Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/nfs_data_storage/llama2_hf/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": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.28.0"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ce08c91e998b40fd73b4a8673663c40488e84e4a93711fa06a44239081e7b7
+size 9956546443

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8248b14b737d33883c0be53eb0ab1dd4117223cc3f38bcf2e9671aa13dbd749
+size 9940859009

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461fda24e61f954387ddddf2b22c954b4bb8055868f8a934a5e52cd7ff13bbdb
+size 9940859567

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d930e03b6e86c2caf6ee5e1ed0ce03a171b09255c198b6faae88f2531de1743
+size 9867417913

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b693fc217e22cef8a45b17d3ecb092abfd79437f23ab588ab0e7036ed314fd
+size 9867459649

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3050261f51c3642693e2def1625b67f1abfe122eab2cec89e5047b433d7eca1
+size 2490476719

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063467520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+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": 4096,
+  "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 +1,997 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9953917050691244,
+  "global_step": 162,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4312,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4237,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2e-05,
+      "loss": 1.3934,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.3338,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 1.3131,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997998037428528e-05,
+      "loss": 1.2994,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.999199295128493e-05,
+      "loss": 1.2578,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.998198714596076e-05,
+      "loss": 1.2713,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.996798462770555e-05,
+      "loss": 1.2291,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.994999100302281e-05,
+      "loss": 1.2212,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.992801347642515e-05,
+      "loss": 1.2206,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9902060847549716e-05,
+      "loss": 1.2123,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.987214350763483e-05,
+      "loss": 1.2006,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9838273435359447e-05,
+      "loss": 1.1977,
+      "step": 14
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9800464192046956e-05,
+      "loss": 1.1972,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9758730916235356e-05,
+      "loss": 1.201,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9713090317615877e-05,
+      "loss": 1.1958,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.966356067034256e-05,
+      "loss": 1.1706,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.96101618057154e-05,
+      "loss": 1.1926,
+      "step": 19
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9552915104240067e-05,
+      "loss": 1.192,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9491843487067305e-05,
+      "loss": 1.1897,
+      "step": 21
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9426971406815464e-05,
+      "loss": 1.1891,
+      "step": 22
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9358324837779864e-05,
+      "loss": 1.186,
+      "step": 23
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9285931265532875e-05,
+      "loss": 1.1704,
+      "step": 24
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.920981967591891e-05,
+      "loss": 1.1822,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9130020543448705e-05,
+      "loss": 1.1682,
+      "step": 26
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9046565819097546e-05,
+      "loss": 1.181,
+      "step": 27
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.895948891751234e-05,
+      "loss": 1.169,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8868824703632658e-05,
+      "loss": 1.1743,
+      "step": 29
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8774609478731048e-05,
+      "loss": 1.1678,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8676880965878293e-05,
+      "loss": 1.1762,
+      "step": 31
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.857567829483937e-05,
+      "loss": 1.1637,
+      "step": 32
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.84710419864062e-05,
+      "loss": 1.1644,
+      "step": 33
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.8363013936173393e-05,
+      "loss": 1.1644,
+      "step": 34
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8251637397763597e-05,
+      "loss": 1.1557,
+      "step": 35
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8136956965509064e-05,
+      "loss": 1.161,
+      "step": 36
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.8019018556596402e-05,
+      "loss": 1.15,
+      "step": 37
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7897869392681685e-05,
+      "loss": 1.1704,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7773557980983264e-05,
+      "loss": 1.1521,
+      "step": 39
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7646134094859816e-05,
+      "loss": 1.1578,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7515648753881495e-05,
+      "loss": 1.1578,
+      "step": 41
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.738215420340205e-05,
+      "loss": 1.1615,
+      "step": 42
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.7245703893640188e-05,
+      "loss": 1.157,
+      "step": 43
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.7106352458278524e-05,
+      "loss": 1.14,
+      "step": 44
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.696415569258862e-05,
+      "loss": 1.1552,
+      "step": 45
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6819170531091018e-05,
+      "loss": 1.1595,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.667145502475907e-05,
+      "loss": 1.1568,
+      "step": 47
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6521068317775756e-05,
+      "loss": 1.1489,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6368070623852794e-05,
+      "loss": 1.1649,
+      "step": 49
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6212523202121547e-05,
+      "loss": 1.1506,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6054488332605282e-05,
+      "loss": 1.1458,
+      "step": 51
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.589402929128276e-05,
+      "loss": 1.1457,
+      "step": 52
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.573121032475297e-05,
+      "loss": 1.1539,
+      "step": 53
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5566096624511306e-05,
+      "loss": 1.155,
+      "step": 54
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5398754300847346e-05,
+      "loss": 1.1385,
+      "step": 55
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5229250356374804e-05,
+      "loss": 1.1467,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.5057652659204198e-05,
+      "loss": 1.1619,
+      "step": 57
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4884029915768945e-05,
+      "loss": 1.1297,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4708451643315827e-05,
+      "loss": 1.144,
+      "step": 59
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4530988142070802e-05,
+      "loss": 1.158,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4351710467091337e-05,
+      "loss": 1.1486,
+      "step": 61
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.4170690399816469e-05,
+      "loss": 1.1456,
+      "step": 62
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3988000419326073e-05,
+      "loss": 1.1473,
+      "step": 63
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3803713673320773e-05,
+      "loss": 1.143,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3617903948834155e-05,
+      "loss": 1.1538,
+      "step": 65
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.343064564268899e-05,
+      "loss": 1.1435,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.324201373170929e-05,
+      "loss": 1.1491,
+      "step": 67
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3052083742700172e-05,
+      "loss": 1.1334,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.286093172220748e-05,
+      "loss": 1.1417,
+      "step": 69
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2668634206069305e-05,
+      "loss": 1.1518,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2475268188771628e-05,
+      "loss": 1.1494,
+      "step": 71
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2280911092620298e-05,
+      "loss": 1.1419,
+      "step": 72
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2085640736741708e-05,
+      "loss": 1.1357,
+      "step": 73
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1889535305924619e-05,
+      "loss": 1.1433,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1692673319315541e-05,
+      "loss": 1.1513,
+      "step": 75
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1495133598980263e-05,
+      "loss": 1.1388,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1296995238344084e-05,
+      "loss": 1.1534,
+      "step": 77
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.1098337570523397e-05,
+      "loss": 1.1606,
+      "step": 78
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.08992401365613e-05,
+      "loss": 1.1422,
+      "step": 79
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0699782653579973e-05,
+      "loss": 1.142,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0500044982862519e-05,
+      "loss": 1.1407,
+      "step": 81
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0300107097877114e-05,
+      "loss": 1.143,
+      "step": 82
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0100049052256236e-05,
+      "loss": 1.1441,
+      "step": 83
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.899950947743767e-06,
+      "loss": 1.1395,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.699892902122887e-06,
+      "loss": 1.1412,
+      "step": 85
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.499955017137485e-06,
+      "loss": 1.1392,
+      "step": 86
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.300217346420029e-06,
+      "loss": 1.1427,
+      "step": 87
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.100759863438702e-06,
+      "loss": 1.1344,
+      "step": 88
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.901662429476607e-06,
+      "loss": 1.1436,
+      "step": 89
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.703004761655918e-06,
+      "loss": 1.1475,
+      "step": 90
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.504866401019738e-06,
+      "loss": 1.1404,
+      "step": 91
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.30732668068446e-06,
+      "loss": 1.1339,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.110464694075383e-06,
+      "loss": 1.1467,
+      "step": 93
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.914359263258295e-06,
+      "loss": 1.1414,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.719088907379705e-06,
+      "loss": 1.1364,
+      "step": 95
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.524731811228374e-06,
+      "loss": 1.1235,
+      "step": 96
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.331365793930698e-06,
+      "loss": 1.1377,
+      "step": 97
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.139068277792524e-06,
+      "loss": 1.1398,
+      "step": 98
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.947916257299829e-06,
+      "loss": 1.1281,
+      "step": 99
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.757986268290713e-06,
+      "loss": 1.1355,
+      "step": 100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.569354357311015e-06,
+      "loss": 1.1415,
+      "step": 101
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.382096051165847e-06,
+      "loss": 1.1266,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.196286326679231e-06,
+      "loss": 1.1503,
+      "step": 103
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.0119995806739316e-06,
+      "loss": 1.1375,
+      "step": 104
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.829309600183536e-06,
+      "loss": 1.1273,
+      "step": 105
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.648289532908666e-06,
+      "loss": 1.1294,
+      "step": 106
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.469011857929202e-06,
+      "loss": 1.1322,
+      "step": 107
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.291548356684177e-06,
+      "loss": 1.1385,
+      "step": 108
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.115970084231059e-06,
+      "loss": 1.1479,
+      "step": 109
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.942347340795803e-06,
+      "loss": 1.1376,
+      "step": 110
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.7707496436252e-06,
+      "loss": 1.1315,
+      "step": 111
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.601245699152659e-06,
+      "loss": 1.1318,
+      "step": 112
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.4339033754886974e-06,
+      "loss": 1.1319,
+      "step": 113
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.268789675247029e-06,
+      "loss": 1.1293,
+      "step": 114
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.105970708717244e-06,
+      "loss": 1.1245,
+      "step": 115
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.945511667394719e-06,
+      "loss": 1.1403,
+      "step": 116
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.787476797878459e-06,
+      "loss": 1.141,
+      "step": 117
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6319293761472073e-06,
+      "loss": 1.1272,
+      "step": 118
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.47893168222425e-06,
+      "loss": 1.1353,
+      "step": 119
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.3285449752409315e-06,
+      "loss": 1.1352,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.1808294689089856e-06,
+      "loss": 1.1348,
+      "step": 121
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.035844307411384e-06,
+      "loss": 1.1303,
+      "step": 122
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8936475417214795e-06,
+      "loss": 1.1252,
+      "step": 123
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.754296106359811e-06,
+      "loss": 1.1362,
+      "step": 124
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6178457965979543e-06,
+      "loss": 1.1346,
+      "step": 125
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.484351246118507e-06,
+      "loss": 1.1387,
+      "step": 126
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.353865905140187e-06,
+      "loss": 1.1345,
+      "step": 127
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.226442019016739e-06,
+      "loss": 1.1253,
+      "step": 128
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1021306073183166e-06,
+      "loss": 1.1274,
+      "step": 129
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9809814434036e-06,
+      "loss": 1.1356,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8630430344909378e-06,
+      "loss": 1.1375,
+      "step": 131
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.748362602236403e-06,
+      "loss": 1.1236,
+      "step": 132
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.63698606382661e-06,
+      "loss": 1.1405,
+      "step": 133
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.528958013593801e-06,
+      "loss": 1.1332,
+      "step": 134
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4243217051606285e-06,
+      "loss": 1.1283,
+      "step": 135
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3231190341217081e-06,
+      "loss": 1.1321,
+      "step": 136
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2253905212689554e-06,
+      "loss": 1.1269,
+      "step": 137
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1311752963673438e-06,
+      "loss": 1.1288,
+      "step": 138
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.0405110824876619e-06,
+      "loss": 1.1348,
+      "step": 139
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.534341809024583e-07,
+      "loss": 1.1371,
+      "step": 140
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.699794565512976e-07,
+      "loss": 1.1294,
+      "step": 141
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.901803240810901e-07,
+      "loss": 1.1365,
+      "step": 142
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.140687344671282e-07,
+      "loss": 1.1381,
+      "step": 143
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.416751622201389e-07,
+      "loss": 1.1416,
+      "step": 144
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.730285931845381e-07,
+      "loss": 1.1299,
+      "step": 145
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.08156512932696e-07,
+      "loss": 1.1346,
+      "step": 146
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.4708489575993496e-07,
+      "loss": 1.139,
+      "step": 147
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.8983819428460414e-07,
+      "loss": 1.119,
+      "step": 148
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.364393296574453e-07,
+      "loss": 1.1309,
+      "step": 149
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.8690968238412444e-07,
+      "loss": 1.1268,
+      "step": 150
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.41269083764647e-07,
+      "loss": 1.1372,
+      "step": 151
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9953580795304628e-07,
+      "loss": 1.1429,
+      "step": 152
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6172656464055748e-07,
+      "loss": 1.1181,
+      "step": 153
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.278564923651704e-07,
+      "loss": 1.1209,
+      "step": 154
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.793915245028595e-08,
+      "loss": 1.123,
+      "step": 155
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.19865235748507e-08,
+      "loss": 1.1397,
+      "step": 156
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.000899697719552e-08,
+      "loss": 1.136,
+      "step": 157
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.201537229445051e-08,
+      "loss": 1.137,
+      "step": 158
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.8012854039244354e-08,
+      "loss": 1.1256,
+      "step": 159
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.007048715068522e-09,
+      "loss": 1.1329,
+      "step": 160
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.0019625714740032e-09,
+      "loss": 1.1339,
+      "step": 161
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.1352,
+      "step": 162
+    },
+    {
+      "epoch": 1.0,
+      "step": 162,
+      "total_flos": 8.291234906646774e+17,
+      "train_loss": 1.1575636539930179,
+      "train_runtime": 7042.5737,
+      "train_samples_per_second": 2.956,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "max_steps": 162,
+  "num_train_epochs": 1,
+  "total_flos": 8.291234906646774e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0575a82acae570d523a62fcf420b69fdf61b094c1d8e5466f435e1f11a808164
+size 3771