初始化项目，由ModelHub XC社区提供模型

Model: Josephgflowers/TinyLlama-Cinder-Nerd-Parse-Address-Test
Source: Original Platform

.gitattributes

@@ -0,0 +1 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+base_model: Josephgflowers/TinyLlama-Cinder-Agent-v1
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-Cinder-Nerd-Parse-Address-Test
+  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. -->
+
+# TinyLlama-Cinder-Nerd-Parse-Address-Test
+
+This model is a fine-tuned version of [Josephgflowers/TinyLlama-Cinder-Agent-v1](https://huggingface.co/Josephgflowers/TinyLlama-Cinder-Agent-v1) on an unknown 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: 5e-05
+- train_batch_size: 12
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.5754690641723392e+17,
+    "train_loss": 0.6758780561303726,
+    "train_runtime": 23583.4151,
+    "train_samples": 20260,
+    "train_samples_per_second": 0.859,
+    "train_steps_per_second": 0.072
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Josephgflowers/TinyLlama-Cinder-Agent-v1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b36dd22118828fc6d8ab5cf875f44a6bb5c1ab0fa2f2cc25df5e3c39010190
+size 4400216536

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.5754690641723392e+17,
+    "train_loss": 0.6758780561303726,
+    "train_runtime": 23583.4151,
+    "train_samples": 20260,
+    "train_samples_per_second": 0.859,
+    "train_steps_per_second": 0.072
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05920663114268798,
+      "grad_norm": 58774.96875,
+      "learning_rate": 4.70396684428656e-05,
+      "loss": 0.767,
+      "step": 100
+    },
+    {
+      "epoch": 0.11841326228537596,
+      "grad_norm": 84537.3046875,
+      "learning_rate": 4.40793368857312e-05,
+      "loss": 0.7032,
+      "step": 200
+    },
+    {
+      "epoch": 0.17761989342806395,
+      "grad_norm": 62910.03515625,
+      "learning_rate": 4.111900532859681e-05,
+      "loss": 0.712,
+      "step": 300
+    },
+    {
+      "epoch": 0.23682652457075193,
+      "grad_norm": 60269.59765625,
+      "learning_rate": 3.8158673771462406e-05,
+      "loss": 0.6845,
+      "step": 400
+    },
+    {
+      "epoch": 0.2960331557134399,
+      "grad_norm": 48000.21875,
+      "learning_rate": 3.5198342214328006e-05,
+      "loss": 0.6896,
+      "step": 500
+    },
+    {
+      "epoch": 0.3552397868561279,
+      "grad_norm": 69728.296875,
+      "learning_rate": 3.2238010657193605e-05,
+      "loss": 0.6967,
+      "step": 600
+    },
+    {
+      "epoch": 0.4144464179988159,
+      "grad_norm": 58644.7578125,
+      "learning_rate": 2.9277679100059208e-05,
+      "loss": 0.6894,
+      "step": 700
+    },
+    {
+      "epoch": 0.47365304914150386,
+      "grad_norm": 58962.94921875,
+      "learning_rate": 2.6317347542924807e-05,
+      "loss": 0.6831,
+      "step": 800
+    },
+    {
+      "epoch": 0.5328596802841918,
+      "grad_norm": 59192.22265625,
+      "learning_rate": 2.335701598579041e-05,
+      "loss": 0.6745,
+      "step": 900
+    },
+    {
+      "epoch": 0.5920663114268798,
+      "grad_norm": 58689.921875,
+      "learning_rate": 2.039668442865601e-05,
+      "loss": 0.6616,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6512729425695678,
+      "grad_norm": 51845.45703125,
+      "learning_rate": 1.743635287152161e-05,
+      "loss": 0.6563,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7104795737122558,
+      "grad_norm": 55519.21484375,
+      "learning_rate": 1.4476021314387211e-05,
+      "loss": 0.6345,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7696862048549438,
+      "grad_norm": 60519.421875,
+      "learning_rate": 1.1515689757252812e-05,
+      "loss": 0.6346,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8288928359976317,
+      "grad_norm": 59432.31640625,
+      "learning_rate": 8.555358200118415e-06,
+      "loss": 0.6711,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8880994671403197,
+      "grad_norm": 58101.1015625,
+      "learning_rate": 5.595026642984015e-06,
+      "loss": 0.6353,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9473060982830077,
+      "grad_norm": 62020.96875,
+      "learning_rate": 2.634695085849615e-06,
+      "loss": 0.6437,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "step": 1689,
+      "total_flos": 2.5754690641723392e+17,
+      "train_loss": 0.6758780561303726,
+      "train_runtime": 23583.4151,
+      "train_samples_per_second": 0.859,
+      "train_steps_per_second": 0.072
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1689,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5754690641723392e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}