Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9faab0b85f376cab3e0c6bdf7b46ab3afd1a7727dd410b37a6d9e48db6b702
+size 9976623130

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cfe9b1f1841297b86ed2e444c033dda5218aa13a28ade926da8e459a381433
+size 3500311811

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
+size 14575

trainer_state.json

@@ -0,0 +1,1867 @@
+{
+  "best_metric": 1.3819955587387085,
+  "best_model_checkpoint": "./lora-out/checkpoint-300",
+  "epoch": 0.6818181818181818,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 2.5888,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.4416,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8e-06,
+      "loss": 2.535,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.4892,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3e-06,
+      "loss": 2.519,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.6e-06,
+      "loss": 2.4774,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 2.3631,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 2.3431,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.4e-06,
+      "loss": 2.2224,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6e-06,
+      "loss": 2.1104,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.6e-06,
+      "loss": 2.0343,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.2e-06,
+      "loss": 1.9169,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.8e-06,
+      "loss": 1.7917,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.776,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9e-06,
+      "loss": 1.6864,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.6062,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.02e-05,
+      "loss": 1.5691,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.08e-05,
+      "loss": 1.5371,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 1.4481,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2e-05,
+      "loss": 1.4274,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.26e-05,
+      "loss": 1.4749,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.32e-05,
+      "loss": 1.3852,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.3800000000000002e-05,
+      "loss": 1.4056,
+      "step": 23
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.44e-05,
+      "loss": 1.3663,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4095,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.56e-05,
+      "loss": 1.4038,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.62e-05,
+      "loss": 1.3755,
+      "step": 27
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 1.371,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.74e-05,
+      "loss": 1.3186,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8e-05,
+      "loss": 1.3633,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.86e-05,
+      "loss": 1.3077,
+      "step": 31
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.3526,
+      "step": 32
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.98e-05,
+      "loss": 1.3222,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.04e-05,
+      "loss": 1.3295,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.1e-05,
+      "loss": 1.3303,
+      "step": 35
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.16e-05,
+      "loss": 1.278,
+      "step": 36
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.22e-05,
+      "loss": 1.3017,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 1.2691,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.3400000000000003e-05,
+      "loss": 1.2553,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4e-05,
+      "loss": 1.2799,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4599999999999998e-05,
+      "loss": 1.2588,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.52e-05,
+      "loss": 1.3316,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.58e-05,
+      "loss": 1.2778,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.64e-05,
+      "loss": 1.3134,
+      "step": 44
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.2694,
+      "step": 45
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.7600000000000003e-05,
+      "loss": 1.3031,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.8199999999999998e-05,
+      "loss": 1.271,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.88e-05,
+      "loss": 1.2857,
+      "step": 48
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.94e-05,
+      "loss": 1.2934,
+      "step": 49
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3e-05,
+      "loss": 1.2111,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 1.3991743326187134,
+      "eval_runtime": 19.271,
+      "eval_samples_per_second": 42.81,
+      "eval_steps_per_second": 14.27,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.999995410627115e-05,
+      "loss": 1.2867,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9999816425365436e-05,
+      "loss": 1.2333,
+      "step": 52
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9999586958125338e-05,
+      "loss": 1.264,
+      "step": 53
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9999265705955012e-05,
+      "loss": 1.256,
+      "step": 54
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.9998852670820255e-05,
+      "loss": 1.2545,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9998347855248495e-05,
+      "loss": 1.3151,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9997751262328776e-05,
+      "loss": 1.2318,
+      "step": 57
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9997062895711745e-05,
+      "loss": 1.2811,
+      "step": 58
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.9996282759609647e-05,
+      "loss": 1.2562,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9995410858796248e-05,
+      "loss": 1.2795,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9994447198606855e-05,
+      "loss": 1.2519,
+      "step": 61
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9993391784938268e-05,
+      "loss": 1.2248,
+      "step": 62
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9992244624248724e-05,
+      "loss": 1.2444,
+      "step": 63
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9991005723557904e-05,
+      "loss": 1.2628,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.998967509044683e-05,
+      "loss": 1.2788,
+      "step": 65
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9988252733057872e-05,
+      "loss": 1.2129,
+      "step": 66
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9986738660094662e-05,
+      "loss": 1.2414,
+      "step": 67
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9985132880822063e-05,
+      "loss": 1.2789,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.9983435405066108e-05,
+      "loss": 1.2925,
+      "step": 69
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.9981646243213917e-05,
+      "loss": 1.2704,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.997976540621368e-05,
+      "loss": 1.2619,
+      "step": 71
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.997779290557453e-05,
+      "loss": 1.2477,
+      "step": 72
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.997572875336653e-05,
+      "loss": 1.2773,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.997357296222057e-05,
+      "loss": 1.2413,
+      "step": 74
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.997132554532828e-05,
+      "loss": 1.2535,
+      "step": 75
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.9968986516441977e-05,
+      "loss": 1.235,
+      "step": 76
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.996655588987456e-05,
+      "loss": 1.2657,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9964033680499436e-05,
+      "loss": 1.2303,
+      "step": 78
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9961419903750415e-05,
+      "loss": 1.2303,
+      "step": 79
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.995871457562162e-05,
+      "loss": 1.2091,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.9955917712667405e-05,
+      "loss": 1.2518,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9953029332002226e-05,
+      "loss": 1.2326,
+      "step": 82
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.995004945130056e-05,
+      "loss": 1.236,
+      "step": 83
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.994697808879679e-05,
+      "loss": 1.2507,
+      "step": 84
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.994381526328508e-05,
+      "loss": 1.2909,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.994056099411928e-05,
+      "loss": 1.199,
+      "step": 86
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.9937215301212796e-05,
+      "loss": 1.2248,
+      "step": 87
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.993377820503847e-05,
+      "loss": 1.2329,
+      "step": 88
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.9930249726628458e-05,
+      "loss": 1.2258,
+      "step": 89
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.99266298875741e-05,
+      "loss": 1.2195,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.992291871002578e-05,
+      "loss": 1.2376,
+      "step": 91
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.99191162166928e-05,
+      "loss": 1.2228,
+      "step": 92
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.991522243084325e-05,
+      "loss": 1.229,
+      "step": 93
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.9911237376303827e-05,
+      "loss": 1.216,
+      "step": 94
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.9907161077459747e-05,
+      "loss": 1.2163,
+      "step": 95
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.9902993559254546e-05,
+      "loss": 1.2751,
+      "step": 96
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.989873484718995e-05,
+      "loss": 1.2386,
+      "step": 97
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.989438496732571e-05,
+      "loss": 1.2202,
+      "step": 98
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9889943946279467e-05,
+      "loss": 1.2149,
+      "step": 99
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9885411811226547e-05,
+      "loss": 1.2496,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.3802446126937866,
+      "eval_runtime": 19.2659,
+      "eval_samples_per_second": 42.822,
+      "eval_steps_per_second": 14.274,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9880788589899827e-05,
+      "loss": 1.2888,
+      "step": 101
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.9876074310589562e-05,
+      "loss": 1.2461,
+      "step": 102
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.987126900214319e-05,
+      "loss": 1.2299,
+      "step": 103
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.9866372693965192e-05,
+      "loss": 1.2413,
+      "step": 104
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.9861385416016872e-05,
+      "loss": 1.2735,
+      "step": 105
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.98563071988162e-05,
+      "loss": 1.2288,
+      "step": 106
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.9851138073437628e-05,
+      "loss": 1.2398,
+      "step": 107
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.9845878071511873e-05,
+      "loss": 1.2561,
+      "step": 108
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.984052722522575e-05,
+      "loss": 1.2486,
+      "step": 109
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.983508556732196e-05,
+      "loss": 1.2573,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.982955313109891e-05,
+      "loss": 1.2443,
+      "step": 111
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.982392995041048e-05,
+      "loss": 1.2766,
+      "step": 112
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.9818216059665826e-05,
+      "loss": 1.2736,
+      "step": 113
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.9812411493829193e-05,
+      "loss": 1.2713,
+      "step": 114
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.9806516288419662e-05,
+      "loss": 1.1709,
+      "step": 115
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.9800530479510968e-05,
+      "loss": 1.2394,
+      "step": 116
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.9794454103731248e-05,
+      "loss": 1.2215,
+      "step": 117
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.9788287198262846e-05,
+      "loss": 1.2532,
+      "step": 118
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.9782029800842065e-05,
+      "loss": 1.2705,
+      "step": 119
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.977568194975895e-05,
+      "loss": 1.2237,
+      "step": 120
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.9769243683857038e-05,
+      "loss": 1.2001,
+      "step": 121
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.976271504253313e-05,
+      "loss": 1.2475,
+      "step": 122
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.975609606573706e-05,
+      "loss": 1.2128,
+      "step": 123
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.9749386793971424e-05,
+      "loss": 1.2245,
+      "step": 124
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.974258726829136e-05,
+      "loss": 1.2454,
+      "step": 125
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9735697530304274e-05,
+      "loss": 1.2235,
+      "step": 126
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9728717622169605e-05,
+      "loss": 1.2109,
+      "step": 127
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9721647586598558e-05,
+      "loss": 1.213,
+      "step": 128
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9714487466853836e-05,
+      "loss": 1.2002,
+      "step": 129
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.970723730674938e-05,
+      "loss": 1.2559,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.9699897150650117e-05,
+      "loss": 1.259,
+      "step": 131
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.969246704347166e-05,
+      "loss": 1.2448,
+      "step": 132
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.9684947030680048e-05,
+      "loss": 1.2077,
+      "step": 133
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.967733715829148e-05,
+      "loss": 1.2555,
+      "step": 134
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.9669637472872005e-05,
+      "loss": 1.2115,
+      "step": 135
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.9661848021537262e-05,
+      "loss": 1.217,
+      "step": 136
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.9653968851952186e-05,
+      "loss": 1.2788,
+      "step": 137
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.9646000012330696e-05,
+      "loss": 1.2669,
+      "step": 138
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.9637941551435432e-05,
+      "loss": 1.2502,
+      "step": 139
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.9629793518577443e-05,
+      "loss": 1.2325,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.9621555963615863e-05,
+      "loss": 1.2048,
+      "step": 141
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.9613228936957654e-05,
+      "loss": 1.214,
+      "step": 142
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.960481248955725e-05,
+      "loss": 1.1924,
+      "step": 143
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.959630667291627e-05,
+      "loss": 1.2184,
+      "step": 144
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.9587711539083208e-05,
+      "loss": 1.2191,
+      "step": 145
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.9579027140653083e-05,
+      "loss": 1.2292,
+      "step": 146
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.957025353076716e-05,
+      "loss": 1.2634,
+      "step": 147
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.95613907631126e-05,
+      "loss": 1.2098,
+      "step": 148
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.955243889192212e-05,
+      "loss": 1.2232,
+      "step": 149
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.95433979719737e-05,
+      "loss": 1.2197,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 1.3666081428527832,
+      "eval_runtime": 19.2645,
+      "eval_samples_per_second": 42.825,
+      "eval_steps_per_second": 14.275,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.9534268058590196e-05,
+      "loss": 1.2501,
+      "step": 151
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.952504920763905e-05,
+      "loss": 1.2316,
+      "step": 152
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.9515741475531928e-05,
+      "loss": 1.1957,
+      "step": 153
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.9506344919224355e-05,
+      "loss": 1.2428,
+      "step": 154
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.9496859596215406e-05,
+      "loss": 1.2178,
+      "step": 155
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.9487285564547328e-05,
+      "loss": 1.207,
+      "step": 156
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9477622882805186e-05,
+      "loss": 1.2126,
+      "step": 157
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9467871610116514e-05,
+      "loss": 1.195,
+      "step": 158
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9458031806150946e-05,
+      "loss": 1.2331,
+      "step": 159
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9448103531119858e-05,
+      "loss": 1.2291,
+      "step": 160
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.9438086845775988e-05,
+      "loss": 1.237,
+      "step": 161
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.9427981811413075e-05,
+      "loss": 1.2473,
+      "step": 162
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.9417788489865485e-05,
+      "loss": 1.2185,
+      "step": 163
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.9407506943507817e-05,
+      "loss": 1.1911,
+      "step": 164
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9397137235254543e-05,
+      "loss": 1.2265,
+      "step": 165
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9386679428559596e-05,
+      "loss": 1.2694,
+      "step": 166
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9376133587416023e-05,
+      "loss": 1.2135,
+      "step": 167
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9365499776355545e-05,
+      "loss": 1.1883,
+      "step": 168
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.9354778060448197e-05,
+      "loss": 1.17,
+      "step": 169
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.9343968505301914e-05,
+      "loss": 1.2016,
+      "step": 170
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.9333071177062134e-05,
+      "loss": 1.2053,
+      "step": 171
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.93220861424114e-05,
+      "loss": 1.2364,
+      "step": 172
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.931101346856893e-05,
+      "loss": 1.2095,
+      "step": 173
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.929985322329024e-05,
+      "loss": 1.1902,
+      "step": 174
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.9288605474866687e-05,
+      "loss": 1.2318,
+      "step": 175
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.9277270292125095e-05,
+      "loss": 1.2324,
+      "step": 176
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 1.2255,
+      "step": 177
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.9254337901669754e-05,
+      "loss": 1.1992,
+      "step": 178
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9242740834283058e-05,
+      "loss": 1.1802,
+      "step": 179
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9231056613231567e-05,
+      "loss": 1.2289,
+      "step": 180
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9219285310012953e-05,
+      "loss": 1.2465,
+      "step": 181
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9207426996657745e-05,
+      "loss": 1.1908,
+      "step": 182
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.91954817457289e-05,
+      "loss": 1.2223,
+      "step": 183
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.9183449630321373e-05,
+      "loss": 1.2173,
+      "step": 184
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.9171330724061648e-05,
+      "loss": 1.2304,
+      "step": 185
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.91591251011073e-05,
+      "loss": 1.2192,
+      "step": 186
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.914683283614653e-05,
+      "loss": 1.1925,
+      "step": 187
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.9134454004397725e-05,
+      "loss": 1.1751,
+      "step": 188
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.9121988681608982e-05,
+      "loss": 1.2152,
+      "step": 189
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.9109436944057662e-05,
+      "loss": 1.1772,
+      "step": 190
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.9096798868549888e-05,
+      "loss": 1.2318,
+      "step": 191
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.908407453242013e-05,
+      "loss": 1.1974,
+      "step": 192
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.9071264013530676e-05,
+      "loss": 1.2101,
+      "step": 193
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.9058367390271195e-05,
+      "loss": 1.201,
+      "step": 194
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.9045384741558237e-05,
+      "loss": 1.1733,
+      "step": 195
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9032316146834758e-05,
+      "loss": 1.1894,
+      "step": 196
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9019161686069628e-05,
+      "loss": 1.1857,
+      "step": 197
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9005921439757145e-05,
+      "loss": 1.2126,
+      "step": 198
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.899259548891655e-05,
+      "loss": 1.1682,
+      "step": 199
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.8979183915091518e-05,
+      "loss": 1.2026,
+      "step": 200
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 1.3707293272018433,
+      "eval_runtime": 19.2762,
+      "eval_samples_per_second": 42.799,
+      "eval_steps_per_second": 14.266,
+      "step": 200
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8965686800349666e-05,
+      "loss": 1.2136,
+      "step": 201
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8952104227282055e-05,
+      "loss": 1.2168,
+      "step": 202
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.893843627900267e-05,
+      "loss": 1.2064,
+      "step": 203
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.892468303914793e-05,
+      "loss": 1.2324,
+      "step": 204
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8910844591876156e-05,
+      "loss": 1.2649,
+      "step": 205
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8896921021867082e-05,
+      "loss": 1.2351,
+      "step": 206
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8882912414321308e-05,
+      "loss": 1.2662,
+      "step": 207
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8868818854959803e-05,
+      "loss": 1.1938,
+      "step": 208
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.8854640430023366e-05,
+      "loss": 1.2462,
+      "step": 209
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.8840377226272102e-05,
+      "loss": 1.1818,
+      "step": 210
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.882602933098489e-05,
+      "loss": 1.2178,
+      "step": 211
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.8811596831958854e-05,
+      "loss": 1.2202,
+      "step": 212
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.8797079817508816e-05,
+      "loss": 1.2,
+      "step": 213
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.878247837646677e-05,
+      "loss": 1.2396,
+      "step": 214
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.8767792598181326e-05,
+      "loss": 1.2047,
+      "step": 215
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.8753022572517166e-05,
+      "loss": 1.2051,
+      "step": 216
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.87381683898545e-05,
+      "loss": 1.1645,
+      "step": 217
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.8723230141088504e-05,
+      "loss": 1.1804,
+      "step": 218
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.8708207917628766e-05,
+      "loss": 1.1753,
+      "step": 219
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.869310181139874e-05,
+      "loss": 1.2039,
+      "step": 220
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.867791191483516e-05,
+      "loss": 1.2174,
+      "step": 221
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.8662638320887488e-05,
+      "loss": 1.192,
+      "step": 222
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.864728112301736e-05,
+      "loss": 1.2348,
+      "step": 223
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.8631840415197975e-05,
+      "loss": 1.1923,
+      "step": 224
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.861631629191356e-05,
+      "loss": 1.2317,
+      "step": 225
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.8600708848158767e-05,
+      "loss": 1.1599,
+      "step": 226
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.85850181794381e-05,
+      "loss": 1.2131,
+      "step": 227
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.856924438176533e-05,
+      "loss": 1.1725,
+      "step": 228
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.8553387551662914e-05,
+      "loss": 1.2024,
+      "step": 229
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.8537447786161393e-05,
+      "loss": 1.2355,
+      "step": 230
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.8521425182798807e-05,
+      "loss": 1.1666,
+      "step": 231
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.8505319839620082e-05,
+      "loss": 1.192,
+      "step": 232
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.8489131855176457e-05,
+      "loss": 1.2033,
+      "step": 233
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.8472861328524866e-05,
+      "loss": 1.2144,
+      "step": 234
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.8456508359227316e-05,
+      "loss": 1.2534,
+      "step": 235
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.8440073047350316e-05,
+      "loss": 1.2154,
+      "step": 236
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.8423555493464228e-05,
+      "loss": 1.2348,
+      "step": 237
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.8406955798642668e-05,
+      "loss": 1.2115,
+      "step": 238
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.8390274064461898e-05,
+      "loss": 1.171,
+      "step": 239
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.8373510393000163e-05,
+      "loss": 1.1938,
+      "step": 240
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.835666488683714e-05,
+      "loss": 1.2592,
+      "step": 241
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.8339737649053223e-05,
+      "loss": 1.2453,
+      "step": 242
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.8322728783228963e-05,
+      "loss": 1.2605,
+      "step": 243
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.8305638393444394e-05,
+      "loss": 1.1979,
+      "step": 244
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.828846658427841e-05,
+      "loss": 1.2316,
+      "step": 245
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.8271213460808126e-05,
+      "loss": 1.1768,
+      "step": 246
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.8253879128608234e-05,
+      "loss": 1.2156,
+      "step": 247
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.8236463693750347e-05,
+      "loss": 1.196,
+      "step": 248
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.8218967262802372e-05,
+      "loss": 1.2093,
+      "step": 249
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.8201389942827827e-05,
+      "loss": 1.1745,
+      "step": 250
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 1.3811564445495605,
+      "eval_runtime": 19.2683,
+      "eval_samples_per_second": 42.816,
+      "eval_steps_per_second": 14.272,
+      "step": 250
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.818373184138522e-05,
+      "loss": 1.1833,
+      "step": 251
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.8165993066527362e-05,
+      "loss": 1.2108,
+      "step": 252
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.814817372680073e-05,
+      "loss": 1.1952,
+      "step": 253
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.813027393124478e-05,
+      "loss": 1.2075,
+      "step": 254
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.811229378939129e-05,
+      "loss": 1.1751,
+      "step": 255
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.80942334112637e-05,
+      "loss": 1.2623,
+      "step": 256
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.807609290737642e-05,
+      "loss": 1.1907,
+      "step": 257
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.8057872388734165e-05,
+      "loss": 1.2018,
+      "step": 258
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.8039571966831276e-05,
+      "loss": 1.233,
+      "step": 259
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.8021191753651025e-05,
+      "loss": 1.1869,
+      "step": 260
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.8002731861664957e-05,
+      "loss": 1.19,
+      "step": 261
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.798419240383218e-05,
+      "loss": 1.2182,
+      "step": 262
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.7965573493598663e-05,
+      "loss": 1.1963,
+      "step": 263
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.794687524489657e-05,
+      "loss": 1.2597,
+      "step": 264
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.7928097772143555e-05,
+      "loss": 1.2109,
+      "step": 265
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.7909241190242047e-05,
+      "loss": 1.2121,
+      "step": 266
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.7890305614578558e-05,
+      "loss": 1.2048,
+      "step": 267
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.787129116102298e-05,
+      "loss": 1.1774,
+      "step": 268
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.785219794592787e-05,
+      "loss": 1.2256,
+      "step": 269
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.783302608612774e-05,
+      "loss": 1.2227,
+      "step": 270
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.781377569893834e-05,
+      "loss": 1.1616,
+      "step": 271
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.7794446902155946e-05,
+      "loss": 1.2262,
+      "step": 272
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.7775039814056624e-05,
+      "loss": 1.2172,
+      "step": 273
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.775555455339554e-05,
+      "loss": 1.1975,
+      "step": 274
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.7735991239406184e-05,
+      "loss": 1.1991,
+      "step": 275
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.7716349991799682e-05,
+      "loss": 1.1887,
+      "step": 276
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.7696630930764055e-05,
+      "loss": 1.2017,
+      "step": 277
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.7676834176963457e-05,
+      "loss": 1.1839,
+      "step": 278
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.7656959851537476e-05,
+      "loss": 1.2194,
+      "step": 279
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.7637008076100362e-05,
+      "loss": 1.1807,
+      "step": 280
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.76169789727403e-05,
+      "loss": 1.2413,
+      "step": 281
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.759687266401865e-05,
+      "loss": 1.2419,
+      "step": 282
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.7576689272969218e-05,
+      "loss": 1.2428,
+      "step": 283
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.7556428923097478e-05,
+      "loss": 1.202,
+      "step": 284
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.753609173837982e-05,
+      "loss": 1.186,
+      "step": 285
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.7515677843262826e-05,
+      "loss": 1.1984,
+      "step": 286
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.7495187362662454e-05,
+      "loss": 1.2065,
+      "step": 287
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.7474620421963318e-05,
+      "loss": 1.1854,
+      "step": 288
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.7453977147017888e-05,
+      "loss": 1.2034,
+      "step": 289
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.7433257664145757e-05,
+      "loss": 1.1712,
+      "step": 290
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.7412462100132835e-05,
+      "loss": 1.2189,
+      "step": 291
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.7391590582230573e-05,
+      "loss": 1.2238,
+      "step": 292
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.737064323815523e-05,
+      "loss": 1.2072,
+      "step": 293
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.7349620196087014e-05,
+      "loss": 1.2197,
+      "step": 294
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.7328521584669376e-05,
+      "loss": 1.2501,
+      "step": 295
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2.7307347533008175e-05,
+      "loss": 1.1692,
+      "step": 296
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.7286098170670905e-05,
+      "loss": 1.1953,
+      "step": 297
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.7264773627685888e-05,
+      "loss": 1.193,
+      "step": 298
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.7243374034541505e-05,
+      "loss": 1.1933,
+      "step": 299
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2.7221899522185365e-05,
+      "loss": 1.1974,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.3819955587387085,
+      "eval_runtime": 19.2854,
+      "eval_samples_per_second": 42.779,
+      "eval_steps_per_second": 14.26,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1320,
+  "num_train_epochs": 3,
+  "save_steps": 300,
+  "total_flos": 1.461438690361344e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78415bcae2f7c3f9938bf64b1d511b45667b5279d9a9aef0113a7151b52d21fb
+size 4411