初始化项目，由ModelHub XC社区提供模型

Model: AmberYifan/capmix-marin-8b-base-select
Source: Original Platform

checkpoint-63/chat_template.jinja

@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}

checkpoint-63/config.json

@@ -0,0 +1,51 @@
+{
+  "_attn_implementation_autoset": false,
+  "add_cross_attention": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "finetuning_task": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": false,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "prefix": null,
+  "pretraining_tp": 1,
+  "pruned_heads": {},
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "llama3"
+  },
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "5.7.0",
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-63/generation_config.json

@@ -0,0 +1,37 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 128009,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.7.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

checkpoint-63/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f746cf813385525ba5580b006c92209b1e4a3680c69c8cca944c18dc17a0dbb
+size 16060556616

checkpoint-63/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-63/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4540108290704708,
+      "learning_rate": 8.202965893490877e-06,
+      "loss": 0.5189290046691895,
+      "step": 20
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.40991677407712307,
+      "learning_rate": 3.3572880904458267e-06,
+      "loss": 0.4767247200012207,
+      "step": 40
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.4387410289675732,
+      "learning_rate": 1.0572157452321097e-07,
+      "loss": 0.4906019687652588,
+      "step": 60
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5418005299200.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2df73783539a415d81e049c69e7573958ce6f11d6be477f80dedd535a87ffa
+size 7761