初始化项目，由ModelHub XC社区提供模型

Model: anwgpt/anwllama-1-chat
Source: Original Platform

checkpoint-1400/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-1400/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-1400/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-1400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8573c7f451183d31347b50f28da0b0e1f1f24cd512d0561474b8fd1c90655a
+size 136085144

checkpoint-1400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c2d9492fcb75ba4eab2dfc413c7701bbb667f265d0d4fcde2d8ca6226cc6bb
+size 272206475

checkpoint-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+size 14645

checkpoint-1400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3b03c8c40e45be48b5956b82e1abb2c1ec5641f4fc77e6fdec0942a77964500
+size 1383

checkpoint-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684ed66f1386fce5d7384ea503951affbcb70128a88cfdbeea8ec88fdea72041
+size 1465

checkpoint-1400/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-1400/trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.58112,
+  "eval_steps": 500,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.265313982963562,
+      "learning_rate": 2.4750000000000002e-05,
+      "loss": 6.332213745117188,
+      "step": 100
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.302055835723877,
+      "learning_rate": 4.975e-05,
+      "loss": 4.7161932373046875,
+      "step": 200
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.1382993459701538,
+      "learning_rate": 7.475e-05,
+      "loss": 4.228371276855468,
+      "step": 300
+    },
+    {
+      "epoch": 1.02304,
+      "grad_norm": 1.2706514596939087,
+      "learning_rate": 9.975000000000001e-05,
+      "loss": 3.9627920532226564,
+      "step": 400
+    },
+    {
+      "epoch": 1.27904,
+      "grad_norm": 1.1472086906433105,
+      "learning_rate": 0.00012475,
+      "loss": 3.7471749877929685,
+      "step": 500
+    },
+    {
+      "epoch": 1.53504,
+      "grad_norm": 1.0958755016326904,
+      "learning_rate": 0.00014975,
+      "loss": 3.609476318359375,
+      "step": 600
+    },
+    {
+      "epoch": 1.79104,
+      "grad_norm": 1.1427408456802368,
+      "learning_rate": 0.00017475,
+      "loss": 3.5249368286132814,
+      "step": 700
+    },
+    {
+      "epoch": 2.04608,
+      "grad_norm": 2.976166248321533,
+      "learning_rate": 0.00019975,
+      "loss": 3.419891357421875,
+      "step": 800
+    },
+    {
+      "epoch": 2.30208,
+      "grad_norm": 1.2115665674209595,
+      "learning_rate": 0.00022475000000000001,
+      "loss": 3.2445193481445314,
+      "step": 900
+    },
+    {
+      "epoch": 2.55808,
+      "grad_norm": 1.1276987791061401,
+      "learning_rate": 0.00024975,
+      "loss": 3.2045053100585936,
+      "step": 1000
+    },
+    {
+      "epoch": 2.81408,
+      "grad_norm": 1.2419933080673218,
+      "learning_rate": 0.00022658677055413672,
+      "loss": 3.169610595703125,
+      "step": 1100
+    },
+    {
+      "epoch": 3.06912,
+      "grad_norm": 1.1096692085266113,
+      "learning_rate": 0.0001643733149569131,
+      "loss": 3.0363580322265626,
+      "step": 1200
+    },
+    {
+      "epoch": 3.32512,
+      "grad_norm": 1.0762932300567627,
+      "learning_rate": 8.712059129590328e-05,
+      "loss": 2.8395703125,
+      "step": 1300
+    },
+    {
+      "epoch": 3.58112,
+      "grad_norm": 1.061633586883545,
+      "learning_rate": 2.4336514286109764e-05,
+      "loss": 2.7858563232421876,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 5976661876015104.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbcdc47543731af5d7dd1c833f58eff8fc4bfa98ba06b89b2b240e832937ee6
+size 5137