Training in progress, epoch 1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61fd624ddcf57b2001d3b87b5b17b0c5deab51b834e2c36b3b7488219a3b164
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5324eb885da58b69a352f6bae2921cf388b2c145fb282481425cc2c545b224d
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc748ad638e710465b49abd4a361470a6325161c2aa5ecbf5ca95437e7892a6
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "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 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_log.jsonl

@@ -0,0 +1,53 @@
+{"current_steps": 10, "total_steps": 1497, "loss": 0.914, "lr": 6.666666666666667e-07, "epoch": 0.02004008016032064, "percentage": 0.67, "elapsed_time": "0:00:58", "remaining_time": "2:25:06"}
+{"current_steps": 20, "total_steps": 1497, "loss": 0.7761, "lr": 1.3333333333333334e-06, "epoch": 0.04008016032064128, "percentage": 1.34, "elapsed_time": "0:01:56", "remaining_time": "2:23:28"}
+{"current_steps": 30, "total_steps": 1497, "loss": 0.6765, "lr": 2.0000000000000003e-06, "epoch": 0.06012024048096192, "percentage": 2.0, "elapsed_time": "0:02:55", "remaining_time": "2:23:24"}
+{"current_steps": 40, "total_steps": 1497, "loss": 0.6319, "lr": 2.666666666666667e-06, "epoch": 0.08016032064128256, "percentage": 2.67, "elapsed_time": "0:03:55", "remaining_time": "2:23:10"}
+{"current_steps": 50, "total_steps": 1497, "loss": 0.6028, "lr": 3.3333333333333333e-06, "epoch": 0.10020040080160321, "percentage": 3.34, "elapsed_time": "0:04:54", "remaining_time": "2:22:16"}
+{"current_steps": 60, "total_steps": 1497, "loss": 0.5846, "lr": 4.000000000000001e-06, "epoch": 0.12024048096192384, "percentage": 4.01, "elapsed_time": "0:05:53", "remaining_time": "2:21:16"}
+{"current_steps": 70, "total_steps": 1497, "loss": 0.5761, "lr": 4.666666666666667e-06, "epoch": 0.1402805611222445, "percentage": 4.68, "elapsed_time": "0:06:53", "remaining_time": "2:20:35"}
+{"current_steps": 80, "total_steps": 1497, "loss": 0.5758, "lr": 4.999862725880242e-06, "epoch": 0.16032064128256512, "percentage": 5.34, "elapsed_time": "0:07:52", "remaining_time": "2:19:32"}
+{"current_steps": 90, "total_steps": 1497, "loss": 0.5667, "lr": 4.998764633422446e-06, "epoch": 0.18036072144288579, "percentage": 6.01, "elapsed_time": "0:08:51", "remaining_time": "2:18:27"}
+{"current_steps": 100, "total_steps": 1497, "loss": 0.5651, "lr": 4.996568984453794e-06, "epoch": 0.20040080160320642, "percentage": 6.68, "elapsed_time": "0:09:50", "remaining_time": "2:17:35"}
+{"current_steps": 110, "total_steps": 1497, "loss": 0.5593, "lr": 4.993276850606589e-06, "epoch": 0.22044088176352705, "percentage": 7.35, "elapsed_time": "0:10:50", "remaining_time": "2:16:45"}
+{"current_steps": 120, "total_steps": 1497, "loss": 0.5566, "lr": 4.988889838675462e-06, "epoch": 0.24048096192384769, "percentage": 8.02, "elapsed_time": "0:11:49", "remaining_time": "2:15:44"}
+{"current_steps": 130, "total_steps": 1497, "loss": 0.554, "lr": 4.9834100898331425e-06, "epoch": 0.2605210420841683, "percentage": 8.68, "elapsed_time": "0:12:48", "remaining_time": "2:14:45"}
+{"current_steps": 140, "total_steps": 1497, "loss": 0.5412, "lr": 4.976840278585413e-06, "epoch": 0.280561122244489, "percentage": 9.35, "elapsed_time": "0:13:48", "remaining_time": "2:13:54"}
+{"current_steps": 150, "total_steps": 1497, "loss": 0.5494, "lr": 4.969183611465766e-06, "epoch": 0.30060120240480964, "percentage": 10.02, "elapsed_time": "0:14:47", "remaining_time": "2:12:48"}
+{"current_steps": 160, "total_steps": 1497, "loss": 0.5342, "lr": 4.9604438254703845e-06, "epoch": 0.32064128256513025, "percentage": 10.69, "elapsed_time": "0:15:46", "remaining_time": "2:11:52"}
+{"current_steps": 170, "total_steps": 1497, "loss": 0.5427, "lr": 4.95062518623422e-06, "epoch": 0.3406813627254509, "percentage": 11.36, "elapsed_time": "0:16:46", "remaining_time": "2:10:55"}
+{"current_steps": 180, "total_steps": 1497, "loss": 0.5379, "lr": 4.939732485949066e-06, "epoch": 0.36072144288577157, "percentage": 12.02, "elapsed_time": "0:17:44", "remaining_time": "2:09:49"}
+{"current_steps": 190, "total_steps": 1497, "loss": 0.5355, "lr": 4.927771041024627e-06, "epoch": 0.3807615230460922, "percentage": 12.69, "elapsed_time": "0:18:44", "remaining_time": "2:08:53"}
+{"current_steps": 200, "total_steps": 1497, "loss": 0.54, "lr": 4.914746689493731e-06, "epoch": 0.40080160320641284, "percentage": 13.36, "elapsed_time": "0:19:44", "remaining_time": "2:07:59"}
+{"current_steps": 210, "total_steps": 1497, "loss": 0.5306, "lr": 4.900665788162962e-06, "epoch": 0.42084168336673344, "percentage": 14.03, "elapsed_time": "0:20:43", "remaining_time": "2:07:00"}
+{"current_steps": 220, "total_steps": 1497, "loss": 0.531, "lr": 4.885535209510081e-06, "epoch": 0.4408817635270541, "percentage": 14.7, "elapsed_time": "0:21:42", "remaining_time": "2:05:57"}
+{"current_steps": 230, "total_steps": 1497, "loss": 0.528, "lr": 4.869362338329773e-06, "epoch": 0.46092184368737477, "percentage": 15.36, "elapsed_time": "0:22:42", "remaining_time": "2:05:03"}
+{"current_steps": 240, "total_steps": 1497, "loss": 0.53, "lr": 4.852155068129343e-06, "epoch": 0.48096192384769537, "percentage": 16.03, "elapsed_time": "0:23:41", "remaining_time": "2:04:02"}
+{"current_steps": 250, "total_steps": 1497, "loss": 0.5242, "lr": 4.8339217972761274e-06, "epoch": 0.501002004008016, "percentage": 16.7, "elapsed_time": "0:24:39", "remaining_time": "2:03:02"}
+{"current_steps": 260, "total_steps": 1497, "loss": 0.5218, "lr": 4.814671424898493e-06, "epoch": 0.5210420841683366, "percentage": 17.37, "elapsed_time": "0:25:40", "remaining_time": "2:02:07"}
+{"current_steps": 270, "total_steps": 1497, "loss": 0.516, "lr": 4.794413346542432e-06, "epoch": 0.5410821643286573, "percentage": 18.04, "elapsed_time": "0:26:39", "remaining_time": "2:01:08"}
+{"current_steps": 280, "total_steps": 1497, "loss": 0.519, "lr": 4.773157449585871e-06, "epoch": 0.561122244488978, "percentage": 18.7, "elapsed_time": "0:27:38", "remaining_time": "2:00:07"}
+{"current_steps": 290, "total_steps": 1497, "loss": 0.5168, "lr": 4.750914108412927e-06, "epoch": 0.5811623246492986, "percentage": 19.37, "elapsed_time": "0:28:36", "remaining_time": "1:59:05"}
+{"current_steps": 300, "total_steps": 1497, "loss": 0.5125, "lr": 4.727694179350476e-06, "epoch": 0.6012024048096193, "percentage": 20.04, "elapsed_time": "0:29:35", "remaining_time": "1:58:04"}
+{"current_steps": 310, "total_steps": 1497, "loss": 0.513, "lr": 4.703508995369497e-06, "epoch": 0.6212424849699398, "percentage": 20.71, "elapsed_time": "0:30:34", "remaining_time": "1:57:03"}
+{"current_steps": 320, "total_steps": 1497, "loss": 0.5147, "lr": 4.6783703605537715e-06, "epoch": 0.6412825651302605, "percentage": 21.38, "elapsed_time": "0:31:32", "remaining_time": "1:56:01"}
+{"current_steps": 330, "total_steps": 1497, "loss": 0.5173, "lr": 4.652290544338663e-06, "epoch": 0.6613226452905812, "percentage": 22.04, "elapsed_time": "0:32:31", "remaining_time": "1:55:01"}
+{"current_steps": 340, "total_steps": 1497, "loss": 0.5108, "lr": 4.6252822755227605e-06, "epoch": 0.6813627254509018, "percentage": 22.71, "elapsed_time": "0:33:30", "remaining_time": "1:54:01"}
+{"current_steps": 350, "total_steps": 1497, "loss": 0.5131, "lr": 4.5973587360553185e-06, "epoch": 0.7014028056112225, "percentage": 23.38, "elapsed_time": "0:34:29", "remaining_time": "1:53:01"}
+{"current_steps": 360, "total_steps": 1497, "loss": 0.5083, "lr": 4.568533554602535e-06, "epoch": 0.7214428857715431, "percentage": 24.05, "elapsed_time": "0:35:27", "remaining_time": "1:51:58"}
+{"current_steps": 370, "total_steps": 1497, "loss": 0.5133, "lr": 4.5388207998957986e-06, "epoch": 0.7414829659318637, "percentage": 24.72, "elapsed_time": "0:36:26", "remaining_time": "1:50:59"}
+{"current_steps": 380, "total_steps": 1497, "loss": 0.5157, "lr": 4.508234973865145e-06, "epoch": 0.7615230460921844, "percentage": 25.38, "elapsed_time": "0:37:24", "remaining_time": "1:49:58"}
+{"current_steps": 390, "total_steps": 1497, "loss": 0.512, "lr": 4.476791004561293e-06, "epoch": 0.781563126252505, "percentage": 26.05, "elapsed_time": "0:38:23", "remaining_time": "1:48:58"}
+{"current_steps": 400, "total_steps": 1497, "loss": 0.5095, "lr": 4.4445042388696935e-06, "epoch": 0.8016032064128257, "percentage": 26.72, "elapsed_time": "0:39:23", "remaining_time": "1:48:00"}
+{"current_steps": 410, "total_steps": 1497, "loss": 0.5131, "lr": 4.411390435020164e-06, "epoch": 0.8216432865731463, "percentage": 27.39, "elapsed_time": "0:40:22", "remaining_time": "1:47:03"}
+{"current_steps": 420, "total_steps": 1497, "loss": 0.5052, "lr": 4.377465754895757e-06, "epoch": 0.8416833667334669, "percentage": 28.06, "elapsed_time": "0:41:21", "remaining_time": "1:46:04"}
+{"current_steps": 430, "total_steps": 1497, "loss": 0.5124, "lr": 4.342746756144609e-06, "epoch": 0.8617234468937875, "percentage": 28.72, "elapsed_time": "0:42:21", "remaining_time": "1:45:06"}
+{"current_steps": 440, "total_steps": 1497, "loss": 0.5094, "lr": 4.307250384098645e-06, "epoch": 0.8817635270541082, "percentage": 29.39, "elapsed_time": "0:43:20", "remaining_time": "1:44:07"}
+{"current_steps": 450, "total_steps": 1497, "loss": 0.5055, "lr": 4.270993963503048e-06, "epoch": 0.9018036072144289, "percentage": 30.06, "elapsed_time": "0:44:19", "remaining_time": "1:43:07"}
+{"current_steps": 460, "total_steps": 1497, "loss": 0.511, "lr": 4.233995190060559e-06, "epoch": 0.9218436873747495, "percentage": 30.73, "elapsed_time": "0:45:18", "remaining_time": "1:42:09"}
+{"current_steps": 470, "total_steps": 1497, "loss": 0.5122, "lr": 4.196272121794714e-06, "epoch": 0.9418837675350702, "percentage": 31.4, "elapsed_time": "0:46:18", "remaining_time": "1:41:11"}
+{"current_steps": 480, "total_steps": 1497, "loss": 0.5068, "lr": 4.15784317023626e-06, "epoch": 0.9619238476953907, "percentage": 32.06, "elapsed_time": "0:47:17", "remaining_time": "1:40:12"}
+{"current_steps": 490, "total_steps": 1497, "loss": 0.5002, "lr": 4.118727091437013e-06, "epoch": 0.9819639278557114, "percentage": 32.73, "elapsed_time": "0:48:17", "remaining_time": "1:39:14"}
+{"current_steps": 499, "total_steps": 1497, "eval_loss": 0.5069113373756409, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:49:55", "remaining_time": "1:39:51"}
+{"current_steps": 500, "total_steps": 1497, "loss": 0.4942, "lr": 4.078942976815581e-06, "epoch": 1.002004008016032, "percentage": 33.4, "elapsed_time": "0:50:59", "remaining_time": "1:41:39"}
+{"current_steps": 510, "total_steps": 1497, "loss": 0.418, "lr": 4.038510243839396e-06, "epoch": 1.0220440881763526, "percentage": 34.07, "elapsed_time": "0:51:58", "remaining_time": "1:40:35"}
+{"current_steps": 520, "total_steps": 1497, "loss": 0.4136, "lr": 3.997448626547613e-06, "epoch": 1.0420841683366733, "percentage": 34.74, "elapsed_time": "0:52:58", "remaining_time": "1:39:31"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f04077304d10db5976d5ea3c9aff588e8d9efa51561b6783efeac7cdb205454
+size 7352