Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_new_tokens": 256,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ca3fb841bee4cff14b2e462ea2de09ad87bb9b917dcea5988b5b92798683c5
+size 9949048046

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9feb0e50da1f7109a9c960499cf59fceedc93911c11f3fd98763ee1fe843eb
+size 9904474400

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13d5cb462af48e05cc9cc9a004c95e650425446d86a20afd156f32e717d2435
+size 6179210249

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26032588800
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98faac54bb4691597f342efb5e51a9af83dbd7d612cb41773ce3397e9739d297
+size 14511

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
+size 627

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,2124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0009760716430288746,
+  "global_step": 3100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 4.3689,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 3.0166,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6587,
+      "step": 30
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.7002,
+      "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.8247,
+      "step": 50
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.7709,
+      "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5964,
+      "step": 70
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5285,
+      "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6166,
+      "step": 90
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.7509,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.828864097595215,
+      "eval_runtime": 25015.5353,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6819,
+      "step": 110
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5314,
+      "step": 120
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4678,
+      "step": 130
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5079,
+      "step": 140
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6501,
+      "step": 150
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6981,
+      "step": 160
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5262,
+      "step": 170
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4819,
+      "step": 180
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4657,
+      "step": 190
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6072,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.7019286155700684,
+      "eval_runtime": 25020.9542,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5656,
+      "step": 210
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5185,
+      "step": 220
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4271,
+      "step": 230
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4286,
+      "step": 240
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5728,
+      "step": 250
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5597,
+      "step": 260
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4337,
+      "step": 270
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4491,
+      "step": 280
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4494,
+      "step": 290
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5075,
+      "step": 300
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.6475937366485596,
+      "eval_runtime": 25026.694,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.023,
+      "step": 300
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5654,
+      "step": 310
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.445,
+      "step": 320
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4604,
+      "step": 330
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4279,
+      "step": 340
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.545,
+      "step": 350
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.579,
+      "step": 360
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4052,
+      "step": 370
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3807,
+      "step": 380
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4444,
+      "step": 390
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4991,
+      "step": 400
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.606245279312134,
+      "eval_runtime": 25030.0633,
+      "eval_samples_per_second": 4.046,
+      "eval_steps_per_second": 2.023,
+      "step": 400
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.6451,
+      "step": 410
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4054,
+      "step": 420
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4127,
+      "step": 430
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3986,
+      "step": 440
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4556,
+      "step": 450
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.531,
+      "step": 460
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4173,
+      "step": 470
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4098,
+      "step": 480
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3917,
+      "step": 490
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5342,
+      "step": 500
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.553729772567749,
+      "eval_runtime": 25028.6332,
+      "eval_samples_per_second": 4.046,
+      "eval_steps_per_second": 2.023,
+      "step": 500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5335,
+      "step": 510
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4117,
+      "step": 520
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3891,
+      "step": 530
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3963,
+      "step": 540
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4859,
+      "step": 550
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5574,
+      "step": 560
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4218,
+      "step": 570
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3816,
+      "step": 580
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3866,
+      "step": 590
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4992,
+      "step": 600
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.5366227626800537,
+      "eval_runtime": 25013.3524,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 600
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5315,
+      "step": 610
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4261,
+      "step": 620
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3737,
+      "step": 630
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.385,
+      "step": 640
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.405,
+      "step": 650
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5182,
+      "step": 660
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3498,
+      "step": 670
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3539,
+      "step": 680
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3276,
+      "step": 690
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4602,
+      "step": 700
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.5101232528686523,
+      "eval_runtime": 25025.24,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.023,
+      "step": 700
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5107,
+      "step": 710
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3919,
+      "step": 720
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3818,
+      "step": 730
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3866,
+      "step": 740
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4079,
+      "step": 750
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4908,
+      "step": 760
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3965,
+      "step": 770
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.323,
+      "step": 780
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3136,
+      "step": 790
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3786,
+      "step": 800
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.50821590423584,
+      "eval_runtime": 25013.6917,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 800
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5106,
+      "step": 810
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3971,
+      "step": 820
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3305,
+      "step": 830
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3711,
+      "step": 840
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4803,
+      "step": 850
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4738,
+      "step": 860
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3712,
+      "step": 870
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3463,
+      "step": 880
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2843,
+      "step": 890
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3725,
+      "step": 900
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.494638204574585,
+      "eval_runtime": 25014.3413,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 900
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.5215,
+      "step": 910
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3802,
+      "step": 920
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3499,
+      "step": 930
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3199,
+      "step": 940
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3491,
+      "step": 950
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4885,
+      "step": 960
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3633,
+      "step": 970
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3226,
+      "step": 980
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2587,
+      "step": 990
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3803,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.458460807800293,
+      "eval_runtime": 25021.0121,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3921,
+      "step": 1010
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3305,
+      "step": 1020
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2907,
+      "step": 1030
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.319,
+      "step": 1040
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4507,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.467,
+      "step": 1060
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3639,
+      "step": 1070
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3189,
+      "step": 1080
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2974,
+      "step": 1090
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3331,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.454998254776001,
+      "eval_runtime": 25014.8749,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4715,
+      "step": 1110
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3549,
+      "step": 1120
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3196,
+      "step": 1130
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2633,
+      "step": 1140
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3661,
+      "step": 1150
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4783,
+      "step": 1160
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3531,
+      "step": 1170
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2943,
+      "step": 1180
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2409,
+      "step": 1190
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3605,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.448063611984253,
+      "eval_runtime": 25013.9619,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4612,
+      "step": 1210
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3746,
+      "step": 1220
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.304,
+      "step": 1230
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2925,
+      "step": 1240
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2926,
+      "step": 1250
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4145,
+      "step": 1260
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3593,
+      "step": 1270
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2417,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.301,
+      "step": 1290
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3336,
+      "step": 1300
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.424609661102295,
+      "eval_runtime": 25025.8125,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.023,
+      "step": 1300
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4126,
+      "step": 1310
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.308,
+      "step": 1320
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3052,
+      "step": 1330
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2798,
+      "step": 1340
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3208,
+      "step": 1350
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3309,
+      "step": 1360
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.331,
+      "step": 1370
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3068,
+      "step": 1380
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1971,
+      "step": 1390
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3114,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.4197137355804443,
+      "eval_runtime": 25013.8484,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4611,
+      "step": 1410
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2463,
+      "step": 1420
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2844,
+      "step": 1430
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2544,
+      "step": 1440
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3002,
+      "step": 1450
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4263,
+      "step": 1460
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.328,
+      "step": 1470
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2609,
+      "step": 1480
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2854,
+      "step": 1490
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3257,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.407323122024536,
+      "eval_runtime": 25024.2416,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.024,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4174,
+      "step": 1510
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2817,
+      "step": 1520
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2796,
+      "step": 1530
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2834,
+      "step": 1540
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2803,
+      "step": 1550
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.39,
+      "step": 1560
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2672,
+      "step": 1570
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3054,
+      "step": 1580
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2576,
+      "step": 1590
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3099,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.401474952697754,
+      "eval_runtime": 25023.95,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.024,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4225,
+      "step": 1610
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3135,
+      "step": 1620
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2705,
+      "step": 1630
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2075,
+      "step": 1640
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3811,
+      "step": 1650
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4239,
+      "step": 1660
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3319,
+      "step": 1670
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3106,
+      "step": 1680
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2231,
+      "step": 1690
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.311,
+      "step": 1700
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3863916397094727,
+      "eval_runtime": 25021.8392,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.024,
+      "step": 1700
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4332,
+      "step": 1710
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3183,
+      "step": 1720
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2177,
+      "step": 1730
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3045,
+      "step": 1740
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2627,
+      "step": 1750
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4087,
+      "step": 1760
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3026,
+      "step": 1770
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3316,
+      "step": 1780
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.256,
+      "step": 1790
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3276,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3831562995910645,
+      "eval_runtime": 25030.8877,
+      "eval_samples_per_second": 4.046,
+      "eval_steps_per_second": 2.023,
+      "step": 1800
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3993,
+      "step": 1810
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3138,
+      "step": 1820
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2652,
+      "step": 1830
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2848,
+      "step": 1840
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3009,
+      "step": 1850
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3942,
+      "step": 1860
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2951,
+      "step": 1870
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2457,
+      "step": 1880
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2514,
+      "step": 1890
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2656,
+      "step": 1900
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3777658939361572,
+      "eval_runtime": 25024.5627,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.023,
+      "step": 1900
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3702,
+      "step": 1910
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2896,
+      "step": 1920
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2635,
+      "step": 1930
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2506,
+      "step": 1940
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2108,
+      "step": 1950
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3469,
+      "step": 1960
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2863,
+      "step": 1970
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3095,
+      "step": 1980
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2594,
+      "step": 1990
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3124,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3710832595825195,
+      "eval_runtime": 25009.9377,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.025,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.42,
+      "step": 2010
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2725,
+      "step": 2020
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.243,
+      "step": 2030
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1696,
+      "step": 2040
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2764,
+      "step": 2050
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.4149,
+      "step": 2060
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3201,
+      "step": 2070
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2489,
+      "step": 2080
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1856,
+      "step": 2090
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.295,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3622617721557617,
+      "eval_runtime": 25023.6158,
+      "eval_samples_per_second": 4.047,
+      "eval_steps_per_second": 2.024,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3851,
+      "step": 2110
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2984,
+      "step": 2120
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.189,
+      "step": 2130
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2425,
+      "step": 2140
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.312,
+      "step": 2150
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3269,
+      "step": 2160
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3006,
+      "step": 2170
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2974,
+      "step": 2180
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1995,
+      "step": 2190
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3021,
+      "step": 2200
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.356457471847534,
+      "eval_runtime": 25014.0777,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 2200
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3836,
+      "step": 2210
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2795,
+      "step": 2220
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.196,
+      "step": 2230
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2284,
+      "step": 2240
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2464,
+      "step": 2250
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.406,
+      "step": 2260
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2814,
+      "step": 2270
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2595,
+      "step": 2280
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2578,
+      "step": 2290
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2471,
+      "step": 2300
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.334439516067505,
+      "eval_runtime": 25021.2061,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 2300
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3846,
+      "step": 2310
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2797,
+      "step": 2320
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2136,
+      "step": 2330
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2303,
+      "step": 2340
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3312,
+      "step": 2350
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3484,
+      "step": 2360
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3012,
+      "step": 2370
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2255,
+      "step": 2380
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1879,
+      "step": 2390
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2432,
+      "step": 2400
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3361294269561768,
+      "eval_runtime": 25017.0273,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 2400
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3223,
+      "step": 2410
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2756,
+      "step": 2420
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2312,
+      "step": 2430
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2296,
+      "step": 2440
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2083,
+      "step": 2450
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3684,
+      "step": 2460
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2336,
+      "step": 2470
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2262,
+      "step": 2480
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1644,
+      "step": 2490
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3096,
+      "step": 2500
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.336559772491455,
+      "eval_runtime": 25015.5454,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 2500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3185,
+      "step": 2510
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2768,
+      "step": 2520
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2151,
+      "step": 2530
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2017,
+      "step": 2540
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2616,
+      "step": 2550
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3333,
+      "step": 2560
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2404,
+      "step": 2570
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.25,
+      "step": 2580
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.22,
+      "step": 2590
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2884,
+      "step": 2600
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.332972526550293,
+      "eval_runtime": 25018.5289,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 2600
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3739,
+      "step": 2610
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2611,
+      "step": 2620
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2323,
+      "step": 2630
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1285,
+      "step": 2640
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2504,
+      "step": 2650
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3694,
+      "step": 2660
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2317,
+      "step": 2670
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2714,
+      "step": 2680
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1926,
+      "step": 2690
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2617,
+      "step": 2700
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.325580596923828,
+      "eval_runtime": 25014.9463,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 2700
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3665,
+      "step": 2710
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2604,
+      "step": 2720
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2129,
+      "step": 2730
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2166,
+      "step": 2740
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2418,
+      "step": 2750
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3793,
+      "step": 2760
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2684,
+      "step": 2770
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1758,
+      "step": 2780
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2116,
+      "step": 2790
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2753,
+      "step": 2800
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3111133575439453,
+      "eval_runtime": 25017.4138,
+      "eval_samples_per_second": 4.048,
+      "eval_steps_per_second": 2.024,
+      "step": 2800
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3754,
+      "step": 2810
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2508,
+      "step": 2820
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1793,
+      "step": 2830
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1444,
+      "step": 2840
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2093,
+      "step": 2850
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2917,
+      "step": 2860
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2487,
+      "step": 2870
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1931,
+      "step": 2880
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1862,
+      "step": 2890
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3007,
+      "step": 2900
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.3113691806793213,
+      "eval_runtime": 25009.312,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.025,
+      "step": 2900
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3637,
+      "step": 2910
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2385,
+      "step": 2920
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2092,
+      "step": 2930
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1755,
+      "step": 2940
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2523,
+      "step": 2950
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3127,
+      "step": 2960
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2634,
+      "step": 2970
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2487,
+      "step": 2980
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1269,
+      "step": 2990
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1926,
+      "step": 3000
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.2998297214508057,
+      "eval_runtime": 25014.9441,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 3000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3595,
+      "step": 3010
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2325,
+      "step": 3020
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1953,
+      "step": 3030
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.184,
+      "step": 3040
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1961,
+      "step": 3050
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.3776,
+      "step": 3060
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2627,
+      "step": 3070
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2189,
+      "step": 3080
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.1835,
+      "step": 3090
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 2.2283,
+      "step": 3100
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 2.2964084148406982,
+      "eval_runtime": 25012.2645,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 2.024,
+      "step": 3100
+    }
+  ],
+  "max_steps": 10000,
+  "num_train_epochs": 1,
+  "total_flos": 5.849399834018734e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc23f5cf300528a33ebc8b688eabafcfb40b0fb5049cbbda172a08cb5a27121f
+size 5755