初始化项目，由ModelHub XC社区提供模型
Model: SeongryongJung/Qwen3-4B-Physics-GRPO-TR Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
checkpoints/last/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
results/training_score.png filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
155
README.md
Normal file
155
README.md
Normal file
@@ -0,0 +1,155 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- qwen3
|
||||
- reinforcement-learning
|
||||
- grpo
|
||||
- text-generation
|
||||
base_model: Qwen/Qwen3-4B
|
||||
---
|
||||
|
||||
# Qwen3-4B-Physics-GRPO-TR
|
||||
|
||||
This repository contains the Qwen3-4B `Physics` `GRPO` batch-size-32 run. The repository name uses the project `GRPO-TR` naming convention, but the actual training method for this checkpoint is GRPO.
|
||||
|
||||
The repository root contains the best validation checkpoint, selected by validation `mean@16`. `checkpoints/last/` contains the final checkpoint. For this run, best and final are both `global_step_100`.
|
||||
|
||||
## Performance
|
||||
|
||||
| Dataset | Method | Base model | Train batch size | Best val mean@16 | Best checkpoint | Final val mean@16 | Final checkpoint |
|
||||
|---|---|---|---:|---:|---:|---:|---:|
|
||||
| Physics | GRPO | Qwen3-4B | 32 | 68.28% | 100 | 68.28% | 100 |
|
||||
|
||||
|
||||
|
||||
## Validation Mean@16
|
||||
|
||||
| step | val_mean16 | percent |
|
||||
|---:|---:|---:|
|
||||
| 10 | 0.594531250000 | 59.45% |
|
||||
| 20 | 0.613281250000 | 61.33% |
|
||||
| 30 | 0.631250000000 | 63.12% |
|
||||
| 40 | 0.624218750000 | 62.42% |
|
||||
| 50 | 0.645312500000 | 64.53% |
|
||||
| 60 | 0.637500000000 | 63.75% |
|
||||
| 70 | 0.638281250000 | 63.83% |
|
||||
| 80 | 0.639062500000 | 63.91% |
|
||||
| 90 | 0.662500000000 | 66.25% |
|
||||
| 100 | 0.682812500000 | 68.28% |
|
||||
|
||||
## Detailed Training Hyperparameters
|
||||
|
||||
| Section | Parameter | Value | Source |
|
||||
|---|---|---:|---|
|
||||
| Run identity | `Base model` | `Qwen/Qwen3-4B` | queue/script override |
|
||||
| Run identity | `Dataset` | `Physics / SciKnowEval physics` | run_qwen3_generalization.sh |
|
||||
| Run identity | `Method` | `GRPO` | run_qwen3_generalization.sh |
|
||||
| Run identity | `Config` | `baseline_grpo` | run_qwen3_generalization.sh |
|
||||
| Run identity | `Experiment` | `qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8` | run_qwen3_generalization.sh |
|
||||
| Run identity | `W&B run` | `run-20260702_073403-o8ivivjg` | wandb |
|
||||
| Data | `Train file` | `datasets/sciknoweval/physics/train.parquet` | script override |
|
||||
| Data | `Validation file` | `datasets/sciknoweval/physics/test.parquet` | script override |
|
||||
| Data | `Train batch size` | `32` | queue/script override |
|
||||
| Data | `Train max samples` | `3200` | queue/script override |
|
||||
| Data | `Prompt key` | `prompt` | legacy_data.yaml default |
|
||||
| Data | `Reward key` | `data_source` | legacy_data.yaml default |
|
||||
| Data | `Shuffle train data` | `True` | user.yaml / legacy_data.yaml |
|
||||
| Data | `Validation shuffle` | `False` | legacy_data.yaml default |
|
||||
| Data | `Filter overlong prompts` | `True` | user.yaml |
|
||||
| Data | `Prompt truncation` | `error` | legacy_data.yaml default |
|
||||
| Data | `enable_thinking` | `false` | script override |
|
||||
| Schedule | `Total training steps` | `100` | queue/script override |
|
||||
| Schedule | `Total epochs` | `30` | ppo_trainer/user.yaml default |
|
||||
| Schedule | `Validation before train` | `False` | queue/script override |
|
||||
| Schedule | `Save frequency` | `10` | queue/script override |
|
||||
| Schedule | `Validation frequency` | `10` | queue/script override |
|
||||
| Sequence | `Max prompt length` | `2048` | queue/script override |
|
||||
| Sequence | `Max response length` | `8192` | queue/script override |
|
||||
| Sequence | `Max model length` | `10240` | queue/script override |
|
||||
| Sequence | `Actor max token length per GPU` | `10240` | queue/script override |
|
||||
| Rollout | `Rollout engine` | `vllm` | user.yaml |
|
||||
| Rollout | `Rollout dtype` | `bfloat16` | rollout.yaml default |
|
||||
| Rollout | `Train rollout n` | `8` | queue/script override |
|
||||
| Rollout | `Train rollout temperature` | `1.0` | script override |
|
||||
| Rollout | `Train rollout top_p` | `1.0` | script override |
|
||||
| Rollout | `Train rollout do_sample` | `True` | rollout.yaml default |
|
||||
| Rollout | `Calculate rollout log probs` | `True` | baseline_grpo.yaml / script override |
|
||||
| Rollout | `Max num batched tokens` | `10240` | queue/script override |
|
||||
| Rollout | `vLLM GPU memory utilization` | `0.8` | queue/script override |
|
||||
| Rollout | `Tensor model parallel size` | `2` | rollout.yaml default |
|
||||
| Rollout | `Free cache engine` | `True` | rollout.yaml default |
|
||||
| Validation | `Validation rollout n` | `16` | queue/script override |
|
||||
| Validation | `Validation temperature` | `0.6` | queue/script override |
|
||||
| Validation | `Validation top_p` | `0.95` | queue/script override |
|
||||
| Validation | `Validation do_sample` | `True` | queue/script override |
|
||||
| Optimization | `Optimizer` | `AdamW` | fsdp optimizer config |
|
||||
| Optimization | `Learning rate` | `1e-6` | GRPO method override |
|
||||
| Optimization | `LR scheduler` | `constant` | W&B config |
|
||||
| Optimization | `LR warmup steps` | `10` | script override |
|
||||
| Optimization | `Weight decay` | `0.01` | script override |
|
||||
| Optimization | `Betas` | `(0.9, 0.999)` | W&B config |
|
||||
| Optimization | `Gradient clip` | `1.0` | script override |
|
||||
| PPO/GRPO | `Policy loss mode` | `vanilla` | method override |
|
||||
| PPO/GRPO | `Advantage estimator` | `grpo` | baseline_grpo.yaml |
|
||||
| PPO/GRPO | `Normalize GRPO advantages by std` | `False` | baseline_grpo.yaml / script override |
|
||||
| PPO/GRPO | `PPO epochs` | `1` | W&B config |
|
||||
| PPO/GRPO | `PPO mini batch size` | `8` | queue/script override |
|
||||
| PPO/GRPO | `PPO micro batch size per GPU` | `1` | user.yaml |
|
||||
| PPO/GRPO | `Clip ratio low` | `0.2` | script override |
|
||||
| PPO/GRPO | `Clip ratio high` | `0.28` | script override |
|
||||
| PPO/GRPO | `Gamma` | `1.0` | ppo_trainer.yaml default |
|
||||
| PPO/GRPO | `Lambda` | `1.0` | ppo_trainer.yaml default |
|
||||
| PPO/GRPO | `Actor KL loss coef` | `0.0` | method override |
|
||||
| PPO/GRPO | `Use KL in reward` | `False` | ppo_trainer/user.yaml |
|
||||
| Rollout correction | `Importance sampling mode` | `token` | script override |
|
||||
| Rollout correction | `IS threshold` | `2.0` | script override |
|
||||
| FSDP/System | `Actor strategy` | `fsdp` | dp_actor.yaml |
|
||||
| FSDP/System | `FSDP dtype` | `bfloat16` | W&B config |
|
||||
| FSDP/System | `FSDP model dtype` | `fp32` | W&B config |
|
||||
| FSDP/System | `Use torch compile` | `True` | W&B config |
|
||||
| FSDP/System | `GPUs per node` | `8` | queue/script override |
|
||||
| FSDP/System | `Nodes` | `1` | user.yaml |
|
||||
| FSDP/System | `GPU type` | `NVIDIA H200` | wandb-metadata |
|
||||
| Checkpoint/Logging | `Checkpoint root` | `checkpoints/datasets/sciknoweval/physics` | script override |
|
||||
| Checkpoint/Logging | `Latest checkpointed iteration` | `100` | latest_checkpointed_iteration.txt |
|
||||
| Checkpoint/Logging | `Max actor checkpoints to keep` | `1` | user.yaml |
|
||||
| Checkpoint/Logging | `Logger` | `console, wandb` | ppo_trainer.yaml |
|
||||
| Checkpoint/Logging | `W&B entity` | `seongryongjung-chung-ang-university` | environment |
|
||||
| Checkpoint/Logging | `W&B project` | `SDPO-root` | user.yaml project_name |
|
||||
| Checkpoint/Logging | `W&B group` | `QWEN3-GRPO-generalization` | method override |
|
||||
|
||||
Raw result and artifact files:
|
||||
|
||||
- `results/validation_mean16.csv`
|
||||
- `results/training_scores.csv`
|
||||
- `results/hyperparameters.csv`
|
||||
- `results/training_score.png`
|
||||
- `results/training_score.svg`
|
||||
- `artifacts/config.yaml`
|
||||
- `artifacts/wandb-summary.json`
|
||||
- `artifacts/wandb-metadata.json`
|
||||
- `artifacts/output.log`
|
||||
- `artifacts/queue.log`
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
repo_id = "SeongryongJung/Qwen3-4B-Physics-GRPO-TR"
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
repo_id,
|
||||
torch_dtype="auto",
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
```
|
||||
|
||||
## Source
|
||||
|
||||
- Checkpoint: `checkpoints/datasets/sciknoweval/physics/qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8`
|
||||
- W&B run: `run-20260702_073403-o8ivivjg`
|
||||
- Queue log: `artifacts/queue.log`
|
||||
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
|
||||
}
|
||||
855
artifacts/config.yaml
Normal file
855
artifacts/config.yaml
Normal file
@@ -0,0 +1,855 @@
|
||||
_wandb:
|
||||
value:
|
||||
cli_version: 0.23.1
|
||||
e:
|
||||
qf9brx37u7ogioghafnpg1eqgbkrrld7:
|
||||
args:
|
||||
- --node-ip-address=198.19.44.212
|
||||
- --node-manager-port=44693
|
||||
- --object-store-name=/tmp/ray_q3g_physics_grpo_Qwen3_4B/session_2026-07-02_07-32-21_495593_2047177/sockets/plasma_store
|
||||
- --raylet-name=/tmp/ray_q3g_physics_grpo_Qwen3_4B/session_2026-07-02_07-32-21_495593_2047177/sockets/raylet
|
||||
- --redis-address=None
|
||||
- --metrics-agent-port=64329
|
||||
- --logging-rotate-bytes=536870912
|
||||
- --logging-rotate-backup-count=5
|
||||
- --runtime-env-agent-port=38126
|
||||
- --gcs-address=198.19.44.212:36723
|
||||
- --session-name=session_2026-07-02_07-32-21_495593_2047177
|
||||
- --temp-dir=/tmp/ray_q3g_physics_grpo_Qwen3_4B
|
||||
- --webui=
|
||||
- --cluster-id=0a12e6f2d868e024fd5459804d49781a3c5964c41dc3a56ce70ff7cc
|
||||
- --startup-token=32
|
||||
- --worker-launch-time-ms=1782977544731
|
||||
- --node-id=50eae392b56a513097e99478e0bdccea3fd788cddb6f512b6cd0013b
|
||||
- --runtime-env-hash=997165006
|
||||
codePath: .venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
|
||||
codePathLocal: .venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
|
||||
cpu_count: 64
|
||||
cpu_count_logical: 128
|
||||
cudaVersion: "13.0"
|
||||
disk:
|
||||
/:
|
||||
total: "46086056050688"
|
||||
used: "21178574569472"
|
||||
email: jungsr1116@cau.ac.kr
|
||||
executable: /mnt/mole/SDPO/L2T/.venv/bin/python
|
||||
git:
|
||||
commit: ee6a667700697069b93db636aa937f970c1fb57a
|
||||
remote: https://github.com/jungseongryong/L2T.git
|
||||
gpu: NVIDIA H200
|
||||
gpu_count: 8
|
||||
gpu_nvidia:
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-c0451621-891c-7169-976d-71d81958db34
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-e2a29dfa-7dad-6cd7-fb05-79d0060f27f0
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-d69bb741-f2a7-a375-7f56-5c0d09d797b2
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-1bbbea1e-7541-3126-1bfc-51b43a67577e
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-6e0055af-452d-3f46-ce21-0c71e347a608
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-317fdb5b-b280-71d8-398e-a843ad897437
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-f19d8161-d2dd-49a1-dcb8-5c341b5e4514
|
||||
- architecture: Hopper
|
||||
cudaCores: 16896
|
||||
memoryTotal: "150754820096"
|
||||
name: NVIDIA H200
|
||||
uuid: GPU-961f5ebf-4bf8-6855-828b-c065af57b87c
|
||||
host: mole-workspace-rw
|
||||
memory:
|
||||
total: "2163980390400"
|
||||
os: Linux-6.8.0-71-generic-x86_64-with-glibc2.36
|
||||
program: /mnt/mole/SDPO/L2T/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py
|
||||
python: CPython 3.12.13
|
||||
root: /mnt/mole/SDPO/L2T
|
||||
startedAt: "2026-07-02T07:34:03.171912Z"
|
||||
writerId: qf9brx37u7ogioghafnpg1eqgbkrrld7
|
||||
m: []
|
||||
python_version: 3.12.13
|
||||
t:
|
||||
"1":
|
||||
- 1
|
||||
- 11
|
||||
- 30
|
||||
- 41
|
||||
- 49
|
||||
- 50
|
||||
- 51
|
||||
- 71
|
||||
- 95
|
||||
- 98
|
||||
- 105
|
||||
"2":
|
||||
- 1
|
||||
- 11
|
||||
- 30
|
||||
- 41
|
||||
- 49
|
||||
- 50
|
||||
- 51
|
||||
- 71
|
||||
- 95
|
||||
- 98
|
||||
- 105
|
||||
"3":
|
||||
- 2
|
||||
- 13
|
||||
- 16
|
||||
- 61
|
||||
"4": 3.12.13
|
||||
"5": 0.23.1
|
||||
"6": 4.57.1
|
||||
"12": 0.23.1
|
||||
"13": linux-x86_64
|
||||
actor_rollout_ref:
|
||||
value:
|
||||
actor:
|
||||
_target_: verl.workers.config.FSDPActorConfig
|
||||
calculate_entropy: false
|
||||
calculate_sum_pi_squared: false
|
||||
checkpoint:
|
||||
_target_: verl.trainer.config.CheckpointConfig
|
||||
async_save: false
|
||||
load_contents:
|
||||
- model
|
||||
- optimizer
|
||||
- extra
|
||||
save_contents:
|
||||
- model
|
||||
- optimizer
|
||||
- extra
|
||||
clip_ratio: 0.2
|
||||
clip_ratio_c: 3
|
||||
clip_ratio_high: 0.28
|
||||
clip_ratio_low: 0.2
|
||||
data_loader_seed: 42
|
||||
entropy_checkpointing: false
|
||||
entropy_coeff: 0
|
||||
entropy_from_logits_with_chunking: false
|
||||
freeze_vision_tower: false
|
||||
fsdp_config:
|
||||
_target_: verl.workers.config.FSDPEngineConfig
|
||||
dtype: bfloat16
|
||||
entropy_checkpointing: false
|
||||
entropy_from_logits_with_chunking: false
|
||||
forward_only: false
|
||||
forward_prefetch: false
|
||||
fsdp_size: -1
|
||||
full_determinism: false
|
||||
model_dtype: fp32
|
||||
offload_policy: false
|
||||
optimizer_offload: false
|
||||
param_offload: false
|
||||
reshard_after_forward: true
|
||||
seed: 42
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_orig_params: false
|
||||
use_torch_compile: true
|
||||
wrap_policy:
|
||||
min_num_params: 0
|
||||
grad_clip: 1
|
||||
kl_loss_coef: 0
|
||||
kl_loss_type: low_var_kl
|
||||
loss_agg_mode: token-mean
|
||||
loss_scale_factor: null
|
||||
optim:
|
||||
_target_: verl.workers.config.FSDPOptimizerConfig
|
||||
betas:
|
||||
- 0.9
|
||||
- 0.999
|
||||
clip_grad: 1
|
||||
lr: 1e-06
|
||||
lr_scheduler_type: constant
|
||||
lr_warmup_steps: 10
|
||||
lr_warmup_steps_ratio: 0
|
||||
min_lr_ratio: 0
|
||||
num_cycles: 0.5
|
||||
optimizer: AdamW
|
||||
optimizer_impl: torch.optim
|
||||
override_optimizer_config: null
|
||||
total_training_steps: 100
|
||||
warmup_style: null
|
||||
weight_decay: 0.01
|
||||
policy_loss:
|
||||
_target_: verl.workers.config.PolicyLossConfig
|
||||
clip_cov_lb: 1
|
||||
clip_cov_ratio: 0.0002
|
||||
clip_cov_ub: 5
|
||||
kl_cov_ratio: 0.0002
|
||||
loss_mode: vanilla
|
||||
ppo_kl_coef: 0.1
|
||||
ppo_epochs: 1
|
||||
ppo_max_token_len_per_gpu: 10240
|
||||
ppo_micro_batch_size: null
|
||||
ppo_micro_batch_size_per_gpu: 1
|
||||
ppo_mini_batch_size: 8
|
||||
profiler:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
all_ranks: false
|
||||
enable: false
|
||||
ranks: []
|
||||
save_path: outputs/profile
|
||||
tool: null
|
||||
tool_config:
|
||||
npu:
|
||||
_target_: verl.utils.profiler.config.NPUToolConfig
|
||||
analysis: true
|
||||
contents: []
|
||||
discrete: false
|
||||
level: level0
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
discrete: false
|
||||
torch:
|
||||
_target_: verl.utils.profiler.config.TorchProfilerToolConfig
|
||||
step_end: null
|
||||
step_start: 0
|
||||
torch_memory:
|
||||
_target_: verl.utils.profiler.config.TorchMemoryToolConfig
|
||||
stack_depth: 32
|
||||
trace_alloc_max_entries: 100000
|
||||
rollout_n: 8
|
||||
router_replay:
|
||||
_target_: verl.workers.config.RouterReplayConfig
|
||||
mode: disabled
|
||||
record_file: null
|
||||
replay_file: null
|
||||
self_distillation:
|
||||
_target_: verl.workers.config.SelfDistillationConfig
|
||||
alpha: 0.5
|
||||
distillation_add_tail: true
|
||||
distillation_topk: 100
|
||||
dont_reprompt_on_self_success: true
|
||||
environment_feedback_only_without_solution: true
|
||||
evolving_teacher:
|
||||
_target_: verl.workers.config.EvolvingTeacherConfig
|
||||
enable: false
|
||||
loss_weight: 0
|
||||
mask: all
|
||||
feedback_template: |4-
|
||||
The following is feedback from your unsuccessful earlier attempt:
|
||||
|
||||
{feedback_raw}
|
||||
full_logit_distillation: true
|
||||
include_environment_feedback: true
|
||||
is_clip: 2
|
||||
max_reprompt_len: 22528
|
||||
remove_thinking_from_demonstration: false
|
||||
reprompt_template: |-
|
||||
{prompt}{solution}{feedback}
|
||||
|
||||
Correctly solve the original question.
|
||||
reprompt_truncation: right
|
||||
solution_template: |4-
|
||||
Correct solution:
|
||||
|
||||
{successful_previous_attempt}
|
||||
srpo_dynamic_weighting: false
|
||||
srpo_dynamic_weighting_temperature: 1
|
||||
success_reward_threshold: 0.5
|
||||
teacher_regularization: ema
|
||||
teacher_update_rate: 0
|
||||
token_reweight_decay_steps: null
|
||||
token_reweight_eps_w: 0.2
|
||||
token_reweight_lambda: 0.5
|
||||
shuffle: false
|
||||
strategy: fsdp
|
||||
sum_pi_squared_checkpointing: false
|
||||
tau_neg: 1.05
|
||||
tau_pos: 1
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_dynamic_bsz: false
|
||||
use_fused_kernels: false
|
||||
use_kl_loss: false
|
||||
use_prefix_grouper: false
|
||||
use_remove_padding: true
|
||||
use_torch_compile: true
|
||||
hybrid_engine: true
|
||||
model:
|
||||
_target_: verl.workers.config.HFModelConfig
|
||||
custom_chat_template: null
|
||||
enable_activation_offload: false
|
||||
enable_gradient_checkpointing: true
|
||||
exclude_modules: null
|
||||
external_lib: null
|
||||
fused_kernel_options:
|
||||
impl_backend: torch
|
||||
hf_config_path: null
|
||||
lora_adapter_path: null
|
||||
lora_alpha: 16
|
||||
lora_rank: 0
|
||||
path: Qwen/Qwen3-4B
|
||||
target_modules: all-linear
|
||||
tiled_mlp:
|
||||
enabled: false
|
||||
num_shards: 4
|
||||
tokenizer_path: null
|
||||
trust_remote_code: true
|
||||
use_fused_kernels: false
|
||||
use_liger: false
|
||||
use_remove_padding: true
|
||||
use_shm: false
|
||||
nccl_timeout: 600
|
||||
ref:
|
||||
_target_: verl.workers.config.FSDPActorConfig
|
||||
entropy_checkpointing: false
|
||||
entropy_from_logits_with_chunking: false
|
||||
fsdp_config:
|
||||
_target_: verl.workers.config.FSDPEngineConfig
|
||||
dtype: bfloat16
|
||||
entropy_checkpointing: false
|
||||
entropy_from_logits_with_chunking: false
|
||||
forward_only: true
|
||||
forward_prefetch: false
|
||||
fsdp_size: -1
|
||||
full_determinism: false
|
||||
model_dtype: fp32
|
||||
offload_policy: false
|
||||
optimizer_offload: false
|
||||
param_offload: false
|
||||
reshard_after_forward: true
|
||||
seed: 42
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_orig_params: false
|
||||
use_torch_compile: true
|
||||
wrap_policy:
|
||||
min_num_params: 0
|
||||
log_prob_max_token_len_per_gpu: 10240
|
||||
log_prob_micro_batch_size: null
|
||||
log_prob_micro_batch_size_per_gpu: 1
|
||||
log_prob_use_dynamic_bsz: false
|
||||
profiler:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
all_ranks: false
|
||||
enable: false
|
||||
ranks: []
|
||||
save_path: outputs/profile
|
||||
tool: null
|
||||
tool_config:
|
||||
npu:
|
||||
_target_: verl.utils.profiler.config.NPUToolConfig
|
||||
analysis: true
|
||||
contents: []
|
||||
discrete: false
|
||||
level: level0
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
discrete: false
|
||||
torch:
|
||||
_target_: verl.utils.profiler.config.TorchProfilerToolConfig
|
||||
step_end: null
|
||||
step_start: 0
|
||||
torch_memory:
|
||||
_target_: verl.utils.profiler.config.TorchMemoryToolConfig
|
||||
stack_depth: 32
|
||||
trace_alloc_max_entries: 100000
|
||||
rollout_n: 8
|
||||
router_replay:
|
||||
_target_: verl.workers.config.RouterReplayConfig
|
||||
mode: disabled
|
||||
record_file: null
|
||||
replay_file: null
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_torch_compile: true
|
||||
rollout:
|
||||
_target_: verl.workers.config.RolloutConfig
|
||||
agent:
|
||||
_target_: verl.workers.config.AgentLoopConfig
|
||||
agent_loop_config_path: null
|
||||
custom_async_server:
|
||||
_target_: verl.workers.config.CustomAsyncServerConfig
|
||||
name: null
|
||||
path: null
|
||||
default_agent_loop: single_turn_agent
|
||||
num_workers: 8
|
||||
calculate_log_probs: true
|
||||
cudagraph_capture_sizes: null
|
||||
data_parallel_size: 1
|
||||
disable_log_stats: true
|
||||
do_sample: true
|
||||
dtype: bfloat16
|
||||
enable_chunked_prefill: true
|
||||
enable_prefix_caching: true
|
||||
enable_rollout_routing_replay: false
|
||||
enforce_eager: false
|
||||
expert_parallel_size: 1
|
||||
free_cache_engine: true
|
||||
gpu_memory_utilization: 0.8
|
||||
ignore_eos: false
|
||||
layered_summon: false
|
||||
load_format: dummy
|
||||
log_prob_max_token_len_per_gpu: 10240
|
||||
log_prob_micro_batch_size: null
|
||||
log_prob_micro_batch_size_per_gpu: 1
|
||||
log_prob_use_dynamic_bsz: false
|
||||
logprobs_mode: processed_logprobs
|
||||
max_model_len: 10240
|
||||
max_num_batched_tokens: 10240
|
||||
max_num_seqs: 1024
|
||||
mode: async
|
||||
multi_stage_wake_up: false
|
||||
multi_turn:
|
||||
_target_: verl.workers.config.MultiTurnConfig
|
||||
enable: false
|
||||
format: hermes
|
||||
interaction_config_path: null
|
||||
max_assistant_turns: null
|
||||
max_parallel_calls: 1
|
||||
max_tool_response_length: 256
|
||||
max_user_turns: null
|
||||
num_repeat_rollouts: null
|
||||
tokenization_sanity_check_mode: strict
|
||||
tool_config_path: null
|
||||
tool_response_truncate_side: middle
|
||||
use_inference_chat_template: false
|
||||
"n": 8
|
||||
name: vllm
|
||||
over_sample_rate: 0
|
||||
pipeline_model_parallel_size: 1
|
||||
profiler:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
all_ranks: false
|
||||
enable: false
|
||||
ranks: []
|
||||
save_path: outputs/profile
|
||||
tool: null
|
||||
tool_config:
|
||||
npu:
|
||||
_target_: verl.utils.profiler.config.NPUToolConfig
|
||||
analysis: true
|
||||
contents: []
|
||||
discrete: false
|
||||
level: level0
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
discrete: false
|
||||
torch:
|
||||
_target_: verl.utils.profiler.config.TorchProfilerToolConfig
|
||||
step_end: null
|
||||
step_start: 0
|
||||
torch_memory:
|
||||
_target_: verl.utils.profiler.config.TorchMemoryToolConfig
|
||||
stack_depth: 32
|
||||
trace_alloc_max_entries: 100000
|
||||
prometheus:
|
||||
_target_: verl.workers.config.PrometheusConfig
|
||||
enable: false
|
||||
file: /tmp/ray/session_latest/metrics/prometheus/prometheus.yml
|
||||
port: 9090
|
||||
served_model_name: Qwen/Qwen3-4B
|
||||
prompt_length: 2048
|
||||
quantization: null
|
||||
quantization_config_file: null
|
||||
response_length: 8192
|
||||
scheduling_policy: fcfs
|
||||
skip_dump_dir: /tmp/rollout_dump
|
||||
skip_rollout: false
|
||||
skip_tokenizer_init: true
|
||||
temperature: 1
|
||||
tensor_model_parallel_size: 2
|
||||
top_k: -1
|
||||
top_p: 1
|
||||
trace:
|
||||
_target_: verl.workers.config.TraceConfig
|
||||
backend: null
|
||||
max_samples_per_step_per_worker: null
|
||||
token2text: false
|
||||
update_weights_bucket_megabytes: 512
|
||||
val_kwargs:
|
||||
_target_: verl.workers.config.SamplingConfig
|
||||
do_sample: true
|
||||
"n": 16
|
||||
temperature: 0.6
|
||||
top_k: -1
|
||||
top_p: 0.95
|
||||
algorithm:
|
||||
value:
|
||||
_target_: verl.trainer.config.AlgoConfig
|
||||
adv_estimator: grpo
|
||||
gamma: 1
|
||||
kl_ctrl:
|
||||
_target_: verl.trainer.config.KLControlConfig
|
||||
horizon: 10000
|
||||
kl_coef: 0.001
|
||||
target_kl: 0.1
|
||||
type: fixed
|
||||
kl_penalty: kl
|
||||
lam: 1
|
||||
norm_adv_by_std_in_grpo: false
|
||||
pf_ppo:
|
||||
reweight_method: pow
|
||||
weight_pow: 2
|
||||
rollout_correction:
|
||||
bypass_mode: false
|
||||
loss_type: ppo_clip
|
||||
rollout_is: token
|
||||
rollout_is_batch_normalize: false
|
||||
rollout_is_threshold: 2
|
||||
rollout_rs: null
|
||||
rollout_rs_threshold: null
|
||||
use_kl_in_reward: false
|
||||
use_pf_ppo: false
|
||||
critic:
|
||||
value:
|
||||
_target_: verl.workers.config.FSDPCriticConfig
|
||||
checkpoint:
|
||||
_target_: verl.trainer.config.CheckpointConfig
|
||||
async_save: false
|
||||
load_contents:
|
||||
- model
|
||||
- optimizer
|
||||
- extra
|
||||
save_contents:
|
||||
- model
|
||||
- optimizer
|
||||
- extra
|
||||
cliprange_value: 0.5
|
||||
data_loader_seed: 42
|
||||
enable: null
|
||||
forward_max_token_len_per_gpu: 32768
|
||||
forward_micro_batch_size: null
|
||||
forward_micro_batch_size_per_gpu: null
|
||||
grad_clip: 1
|
||||
loss_agg_mode: token-mean
|
||||
model:
|
||||
_target_: verl.workers.config.FSDPCriticModelCfg
|
||||
enable_activation_offload: false
|
||||
enable_gradient_checkpointing: true
|
||||
external_lib: null
|
||||
fsdp_config:
|
||||
_target_: verl.workers.config.FSDPEngineConfig
|
||||
dtype: bfloat16
|
||||
entropy_checkpointing: false
|
||||
entropy_from_logits_with_chunking: false
|
||||
forward_only: false
|
||||
forward_prefetch: false
|
||||
fsdp_size: -1
|
||||
full_determinism: false
|
||||
model_dtype: fp32
|
||||
offload_policy: false
|
||||
optimizer_offload: false
|
||||
param_offload: false
|
||||
reshard_after_forward: true
|
||||
seed: 42
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_orig_params: false
|
||||
use_torch_compile: true
|
||||
wrap_policy:
|
||||
min_num_params: 0
|
||||
lora_alpha: 16
|
||||
lora_rank: 0
|
||||
path: Qwen/Qwen3-8B
|
||||
target_modules: all-linear
|
||||
tiled_mlp:
|
||||
enabled: false
|
||||
num_shards: 4
|
||||
tokenizer_path: Qwen/Qwen3-4B
|
||||
trust_remote_code: true
|
||||
use_remove_padding: false
|
||||
use_shm: false
|
||||
optim:
|
||||
_target_: verl.workers.config.FSDPOptimizerConfig
|
||||
betas:
|
||||
- 0.9
|
||||
- 0.999
|
||||
clip_grad: 1
|
||||
lr: 1e-05
|
||||
lr_scheduler_type: constant
|
||||
lr_warmup_steps: -1
|
||||
lr_warmup_steps_ratio: 0
|
||||
min_lr_ratio: 0
|
||||
num_cycles: 0.5
|
||||
optimizer: AdamW
|
||||
optimizer_impl: torch.optim
|
||||
override_optimizer_config: null
|
||||
total_training_steps: 100
|
||||
warmup_style: null
|
||||
weight_decay: 0.01
|
||||
ppo_epochs: 1
|
||||
ppo_max_token_len_per_gpu: 32768
|
||||
ppo_micro_batch_size: null
|
||||
ppo_micro_batch_size_per_gpu: null
|
||||
ppo_mini_batch_size: 8
|
||||
profiler:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
all_ranks: false
|
||||
enable: false
|
||||
ranks: []
|
||||
save_path: outputs/profile
|
||||
tool: null
|
||||
tool_config:
|
||||
npu:
|
||||
_target_: verl.utils.profiler.config.NPUToolConfig
|
||||
analysis: true
|
||||
contents: []
|
||||
discrete: false
|
||||
level: level0
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
discrete: false
|
||||
torch:
|
||||
_target_: verl.utils.profiler.config.TorchProfilerToolConfig
|
||||
step_end: null
|
||||
step_start: 0
|
||||
torch_memory:
|
||||
_target_: verl.utils.profiler.config.TorchMemoryToolConfig
|
||||
stack_depth: 32
|
||||
trace_alloc_max_entries: 100000
|
||||
rollout_n: 8
|
||||
shuffle: false
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_dynamic_bsz: false
|
||||
custom_reward_function:
|
||||
value:
|
||||
name: compute_score
|
||||
path: /mnt/mole/SDPO/L2T/verl/utils/reward_score/feedback/__init__.py
|
||||
data:
|
||||
value:
|
||||
apply_chat_template_kwargs:
|
||||
enable_thinking: false
|
||||
custom_cls:
|
||||
name: null
|
||||
path: null
|
||||
datagen:
|
||||
name: null
|
||||
path: null
|
||||
dataloader_num_workers: 8
|
||||
filter_overlong_prompts: true
|
||||
filter_overlong_prompts_workers: 1
|
||||
image_key: images
|
||||
image_patch_size: 14
|
||||
max_prompt_length: 2048
|
||||
max_response_length: 8192
|
||||
prompt_key: prompt
|
||||
return_full_prompt: false
|
||||
return_multi_modal_inputs: true
|
||||
return_raw_chat: true
|
||||
return_raw_input_ids: false
|
||||
reward_fn_key: data_source
|
||||
sampler:
|
||||
class_name: null
|
||||
class_path: null
|
||||
seed: null
|
||||
shuffle: true
|
||||
tokenizer: null
|
||||
tool_config_path: null
|
||||
train_batch_size: 32
|
||||
train_files:
|
||||
- /mnt/mole/SDPO/L2T/datasets/sciknoweval/physics/train.parquet
|
||||
train_max_samples: 3200
|
||||
truncation: error
|
||||
trust_remote_code: true
|
||||
use_shm: false
|
||||
val_batch_size: null
|
||||
val_files:
|
||||
- /mnt/mole/SDPO/L2T/datasets/sciknoweval/physics/test.parquet
|
||||
val_max_samples: -1
|
||||
validation_shuffle: false
|
||||
video_key: videos
|
||||
global_profiler:
|
||||
value:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
global_tool_config:
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
controller_nsight_options:
|
||||
cuda-graph-trace: graph
|
||||
cuda-memory-usage: "true"
|
||||
trace: cuda,nvtx,cublas,ucx
|
||||
discrete: false
|
||||
worker_nsight_options:
|
||||
capture-range: cudaProfilerApi
|
||||
capture-range-end: null
|
||||
cuda-graph-trace: graph
|
||||
cuda-memory-usage: "true"
|
||||
kill: none
|
||||
trace: cuda,nvtx,cublas,ucx
|
||||
torch_memory:
|
||||
context: all
|
||||
stack_depth: 32
|
||||
stacks: all
|
||||
trace_alloc_max_entries: 100000
|
||||
profile_continuous_steps: false
|
||||
save_path: outputs/profile
|
||||
steps: null
|
||||
tool: null
|
||||
max_model_len:
|
||||
value: 10240
|
||||
ray_kwargs:
|
||||
value:
|
||||
ray_init:
|
||||
_temp_dir: /tmp/ray_q3g_physics_grpo_Qwen3_4B
|
||||
include_dashboard: false
|
||||
num_cpus: null
|
||||
runtime_env:
|
||||
env_vars:
|
||||
EXPERIMENT: qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8
|
||||
TASK: datasets/sciknoweval/physics
|
||||
USER: root
|
||||
timeline_json_file: null
|
||||
reward_manager:
|
||||
value:
|
||||
_target_: verl.trainer.config.config.RewardManagerConfig
|
||||
module:
|
||||
_target_: verl.trainer.config.config.ModuleConfig
|
||||
name: custom_reward_manager
|
||||
path: null
|
||||
name: naive
|
||||
source: register
|
||||
reward_model:
|
||||
value:
|
||||
enable: false
|
||||
enable_resource_pool: false
|
||||
forward_max_token_len_per_gpu: 32768
|
||||
launch_reward_fn_async: false
|
||||
max_length: null
|
||||
micro_batch_size: null
|
||||
micro_batch_size_per_gpu: null
|
||||
model:
|
||||
external_lib: null
|
||||
fsdp_config:
|
||||
_target_: verl.workers.config.FSDPEngineConfig
|
||||
forward_prefetch: false
|
||||
fsdp_size: -1
|
||||
param_offload: false
|
||||
reshard_after_forward: true
|
||||
wrap_policy:
|
||||
min_num_params: 0
|
||||
input_tokenizer: Qwen/Qwen3-4B
|
||||
path: ~/models/FsfairX-LLaMA3-RM-v0.1
|
||||
trust_remote_code: false
|
||||
use_fused_kernels: false
|
||||
use_remove_padding: false
|
||||
use_shm: false
|
||||
n_gpus_per_node: 8
|
||||
nnodes: 0
|
||||
num_workers: 1
|
||||
profiler:
|
||||
_target_: verl.utils.profiler.ProfilerConfig
|
||||
all_ranks: false
|
||||
enable: false
|
||||
ranks: []
|
||||
save_path: outputs/profile
|
||||
tool: null
|
||||
tool_config:
|
||||
npu:
|
||||
_target_: verl.utils.profiler.config.NPUToolConfig
|
||||
analysis: true
|
||||
contents: []
|
||||
discrete: false
|
||||
level: level0
|
||||
nsys:
|
||||
_target_: verl.utils.profiler.config.NsightToolConfig
|
||||
discrete: false
|
||||
torch:
|
||||
_target_: verl.utils.profiler.config.TorchProfilerToolConfig
|
||||
step_end: null
|
||||
step_start: 0
|
||||
torch_memory:
|
||||
_target_: verl.utils.profiler.config.TorchMemoryToolConfig
|
||||
stack_depth: 32
|
||||
trace_alloc_max_entries: 100000
|
||||
reward_loop_class_name: null
|
||||
reward_loop_module_path: null
|
||||
reward_loop_source: register
|
||||
reward_manager: naive
|
||||
rollout:
|
||||
_target_: verl.workers.config.RolloutConfig
|
||||
cudagraph_capture_sizes: null
|
||||
data_parallel_size: 1
|
||||
disable_log_stats: true
|
||||
dtype: bfloat16
|
||||
enable_chunked_prefill: true
|
||||
enable_prefix_caching: true
|
||||
enforce_eager: true
|
||||
expert_parallel_size: 1
|
||||
free_cache_engine: true
|
||||
gpu_memory_utilization: 0.5
|
||||
limit_images: null
|
||||
load_format: auto
|
||||
max_model_len: null
|
||||
max_num_batched_tokens: 8192
|
||||
max_num_seqs: 1024
|
||||
name: ???
|
||||
prompt_length: 2048
|
||||
response_length: 2048
|
||||
skip_tokenizer_init: false
|
||||
tensor_model_parallel_size: 2
|
||||
sandbox_fusion:
|
||||
max_concurrent: 64
|
||||
memory_limit_mb: 1024
|
||||
url: null
|
||||
strategy: fsdp
|
||||
ulysses_sequence_parallel_size: 1
|
||||
use_dynamic_bsz: false
|
||||
use_reward_loop: false
|
||||
trainer:
|
||||
value:
|
||||
balance_batch: true
|
||||
critic_warmup: 0
|
||||
default_hdfs_dir: null
|
||||
default_local_dir: /mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/physics/qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8
|
||||
del_local_ckpt_after_load: false
|
||||
device: cuda
|
||||
esi_redundant_time: 0
|
||||
experiment_name: qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8
|
||||
group_name: QWEN3-GRPO-generalization
|
||||
log_val_generations: 0
|
||||
logger:
|
||||
- console
|
||||
- wandb
|
||||
max_actor_ckpt_to_keep: 1
|
||||
max_critic_ckpt_to_keep: null
|
||||
n_gpus_per_node: 8
|
||||
nnodes: 1
|
||||
project_name: SDPO-root
|
||||
ray_wait_register_center_timeout: 300
|
||||
resume_from_path: null
|
||||
resume_mode: auto
|
||||
rollout_data_dir: null
|
||||
save_freq: 10
|
||||
test_freq: 10
|
||||
total_epochs: 30
|
||||
total_training_steps: 100
|
||||
use_legacy_worker_impl: auto
|
||||
val_before_train: false
|
||||
val_only: false
|
||||
validation_data_dir: null
|
||||
transfer_queue:
|
||||
value:
|
||||
enable: false
|
||||
vars:
|
||||
value:
|
||||
ckpt_dir: /capstor/scratch/cscs/root/ttrl_runs/datasets/sciknoweval/physics
|
||||
dir: /users/root/SDPO
|
||||
log_dir: /users/root/output
|
||||
task: datasets/sciknoweval/physics
|
||||
1045
artifacts/output.log
Normal file
1045
artifacts/output.log
Normal file
File diff suppressed because it is too large
Load Diff
5099
artifacts/queue.log
Normal file
5099
artifacts/queue.log
Normal file
File diff suppressed because one or more lines are too long
109
artifacts/wandb-metadata.json
Normal file
109
artifacts/wandb-metadata.json
Normal file
@@ -0,0 +1,109 @@
|
||||
{
|
||||
"os": "Linux-6.8.0-71-generic-x86_64-with-glibc2.36",
|
||||
"python": "CPython 3.12.13",
|
||||
"startedAt": "2026-07-02T07:34:03.171912Z",
|
||||
"args": [
|
||||
"--node-ip-address=198.19.44.212",
|
||||
"--node-manager-port=44693",
|
||||
"--object-store-name=/tmp/ray_q3g_physics_grpo_Qwen3_4B/session_2026-07-02_07-32-21_495593_2047177/sockets/plasma_store",
|
||||
"--raylet-name=/tmp/ray_q3g_physics_grpo_Qwen3_4B/session_2026-07-02_07-32-21_495593_2047177/sockets/raylet",
|
||||
"--redis-address=None",
|
||||
"--metrics-agent-port=64329",
|
||||
"--logging-rotate-bytes=536870912",
|
||||
"--logging-rotate-backup-count=5",
|
||||
"--runtime-env-agent-port=38126",
|
||||
"--gcs-address=198.19.44.212:36723",
|
||||
"--session-name=session_2026-07-02_07-32-21_495593_2047177",
|
||||
"--temp-dir=/tmp/ray_q3g_physics_grpo_Qwen3_4B",
|
||||
"--webui=",
|
||||
"--cluster-id=0a12e6f2d868e024fd5459804d49781a3c5964c41dc3a56ce70ff7cc",
|
||||
"--startup-token=32",
|
||||
"--worker-launch-time-ms=1782977544731",
|
||||
"--node-id=50eae392b56a513097e99478e0bdccea3fd788cddb6f512b6cd0013b",
|
||||
"--runtime-env-hash=997165006"
|
||||
],
|
||||
"program": "/mnt/mole/SDPO/L2T/.venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||
"codePath": ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||
"codePathLocal": ".venv/lib/python3.12/site-packages/ray/_private/workers/default_worker.py",
|
||||
"git": {
|
||||
"remote": "https://github.com/jungseongryong/L2T.git",
|
||||
"commit": "ee6a667700697069b93db636aa937f970c1fb57a"
|
||||
},
|
||||
"email": "jungsr1116@cau.ac.kr",
|
||||
"root": "/mnt/mole/SDPO/L2T",
|
||||
"host": "mole-workspace-rw",
|
||||
"executable": "/mnt/mole/SDPO/L2T/.venv/bin/python",
|
||||
"cpu_count": 64,
|
||||
"cpu_count_logical": 128,
|
||||
"gpu": "NVIDIA H200",
|
||||
"gpu_count": 8,
|
||||
"disk": {
|
||||
"/": {
|
||||
"total": "46086056050688",
|
||||
"used": "21178574569472"
|
||||
}
|
||||
},
|
||||
"memory": {
|
||||
"total": "2163980390400"
|
||||
},
|
||||
"gpu_nvidia": [
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-c0451621-891c-7169-976d-71d81958db34"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-e2a29dfa-7dad-6cd7-fb05-79d0060f27f0"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-d69bb741-f2a7-a375-7f56-5c0d09d797b2"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-1bbbea1e-7541-3126-1bfc-51b43a67577e"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-6e0055af-452d-3f46-ce21-0c71e347a608"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-317fdb5b-b280-71d8-398e-a843ad897437"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-f19d8161-d2dd-49a1-dcb8-5c341b5e4514"
|
||||
},
|
||||
{
|
||||
"name": "NVIDIA H200",
|
||||
"memoryTotal": "150754820096",
|
||||
"cudaCores": 16896,
|
||||
"architecture": "Hopper",
|
||||
"uuid": "GPU-961f5ebf-4bf8-6855-828b-c065af57b87c"
|
||||
}
|
||||
],
|
||||
"cudaVersion": "13.0",
|
||||
"writerId": "qf9brx37u7ogioghafnpg1eqgbkrrld7"
|
||||
}
|
||||
1
artifacts/wandb-summary.json
Normal file
1
artifacts/wandb-summary.json
Normal file
File diff suppressed because one or more lines are too long
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- 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 %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- 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" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- 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' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
28
checkpoints/last/added_tokens.json
Normal file
28
checkpoints/last/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
|
||||
}
|
||||
89
checkpoints/last/chat_template.jinja
Normal file
89
checkpoints/last/chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- 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 %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- 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" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- 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' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
checkpoints/last/config.json
Normal file
68
checkpoints/last/config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"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": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
checkpoints/last/generation_config.json
Normal file
13
checkpoints/last/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": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
checkpoints/last/merges.txt
Normal file
151388
checkpoints/last/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoints/last/model-00001-of-00002.safetensors
Normal file
3
checkpoints/last/model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9d46386d369a8ea684c51c93b6fd2c9d8e87d28efd549e4d02f4f6472d5d912b
|
||||
size 4956764432
|
||||
3
checkpoints/last/model-00002-of-00002.safetensors
Normal file
3
checkpoints/last/model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0c0b22b312478acc35202afba86689b13769c53b77169797d85dbc4955ac77bb
|
||||
size 3866130088
|
||||
407
checkpoints/last/model.safetensors.index.json
Normal file
407
checkpoints/last/model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4411424256,
|
||||
"total_size": 8822848512
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00001-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-00001-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-00001-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-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-00002-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-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
31
checkpoints/last/special_tokens_map.json
Normal file
31
checkpoints/last/special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"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|>"
|
||||
],
|
||||
"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
|
||||
}
|
||||
}
|
||||
BIN
checkpoints/last/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoints/last/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
checkpoints/last/tokenizer_config.json
Normal file
239
checkpoints/last/tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
checkpoints/last/vocab.json
Normal file
1
checkpoints/last/vocab.json
Normal file
File diff suppressed because one or more lines are too long
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"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": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"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": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
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 sha256:9d46386d369a8ea684c51c93b6fd2c9d8e87d28efd549e4d02f4f6472d5d912b
|
||||
size 4956764432
|
||||
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 sha256:0c0b22b312478acc35202afba86689b13769c53b77169797d85dbc4955ac77bb
|
||||
size 3866130088
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4411424256,
|
||||
"total_size": 8822848512
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-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-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00001-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-00001-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-00001-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-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-00002-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-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-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-00002-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-00001-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
77
results/hyperparameters.csv
Normal file
77
results/hyperparameters.csv
Normal file
@@ -0,0 +1,77 @@
|
||||
section,parameter,value,source
|
||||
Run identity,Base model,Qwen/Qwen3-4B,queue/script override
|
||||
Run identity,Dataset,Physics / SciKnowEval physics,run_qwen3_generalization.sh
|
||||
Run identity,Method,GRPO,run_qwen3_generalization.sh
|
||||
Run identity,Config,baseline_grpo,run_qwen3_generalization.sh
|
||||
Run identity,Experiment,qwen3gen-physics-GRPO-Qwen-Qwen3-4B-mbs8-train32-rollout8-lr1e-6-vllm0.8,run_qwen3_generalization.sh
|
||||
Run identity,W&B run,run-20260702_073403-o8ivivjg,wandb
|
||||
Data,Train file,datasets/sciknoweval/physics/train.parquet,script override
|
||||
Data,Validation file,datasets/sciknoweval/physics/test.parquet,script override
|
||||
Data,Train batch size,32,queue/script override
|
||||
Data,Train max samples,3200,queue/script override
|
||||
Data,Prompt key,prompt,legacy_data.yaml default
|
||||
Data,Reward key,data_source,legacy_data.yaml default
|
||||
Data,Shuffle train data,True,user.yaml / legacy_data.yaml
|
||||
Data,Validation shuffle,False,legacy_data.yaml default
|
||||
Data,Filter overlong prompts,True,user.yaml
|
||||
Data,Prompt truncation,error,legacy_data.yaml default
|
||||
Data,enable_thinking,false,script override
|
||||
Schedule,Total training steps,100,queue/script override
|
||||
Schedule,Total epochs,30,ppo_trainer/user.yaml default
|
||||
Schedule,Validation before train,False,queue/script override
|
||||
Schedule,Save frequency,10,queue/script override
|
||||
Schedule,Validation frequency,10,queue/script override
|
||||
Sequence,Max prompt length,2048,queue/script override
|
||||
Sequence,Max response length,8192,queue/script override
|
||||
Sequence,Max model length,10240,queue/script override
|
||||
Sequence,Actor max token length per GPU,10240,queue/script override
|
||||
Rollout,Rollout engine,vllm,user.yaml
|
||||
Rollout,Rollout dtype,bfloat16,rollout.yaml default
|
||||
Rollout,Train rollout n,8,queue/script override
|
||||
Rollout,Train rollout temperature,1.0,script override
|
||||
Rollout,Train rollout top_p,1.0,script override
|
||||
Rollout,Train rollout do_sample,True,rollout.yaml default
|
||||
Rollout,Calculate rollout log probs,True,baseline_grpo.yaml / script override
|
||||
Rollout,Max num batched tokens,10240,queue/script override
|
||||
Rollout,vLLM GPU memory utilization,0.8,queue/script override
|
||||
Rollout,Tensor model parallel size,2,rollout.yaml default
|
||||
Rollout,Free cache engine,True,rollout.yaml default
|
||||
Validation,Validation rollout n,16,queue/script override
|
||||
Validation,Validation temperature,0.6,queue/script override
|
||||
Validation,Validation top_p,0.95,queue/script override
|
||||
Validation,Validation do_sample,True,queue/script override
|
||||
Optimization,Optimizer,AdamW,fsdp optimizer config
|
||||
Optimization,Learning rate,1e-6,GRPO method override
|
||||
Optimization,LR scheduler,constant,W&B config
|
||||
Optimization,LR warmup steps,10,script override
|
||||
Optimization,Weight decay,0.01,script override
|
||||
Optimization,Betas,"(0.9, 0.999)",W&B config
|
||||
Optimization,Gradient clip,1.0,script override
|
||||
PPO/GRPO,Policy loss mode,vanilla,method override
|
||||
PPO/GRPO,Advantage estimator,grpo,baseline_grpo.yaml
|
||||
PPO/GRPO,Normalize GRPO advantages by std,False,baseline_grpo.yaml / script override
|
||||
PPO/GRPO,PPO epochs,1,W&B config
|
||||
PPO/GRPO,PPO mini batch size,8,queue/script override
|
||||
PPO/GRPO,PPO micro batch size per GPU,1,user.yaml
|
||||
PPO/GRPO,Clip ratio low,0.2,script override
|
||||
PPO/GRPO,Clip ratio high,0.28,script override
|
||||
PPO/GRPO,Gamma,1.0,ppo_trainer.yaml default
|
||||
PPO/GRPO,Lambda,1.0,ppo_trainer.yaml default
|
||||
PPO/GRPO,Actor KL loss coef,0.0,method override
|
||||
PPO/GRPO,Use KL in reward,False,ppo_trainer/user.yaml
|
||||
Rollout correction,Importance sampling mode,token,script override
|
||||
Rollout correction,IS threshold,2.0,script override
|
||||
FSDP/System,Actor strategy,fsdp,dp_actor.yaml
|
||||
FSDP/System,FSDP dtype,bfloat16,W&B config
|
||||
FSDP/System,FSDP model dtype,fp32,W&B config
|
||||
FSDP/System,Use torch compile,True,W&B config
|
||||
FSDP/System,GPUs per node,8,queue/script override
|
||||
FSDP/System,Nodes,1,user.yaml
|
||||
FSDP/System,GPU type,NVIDIA H200,wandb-metadata
|
||||
Checkpoint/Logging,Checkpoint root,checkpoints/datasets/sciknoweval/physics,script override
|
||||
Checkpoint/Logging,Latest checkpointed iteration,100,latest_checkpointed_iteration.txt
|
||||
Checkpoint/Logging,Max actor checkpoints to keep,1,user.yaml
|
||||
Checkpoint/Logging,Logger,"console, wandb",ppo_trainer.yaml
|
||||
Checkpoint/Logging,W&B entity,seongryongjung-chung-ang-university,environment
|
||||
Checkpoint/Logging,W&B project,SDPO-root,user.yaml project_name
|
||||
Checkpoint/Logging,W&B group,QWEN3-GRPO-generalization,method override
|
||||
|
24
results/summary.json
Normal file
24
results/summary.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"repo_id": "SeongryongJung/Qwen3-4B-Physics-GRPO-TR",
|
||||
"output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-4B-Physics-GRPO-TR",
|
||||
"best_step": 100,
|
||||
"best_val_mean16": 0.6828125,
|
||||
"final_step": 100,
|
||||
"final_val_mean16": 0.6828125,
|
||||
"train_rows": 90,
|
||||
"val_rows": 10,
|
||||
"hf_model_files": [
|
||||
"added_tokens.json",
|
||||
"chat_template.jinja",
|
||||
"config.json",
|
||||
"generation_config.json",
|
||||
"merges.txt",
|
||||
"model.safetensors.index.json",
|
||||
"special_tokens_map.json",
|
||||
"tokenizer.json",
|
||||
"tokenizer_config.json",
|
||||
"vocab.json",
|
||||
"model-00001-of-00002.safetensors",
|
||||
"model-00002-of-00002.safetensors"
|
||||
]
|
||||
}
|
||||
3
results/training_score.png
Normal file
3
results/training_score.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6de5124859a1f32d9fed6bbfbb7496e94236aedd46aaaf8bfd5c02c4d6457726
|
||||
size 120349
|
||||
1591
results/training_score.svg
Normal file
1591
results/training_score.svg
Normal file
File diff suppressed because it is too large
Load Diff
|
After Width: | Height: | Size: 43 KiB |
91
results/training_scores.csv
Normal file
91
results/training_scores.csv
Normal file
@@ -0,0 +1,91 @@
|
||||
step,critic_score_mean
|
||||
1,0.6640625
|
||||
2,0.578125
|
||||
3,0.5546875
|
||||
4,0.625
|
||||
5,0.7578125
|
||||
6,0.55859375
|
||||
7,0.703125
|
||||
8,0.671875
|
||||
9,0.64453125
|
||||
11,0.609375
|
||||
12,0.59375
|
||||
13,0.515625
|
||||
14,0.640625
|
||||
15,0.6796875
|
||||
16,0.6953125
|
||||
17,0.65234375
|
||||
18,0.40234375
|
||||
19,0.6875
|
||||
21,0.671875
|
||||
22,0.625
|
||||
23,0.46484375
|
||||
24,0.7265625
|
||||
25,0.6640625
|
||||
26,0.7578125
|
||||
27,0.71875
|
||||
28,0.65234375
|
||||
29,0.6875
|
||||
31,0.65625
|
||||
32,0.68359375
|
||||
33,0.6953125
|
||||
34,0.65625
|
||||
35,0.6640625
|
||||
36,0.56640625
|
||||
37,0.671875
|
||||
38,0.61328125
|
||||
39,0.79296875
|
||||
41,0.75390625
|
||||
42,0.5703125
|
||||
43,0.69140625
|
||||
44,0.61328125
|
||||
45,0.625
|
||||
46,0.7578125
|
||||
47,0.78125
|
||||
48,0.69921875
|
||||
49,0.77734375
|
||||
51,0.66796875
|
||||
52,0.65625
|
||||
53,0.71484375
|
||||
54,0.73828125
|
||||
55,0.75390625
|
||||
56,0.68359375
|
||||
57,0.59765625
|
||||
58,0.5859375
|
||||
59,0.62109375
|
||||
61,0.68359375
|
||||
62,0.6328125
|
||||
63,0.6640625
|
||||
64,0.66796875
|
||||
65,0.890625
|
||||
66,0.7265625
|
||||
67,0.734375
|
||||
68,0.7265625
|
||||
69,0.7265625
|
||||
71,0.75
|
||||
72,0.7421875
|
||||
73,0.61328125
|
||||
74,0.75390625
|
||||
75,0.859375
|
||||
76,0.6875
|
||||
77,0.703125
|
||||
78,0.78125
|
||||
79,0.8046875
|
||||
81,0.7109375
|
||||
82,0.63671875
|
||||
83,0.66796875
|
||||
84,0.671875
|
||||
85,0.671875
|
||||
86,0.6328125
|
||||
87,0.6875
|
||||
88,0.66015625
|
||||
89,0.79296875
|
||||
91,0.81640625
|
||||
92,0.69921875
|
||||
93,0.734375
|
||||
94,0.7265625
|
||||
95,0.625
|
||||
96,0.67578125
|
||||
97,0.6796875
|
||||
98,0.70703125
|
||||
99,0.86328125
|
||||
|
11
results/validation_mean16.csv
Normal file
11
results/validation_mean16.csv
Normal file
@@ -0,0 +1,11 @@
|
||||
step,val_mean16
|
||||
10,0.59453125
|
||||
20,0.61328125
|
||||
30,0.63125
|
||||
40,0.62421875
|
||||
50,0.6453125
|
||||
60,0.6375
|
||||
70,0.63828125
|
||||
80,0.6390625
|
||||
90,0.6625
|
||||
100,0.6828125
|
||||
|
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"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|>"
|
||||
],
|
||||
"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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
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