初始化项目，由ModelHub XC社区提供模型

Model: rbelanec/train_sst2_42_1779194533
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_sst2_42_1779194533
+  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_sst2_42_1779194533
+
+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 sst2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0970
+- Num Input Tokens Seen: 18647328
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:-----------------:|
+| 0.4074        | 0.2501 | 1895  | 0.1552          | 930944            |
+| 0.3196        | 0.5002 | 3790  | 0.1577          | 1864128           |
+| 0.0028        | 0.7503 | 5685  | 0.0970          | 2790656           |
+| 0.0006        | 1.0004 | 7580  | 0.1143          | 3726464           |
+| 0.1179        | 1.2505 | 9475  | 0.1166          | 4658240           |
+| 0.1073        | 1.5006 | 11370 | 0.1257          | 5591680           |
+| 0.342         | 1.7507 | 13265 | 0.1152          | 6528448           |
+| 0.0004        | 2.0008 | 15160 | 0.1182          | 7463024           |
+| 0.0556        | 2.2509 | 17055 | 0.1500          | 8395632           |
+| 0.0962        | 2.5010 | 18950 | 0.1142          | 9326256           |
+| 0.0429        | 2.7511 | 20845 | 0.1603          | 10259504          |
+| 0.0352        | 3.0012 | 22740 | 0.1483          | 11196096          |
+| 0.0352        | 3.2513 | 24635 | 0.1809          | 12128448          |
+| 0.0           | 3.5014 | 26530 | 0.1809          | 13069824          |
+| 0.0243        | 3.7515 | 28425 | 0.2036          | 13996672          |
+| 0.0002        | 4.0016 | 30320 | 0.1816          | 14924944          |
+| 0.0087        | 4.2517 | 32215 | 0.2473          | 15859920          |
+| 0.0           | 4.5018 | 34110 | 0.2764          | 16790288          |
+| 0.0           | 4.7519 | 36005 | 0.2836          | 17721744          |
+
+
+### 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": 0.09698151051998138,
+    "eval_runtime": 8.0011,
+    "eval_samples_per_second": 841.76,
+    "eval_steps_per_second": 105.236,
+    "num_input_tokens_seen": 18647328,
+    "total_flos": 1.0887944845433242e+17,
+    "train_loss": 0.05778941776209685,
+    "train_runtime": 3377.0005,
+    "train_samples_per_second": 89.745,
+    "train_steps_per_second": 11.219
+}

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": 0.09698151051998138,
+    "eval_runtime": 8.0011,
+    "eval_samples_per_second": 841.76,
+    "eval_steps_per_second": 105.236,
+    "num_input_tokens_seen": 18647328
+}

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:dc4bbd3b9a180d790332e718e4fe84f5372702d00714f50a6950ba183895fb7f
+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: sst2
+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_sst2_42_1779194533
+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_sst2_42_1779194533
+
+### 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": 18647328,
+    "total_flos": 1.0887944845433242e+17,
+    "train_loss": 0.05778941776209685,
+    "train_runtime": 3377.0005,
+    "train_samples_per_second": 89.745,
+    "train_steps_per_second": 11.219
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66b58030769e17f159c6e254a4d89cea315a8135b8705c5c225420f0e0a8ead
+size 6289