adding remaining files

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0"
+}

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13476835328
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1280,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,971 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9960768928991763,
+  "global_step": 954,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.997799572243123e-06,
+      "loss": 0.4974,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.990195641770761e-06,
+      "loss": 0.4841,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.4602764844894409,
+      "eval_runtime": 62.0223,
+      "eval_samples_per_second": 13.431,
+      "eval_steps_per_second": 0.855,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.9771693033643e-06,
+      "loss": 0.4748,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.958734711603195e-06,
+      "loss": 0.4678,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.45144811272621155,
+      "eval_runtime": 61.8568,
+      "eval_samples_per_second": 13.467,
+      "eval_steps_per_second": 0.857,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.934911897741493e-06,
+      "loss": 0.4687,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.905726747941616e-06,
+      "loss": 0.4687,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.44708773493766785,
+      "eval_runtime": 62.0907,
+      "eval_samples_per_second": 13.416,
+      "eval_steps_per_second": 0.854,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.871210975146135e-06,
+      "loss": 0.473,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.831402084618113e-06,
+      "loss": 0.4608,
+      "step": 80
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.44395506381988525,
+      "eval_runtime": 61.9484,
+      "eval_samples_per_second": 13.447,
+      "eval_steps_per_second": 0.856,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.786343333187412e-06,
+      "loss": 0.4542,
+      "step": 90
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.736083682247287e-06,
+      "loss": 0.4593,
+      "step": 100
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.43974635004997253,
+      "eval_runtime": 61.9084,
+      "eval_samples_per_second": 13.455,
+      "eval_steps_per_second": 0.856,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.680677744552346e-06,
+      "loss": 0.4681,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.620185724875652e-06,
+      "loss": 0.4488,
+      "step": 120
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.435758113861084,
+      "eval_runtime": 61.8043,
+      "eval_samples_per_second": 13.478,
+      "eval_steps_per_second": 0.858,
+      "step": 120
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.55467335458948e-06,
+      "loss": 0.4478,
+      "step": 130
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.484211820240797e-06,
+      "loss": 0.4494,
+      "step": 140
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.434115469455719,
+      "eval_runtime": 61.841,
+      "eval_samples_per_second": 13.47,
+      "eval_steps_per_second": 0.857,
+      "step": 140
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.408877686199078e-06,
+      "loss": 0.44,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.328752811460542e-06,
+      "loss": 0.4477,
+      "step": 160
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.4319334030151367,
+      "eval_runtime": 61.9956,
+      "eval_samples_per_second": 13.436,
+      "eval_steps_per_second": 0.855,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.243924260699133e-06,
+      "loss": 0.4465,
+      "step": 170
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.154484209661002e-06,
+      "loss": 0.445,
+      "step": 180
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.42997926473617554,
+      "eval_runtime": 62.0149,
+      "eval_samples_per_second": 13.432,
+      "eval_steps_per_second": 0.855,
+      "step": 180
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.060529845005184e-06,
+      "loss": 0.4332,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.962163258699397e-06,
+      "loss": 0.4366,
+      "step": 200
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.4274918735027313,
+      "eval_runtime": 61.8797,
+      "eval_samples_per_second": 13.462,
+      "eval_steps_per_second": 0.857,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.859491337085643e-06,
+      "loss": 0.428,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.752625644736204e-06,
+      "loss": 0.442,
+      "step": 220
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.42491650581359863,
+      "eval_runtime": 62.1183,
+      "eval_samples_per_second": 13.41,
+      "eval_steps_per_second": 0.853,
+      "step": 220
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.641682303226197e-06,
+      "loss": 0.4442,
+      "step": 230
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.526781864954453e-06,
+      "loss": 0.4424,
+      "step": 240
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.4228505492210388,
+      "eval_runtime": 62.0338,
+      "eval_samples_per_second": 13.428,
+      "eval_steps_per_second": 0.854,
+      "step": 240
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.40804918214979e-06,
+      "loss": 0.4301,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.28561327120505e-06,
+      "loss": 0.4427,
+      "step": 260
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 0.41998758912086487,
+      "eval_runtime": 61.9344,
+      "eval_samples_per_second": 13.45,
+      "eval_steps_per_second": 0.856,
+      "step": 260
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.159607172486301e-06,
+      "loss": 0.4316,
+      "step": 270
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.030167805769537e-06,
+      "loss": 0.4372,
+      "step": 280
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.4175536036491394,
+      "eval_runtime": 61.971,
+      "eval_samples_per_second": 13.442,
+      "eval_steps_per_second": 0.855,
+      "step": 280
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.897435821461964e-06,
+      "loss": 0.4398,
+      "step": 290
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.761555447769548e-06,
+      "loss": 0.4335,
+      "step": 300
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.4155929982662201,
+      "eval_runtime": 61.9696,
+      "eval_samples_per_second": 13.442,
+      "eval_steps_per_second": 0.855,
+      "step": 300
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.622674333976863e-06,
+      "loss": 0.4371,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.4809433900095705e-06,
+      "loss": 0.4088,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.41465404629707336,
+      "eval_runtime": 61.9822,
+      "eval_samples_per_second": 13.439,
+      "eval_steps_per_second": 0.855,
+      "step": 320
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.336516622453833e-06,
+      "loss": 0.3166,
+      "step": 330
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.1895509672108674e-06,
+      "loss": 0.3145,
+      "step": 340
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.42051395773887634,
+      "eval_runtime": 62.5118,
+      "eval_samples_per_second": 13.325,
+      "eval_steps_per_second": 0.848,
+      "step": 340
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.040206118968466e-06,
+      "loss": 0.3136,
+      "step": 350
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 6.88864435767478e-06,
+      "loss": 0.3151,
+      "step": 360
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 0.4205115735530853,
+      "eval_runtime": 62.5792,
+      "eval_samples_per_second": 13.311,
+      "eval_steps_per_second": 0.847,
+      "step": 360
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.735030372202942e-06,
+      "loss": 0.3137,
+      "step": 370
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.579531081398105e-06,
+      "loss": 0.3019,
+      "step": 380
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.4216003119945526,
+      "eval_runtime": 62.3646,
+      "eval_samples_per_second": 13.357,
+      "eval_steps_per_second": 0.85,
+      "step": 380
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.4223154527013755e-06,
+      "loss": 0.3044,
+      "step": 390
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.263554318547713e-06,
+      "loss": 0.3044,
+      "step": 400
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.4185173809528351,
+      "eval_runtime": 61.9058,
+      "eval_samples_per_second": 13.456,
+      "eval_steps_per_second": 0.856,
+      "step": 400
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.1034201907373045e-06,
+      "loss": 0.305,
+      "step": 410
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.942087072982131e-06,
+      "loss": 0.3034,
+      "step": 420
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.41815003752708435,
+      "eval_runtime": 62.0238,
+      "eval_samples_per_second": 13.43,
+      "eval_steps_per_second": 0.855,
+      "step": 420
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 5.779730271831384e-06,
+      "loss": 0.3115,
+      "step": 430
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 5.616526206181215e-06,
+      "loss": 0.3026,
+      "step": 440
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 0.41711267828941345,
+      "eval_runtime": 62.5134,
+      "eval_samples_per_second": 13.325,
+      "eval_steps_per_second": 0.848,
+      "step": 440
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.4526522155758015e-06,
+      "loss": 0.3077,
+      "step": 450
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.288286367508009e-06,
+      "loss": 0.3062,
+      "step": 460
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.41751572489738464,
+      "eval_runtime": 62.561,
+      "eval_samples_per_second": 13.315,
+      "eval_steps_per_second": 0.847,
+      "step": 460
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.123607263929075e-06,
+      "loss": 0.3076,
+      "step": 470
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 4.958793847177518e-06,
+      "loss": 0.315,
+      "step": 480
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 0.41455498337745667,
+      "eval_runtime": 62.0669,
+      "eval_samples_per_second": 13.421,
+      "eval_steps_per_second": 0.854,
+      "step": 480
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.7940252055382115e-06,
+      "loss": 0.3024,
+      "step": 490
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.629480378642832e-06,
+      "loss": 0.3124,
+      "step": 500
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.41453319787979126,
+      "eval_runtime": 61.9067,
+      "eval_samples_per_second": 13.456,
+      "eval_steps_per_second": 0.856,
+      "step": 500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.46533816292321e-06,
+      "loss": 0.31,
+      "step": 510
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.301776917328918e-06,
+      "loss": 0.3096,
+      "step": 520
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 0.41273748874664307,
+      "eval_runtime": 62.1417,
+      "eval_samples_per_second": 13.405,
+      "eval_steps_per_second": 0.853,
+      "step": 520
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.138974369520252e-06,
+      "loss": 0.3044,
+      "step": 530
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.977107422747163e-06,
+      "loss": 0.3178,
+      "step": 540
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 0.4111482501029968,
+      "eval_runtime": 62.5639,
+      "eval_samples_per_second": 13.314,
+      "eval_steps_per_second": 0.847,
+      "step": 540
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.816351963624017e-06,
+      "loss": 0.3102,
+      "step": 550
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.6568826710090353e-06,
+      "loss": 0.3044,
+      "step": 560
+    },
+    {
+      "epoch": 1.76,
+      "eval_loss": 0.4110707640647888,
+      "eval_runtime": 62.5689,
+      "eval_samples_per_second": 13.313,
+      "eval_steps_per_second": 0.847,
+      "step": 560
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.4988728261960957e-06,
+      "loss": 0.306,
+      "step": 570
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.3424941246251574e-06,
+      "loss": 0.3078,
+      "step": 580
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 0.4091060757637024,
+      "eval_runtime": 62.0676,
+      "eval_samples_per_second": 13.421,
+      "eval_steps_per_second": 0.854,
+      "step": 580
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.1879164893158713e-06,
+      "loss": 0.2977,
+      "step": 590
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 3.035307886227156e-06,
+      "loss": 0.2967,
+      "step": 600
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.4094270169734955,
+      "eval_runtime": 62.0655,
+      "eval_samples_per_second": 13.421,
+      "eval_steps_per_second": 0.854,
+      "step": 600
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.8848341417433036e-06,
+      "loss": 0.3069,
+      "step": 610
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2.736658762485005e-06,
+      "loss": 0.3068,
+      "step": 620
+    },
+    {
+      "epoch": 1.95,
+      "eval_loss": 0.4080323278903961,
+      "eval_runtime": 62.0098,
+      "eval_samples_per_second": 13.433,
+      "eval_steps_per_second": 0.855,
+      "step": 620
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.590942757641035e-06,
+      "loss": 0.3037,
+      "step": 630
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 2.447844464013703e-06,
+      "loss": 0.276,
+      "step": 640
+    },
+    {
+      "epoch": 2.01,
+      "eval_loss": 0.4152510464191437,
+      "eval_runtime": 61.9609,
+      "eval_samples_per_second": 13.444,
+      "eval_steps_per_second": 0.855,
+      "step": 640
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.3075193739681182e-06,
+      "loss": 0.2327,
+      "step": 650
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 2.170119966472293e-06,
+      "loss": 0.2288,
+      "step": 660
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 0.43204566836357117,
+      "eval_runtime": 62.0792,
+      "eval_samples_per_second": 13.418,
+      "eval_steps_per_second": 0.854,
+      "step": 660
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 2.0357955414116075e-06,
+      "loss": 0.2267,
+      "step": 670
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.9046920573577239e-06,
+      "loss": 0.2244,
+      "step": 680
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.4292474389076233,
+      "eval_runtime": 62.0223,
+      "eval_samples_per_second": 13.431,
+      "eval_steps_per_second": 0.855,
+      "step": 680
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.7769519729682105e-06,
+      "loss": 0.2327,
+      "step": 690
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.6527140921892066e-06,
+      "loss": 0.2336,
+      "step": 700
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 0.427610844373703,
+      "eval_runtime": 62.1107,
+      "eval_samples_per_second": 13.412,
+      "eval_steps_per_second": 0.853,
+      "step": 700
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.532113413429357e-06,
+      "loss": 0.2386,
+      "step": 710
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 1.4152809828688708e-06,
+      "loss": 0.2266,
+      "step": 720
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 0.4290391206741333,
+      "eval_runtime": 62.2449,
+      "eval_samples_per_second": 13.383,
+      "eval_steps_per_second": 0.851,
+      "step": 720
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.3023437520631426e-06,
+      "loss": 0.2328,
+      "step": 730
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.1934244399956206e-06,
+      "loss": 0.2312,
+      "step": 740
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 0.42950907349586487,
+      "eval_runtime": 62.2915,
+      "eval_samples_per_second": 13.373,
+      "eval_steps_per_second": 0.851,
+      "step": 740
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.0886413997298595e-06,
+      "loss": 0.2338,
+      "step": 750
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 9.881084898056197e-07,
+      "loss": 0.2277,
+      "step": 760
+    },
+    {
+      "epoch": 2.39,
+      "eval_loss": 0.4284292161464691,
+      "eval_runtime": 62.4097,
+      "eval_samples_per_second": 13.347,
+      "eval_steps_per_second": 0.849,
+      "step": 760
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.919349505187813e-07,
+      "loss": 0.2333,
+      "step": 770
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.002252852194992e-07,
+      "loss": 0.2332,
+      "step": 780
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.42790091037750244,
+      "eval_runtime": 62.4651,
+      "eval_samples_per_second": 13.335,
+      "eval_steps_per_second": 0.848,
+      "step": 780
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.130791467575676e-07,
+      "loss": 0.2257,
+      "step": 790
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 6.305912291984229e-07,
+      "loss": 0.2289,
+      "step": 800
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 0.42792582511901855,
+      "eval_runtime": 62.5296,
+      "eval_samples_per_second": 13.322,
+      "eval_steps_per_second": 0.848,
+      "step": 800
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 5.528511649273932e-07,
+      "loss": 0.2303,
+      "step": 810
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 4.799434272540576e-07,
+      "loss": 0.2279,
+      "step": 820
+    },
+    {
+      "epoch": 2.58,
+      "eval_loss": 0.4278266131877899,
+      "eval_runtime": 62.5218,
+      "eval_samples_per_second": 13.323,
+      "eval_steps_per_second": 0.848,
+      "step": 820
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.1194723862250317e-07,
+      "loss": 0.2267,
+      "step": 830
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 3.4893648452724636e-07,
+      "loss": 0.2312,
+      "step": 840
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.4273243546485901,
+      "eval_runtime": 62.5591,
+      "eval_samples_per_second": 13.315,
+      "eval_steps_per_second": 0.847,
+      "step": 840
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.9097963322834597e-07,
+      "loss": 0.2306,
+      "step": 850
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 2.3813966135294574e-07,
+      "loss": 0.2334,
+      "step": 860
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 0.42646506428718567,
+      "eval_runtime": 62.6378,
+      "eval_samples_per_second": 13.299,
+      "eval_steps_per_second": 0.846,
+      "step": 860
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.9047398546410633e-07,
+      "loss": 0.2306,
+      "step": 870
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.4803439967125022e-07,
+      "loss": 0.2278,
+      "step": 880
+    },
+    {
+      "epoch": 2.76,
+      "eval_loss": 0.42754805088043213,
+      "eval_runtime": 62.1476,
+      "eval_samples_per_second": 13.404,
+      "eval_steps_per_second": 0.853,
+      "step": 880
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.1086701935005606e-07,
+      "loss": 0.2296,
+      "step": 890
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 7.901223103291833e-08,
+      "loss": 0.2295,
+      "step": 900
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 0.4276488721370697,
+      "eval_runtime": 61.9957,
+      "eval_samples_per_second": 13.436,
+      "eval_steps_per_second": 0.855,
+      "step": 900
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.250464852444792e-08,
+      "loss": 0.2334,
+      "step": 910
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.137307528968292e-08,
+      "loss": 0.2292,
+      "step": 920
+    },
+    {
+      "epoch": 2.89,
+      "eval_loss": 0.4273829162120819,
+      "eval_runtime": 62.0452,
+      "eval_samples_per_second": 13.426,
+      "eval_steps_per_second": 0.854,
+      "step": 920
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.5640473155894566e-08,
+      "loss": 0.2284,
+      "step": 930
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.323937361977338e-09,
+      "loss": 0.2291,
+      "step": 940
+    },
+    {
+      "epoch": 2.95,
+      "eval_loss": 0.42734310030937195,
+      "eval_runtime": 61.9825,
+      "eval_samples_per_second": 13.439,
+      "eval_steps_per_second": 0.855,
+      "step": 940
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 4.346779825575853e-10,
+      "loss": 0.2288,
+      "step": 950
+    },
+    {
+      "epoch": 3.0,
+      "step": 954,
+      "total_flos": 6.195687991759864e+18,
+      "train_loss": 0.1527079766776327,
+      "train_runtime": 29559.5606,
+      "train_samples_per_second": 4.138,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "max_steps": 954,
+  "num_train_epochs": 3,
+  "total_flos": 6.195687991759864e+18,
+  "trial_name": null,
+  "trial_params": null
+}