Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/paratera5-data/home/wangchenyue/model/SUS-Chat-34B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 5000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 64000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2531cd935debf258d5c7994494978c45fb0e42f845e40039a5bce0ecef0655fb
+size 4793130760

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6abeacb04cf8651c4addc5c29adc04b95f661ad03da42834a6a5a1697f59aae2
+size 4756459720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8250b6d703a5158f10c2dc874fae41c35839560fa56a05956eae37a78df461bc
+size 4991370136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e19e412b718f7a1fa2d1ca6ed74da58edad822b45655e2b8d356dae6c133d78
+size 4756459760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787f34e56788ff3a0d809b6ab5bc4a23629fb8e32fdabfd2c97b5f813e015ec8
+size 4756459760

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc37b542bedc2246c09a7deb6a26b56ebd511ea49036cbc00d6b1f3736356329
+size 4991370160

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5d028c25eacb475ab768b8e2a79c497f84cee6ddded435af94867f822dd9cd
+size 4756459760

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0192884880fa94a9972ef45157d07bc98e8f9c5170c1b84b1e924497a4d2fd
+size 4756459760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51245a0b8fb6d8fd9e1d45f7228bd26d78289f3daa8b6e589f414343bd232a46
+size 4991370160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1f39e6a555bf37e07ba6ef926cb93642676ec10a007b4ed303b77de5a70a86
+size 4756459760

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae30b4d0940ea8c6008b2c7b7438e145eea218c6ac5d97a7ee728dd41849b594
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a8e81e14ef5dc1a4da2ed571406ab92cf0c352785c15d2eb93aaaff6eaa1e9
+size 4991370160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999ca0b734b5b48fd508291288475530fbca3344793ffa0d3629a2cab16c751c
+size 4756459760

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657d7b77e86941f0600154517f4ec8ea05dced413fac15c27642dc86e1cce490
+size 4756459760

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b80b98add243b12c62ed484e209674a7017a11c0bafdc12c4535afda6abe15b
+size 1211148856

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 68777834496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1253 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.275154413229727,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 0.8842,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 0.9108,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8097,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2e-05,
+      "loss": 0.8007,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9999479806942976e-05,
+      "loss": 0.8092,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9997919281892066e-05,
+      "loss": 0.7677,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9995318587202132e-05,
+      "loss": 0.7347,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9991677993445832e-05,
+      "loss": 0.7468,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9986997879385488e-05,
+      "loss": 0.7442,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.998127873193367e-05,
+      "loss": 0.7988,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9974521146102535e-05,
+      "loss": 0.8289,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9966725824941933e-05,
+      "loss": 0.8913,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9957893579466252e-05,
+      "loss": 0.9097,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.994802532857004e-05,
+      "loss": 0.8147,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.7253,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.992518502491028e-05,
+      "loss": 0.7241,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.99122153484202e-05,
+      "loss": 0.711,
+      "step": 17
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.989821441880933e-05,
+      "loss": 0.7079,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9883183692714935e-05,
+      "loss": 0.7709,
+      "step": 19
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.986712473391289e-05,
+      "loss": 0.7019,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9850039213154972e-05,
+      "loss": 0.7152,
+      "step": 21
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9831928907995032e-05,
+      "loss": 0.6952,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9812795702604073e-05,
+      "loss": 0.7087,
+      "step": 23
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9792641587574212e-05,
+      "loss": 0.7014,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9771468659711595e-05,
+      "loss": 0.6856,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.6408,
+      "step": 26
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9726075282462847e-05,
+      "loss": 0.6791,
+      "step": 27
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9701859555740647e-05,
+      "loss": 0.6508,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9676634461022222e-05,
+      "loss": 0.6494,
+      "step": 29
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.96504026226914e-05,
+      "loss": 0.6653,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9623166769872216e-05,
+      "loss": 0.6605,
+      "step": 31
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.6368,
+      "step": 32
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9565694459251457e-05,
+      "loss": 0.652,
+      "step": 33
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9535463980789277e-05,
+      "loss": 0.6275,
+      "step": 34
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9504241445895434e-05,
+      "loss": 0.6504,
+      "step": 35
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9472030102919102e-05,
+      "loss": 0.6485,
+      "step": 36
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 0.6612,
+      "step": 37
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9404654500138117e-05,
+      "loss": 0.6432,
+      "step": 38
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.936949724999762e-05,
+      "loss": 0.6332,
+      "step": 39
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9333365210373668e-05,
+      "loss": 0.6515,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9296262140393498e-05,
+      "loss": 0.6343,
+      "step": 41
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.925819190020898e-05,
+      "loss": 0.6252,
+      "step": 42
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.921915845059505e-05,
+      "loss": 0.6393,
+      "step": 43
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9179165852537596e-05,
+      "loss": 0.6278,
+      "step": 44
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.913821826681099e-05,
+      "loss": 0.634,
+      "step": 45
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9096319953545186e-05,
+      "loss": 0.6231,
+      "step": 46
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9053475271782523e-05,
+      "loss": 0.6128,
+      "step": 47
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.6482,
+      "step": 48
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.896496473076651e-05,
+      "loss": 0.6099,
+      "step": 49
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.891930808002694e-05,
+      "loss": 0.6066,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.6270840167999268,
+      "eval_runtime": 44.9662,
+      "eval_samples_per_second": 18.058,
+      "eval_steps_per_second": 0.578,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8872723476860033e-05,
+      "loss": 0.6427,
+      "step": 51
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8825215767863215e-05,
+      "loss": 0.6114,
+      "step": 52
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8776789895672557e-05,
+      "loss": 0.6422,
+      "step": 53
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8727450898448562e-05,
+      "loss": 0.6153,
+      "step": 54
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.867720390935199e-05,
+      "loss": 0.6057,
+      "step": 55
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8626054156009807e-05,
+      "loss": 0.6384,
+      "step": 56
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8574006959971335e-05,
+      "loss": 0.6092,
+      "step": 57
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8521067736154567e-05,
+      "loss": 0.5852,
+      "step": 58
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.587,
+      "step": 59
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.595,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.835695343584683e-05,
+      "loss": 0.5945,
+      "step": 61
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8300502097550807e-05,
+      "loss": 0.5804,
+      "step": 62
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8243187186542594e-05,
+      "loss": 0.6172,
+      "step": 63
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8185014665785936e-05,
+      "loss": 0.6006,
+      "step": 64
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8125990587469125e-05,
+      "loss": 0.6111,
+      "step": 65
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8066121092375303e-05,
+      "loss": 0.5765,
+      "step": 66
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8005412409243604e-05,
+      "loss": 0.5885,
+      "step": 67
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.7943870854121126e-05,
+      "loss": 0.5915,
+      "step": 68
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7881502829705808e-05,
+      "loss": 0.6137,
+      "step": 69
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.5995,
+      "step": 70
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.7754313413036907e-05,
+      "loss": 0.5913,
+      "step": 71
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.768950525339362e-05,
+      "loss": 0.5825,
+      "step": 72
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7623897088301387e-05,
+      "loss": 0.5772,
+      "step": 73
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.7557495743542586e-05,
+      "loss": 0.5858,
+      "step": 74
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7490308127420928e-05,
+      "loss": 0.578,
+      "step": 75
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.74223412300427e-05,
+      "loss": 0.5934,
+      "step": 76
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7353602122589528e-05,
+      "loss": 0.5851,
+      "step": 77
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7284097956582694e-05,
+      "loss": 0.5872,
+      "step": 78
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.721383596313912e-05,
+      "loss": 0.5897,
+      "step": 79
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7142823452219036e-05,
+      "loss": 0.59,
+      "step": 80
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.589,
+      "step": 81
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.699857650743562e-05,
+      "loss": 0.5931,
+      "step": 82
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.692535708082412e-05,
+      "loss": 0.5665,
+      "step": 83
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6851417149678442e-05,
+      "loss": 0.5843,
+      "step": 84
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6776764406606362e-05,
+      "loss": 0.5932,
+      "step": 85
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.67014066183756e-05,
+      "loss": 0.5775,
+      "step": 86
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6625351625105796e-05,
+      "loss": 0.5806,
+      "step": 87
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.5668,
+      "step": 88
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6471181745785673e-05,
+      "loss": 0.5972,
+      "step": 89
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6393082899355516e-05,
+      "loss": 0.6005,
+      "step": 90
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.631431892545791e-05,
+      "loss": 0.5908,
+      "step": 91
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.5833,
+      "step": 92
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6154828441584655e-05,
+      "loss": 0.5836,
+      "step": 93
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.607411852477748e-05,
+      "loss": 0.5657,
+      "step": 94
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.599277666511347e-05,
+      "loss": 0.5763,
+      "step": 95
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5910811325286768e-05,
+      "loss": 0.5964,
+      "step": 96
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5828231032857503e-05,
+      "loss": 0.6056,
+      "step": 97
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5745044379364637e-05,
+      "loss": 0.5794,
+      "step": 98
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5661260019432077e-05,
+      "loss": 0.5797,
+      "step": 99
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5576886669868297e-05,
+      "loss": 0.5828,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.5864700078964233,
+      "eval_runtime": 45.0205,
+      "eval_samples_per_second": 18.036,
+      "eval_steps_per_second": 0.578,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5491933108759417e-05,
+      "loss": 0.5829,
+      "step": 101
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5406408174555978e-05,
+      "loss": 0.5705,
+      "step": 102
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.5713,
+      "step": 103
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.5233679836966122e-05,
+      "loss": 0.5684,
+      "step": 104
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5146494403996101e-05,
+      "loss": 0.5883,
+      "step": 105
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5058773536894685e-05,
+      "loss": 0.5756,
+      "step": 106
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.4970526362019077e-05,
+      "loss": 0.5846,
+      "step": 107
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4881762060482814e-05,
+      "loss": 0.5779,
+      "step": 108
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.479248986720057e-05,
+      "loss": 0.5933,
+      "step": 109
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4702719069927368e-05,
+      "loss": 0.5606,
+      "step": 110
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4612459008292307e-05,
+      "loss": 0.5698,
+      "step": 111
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4521719072826858e-05,
+      "loss": 0.561,
+      "step": 112
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4430508703987914e-05,
+      "loss": 0.576,
+      "step": 113
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.5893,
+      "step": 114
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4246714671745964e-05,
+      "loss": 0.5689,
+      "step": 115
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.5804,
+      "step": 116
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4061153396280673e-05,
+      "loss": 0.5777,
+      "step": 117
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.3967734145782425e-05,
+      "loss": 0.5638,
+      "step": 118
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.3873902097733231e-05,
+      "loss": 0.5921,
+      "step": 119
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3779667014289067e-05,
+      "loss": 0.5458,
+      "step": 120
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3685038699537165e-05,
+      "loss": 0.5788,
+      "step": 121
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3590026998475987e-05,
+      "loss": 0.5759,
+      "step": 122
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.3494641795990986e-05,
+      "loss": 0.5666,
+      "step": 123
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3398893015826166e-05,
+      "loss": 0.5921,
+      "step": 124
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.5761,
+      "step": 125
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3206344605527355e-05,
+      "loss": 0.5847,
+      "step": 126
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3109565007862597e-05,
+      "loss": 0.5782,
+      "step": 127
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3012461895372343e-05,
+      "loss": 0.568,
+      "step": 128
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2915045370529586e-05,
+      "loss": 0.5639,
+      "step": 129
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.2817325568414299e-05,
+      "loss": 0.5718,
+      "step": 130
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2719312655658995e-05,
+      "loss": 0.5873,
+      "step": 131
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2621016829391022e-05,
+      "loss": 0.5804,
+      "step": 132
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2522448316171651e-05,
+      "loss": 0.5644,
+      "step": 133
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2423617370932127e-05,
+      "loss": 0.5799,
+      "step": 134
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2324534275906747e-05,
+      "loss": 0.5835,
+      "step": 135
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.562,
+      "step": 136
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2125652895529766e-05,
+      "loss": 0.5591,
+      "step": 137
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2025875301520811e-05,
+      "loss": 0.5718,
+      "step": 138
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1925886938258606e-05,
+      "loss": 0.5626,
+      "step": 139
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.182569820839362e-05,
+      "loss": 0.5614,
+      "step": 140
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1725319535422189e-05,
+      "loss": 0.5363,
+      "step": 141
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1624761362602061e-05,
+      "loss": 0.5751,
+      "step": 142
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1524034151865904e-05,
+      "loss": 0.5614,
+      "step": 143
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.5644,
+      "step": 144
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.132211455121824e-05,
+      "loss": 0.5647,
+      "step": 145
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.12209431687416e-05,
+      "loss": 0.5876,
+      "step": 146
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.5621,
+      "step": 147
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1018229867038358e-05,
+      "loss": 0.5907,
+      "step": 148
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0916709037822172e-05,
+      "loss": 0.5468,
+      "step": 149
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0815092835470633e-05,
+      "loss": 0.5647,
+      "step": 150
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.5674496293067932,
+      "eval_runtime": 44.5413,
+      "eval_samples_per_second": 18.23,
+      "eval_steps_per_second": 0.584,
+      "step": 150
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0713391831992324e-05,
+      "loss": 0.5799,
+      "step": 151
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0611616608218429e-05,
+      "loss": 0.5625,
+      "step": 152
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.05097777527019e-05,
+      "loss": 0.5695,
+      "step": 153
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0407885860615859e-05,
+      "loss": 0.5738,
+      "step": 154
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0305951532651262e-05,
+      "loss": 0.5536,
+      "step": 155
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0203985373914056e-05,
+      "loss": 0.5597,
+      "step": 156
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0101997992821798e-05,
+      "loss": 0.5348,
+      "step": 157
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1e-05,
+      "loss": 0.3475,
+      "step": 158
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.898002007178204e-06,
+      "loss": 0.3412,
+      "step": 159
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.79601462608595e-06,
+      "loss": 0.3208,
+      "step": 160
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.69404846734874e-06,
+      "loss": 0.3348,
+      "step": 161
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.592114139384146e-06,
+      "loss": 0.3419,
+      "step": 162
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.4902222472981e-06,
+      "loss": 0.3411,
+      "step": 163
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.388383391781576e-06,
+      "loss": 0.3265,
+      "step": 164
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.286608168007678e-06,
+      "loss": 0.3317,
+      "step": 165
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.184907164529369e-06,
+      "loss": 0.3492,
+      "step": 166
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.083290962177828e-06,
+      "loss": 0.3401,
+      "step": 167
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.981770132961649e-06,
+      "loss": 0.3334,
+      "step": 168
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.3134,
+      "step": 169
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.779056831258402e-06,
+      "loss": 0.3087,
+      "step": 170
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.67788544878176e-06,
+      "loss": 0.3144,
+      "step": 171
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.3234,
+      "step": 172
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.4759658481341e-06,
+      "loss": 0.3105,
+      "step": 173
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.375238637397942e-06,
+      "loss": 0.319,
+      "step": 174
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.274680464577816e-06,
+      "loss": 0.3343,
+      "step": 175
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.174301791606384e-06,
+      "loss": 0.3218,
+      "step": 176
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.074113061741397e-06,
+      "loss": 0.3247,
+      "step": 177
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 7.974124698479192e-06,
+      "loss": 0.3257,
+      "step": 178
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 7.874347104470234e-06,
+      "loss": 0.3161,
+      "step": 179
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3161,
+      "step": 180
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.675465724093254e-06,
+      "loss": 0.315,
+      "step": 181
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.576382629067877e-06,
+      "loss": 0.3069,
+      "step": 182
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.47755168382835e-06,
+      "loss": 0.2958,
+      "step": 183
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.378983170608982e-06,
+      "loss": 0.3021,
+      "step": 184
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.280687344341006e-06,
+      "loss": 0.3246,
+      "step": 185
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.182674431585703e-06,
+      "loss": 0.297,
+      "step": 186
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.084954629470417e-06,
+      "loss": 0.3084,
+      "step": 187
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.9875381046276605e-06,
+      "loss": 0.3008,
+      "step": 188
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.8904349921374065e-06,
+      "loss": 0.3002,
+      "step": 189
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.793655394472645e-06,
+      "loss": 0.3191,
+      "step": 190
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.2975,
+      "step": 191
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.601106984173835e-06,
+      "loss": 0.2993,
+      "step": 192
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.505358204009018e-06,
+      "loss": 0.2952,
+      "step": 193
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.409973001524012e-06,
+      "loss": 0.308,
+      "step": 194
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.314961300462841e-06,
+      "loss": 0.3146,
+      "step": 195
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.220332985710936e-06,
+      "loss": 0.3156,
+      "step": 196
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.126097902266772e-06,
+      "loss": 0.3198,
+      "step": 197
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.032265854217574e-06,
+      "loss": 0.3036,
+      "step": 198
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.938846603719333e-06,
+      "loss": 0.3061,
+      "step": 199
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.3258,
+      "step": 200
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 0.5941755771636963,
+      "eval_runtime": 45.0109,
+      "eval_samples_per_second": 18.04,
+      "eval_steps_per_second": 0.578,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 236151238623232.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37535bc747052a31438d56207078ebe5e448ec61636e90a302210b456652b969
+size 6776