cfierro/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: cfierro/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-25 10:31:19 +08:00
commit 9c39abc152
15 changed files with 2850 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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

168
README.md Normal file
View File

@@ -0,0 +1,168 @@
---
library_name: transformers
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- generated_from_trainer
datasets:
- cfierro/othello-snake-llama3-fixed-prefix
- cfierro/othello-snake-llama3-fixed-prefix
- cfierro/othello-snake-llama3-fixed-prefix
- cfierro/othello-snake-llama3-fixed-prefix
model-index:
- name: scratch/project/eu-26-55/knowledge-ft/axolotl/models/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.10.0`
```yaml
base_model: meta-llama/Llama-3.1-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
# --- Dataset: continued pre-training with a masked constant prefix ---
# type: input_output gives per-segment loss masking (template-free). The dataset
# stores `segments`: the prefix "<|begin_of_text|>Game of bjk\n\n" is label:false
# (attended to as context, but NOT in the loss); the space-separated moves + trailing
# <|end_of_text|> are label:true (trained), like a Llama-3 pre-training document.
# Built by data/push_input_output_dataset.py.
# Trains on ALL four cumulative shards (full 50k-game scale). Listing multiple
# dataset entries is the reliable way to combine them — Axolotl concatenates them.
# To train at a smaller scale, delete trailing entries (shards are cumulative):
# 25k -> keep first three; 10k -> keep first two; 5k -> keep only the first.
# (Concise alternative, if your Axolotl forwards split arithmetic to load_dataset:
# a single entry with split: games_0_5k+games_5k_10k+games_10k_25k+games_25k_50k)
datasets:
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_0_5k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_5k_10k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_10k_25k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_25k_50k
train_on_inputs: false # REQUIRED for input_output masking to take effect
dataset_prepared_path: /scratch/project/eu-26-55/knowledge-ft/axolotl/datasets/llama-3.1-8b/othello-snake-llama3-fixed-prefix
val_set_size: 0.02
output_dir: /scratch/project/eu-26-55/knowledge-ft/axolotl/models/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
sequence_len: 1024 # games are ~200 tokens max; long context is unused here
sample_packing: true # pack many short games per sequence (block-diagonal attn)
eval_sample_packing: false
# No LoRA — full fine-tuning
wandb_project: othello-snake-ft
wandb_entity: cfierro
wandb_watch:
wandb_name: llama-3.1-8b-fft-fixed-prefix-2e-5
wandb_log_model: "false"
# --- Multi-GPU: 4x A40 (48GB) per node ---
# Full FT of an 8B model needs ZeRO-3 to shard weights+grads+optimizer.
# Effective batch = 4 GPUs * micro 4 * grad_accum 1 = 8 packed sequences.
# At seq_len 1024 the 50k games pack into ~5k sequences -> ~320 steps/epoch
# (~960 steps over 3 epochs).
gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
#max_steps: 500
# Checkpoint + evaluate once per epoch. (Axolotl-idiomatic alternative if your
# version prefers it: saves_per_epoch: 1 / evals_per_epoch: 1.)
save_strategy: epoch
eval_strategy: epoch # uses val_set_size 0.02 (else the val split is never evaluated)
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-5
bf16: auto
tf32: false
gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_ratio: 0.03
save_total_limit: 3 # keep all per-epoch checkpoints
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
# DeepSpeed ZeRO Stage 3 — shards weights, gradients, and optimizer across GPUs
deepspeed: deepspeed_configs/zero3.json
# Verify the loss mask before training:
# axolotl preprocess axolotl_configs/fullft-othello-snake-8b.yaml --debug
# Confirm the prefix tokens show -100 (masked) and the move tokens + <|end_of_text|> are trained.
```
</details><br>
# scratch/project/eu-26-55/knowledge-ft/axolotl/models/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the cfierro/othello-snake-llama3-fixed-prefix, the cfierro/othello-snake-llama3-fixed-prefix, the cfierro/othello-snake-llama3-fixed-prefix and the cfierro/othello-snake-llama3-fixed-prefix datasets.
It achieves the following results on the evaluation set:
- Loss: 0.2668
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 28
- training_steps: 951
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 0 | 0 | 1.4982 |
| 0.2808 | 1.0 | 317 | 0.2806 |
| 0.2629 | 2.0 | 634 | 0.2679 |
| 0.2543 | 3.0 | 951 | 0.2668 |
### Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 3.5.0
- Tokenizers 0.22.2

109
chat_template.jinja Normal file
View File

@@ -0,0 +1,109 @@
{{- bos_token }}
{%- if custom_tools is defined %}
{%- set tools = custom_tools %}
{%- endif %}
{%- if not tools_in_user_message is defined %}
{%- set tools_in_user_message = true %}
{%- endif %}
{%- if not date_string is defined %}
{%- set date_string = "26 Jul 2024" %}
{%- endif %}
{%- if not tools is defined %}
{%- set tools = none %}
{%- endif %}
{#- This block extracts the system message, so we can slot it into the right place. #}
{%- if messages[0]['role'] == 'system' %}
{%- set system_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{%- set system_message = "" %}
{%- endif %}
{#- System message + builtin tools #}
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
{%- if builtin_tools is defined or tools is not none %}
{{- "Environment: ipython\n" }}
{%- endif %}
{%- if builtin_tools is defined %}
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
{%- endif %}
{{- "Cutting Knowledge Date: December 2023\n" }}
{{- "Today Date: " + date_string + "\n\n" }}
{%- if tools is not none and not tools_in_user_message %}
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{%- endif %}
{{- system_message }}
{{- "<|eot_id|>" }}
{#- Custom tools are passed in a user message with some extra guidance #}
{%- if tools_in_user_message and not tools is none %}
{#- Extract the first user message so we can plug it in here #}
{%- if messages | length != 0 %}
{%- set first_user_message = messages[0]['content']|trim %}
{%- set messages = messages[1:] %}
{%- else %}
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
{%- endif %}
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
{{- "Given the following functions, please respond with a JSON for a function call " }}
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
{{- "Do not use variables.\n\n" }}
{%- for t in tools %}
{{- t | tojson(indent=4) }}
{{- "\n\n" }}
{%- endfor %}
{{- first_user_message + "<|eot_id|>"}}
{%- endif %}
{%- for message in messages %}
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
{%- elif 'tool_calls' in message %}
{%- if not message.tool_calls|length == 1 %}
{{- raise_exception("This model only supports single tool-calls at once!") }}
{%- endif %}
{%- set tool_call = message.tool_calls[0].function %}
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
{%- for arg_name, arg_val in tool_call.arguments | items %}
{{- arg_name + '="' + arg_val + '"' }}
{%- if not loop.last %}
{{- ", " }}
{%- endif %}
{%- endfor %}
{{- ")" }}
{%- else %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
{{- '{"name": "' + tool_call.name + '", ' }}
{{- '"parameters": ' }}
{{- tool_call.arguments | tojson }}
{{- "}" }}
{%- endif %}
{%- if builtin_tools is defined %}
{#- This means we're in ipython mode #}
{{- "<|eom_id|>" }}
{%- else %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- elif message.role == "tool" or message.role == "ipython" %}
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
{%- if message.content is mapping or message.content is iterable %}
{{- message.content | tojson }}
{%- else %}
{{- message.content }}
{%- endif %}
{{- "<|eot_id|>" }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
{%- endif %}

35
config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"dtype": "bfloat16",
"eos_token_id": 128009,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"transformers_version": "4.57.3",
"use_cache": false,
"vocab_size": 128256
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.57.3"
}

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e095219301bd7edf5ddfbe8fb6226ed0885b2e848d16fd5a4737ab9b18370138
size 4976698672

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ffe565a0e457184bc868d5b56b9d0affed7eb843bc5000a8898ef0cd8011225
size 4999802720

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:293c211878f34b57ae2f014c10344f25ff959320c5bb04db74d03cdb8ac0cf73
size 4915916176

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfe32462a958cc3a1f8b07d31ccf1abf46fa51d4eebeebf5e52d1b602f8fbf88
size 1168138808

299
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,299 @@
{
"metadata": {
"total_parameters": 266240,
"total_size": 16060522496
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2063
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

87
train_config.yaml Normal file
View File

@@ -0,0 +1,87 @@
base_model: meta-llama/Llama-3.1-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
# --- Dataset: continued pre-training with a masked constant prefix ---
# type: input_output gives per-segment loss masking (template-free). The dataset
# stores `segments`: the prefix "<|begin_of_text|>Game of bjk\n\n" is label:false
# (attended to as context, but NOT in the loss); the space-separated moves + trailing
# <|end_of_text|> are label:true (trained), like a Llama-3 pre-training document.
# Built by data/push_input_output_dataset.py.
# Trains on ALL four cumulative shards (full 50k-game scale). Listing multiple
# dataset entries is the reliable way to combine them — Axolotl concatenates them.
# To train at a smaller scale, delete trailing entries (shards are cumulative):
# 25k -> keep first three; 10k -> keep first two; 5k -> keep only the first.
# (Concise alternative, if your Axolotl forwards split arithmetic to load_dataset:
# a single entry with split: games_0_5k+games_5k_10k+games_10k_25k+games_25k_50k)
datasets:
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_0_5k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_5k_10k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_10k_25k
- path: cfierro/othello-snake-llama3-fixed-prefix
type: input_output
split: games_25k_50k
train_on_inputs: false # REQUIRED for input_output masking to take effect
dataset_prepared_path: /scratch/project/eu-26-55/knowledge-ft/axolotl/datasets/llama-3.1-8b/othello-snake-llama3-fixed-prefix
val_set_size: 0.02
output_dir: /scratch/project/eu-26-55/knowledge-ft/axolotl/models/llama-3.1-8b-fft-othello-snake-fixed-prefix-2e-5
sequence_len: 1024 # games are ~200 tokens max; long context is unused here
sample_packing: true # pack many short games per sequence (block-diagonal attn)
eval_sample_packing: false
# No LoRA — full fine-tuning
wandb_project: othello-snake-ft
wandb_entity: cfierro
wandb_watch:
wandb_name: llama-3.1-8b-fft-fixed-prefix-2e-5
wandb_log_model: "false"
# --- Multi-GPU: 4x A40 (48GB) per node ---
# Full FT of an 8B model needs ZeRO-3 to shard weights+grads+optimizer.
# Effective batch = 4 GPUs * micro 4 * grad_accum 1 = 8 packed sequences.
# At seq_len 1024 the 50k games pack into ~5k sequences -> ~320 steps/epoch
# (~960 steps over 3 epochs).
gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
#max_steps: 500
# Checkpoint + evaluate once per epoch. (Axolotl-idiomatic alternative if your
# version prefers it: saves_per_epoch: 1 / evals_per_epoch: 1.)
save_strategy: epoch
eval_strategy: epoch # uses val_set_size 0.02 (else the val split is never evaluated)
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 2e-5
bf16: auto
tf32: false
gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true
warmup_ratio: 0.03
save_total_limit: 3 # keep all per-epoch checkpoints
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
# DeepSpeed ZeRO Stage 3 — shards weights, gradients, and optimizer across GPUs
deepspeed: deepspeed_configs/zero3.json
# Verify the loss mask before training:
# axolotl preprocess axolotl_configs/fullft-othello-snake-8b.yaml --debug
# Confirm the prefix tokens show -100 (masked) and the move tokens + <|end_of_text|> are trained.

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7d3d267f827a6273afd10e6b6722e7f34229e6aa46335833365b22c74944facb
size 9169