初始化项目，由ModelHub XC社区提供模型

Model: infiniV/ml-intern-smoke-test
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 +1,58 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M
+library_name: transformers
+model_name: ml-intern-smoke-test
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for ml-intern-smoke-test
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M).
+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="infiniV/ml-intern-smoke-test", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.2.0
+- Transformers: 5.6.2
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.6.2"
+}

last-checkpoint/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.2",
+  "use_cache": false,
+  "vocab_size": 49152
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.6.2"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46449eca4f765a9ea030700fe2088d993e5c32a265f8954379b815e814f56b4d
+size 538090408

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69a1ae1e89a6a95c4250947267c2db31aac42cc65aa816e0ee3734cfd9e5eb1
+size 1076349050

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11c2ec697a3b8b5a4895af88c59dbba480386a7d5b8df6ae55e6659177ce0be4
+size 988

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a36d45a540b06d003e6e4989b2d794c797e01ca5c38de986fb353c8781098149
+size 1064

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,284 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4705882352941178,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 3.6089425086975098,
+      "epoch": 0.058823529411764705,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 6.292151927947998,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 15.0,
+      "step": 1
+    },
+    {
+      "entropy": 5.715427875518799,
+      "epoch": 0.11764705882352941,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 6.3516693115234375,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 22.0,
+      "step": 2
+    },
+    {
+      "entropy": 6.061905860900879,
+      "epoch": 0.17647058823529413,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 4.695749282836914,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 29.0,
+      "step": 3
+    },
+    {
+      "entropy": 5.138950824737549,
+      "epoch": 0.23529411764705882,
+      "grad_norm": 34.225440979003906,
+      "learning_rate": 0.0,
+      "loss": 4.924757957458496,
+      "mean_token_accuracy": 0.375,
+      "num_tokens": 41.0,
+      "step": 4
+    },
+    {
+      "entropy": 5.107641220092773,
+      "epoch": 0.29411764705882354,
+      "grad_norm": Infinity,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 4.769550800323486,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 47.0,
+      "step": 5
+    },
+    {
+      "entropy": 4.351223945617676,
+      "epoch": 0.35294117647058826,
+      "grad_norm": 26.4381046295166,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.740773916244507,
+      "mean_token_accuracy": 0.4285714328289032,
+      "num_tokens": 62.0,
+      "step": 6
+    },
+    {
+      "entropy": 4.605663299560547,
+      "epoch": 0.4117647058823529,
+      "grad_norm": 44.312320709228516,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 4.73244571685791,
+      "mean_token_accuracy": 0.25,
+      "num_tokens": 70.0,
+      "step": 7
+    },
+    {
+      "entropy": 4.652010440826416,
+      "epoch": 0.47058823529411764,
+      "grad_norm": 29.16073989868164,
+      "learning_rate": 1.2e-05,
+      "loss": 3.551349639892578,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 83.0,
+      "step": 8
+    },
+    {
+      "entropy": 3.92993426322937,
+      "epoch": 0.5294117647058824,
+      "grad_norm": 24.797420501708984,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.086703300476074,
+      "mean_token_accuracy": 0.5454545617103577,
+      "num_tokens": 101.0,
+      "step": 9
+    },
+    {
+      "entropy": 4.687472343444824,
+      "epoch": 0.5882352941176471,
+      "grad_norm": 65.40557098388672,
+      "learning_rate": 2e-05,
+      "loss": 6.584832668304443,
+      "mean_token_accuracy": 0.0,
+      "num_tokens": 106.0,
+      "step": 10
+    },
+    {
+      "entropy": 5.460619926452637,
+      "epoch": 0.6470588235294118,
+      "grad_norm": 62.57985305786133,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 5.282391548156738,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 111.0,
+      "step": 11
+    },
+    {
+      "entropy": 5.458609580993652,
+      "epoch": 0.7058823529411765,
+      "grad_norm": 47.68376922607422,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 3.4104318618774414,
+      "mean_token_accuracy": 0.5,
+      "num_tokens": 118.0,
+      "step": 12
+    },
+    {
+      "entropy": 5.297245979309082,
+      "epoch": 0.7647058823529411,
+      "grad_norm": 27.625783920288086,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 2.5839743614196777,
+      "mean_token_accuracy": 0.6000000238418579,
+      "num_tokens": 126.0,
+      "step": 13
+    },
+    {
+      "entropy": 4.2264180183410645,
+      "epoch": 0.8235294117647058,
+      "grad_norm": 21.131492614746094,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 2.5414154529571533,
+      "mean_token_accuracy": 0.5714285969734192,
+      "num_tokens": 138.0,
+      "step": 14
+    },
+    {
+      "entropy": 4.7774658203125,
+      "epoch": 0.8823529411764706,
+      "grad_norm": 40.83763885498047,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 2.8697211742401123,
+      "mean_token_accuracy": 0.4000000059604645,
+      "num_tokens": 145.0,
+      "step": 15
+    },
+    {
+      "entropy": 5.260831832885742,
+      "epoch": 0.9411764705882353,
+      "grad_norm": 40.107913970947266,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 2.11948561668396,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 153.0,
+      "step": 16
+    },
+    {
+      "entropy": 5.279318332672119,
+      "epoch": 1.0,
+      "grad_norm": 34.499481201171875,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 2.028179883956909,
+      "mean_token_accuracy": 0.5,
+      "num_tokens": 161.0,
+      "step": 17
+    },
+    {
+      "entropy": 3.6013762950897217,
+      "epoch": 1.0588235294117647,
+      "grad_norm": 45.223697662353516,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 4.955894470214844,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 176.0,
+      "step": 18
+    },
+    {
+      "entropy": 4.529469966888428,
+      "epoch": 1.1176470588235294,
+      "grad_norm": 30.39960479736328,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.4438493251800537,
+      "mean_token_accuracy": 0.6000000238418579,
+      "num_tokens": 184.0,
+      "step": 19
+    },
+    {
+      "entropy": 3.973909378051758,
+      "epoch": 1.1764705882352942,
+      "grad_norm": 18.265600204467773,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.7491637468338013,
+      "mean_token_accuracy": 0.7142857313156128,
+      "num_tokens": 196.0,
+      "step": 20
+    },
+    {
+      "entropy": 4.81941556930542,
+      "epoch": 1.2352941176470589,
+      "grad_norm": 37.519798278808594,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 3.381870985031128,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 202.0,
+      "step": 21
+    },
+    {
+      "entropy": 4.61383056640625,
+      "epoch": 1.2941176470588236,
+      "grad_norm": 24.117401123046875,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.9651630520820618,
+      "mean_token_accuracy": 0.75,
+      "num_tokens": 210.0,
+      "step": 22
+    },
+    {
+      "entropy": 4.4701128005981445,
+      "epoch": 1.3529411764705883,
+      "grad_norm": 28.767288208007812,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.8833061456680298,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 217.0,
+      "step": 23
+    },
+    {
+      "entropy": 4.853976726531982,
+      "epoch": 1.4117647058823528,
+      "grad_norm": 41.10981369018555,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 3.586022138595581,
+      "mean_token_accuracy": 0.3333333432674408,
+      "num_tokens": 222.0,
+      "step": 24
+    },
+    {
+      "entropy": 4.533289909362793,
+      "epoch": 1.4705882352941178,
+      "grad_norm": Infinity,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.87251877784729,
+      "mean_token_accuracy": 0.5,
+      "num_tokens": 229.0,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 145923548544.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c5333d0f38134cb6765a79bd8460d792c18fea15a8621e114e7d25c2deabce
+size 5368

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46449eca4f765a9ea030700fe2088d993e5c32a265f8954379b815e814f56b4d
+size 538090408

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c5333d0f38134cb6765a79bd8460d792c18fea15a8621e114e7d25c2deabce
+size 5368