-06,,,,,
|
||||||
|
137,,,,,,,,3.319789911802596,33500,0.047,0.45638665556907654,8.968574781588213e-06,,,,,
|
||||||
|
138,,,,,,,,3.344564463383213,33750,0.0542,0.9393787384033203,8.642587038727344e-06,,,,,
|
||||||
|
139,,,,,,,,3.3693390149638294,34000,0.0506,0.20903021097183228,8.316599295866476e-06,,,,,
|
||||||
|
140,,,,,,,,3.3941135665444455,34250,0.0508,0.5082834959030151,7.990611553005607e-06,,,,,
|
||||||
|
141,,,,,,,,3.418888118125062,34500,0.0474,0.20875811576843262,7.66462381014474e-06,,,,,
|
||||||
|
142,,,,,,,,3.4436626697056782,34750,0.0497,0.28049978613853455,7.33863606728387e-06,,,,,
|
||||||
|
143,,,,,,,,3.468437221286295,35000,0.054,0.8045966625213623,7.0126483244230014e-06,,,,,
|
||||||
|
144,,,,,,,,3.493211772866911,35250,0.0463,1.8549096584320068,6.686660581562133e-06,,,,,
|
||||||
|
145,,,,,,,,3.5179863244475276,35500,0.0493,0.01312224566936493,6.363280740644152e-06,,,,,
|
||||||
|
146,,,,,,,,3.5427608760281437,35750,0.049,1.024755835533142,6.037292997783284e-06,,,,,
|
||||||
|
147,,,,,,,,3.5675354276087603,36000,0.0495,1.1740553379058838,5.711305254922415e-06,,,,,
|
||||||
|
148,,,,,,,,3.592309979189377,36250,0.0537,0.3666393458843231,5.385317512061547e-06,,,,,
|
||||||
|
149,,,,,,,,3.617084530769993,36500,0.0483,1.2278428077697754,5.059329769200678e-06,,,,,
|
||||||
|
150,,,,,,,,3.641859082350609,36750,0.0507,1.8344718217849731,4.73334202633981e-06,,,,,
|
||||||
|
151,,,,,,,,3.6666336339312258,37000,0.0489,1.3024396896362305,4.407354283478941e-06,,,,,
|
||||||
|
152,,,,,,,,3.6914081855118424,37250,0.0529,0.5916293859481812,4.081366540618073e-06,,,,,
|
||||||
|
153,,,,,,,,3.7161827370924585,37500,0.0522,0.7963153719902039,3.7553787977572044e-06,,,,,
|
||||||
|
154,,,,,,,,3.740957288673075,37750,0.0495,1.1936062574386597,3.429391054896336e-06,,,,,
|
||||||
|
155,,,,,,,,3.7657318402536912,38000,0.05,0.0045746322721242905,3.1034033120354673e-06,,,,,
|
||||||
|
156,,,,,,,,3.790506391834308,38250,0.0525,0.3080344498157501,2.777415569174599e-06,,,,,
|
||||||
|
157,,,,,,,,3.8152809434149244,38500,0.0497,0.7108872532844543,2.4514278263137307e-06,,,,,
|
||||||
|
158,,,,,,,,3.8400554949955406,38750,0.0529,0.5039321184158325,2.1254400834528626e-06,,,,,
|
||||||
|
159,,,,,,,,3.8648300465761567,39000,0.0515,0.45206305384635925,1.7994523405919939e-06,,,,,
|
||||||
|
160,,,,,,,,3.8896045981567733,39250,0.0451,0.5372409820556641,1.4734645977311256e-06,,,,,
|
||||||
|
161,,,,,,,,3.91437914973739,39500,0.0579,0.23797687888145447,1.147476854870257e-06,,,,,
|
||||||
|
162,,,,,,,,3.939153701318006,39750,0.0487,0.8789421319961548,8.22793062980832e-07,,,,,
|
||||||
|
163,,,,,,,,3.9639282528986226,40000,0.0492,0.1474274843931198,4.968053201199636e-07,,,,,
|
||||||
|
164,,,,,,,,3.9887028044792388,40250,0.0538,0.007477769162505865,1.7081757725909506e-07,,,,,
|
||||||
|
165,0.05352379381656647,0.54,0.9770745948806367,0.54,39.8893,1.253,1.253,4.0,40364,,,,,,,,
|
||||||
|
166,,,,,,,,4.0,40364,,,,6734.6117,5.994,5.994,3.153073337044746e+17,0.08114129684687535
|
||||||
|
167
training-logs.json
Normal file
167
training-logs.json
Normal file
@@ -0,0 +1,167 @@
|
|||||||
|
{"eval_loss":1.0263168812,"eval_binary":0.0,"eval_rouge":0.8630774331,"eval_llm_as_a_judge":0.0,"eval_runtime":49.0875,"eval_samples_per_second":1.019,"eval_steps_per_second":1.019,"epoch":0.0,"step":0,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0247745516,"step":250,"loss":0.5324,"grad_norm":1.523032546,"learning_rate":0.0000060674,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0495491032,"step":500,"loss":0.1588,"grad_norm":1.861987114,"learning_rate":0.0000122585,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0743236547,"step":750,"loss":0.1432,"grad_norm":0.0460563935,"learning_rate":0.0000184497,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.0990982063,"step":1000,"loss":0.1222,"grad_norm":0.7678105831,"learning_rate":0.0000246409,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1238727579,"step":1250,"loss":0.1289,"grad_norm":0.0857704207,"learning_rate":0.0000308321,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1486473095,"step":1500,"loss":0.123,"grad_norm":0.9776291847,"learning_rate":0.0000370233,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1734218611,"step":1750,"loss":0.1247,"grad_norm":0.6648195386,"learning_rate":0.0000432145,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.1981964126,"step":2000,"loss":0.1222,"grad_norm":0.1074415967,"learning_rate":0.0000494056,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.2229709642,"step":2250,"loss":0.1197,"grad_norm":0.4264952838,"learning_rate":0.0000497053,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.2477455158,"step":2500,"loss":0.1319,"grad_norm":0.7932649851,"learning_rate":0.0000493793,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.2725200674,"step":2750,"loss":0.124,"grad_norm":0.0169372503,"learning_rate":0.0000490533,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.297294619,"step":3000,"loss":0.112,"grad_norm":1.0842401981,"learning_rate":0.0000487273,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3220691705,"step":3250,"loss":0.1105,"grad_norm":0.0589365289,"learning_rate":0.0000484014,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3468437221,"step":3500,"loss":0.117,"grad_norm":2.2370946407,"learning_rate":0.0000480754,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3716182737,"step":3750,"loss":0.1142,"grad_norm":0.2535243928,"learning_rate":0.0000477494,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.3963928253,"step":4000,"loss":0.115,"grad_norm":0.7460672259,"learning_rate":0.0000474234,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.4211673769,"step":4250,"loss":0.1315,"grad_norm":0.5937117338,"learning_rate":0.0000470974,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.4459419285,"step":4500,"loss":0.1148,"grad_norm":0.0067167096,"learning_rate":0.0000467714,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.47071648,"step":4750,"loss":0.1094,"grad_norm":0.6822088361,"learning_rate":0.0000464454,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.4954910316,"step":5000,"loss":0.1123,"grad_norm":0.5732296705,"learning_rate":0.0000461194,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.5202655832,"step":5250,"loss":0.105,"grad_norm":1.0334236622,"learning_rate":0.0000457935,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.5450401348,"step":5500,"loss":0.1097,"grad_norm":0.1588985473,"learning_rate":0.0000454675,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.5698146864,"step":5750,"loss":0.1125,"grad_norm":1.1788893938,"learning_rate":0.0000451415,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.5945892379,"step":6000,"loss":0.1078,"grad_norm":0.230259642,"learning_rate":0.0000448155,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6193637895,"step":6250,"loss":0.1026,"grad_norm":0.9611893892,"learning_rate":0.0000444895,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6441383411,"step":6500,"loss":0.0974,"grad_norm":0.0160588399,"learning_rate":0.0000441635,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6689128927,"step":6750,"loss":0.0965,"grad_norm":0.3839409649,"learning_rate":0.0000438375,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.6936874443,"step":7000,"loss":0.1098,"grad_norm":0.3105497658,"learning_rate":0.0000435115,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.7184619958,"step":7250,"loss":0.1116,"grad_norm":0.0435747579,"learning_rate":0.0000431856,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.7432365474,"step":7500,"loss":0.1061,"grad_norm":0.265334934,"learning_rate":0.0000428596,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.768011099,"step":7750,"loss":0.1009,"grad_norm":0.647885263,"learning_rate":0.0000425336,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.7927856506,"step":8000,"loss":0.0929,"grad_norm":1.2587280273,"learning_rate":0.0000422076,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8175602022,"step":8250,"loss":0.0992,"grad_norm":0.7607027888,"learning_rate":0.0000418816,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8423347537,"step":8500,"loss":0.097,"grad_norm":0.0234140866,"learning_rate":0.0000415556,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8671093053,"step":8750,"loss":0.0974,"grad_norm":1.6173541546,"learning_rate":0.0000412296,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.8918838569,"step":9000,"loss":0.0992,"grad_norm":0.3484966755,"learning_rate":0.0000409036,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9166584085,"step":9250,"loss":0.1068,"grad_norm":0.4587571025,"learning_rate":0.0000405777,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9414329601,"step":9500,"loss":0.0989,"grad_norm":0.5602991581,"learning_rate":0.0000402517,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9662075116,"step":9750,"loss":0.0957,"grad_norm":0.3049614131,"learning_rate":0.0000399257,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":0.9909820632,"step":10000,"loss":0.1069,"grad_norm":0.5346589684,"learning_rate":0.0000395997,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":0.0627685115,"eval_binary":0.5,"eval_rouge":0.9718670465,"eval_llm_as_a_judge":0.5,"eval_runtime":39.1908,"eval_samples_per_second":1.276,"eval_steps_per_second":1.276,"epoch":1.0,"step":10091,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.0157566148,"step":10250,"loss":0.093,"grad_norm":1.1988984346,"learning_rate":0.0000392737,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.0405311664,"step":10500,"loss":0.0856,"grad_norm":0.5537581444,"learning_rate":0.0000389477,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.065305718,"step":10750,"loss":0.0932,"grad_norm":0.7537667155,"learning_rate":0.0000386217,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.0900802695,"step":11000,"loss":0.0842,"grad_norm":0.5561412573,"learning_rate":0.0000382957,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1148548211,"step":11250,"loss":0.0867,"grad_norm":0.6610764861,"learning_rate":0.0000379711,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1396293727,"step":11500,"loss":0.08,"grad_norm":2.3849334717,"learning_rate":0.0000376451,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1644039243,"step":11750,"loss":0.0848,"grad_norm":0.4288468063,"learning_rate":0.0000373191,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.1891784759,"step":12000,"loss":0.0825,"grad_norm":1.3528180122,"learning_rate":0.0000369944,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.2139530275,"step":12250,"loss":0.0806,"grad_norm":1.9075659513,"learning_rate":0.0000366684,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.238727579,"step":12500,"loss":0.0832,"grad_norm":0.8397055268,"learning_rate":0.0000363424,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.2635021306,"step":12750,"loss":0.0877,"grad_norm":0.148780033,"learning_rate":0.0000360164,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.2882766822,"step":13000,"loss":0.0866,"grad_norm":0.0096390331,"learning_rate":0.0000356904,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.3130512338,"step":13250,"loss":0.0791,"grad_norm":0.0332148783,"learning_rate":0.0000353645,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.3378257854,"step":13500,"loss":0.0809,"grad_norm":0.0060375775,"learning_rate":0.0000350385,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.3626003369,"step":13750,"loss":0.0854,"grad_norm":0.0187670588,"learning_rate":0.0000347125,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.3873748885,"step":14000,"loss":0.0922,"grad_norm":0.0784000084,"learning_rate":0.0000343865,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4121494401,"step":14250,"loss":0.0837,"grad_norm":0.0023212512,"learning_rate":0.0000340605,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4369239917,"step":14500,"loss":0.0848,"grad_norm":0.0057139895,"learning_rate":0.0000337345,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4616985433,"step":14750,"loss":0.0858,"grad_norm":0.5069279671,"learning_rate":0.0000334085,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.4864730948,"step":15000,"loss":0.079,"grad_norm":0.7604624033,"learning_rate":0.0000330825,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.5112476464,"step":15250,"loss":0.0929,"grad_norm":0.8304641247,"learning_rate":0.0000327566,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.536022198,"step":15500,"loss":0.0883,"grad_norm":0.7251547575,"learning_rate":0.0000324319,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.5607967496,"step":15750,"loss":0.0778,"grad_norm":1.3709897995,"learning_rate":0.0000321059,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.5855713012,"step":16000,"loss":0.0802,"grad_norm":2.15670228,"learning_rate":0.0000317799,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6103458527,"step":16250,"loss":0.0831,"grad_norm":0.0983608514,"learning_rate":0.0000314539,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6351204043,"step":16500,"loss":0.0795,"grad_norm":0.4006144106,"learning_rate":0.0000311279,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6598949559,"step":16750,"loss":0.0856,"grad_norm":0.296091944,"learning_rate":0.0000308019,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.6846695075,"step":17000,"loss":0.0889,"grad_norm":0.0206144322,"learning_rate":0.0000304759,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7094440591,"step":17250,"loss":0.0754,"grad_norm":0.7631092072,"learning_rate":0.00003015,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7342186106,"step":17500,"loss":0.0775,"grad_norm":0.670375824,"learning_rate":0.000029824,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7589931622,"step":17750,"loss":0.0817,"grad_norm":0.7563747168,"learning_rate":0.000029498,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.7837677138,"step":18000,"loss":0.0876,"grad_norm":0.549282074,"learning_rate":0.000029172,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.8085422654,"step":18250,"loss":0.0882,"grad_norm":0.3442634642,"learning_rate":0.000028846,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.833316817,"step":18500,"loss":0.0861,"grad_norm":3.4848599434,"learning_rate":0.00002852,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.8580913685,"step":18750,"loss":0.0921,"grad_norm":0.4657160044,"learning_rate":0.000028194,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.8828659201,"step":19000,"loss":0.0792,"grad_norm":0.2213658243,"learning_rate":0.000027868,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.9076404717,"step":19250,"loss":0.0849,"grad_norm":0.8199850321,"learning_rate":0.0000275421,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.9324150233,"step":19500,"loss":0.0879,"grad_norm":0.0659607574,"learning_rate":0.0000272161,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.9571895749,"step":19750,"loss":0.0855,"grad_norm":0.5881988406,"learning_rate":0.0000268914,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":1.9819641264,"step":20000,"loss":0.0782,"grad_norm":0.5516498685,"learning_rate":0.0000265654,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":0.0534980074,"eval_binary":0.54,"eval_rouge":0.976516761,"eval_llm_as_a_judge":0.54,"eval_runtime":39.3735,"eval_samples_per_second":1.27,"eval_steps_per_second":1.27,"epoch":2.0,"step":20182,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.006738678,"step":20250,"loss":0.0736,"grad_norm":0.7942800522,"learning_rate":0.0000262394,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.0315132296,"step":20500,"loss":0.0626,"grad_norm":0.00088776,"learning_rate":0.0000259134,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.0562877812,"step":20750,"loss":0.0667,"grad_norm":1.7306857109,"learning_rate":0.0000255874,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.0810623328,"step":21000,"loss":0.0611,"grad_norm":0.0800337344,"learning_rate":0.0000252614,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1058368844,"step":21250,"loss":0.0651,"grad_norm":0.6958248019,"learning_rate":0.0000249355,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1306114359,"step":21500,"loss":0.0698,"grad_norm":0.6856549978,"learning_rate":0.0000246095,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1553859875,"step":21750,"loss":0.0619,"grad_norm":0.2869307995,"learning_rate":0.0000242835,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.1801605391,"step":22000,"loss":0.0698,"grad_norm":0.2166688591,"learning_rate":0.0000239575,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2049350907,"step":22250,"loss":0.0668,"grad_norm":0.8755005598,"learning_rate":0.0000236315,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2297096423,"step":22500,"loss":0.0713,"grad_norm":0.2372335643,"learning_rate":0.0000233055,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2544841938,"step":22750,"loss":0.0593,"grad_norm":0.7852942944,"learning_rate":0.0000229795,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.2792587454,"step":23000,"loss":0.067,"grad_norm":1.178085804,"learning_rate":0.0000226535,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.304033297,"step":23250,"loss":0.0691,"grad_norm":0.7586830854,"learning_rate":0.0000223276,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.3288078486,"step":23500,"loss":0.0673,"grad_norm":0.2725040615,"learning_rate":0.0000220016,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.3535824002,"step":23750,"loss":0.0702,"grad_norm":0.8307171464,"learning_rate":0.0000216769,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.3783569517,"step":24000,"loss":0.0693,"grad_norm":1.0476861,"learning_rate":0.0000213509,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.4031315033,"step":24250,"loss":0.0601,"grad_norm":0.2545061409,"learning_rate":0.0000210249,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.4279060549,"step":24500,"loss":0.0645,"grad_norm":0.5762472153,"learning_rate":0.0000206989,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.4526806065,"step":24750,"loss":0.0754,"grad_norm":0.5169177055,"learning_rate":0.0000203729,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.4774551581,"step":25000,"loss":0.0648,"grad_norm":0.3621724546,"learning_rate":0.0000200469,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5022297096,"step":25250,"loss":0.071,"grad_norm":0.9184062481,"learning_rate":0.000019721,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5270042612,"step":25500,"loss":0.0733,"grad_norm":0.056006413,"learning_rate":0.000019395,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5517788128,"step":25750,"loss":0.0667,"grad_norm":0.0178615637,"learning_rate":0.0000190703,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.5765533644,"step":26000,"loss":0.0595,"grad_norm":1.1122207642,"learning_rate":0.0000187443,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.601327916,"step":26250,"loss":0.0657,"grad_norm":0.0229800809,"learning_rate":0.0000184196,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.6261024675,"step":26500,"loss":0.0718,"grad_norm":0.4926201105,"learning_rate":0.0000180936,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.6508770191,"step":26750,"loss":0.0633,"grad_norm":0.6802681088,"learning_rate":0.0000177676,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.6756515707,"step":27000,"loss":0.063,"grad_norm":0.3343955576,"learning_rate":0.0000174416,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7004261223,"step":27250,"loss":0.067,"grad_norm":0.0725091696,"learning_rate":0.0000171157,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7252006739,"step":27500,"loss":0.0678,"grad_norm":0.0133264381,"learning_rate":0.0000167897,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7499752254,"step":27750,"loss":0.0651,"grad_norm":0.4858928025,"learning_rate":0.0000164637,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.774749777,"step":28000,"loss":0.0582,"grad_norm":0.0067026918,"learning_rate":0.0000161377,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.7995243286,"step":28250,"loss":0.0682,"grad_norm":0.00316608,"learning_rate":0.0000158117,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8242988802,"step":28500,"loss":0.0648,"grad_norm":1.3722319603,"learning_rate":0.0000154857,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8490734318,"step":28750,"loss":0.0687,"grad_norm":0.9632564187,"learning_rate":0.0000151597,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8738479834,"step":29000,"loss":0.0567,"grad_norm":0.3386249244,"learning_rate":0.0000148337,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.8986225349,"step":29250,"loss":0.0679,"grad_norm":0.3381203413,"learning_rate":0.0000145078,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9233970865,"step":29500,"loss":0.0609,"grad_norm":0.3560456634,"learning_rate":0.0000141818,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9481716381,"step":29750,"loss":0.0675,"grad_norm":0.0316419937,"learning_rate":0.0000138558,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9729461897,"step":30000,"loss":0.0637,"grad_norm":0.0011654273,"learning_rate":0.0000135298,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":2.9977207413,"step":30250,"loss":0.0642,"grad_norm":0.0002235201,"learning_rate":0.0000132038,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":0.0562961921,"eval_binary":0.54,"eval_rouge":0.9778917608,"eval_llm_as_a_judge":0.54,"eval_runtime":39.6277,"eval_samples_per_second":1.262,"eval_steps_per_second":1.262,"epoch":3.0,"step":30273,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.0224952928,"step":30500,"loss":0.0566,"grad_norm":0.7295501828,"learning_rate":0.0000128791,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.0472698444,"step":30750,"loss":0.055,"grad_norm":2.9202334881,"learning_rate":0.0000125531,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.072044396,"step":31000,"loss":0.0614,"grad_norm":0.2907790244,"learning_rate":0.0000122271,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.0968189476,"step":31250,"loss":0.0532,"grad_norm":0.0033611483,"learning_rate":0.0000119012,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1215934992,"step":31500,"loss":0.0478,"grad_norm":0.5726149678,"learning_rate":0.0000115752,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1463680507,"step":31750,"loss":0.0544,"grad_norm":0.8363867402,"learning_rate":0.0000112492,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1711426023,"step":32000,"loss":0.0594,"grad_norm":0.7790529728,"learning_rate":0.0000109232,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.1959171539,"step":32250,"loss":0.0544,"grad_norm":0.0100028552,"learning_rate":0.0000105972,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2206917055,"step":32500,"loss":0.0538,"grad_norm":0.0261486471,"learning_rate":0.0000102712,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2454662571,"step":32750,"loss":0.0492,"grad_norm":1.2334165573,"learning_rate":0.0000099452,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2702408086,"step":33000,"loss":0.0557,"grad_norm":0.4991805851,"learning_rate":0.0000096192,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.2950153602,"step":33250,"loss":0.0522,"grad_norm":0.7711235285,"learning_rate":0.0000092946,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.3197899118,"step":33500,"loss":0.047,"grad_norm":0.4563866556,"learning_rate":0.0000089686,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.3445644634,"step":33750,"loss":0.0542,"grad_norm":0.9393787384,"learning_rate":0.0000086426,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.369339015,"step":34000,"loss":0.0506,"grad_norm":0.209030211,"learning_rate":0.0000083166,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.3941135665,"step":34250,"loss":0.0508,"grad_norm":0.5082834959,"learning_rate":0.0000079906,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4188881181,"step":34500,"loss":0.0474,"grad_norm":0.2087581158,"learning_rate":0.0000076646,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4436626697,"step":34750,"loss":0.0497,"grad_norm":0.2804997861,"learning_rate":0.0000073386,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4684372213,"step":35000,"loss":0.054,"grad_norm":0.8045966625,"learning_rate":0.0000070126,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.4932117729,"step":35250,"loss":0.0463,"grad_norm":1.8549096584,"learning_rate":0.0000066867,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.5179863244,"step":35500,"loss":0.0493,"grad_norm":0.0131222457,"learning_rate":0.0000063633,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.542760876,"step":35750,"loss":0.049,"grad_norm":1.0247558355,"learning_rate":0.0000060373,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.5675354276,"step":36000,"loss":0.0495,"grad_norm":1.1740553379,"learning_rate":0.0000057113,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.5923099792,"step":36250,"loss":0.0537,"grad_norm":0.3666393459,"learning_rate":0.0000053853,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6170845308,"step":36500,"loss":0.0483,"grad_norm":1.2278428078,"learning_rate":0.0000050593,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6418590824,"step":36750,"loss":0.0507,"grad_norm":1.8344718218,"learning_rate":0.0000047333,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6666336339,"step":37000,"loss":0.0489,"grad_norm":1.3024396896,"learning_rate":0.0000044074,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.6914081855,"step":37250,"loss":0.0529,"grad_norm":0.5916293859,"learning_rate":0.0000040814,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7161827371,"step":37500,"loss":0.0522,"grad_norm":0.796315372,"learning_rate":0.0000037554,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7409572887,"step":37750,"loss":0.0495,"grad_norm":1.1936062574,"learning_rate":0.0000034294,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7657318403,"step":38000,"loss":0.05,"grad_norm":0.0045746323,"learning_rate":0.0000031034,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.7905063918,"step":38250,"loss":0.0525,"grad_norm":0.3080344498,"learning_rate":0.0000027774,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.8152809434,"step":38500,"loss":0.0497,"grad_norm":0.7108872533,"learning_rate":0.0000024514,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.840055495,"step":38750,"loss":0.0529,"grad_norm":0.5039321184,"learning_rate":0.0000021254,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.8648300466,"step":39000,"loss":0.0515,"grad_norm":0.4520630538,"learning_rate":0.0000017995,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.8896045982,"step":39250,"loss":0.0451,"grad_norm":0.5372409821,"learning_rate":0.0000014735,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9143791497,"step":39500,"loss":0.0579,"grad_norm":0.2379768789,"learning_rate":0.0000011475,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9391537013,"step":39750,"loss":0.0487,"grad_norm":0.878942132,"learning_rate":0.0000008228,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9639282529,"step":40000,"loss":0.0492,"grad_norm":0.1474274844,"learning_rate":0.0000004968,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":3.9887028045,"step":40250,"loss":0.0538,"grad_norm":0.0074777692,"learning_rate":0.0000001708,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":0.0535237938,"eval_binary":0.54,"eval_rouge":0.9770745949,"eval_llm_as_a_judge":0.54,"eval_runtime":39.8893,"eval_samples_per_second":1.253,"eval_steps_per_second":1.253,"epoch":4.0,"step":40364,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":null,"train_samples_per_second":null,"train_steps_per_second":null,"total_flos":null,"train_loss":null}
|
||||||
|
{"eval_loss":null,"eval_binary":null,"eval_rouge":null,"eval_llm_as_a_judge":null,"eval_runtime":null,"eval_samples_per_second":null,"eval_steps_per_second":null,"epoch":4.0,"step":40364,"loss":null,"grad_norm":null,"learning_rate":null,"train_runtime":6734.6117,"train_samples_per_second":5.994,"train_steps_per_second":5.994,"total_flos":3.153073337e+17,"train_loss":0.0811412968}
|
||||||
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