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 sha256:95f013399b78819699db1c593681c158fff71979f9b58a1728ef7c26ef40f403
+size 4793130760

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e312008720ef7c1d4128837a83334cdde0be497b661fcf0eb08ff5b50022b0bb
+size 4756459720

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9319b1a1247f79a10c307168b99cb0f0be6bf2a9f24f1ca7a9b0f04c1a475a31
+size 4991370136

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3363ae5a43f5648d95fb28bed3969434410e2796276e9d76bc5f61198e0b776
+size 4756459760

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9808b4dba5605dc57ebbd8de8f3dd7f45eaef4d96f2d3927da0452886bbc2131
+size 4756459760

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ffe346d7c0ae424c6f0d98c176ef2e8bc59f4908a306153c7234d1ec0ac67d
+size 4991370160

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20be248e011be9eb8c744c6cd07166945bf0b747ad838e7888dfd06c86d49aff
+size 4756459760

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1439bb19c3ec01cc3225e02938c8f7df39089677e5c1367a2d0a957e3b6c9537
+size 4756459760

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf31b42180ddfbc1d1e4f0a651694589de99c773184a9ac54e114a0f66ece7ce
+size 4991370160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46265598131aab950f9b176b39115ecf344dd4b456c269f5761c76bcc5c0e426
+size 4756459760

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9334aea16b6f214360a2108da2daf21c13f4ce634e0a056d0521cd37066d4fc2
+size 4756459760

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6315c154a0f7ed1b8cbeb85325a60b2f7895e5bf0a1caf77dc54cad5a6bbbb3
+size 4991370160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c1a987e07384ace245a66ada75690792b162dd76adb87101bbcd0e662e0e49
+size 4756459760

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2cd5d2be196cf0c00660ce8a446dbb189362edbe92ba1d263e132b509d3216
+size 4756459760

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c0329212b25e1e51ca9360bd3f28184300b6845e100c760a26a5042dc94b58
+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": 1.3301465239530292,
+  "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": 1.3333333333333334e-06,
+      "loss": 1.1551,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.154,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1059,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.0639,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0078,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9614,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.9721,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.9311,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2e-05,
+      "loss": 0.9092,
+      "step": 9
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8757,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.9356,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.8963,
+      "step": 12
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.9095,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.9306,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.9089,
+      "step": 15
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9999392458943432e-05,
+      "loss": 0.9064,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997569909594948e-05,
+      "loss": 0.8986,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999453257340926e-05,
+      "loss": 0.923,
+      "step": 18
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9990280819447662e-05,
+      "loss": 0.9112,
+      "step": 19
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9984815164333163e-05,
+      "loss": 0.8882,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9978136272187745e-05,
+      "loss": 0.9149,
+      "step": 21
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9970244954551648e-05,
+      "loss": 0.9003,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9961142170284762e-05,
+      "loss": 0.8286,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9950829025450116e-05,
+      "loss": 0.8972,
+      "step": 24
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9939306773179498e-05,
+      "loss": 0.887,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9926576813521167e-05,
+      "loss": 0.8968,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9912640693269754e-05,
+      "loss": 0.8983,
+      "step": 27
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.98975001057783e-05,
+      "loss": 0.9228,
+      "step": 28
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9881156890752517e-05,
+      "loss": 0.905,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.879,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9844870667325073e-05,
+      "loss": 0.8406,
+      "step": 31
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9824932067997516e-05,
+      "loss": 0.8851,
+      "step": 32
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9803799658748096e-05,
+      "loss": 0.884,
+      "step": 33
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.8482,
+      "step": 34
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9757963826274357e-05,
+      "loss": 0.8561,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.973326597248006e-05,
+      "loss": 0.923,
+      "step": 36
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.97073854469472e-05,
+      "loss": 0.848,
+      "step": 37
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.968032539437215e-05,
+      "loss": 0.8416,
+      "step": 38
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9652089102773487e-05,
+      "loss": 0.8664,
+      "step": 39
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9622680003092503e-05,
+      "loss": 0.8776,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.95921016687763e-05,
+      "loss": 0.902,
+      "step": 41
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9560357815343577e-05,
+      "loss": 0.895,
+      "step": 42
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9527452299933192e-05,
+      "loss": 0.8891,
+      "step": 43
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9493389120835462e-05,
+      "loss": 0.8614,
+      "step": 44
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.8723,
+      "step": 45
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9421806467564546e-05,
+      "loss": 0.8956,
+      "step": 46
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9384295691271523e-05,
+      "loss": 0.9021,
+      "step": 47
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.934564464599461e-05,
+      "loss": 0.9069,
+      "step": 48
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9305858028153186e-05,
+      "loss": 0.8903,
+      "step": 49
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9264940672148018e-05,
+      "loss": 0.8661,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 1.056524395942688,
+      "eval_runtime": 106.5377,
+      "eval_samples_per_second": 7.303,
+      "eval_steps_per_second": 0.235,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.922289754977385e-05,
+      "loss": 0.8758,
+      "step": 51
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9179733769615273e-05,
+      "loss": 0.87,
+      "step": 52
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.8788,
+      "step": 53
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.909006535049163e-05,
+      "loss": 0.8621,
+      "step": 54
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9043571606975776e-05,
+      "loss": 0.8481,
+      "step": 55
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.899597899525007e-05,
+      "loss": 0.8284,
+      "step": 56
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8947293298207637e-05,
+      "loss": 0.8297,
+      "step": 57
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8897520431560435e-05,
+      "loss": 0.8697,
+      "step": 58
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.884666644312046e-05,
+      "loss": 0.8544,
+      "step": 59
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.9064,
+      "step": 60
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8741739948185256e-05,
+      "loss": 0.8845,
+      "step": 61
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8687680191120746e-05,
+      "loss": 0.8724,
+      "step": 62
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.863256480957574e-05,
+      "loss": 0.8918,
+      "step": 63
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8576400500521673e-05,
+      "loss": 0.893,
+      "step": 64
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.851919408838327e-05,
+      "loss": 0.8763,
+      "step": 65
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8460952524209355e-05,
+      "loss": 0.8619,
+      "step": 66
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8401682884828212e-05,
+      "loss": 0.8779,
+      "step": 67
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.83413923719877e-05,
+      "loss": 0.8755,
+      "step": 68
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8280088311480203e-05,
+      "loss": 0.8846,
+      "step": 69
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.821777815225245e-05,
+      "loss": 0.8681,
+      "step": 70
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8154469465500447e-05,
+      "loss": 0.865,
+      "step": 71
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.832,
+      "step": 72
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.802488739991941e-05,
+      "loss": 0.8529,
+      "step": 73
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.7958629766375387e-05,
+      "loss": 0.8143,
+      "step": 74
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.8611,
+      "step": 75
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7823221551034766e-05,
+      "loss": 0.8464,
+      "step": 76
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7754087422448217e-05,
+      "loss": 0.828,
+      "step": 77
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7684011108568593e-05,
+      "loss": 0.8649,
+      "step": 78
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7613001124243448e-05,
+      "loss": 0.8319,
+      "step": 79
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7541066097768965e-05,
+      "loss": 0.8834,
+      "step": 80
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7468214769841542e-05,
+      "loss": 0.8508,
+      "step": 81
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7394455992495722e-05,
+      "loss": 0.8629,
+      "step": 82
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7319798728028617e-05,
+      "loss": 0.8607,
+      "step": 83
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7244252047910893e-05,
+      "loss": 0.81,
+      "step": 84
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7167825131684516e-05,
+      "loss": 0.8616,
+      "step": 85
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7090527265847375e-05,
+      "loss": 0.8772,
+      "step": 86
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7012367842724887e-05,
+      "loss": 0.8661,
+      "step": 87
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6933356359328756e-05,
+      "loss": 0.8721,
+      "step": 88
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6853502416203e-05,
+      "loss": 0.8814,
+      "step": 89
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.8447,
+      "step": 90
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.8353,
+      "step": 91
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6608983362288612e-05,
+      "loss": 0.8291,
+      "step": 92
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6525857615241686e-05,
+      "loss": 0.8955,
+      "step": 93
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6441938922908644e-05,
+      "loss": 0.8361,
+      "step": 94
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6357237482099682e-05,
+      "loss": 0.8597,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6271763584735373e-05,
+      "loss": 0.8375,
+      "step": 96
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.6185527616596096e-05,
+      "loss": 0.8907,
+      "step": 97
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.609854005606009e-05,
+      "loss": 0.8775,
+      "step": 98
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.6010811472830253e-05,
+      "loss": 0.8629,
+      "step": 99
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.5922352526649803e-05,
+      "loss": 0.8306,
+      "step": 100
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0295250415802002,
+      "eval_runtime": 108.1298,
+      "eval_samples_per_second": 7.195,
+      "eval_steps_per_second": 0.231,
+      "step": 100
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.583317396600707e-05,
+      "loss": 0.856,
+      "step": 101
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5743286626829437e-05,
+      "loss": 0.8463,
+      "step": 102
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.565270143116672e-05,
+      "loss": 0.8399,
+      "step": 103
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5561429385864005e-05,
+      "loss": 0.9041,
+      "step": 104
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.8555,
+      "step": 105
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5376869189660784e-05,
+      "loss": 0.8195,
+      "step": 106
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.528360346433959e-05,
+      "loss": 0.8211,
+      "step": 107
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5189695737812153e-05,
+      "loss": 0.8115,
+      "step": 108
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5095157420638349e-05,
+      "loss": 0.8764,
+      "step": 109
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8073,
+      "step": 110
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4904235038305084e-05,
+      "loss": 0.8068,
+      "step": 111
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.4807874171782795e-05,
+      "loss": 0.8571,
+      "step": 112
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4710929109069674e-05,
+      "loss": 0.8372,
+      "step": 113
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.461341162978688e-05,
+      "loss": 0.8119,
+      "step": 114
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.4515333583108896e-05,
+      "loss": 0.8474,
+      "step": 115
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4416706886323741e-05,
+      "loss": 0.8273,
+      "step": 116
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4317543523384928e-05,
+      "loss": 0.8668,
+      "step": 117
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4217855543455323e-05,
+      "loss": 0.8522,
+      "step": 118
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4117655059443052e-05,
+      "loss": 0.8469,
+      "step": 119
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.8221,
+      "step": 120
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3915765340690916e-05,
+      "loss": 0.851,
+      "step": 121
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.3814100637209663e-05,
+      "loss": 0.8476,
+      "step": 122
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3711972489182208e-05,
+      "loss": 0.8443,
+      "step": 123
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.3609393306017149e-05,
+      "loss": 0.848,
+      "step": 124
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3506375551927546e-05,
+      "loss": 0.815,
+      "step": 125
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3402931744416432e-05,
+      "loss": 0.8309,
+      "step": 126
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3299074452755829e-05,
+      "loss": 0.7954,
+      "step": 127
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3194816296459483e-05,
+      "loss": 0.8263,
+      "step": 128
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.8303,
+      "step": 129
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2985148110016947e-05,
+      "loss": 0.8463,
+      "step": 130
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2879763556277062e-05,
+      "loss": 0.8681,
+      "step": 131
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2774029087618448e-05,
+      "loss": 0.8244,
+      "step": 132
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2667957551647263e-05,
+      "loss": 0.8291,
+      "step": 133
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2561561836926115e-05,
+      "loss": 0.8724,
+      "step": 134
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.8229,
+      "step": 135
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.234784962086541e-05,
+      "loss": 0.8299,
+      "step": 136
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.224055908731496e-05,
+      "loss": 0.8297,
+      "step": 137
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.213299630743747e-05,
+      "loss": 0.8286,
+      "step": 138
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.2025174350993923e-05,
+      "loss": 0.8542,
+      "step": 139
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1917106319237386e-05,
+      "loss": 0.8157,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1808805343321102e-05,
+      "loss": 0.8591,
+      "step": 141
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.1700284582702933e-05,
+      "loss": 0.8192,
+      "step": 142
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1591557223546394e-05,
+      "loss": 0.8493,
+      "step": 143
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.148263647711842e-05,
+      "loss": 0.858,
+      "step": 144
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1373535578184083e-05,
+      "loss": 0.7751,
+      "step": 145
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1264267783398463e-05,
+      "loss": 0.7998,
+      "step": 146
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1154846369695864e-05,
+      "loss": 0.8321,
+      "step": 147
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.8339,
+      "step": 148
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.093559588499118e-05,
+      "loss": 0.8018,
+      "step": 149
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.8481,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0097606182098389,
+      "eval_runtime": 105.9007,
+      "eval_samples_per_second": 7.347,
+      "eval_steps_per_second": 0.236,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0715890683769872e-05,
+      "loss": 0.6491,
+      "step": 151
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.060590092621994e-05,
+      "loss": 0.566,
+      "step": 152
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0495837546732224e-05,
+      "loss": 0.5246,
+      "step": 153
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0385713918911104e-05,
+      "loss": 0.553,
+      "step": 154
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.0275543423681622e-05,
+      "loss": 0.5431,
+      "step": 155
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.0165339447663586e-05,
+      "loss": 0.5586,
+      "step": 156
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.0055115381545006e-05,
+      "loss": 0.5666,
+      "step": 157
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.944884618454996e-06,
+      "loss": 0.5396,
+      "step": 158
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.834660552336415e-06,
+      "loss": 0.5399,
+      "step": 159
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 9.724456576318383e-06,
+      "loss": 0.5398,
+      "step": 160
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.614286081088895e-06,
+      "loss": 0.5432,
+      "step": 161
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.504162453267776e-06,
+      "loss": 0.5178,
+      "step": 162
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 9.394099073780066e-06,
+      "loss": 0.5477,
+      "step": 163
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.284109316230133e-06,
+      "loss": 0.5143,
+      "step": 164
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.5184,
+      "step": 165
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 9.064404115008824e-06,
+      "loss": 0.551,
+      "step": 166
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.5344,
+      "step": 167
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.84515363030414e-06,
+      "loss": 0.5309,
+      "step": 168
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.735732216601538e-06,
+      "loss": 0.5222,
+      "step": 169
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 8.626464421815919e-06,
+      "loss": 0.5409,
+      "step": 170
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.51736352288158e-06,
+      "loss": 0.505,
+      "step": 171
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.408442776453606e-06,
+      "loss": 0.5329,
+      "step": 172
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 8.299715417297072e-06,
+      "loss": 0.5214,
+      "step": 173
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.191194656678905e-06,
+      "loss": 0.5575,
+      "step": 174
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.082893680762619e-06,
+      "loss": 0.4793,
+      "step": 175
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.974825649006082e-06,
+      "loss": 0.5347,
+      "step": 176
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.867003692562533e-06,
+      "loss": 0.5023,
+      "step": 177
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.759440912685043e-06,
+      "loss": 0.5287,
+      "step": 178
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 7.652150379134593e-06,
+      "loss": 0.5421,
+      "step": 179
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.5401,
+      "step": 180
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.438438163073884e-06,
+      "loss": 0.5294,
+      "step": 181
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.3320424483527385e-06,
+      "loss": 0.5514,
+      "step": 182
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.225970912381557e-06,
+      "loss": 0.5564,
+      "step": 183
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 7.120236443722941e-06,
+      "loss": 0.5374,
+      "step": 184
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.014851889983058e-06,
+      "loss": 0.5404,
+      "step": 185
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.5479,
+      "step": 186
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.80518370354052e-06,
+      "loss": 0.4935,
+      "step": 187
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.700925547244173e-06,
+      "loss": 0.4902,
+      "step": 188
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.59706825558357e-06,
+      "loss": 0.5132,
+      "step": 189
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.4936244480724575e-06,
+      "loss": 0.5228,
+      "step": 190
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.3906066939828546e-06,
+      "loss": 0.5442,
+      "step": 191
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.2880275108177915e-06,
+      "loss": 0.516,
+      "step": 192
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.18589936279034e-06,
+      "loss": 0.5257,
+      "step": 193
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 6.084234659309088e-06,
+      "loss": 0.5389,
+      "step": 194
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.5254,
+      "step": 195
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.8823449405569525e-06,
+      "loss": 0.5112,
+      "step": 196
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 5.782144456544681e-06,
+      "loss": 0.5496,
+      "step": 197
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.6824564766150724e-06,
+      "loss": 0.5285,
+      "step": 198
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.58329311367626e-06,
+      "loss": 0.5261,
+      "step": 199
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.484666416891109e-06,
+      "loss": 0.5185,
+      "step": 200
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.0541412830352783,
+      "eval_runtime": 105.5736,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 0.237,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 304188748595200.0,
+  "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 sha256:1672e9d251f751fdc94ee38d76a961e37e6c2e91b208a8ee086afc91ce2211fd
+size 6776