Upload task output 22683721-f995-4c95-ad47-2bd47697bc9d

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+350,2.140592098236084,2.140592098236084,single_best

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581fa1650dfcb5366bc8046a2dba5d3492ce7597b1b18f54912a574ba49fa060
+size 4943178720

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a305af4b7380a6a934f6134f4dbdb40f5895144b34931a81f4b0d9a4a8a88067
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8608ecfbdb2ac09d87a8551d47389cc963f0e04ba6861779556ac856299981
+size 4540532728

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483496960
+  },
+  "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-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-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"
+  }
+}

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
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,540 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014285714285714285,
+      "grad_norm": 24.125,
+      "learning_rate": 9.789843888706694e-07,
+      "loss": 2.3634,
+      "step": 5
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 12.5,
+      "learning_rate": 2.202714874959006e-06,
+      "loss": 2.2737,
+      "step": 10
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 10.125,
+      "learning_rate": 3.4264453610473433e-06,
+      "loss": 2.2243,
+      "step": 15
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 6.1875,
+      "learning_rate": 4.6501758471356796e-06,
+      "loss": 2.1777,
+      "step": 20
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 7.90625,
+      "learning_rate": 5.873906333224017e-06,
+      "loss": 2.1515,
+      "step": 25
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 5.8125,
+      "learning_rate": 7.097636819312354e-06,
+      "loss": 2.1361,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.875,
+      "learning_rate": 8.32136730540069e-06,
+      "loss": 2.1371,
+      "step": 35
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 5.15625,
+      "learning_rate": 8.565867214444041e-06,
+      "loss": 2.1394,
+      "step": 40
+    },
+    {
+      "epoch": 0.12857142857142856,
+      "grad_norm": 5.71875,
+      "learning_rate": 8.564867139659044e-06,
+      "loss": 2.1553,
+      "step": 45
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 6.78125,
+      "learning_rate": 8.563098030832528e-06,
+      "loss": 2.135,
+      "step": 50
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 6.9375,
+      "learning_rate": 8.560560311659701e-06,
+      "loss": 2.1494,
+      "step": 55
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 6.09375,
+      "learning_rate": 8.557254589915187e-06,
+      "loss": 2.1446,
+      "step": 60
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.553181657307465e-06,
+      "loss": 2.1517,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.125,
+      "learning_rate": 8.548342489289255e-06,
+      "loss": 2.12,
+      "step": 70
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 4.875,
+      "learning_rate": 8.542738244823914e-06,
+      "loss": 2.1737,
+      "step": 75
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 5.5625,
+      "learning_rate": 8.53637026610785e-06,
+      "loss": 2.1496,
+      "step": 80
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "eval_loss": 2.1535961627960205,
+      "eval_runtime": 1.2567,
+      "eval_samples_per_second": 16.71,
+      "eval_steps_per_second": 8.753,
+      "step": 80
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.529240078249084e-06,
+      "loss": 2.1308,
+      "step": 85
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 5.3125,
+      "learning_rate": 8.521349388901986e-06,
+      "loss": 2.1588,
+      "step": 90
+    },
+    {
+      "epoch": 0.2714285714285714,
+      "grad_norm": 4.59375,
+      "learning_rate": 8.512700087858303e-06,
+      "loss": 2.144,
+      "step": 95
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.503294246594551e-06,
+      "loss": 2.1222,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.493134117775916e-06,
+      "loss": 2.1261,
+      "step": 105
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 4.9375,
+      "learning_rate": 8.482222134716743e-06,
+      "loss": 2.1477,
+      "step": 110
+    },
+    {
+      "epoch": 0.32857142857142857,
+      "grad_norm": 5.21875,
+      "learning_rate": 8.470560910797759e-06,
+      "loss": 2.16,
+      "step": 115
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.458153238840195e-06,
+      "loss": 2.1347,
+      "step": 120
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 5.375,
+      "learning_rate": 8.445002090436896e-06,
+      "loss": 2.1438,
+      "step": 125
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 5.53125,
+      "learning_rate": 8.431110615240647e-06,
+      "loss": 2.1603,
+      "step": 130
+    },
+    {
+      "epoch": 0.38571428571428573,
+      "grad_norm": 5.0,
+      "learning_rate": 8.416482140209844e-06,
+      "loss": 2.1381,
+      "step": 135
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.875,
+      "learning_rate": 8.401120168811687e-06,
+      "loss": 2.1386,
+      "step": 140
+    },
+    {
+      "epoch": 0.4142857142857143,
+      "grad_norm": 5.21875,
+      "learning_rate": 8.385028380183127e-06,
+      "loss": 2.1461,
+      "step": 145
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 4.9375,
+      "learning_rate": 8.368210628249719e-06,
+      "loss": 2.1229,
+      "step": 150
+    },
+    {
+      "epoch": 0.44285714285714284,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.350670940802612e-06,
+      "loss": 2.1335,
+      "step": 155
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 5.3125,
+      "learning_rate": 8.33241351853393e-06,
+      "loss": 2.1415,
+      "step": 160
+    },
+    {
+      "epoch": 0.4714285714285714,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.313442734030699e-06,
+      "loss": 2.1261,
+      "step": 165
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 5.65625,
+      "learning_rate": 8.293763130727635e-06,
+      "loss": 2.1244,
+      "step": 170
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.273379421819017e-06,
+      "loss": 2.1322,
+      "step": 175
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 4.65625,
+      "learning_rate": 8.252296489129878e-06,
+      "loss": 2.1575,
+      "step": 180
+    },
+    {
+      "epoch": 0.5285714285714286,
+      "grad_norm": 5.0,
+      "learning_rate": 8.230519381946843e-06,
+      "loss": 2.1194,
+      "step": 185
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 4.625,
+      "learning_rate": 8.208053315808828e-06,
+      "loss": 2.1232,
+      "step": 190
+    },
+    {
+      "epoch": 0.5571428571428572,
+      "grad_norm": 4.6875,
+      "learning_rate": 8.184903671257942e-06,
+      "loss": 2.1226,
+      "step": 195
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.161075992550872e-06,
+      "loss": 2.1488,
+      "step": 200
+    },
+    {
+      "epoch": 0.5857142857142857,
+      "grad_norm": 4.59375,
+      "learning_rate": 8.136575986331045e-06,
+      "loss": 2.1211,
+      "step": 205
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.75,
+      "learning_rate": 8.111409520261913e-06,
+      "loss": 2.1438,
+      "step": 210
+    },
+    {
+      "epoch": 0.6142857142857143,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.08558262162167e-06,
+      "loss": 2.1282,
+      "step": 215
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.059101475859732e-06,
+      "loss": 2.1188,
+      "step": 220
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 4.90625,
+      "learning_rate": 8.03197242511535e-06,
+      "loss": 2.1411,
+      "step": 225
+    },
+    {
+      "epoch": 0.6571428571428571,
+      "grad_norm": 4.84375,
+      "learning_rate": 8.0042019666987e-06,
+      "loss": 2.1477,
+      "step": 230
+    },
+    {
+      "epoch": 0.6714285714285714,
+      "grad_norm": 4.90625,
+      "learning_rate": 7.975796751534778e-06,
+      "loss": 2.1519,
+      "step": 235
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 4.84375,
+      "learning_rate": 7.946763582570545e-06,
+      "loss": 2.1364,
+      "step": 240
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.28125,
+      "learning_rate": 7.917109413145643e-06,
+      "loss": 2.1108,
+      "step": 245
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.88684134532709e-06,
+      "loss": 2.149,
+      "step": 250
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.855966628208364e-06,
+      "loss": 2.1453,
+      "step": 255
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 5.0,
+      "learning_rate": 7.824492656173272e-06,
+      "loss": 2.1271,
+      "step": 260
+    },
+    {
+      "epoch": 0.7571428571428571,
+      "grad_norm": 4.40625,
+      "learning_rate": 7.792426967125019e-06,
+      "loss": 2.1301,
+      "step": 265
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 5.03125,
+      "learning_rate": 7.759777240680905e-06,
+      "loss": 2.1464,
+      "step": 270
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.726551296333093e-06,
+      "loss": 2.1404,
+      "step": 275
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.692757091575864e-06,
+      "loss": 2.1292,
+      "step": 280
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 4.71875,
+      "learning_rate": 7.658402719999816e-06,
+      "loss": 2.1242,
+      "step": 285
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.6234964093534964e-06,
+      "loss": 2.1357,
+      "step": 290
+    },
+    {
+      "epoch": 0.8428571428571429,
+      "grad_norm": 4.625,
+      "learning_rate": 7.588046519572876e-06,
+      "loss": 2.1187,
+      "step": 295
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.55206154077917e-06,
+      "loss": 2.1289,
+      "step": 300
+    },
+    {
+      "epoch": 0.8714285714285714,
+      "grad_norm": 4.625,
+      "learning_rate": 7.515550091245495e-06,
+      "loss": 2.1067,
+      "step": 305
+    },
+    {
+      "epoch": 0.8857142857142857,
+      "grad_norm": 4.875,
+      "learning_rate": 7.4785209153328105e-06,
+      "loss": 2.1358,
+      "step": 310
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.78125,
+      "learning_rate": 7.440982881395693e-06,
+      "loss": 2.1356,
+      "step": 315
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.402944979658378e-06,
+      "loss": 2.1308,
+      "step": 320
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 4.375,
+      "learning_rate": 7.364416320061651e-06,
+      "loss": 2.1369,
+      "step": 325
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 4.84375,
+      "learning_rate": 7.325406130081036e-06,
+      "loss": 2.1334,
+      "step": 330
+    },
+    {
+      "epoch": 0.9571428571428572,
+      "grad_norm": 4.59375,
+      "learning_rate": 7.285923752516855e-06,
+      "loss": 2.1321,
+      "step": 335
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 4.3125,
+      "learning_rate": 7.2459786432566614e-06,
+      "loss": 2.1186,
+      "step": 340
+    },
+    {
+      "epoch": 0.9857142857142858,
+      "grad_norm": 5.25,
+      "learning_rate": 7.205580369010584e-06,
+      "loss": 2.1272,
+      "step": 345
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.71875,
+      "learning_rate": 7.16473860502014e-06,
+      "loss": 2.126,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.140592098236084,
+      "eval_runtime": 1.248,
+      "eval_samples_per_second": 16.828,
+      "eval_steps_per_second": 8.814,
+      "step": 350
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1050,
+  "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": 1.7125675286659072e+18,
+  "train_batch_size": 28,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39cb244b5cc70cf8919c44f0ee5a8b83a9c924d1dcf746f3f9196b7c2de8dfa
+size 5688