zjrwtxtechstudio commited on May 19, 2025

Commit

1054bca

verified ·

1 Parent(s): 0984cad

Upload folder using huggingface_hub

Browse files

Files changed (44) hide show

.gitattributes +2 -0
.ipynb_checkpoints/README-checkpoint.md +61 -0
.ipynb_checkpoints/llamaboard_config-checkpoint.yaml +78 -0
.ipynb_checkpoints/merges-checkpoint.txt +0 -0
.ipynb_checkpoints/running_log-checkpoint.txt +296 -0
.ipynb_checkpoints/special_tokens_map-checkpoint.json +31 -0
.ipynb_checkpoints/tokenizer_config-checkpoint.json +241 -0
.ipynb_checkpoints/train_results-checkpoint.json +9 -0
.ipynb_checkpoints/training_args-checkpoint.yaml +36 -0
.ipynb_checkpoints/training_loss-checkpoint.png +0 -0
README.md +61 -0
adapter_config.json +39 -0
adapter_model.safetensors +3 -0
added_tokens.json +28 -0
all_results.json +9 -0
checkpoint-93/README.md +202 -0
checkpoint-93/adapter_config.json +39 -0
checkpoint-93/adapter_model.safetensors +3 -0
checkpoint-93/added_tokens.json +28 -0
checkpoint-93/merges.txt +0 -0
checkpoint-93/optimizer.pt +3 -0
checkpoint-93/rng_state_0.pth +3 -0
checkpoint-93/rng_state_1.pth +3 -0
checkpoint-93/scheduler.pt +3 -0
checkpoint-93/special_tokens_map.json +31 -0
checkpoint-93/tokenizer.json +3 -0
checkpoint-93/tokenizer_config.json +241 -0
checkpoint-93/trainer_state.json +178 -0
checkpoint-93/training_args.bin +3 -0
checkpoint-93/vocab.json +0 -0
llamaboard_config.yaml +78 -0
merges.txt +0 -0
running_log.txt +296 -0
special_tokens_map.json +31 -0
swanlab_public_config.json +13 -0
tokenizer.json +3 -0
tokenizer_config.json +241 -0
train_results.json +9 -0
trainer_log.jsonl +19 -0
trainer_state.json +188 -0
training_args.bin +3 -0
training_args.yaml +36 -0
training_loss.png +0 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ saved_model/**/* 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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-93/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md ADDED Viewed

	@@ -0,0 +1,61 @@

+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-4B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-05-18-16-33-56
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# train_2025-05-18-16-33-56
+This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the alpaca_zh_demo dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+### Training results
+### Framework versions
+- PEFT 0.15.1
+- Transformers 4.51.3
+- Pytorch 2.1.0+cu118
+- Datasets 3.2.0
+- Tokenizers 0.21.1

.ipynb_checkpoints/llamaboard_config-checkpoint.yaml ADDED Viewed

	@@ -0,0 +1,78 @@

+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen3-4B-Instruct
+top.quantization_bit: none
+top.quantization_method: bnb
+top.rope_scaling: none
+top.template: qwen3
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- alpaca_zh_demo
+train.dataset_dir: LLaMA-Factory/data/
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to:
+- none
+train.resize_vocab: false
+train.reward_model: []
+train.save_steps: 100
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: true
+train.val_size: 0
+train.warmup_steps: 0

.ipynb_checkpoints/merges-checkpoint.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

.ipynb_checkpoints/running_log-checkpoint.txt ADDED Viewed

	@@ -0,0 +1,296 @@

+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/vocab.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/merges.txt
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file added_tokens.json from cache at None
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file special_tokens_map.json from cache at None
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer_config.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file chat_template.jinja from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|2025-05-18 16:53:57] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:53:57] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/vocab.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/merges.txt
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file added_tokens.json from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file special_tokens_map.json from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer_config.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file chat_template.jinja from cache at None
+[INFO|2025-05-18 16:53:58] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|2025-05-18 16:53:58] logging.py:143 >> Loading dataset alpaca_zh_demo.json...
+[INFO|2025-05-18 16:53:59] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:53:59] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:53:59] logging.py:143 >> KV cache is disabled during training.
+[INFO|2025-05-18 16:53:59] modeling_utils.py:1124 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/model.safetensors.index.json
+[INFO|2025-05-18 16:53:59] modeling_utils.py:2167 >> Instantiating Qwen3ForCausalLM model under default dtype torch.bfloat16.
+[INFO|2025-05-18 16:53:59] configuration_utils.py:1142 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "use_cache": false
+}
+[INFO|2025-05-18 16:54:01] modeling_utils.py:4930 >> All model checkpoint weights were used when initializing Qwen3ForCausalLM.
+[INFO|2025-05-18 16:54:01] modeling_utils.py:4938 >> All the weights of Qwen3ForCausalLM were initialized from the model checkpoint at Qwen/Qwen3-4B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen3ForCausalLM for predictions without further training.
+[INFO|2025-05-18 16:54:01] configuration_utils.py:1097 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/generation_config.json
+[INFO|2025-05-18 16:54:01] configuration_utils.py:1142 >> Generate config GenerationConfig {
+  "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
+}
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Gradient checkpointing enabled.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Using vanilla attention implementation.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Upcasting trainable params to float32.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Fine-tuning method: LoRA
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Found linear modules: k_proj,o_proj,q_proj,up_proj,v_proj,gate_proj,down_proj
+[INFO|2025-05-18 16:54:02] logging.py:143 >> trainable params: 16,515,072 || all params: 4,038,983,168 || trainable%: 0.4089
+[INFO|2025-05-18 16:54:02] trainer.py:748 >> Using auto half precision backend
+[INFO|2025-05-18 16:54:02] trainer.py:2414 >> ***** Running training *****
+[INFO|2025-05-18 16:54:02] trainer.py:2415 >>   Num examples = 1,000
+[INFO|2025-05-18 16:54:02] trainer.py:2416 >>   Num Epochs = 3
+[INFO|2025-05-18 16:54:02] trainer.py:2417 >>   Instantaneous batch size per device = 2
+[INFO|2025-05-18 16:54:02] trainer.py:2420 >>   Total train batch size (w. parallel, distributed & accumulation) = 32
+[INFO|2025-05-18 16:54:02] trainer.py:2421 >>   Gradient Accumulation steps = 8
+[INFO|2025-05-18 16:54:02] trainer.py:2422 >>   Total optimization steps = 93
+[INFO|2025-05-18 16:54:02] trainer.py:2423 >>   Number of trainable parameters = 16,515,072
+[INFO|2025-05-18 16:54:38] logging.py:143 >> {'loss': 2.5834, 'learning_rate': 4.9772e-05, 'epoch': 0.16, 'throughput': 843.60}
+[INFO|2025-05-18 16:54:52] logging.py:143 >> {'loss': 2.0249, 'learning_rate': 4.8853e-05, 'epoch': 0.32, 'throughput': 1214.74}
+[INFO|2025-05-18 16:55:08] logging.py:143 >> {'loss': 1.6448, 'learning_rate': 4.7256e-05, 'epoch': 0.48, 'throughput': 1395.41}
+[INFO|2025-05-18 16:55:22] logging.py:143 >> {'loss': 1.5754, 'learning_rate': 4.5025e-05, 'epoch': 0.64, 'throughput': 1525.57}
+[INFO|2025-05-18 16:55:36] logging.py:143 >> {'loss': 1.5325, 'learning_rate': 4.2224e-05, 'epoch': 0.80, 'throughput': 1608.49}
+[INFO|2025-05-18 16:55:49] logging.py:143 >> {'loss': 1.5399, 'learning_rate': 3.8933e-05, 'epoch': 0.96, 'throughput': 1681.17}
+[INFO|2025-05-18 16:56:01] logging.py:143 >> {'loss': 1.4496, 'learning_rate': 3.5246e-05, 'epoch': 1.10, 'throughput': 1726.10}
+[INFO|2025-05-18 16:56:15] logging.py:143 >> {'loss': 1.4453, 'learning_rate': 3.1266e-05, 'epoch': 1.26, 'throughput': 1763.43}
+[INFO|2025-05-18 16:56:30] logging.py:143 >> {'loss': 1.5063, 'learning_rate': 2.7109e-05, 'epoch': 1.42, 'throughput': 1802.17}
+[INFO|2025-05-18 16:56:44] logging.py:143 >> {'loss': 1.5230, 'learning_rate': 2.2891e-05, 'epoch': 1.58, 'throughput': 1835.87}
+[INFO|2025-05-18 16:56:58] logging.py:143 >> {'loss': 1.4390, 'learning_rate': 1.8734e-05, 'epoch': 1.74, 'throughput': 1861.70}
+[INFO|2025-05-18 16:57:12] logging.py:143 >> {'loss': 1.4884, 'learning_rate': 1.4754e-05, 'epoch': 1.90, 'throughput': 1880.88}
+[INFO|2025-05-18 16:57:23] logging.py:143 >> {'loss': 1.5448, 'learning_rate': 1.1067e-05, 'epoch': 2.03, 'throughput': 1886.27}
+[INFO|2025-05-18 16:57:39] logging.py:143 >> {'loss': 1.4931, 'learning_rate': 7.7758e-06, 'epoch': 2.19, 'throughput': 1903.44}
+[INFO|2025-05-18 16:57:52] logging.py:143 >> {'loss': 1.4863, 'learning_rate': 4.9750e-06, 'epoch': 2.35, 'throughput': 1913.31}
+[INFO|2025-05-18 16:58:06] logging.py:143 >> {'loss': 1.4528, 'learning_rate': 2.7440e-06, 'epoch': 2.51, 'throughput': 1926.75}
+[INFO|2025-05-18 16:58:21] logging.py:143 >> {'loss': 1.3916, 'learning_rate': 1.1465e-06, 'epoch': 2.67, 'throughput': 1933.94}
+[INFO|2025-05-18 16:58:35] logging.py:143 >> {'loss': 1.4927, 'learning_rate': 2.2788e-07, 'epoch': 2.83, 'throughput': 1947.73}
+[INFO|2025-05-18 16:58:43] trainer.py:3984 >> Saving model checkpoint to saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93
+[INFO|2025-05-18 16:58:43] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:58:43] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:58:44] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93/tokenizer_config.json
+[INFO|2025-05-18 16:58:44] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93/special_tokens_map.json
+[INFO|2025-05-18 16:58:45] trainer.py:2681 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+[INFO|2025-05-18 16:58:45] trainer.py:3984 >> Saving model checkpoint to saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56
+[INFO|2025-05-18 16:58:45] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:58:45] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:58:46] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/tokenizer_config.json
+[INFO|2025-05-18 16:58:46] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/special_tokens_map.json
+[WARNING|2025-05-18 16:58:46] logging.py:148 >> No metric eval_loss to plot.
+[WARNING|2025-05-18 16:58:46] logging.py:148 >> No metric eval_accuracy to plot.
+[INFO|2025-05-18 16:58:46] modelcard.py:450 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}

.ipynb_checkpoints/special_tokens_map-checkpoint.json ADDED Viewed

	@@ -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
+  }
+}

.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED Viewed

	@@ -0,0 +1,241 @@

+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

.ipynb_checkpoints/train_results-checkpoint.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 2.928,
+    "num_input_tokens_seen": 547088,
+    "total_flos": 1.1981315796631552e+16,
+    "train_loss": 1.5843523497222571,
+    "train_runtime": 282.8295,
+    "train_samples_per_second": 10.607,
+    "train_steps_per_second": 0.329
+}

.ipynb_checkpoints/training_args-checkpoint.yaml ADDED Viewed

	@@ -0,0 +1,36 @@

+bf16: true
+cutoff_len: 2048
+dataset: alpaca_zh_demo
+dataset_dir: LLaMA-Factory/data/
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen3-4B
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+swanlab_mode: cloud
+swanlab_project: llamafactory
+template: qwen3
+trust_remote_code: true
+use_swanlab: true
+warmup_steps: 0

.ipynb_checkpoints/training_loss-checkpoint.png ADDED Viewed

README.md ADDED Viewed

	@@ -0,0 +1,61 @@

+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-4B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-05-18-16-33-56
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# train_2025-05-18-16-33-56
+This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the alpaca_zh_demo dataset.
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+### Training results
+### Framework versions
+- PEFT 0.15.1
+- Transformers 4.51.3
+- Pytorch 2.1.0+cu118
+- Datasets 3.2.0
+- Tokenizers 0.21.1

adapter_config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:459642fa53d4f0b543db682e7bb1866adc2cfd833f52c3dc83492947b8180ca1
+size 66126768

added_tokens.json ADDED Viewed

	@@ -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
+}

all_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 2.928,
+    "num_input_tokens_seen": 547088,
+    "total_flos": 1.1981315796631552e+16,
+    "train_loss": 1.5843523497222571,
+    "train_runtime": 282.8295,
+    "train_samples_per_second": 10.607,
+    "train_steps_per_second": 0.329
+}

checkpoint-93/README.md ADDED Viewed

	@@ -0,0 +1,202 @@

+---
+base_model: Qwen/Qwen3-4B
+library_name: peft
+---
+# Model Card for Model ID
+<!-- Provide a quick summary of what the model is/does. -->
+## Model Details
+### Model Description
+<!-- Provide a longer summary of what this model is. -->
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+### Model Sources [optional]
+<!-- Provide the basic links for the model. -->
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+## Uses
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+### Direct Use
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+[More Information Needed]
+### Downstream Use [optional]
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+[More Information Needed]
+### Out-of-Scope Use
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+[More Information Needed]
+## Bias, Risks, and Limitations
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+[More Information Needed]
+### Recommendations
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+## How to Get Started with the Model
+Use the code below to get started with the model.
+[More Information Needed]
+## Training Details
+### Training Data
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+[More Information Needed]
+### Training Procedure
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+#### Preprocessing [optional]
+[More Information Needed]
+#### Training Hyperparameters
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+#### Speeds, Sizes, Times [optional]
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+[More Information Needed]
+## Evaluation
+<!-- This section describes the evaluation protocols and provides the results. -->
+### Testing Data, Factors & Metrics
+#### Testing Data
+<!-- This should link to a Dataset Card if possible. -->
+[More Information Needed]
+#### Factors
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+[More Information Needed]
+#### Metrics
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+[More Information Needed]
+### Results
+[More Information Needed]
+#### Summary
+## Model Examination [optional]
+<!-- Relevant interpretability work for the model goes here -->
+[More Information Needed]
+## Environmental Impact
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+## Technical Specifications [optional]
+### Model Architecture and Objective
+[More Information Needed]
+### Compute Infrastructure
+[More Information Needed]
+#### Hardware
+[More Information Needed]
+#### Software
+[More Information Needed]
+## Citation [optional]
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+**BibTeX:**
+[More Information Needed]
+**APA:**
+[More Information Needed]
+## Glossary [optional]
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+[More Information Needed]
+## More Information [optional]
+[More Information Needed]
+## Model Card Authors [optional]
+[More Information Needed]
+## Model Card Contact
+[More Information Needed]
+### Framework versions
+- PEFT 0.15.1

checkpoint-93/adapter_config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-93/adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:459642fa53d4f0b543db682e7bb1866adc2cfd833f52c3dc83492947b8180ca1
+size 66126768

checkpoint-93/added_tokens.json ADDED Viewed

	@@ -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
+}

checkpoint-93/merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-93/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0db6036def3da432143952f14cdbfe7493465808b68336455af0f47ea7cc7711
+size 132544890

checkpoint-93/rng_state_0.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3971cc9e300ddfc20a1d825fdca90e3722b77abcc43ede089645d312e7e069cc
+size 14512

checkpoint-93/rng_state_1.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+size 14512

checkpoint-93/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7cae7b003796dc8f4400a4d098d5ca8afcb88f9c9aa5b0378e0df743bfdf493e
+size 1064

checkpoint-93/special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

checkpoint-93/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-93/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,241 @@

+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-93/trainer_state.json ADDED Viewed

	@@ -0,0 +1,178 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.928,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.637537956237793,
+      "learning_rate": 4.977212170395598e-05,
+      "loss": 2.5834,
+      "num_input_tokens_seen": 29984,
+      "step": 5
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3269447088241577,
+      "learning_rate": 4.885348141000122e-05,
+      "loss": 2.0249,
+      "num_input_tokens_seen": 60896,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.684715211391449,
+      "learning_rate": 4.725596127020879e-05,
+      "loss": 1.6448,
+      "num_input_tokens_seen": 91008,
+      "step": 15
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.44713008403778076,
+      "learning_rate": 4.502502736173462e-05,
+      "loss": 1.5754,
+      "num_input_tokens_seen": 121056,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.31067565083503723,
+      "learning_rate": 4.222417297689217e-05,
+      "loss": 1.5325,
+      "num_input_tokens_seen": 150608,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2663392126560211,
+      "learning_rate": 3.893311157806091e-05,
+      "loss": 1.5399,
+      "num_input_tokens_seen": 179936,
+      "step": 30
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.29055070877075195,
+      "learning_rate": 3.5245508119914687e-05,
+      "loss": 1.4496,
+      "num_input_tokens_seen": 204992,
+      "step": 35
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.2754141688346863,
+      "learning_rate": 3.126631330646802e-05,
+      "loss": 1.4453,
+      "num_input_tokens_seen": 234704,
+      "step": 40
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.23875507712364197,
+      "learning_rate": 2.7108776651076118e-05,
+      "loss": 1.5063,
+      "num_input_tokens_seen": 265392,
+      "step": 45
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.2538706660270691,
+      "learning_rate": 2.2891223348923884e-05,
+      "loss": 1.523,
+      "num_input_tokens_seen": 296416,
+      "step": 50
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.25537464022636414,
+      "learning_rate": 1.8733686693531985e-05,
+      "loss": 1.439,
+      "num_input_tokens_seen": 327520,
+      "step": 55
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.27788516879081726,
+      "learning_rate": 1.475449188008532e-05,
+      "loss": 1.4884,
+      "num_input_tokens_seen": 357648,
+      "step": 60
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.2592379152774811,
+      "learning_rate": 1.1066888421939093e-05,
+      "loss": 1.5448,
+      "num_input_tokens_seen": 379152,
+      "step": 65
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.23788605630397797,
+      "learning_rate": 7.775827023107835e-06,
+      "loss": 1.4931,
+      "num_input_tokens_seen": 412208,
+      "step": 70
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 0.28915899991989136,
+      "learning_rate": 4.9749726382653905e-06,
+      "loss": 1.4863,
+      "num_input_tokens_seen": 439808,
+      "step": 75
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.2782565951347351,
+      "learning_rate": 2.7440387297912123e-06,
+      "loss": 1.4528,
+      "num_input_tokens_seen": 470048,
+      "step": 80
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 0.3000349700450897,
+      "learning_rate": 1.1465185899987797e-06,
+      "loss": 1.3916,
+      "num_input_tokens_seen": 499456,
+      "step": 85
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.24277131259441376,
+      "learning_rate": 2.27878296044029e-07,
+      "loss": 1.4927,
+      "num_input_tokens_seen": 531136,
+      "step": 90
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 93,
+  "num_input_tokens_seen": 547088,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1981315796631552e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-93/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1eea7c59190af26a5b0784b7e06faa36ec1a790afd67a8f8488ad0b50262870b
+size 5752

checkpoint-93/vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

llamaboard_config.yaml ADDED Viewed

	@@ -0,0 +1,78 @@

+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen3-4B-Instruct
+top.quantization_bit: none
+top.quantization_method: bnb
+top.rope_scaling: none
+top.template: qwen3
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- alpaca_zh_demo
+train.dataset_dir: LLaMA-Factory/data/
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to:
+- none
+train.resize_vocab: false
+train.reward_model: []
+train.save_steps: 100
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: true
+train.val_size: 0
+train.warmup_steps: 0

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

running_log.txt ADDED Viewed

	@@ -0,0 +1,296 @@

+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/vocab.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/merges.txt
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file added_tokens.json from cache at None
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file special_tokens_map.json from cache at None
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer_config.json
+[INFO|2025-05-18 16:53:56] tokenization_utils_base.py:2060 >> loading file chat_template.jinja from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|2025-05-18 16:53:57] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:53:57] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/vocab.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/merges.txt
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file added_tokens.json from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file special_tokens_map.json from cache at None
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/tokenizer_config.json
+[INFO|2025-05-18 16:53:57] tokenization_utils_base.py:2060 >> loading file chat_template.jinja from cache at None
+[INFO|2025-05-18 16:53:58] tokenization_utils_base.py:2323 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[INFO|2025-05-18 16:53:58] logging.py:143 >> Loading dataset alpaca_zh_demo.json...
+[INFO|2025-05-18 16:53:59] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:53:59] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:53:59] logging.py:143 >> KV cache is disabled during training.
+[INFO|2025-05-18 16:53:59] modeling_utils.py:1124 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/model.safetensors.index.json
+[INFO|2025-05-18 16:53:59] modeling_utils.py:2167 >> Instantiating Qwen3ForCausalLM model under default dtype torch.bfloat16.
+[INFO|2025-05-18 16:53:59] configuration_utils.py:1142 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "use_cache": false
+}
+[INFO|2025-05-18 16:54:01] modeling_utils.py:4930 >> All model checkpoint weights were used when initializing Qwen3ForCausalLM.
+[INFO|2025-05-18 16:54:01] modeling_utils.py:4938 >> All the weights of Qwen3ForCausalLM were initialized from the model checkpoint at Qwen/Qwen3-4B.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen3ForCausalLM for predictions without further training.
+[INFO|2025-05-18 16:54:01] configuration_utils.py:1097 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/generation_config.json
+[INFO|2025-05-18 16:54:01] configuration_utils.py:1142 >> Generate config GenerationConfig {
+  "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
+}
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Gradient checkpointing enabled.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Using vanilla attention implementation.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Upcasting trainable params to float32.
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Fine-tuning method: LoRA
+[INFO|2025-05-18 16:54:01] logging.py:143 >> Found linear modules: k_proj,o_proj,q_proj,up_proj,v_proj,gate_proj,down_proj
+[INFO|2025-05-18 16:54:02] logging.py:143 >> trainable params: 16,515,072 || all params: 4,038,983,168 || trainable%: 0.4089
+[INFO|2025-05-18 16:54:02] trainer.py:748 >> Using auto half precision backend
+[INFO|2025-05-18 16:54:02] trainer.py:2414 >> ***** Running training *****
+[INFO|2025-05-18 16:54:02] trainer.py:2415 >>   Num examples = 1,000
+[INFO|2025-05-18 16:54:02] trainer.py:2416 >>   Num Epochs = 3
+[INFO|2025-05-18 16:54:02] trainer.py:2417 >>   Instantaneous batch size per device = 2
+[INFO|2025-05-18 16:54:02] trainer.py:2420 >>   Total train batch size (w. parallel, distributed & accumulation) = 32
+[INFO|2025-05-18 16:54:02] trainer.py:2421 >>   Gradient Accumulation steps = 8
+[INFO|2025-05-18 16:54:02] trainer.py:2422 >>   Total optimization steps = 93
+[INFO|2025-05-18 16:54:02] trainer.py:2423 >>   Number of trainable parameters = 16,515,072
+[INFO|2025-05-18 16:54:38] logging.py:143 >> {'loss': 2.5834, 'learning_rate': 4.9772e-05, 'epoch': 0.16, 'throughput': 843.60}
+[INFO|2025-05-18 16:54:52] logging.py:143 >> {'loss': 2.0249, 'learning_rate': 4.8853e-05, 'epoch': 0.32, 'throughput': 1214.74}
+[INFO|2025-05-18 16:55:08] logging.py:143 >> {'loss': 1.6448, 'learning_rate': 4.7256e-05, 'epoch': 0.48, 'throughput': 1395.41}
+[INFO|2025-05-18 16:55:22] logging.py:143 >> {'loss': 1.5754, 'learning_rate': 4.5025e-05, 'epoch': 0.64, 'throughput': 1525.57}
+[INFO|2025-05-18 16:55:36] logging.py:143 >> {'loss': 1.5325, 'learning_rate': 4.2224e-05, 'epoch': 0.80, 'throughput': 1608.49}
+[INFO|2025-05-18 16:55:49] logging.py:143 >> {'loss': 1.5399, 'learning_rate': 3.8933e-05, 'epoch': 0.96, 'throughput': 1681.17}
+[INFO|2025-05-18 16:56:01] logging.py:143 >> {'loss': 1.4496, 'learning_rate': 3.5246e-05, 'epoch': 1.10, 'throughput': 1726.10}
+[INFO|2025-05-18 16:56:15] logging.py:143 >> {'loss': 1.4453, 'learning_rate': 3.1266e-05, 'epoch': 1.26, 'throughput': 1763.43}
+[INFO|2025-05-18 16:56:30] logging.py:143 >> {'loss': 1.5063, 'learning_rate': 2.7109e-05, 'epoch': 1.42, 'throughput': 1802.17}
+[INFO|2025-05-18 16:56:44] logging.py:143 >> {'loss': 1.5230, 'learning_rate': 2.2891e-05, 'epoch': 1.58, 'throughput': 1835.87}
+[INFO|2025-05-18 16:56:58] logging.py:143 >> {'loss': 1.4390, 'learning_rate': 1.8734e-05, 'epoch': 1.74, 'throughput': 1861.70}
+[INFO|2025-05-18 16:57:12] logging.py:143 >> {'loss': 1.4884, 'learning_rate': 1.4754e-05, 'epoch': 1.90, 'throughput': 1880.88}
+[INFO|2025-05-18 16:57:23] logging.py:143 >> {'loss': 1.5448, 'learning_rate': 1.1067e-05, 'epoch': 2.03, 'throughput': 1886.27}
+[INFO|2025-05-18 16:57:39] logging.py:143 >> {'loss': 1.4931, 'learning_rate': 7.7758e-06, 'epoch': 2.19, 'throughput': 1903.44}
+[INFO|2025-05-18 16:57:52] logging.py:143 >> {'loss': 1.4863, 'learning_rate': 4.9750e-06, 'epoch': 2.35, 'throughput': 1913.31}
+[INFO|2025-05-18 16:58:06] logging.py:143 >> {'loss': 1.4528, 'learning_rate': 2.7440e-06, 'epoch': 2.51, 'throughput': 1926.75}
+[INFO|2025-05-18 16:58:21] logging.py:143 >> {'loss': 1.3916, 'learning_rate': 1.1465e-06, 'epoch': 2.67, 'throughput': 1933.94}
+[INFO|2025-05-18 16:58:35] logging.py:143 >> {'loss': 1.4927, 'learning_rate': 2.2788e-07, 'epoch': 2.83, 'throughput': 1947.73}
+[INFO|2025-05-18 16:58:43] trainer.py:3984 >> Saving model checkpoint to saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93
+[INFO|2025-05-18 16:58:43] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:58:43] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:58:44] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93/tokenizer_config.json
+[INFO|2025-05-18 16:58:44] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/checkpoint-93/special_tokens_map.json
+[INFO|2025-05-18 16:58:45] trainer.py:2681 >>
+Training completed. Do not forget to share your model on huggingface.co/models =)
+[INFO|2025-05-18 16:58:45] trainer.py:3984 >> Saving model checkpoint to saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56
+[INFO|2025-05-18 16:58:45] configuration_utils.py:693 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen3-4B/snapshots/82d62bb073771e7a1ea59435f548908540217d1f/config.json
+[INFO|2025-05-18 16:58:45] configuration_utils.py:765 >> Model config Qwen3Config {
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+[INFO|2025-05-18 16:58:46] tokenization_utils_base.py:2510 >> tokenizer config file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/tokenizer_config.json
+[INFO|2025-05-18 16:58:46] tokenization_utils_base.py:2519 >> Special tokens file saved in saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56/special_tokens_map.json
+[WARNING|2025-05-18 16:58:46] logging.py:148 >> No metric eval_loss to plot.
+[WARNING|2025-05-18 16:58:46] logging.py:148 >> No metric eval_accuracy to plot.
+[INFO|2025-05-18 16:58:46] modelcard.py:450 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}

special_tokens_map.json ADDED Viewed

	@@ -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
+  }
+}

swanlab_public_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "project_name": "llamafactory",
+  "version": "0.5.8",
+  "run_id": "run-20250518_165421-a3b1799d",
+  "swanlog_dir": "/workspace/swanlog",
+  "run_dir": "/workspace/swanlog/run-20250518_165421-a3b1799d",
+  "cloud": {
+    "project_name": "llamafactory",
+    "project_url": "https://swanlab.cn/@testchat/llamafactory",
+    "experiment_name": "swan-1",
+    "experiment_url": "https://swanlab.cn/@testchat/llamafactory/runs/152cf90opcdah8j8cm7ne"
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,241 @@

+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 2.928,
+    "num_input_tokens_seen": 547088,
+    "total_flos": 1.1981315796631552e+16,
+    "train_loss": 1.5843523497222571,
+    "train_runtime": 282.8295,
+    "train_samples_per_second": 10.607,
+    "train_steps_per_second": 0.329
+}

trainer_log.jsonl ADDED Viewed

	@@ -0,0 +1,19 @@

+{"current_steps": 5, "total_steps": 93, "loss": 2.5834, "lr": 4.977212170395598e-05, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:00:35", "remaining_time": "0:10:25", "throughput": 843.6, "total_tokens": 29984}
+{"current_steps": 10, "total_steps": 93, "loss": 2.0249, "lr": 4.885348141000122e-05, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:00:50", "remaining_time": "0:06:56", "throughput": 1214.74, "total_tokens": 60896}
+{"current_steps": 15, "total_steps": 93, "loss": 1.6448, "lr": 4.725596127020879e-05, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:01:05", "remaining_time": "0:05:39", "throughput": 1395.41, "total_tokens": 91008}
+{"current_steps": 20, "total_steps": 93, "loss": 1.5754, "lr": 4.502502736173462e-05, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:01:19", "remaining_time": "0:04:49", "throughput": 1525.57, "total_tokens": 121056}
+{"current_steps": 25, "total_steps": 93, "loss": 1.5325, "lr": 4.222417297689217e-05, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:01:33", "remaining_time": "0:04:14", "throughput": 1608.49, "total_tokens": 150608}
+{"current_steps": 30, "total_steps": 93, "loss": 1.5399, "lr": 3.893311157806091e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:01:47", "remaining_time": "0:03:44", "throughput": 1681.17, "total_tokens": 179936}
+{"current_steps": 35, "total_steps": 93, "loss": 1.4496, "lr": 3.5245508119914687e-05, "epoch": 1.096, "percentage": 37.63, "elapsed_time": "0:01:58", "remaining_time": "0:03:16", "throughput": 1726.1, "total_tokens": 204992}
+{"current_steps": 40, "total_steps": 93, "loss": 1.4453, "lr": 3.126631330646802e-05, "epoch": 1.256, "percentage": 43.01, "elapsed_time": "0:02:13", "remaining_time": "0:02:56", "throughput": 1763.43, "total_tokens": 234704}
+{"current_steps": 45, "total_steps": 93, "loss": 1.5063, "lr": 2.7108776651076118e-05, "epoch": 1.416, "percentage": 48.39, "elapsed_time": "0:02:27", "remaining_time": "0:02:37", "throughput": 1802.17, "total_tokens": 265392}
+{"current_steps": 50, "total_steps": 93, "loss": 1.523, "lr": 2.2891223348923884e-05, "epoch": 1.576, "percentage": 53.76, "elapsed_time": "0:02:41", "remaining_time": "0:02:18", "throughput": 1835.87, "total_tokens": 296416}
+{"current_steps": 55, "total_steps": 93, "loss": 1.439, "lr": 1.8733686693531985e-05, "epoch": 1.736, "percentage": 59.14, "elapsed_time": "0:02:55", "remaining_time": "0:02:01", "throughput": 1861.7, "total_tokens": 327520}
+{"current_steps": 60, "total_steps": 93, "loss": 1.4884, "lr": 1.475449188008532e-05, "epoch": 1.896, "percentage": 64.52, "elapsed_time": "0:03:10", "remaining_time": "0:01:44", "throughput": 1880.88, "total_tokens": 357648}
+{"current_steps": 65, "total_steps": 93, "loss": 1.5448, "lr": 1.1066888421939093e-05, "epoch": 2.032, "percentage": 69.89, "elapsed_time": "0:03:21", "remaining_time": "0:01:26", "throughput": 1886.27, "total_tokens": 379152}
+{"current_steps": 70, "total_steps": 93, "loss": 1.4931, "lr": 7.775827023107835e-06, "epoch": 2.192, "percentage": 75.27, "elapsed_time": "0:03:36", "remaining_time": "0:01:11", "throughput": 1903.44, "total_tokens": 412208}
+{"current_steps": 75, "total_steps": 93, "loss": 1.4863, "lr": 4.9749726382653905e-06, "epoch": 2.352, "percentage": 80.65, "elapsed_time": "0:03:49", "remaining_time": "0:00:55", "throughput": 1913.31, "total_tokens": 439808}
+{"current_steps": 80, "total_steps": 93, "loss": 1.4528, "lr": 2.7440387297912123e-06, "epoch": 2.512, "percentage": 86.02, "elapsed_time": "0:04:03", "remaining_time": "0:00:39", "throughput": 1926.75, "total_tokens": 470048}
+{"current_steps": 85, "total_steps": 93, "loss": 1.3916, "lr": 1.1465185899987797e-06, "epoch": 2.672, "percentage": 91.4, "elapsed_time": "0:04:18", "remaining_time": "0:00:24", "throughput": 1933.94, "total_tokens": 499456}
+{"current_steps": 90, "total_steps": 93, "loss": 1.4927, "lr": 2.27878296044029e-07, "epoch": 2.832, "percentage": 96.77, "elapsed_time": "0:04:32", "remaining_time": "0:00:09", "throughput": 1947.73, "total_tokens": 531136}
+{"current_steps": 93, "total_steps": 93, "epoch": 2.928, "percentage": 100.0, "elapsed_time": "0:04:42", "remaining_time": "0:00:00", "throughput": 1936.54, "total_tokens": 547088}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,188 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.928,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.637537956237793,
+      "learning_rate": 4.977212170395598e-05,
+      "loss": 2.5834,
+      "num_input_tokens_seen": 29984,
+      "step": 5
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3269447088241577,
+      "learning_rate": 4.885348141000122e-05,
+      "loss": 2.0249,
+      "num_input_tokens_seen": 60896,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.684715211391449,
+      "learning_rate": 4.725596127020879e-05,
+      "loss": 1.6448,
+      "num_input_tokens_seen": 91008,
+      "step": 15
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.44713008403778076,
+      "learning_rate": 4.502502736173462e-05,
+      "loss": 1.5754,
+      "num_input_tokens_seen": 121056,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.31067565083503723,
+      "learning_rate": 4.222417297689217e-05,
+      "loss": 1.5325,
+      "num_input_tokens_seen": 150608,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2663392126560211,
+      "learning_rate": 3.893311157806091e-05,
+      "loss": 1.5399,
+      "num_input_tokens_seen": 179936,
+      "step": 30
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.29055070877075195,
+      "learning_rate": 3.5245508119914687e-05,
+      "loss": 1.4496,
+      "num_input_tokens_seen": 204992,
+      "step": 35
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.2754141688346863,
+      "learning_rate": 3.126631330646802e-05,
+      "loss": 1.4453,
+      "num_input_tokens_seen": 234704,
+      "step": 40
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.23875507712364197,
+      "learning_rate": 2.7108776651076118e-05,
+      "loss": 1.5063,
+      "num_input_tokens_seen": 265392,
+      "step": 45
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.2538706660270691,
+      "learning_rate": 2.2891223348923884e-05,
+      "loss": 1.523,
+      "num_input_tokens_seen": 296416,
+      "step": 50
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.25537464022636414,
+      "learning_rate": 1.8733686693531985e-05,
+      "loss": 1.439,
+      "num_input_tokens_seen": 327520,
+      "step": 55
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.27788516879081726,
+      "learning_rate": 1.475449188008532e-05,
+      "loss": 1.4884,
+      "num_input_tokens_seen": 357648,
+      "step": 60
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.2592379152774811,
+      "learning_rate": 1.1066888421939093e-05,
+      "loss": 1.5448,
+      "num_input_tokens_seen": 379152,
+      "step": 65
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.23788605630397797,
+      "learning_rate": 7.775827023107835e-06,
+      "loss": 1.4931,
+      "num_input_tokens_seen": 412208,
+      "step": 70
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 0.28915899991989136,
+      "learning_rate": 4.9749726382653905e-06,
+      "loss": 1.4863,
+      "num_input_tokens_seen": 439808,
+      "step": 75
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.2782565951347351,
+      "learning_rate": 2.7440387297912123e-06,
+      "loss": 1.4528,
+      "num_input_tokens_seen": 470048,
+      "step": 80
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 0.3000349700450897,
+      "learning_rate": 1.1465185899987797e-06,
+      "loss": 1.3916,
+      "num_input_tokens_seen": 499456,
+      "step": 85
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.24277131259441376,
+      "learning_rate": 2.27878296044029e-07,
+      "loss": 1.4927,
+      "num_input_tokens_seen": 531136,
+      "step": 90
+    },
+    {
+      "epoch": 2.928,
+      "num_input_tokens_seen": 547088,
+      "step": 93,
+      "total_flos": 1.1981315796631552e+16,
+      "train_loss": 1.5843523497222571,
+      "train_runtime": 282.8295,
+      "train_samples_per_second": 10.607,
+      "train_steps_per_second": 0.329
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 93,
+  "num_input_tokens_seen": 547088,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1981315796631552e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1eea7c59190af26a5b0784b7e06faa36ec1a790afd67a8f8488ad0b50262870b
+size 5752

training_args.yaml ADDED Viewed

	@@ -0,0 +1,36 @@

+bf16: true
+cutoff_len: 2048
+dataset: alpaca_zh_demo
+dataset_dir: LLaMA-Factory/data/
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen3-4B
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen3-4B-Instruct/lora/train_2025-05-18-16-33-56
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+swanlab_mode: cloud
+swanlab_project: llamafactory
+template: qwen3
+trust_remote_code: true
+use_swanlab: true
+warmup_steps: 0

training_loss.png ADDED Viewed

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff