初始化项目，由ModelHub XC社区提供模型

Model: trl-lib/qwen1.5-1.8b-sft
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,67 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/deita-6k-v0-sft
+model-index:
+- name: qwen-1.5-1.8b-sft-v0.0
+  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. -->
+
+# qwen-1.5-1.8b-sft-v0.0
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the HuggingFaceH4/deita-6k-v0-sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0886
+
+## 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-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0963        | 1.0   | 237  | 1.0788          |
+| 0.9779        | 2.0   | 474  | 1.0728          |
+| 0.8734        | 3.0   | 711  | 1.0886          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0886437892913818,
+    "eval_runtime": 4.9902,
+    "eval_samples": 300,
+    "eval_samples_per_second": 295.379,
+    "eval_steps_per_second": 4.809,
+    "perplexity": 2.970243064281644,
+    "train_loss": 0.9885472514458347,
+    "train_runtime": 1164.5291,
+    "train_samples": 5700,
+    "train_samples_per_second": 77.885,
+    "train_steps_per_second": 0.611
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151648
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.0886437892913818,
+    "eval_runtime": 4.9902,
+    "eval_samples": 300,
+    "eval_samples_per_second": 295.379,
+    "eval_steps_per_second": 4.809,
+    "perplexity": 2.970243064281644
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0528c447ff8ef58d7e4b75f6dffdc118c7e6265f71cba9d51f5f82568116307
+size 3671331400

runs/Mar13_15-55-26_ip-26-0-167-175/events.out.tfevents.1710345414.ip-26-0-167-175.47301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcbb00e9e4a6f8a9cff3001a39152ae4220f2a3ba65b4ed36428d04b9a238ae
+size 5110

runs/Mar13_16-10-47_ip-26-0-167-175/events.out.tfevents.1710346278.ip-26-0-167-175.49847.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167ac8274f99fda2d60119233034cad0bbe44b2aeb1f55df903356b9394d257d
+size 5110

runs/Mar13_16-17-22_ip-26-0-167-175/events.out.tfevents.1710346695.ip-26-0-167-175.50976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a971f7d2d93ef149c56b264a95b1fe506e03c9a211259843b5e59aa52e9921
+size 5317

runs/Mar13_16-33-16_ip-26-0-167-175/events.out.tfevents.1710347631.ip-26-0-167-175.54812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becc4d3160a74d30ac97faae40040b5977547de2d0e8779c770127e2151d21df
+size 5105

runs/Mar13_16-35-17_ip-26-0-167-175/events.out.tfevents.1710347746.ip-26-0-167-175.55966.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b941c9b2a5ddf02dc52346adf9c57b72e773e694d4cc30cb6046a3805a3d698
+size 5519

runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710354517.ip-26-0-166-244.384933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c12ca5f508bfce039e6123ea4eb46789c5bb749ec484f8831905745ee75c78c
+size 36317

runs/Mar13_18-28-03_ip-26-0-166-244/events.out.tfevents.1710355686.ip-26-0-166-244.384933.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad5e4f6ab8854be1b807b29c827115dab39773081d73145e925d633d9817241
+size 359

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9885472514458347,
+    "train_runtime": 1164.5291,
+    "train_samples": 5700,
+    "train_samples_per_second": 77.885,
+    "train_steps_per_second": 0.611
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa6275ea3a7ab0b52842a3362c23f21aec0ad272d596daabddb4e6c8543f247
+size 6520