End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
+datasets: AI-MO/NuminaMath-TIR
 library_name: transformers
 model_name: deepseek-v2-lite-16b-chat-R1-Distill-batch16-lora-numinamath
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for deepseek-v2-lite-16b-chat-R1-Distill-batch16-lora-numinamath
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat).
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -0,0 +1,62 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "deepseek-ai/DeepSeek-V2-Lite-Chat",
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "deepseek-ai/DeepSeek-V2-Lite-Chat--configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "deepseek-ai/DeepSeek-V2-Lite-Chat--modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "deepseek-ai/DeepSeek-V2-Lite-Chat--modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 0.707,
+    "mscale_all_dim": 0.707,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}