初始化项目，由ModelHub XC社区提供模型

Model: misterJB/atlas-field-528hz
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 +1,59 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: transformers
+model_name: atlas-field-528hz
+tags:
+- generated_from_trainer
+- trl
+- hf_jobs
+- sft
+licence: license
+---
+
+# Model Card for atlas-field-528hz
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+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="misterJB/atlas-field-528hz", 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: 0.29.1
+- Transformers: 5.3.0
+- Pytorch: 2.8.0
+- 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 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.3.0"
+}

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.3.0"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66178a76e2e538ab6e342d35d4825b54fb08bc7578c7f109ed6078644b924e57
+size 14483498224

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746f096c66d8710446f9de2a6693a158809fc4412c46e38fd8a89be0d932f54f
+size 28967187355

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d816652875af5b096437609afdf7a105e45a5aed127110ed63352bdde6ad2657
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.78125,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5879646396264434,
+      "epoch": 0.0390625,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.828125000000001e-06,
+      "loss": 0.5608741760253906,
+      "mean_token_accuracy": 0.8732133361697197,
+      "num_tokens": 309908.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.09950160900130868,
+      "epoch": 0.078125,
+      "grad_norm": 2.296875,
+      "learning_rate": 7.734375e-06,
+      "loss": 0.08675869941711425,
+      "mean_token_accuracy": 0.9764643028378487,
+      "num_tokens": 618662.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.06861632030457258,
+      "epoch": 0.1171875,
+      "grad_norm": 0.97265625,
+      "learning_rate": 1.1640625000000002e-05,
+      "loss": 0.059808659553527835,
+      "mean_token_accuracy": 0.9829691171646118,
+      "num_tokens": 923343.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.06371763135306537,
+      "epoch": 0.15625,
+      "grad_norm": 1.125,
+      "learning_rate": 1.5546875e-05,
+      "loss": 0.05767580032348633,
+      "mean_token_accuracy": 0.9834094086289406,
+      "num_tokens": 1231860.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.05956988543272018,
+      "epoch": 0.1953125,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.9453125e-05,
+      "loss": 0.052296199798583985,
+      "mean_token_accuracy": 0.9851513150334358,
+      "num_tokens": 1539428.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.06213963699527085,
+      "epoch": 0.234375,
+      "grad_norm": 2.515625,
+      "learning_rate": 1.9626736111111114e-05,
+      "loss": 0.057163243293762205,
+      "mean_token_accuracy": 0.9842589551210403,
+      "num_tokens": 1844184.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.051620940826833245,
+      "epoch": 0.2734375,
+      "grad_norm": 0.6015625,
+      "learning_rate": 1.9192708333333335e-05,
+      "loss": 0.04214866161346435,
+      "mean_token_accuracy": 0.9875012004375457,
+      "num_tokens": 2145404.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.032940625557675955,
+      "epoch": 0.3125,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.8758680555555557e-05,
+      "loss": 0.0279494047164917,
+      "mean_token_accuracy": 0.9905313903093338,
+      "num_tokens": 2454513.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.03187832637690008,
+      "epoch": 0.3515625,
+      "grad_norm": 0.130859375,
+      "learning_rate": 1.8324652777777778e-05,
+      "loss": 0.024850430488586425,
+      "mean_token_accuracy": 0.9914047086238861,
+      "num_tokens": 2763494.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.029858413645997645,
+      "epoch": 0.390625,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.7890625000000003e-05,
+      "loss": 0.022111225128173827,
+      "mean_token_accuracy": 0.9919667416810989,
+      "num_tokens": 3070032.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.032282271897420285,
+      "epoch": 0.4296875,
+      "grad_norm": 0.099609375,
+      "learning_rate": 1.7456597222222224e-05,
+      "loss": 0.024263689517974852,
+      "mean_token_accuracy": 0.9916365548968316,
+      "num_tokens": 3371923.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.02768919712398201,
+      "epoch": 0.46875,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.7022569444444446e-05,
+      "loss": 0.02068368673324585,
+      "mean_token_accuracy": 0.9922330856323243,
+      "num_tokens": 3681052.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.027916706460528077,
+      "epoch": 0.5078125,
+      "grad_norm": 0.146484375,
+      "learning_rate": 1.6588541666666667e-05,
+      "loss": 0.02017390251159668,
+      "mean_token_accuracy": 0.9925840869545937,
+      "num_tokens": 3985154.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.024339500861242414,
+      "epoch": 0.546875,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 1.615451388888889e-05,
+      "loss": 0.017752493619918822,
+      "mean_token_accuracy": 0.992968330681324,
+      "num_tokens": 4294960.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.02500485216733068,
+      "epoch": 0.5859375,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 1.5720486111111114e-05,
+      "loss": 0.018282731771469118,
+      "mean_token_accuracy": 0.9928615567088127,
+      "num_tokens": 4596846.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.023879703185521066,
+      "epoch": 0.625,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.5286458333333335e-05,
+      "loss": 0.017627782821655273,
+      "mean_token_accuracy": 0.9931773543357849,
+      "num_tokens": 4904237.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.02569641772657633,
+      "epoch": 0.6640625,
+      "grad_norm": 0.09765625,
+      "learning_rate": 1.4852430555555556e-05,
+      "loss": 0.01919528007507324,
+      "mean_token_accuracy": 0.9929538157582283,
+      "num_tokens": 5205258.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.02546143492218107,
+      "epoch": 0.703125,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 1.4418402777777778e-05,
+      "loss": 0.018223344087600707,
+      "mean_token_accuracy": 0.9930938303470611,
+      "num_tokens": 5511048.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.023580400524660945,
+      "epoch": 0.7421875,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 1.3984375000000001e-05,
+      "loss": 0.01719343423843384,
+      "mean_token_accuracy": 0.9934566602110863,
+      "num_tokens": 5824149.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.022929171579889954,
+      "epoch": 0.78125,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.3550347222222224e-05,
+      "loss": 0.016624774932861328,
+      "mean_token_accuracy": 0.9935434520244598,
+      "num_tokens": 6133395.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.885719471186084e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f86bcfd098aae8e261cc44af568a1b790f321588e8fdcc26b68725adda0314
+size 5713

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2682691f9fd3d48765059e55f5c195ea1f45c9e5b08d5853dd47c693872025
+size 14483498224

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32b6e6c68062bc966982620c00aa99360eaa667ad24cb44893f2631509ba845
+size 5713