初始化项目，由ModelHub XC社区提供模型

Model: rbelanec/train_boolq_42_1776331558
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B-Instruct
+tags:
+- peft-factory
+- full
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: train_boolq_42_1776331558
+  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_boolq_42_1776331558
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the boolq dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1885
+- Num Input Tokens Seen: 12333600
+
+## 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-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |
+|:-------------:|:------:|:----:|:---------------:|:-----------------:|
+| 0.2277        | 0.2507 | 266  | 0.2505          | 618432            |
+| 0.2193        | 0.5014 | 532  | 0.3166          | 1225408           |
+| 0.2554        | 0.7521 | 798  | 0.2179          | 1851072           |
+| 0.3676        | 1.0028 | 1064 | 0.1885          | 2475808           |
+| 0.165         | 1.2535 | 1330 | 0.4608          | 3091552           |
+| 0.2207        | 1.5042 | 1596 | 0.3545          | 3699104           |
+| 0.1138        | 1.7549 | 1862 | 0.3500          | 4324256           |
+| 0.0762        | 2.0057 | 2128 | 0.3345          | 4940992           |
+| 0.0898        | 2.2564 | 2394 | 0.4647          | 5558144           |
+| 0.0692        | 2.5071 | 2660 | 0.4098          | 6183872           |
+| 0.227         | 2.7578 | 2926 | 0.4303          | 6806208           |
+| 0.0004        | 3.0085 | 3192 | 0.3937          | 7421856           |
+| 0.0           | 3.2592 | 3458 | 0.5191          | 8043744           |
+| 0.0002        | 3.5099 | 3724 | 0.4636          | 8660768           |
+| 0.0           | 3.7606 | 3990 | 0.5201          | 9286304           |
+| 0.0001        | 4.0113 | 4256 | 0.5146          | 9894624           |
+| 0.0782        | 4.2620 | 4522 | 0.5548          | 10512416          |
+| 0.0           | 4.5127 | 4788 | 0.5418          | 11115040          |
+| 0.0           | 4.7634 | 5054 | 0.5422          | 11736672          |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.10.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.21.4

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.18848362565040588,
+    "eval_runtime": 2.7208,
+    "eval_samples_per_second": 346.59,
+    "eval_steps_per_second": 43.37,
+    "num_input_tokens_seen": 12333600,
+    "total_flos": 7.20143693217792e+16,
+    "train_loss": 0.11108403178044919,
+    "train_runtime": 1575.5047,
+    "train_samples_per_second": 26.925,
+    "train_steps_per_second": 3.367
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.18848362565040588,
+    "eval_runtime": 2.7208,
+    "eval_samples_per_second": 346.59,
+    "eval_steps_per_second": 43.37,
+    "num_input_tokens_seen": 12333600
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da06e50263a9fa89db7141d357687cbad06fe618344dc99d66e34eeb5327e36
+size 4943274328

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

train.yaml

@@ -0,0 +1,55 @@
+seed: 42
+
+### model
+model_name_or_path: meta-llama/Llama-3.2-1B-Instruct
+trust_remote_code: true
+flash_attn: auto
+use_cache: false
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+
+### dataset
+dataset: boolq
+template: llama3
+cutoff_len: 2048
+overwrite_cache: true
+preprocessing_num_workers: 4
+dataloader_num_workers: 4
+packing: false
+
+### output
+output_dir: saves_bts_preliminary/base/llama-3.2-1b-instruct/train_boolq_42_1776331558
+logging_steps: 5
+save_steps: 0.05
+overwrite_output_dir: true
+save_only_model: false
+plot_loss: true
+include_num_input_tokens_seen: true
+push_to_hub: true
+push_to_hub_organization: rbelanec
+load_best_model_at_end: true
+save_total_limit: 1
+
+### train
+per_device_train_batch_size: 8
+learning_rate: 5.0e-6
+num_train_epochs: 5
+weight_decay: 1.0e-5
+lr_scheduler_type: cosine
+bf16: true
+ddp_timeout: 180000000
+resume_from_checkpoint: null
+warmup_ratio: 0.1
+optim: adamw_torch
+report_to:
+- wandb
+run_name: base_llama-3.2-1b-instruct_train_boolq_42_1776331558
+
+### eval
+per_device_eval_batch_size: 8
+eval_strategy: steps
+eval_steps: 0.05
+val_size: 0.1

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "num_input_tokens_seen": 12333600,
+    "total_flos": 7.20143693217792e+16,
+    "train_loss": 0.11108403178044919,
+    "train_runtime": 1575.5047,
+    "train_samples_per_second": 26.925,
+    "train_steps_per_second": 3.367
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c48857d0c3d47661e9acd14ef454a027ceefd076c60dfa85538fe6e7c8a6f3c
+size 6289