初始化项目，由ModelHub XC社区提供模型

Model: alwaysgood/QWEN3-4B-CPT-stage2 Source: Original Platform
2026-05-01 18:53:17 +08:00
commit 3cd946cc4c
27 changed files with 10877 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,38 @@
+*.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
+checkpoint-90/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,59 @@
+---
+base_model: alwaysgood/QWEN3-4B-CPT
+library_name: transformers
+model_name: checkpoints
+tags:
+- generated_from_trainer
+- unsloth
+- trl
+- sft
+licence: license
+---
+
+# Model Card for checkpoints
+
+This model is a fine-tuned version of [alwaysgood/QWEN3-4B-CPT](https://huggingface.co/alwaysgood/QWEN3-4B-CPT).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hiloong/parallel-cpt/runs/zkww2vcc) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.24.0
+- Transformers: 5.5.3
+- Pytorch: 2.9.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.7952755689620972,
+    "eval_runtime": 1.7545,
+    "eval_samples_per_second": 41.038,
+    "eval_steps_per_second": 5.13,
+    "total_flos": 1.6013083311596544e+16,
+    "train_loss": 1.9445130242241753,
+    "train_runtime": 226.5501,
+    "train_samples_per_second": 15.727,
+    "train_steps_per_second": 0.397
+}
--- a/checkpoint-90/config.json
+++ b/checkpoint-90/config.json
@@ -0,0 +1,74 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_name": "alwaysgood/QWEN3-4B-CPT",
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151669,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.4.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/checkpoint-90/generation_config.json
+++ b/checkpoint-90/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_length": 32768,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151669,
+  "transformers_version": "5.5.3"
+}
--- a/checkpoint-90/model.safetensors
+++ b/checkpoint-90/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2e1f1757f163af8b269039a3ef7167612a4581b9ebe72658607b2037898ca4
+size 8044982080
--- a/checkpoint-90/optimizer.pt
+++ b/checkpoint-90/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245fd3aa0b66ca73cfe4f9d068a4cf0db0b0ad27f7b3ff05bc44e6ede1660c64
+size 14534393422
--- a/checkpoint-90/rng_state.pth
+++ b/checkpoint-90/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645
--- a/checkpoint-90/scheduler.pt
+++ b/checkpoint-90/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4da37e1d2639c6a3c48eabc833153fc8f9bf81ee46a2bc40f3b4e879988db4
+size 1465
--- a/checkpoint-90/tokenizer.json
+++ b/checkpoint-90/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
+size 11422840
--- a/checkpoint-90/tokenizer_config.json
+++ b/checkpoint-90/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/checkpoint-90/trainer_state.json
+++ b/checkpoint-90/trainer_state.json
@@ -0,0 +1,105 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11204481792717087,
+      "grad_norm": 14.0,
+      "learning_rate": 1e-05,
+      "loss": 2.211936187744141,
+      "step": 10
+    },
+    {
+      "epoch": 0.22408963585434175,
+      "grad_norm": 7.21875,
+      "learning_rate": 9.628619846344453e-06,
+      "loss": 1.982374382019043,
+      "step": 20
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 6.75,
+      "learning_rate": 8.569648672789496e-06,
+      "loss": 1.939706802368164,
+      "step": 30
+    },
+    {
+      "epoch": 0.4481792717086835,
+      "grad_norm": 8.0,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 1.9272880554199219,
+      "step": 40
+    },
+    {
+      "epoch": 0.5602240896358543,
+      "grad_norm": 4.5,
+      "learning_rate": 5.096956658859122e-06,
+      "loss": 1.8303054809570312,
+      "step": 50
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.1991113759764493e-06,
+      "loss": 1.8838277816772462,
+      "step": 60
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 4.875,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 1.8752876281738282,
+      "step": 70
+    },
+    {
+      "epoch": 0.896358543417367,
+      "grad_norm": 4.53125,
+      "learning_rate": 4.481852951692672e-07,
+      "loss": 1.8907934188842774,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.25,
+      "learning_rate": 3.760237478849793e-09,
+      "loss": 1.9590974807739259,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7950044870376587,
+      "eval_runtime": 4.0343,
+      "eval_samples_per_second": 17.847,
+      "eval_steps_per_second": 2.231,
+      "step": 90
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6013083311596544e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-90/training_args.bin
+++ b/checkpoint-90/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a665cf825105cd5773c40316561897beba1d0ede4c24ba1bf17b1b2984ae2d
+size 5777
--- a/config.json
+++ b/config.json
@@ -0,0 +1,74 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_name": "alwaysgood/QWEN3-4B-CPT",
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151669,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.3",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.4.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/eval/checkpoints/cpt/homeunsloth__scp_stage2_pdartifactscpt_parallel_full_96gb_alwaysgood_qwen3_4b_cpt__checkpoints/results_2026-04-13T07-05-52.814598.json
+++ b/eval/checkpoints/cpt/homeunsloth__scp_stage2_pdartifactscpt_parallel_full_96gb_alwaysgood_qwen3_4b_cpt__checkpoints/results_2026-04-13T07-05-52.814598.json
--- a/eval/checkpoints/cpt/stdout.txt
+++ b/eval/checkpoints/cpt/stdout.txt
--- a/eval/summary.json
+++ b/eval/summary.json
@@ -0,0 +1,8 @@
+[
+  {
+    "label": "final",
+    "ppl": 6.266658710713712,
+    "base_ppl": 9.347266743308177,
+    "path": "/home/unsloth/scp_stage2_pd/artifacts/cpt_parallel_full_96gb_alwaysgood_qwen3_4b_cpt/checkpoints"
+  }
+]
--- a/eval_results.json
+++ b/eval_results.json
@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.7952755689620972,
+    "eval_runtime": 1.7545,
+    "eval_samples_per_second": 41.038,
+    "eval_steps_per_second": 5.13
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_length": 32768,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151669,
+  "transformers_version": "5.5.3"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2e1f1757f163af8b269039a3ef7167612a4581b9ebe72658607b2037898ca4
+size 8044982080
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
+size 11422840
--- a/tokenizer/tokenizer.json
+++ b/tokenizer/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
+size 11422840
--- a/tokenizer/tokenizer_config.json
+++ b/tokenizer/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.6013083311596544e+16,
+    "train_loss": 1.9445130242241753,
+    "train_runtime": 226.5501,
+    "train_samples_per_second": 15.727,
+    "train_steps_per_second": 0.397
+}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11204481792717087,
+      "grad_norm": 14.0,
+      "learning_rate": 1e-05,
+      "loss": 2.211936187744141,
+      "step": 10
+    },
+    {
+      "epoch": 0.22408963585434175,
+      "grad_norm": 7.21875,
+      "learning_rate": 9.628619846344453e-06,
+      "loss": 1.982374382019043,
+      "step": 20
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 6.75,
+      "learning_rate": 8.569648672789496e-06,
+      "loss": 1.939706802368164,
+      "step": 30
+    },
+    {
+      "epoch": 0.4481792717086835,
+      "grad_norm": 8.0,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 1.9272880554199219,
+      "step": 40
+    },
+    {
+      "epoch": 0.5602240896358543,
+      "grad_norm": 4.5,
+      "learning_rate": 5.096956658859122e-06,
+      "loss": 1.8303054809570312,
+      "step": 50
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.1991113759764493e-06,
+      "loss": 1.8838277816772462,
+      "step": 60
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 4.875,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 1.8752876281738282,
+      "step": 70
+    },
+    {
+      "epoch": 0.896358543417367,
+      "grad_norm": 4.53125,
+      "learning_rate": 4.481852951692672e-07,
+      "loss": 1.8907934188842774,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 26.25,
+      "learning_rate": 3.760237478849793e-09,
+      "loss": 1.9590974807739259,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.7950044870376587,
+      "eval_runtime": 4.0343,
+      "eval_samples_per_second": 17.847,
+      "eval_steps_per_second": 2.231,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "step": 90,
+      "total_flos": 1.6013083311596544e+16,
+      "train_loss": 1.9445130242241753,
+      "train_runtime": 226.5501,
+      "train_samples_per_second": 15.727,
+      "train_steps_per_second": 0.397
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6013083311596544e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a665cf825105cd5773c40316561897beba1d0ede4c24ba1bf17b1b2984ae2d
+size 5777