初始化项目，由ModelHub XC社区提供模型
Model: hZzy/mistral-7b-sft-7b-submission-win Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
||||
library_name: transformers
|
||||
model_name: mistral-7b-sft-7b-submission-win
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- sft
|
||||
- trl
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for mistral-7b-sft-7b-submission-win
|
||||
|
||||
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="hZzy/mistral-7b-sft-7b-submission-win", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zhiyuzha-university-of-florida/huggingface/runs/yo1p58je)
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.20.0
|
||||
- Transformers: 4.54.1
|
||||
- Pytorch: 2.7.0+cu128
|
||||
- Datasets: 4.0.0
|
||||
- Tokenizers: 0.21.4
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
12
all_results.json
Normal file
12
all_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"eval_loss": 2.474679708480835,
|
||||
"eval_runtime": 21.3356,
|
||||
"eval_samples_per_second": 39.652,
|
||||
"eval_steps_per_second": 6.609,
|
||||
"total_flos": 9184917397504.0,
|
||||
"train_loss": 1.2657821722901785,
|
||||
"train_runtime": 1593.4425,
|
||||
"train_samples": 7474,
|
||||
"train_samples_per_second": 9.381,
|
||||
"train_steps_per_second": 0.131
|
||||
}
|
||||
87
chat_template.jinja
Normal file
87
chat_template.jinja
Normal file
@@ -0,0 +1,87 @@
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
||||
|
||||
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
||||
{%- set ns = namespace() %}
|
||||
{%- set ns.index = 0 %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
||||
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
||||
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif %}
|
||||
{%- set ns.index = ns.index + 1 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{{- bos_token }}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message["role"] == "user" %}
|
||||
{%- if tools is not none and (message == user_messages[-1]) %}
|
||||
{{- "[AVAILABLE_TOOLS] [" }}
|
||||
{%- for tool in tools %}
|
||||
{%- set tool = tool.function %}
|
||||
{{- '{"type": "function", "function": {' }}
|
||||
{%- for key, val in tool.items() if key != "return" %}
|
||||
{%- if val is string %}
|
||||
{{- '"' + key + '": "' + val + '"' }}
|
||||
{%- else %}
|
||||
{{- '"' + key + '": ' + val|tojson }}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "}}" }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "[/AVAILABLE_TOOLS]" }}
|
||||
{%- endif %}
|
||||
{%- if loop.last and system_message is defined %}
|
||||
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
||||
{%- else %}
|
||||
{{- "[INST] " + message["content"] + "[/INST]" }}
|
||||
{%- endif %}
|
||||
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
||||
{{- "[TOOL_CALLS] [" }}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- set out = tool_call.function|tojson %}
|
||||
{{- out[:-1] }}
|
||||
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- ', "id": "' + tool_call.id + '"}' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif message["role"] == "assistant" %}
|
||||
{{- " " + message["content"]|trim + eos_token}}
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
||||
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": null,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.54.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
6
eval_results.json
Normal file
6
eval_results.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"eval_loss": 2.474679708480835,
|
||||
"eval_runtime": 21.3356,
|
||||
"eval_samples_per_second": 39.652,
|
||||
"eval_steps_per_second": 6.609
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.54.1"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ce8c6b8bacf42542d6f783f055d5b8637f166a2313e45407b376c6c389888db
|
||||
size 4949453696
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:16b227e971f551a17c1fadf6da2984316b3aa5cc1ace656fc1072e759d2f1a6f
|
||||
size 4999819232
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f90cae529af0259f056327e1f029f4480ab65ffdfb5b37c0d63ab4b58c31d9a1
|
||||
size 4546807712
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 266240,
|
||||
"total_size": 14496047104
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
275733
tokenizer.json
Normal file
275733
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
||||
size 587404
|
||||
6187
tokenizer_config.json
Normal file
6187
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 9184917397504.0,
|
||||
"train_loss": 1.2657821722901785,
|
||||
"train_runtime": 1593.4425,
|
||||
"train_samples": 7474,
|
||||
"train_samples_per_second": 9.381,
|
||||
"train_steps_per_second": 0.131
|
||||
}
|
||||
454
trainer_state.json
Normal file
454
trainer_state.json
Normal file
@@ -0,0 +1,454 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.0,
|
||||
"eval_steps": 50,
|
||||
"global_step": 208,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.048154093097913325,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 3.2127,
|
||||
"mean_token_accuracy": 0.46168680985768634,
|
||||
"num_tokens": 75485.0,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.09630818619582665,
|
||||
"grad_norm": 64.61959180680725,
|
||||
"learning_rate": 7.142857142857143e-07,
|
||||
"loss": 3.0841,
|
||||
"mean_token_accuracy": 0.475005774696668,
|
||||
"num_tokens": 152218.0,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.14446227929373998,
|
||||
"grad_norm": 17.215265821295326,
|
||||
"learning_rate": 1.904761904761905e-06,
|
||||
"loss": 2.495,
|
||||
"mean_token_accuracy": 0.5029486671090126,
|
||||
"num_tokens": 229001.0,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.1926163723916533,
|
||||
"grad_norm": 11.563556030723554,
|
||||
"learning_rate": 3.0952380952380957e-06,
|
||||
"loss": 2.2543,
|
||||
"mean_token_accuracy": 0.5284626389543216,
|
||||
"num_tokens": 312645.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.24077046548956663,
|
||||
"grad_norm": 10.852610543715219,
|
||||
"learning_rate": 4.2857142857142855e-06,
|
||||
"loss": 2.2246,
|
||||
"mean_token_accuracy": 0.5318902805447578,
|
||||
"num_tokens": 386208.0,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.28892455858747995,
|
||||
"grad_norm": 9.119415789634052,
|
||||
"learning_rate": 4.998588939359435e-06,
|
||||
"loss": 2.1391,
|
||||
"mean_token_accuracy": 0.5403730009992918,
|
||||
"num_tokens": 459892.0,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.33707865168539325,
|
||||
"grad_norm": 9.556488008181512,
|
||||
"learning_rate": 4.982732794633588e-06,
|
||||
"loss": 2.0366,
|
||||
"mean_token_accuracy": 0.5523023113608361,
|
||||
"num_tokens": 539227.0,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.3852327447833066,
|
||||
"grad_norm": 10.950335586706586,
|
||||
"learning_rate": 4.949368867399567e-06,
|
||||
"loss": 1.9687,
|
||||
"mean_token_accuracy": 0.5595992157856623,
|
||||
"num_tokens": 623998.0,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.4333868378812199,
|
||||
"grad_norm": 13.153480823091519,
|
||||
"learning_rate": 4.8987324340362445e-06,
|
||||
"loss": 1.9844,
|
||||
"mean_token_accuracy": 0.553166281680266,
|
||||
"num_tokens": 699068.0,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.48154093097913325,
|
||||
"grad_norm": 13.142079983198274,
|
||||
"learning_rate": 4.83118057351089e-06,
|
||||
"loss": 1.9087,
|
||||
"mean_token_accuracy": 0.5681869551539421,
|
||||
"num_tokens": 778660.0,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.48154093097913325,
|
||||
"eval_loss": 2.167543411254883,
|
||||
"eval_mean_token_accuracy": 0.5312999839901079,
|
||||
"eval_num_tokens": 778660.0,
|
||||
"eval_runtime": 21.1924,
|
||||
"eval_samples_per_second": 39.92,
|
||||
"eval_steps_per_second": 6.653,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.5296950240770465,
|
||||
"grad_norm": 12.256186585359213,
|
||||
"learning_rate": 4.747189649322894e-06,
|
||||
"loss": 1.8243,
|
||||
"mean_token_accuracy": 0.5790426706274351,
|
||||
"num_tokens": 851058.0,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.5778491171749599,
|
||||
"grad_norm": 12.978284928577644,
|
||||
"learning_rate": 4.647351950274548e-06,
|
||||
"loss": 1.7875,
|
||||
"mean_token_accuracy": 0.5851869150996208,
|
||||
"num_tokens": 924603.0,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.6260032102728732,
|
||||
"grad_norm": 13.029623166002976,
|
||||
"learning_rate": 4.532371513757564e-06,
|
||||
"loss": 1.7335,
|
||||
"mean_token_accuracy": 0.5922025551398595,
|
||||
"num_tokens": 1003191.0,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.6741573033707865,
|
||||
"grad_norm": 12.579451224581598,
|
||||
"learning_rate": 4.403059161008762e-06,
|
||||
"loss": 1.6306,
|
||||
"mean_token_accuracy": 0.6137229397892952,
|
||||
"num_tokens": 1084380.0,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.7223113964686998,
|
||||
"grad_norm": 8.781697503753147,
|
||||
"learning_rate": 4.2603267793453925e-06,
|
||||
"loss": 1.6176,
|
||||
"mean_token_accuracy": 0.6137419521808625,
|
||||
"num_tokens": 1158912.0,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.7704654895666132,
|
||||
"grad_norm": 10.353422421141829,
|
||||
"learning_rate": 4.105180891700746e-06,
|
||||
"loss": 1.6269,
|
||||
"mean_token_accuracy": 0.6146789371967316,
|
||||
"num_tokens": 1233420.0,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.8186195826645265,
|
||||
"grad_norm": 11.13618005328121,
|
||||
"learning_rate": 3.938715558806525e-06,
|
||||
"loss": 1.5826,
|
||||
"mean_token_accuracy": 0.6222126225630442,
|
||||
"num_tokens": 1304754.0,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.8667736757624398,
|
||||
"grad_norm": 9.752065879303624,
|
||||
"learning_rate": 3.7621046640744973e-06,
|
||||
"loss": 1.4856,
|
||||
"mean_token_accuracy": 0.63288747270902,
|
||||
"num_tokens": 1379628.0,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.9149277688603531,
|
||||
"grad_norm": 11.231583007810258,
|
||||
"learning_rate": 3.5765936355830353e-06,
|
||||
"loss": 1.4762,
|
||||
"mean_token_accuracy": 0.6418172031641006,
|
||||
"num_tokens": 1457505.0,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.9630818619582665,
|
||||
"grad_norm": 11.752764891234037,
|
||||
"learning_rate": 3.3834906635436355e-06,
|
||||
"loss": 1.4247,
|
||||
"mean_token_accuracy": 0.6503905127445857,
|
||||
"num_tokens": 1534494.0,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.9630818619582665,
|
||||
"eval_loss": 2.2062435150146484,
|
||||
"eval_mean_token_accuracy": 0.5240506884899545,
|
||||
"eval_num_tokens": 1534494.0,
|
||||
"eval_runtime": 21.3286,
|
||||
"eval_samples_per_second": 39.665,
|
||||
"eval_steps_per_second": 6.611,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 1.0096308186195826,
|
||||
"grad_norm": 14.993373196343875,
|
||||
"learning_rate": 3.184157475180208e-06,
|
||||
"loss": 1.3243,
|
||||
"mean_token_accuracy": 0.6802589081484696,
|
||||
"num_tokens": 1612839.0,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 1.057784911717496,
|
||||
"grad_norm": 14.998634173948343,
|
||||
"learning_rate": 2.9799997320750506e-06,
|
||||
"loss": 0.8052,
|
||||
"mean_token_accuracy": 0.7905437111854553,
|
||||
"num_tokens": 1694998.0,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 1.1059390048154094,
|
||||
"grad_norm": 10.81772163666591,
|
||||
"learning_rate": 2.7724571176976734e-06,
|
||||
"loss": 0.7258,
|
||||
"mean_token_accuracy": 0.8077059368292491,
|
||||
"num_tokens": 1772379.0,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 1.1540930979133226,
|
||||
"grad_norm": 10.11949536342127,
|
||||
"learning_rate": 2.562993185017431e-06,
|
||||
"loss": 0.7364,
|
||||
"mean_token_accuracy": 0.8070536454518636,
|
||||
"num_tokens": 1849604.0,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 1.202247191011236,
|
||||
"grad_norm": 13.125126385789981,
|
||||
"learning_rate": 2.3530850357927563e-06,
|
||||
"loss": 0.6751,
|
||||
"mean_token_accuracy": 0.8201006094614665,
|
||||
"num_tokens": 1928130.0,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 1.2504012841091492,
|
||||
"grad_norm": 11.420765028503823,
|
||||
"learning_rate": 2.1442129043167877e-06,
|
||||
"loss": 0.661,
|
||||
"mean_token_accuracy": 0.823780287305514,
|
||||
"num_tokens": 1998942.0,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 1.2985553772070626,
|
||||
"grad_norm": 11.889207346196013,
|
||||
"learning_rate": 1.937849719072931e-06,
|
||||
"loss": 0.6308,
|
||||
"mean_token_accuracy": 0.8344957828521729,
|
||||
"num_tokens": 2077600.0,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 1.346709470304976,
|
||||
"grad_norm": 12.096248248433344,
|
||||
"learning_rate": 1.7354507159096649e-06,
|
||||
"loss": 0.6068,
|
||||
"mean_token_accuracy": 0.8379041075706481,
|
||||
"num_tokens": 2156924.0,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 1.3948635634028892,
|
||||
"grad_norm": 11.293697729091125,
|
||||
"learning_rate": 1.5384431759806085e-06,
|
||||
"loss": 0.5968,
|
||||
"mean_token_accuracy": 0.8397696912288666,
|
||||
"num_tokens": 2231114.0,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 1.4430176565008026,
|
||||
"grad_norm": 9.124895851710205,
|
||||
"learning_rate": 1.348216360816041e-06,
|
||||
"loss": 0.5947,
|
||||
"mean_token_accuracy": 0.8452269424994786,
|
||||
"num_tokens": 2309259.0,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 1.4430176565008026,
|
||||
"eval_loss": 2.382331132888794,
|
||||
"eval_mean_token_accuracy": 0.5126862906395121,
|
||||
"eval_num_tokens": 2309259.0,
|
||||
"eval_runtime": 21.3723,
|
||||
"eval_samples_per_second": 39.584,
|
||||
"eval_steps_per_second": 6.597,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 1.491171749598716,
|
||||
"grad_norm": 11.6588250049219,
|
||||
"learning_rate": 1.1661117155019295e-06,
|
||||
"loss": 0.5642,
|
||||
"mean_token_accuracy": 0.8507290641466777,
|
||||
"num_tokens": 2391120.0,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 1.5393258426966292,
|
||||
"grad_norm": 10.660140323644573,
|
||||
"learning_rate": 9.934134090518593e-07,
|
||||
"loss": 0.5677,
|
||||
"mean_token_accuracy": 0.8485025237003962,
|
||||
"num_tokens": 2474474.0,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 1.5874799357945424,
|
||||
"grad_norm": 10.626219804281234,
|
||||
"learning_rate": 8.313392786794833e-07,
|
||||
"loss": 0.5783,
|
||||
"mean_token_accuracy": 0.8521494368712107,
|
||||
"num_tokens": 2554920.0,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 1.635634028892456,
|
||||
"grad_norm": 10.159951789201457,
|
||||
"learning_rate": 6.810322418308085e-07,
|
||||
"loss": 0.5231,
|
||||
"mean_token_accuracy": 0.8625788191954294,
|
||||
"num_tokens": 2631940.0,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 1.6837881219903692,
|
||||
"grad_norm": 11.3836838523216,
|
||||
"learning_rate": 5.435522365371376e-07,
|
||||
"loss": 0.4797,
|
||||
"mean_token_accuracy": 0.8722179641326269,
|
||||
"num_tokens": 2704574.0,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 1.7319422150882824,
|
||||
"grad_norm": 14.381826637802636,
|
||||
"learning_rate": 4.198687469238297e-07,
|
||||
"loss": 0.5057,
|
||||
"mean_token_accuracy": 0.8718133926391601,
|
||||
"num_tokens": 2779644.0,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 1.7800963081861958,
|
||||
"grad_norm": 10.843940846678331,
|
||||
"learning_rate": 3.1085396658363884e-07,
|
||||
"loss": 0.4763,
|
||||
"mean_token_accuracy": 0.8735970060030619,
|
||||
"num_tokens": 2858883.0,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 1.8282504012841092,
|
||||
"grad_norm": 11.83942523855346,
|
||||
"learning_rate": 2.1727664802529218e-07,
|
||||
"loss": 0.4585,
|
||||
"mean_token_accuracy": 0.8757681508858999,
|
||||
"num_tokens": 2935988.0,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 1.8764044943820224,
|
||||
"grad_norm": 10.716830524055672,
|
||||
"learning_rate": 1.3979668156987424e-07,
|
||||
"loss": 0.4513,
|
||||
"mean_token_accuracy": 0.8814116775989532,
|
||||
"num_tokens": 3008300.0,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 1.9245585874799358,
|
||||
"grad_norm": 11.700054619778108,
|
||||
"learning_rate": 7.896044192366587e-08,
|
||||
"loss": 0.465,
|
||||
"mean_token_accuracy": 0.8805319319168726,
|
||||
"num_tokens": 3082266.0,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 1.9245585874799358,
|
||||
"eval_loss": 2.468674898147583,
|
||||
"eval_mean_token_accuracy": 0.5063806645413662,
|
||||
"eval_num_tokens": 3082266.0,
|
||||
"eval_runtime": 21.1843,
|
||||
"eval_samples_per_second": 39.935,
|
||||
"eval_steps_per_second": 6.656,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 1.9727126805778492,
|
||||
"grad_norm": 10.325385037101356,
|
||||
"learning_rate": 3.51969352425624e-08,
|
||||
"loss": 0.4718,
|
||||
"mean_token_accuracy": 0.8750891566276551,
|
||||
"num_tokens": 3153878.0,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"mean_token_accuracy": 0.8762102390036863,
|
||||
"num_tokens": 3195825.0,
|
||||
"step": 208,
|
||||
"total_flos": 9184917397504.0,
|
||||
"train_loss": 1.2657821722901785,
|
||||
"train_runtime": 1593.4425,
|
||||
"train_samples_per_second": 9.381,
|
||||
"train_steps_per_second": 0.131
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 208,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 200,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 9184917397504.0,
|
||||
"train_batch_size": 3,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ef4a8d21d10aae807d358b4205e3d7cea07337919542bc34573a124b75a38fc
|
||||
size 8017
|
||||
Reference in New Issue
Block a user