初始化项目，由ModelHub XC社区提供模型

Model: anwgpt/anwllama-1-base
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 +1,48 @@
+---
+license: mit
+language:
+- en
+library_name: transformers
+---
+
+Step	Training Loss
+
+100	9.552530
+
+200	7.434567
+
+300	6.307720
+
+400	5.781603
+
+500	5.459788
+
+600	5.196931
+
+700	4.950012
+
+800	4.757678
+
+900	4.617741
+
+1000	4.509363
+
+1100	4.377576
+
+1200	4.273639
+
+1300	4.202172
+
+1400	4.124585
+
+1500	4.049357
+
+1600	3.946516
+
+1700	3.853138
+
+1800	3.818091
+
+1900	3.790880
+
+2000	3.793084

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-1800/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-1800/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

checkpoint-1800/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

checkpoint-1800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac0de32adc69c63979250a63fbae5c88d6d97e8df5d61075f46341be32be61e
+size 136085144

checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c91fcd6f902fdd0f1ebfa0a767cb08120515694210af17fc1e83b566ea0b5bfd
+size 272206475

checkpoint-1800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-1800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0408efb69cab96d5bab9a1aaf44cedbc9fc8d34f4cef378d81605e5c026d5c
+size 1383

checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6f3854bd163d3bb2c6f034532a0e4b87c6a97b4d340d6ea37fc6f62698bc51
+size 1465

checkpoint-1800/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1800/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.15168,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.6644006967544556,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 9.552529907226562,
+      "step": 100
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.862553060054779,
+      "learning_rate": 9.95e-05,
+      "loss": 7.434567260742187,
+      "step": 200
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.9680566191673279,
+      "learning_rate": 0.0001495,
+      "loss": 6.307720336914063,
+      "step": 300
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.0872560739517212,
+      "learning_rate": 0.00019950000000000002,
+      "loss": 5.781602783203125,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8385273814201355,
+      "learning_rate": 0.0002495,
+      "loss": 5.45978759765625,
+      "step": 500
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.9646134972572327,
+      "learning_rate": 0.0002995,
+      "loss": 5.19693115234375,
+      "step": 600
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.9179049730300903,
+      "learning_rate": 0.0003495,
+      "loss": 4.9500119018554685,
+      "step": 700
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.8189147710800171,
+      "learning_rate": 0.0003995,
+      "loss": 4.757677612304687,
+      "step": 800
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7599812746047974,
+      "learning_rate": 0.00044950000000000003,
+      "loss": 4.617741394042969,
+      "step": 900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8522061109542847,
+      "learning_rate": 0.0004995,
+      "loss": 4.509363403320313,
+      "step": 1000
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7664839029312134,
+      "learning_rate": 0.00048800565673641917,
+      "loss": 4.377576293945313,
+      "step": 1100
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.7524094581604004,
+      "learning_rate": 0.00045271489520809337,
+      "loss": 4.273638916015625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.7883505821228027,
+      "learning_rate": 0.00039758098733907364,
+      "loss": 4.2021722412109375,
+      "step": 1300
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7538483142852783,
+      "learning_rate": 0.0003280008241721038,
+      "loss": 4.124585266113281,
+      "step": 1400
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7969692945480347,
+      "learning_rate": 0.0002507853968714699,
+      "loss": 4.049356994628906,
+      "step": 1500
+    },
+    {
+      "epoch": 1.02368,
+      "grad_norm": 0.7776799201965332,
+      "learning_rate": 0.00017349308945287484,
+      "loss": 3.9465155029296874,
+      "step": 1600
+    },
+    {
+      "epoch": 1.08768,
+      "grad_norm": 0.7725834846496582,
+      "learning_rate": 0.00010368981149362256,
+      "loss": 3.853138427734375,
+      "step": 1700
+    },
+    {
+      "epoch": 1.15168,
+      "grad_norm": 0.7704042792320251,
+      "learning_rate": 4.820839418839992e-05,
+      "loss": 3.818090515136719,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7688323149594624.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0528f70548ba46e710aedab61d7c6c20d04691c057d452c88650b62820e3f5f2
+size 5137

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-2000/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e80182e73a9bd4b4137b28e5080dc7e42f882035389f673d1a939f9768ef6fc
+size 136085144

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c36f3d3e3071b80bb638658adac5861ac0749b9fe029b7b615b7117055429e
+size 272206475

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+size 1383

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b1bcd4e6631a691be1896233c275cbddc53ad8e411f3810cb45227ae9e6e7d
+size 1465

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.27968,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.064,
+      "grad_norm": 1.6644006967544556,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 9.552529907226562,
+      "step": 100
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.862553060054779,
+      "learning_rate": 9.95e-05,
+      "loss": 7.434567260742187,
+      "step": 200
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.9680566191673279,
+      "learning_rate": 0.0001495,
+      "loss": 6.307720336914063,
+      "step": 300
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.0872560739517212,
+      "learning_rate": 0.00019950000000000002,
+      "loss": 5.781602783203125,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8385273814201355,
+      "learning_rate": 0.0002495,
+      "loss": 5.45978759765625,
+      "step": 500
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.9646134972572327,
+      "learning_rate": 0.0002995,
+      "loss": 5.19693115234375,
+      "step": 600
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.9179049730300903,
+      "learning_rate": 0.0003495,
+      "loss": 4.9500119018554685,
+      "step": 700
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.8189147710800171,
+      "learning_rate": 0.0003995,
+      "loss": 4.757677612304687,
+      "step": 800
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7599812746047974,
+      "learning_rate": 0.00044950000000000003,
+      "loss": 4.617741394042969,
+      "step": 900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8522061109542847,
+      "learning_rate": 0.0004995,
+      "loss": 4.509363403320313,
+      "step": 1000
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7664839029312134,
+      "learning_rate": 0.00048800565673641917,
+      "loss": 4.377576293945313,
+      "step": 1100
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.7524094581604004,
+      "learning_rate": 0.00045271489520809337,
+      "loss": 4.273638916015625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.7883505821228027,
+      "learning_rate": 0.00039758098733907364,
+      "loss": 4.2021722412109375,
+      "step": 1300
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.7538483142852783,
+      "learning_rate": 0.0003280008241721038,
+      "loss": 4.124585266113281,
+      "step": 1400
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.7969692945480347,
+      "learning_rate": 0.0002507853968714699,
+      "loss": 4.049356994628906,
+      "step": 1500
+    },
+    {
+      "epoch": 1.02368,
+      "grad_norm": 0.7776799201965332,
+      "learning_rate": 0.00017349308945287484,
+      "loss": 3.9465155029296874,
+      "step": 1600
+    },
+    {
+      "epoch": 1.08768,
+      "grad_norm": 0.7725834846496582,
+      "learning_rate": 0.00010368981149362256,
+      "loss": 3.853138427734375,
+      "step": 1700
+    },
+    {
+      "epoch": 1.15168,
+      "grad_norm": 0.7704042792320251,
+      "learning_rate": 4.820839418839992e-05,
+      "loss": 3.818090515136719,
+      "step": 1800
+    },
+    {
+      "epoch": 1.21568,
+      "grad_norm": 0.7322491407394409,
+      "learning_rate": 1.2479745224807049e-05,
+      "loss": 3.7908795166015623,
+      "step": 1900
+    },
+    {
+      "epoch": 1.27968,
+      "grad_norm": 0.7623891830444336,
+      "learning_rate": 1.2336995354467196e-09,
+      "loss": 3.7930838012695314,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 8542818637185024.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0528f70548ba46e710aedab61d7c6c20d04691c057d452c88650b62820e3f5f2
+size 5137

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e80182e73a9bd4b4137b28e5080dc7e42f882035389f673d1a939f9768ef6fc
+size 136085144

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}