Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[PAD]": 32004,
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.3541707301474347,
+    "train_runtime": 33786.0741,
+    "train_samples_per_second": 5.938,
+    "train_steps_per_second": 0.023
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/group/20025/jiuding/LLM_ZOO/CodeLlama-34b-Python-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.3",
+  "use_cache": false,
+  "vocab_size": 32005
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.3"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446c9047f1db54ce3f2d085b8277cbfa011929ef82c670b72c6ecb4de719d668
+size 9852719417

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63e5caad98d2db21a5fd382f11a94c46898f5f8550b6ea28a730bd81c7aa9fa
+size 9689093137

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d926954ff03de606f61d7efa4eaf48fb1b9487e3ea63e72f4d1abeb7054f623
+size 9689093137

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0780201263b032dd7e3783775d4354091b5d662e03a990a22768fc782237e51
+size 9689093137

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b1fbfa500525514298041fd945181e647f49e548c8ca286a1fd100d9d85368
+size 9689093137

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a058765e8f9dab381253e1c5c7f82c90b6c7771ceb531c67eda1b8cfc84e4b
+size 9689093137

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e744e7a4e50327b48d1a2259ee51330d4d52f59376d86b6251605d73013b73
+size 9190067865

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 67488104448
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "left",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.3541707301474347,
+    "train_runtime": 33786.0741,
+    "train_samples_per_second": 5.938,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,496 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 784,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.99919725148484e-05,
+      "loss": 0.5476,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9967902947497158e-05,
+      "loss": 0.4891,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9927829941565187e-05,
+      "loss": 0.4573,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9871817834144506e-05,
+      "loss": 0.4521,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9799956552507235e-05,
+      "loss": 0.4565,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.971236146972764e-05,
+      "loss": 0.4528,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9609173219450998e-05,
+      "loss": 0.4456,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.949055747010669e-05,
+      "loss": 0.4407,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9356704658928036e-05,
+      "loss": 0.4251,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9207829686205882e-05,
+      "loss": 0.4372,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.904417157026683e-05,
+      "loss": 0.4439,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8865993063730003e-05,
+      "loss": 0.4305,
+      "step": 120
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.867358023165851e-05,
+      "loss": 0.4395,
+      "step": 130
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.4402,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.824730962103356e-05,
+      "loss": 0.4382,
+      "step": 150
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8014136218679566e-05,
+      "loss": 0.4359,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.7768096144425903e-05,
+      "loss": 0.4202,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7509584414881114e-05,
+      "loss": 0.4181,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7239016069859292e-05,
+      "loss": 0.4263,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.6956825506034866e-05,
+      "loss": 0.4227,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.6663465779520042e-05,
+      "loss": 0.4165,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.635940787848455e-05,
+      "loss": 0.4213,
+      "step": 220
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6045139966985562e-05,
+      "loss": 0.4197,
+      "step": 230
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.5721166601221697e-05,
+      "loss": 0.4257,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5388007919469604e-05,
+      "loss": 0.4216,
+      "step": 250
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.504619880700346e-05,
+      "loss": 0.4171,
+      "step": 260
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.4696288037338258e-05,
+      "loss": 0.42,
+      "step": 270
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.4179,
+      "step": 280
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.397442075446633e-05,
+      "loss": 0.4183,
+      "step": 290
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.3603623197038536e-05,
+      "loss": 0.4291,
+      "step": 300
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3227040033269501e-05,
+      "loss": 0.4142,
+      "step": 310
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.2845275866310325e-05,
+      "loss": 0.4154,
+      "step": 320
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2458943617397346e-05,
+      "loss": 0.4199,
+      "step": 330
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.206866354180891e-05,
+      "loss": 0.4213,
+      "step": 340
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1675062233047365e-05,
+      "loss": 0.4039,
+      "step": 350
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.1278771616845061e-05,
+      "loss": 0.4065,
+      "step": 360
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.0880427936609455e-05,
+      "loss": 0.4117,
+      "step": 370
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.0480670731936209e-05,
+      "loss": 0.4132,
+      "step": 380
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0080141811830277e-05,
+      "loss": 0.4099,
+      "step": 390
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 9.67948422428345e-06,
+      "loss": 0.3254,
+      "step": 400
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.279341223862705e-06,
+      "loss": 0.2853,
+      "step": 410
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.2822,
+      "step": 420
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 8.483166840409996e-06,
+      "loss": 0.2859,
+      "step": 430
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.08841371298628e-06,
+      "loss": 0.2797,
+      "step": 440
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.696729631669563e-06,
+      "loss": 0.2731,
+      "step": 450
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.308743444089232e-06,
+      "loss": 0.27,
+      "step": 460
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.925078060917245e-06,
+      "loss": 0.2809,
+      "step": 470
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.546349455786926e-06,
+      "loss": 0.28,
+      "step": 480
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.2863,
+      "step": 490
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.806125868053433e-06,
+      "loss": 0.2804,
+      "step": 500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.4458193122221405e-06,
+      "loss": 0.2797,
+      "step": 510
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.092824479960625e-06,
+      "loss": 0.2861,
+      "step": 520
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.747708103423791e-06,
+      "loss": 0.2777,
+      "step": 530
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 4.411024265929283e-06,
+      "loss": 0.2791,
+      "step": 540
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.083313512378368e-06,
+      "loss": 0.275,
+      "step": 550
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.2787,
+      "step": 560
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.456900560700158e-06,
+      "loss": 0.2777,
+      "step": 570
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.1592040667065393e-06,
+      "loss": 0.2727,
+      "step": 580
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.8724904502688566e-06,
+      "loss": 0.2748,
+      "step": 590
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.597220029246846e-06,
+      "loss": 0.2809,
+      "step": 600
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.333834749484e-06,
+      "loss": 0.2706,
+      "step": 610
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.082757475264804e-06,
+      "loss": 0.2748,
+      "step": 620
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.8443913104073984e-06,
+      "loss": 0.273,
+      "step": 630
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.6191189510815942e-06,
+      "loss": 0.2788,
+      "step": 640
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4073020713912988e-06,
+      "loss": 0.2741,
+      "step": 650
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.209280742707828e-06,
+      "loss": 0.2749,
+      "step": 660
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0253728876863256e-06,
+      "loss": 0.2739,
+      "step": 670
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.558737698418762e-07,
+      "loss": 0.27,
+      "step": 680
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.010555195048241e-07,
+      "loss": 0.2683,
+      "step": 690
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.2701,
+      "step": 700
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 4.3643189316561864e-07,
+      "loss": 0.2705,
+      "step": 710
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 3.2705136960970554e-07,
+      "loss": 0.2695,
+      "step": 720
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2.3320073635432984e-07,
+      "loss": 0.2747,
+      "step": 730
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.55030670312476e-07,
+      "loss": 0.273,
+      "step": 740
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.26666732930348e-08,
+      "loss": 0.2721,
+      "step": 750
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 4.6208870508017703e-08,
+      "loss": 0.2798,
+      "step": 760
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.5731849821833955e-08,
+      "loss": 0.2738,
+      "step": 770
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2845420006879494e-09,
+      "loss": 0.2722,
+      "step": 780
+    },
+    {
+      "epoch": 2.0,
+      "step": 784,
+      "total_flos": 1134283296079872.0,
+      "train_loss": 0.3541707301474347,
+      "train_runtime": 33786.0741,
+      "train_samples_per_second": 5.938,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 784,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1134283296079872.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b00e10f91422ac2a1bcad396c0d1fec9e31735d2a4149fe48e727c6c8e57f2
+size 6075