Upload folder using huggingface_hub

sft_output_SimpleQA_vinallama/checkpoint-836/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 46303,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "init_device": "cuda",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 46305
+}

sft_output_SimpleQA_vinallama/checkpoint-836/generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "max_memory": {
+    "cpu": 329543315456
+  },
+  "no_split_module_classes": [
+    "LlamaDecoderLayer"
+  ],
+  "pad_token_id": 0,
+  "special_dtypes": {},
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

sft_output_SimpleQA_vinallama/checkpoint-836/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b355ef4ea81d0d4ececc0bd61660d5eb4cc5093dc55dc62fbe40505e90080b5
+size 4965994264

sft_output_SimpleQA_vinallama/checkpoint-836/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fdd06f16d99faa281fb0168bde40a24e8badcda8a891789ab9a03e541a71e6
+size 4947390888

sft_output_SimpleQA_vinallama/checkpoint-836/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc15d0919e32e53f8d2f15b0757b66a7330deb6d55378ac9e180fec40283425f
+size 3797853032

sft_output_SimpleQA_vinallama/checkpoint-836/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13711204352
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

sft_output_SimpleQA_vinallama/checkpoint-836/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2224219bec45692f925467a4cd0001c815093614c29148a262ef212620fc10
+size 27422663166

sft_output_SimpleQA_vinallama/checkpoint-836/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
+size 14244

sft_output_SimpleQA_vinallama/checkpoint-836/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaceed25af9fa07b21404ad4e72c29277afcada2051270d474a65ed1fb0b356
+size 1064

sft_output_SimpleQA_vinallama/checkpoint-836/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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
+  }
+}

sft_output_SimpleQA_vinallama/checkpoint-836/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "46303": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46304": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

sft_output_SimpleQA_vinallama/checkpoint-836/trainer_state.json

@@ -0,0 +1,791 @@
+{
+  "best_global_step": 836,
+  "best_metric": 0.0,
+  "best_model_checkpoint": "./sft_output_SimpleQA_vinallama/checkpoint-836",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 836,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011968880909634948,
+      "grad_norm": 4.3428372009657323e-11,
+      "learning_rate": 4.982035928143713e-05,
+      "loss": 0.6529,
+      "mean_token_accuracy": 0.9,
+      "num_tokens": 80.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.023937761819269897,
+      "grad_norm": 7.23048287909478e-11,
+      "learning_rate": 4.962075848303394e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 160.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.03590664272890485,
+      "grad_norm": 2.3447910280083306e-12,
+      "learning_rate": 4.942115768463074e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 240.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.047875523638539794,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.922155688622755e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 320.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.059844404548174746,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.902195608782435e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 400.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0718132854578097,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.882235528942116e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 480.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.08378216636744465,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.862275449101797e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 560.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.09575104727707959,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.8423153692614774e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 640.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.10771992818671454,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.822355289421158e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 720.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.11968880909634949,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.8023952095808386e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 800.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.13165769000598443,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.782435129740519e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 880.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.1436265709156194,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.7624750499002e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 960.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.15559545182525433,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.74251497005988e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1040.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.1675643327348893,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.722554890219561e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1120.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.17953321364452424,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.702594810379241e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1200.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.19150209455415917,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.682634730538922e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1280.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.20347097546379414,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.662674650698603e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1360.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.21543985637342908,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.6427145708582835e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1440.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.22740873728306404,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.6227544910179644e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1520.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.23937761819269898,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.602794411177645e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1600.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.2513464991023339,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.5828343313373256e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1680.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.26331538001196886,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.5628742514970066e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1760.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.27528426092160385,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.542914171656687e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1840.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.2872531418312388,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.522954091816368e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 1920.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.2992220227408737,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.502994011976048e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2000.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.31119090365050867,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.483033932135729e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2080.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.3231597845601436,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.46307385229541e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2160.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.3351286654697786,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.44311377245509e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2240.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.34709754637941354,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.4231536926147705e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2320.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.3590664272890485,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.403193612774451e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2400.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.3710353081986834,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.383233532934132e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2480.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.38300418910831835,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.363273453093813e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2560.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.39497307001795334,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.343313373253493e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2640.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.4069419509275883,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.323353293413174e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2720.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.4189108318372232,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.303393213572854e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2800.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.43087971274685816,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.283433133732535e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2880.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.4428485936564931,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.263473053892216e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 2960.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.4548174745661281,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.243512974051896e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3040.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.466786355475763,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.223552894211577e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3120.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.47875523638539796,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.2035928143712575e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3200.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.4907241172950329,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.1836327345309385e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3280.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.5026929982046678,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.163672654690619e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3360.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.5146618791143028,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.1437125748503e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3440.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.5266307600239377,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.1237524950099806e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3520.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.5385996409335727,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.103792415169661e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3600.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.5505685218432077,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.083832335329342e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3680.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.5625374027528426,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.063872255489022e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3760.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.5745062836624776,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.043912175648703e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3840.0,
+      "step": 480
+    },
+    {
+      "epoch": 0.5864751645721125,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.023952095808383e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 3920.0,
+      "step": 490
+    },
+    {
+      "epoch": 0.5984440454817475,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 4.0039920159680636e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4000.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.6104129263913824,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.9840319361277445e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4080.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.6223818073010173,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.9640718562874255e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4160.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.6343506882106523,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.944111776447106e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4240.0,
+      "step": 530
+    },
+    {
+      "epoch": 0.6463195691202872,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.924151696606787e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4320.0,
+      "step": 540
+    },
+    {
+      "epoch": 0.6582884500299222,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.904191616766467e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4400.0,
+      "step": 550
+    },
+    {
+      "epoch": 0.6702573309395572,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.884231536926148e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4480.0,
+      "step": 560
+    },
+    {
+      "epoch": 0.6822262118491921,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.864271457085828e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4560.0,
+      "step": 570
+    },
+    {
+      "epoch": 0.6941950927588271,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.844311377245509e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4640.0,
+      "step": 580
+    },
+    {
+      "epoch": 0.706163973668462,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.82435129740519e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4720.0,
+      "step": 590
+    },
+    {
+      "epoch": 0.718132854578097,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.8043912175648703e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4800.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.7301017354877319,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.784431137724551e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4880.0,
+      "step": 610
+    },
+    {
+      "epoch": 0.7420706163973668,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.7644710578842316e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 4960.0,
+      "step": 620
+    },
+    {
+      "epoch": 0.7540394973070018,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.7445109780439125e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5040.0,
+      "step": 630
+    },
+    {
+      "epoch": 0.7660083782166367,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.7245508982035935e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5120.0,
+      "step": 640
+    },
+    {
+      "epoch": 0.7779772591262717,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.704590818363274e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5200.0,
+      "step": 650
+    },
+    {
+      "epoch": 0.7899461400359067,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.684630738522955e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5280.0,
+      "step": 660
+    },
+    {
+      "epoch": 0.8019150209455416,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.664670658682635e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5360.0,
+      "step": 670
+    },
+    {
+      "epoch": 0.8138839018551766,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.644710578842316e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5440.0,
+      "step": 680
+    },
+    {
+      "epoch": 0.8258527827648114,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.624750499001996e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5520.0,
+      "step": 690
+    },
+    {
+      "epoch": 0.8378216636744464,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.6047904191616764e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5600.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.8497905445840814,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.5848303393213574e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5680.0,
+      "step": 710
+    },
+    {
+      "epoch": 0.8617594254937163,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.5648702594810376e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5760.0,
+      "step": 720
+    },
+    {
+      "epoch": 0.8737283064033513,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.5449101796407186e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5840.0,
+      "step": 730
+    },
+    {
+      "epoch": 0.8856971873129862,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.5249500998003995e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 5920.0,
+      "step": 740
+    },
+    {
+      "epoch": 0.8976660682226212,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.50499001996008e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6000.0,
+      "step": 750
+    },
+    {
+      "epoch": 0.9096349491322562,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.485029940119761e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6080.0,
+      "step": 760
+    },
+    {
+      "epoch": 0.9216038300418911,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.465069860279441e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6160.0,
+      "step": 770
+    },
+    {
+      "epoch": 0.933572710951526,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.445109780439122e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6240.0,
+      "step": 780
+    },
+    {
+      "epoch": 0.9455415918611609,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.425149700598803e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6320.0,
+      "step": 790
+    },
+    {
+      "epoch": 0.9575104727707959,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.405189620758483e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6400.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.9694793536804309,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.385229540918164e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6480.0,
+      "step": 810
+    },
+    {
+      "epoch": 0.9814482345900658,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.3652694610778444e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6560.0,
+      "step": 820
+    },
+    {
+      "epoch": 0.9934171154997008,
+      "grad_norm": 3.510081114654895e-12,
+      "learning_rate": 3.345309381237525e-05,
+      "loss": 0.0,
+      "mean_token_accuracy": 1.0,
+      "num_tokens": 6640.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.0,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 6684.0,
+      "eval_runtime": 1.5668,
+      "eval_samples_per_second": 266.789,
+      "eval_steps_per_second": 33.827,
+      "step": 836
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 267330733277184.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

sft_output_SimpleQA_vinallama/checkpoint-836/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b566672deb85855dbe7562cefd2aaa492e91a24edbec2b49801c04cda59475
+size 5688

sft_output_SimpleQA_vinallama/final_model/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 46303,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "init_device": "cuda",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 46305
+}

sft_output_SimpleQA_vinallama/final_model/generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "max_memory": {
+    "cpu": 329543315456
+  },
+  "no_split_module_classes": [
+    "LlamaDecoderLayer"
+  ],
+  "pad_token_id": 0,
+  "special_dtypes": {},
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

sft_output_SimpleQA_vinallama/final_model/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b355ef4ea81d0d4ececc0bd61660d5eb4cc5093dc55dc62fbe40505e90080b5
+size 4965994264

sft_output_SimpleQA_vinallama/final_model/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fdd06f16d99faa281fb0168bde40a24e8badcda8a891789ab9a03e541a71e6
+size 4947390888

sft_output_SimpleQA_vinallama/final_model/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc15d0919e32e53f8d2f15b0757b66a7330deb6d55378ac9e180fec40283425f
+size 3797853032

sft_output_SimpleQA_vinallama/final_model/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13711204352
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

sft_output_SimpleQA_vinallama/final_model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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
+  }
+}

sft_output_SimpleQA_vinallama/final_model/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    },
+    "46303": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46304": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

sft_output_SimpleQA_vinallama/final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b566672deb85855dbe7562cefd2aaa492e91a24edbec2b49801c04cda59475
+size 5688