初始化项目，由ModelHub XC社区提供模型

Model: rbelanec/train_qqp_42_1779207273
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_qqp_42_1779207273
+  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_qqp_42_1779207273
+
+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 qqp dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1128
+- Num Input Tokens Seen: 137941664
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-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 |
+|:-------------:|:------:|:------:|:---------------:|:-----------------:|
+| 0.1388        | 0.2500 | 10234  | 0.1504          | 6910656           |
+| 0.1021        | 0.5000 | 20468  | 0.1128          | 13780928          |
+| 0.0459        | 0.7501 | 30702  | 0.1215          | 20680640          |
+| 0.1214        | 1.0001 | 40936  | 0.1224          | 27591776          |
+| 0.1395        | 1.2501 | 51170  | 0.1528          | 34492320          |
+| 0.0425        | 1.5001 | 61404  | 0.1524          | 41393504          |
+| 0.1097        | 1.7501 | 71638  | 0.1231          | 48287456          |
+| 0.0019        | 2.0001 | 81872  | 0.1237          | 55178600          |
+| 0.0001        | 2.2502 | 92106  | 0.2041          | 62093992          |
+| 0.0236        | 2.5002 | 102340 | 0.1835          | 68988456          |
+| 0.0008        | 2.7502 | 112574 | 0.2039          | 75874280          |
+| 0.0003        | 3.0002 | 122808 | 0.1936          | 82772304          |
+| 0.0           | 3.2502 | 133042 | 0.2610          | 89675984          |
+| 0.0332        | 3.5003 | 143276 | 0.2494          | 96560720          |
+| 0.0           | 3.7503 | 153510 | 0.2414          | 103465808         |
+| 0.0           | 4.0003 | 163744 | 0.2473          | 110357352         |
+| 0.0           | 4.2503 | 173978 | 0.3375          | 117230952         |
+| 0.0           | 4.5003 | 184212 | 0.3128          | 124100264         |
+| 0.0727        | 4.7503 | 194446 | 0.3178          | 131030440         |
+
+
+### 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": 0.11281616985797882,
+    "eval_runtime": 47.5121,
+    "eval_samples_per_second": 765.805,
+    "eval_steps_per_second": 95.744,
+    "num_input_tokens_seen": 137941664,
+    "total_flos": 8.054243640264622e+17,
+    "train_loss": 0.052412337061547826,
+    "train_runtime": 15894.9677,
+    "train_samples_per_second": 103.008,
+    "train_steps_per_second": 12.876
+}

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": 0.11281616985797882,
+    "eval_runtime": 47.5121,
+    "eval_samples_per_second": 765.805,
+    "eval_steps_per_second": 95.744,
+    "num_input_tokens_seen": 137941664
+}

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 sha256:8df177d2c3f3f41781538d137ebac602187bd2c359a020c613016d434c4fa7de
+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|>"
+}

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: qqp
+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_qqp_42_1779207273
+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: 2.0e-6
+num_train_epochs: 5
+weight_decay: 1.0e-2
+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_qqp_42_1779207273
+
+### 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": 137941664,
+    "total_flos": 8.054243640264622e+17,
+    "train_loss": 0.052412337061547826,
+    "train_runtime": 15894.9677,
+    "train_samples_per_second": 103.008,
+    "train_steps_per_second": 12.876
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a36b4a7a224ca5cf10921ad2f03cce32ed0aef96de468fb7ec1842fdbbbb8f
+size 6289