Training in progress, epoch 0

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 sha256:65dfae7d6cd56dc695bb5a15750239eb2d6f592c9d17beab8c499b82aeee37dc
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f16865e1e58c7ee2701e3c94950addeb4faa0ed9e6283fa38f23b480448927
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0709bfc4202829070211614a950e58daa004488796bdf2be00fd7879e7342e00
+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 +1,68 @@
+{"current_steps": 10, "total_steps": 2001, "loss": 0.8065, "lr": 5e-06, "epoch": 0.014989694584972832, "percentage": 0.5, "elapsed_time": "0:05:17", "remaining_time": "17:34:40"}
+{"current_steps": 20, "total_steps": 2001, "loss": 0.651, "lr": 5e-06, "epoch": 0.029979389169945664, "percentage": 1.0, "elapsed_time": "0:10:32", "remaining_time": "17:23:59"}
+{"current_steps": 30, "total_steps": 2001, "loss": 0.6152, "lr": 5e-06, "epoch": 0.044969083754918496, "percentage": 1.5, "elapsed_time": "0:15:49", "remaining_time": "17:19:44"}
+{"current_steps": 40, "total_steps": 2001, "loss": 0.5859, "lr": 5e-06, "epoch": 0.05995877833989133, "percentage": 2.0, "elapsed_time": "0:21:03", "remaining_time": "17:12:23"}
+{"current_steps": 50, "total_steps": 2001, "loss": 0.5786, "lr": 5e-06, "epoch": 0.07494847292486416, "percentage": 2.5, "elapsed_time": "0:26:14", "remaining_time": "17:04:04"}
+{"current_steps": 60, "total_steps": 2001, "loss": 0.5685, "lr": 5e-06, "epoch": 0.08993816750983699, "percentage": 3.0, "elapsed_time": "0:31:25", "remaining_time": "16:56:51"}
+{"current_steps": 70, "total_steps": 2001, "loss": 0.5586, "lr": 5e-06, "epoch": 0.10492786209480982, "percentage": 3.5, "elapsed_time": "0:36:36", "remaining_time": "16:49:42"}
+{"current_steps": 80, "total_steps": 2001, "loss": 0.5529, "lr": 5e-06, "epoch": 0.11991755667978266, "percentage": 4.0, "elapsed_time": "0:41:47", "remaining_time": "16:43:22"}
+{"current_steps": 90, "total_steps": 2001, "loss": 0.5461, "lr": 5e-06, "epoch": 0.13490725126475547, "percentage": 4.5, "elapsed_time": "0:47:01", "remaining_time": "16:38:32"}
+{"current_steps": 100, "total_steps": 2001, "loss": 0.5381, "lr": 5e-06, "epoch": 0.14989694584972832, "percentage": 5.0, "elapsed_time": "0:52:16", "remaining_time": "16:33:46"}
+{"current_steps": 110, "total_steps": 2001, "loss": 0.5359, "lr": 5e-06, "epoch": 0.16488664043470114, "percentage": 5.5, "elapsed_time": "0:57:32", "remaining_time": "16:29:03"}
+{"current_steps": 120, "total_steps": 2001, "loss": 0.5318, "lr": 5e-06, "epoch": 0.17987633501967398, "percentage": 6.0, "elapsed_time": "1:02:44", "remaining_time": "16:23:28"}
+{"current_steps": 130, "total_steps": 2001, "loss": 0.5279, "lr": 5e-06, "epoch": 0.1948660296046468, "percentage": 6.5, "elapsed_time": "1:07:59", "remaining_time": "16:18:26"}
+{"current_steps": 140, "total_steps": 2001, "loss": 0.5309, "lr": 5e-06, "epoch": 0.20985572418961965, "percentage": 7.0, "elapsed_time": "1:13:14", "remaining_time": "16:13:33"}
+{"current_steps": 150, "total_steps": 2001, "loss": 0.5207, "lr": 5e-06, "epoch": 0.22484541877459246, "percentage": 7.5, "elapsed_time": "1:18:27", "remaining_time": "16:08:06"}
+{"current_steps": 160, "total_steps": 2001, "loss": 0.5203, "lr": 5e-06, "epoch": 0.2398351133595653, "percentage": 8.0, "elapsed_time": "1:23:41", "remaining_time": "16:02:54"}
+{"current_steps": 170, "total_steps": 2001, "loss": 0.5179, "lr": 5e-06, "epoch": 0.25482480794453816, "percentage": 8.5, "elapsed_time": "1:28:54", "remaining_time": "15:57:40"}
+{"current_steps": 180, "total_steps": 2001, "loss": 0.5134, "lr": 5e-06, "epoch": 0.26981450252951095, "percentage": 9.0, "elapsed_time": "1:34:09", "remaining_time": "15:52:31"}
+{"current_steps": 190, "total_steps": 2001, "loss": 0.5124, "lr": 5e-06, "epoch": 0.2848041971144838, "percentage": 9.5, "elapsed_time": "1:39:23", "remaining_time": "15:47:19"}
+{"current_steps": 200, "total_steps": 2001, "loss": 0.508, "lr": 5e-06, "epoch": 0.29979389169945664, "percentage": 10.0, "elapsed_time": "1:44:38", "remaining_time": "15:42:20"}
+{"current_steps": 210, "total_steps": 2001, "loss": 0.5032, "lr": 5e-06, "epoch": 0.31478358628442943, "percentage": 10.49, "elapsed_time": "1:49:51", "remaining_time": "15:36:55"}
+{"current_steps": 220, "total_steps": 2001, "loss": 0.5051, "lr": 5e-06, "epoch": 0.3297732808694023, "percentage": 10.99, "elapsed_time": "1:55:02", "remaining_time": "15:31:22"}
+{"current_steps": 230, "total_steps": 2001, "loss": 0.5036, "lr": 5e-06, "epoch": 0.3447629754543751, "percentage": 11.49, "elapsed_time": "2:00:17", "remaining_time": "15:26:16"}
+{"current_steps": 240, "total_steps": 2001, "loss": 0.5041, "lr": 5e-06, "epoch": 0.35975267003934797, "percentage": 11.99, "elapsed_time": "2:05:34", "remaining_time": "15:21:24"}
+{"current_steps": 250, "total_steps": 2001, "loss": 0.5001, "lr": 5e-06, "epoch": 0.37474236462432076, "percentage": 12.49, "elapsed_time": "2:10:50", "remaining_time": "15:16:28"}
+{"current_steps": 260, "total_steps": 2001, "loss": 0.5015, "lr": 5e-06, "epoch": 0.3897320592092936, "percentage": 12.99, "elapsed_time": "2:16:04", "remaining_time": "15:11:12"}
+{"current_steps": 270, "total_steps": 2001, "loss": 0.4958, "lr": 5e-06, "epoch": 0.40472175379426645, "percentage": 13.49, "elapsed_time": "2:21:20", "remaining_time": "15:06:08"}
+{"current_steps": 280, "total_steps": 2001, "loss": 0.4996, "lr": 5e-06, "epoch": 0.4197114483792393, "percentage": 13.99, "elapsed_time": "2:26:34", "remaining_time": "15:00:51"}
+{"current_steps": 290, "total_steps": 2001, "loss": 0.4929, "lr": 5e-06, "epoch": 0.4347011429642121, "percentage": 14.49, "elapsed_time": "2:31:50", "remaining_time": "14:55:52"}
+{"current_steps": 300, "total_steps": 2001, "loss": 0.4897, "lr": 5e-06, "epoch": 0.44969083754918493, "percentage": 14.99, "elapsed_time": "2:37:06", "remaining_time": "14:50:46"}
+{"current_steps": 310, "total_steps": 2001, "loss": 0.4927, "lr": 5e-06, "epoch": 0.4646805321341578, "percentage": 15.49, "elapsed_time": "2:42:22", "remaining_time": "14:45:45"}
+{"current_steps": 320, "total_steps": 2001, "loss": 0.4892, "lr": 5e-06, "epoch": 0.4796702267191306, "percentage": 15.99, "elapsed_time": "2:47:39", "remaining_time": "14:40:41"}
+{"current_steps": 330, "total_steps": 2001, "loss": 0.4889, "lr": 5e-06, "epoch": 0.4946599213041034, "percentage": 16.49, "elapsed_time": "2:52:53", "remaining_time": "14:35:26"}
+{"current_steps": 340, "total_steps": 2001, "loss": 0.4872, "lr": 5e-06, "epoch": 0.5096496158890763, "percentage": 16.99, "elapsed_time": "2:58:06", "remaining_time": "14:30:08"}
+{"current_steps": 350, "total_steps": 2001, "loss": 0.4839, "lr": 5e-06, "epoch": 0.5246393104740491, "percentage": 17.49, "elapsed_time": "3:03:21", "remaining_time": "14:24:57"}
+{"current_steps": 360, "total_steps": 2001, "loss": 0.4886, "lr": 5e-06, "epoch": 0.5396290050590219, "percentage": 17.99, "elapsed_time": "3:08:37", "remaining_time": "14:19:47"}
+{"current_steps": 370, "total_steps": 2001, "loss": 0.4837, "lr": 5e-06, "epoch": 0.5546186996439948, "percentage": 18.49, "elapsed_time": "3:13:52", "remaining_time": "14:14:38"}
+{"current_steps": 380, "total_steps": 2001, "loss": 0.4822, "lr": 5e-06, "epoch": 0.5696083942289676, "percentage": 18.99, "elapsed_time": "3:19:07", "remaining_time": "14:09:25"}
+{"current_steps": 390, "total_steps": 2001, "loss": 0.4798, "lr": 5e-06, "epoch": 0.5845980888139404, "percentage": 19.49, "elapsed_time": "3:24:20", "remaining_time": "14:04:04"}
+{"current_steps": 400, "total_steps": 2001, "loss": 0.4831, "lr": 5e-06, "epoch": 0.5995877833989133, "percentage": 19.99, "elapsed_time": "3:29:33", "remaining_time": "13:58:44"}
+{"current_steps": 410, "total_steps": 2001, "loss": 0.4803, "lr": 5e-06, "epoch": 0.6145774779838861, "percentage": 20.49, "elapsed_time": "3:34:48", "remaining_time": "13:53:35"}
+{"current_steps": 420, "total_steps": 2001, "loss": 0.4759, "lr": 5e-06, "epoch": 0.6295671725688589, "percentage": 20.99, "elapsed_time": "3:40:06", "remaining_time": "13:48:32"}
+{"current_steps": 430, "total_steps": 2001, "loss": 0.4759, "lr": 5e-06, "epoch": 0.6445568671538318, "percentage": 21.49, "elapsed_time": "3:45:22", "remaining_time": "13:43:25"}
+{"current_steps": 440, "total_steps": 2001, "loss": 0.4731, "lr": 5e-06, "epoch": 0.6595465617388045, "percentage": 21.99, "elapsed_time": "3:50:37", "remaining_time": "13:38:13"}
+{"current_steps": 450, "total_steps": 2001, "loss": 0.4748, "lr": 5e-06, "epoch": 0.6745362563237775, "percentage": 22.49, "elapsed_time": "3:55:53", "remaining_time": "13:33:03"}
+{"current_steps": 460, "total_steps": 2001, "loss": 0.4692, "lr": 5e-06, "epoch": 0.6895259509087502, "percentage": 22.99, "elapsed_time": "4:01:08", "remaining_time": "13:27:48"}
+{"current_steps": 470, "total_steps": 2001, "loss": 0.469, "lr": 5e-06, "epoch": 0.704515645493723, "percentage": 23.49, "elapsed_time": "4:06:21", "remaining_time": "13:22:28"}
+{"current_steps": 480, "total_steps": 2001, "loss": 0.4742, "lr": 5e-06, "epoch": 0.7195053400786959, "percentage": 23.99, "elapsed_time": "4:11:37", "remaining_time": "13:17:19"}
+{"current_steps": 490, "total_steps": 2001, "loss": 0.4734, "lr": 5e-06, "epoch": 0.7344950346636687, "percentage": 24.49, "elapsed_time": "4:16:51", "remaining_time": "13:12:03"}
+{"current_steps": 500, "total_steps": 2001, "loss": 0.4693, "lr": 5e-06, "epoch": 0.7494847292486415, "percentage": 24.99, "elapsed_time": "4:22:04", "remaining_time": "13:06:44"}
+{"current_steps": 510, "total_steps": 2001, "loss": 0.4734, "lr": 5e-06, "epoch": 0.7644744238336144, "percentage": 25.49, "elapsed_time": "4:27:18", "remaining_time": "13:01:28"}
+{"current_steps": 520, "total_steps": 2001, "loss": 0.4663, "lr": 5e-06, "epoch": 0.7794641184185872, "percentage": 25.99, "elapsed_time": "4:32:32", "remaining_time": "12:56:14"}
+{"current_steps": 530, "total_steps": 2001, "loss": 0.4645, "lr": 5e-06, "epoch": 0.7944538130035601, "percentage": 26.49, "elapsed_time": "4:37:48", "remaining_time": "12:51:02"}
+{"current_steps": 540, "total_steps": 2001, "loss": 0.4647, "lr": 5e-06, "epoch": 0.8094435075885329, "percentage": 26.99, "elapsed_time": "4:43:03", "remaining_time": "12:45:50"}
+{"current_steps": 550, "total_steps": 2001, "loss": 0.4707, "lr": 5e-06, "epoch": 0.8244332021735057, "percentage": 27.49, "elapsed_time": "4:48:19", "remaining_time": "12:40:39"}
+{"current_steps": 560, "total_steps": 2001, "loss": 0.4674, "lr": 5e-06, "epoch": 0.8394228967584786, "percentage": 27.99, "elapsed_time": "4:53:34", "remaining_time": "12:35:25"}
+{"current_steps": 570, "total_steps": 2001, "loss": 0.4678, "lr": 5e-06, "epoch": 0.8544125913434514, "percentage": 28.49, "elapsed_time": "4:58:49", "remaining_time": "12:30:12"}
+{"current_steps": 580, "total_steps": 2001, "loss": 0.4614, "lr": 5e-06, "epoch": 0.8694022859284242, "percentage": 28.99, "elapsed_time": "5:04:04", "remaining_time": "12:24:59"}
+{"current_steps": 590, "total_steps": 2001, "loss": 0.4634, "lr": 5e-06, "epoch": 0.8843919805133971, "percentage": 29.49, "elapsed_time": "5:09:20", "remaining_time": "12:19:48"}
+{"current_steps": 600, "total_steps": 2001, "loss": 0.4649, "lr": 5e-06, "epoch": 0.8993816750983699, "percentage": 29.99, "elapsed_time": "5:14:34", "remaining_time": "12:14:33"}
+{"current_steps": 610, "total_steps": 2001, "loss": 0.4638, "lr": 5e-06, "epoch": 0.9143713696833426, "percentage": 30.48, "elapsed_time": "5:19:50", "remaining_time": "12:09:21"}
+{"current_steps": 620, "total_steps": 2001, "loss": 0.4639, "lr": 5e-06, "epoch": 0.9293610642683156, "percentage": 30.98, "elapsed_time": "5:25:07", "remaining_time": "12:04:11"}
+{"current_steps": 630, "total_steps": 2001, "loss": 0.4656, "lr": 5e-06, "epoch": 0.9443507588532883, "percentage": 31.48, "elapsed_time": "5:30:22", "remaining_time": "11:58:57"}
+{"current_steps": 640, "total_steps": 2001, "loss": 0.4592, "lr": 5e-06, "epoch": 0.9593404534382612, "percentage": 31.98, "elapsed_time": "5:35:37", "remaining_time": "11:53:44"}
+{"current_steps": 650, "total_steps": 2001, "loss": 0.4632, "lr": 5e-06, "epoch": 0.974330148023234, "percentage": 32.48, "elapsed_time": "5:40:53", "remaining_time": "11:48:31"}
+{"current_steps": 660, "total_steps": 2001, "loss": 0.4596, "lr": 5e-06, "epoch": 0.9893198426082068, "percentage": 32.98, "elapsed_time": "5:46:07", "remaining_time": "11:43:16"}
+{"current_steps": 667, "total_steps": 2001, "eval_loss": 0.05758751183748245, "epoch": 0.9998126288176878, "percentage": 33.33, "elapsed_time": "5:57:26", "remaining_time": "11:54:53"}
+{"current_steps": 670, "total_steps": 2001, "loss": 0.4348, "lr": 5e-06, "epoch": 1.0043095371931796, "percentage": 33.48, "elapsed_time": "6:00:02", "remaining_time": "11:55:14"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7236c54b1257e132be0eb11ceeaf7e9b0537e78bcae9c6527f4a59db2ab8ae
+size 7224