Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/root/CodeContestsPlus/magicoder/data/models/deepseek-coder-6.7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

configuration.json

@@ -0,0 +1,8 @@
+{
+    "framework":"pytorch",
+    "task":"chat",
+    "model":{
+        "type": "LlamaForCausalLM"
+    },
+    "allow_remote": true
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad6c63da5a9555c31bb6112822d40f915186a1c18660670790bc26fade8fdc0
+size 4941082504

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a45fde78acb47851552e2f0d5464e6a7a2f892e37bb2460f185a70f98e9a52
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d51397392d08913e1da9b736eeb7f3170900f67794e7930b183e8787d7b1823
+size 3592585968

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13481025536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,876 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9961926091825308,
+  "eval_steps": 500,
+  "global_step": 139,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007166853303471445,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.3116,
+      "step": 1
+    },
+    {
+      "epoch": 0.01433370660694289,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3161,
+      "step": 2
+    },
+    {
+      "epoch": 0.021500559910414333,
+      "learning_rate": 1e-05,
+      "loss": 0.3192,
+      "step": 3
+    },
+    {
+      "epoch": 0.02866741321388578,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.3087,
+      "step": 4
+    },
+    {
+      "epoch": 0.03583426651735722,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.2989,
+      "step": 5
+    },
+    {
+      "epoch": 0.043001119820828666,
+      "learning_rate": 2e-05,
+      "loss": 0.2922,
+      "step": 6
+    },
+    {
+      "epoch": 0.05016797312430011,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.2698,
+      "step": 7
+    },
+    {
+      "epoch": 0.05733482642777156,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.2669,
+      "step": 8
+    },
+    {
+      "epoch": 0.064501679731243,
+      "learning_rate": 3e-05,
+      "loss": 0.3035,
+      "step": 9
+    },
+    {
+      "epoch": 0.07166853303471445,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3008,
+      "step": 10
+    },
+    {
+      "epoch": 0.07883538633818589,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.2836,
+      "step": 11
+    },
+    {
+      "epoch": 0.08600223964165733,
+      "learning_rate": 4e-05,
+      "loss": 0.2824,
+      "step": 12
+    },
+    {
+      "epoch": 0.09316909294512878,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.3204,
+      "step": 13
+    },
+    {
+      "epoch": 0.10033594624860022,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.2791,
+      "step": 14
+    },
+    {
+      "epoch": 0.10750279955207166,
+      "learning_rate": 5e-05,
+      "loss": 0.3355,
+      "step": 15
+    },
+    {
+      "epoch": 0.11466965285554312,
+      "learning_rate": 4.959677419354839e-05,
+      "loss": 0.2947,
+      "step": 16
+    },
+    {
+      "epoch": 0.12183650615901456,
+      "learning_rate": 4.9193548387096775e-05,
+      "loss": 0.2848,
+      "step": 17
+    },
+    {
+      "epoch": 0.129003359462486,
+      "learning_rate": 4.8790322580645164e-05,
+      "loss": 0.2934,
+      "step": 18
+    },
+    {
+      "epoch": 0.13617021276595745,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.267,
+      "step": 19
+    },
+    {
+      "epoch": 0.1433370660694289,
+      "learning_rate": 4.7983870967741937e-05,
+      "loss": 0.2567,
+      "step": 20
+    },
+    {
+      "epoch": 0.15050391937290034,
+      "learning_rate": 4.7580645161290326e-05,
+      "loss": 0.2745,
+      "step": 21
+    },
+    {
+      "epoch": 0.15767077267637178,
+      "learning_rate": 4.7177419354838716e-05,
+      "loss": 0.2732,
+      "step": 22
+    },
+    {
+      "epoch": 0.16483762597984322,
+      "learning_rate": 4.67741935483871e-05,
+      "loss": 0.2674,
+      "step": 23
+    },
+    {
+      "epoch": 0.17200447928331467,
+      "learning_rate": 4.637096774193548e-05,
+      "loss": 0.2634,
+      "step": 24
+    },
+    {
+      "epoch": 0.1791713325867861,
+      "learning_rate": 4.596774193548387e-05,
+      "loss": 0.2558,
+      "step": 25
+    },
+    {
+      "epoch": 0.18633818589025755,
+      "learning_rate": 4.556451612903226e-05,
+      "loss": 0.2409,
+      "step": 26
+    },
+    {
+      "epoch": 0.193505039193729,
+      "learning_rate": 4.516129032258064e-05,
+      "loss": 0.2576,
+      "step": 27
+    },
+    {
+      "epoch": 0.20067189249720044,
+      "learning_rate": 4.475806451612903e-05,
+      "loss": 0.2942,
+      "step": 28
+    },
+    {
+      "epoch": 0.20783874580067188,
+      "learning_rate": 4.435483870967742e-05,
+      "loss": 0.2715,
+      "step": 29
+    },
+    {
+      "epoch": 0.21500559910414332,
+      "learning_rate": 4.395161290322581e-05,
+      "loss": 0.254,
+      "step": 30
+    },
+    {
+      "epoch": 0.22217245240761477,
+      "learning_rate": 4.3548387096774194e-05,
+      "loss": 0.2368,
+      "step": 31
+    },
+    {
+      "epoch": 0.22933930571108624,
+      "learning_rate": 4.3145161290322584e-05,
+      "loss": 0.2398,
+      "step": 32
+    },
+    {
+      "epoch": 0.23650615901455768,
+      "learning_rate": 4.2741935483870973e-05,
+      "loss": 0.2548,
+      "step": 33
+    },
+    {
+      "epoch": 0.24367301231802913,
+      "learning_rate": 4.2338709677419356e-05,
+      "loss": 0.2435,
+      "step": 34
+    },
+    {
+      "epoch": 0.25083986562150057,
+      "learning_rate": 4.1935483870967746e-05,
+      "loss": 0.2423,
+      "step": 35
+    },
+    {
+      "epoch": 0.258006718924972,
+      "learning_rate": 4.1532258064516135e-05,
+      "loss": 0.24,
+      "step": 36
+    },
+    {
+      "epoch": 0.26517357222844345,
+      "learning_rate": 4.112903225806452e-05,
+      "loss": 0.2244,
+      "step": 37
+    },
+    {
+      "epoch": 0.2723404255319149,
+      "learning_rate": 4.072580645161291e-05,
+      "loss": 0.2399,
+      "step": 38
+    },
+    {
+      "epoch": 0.27950727883538634,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.238,
+      "step": 39
+    },
+    {
+      "epoch": 0.2866741321388578,
+      "learning_rate": 3.991935483870968e-05,
+      "loss": 0.2435,
+      "step": 40
+    },
+    {
+      "epoch": 0.29384098544232923,
+      "learning_rate": 3.951612903225806e-05,
+      "loss": 0.2556,
+      "step": 41
+    },
+    {
+      "epoch": 0.30100783874580067,
+      "learning_rate": 3.911290322580645e-05,
+      "loss": 0.2543,
+      "step": 42
+    },
+    {
+      "epoch": 0.3081746920492721,
+      "learning_rate": 3.870967741935484e-05,
+      "loss": 0.2321,
+      "step": 43
+    },
+    {
+      "epoch": 0.31534154535274356,
+      "learning_rate": 3.8306451612903224e-05,
+      "loss": 0.2279,
+      "step": 44
+    },
+    {
+      "epoch": 0.322508398656215,
+      "learning_rate": 3.7903225806451614e-05,
+      "loss": 0.22,
+      "step": 45
+    },
+    {
+      "epoch": 0.32967525195968644,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.2265,
+      "step": 46
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 0.2201,
+      "step": 47
+    },
+    {
+      "epoch": 0.34400895856662933,
+      "learning_rate": 3.6693548387096776e-05,
+      "loss": 0.2273,
+      "step": 48
+    },
+    {
+      "epoch": 0.3511758118701008,
+      "learning_rate": 3.6290322580645165e-05,
+      "loss": 0.2328,
+      "step": 49
+    },
+    {
+      "epoch": 0.3583426651735722,
+      "learning_rate": 3.5887096774193555e-05,
+      "loss": 0.235,
+      "step": 50
+    },
+    {
+      "epoch": 0.36550951847704366,
+      "learning_rate": 3.548387096774194e-05,
+      "loss": 0.2301,
+      "step": 51
+    },
+    {
+      "epoch": 0.3726763717805151,
+      "learning_rate": 3.508064516129033e-05,
+      "loss": 0.2353,
+      "step": 52
+    },
+    {
+      "epoch": 0.37984322508398655,
+      "learning_rate": 3.467741935483872e-05,
+      "loss": 0.2429,
+      "step": 53
+    },
+    {
+      "epoch": 0.387010078387458,
+      "learning_rate": 3.427419354838709e-05,
+      "loss": 0.2289,
+      "step": 54
+    },
+    {
+      "epoch": 0.39417693169092943,
+      "learning_rate": 3.387096774193548e-05,
+      "loss": 0.2241,
+      "step": 55
+    },
+    {
+      "epoch": 0.4013437849944009,
+      "learning_rate": 3.346774193548387e-05,
+      "loss": 0.2215,
+      "step": 56
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "learning_rate": 3.306451612903226e-05,
+      "loss": 0.2237,
+      "step": 57
+    },
+    {
+      "epoch": 0.41567749160134376,
+      "learning_rate": 3.2661290322580644e-05,
+      "loss": 0.2152,
+      "step": 58
+    },
+    {
+      "epoch": 0.4228443449048152,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.2243,
+      "step": 59
+    },
+    {
+      "epoch": 0.43001119820828665,
+      "learning_rate": 3.185483870967742e-05,
+      "loss": 0.2193,
+      "step": 60
+    },
+    {
+      "epoch": 0.4371780515117581,
+      "learning_rate": 3.1451612903225806e-05,
+      "loss": 0.2175,
+      "step": 61
+    },
+    {
+      "epoch": 0.44434490481522954,
+      "learning_rate": 3.1048387096774195e-05,
+      "loss": 0.2143,
+      "step": 62
+    },
+    {
+      "epoch": 0.45151175811870103,
+      "learning_rate": 3.0645161290322585e-05,
+      "loss": 0.219,
+      "step": 63
+    },
+    {
+      "epoch": 0.4586786114221725,
+      "learning_rate": 3.024193548387097e-05,
+      "loss": 0.2084,
+      "step": 64
+    },
+    {
+      "epoch": 0.4658454647256439,
+      "learning_rate": 2.9838709677419357e-05,
+      "loss": 0.2199,
+      "step": 65
+    },
+    {
+      "epoch": 0.47301231802911536,
+      "learning_rate": 2.9435483870967743e-05,
+      "loss": 0.2137,
+      "step": 66
+    },
+    {
+      "epoch": 0.4801791713325868,
+      "learning_rate": 2.9032258064516133e-05,
+      "loss": 0.2277,
+      "step": 67
+    },
+    {
+      "epoch": 0.48734602463605825,
+      "learning_rate": 2.862903225806452e-05,
+      "loss": 0.2167,
+      "step": 68
+    },
+    {
+      "epoch": 0.4945128779395297,
+      "learning_rate": 2.822580645161291e-05,
+      "loss": 0.22,
+      "step": 69
+    },
+    {
+      "epoch": 0.5016797312430011,
+      "learning_rate": 2.7822580645161288e-05,
+      "loss": 0.2175,
+      "step": 70
+    },
+    {
+      "epoch": 0.5088465845464726,
+      "learning_rate": 2.7419354838709678e-05,
+      "loss": 0.2186,
+      "step": 71
+    },
+    {
+      "epoch": 0.516013437849944,
+      "learning_rate": 2.7016129032258064e-05,
+      "loss": 0.2285,
+      "step": 72
+    },
+    {
+      "epoch": 0.5231802911534155,
+      "learning_rate": 2.661290322580645e-05,
+      "loss": 0.2187,
+      "step": 73
+    },
+    {
+      "epoch": 0.5303471444568869,
+      "learning_rate": 2.620967741935484e-05,
+      "loss": 0.2214,
+      "step": 74
+    },
+    {
+      "epoch": 0.5375139977603584,
+      "learning_rate": 2.5806451612903226e-05,
+      "loss": 0.206,
+      "step": 75
+    },
+    {
+      "epoch": 0.5446808510638298,
+      "learning_rate": 2.5403225806451615e-05,
+      "loss": 0.2084,
+      "step": 76
+    },
+    {
+      "epoch": 0.5518477043673012,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2047,
+      "step": 77
+    },
+    {
+      "epoch": 0.5590145576707727,
+      "learning_rate": 2.4596774193548387e-05,
+      "loss": 0.2124,
+      "step": 78
+    },
+    {
+      "epoch": 0.5661814109742441,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.2164,
+      "step": 79
+    },
+    {
+      "epoch": 0.5733482642777156,
+      "learning_rate": 2.3790322580645163e-05,
+      "loss": 0.2166,
+      "step": 80
+    },
+    {
+      "epoch": 0.580515117581187,
+      "learning_rate": 2.338709677419355e-05,
+      "loss": 0.2174,
+      "step": 81
+    },
+    {
+      "epoch": 0.5876819708846585,
+      "learning_rate": 2.2983870967741935e-05,
+      "loss": 0.2091,
+      "step": 82
+    },
+    {
+      "epoch": 0.5948488241881299,
+      "learning_rate": 2.258064516129032e-05,
+      "loss": 0.2109,
+      "step": 83
+    },
+    {
+      "epoch": 0.6020156774916013,
+      "learning_rate": 2.217741935483871e-05,
+      "loss": 0.215,
+      "step": 84
+    },
+    {
+      "epoch": 0.6091825307950728,
+      "learning_rate": 2.1774193548387097e-05,
+      "loss": 0.2254,
+      "step": 85
+    },
+    {
+      "epoch": 0.6163493840985442,
+      "learning_rate": 2.1370967741935487e-05,
+      "loss": 0.2167,
+      "step": 86
+    },
+    {
+      "epoch": 0.6235162374020157,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 0.2124,
+      "step": 87
+    },
+    {
+      "epoch": 0.6306830907054871,
+      "learning_rate": 2.056451612903226e-05,
+      "loss": 0.2192,
+      "step": 88
+    },
+    {
+      "epoch": 0.6378499440089586,
+      "learning_rate": 2.0161290322580645e-05,
+      "loss": 0.2115,
+      "step": 89
+    },
+    {
+      "epoch": 0.64501679731243,
+      "learning_rate": 1.975806451612903e-05,
+      "loss": 0.2138,
+      "step": 90
+    },
+    {
+      "epoch": 0.6521836506159014,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 0.2127,
+      "step": 91
+    },
+    {
+      "epoch": 0.6593505039193729,
+      "learning_rate": 1.8951612903225807e-05,
+      "loss": 0.2084,
+      "step": 92
+    },
+    {
+      "epoch": 0.6665173572228443,
+      "learning_rate": 1.8548387096774193e-05,
+      "loss": 0.2143,
+      "step": 93
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "learning_rate": 1.8145161290322583e-05,
+      "loss": 0.2045,
+      "step": 94
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 0.2015,
+      "step": 95
+    },
+    {
+      "epoch": 0.6880179171332587,
+      "learning_rate": 1.733870967741936e-05,
+      "loss": 0.203,
+      "step": 96
+    },
+    {
+      "epoch": 0.6951847704367301,
+      "learning_rate": 1.693548387096774e-05,
+      "loss": 0.2157,
+      "step": 97
+    },
+    {
+      "epoch": 0.7023516237402015,
+      "learning_rate": 1.653225806451613e-05,
+      "loss": 0.2163,
+      "step": 98
+    },
+    {
+      "epoch": 0.709518477043673,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.2037,
+      "step": 99
+    },
+    {
+      "epoch": 0.7166853303471444,
+      "learning_rate": 1.5725806451612903e-05,
+      "loss": 0.2152,
+      "step": 100
+    },
+    {
+      "epoch": 0.7238521836506159,
+      "learning_rate": 1.5322580645161292e-05,
+      "loss": 0.2088,
+      "step": 101
+    },
+    {
+      "epoch": 0.7310190369540873,
+      "learning_rate": 1.4919354838709679e-05,
+      "loss": 0.2132,
+      "step": 102
+    },
+    {
+      "epoch": 0.7381858902575588,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 0.2099,
+      "step": 103
+    },
+    {
+      "epoch": 0.7453527435610302,
+      "learning_rate": 1.4112903225806454e-05,
+      "loss": 0.2079,
+      "step": 104
+    },
+    {
+      "epoch": 0.7525195968645016,
+      "learning_rate": 1.3709677419354839e-05,
+      "loss": 0.2174,
+      "step": 105
+    },
+    {
+      "epoch": 0.7596864501679731,
+      "learning_rate": 1.3306451612903225e-05,
+      "loss": 0.1999,
+      "step": 106
+    },
+    {
+      "epoch": 0.7668533034714445,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.2148,
+      "step": 107
+    },
+    {
+      "epoch": 0.774020156774916,
+      "learning_rate": 1.25e-05,
+      "loss": 0.1996,
+      "step": 108
+    },
+    {
+      "epoch": 0.7811870100783874,
+      "learning_rate": 1.2096774193548388e-05,
+      "loss": 0.2165,
+      "step": 109
+    },
+    {
+      "epoch": 0.7883538633818589,
+      "learning_rate": 1.1693548387096775e-05,
+      "loss": 0.2134,
+      "step": 110
+    },
+    {
+      "epoch": 0.7955207166853303,
+      "learning_rate": 1.129032258064516e-05,
+      "loss": 0.2122,
+      "step": 111
+    },
+    {
+      "epoch": 0.8026875699888018,
+      "learning_rate": 1.0887096774193549e-05,
+      "loss": 0.2021,
+      "step": 112
+    },
+    {
+      "epoch": 0.8098544232922732,
+      "learning_rate": 1.0483870967741936e-05,
+      "loss": 0.2058,
+      "step": 113
+    },
+    {
+      "epoch": 0.8170212765957446,
+      "learning_rate": 1.0080645161290323e-05,
+      "loss": 0.2154,
+      "step": 114
+    },
+    {
+      "epoch": 0.8241881298992161,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 0.2133,
+      "step": 115
+    },
+    {
+      "epoch": 0.8313549832026875,
+      "learning_rate": 9.274193548387097e-06,
+      "loss": 0.2127,
+      "step": 116
+    },
+    {
+      "epoch": 0.838521836506159,
+      "learning_rate": 8.870967741935484e-06,
+      "loss": 0.2176,
+      "step": 117
+    },
+    {
+      "epoch": 0.8456886898096304,
+      "learning_rate": 8.46774193548387e-06,
+      "loss": 0.2152,
+      "step": 118
+    },
+    {
+      "epoch": 0.8528555431131019,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.2075,
+      "step": 119
+    },
+    {
+      "epoch": 0.8600223964165733,
+      "learning_rate": 7.661290322580646e-06,
+      "loss": 0.2088,
+      "step": 120
+    },
+    {
+      "epoch": 0.8671892497200447,
+      "learning_rate": 7.258064516129033e-06,
+      "loss": 0.2113,
+      "step": 121
+    },
+    {
+      "epoch": 0.8743561030235162,
+      "learning_rate": 6.854838709677419e-06,
+      "loss": 0.2077,
+      "step": 122
+    },
+    {
+      "epoch": 0.8815229563269876,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 0.2127,
+      "step": 123
+    },
+    {
+      "epoch": 0.8886898096304591,
+      "learning_rate": 6.048387096774194e-06,
+      "loss": 0.214,
+      "step": 124
+    },
+    {
+      "epoch": 0.8958566629339306,
+      "learning_rate": 5.64516129032258e-06,
+      "loss": 0.2087,
+      "step": 125
+    },
+    {
+      "epoch": 0.9030235162374021,
+      "learning_rate": 5.241935483870968e-06,
+      "loss": 0.2068,
+      "step": 126
+    },
+    {
+      "epoch": 0.9101903695408735,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 0.2035,
+      "step": 127
+    },
+    {
+      "epoch": 0.917357222844345,
+      "learning_rate": 4.435483870967742e-06,
+      "loss": 0.2224,
+      "step": 128
+    },
+    {
+      "epoch": 0.9245240761478164,
+      "learning_rate": 4.032258064516129e-06,
+      "loss": 0.2128,
+      "step": 129
+    },
+    {
+      "epoch": 0.9316909294512878,
+      "learning_rate": 3.6290322580645166e-06,
+      "loss": 0.2055,
+      "step": 130
+    },
+    {
+      "epoch": 0.9388577827547593,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 0.2143,
+      "step": 131
+    },
+    {
+      "epoch": 0.9460246360582307,
+      "learning_rate": 2.82258064516129e-06,
+      "loss": 0.2045,
+      "step": 132
+    },
+    {
+      "epoch": 0.9531914893617022,
+      "learning_rate": 2.4193548387096776e-06,
+      "loss": 0.21,
+      "step": 133
+    },
+    {
+      "epoch": 0.9603583426651736,
+      "learning_rate": 2.0161290322580646e-06,
+      "loss": 0.2168,
+      "step": 134
+    },
+    {
+      "epoch": 0.9675251959686451,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 0.2069,
+      "step": 135
+    },
+    {
+      "epoch": 0.9746920492721165,
+      "learning_rate": 1.2096774193548388e-06,
+      "loss": 0.2156,
+      "step": 136
+    },
+    {
+      "epoch": 0.9818589025755879,
+      "learning_rate": 8.064516129032258e-07,
+      "loss": 0.2042,
+      "step": 137
+    },
+    {
+      "epoch": 0.9890257558790594,
+      "learning_rate": 4.032258064516129e-07,
+      "loss": 0.2116,
+      "step": 138
+    },
+    {
+      "epoch": 0.9961926091825308,
+      "learning_rate": 0.0,
+      "loss": 0.2087,
+      "step": 139
+    },
+    {
+      "epoch": 0.9961926091825308,
+      "step": 139,
+      "total_flos": 2.1062068551381156e+18,
+      "train_loss": 0.23252247102397808,
+      "train_runtime": 8188.4274,
+      "train_samples_per_second": 8.724,
+      "train_steps_per_second": 0.017
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 139,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1062068551381156e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f478a1fde45039bd8b10c993c4d0bc2d2e9405630a51068bbce2797747a4c77a
+size 4859