初始化项目，由ModelHub XC社区提供模型

Model: open-sci/sft__ot30k_SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated
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 +1,63 @@
+---
+library_name: transformers
+license: other
+base_model: ali-elganzory/SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+datasets:
+- arrow
+model-index:
+- name: sft__f679a5c592c8dffb__e049b46eacd6b07b194d__smollm2-steps
+  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. -->
+
+# sft__f679a5c592c8dffb__e049b46eacd6b07b194d__smollm2-steps
+
+This model is a fine-tuned version of [ali-elganzory/SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated](https://huggingface.co/ali-elganzory/SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated) on the /gpfs/scratch/ehpc524/ot/hf_hub/datasets/open-thoughts_open_thoughts3-1.2_m_30000_samples/default/0.0.0/f679a5c592c8dffb 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.5.0
+- Pytorch 2.10.0+cu128
+- Datasets 4.8.4
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.49867311120033264,
+    "total_flos": 1367557351931904.0,
+    "train_loss": 1.0911384893985505,
+    "train_runtime": 4706.648,
+    "train_samples_per_second": 31.87,
+    "train_steps_per_second": 0.25,
+    "valid_targets_mean": 13716.8,
+    "valid_targets_min": 3353
+}

chat_template.jinja

@@ -0,0 +1,25 @@
+
+{%- for message in messages -%}
+	{%- if message["role"] == "system" -%}
+		{{- "<|system|>
+" + message["content"] + "
+" -}}
+	{%- elif message["role"] == "user" -%}
+		{{- "<|user|>
+" + message["content"] + "
+" -}}
+	{%- elif message["role"] == "assistant" -%}
+		{%- if not loop.last -%}
+			{{- "<|assistant|>
+" + message["content"] + eos_token + "
+" -}}
+		{%- else -%}
+			{{- "<|assistant|>
+" + message["content"] + eos_token -}}
+		{%- endif -%}
+	{%- endif -%}
+	{%- if loop.last and add_generation_prompt -%}
+		{{- "<|assistant|>
+" -}}
+	{%- endif -%}
+{%- endfor -%}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 49152,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 49152,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 2.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 130000,
+    "rope_type": "yarn"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 49216
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    49152
+  ],
+  "pad_token_id": 49152,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e7a5710ec29dc3a5c03b85084eb0505de9156562c63a3160817632c6461ac2
+size 3423040096

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "f679a5c592c8dffb",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "/gpfs/scratch/ehpc524/ot/hf_hub/models--ali-elganzory--SmolLM2-1.7B-16k-SFT-Tulu3-decontaminated/snapshots/e049b46eacd6b07b194dd10dd55afa64f18e3a7d/",
+  "dataset_name": "/gpfs/scratch/ehpc524/ot/hf_hub/datasets/open-thoughts_open_thoughts3-1.2_m_30000_samples/default/0.0.0/f679a5c592c8dffb",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/mlfoundations-dev/sft__f679a5c592c8dffb__e049b46eacd6b07b194d__smollm2-steps/blob/main/config.json",
+  "wandb_link": null,
+  "traces_location_s3": null
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_turn>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "<|im_end|>": "<|im_end|>"
+  },
+  "is_local": true,
+  "model_max_length": 16384,
+  "pad_token": "<end_of_turn>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.49867311120033264,
+    "total_flos": 1367557351931904.0,
+    "train_loss": 1.0911384893985505,
+    "train_runtime": 4706.648,
+    "train_samples_per_second": 31.87,
+    "train_steps_per_second": 0.25,
+    "valid_targets_mean": 13716.8,
+    "valid_targets_min": 3353
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c2cb27c66aa56fb17b2d5967602a5616b9123164304222c557caa9a76b777ee
+size 7953