Upload folder using huggingface_hub

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc6d457b64eb3440b62aafe5fe9c0f95213630748165c3b8270463ae2fc5c2f
+size 4939116424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62754886a90bed127664b763e0bc118b3ce9908df03e009fc5b5e9dbac76a127
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41710b06d60120da499452d9f6c981d305936561ff45bda5b8126874e03254ce
+size 3590619888

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477093376
+  },
+  "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"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2510dd14b082963fe47efc35b0b19b2de181ef1ed034781f54750bf2e8407f
+size 11576325

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70c0b62bd953493d0675c34feecb6cb4564541e1efc60bb1704ce38255044908
+size 15607

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241736953f399f6929c6ad898eaf28227b020331cba8da2c020aaaff41594b10
+size 15607

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636810b414fb21a6f581ba1c3b8e4a411132f7b278886aabe91c31881b6d9576
+size 627

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,735 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9956122856003191,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008509506714532641,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8719,
+      "step": 1
+    },
+    {
+      "epoch": 0.017019013429065283,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8402,
+      "step": 2
+    },
+    {
+      "epoch": 0.025528520143597924,
+      "learning_rate": 1e-05,
+      "loss": 0.8438,
+      "step": 3
+    },
+    {
+      "epoch": 0.034038026858130566,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.8171,
+      "step": 4
+    },
+    {
+      "epoch": 0.04254753357266321,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8029,
+      "step": 5
+    },
+    {
+      "epoch": 0.05105704028719585,
+      "learning_rate": 2e-05,
+      "loss": 0.7858,
+      "step": 6
+    },
+    {
+      "epoch": 0.0595665470017285,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.7671,
+      "step": 7
+    },
+    {
+      "epoch": 0.06807605371626113,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.7989,
+      "step": 8
+    },
+    {
+      "epoch": 0.07658556043079377,
+      "learning_rate": 3e-05,
+      "loss": 0.7546,
+      "step": 9
+    },
+    {
+      "epoch": 0.08509506714532641,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.745,
+      "step": 10
+    },
+    {
+      "epoch": 0.09360457385985906,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.7169,
+      "step": 11
+    },
+    {
+      "epoch": 0.1021140805743917,
+      "learning_rate": 4e-05,
+      "loss": 0.7561,
+      "step": 12
+    },
+    {
+      "epoch": 0.11062358728892434,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.8475,
+      "step": 13
+    },
+    {
+      "epoch": 0.119133094003457,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.9401,
+      "step": 14
+    },
+    {
+      "epoch": 0.12764260071798963,
+      "learning_rate": 5e-05,
+      "loss": 0.8515,
+      "step": 15
+    },
+    {
+      "epoch": 0.13615210743252226,
+      "learning_rate": 4.9509803921568634e-05,
+      "loss": 0.8282,
+      "step": 16
+    },
+    {
+      "epoch": 0.14466161414705492,
+      "learning_rate": 4.901960784313725e-05,
+      "loss": 0.7526,
+      "step": 17
+    },
+    {
+      "epoch": 0.15317112086158755,
+      "learning_rate": 4.8529411764705885e-05,
+      "loss": 0.709,
+      "step": 18
+    },
+    {
+      "epoch": 0.1616806275761202,
+      "learning_rate": 4.803921568627452e-05,
+      "loss": 0.7005,
+      "step": 19
+    },
+    {
+      "epoch": 0.17019013429065283,
+      "learning_rate": 4.7549019607843135e-05,
+      "loss": 0.6978,
+      "step": 20
+    },
+    {
+      "epoch": 0.17869964100518548,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.6689,
+      "step": 21
+    },
+    {
+      "epoch": 0.1872091477197181,
+      "learning_rate": 4.656862745098039e-05,
+      "loss": 0.7231,
+      "step": 22
+    },
+    {
+      "epoch": 0.19571865443425077,
+      "learning_rate": 4.607843137254902e-05,
+      "loss": 0.6685,
+      "step": 23
+    },
+    {
+      "epoch": 0.2042281611487834,
+      "learning_rate": 4.558823529411765e-05,
+      "loss": 0.6776,
+      "step": 24
+    },
+    {
+      "epoch": 0.21273766786331605,
+      "learning_rate": 4.5098039215686275e-05,
+      "loss": 0.6853,
+      "step": 25
+    },
+    {
+      "epoch": 0.22124717457784868,
+      "learning_rate": 4.460784313725491e-05,
+      "loss": 0.7705,
+      "step": 26
+    },
+    {
+      "epoch": 0.22975668129238133,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 0.7922,
+      "step": 27
+    },
+    {
+      "epoch": 0.238266188006914,
+      "learning_rate": 4.362745098039216e-05,
+      "loss": 0.6948,
+      "step": 28
+    },
+    {
+      "epoch": 0.24677569472144661,
+      "learning_rate": 4.313725490196079e-05,
+      "loss": 0.6748,
+      "step": 29
+    },
+    {
+      "epoch": 0.25528520143597927,
+      "learning_rate": 4.2647058823529415e-05,
+      "loss": 0.7134,
+      "step": 30
+    },
+    {
+      "epoch": 0.2637947081505119,
+      "learning_rate": 4.215686274509804e-05,
+      "loss": 0.6921,
+      "step": 31
+    },
+    {
+      "epoch": 0.2723042148650445,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6839,
+      "step": 32
+    },
+    {
+      "epoch": 0.2808137215795772,
+      "learning_rate": 4.11764705882353e-05,
+      "loss": 0.6808,
+      "step": 33
+    },
+    {
+      "epoch": 0.28932322829410984,
+      "learning_rate": 4.068627450980392e-05,
+      "loss": 0.6939,
+      "step": 34
+    },
+    {
+      "epoch": 0.2978327350086425,
+      "learning_rate": 4.0196078431372555e-05,
+      "loss": 0.6846,
+      "step": 35
+    },
+    {
+      "epoch": 0.3063422417231751,
+      "learning_rate": 3.970588235294117e-05,
+      "loss": 0.6456,
+      "step": 36
+    },
+    {
+      "epoch": 0.31485174843770775,
+      "learning_rate": 3.9215686274509805e-05,
+      "loss": 0.6725,
+      "step": 37
+    },
+    {
+      "epoch": 0.3233612551522404,
+      "learning_rate": 3.872549019607844e-05,
+      "loss": 0.682,
+      "step": 38
+    },
+    {
+      "epoch": 0.33187076186677306,
+      "learning_rate": 3.8235294117647055e-05,
+      "loss": 0.7029,
+      "step": 39
+    },
+    {
+      "epoch": 0.34038026858130566,
+      "learning_rate": 3.774509803921569e-05,
+      "loss": 0.7072,
+      "step": 40
+    },
+    {
+      "epoch": 0.3488897752958383,
+      "learning_rate": 3.725490196078432e-05,
+      "loss": 0.6925,
+      "step": 41
+    },
+    {
+      "epoch": 0.35739928201037097,
+      "learning_rate": 3.6764705882352945e-05,
+      "loss": 0.6642,
+      "step": 42
+    },
+    {
+      "epoch": 0.3659087887249036,
+      "learning_rate": 3.627450980392157e-05,
+      "loss": 0.6483,
+      "step": 43
+    },
+    {
+      "epoch": 0.3744182954394362,
+      "learning_rate": 3.5784313725490195e-05,
+      "loss": 0.6779,
+      "step": 44
+    },
+    {
+      "epoch": 0.3829278021539689,
+      "learning_rate": 3.529411764705883e-05,
+      "loss": 0.6664,
+      "step": 45
+    },
+    {
+      "epoch": 0.39143730886850153,
+      "learning_rate": 3.480392156862745e-05,
+      "loss": 0.6493,
+      "step": 46
+    },
+    {
+      "epoch": 0.3999468155830342,
+      "learning_rate": 3.431372549019608e-05,
+      "loss": 0.6853,
+      "step": 47
+    },
+    {
+      "epoch": 0.4084563222975668,
+      "learning_rate": 3.382352941176471e-05,
+      "loss": 0.6549,
+      "step": 48
+    },
+    {
+      "epoch": 0.41696582901209944,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6659,
+      "step": 49
+    },
+    {
+      "epoch": 0.4254753357266321,
+      "learning_rate": 3.284313725490196e-05,
+      "loss": 0.6639,
+      "step": 50
+    },
+    {
+      "epoch": 0.43398484244116475,
+      "learning_rate": 3.235294117647059e-05,
+      "loss": 0.6583,
+      "step": 51
+    },
+    {
+      "epoch": 0.44249434915569735,
+      "learning_rate": 3.186274509803922e-05,
+      "loss": 0.6585,
+      "step": 52
+    },
+    {
+      "epoch": 0.45100385587023,
+      "learning_rate": 3.137254901960784e-05,
+      "loss": 0.6753,
+      "step": 53
+    },
+    {
+      "epoch": 0.45951336258476266,
+      "learning_rate": 3.0882352941176475e-05,
+      "loss": 0.6712,
+      "step": 54
+    },
+    {
+      "epoch": 0.4680228692992953,
+      "learning_rate": 3.0392156862745097e-05,
+      "loss": 0.6632,
+      "step": 55
+    },
+    {
+      "epoch": 0.476532376013828,
+      "learning_rate": 2.9901960784313725e-05,
+      "loss": 0.6673,
+      "step": 56
+    },
+    {
+      "epoch": 0.4850418827283606,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 0.6444,
+      "step": 57
+    },
+    {
+      "epoch": 0.49355138944289323,
+      "learning_rate": 2.8921568627450986e-05,
+      "loss": 0.6673,
+      "step": 58
+    },
+    {
+      "epoch": 0.5020608961574259,
+      "learning_rate": 2.8431372549019608e-05,
+      "loss": 0.6629,
+      "step": 59
+    },
+    {
+      "epoch": 0.5105704028719585,
+      "learning_rate": 2.7941176470588236e-05,
+      "loss": 0.6723,
+      "step": 60
+    },
+    {
+      "epoch": 0.5190799095864912,
+      "learning_rate": 2.7450980392156865e-05,
+      "loss": 0.6622,
+      "step": 61
+    },
+    {
+      "epoch": 0.5275894163010239,
+      "learning_rate": 2.696078431372549e-05,
+      "loss": 0.6606,
+      "step": 62
+    },
+    {
+      "epoch": 0.5360989230155564,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 0.6823,
+      "step": 63
+    },
+    {
+      "epoch": 0.544608429730089,
+      "learning_rate": 2.5980392156862747e-05,
+      "loss": 0.6519,
+      "step": 64
+    },
+    {
+      "epoch": 0.5531179364446217,
+      "learning_rate": 2.5490196078431373e-05,
+      "loss": 0.6702,
+      "step": 65
+    },
+    {
+      "epoch": 0.5616274431591544,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6463,
+      "step": 66
+    },
+    {
+      "epoch": 0.570136949873687,
+      "learning_rate": 2.4509803921568626e-05,
+      "loss": 0.6604,
+      "step": 67
+    },
+    {
+      "epoch": 0.5786464565882197,
+      "learning_rate": 2.401960784313726e-05,
+      "loss": 0.6535,
+      "step": 68
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.6605,
+      "step": 69
+    },
+    {
+      "epoch": 0.595665470017285,
+      "learning_rate": 2.303921568627451e-05,
+      "loss": 0.6514,
+      "step": 70
+    },
+    {
+      "epoch": 0.6041749767318175,
+      "learning_rate": 2.2549019607843138e-05,
+      "loss": 0.6533,
+      "step": 71
+    },
+    {
+      "epoch": 0.6126844834463502,
+      "learning_rate": 2.2058823529411766e-05,
+      "loss": 0.6564,
+      "step": 72
+    },
+    {
+      "epoch": 0.6211939901608828,
+      "learning_rate": 2.1568627450980395e-05,
+      "loss": 0.6679,
+      "step": 73
+    },
+    {
+      "epoch": 0.6297034968754155,
+      "learning_rate": 2.107843137254902e-05,
+      "loss": 0.6476,
+      "step": 74
+    },
+    {
+      "epoch": 0.6382130035899481,
+      "learning_rate": 2.058823529411765e-05,
+      "loss": 0.6917,
+      "step": 75
+    },
+    {
+      "epoch": 0.6467225103044808,
+      "learning_rate": 2.0098039215686277e-05,
+      "loss": 0.6565,
+      "step": 76
+    },
+    {
+      "epoch": 0.6552320170190135,
+      "learning_rate": 1.9607843137254903e-05,
+      "loss": 0.6329,
+      "step": 77
+    },
+    {
+      "epoch": 0.6637415237335461,
+      "learning_rate": 1.9117647058823528e-05,
+      "loss": 0.6149,
+      "step": 78
+    },
+    {
+      "epoch": 0.6722510304480788,
+      "learning_rate": 1.862745098039216e-05,
+      "loss": 0.6799,
+      "step": 79
+    },
+    {
+      "epoch": 0.6807605371626113,
+      "learning_rate": 1.8137254901960785e-05,
+      "loss": 0.6458,
+      "step": 80
+    },
+    {
+      "epoch": 0.689270043877144,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.6376,
+      "step": 81
+    },
+    {
+      "epoch": 0.6977795505916766,
+      "learning_rate": 1.715686274509804e-05,
+      "loss": 0.6688,
+      "step": 82
+    },
+    {
+      "epoch": 0.7062890573062093,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6466,
+      "step": 83
+    },
+    {
+      "epoch": 0.7147985640207419,
+      "learning_rate": 1.6176470588235296e-05,
+      "loss": 0.6386,
+      "step": 84
+    },
+    {
+      "epoch": 0.7233080707352746,
+      "learning_rate": 1.568627450980392e-05,
+      "loss": 0.6427,
+      "step": 85
+    },
+    {
+      "epoch": 0.7318175774498072,
+      "learning_rate": 1.5196078431372548e-05,
+      "loss": 0.6617,
+      "step": 86
+    },
+    {
+      "epoch": 0.7403270841643399,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.6573,
+      "step": 87
+    },
+    {
+      "epoch": 0.7488365908788724,
+      "learning_rate": 1.4215686274509804e-05,
+      "loss": 0.6342,
+      "step": 88
+    },
+    {
+      "epoch": 0.7573460975934051,
+      "learning_rate": 1.3725490196078432e-05,
+      "loss": 0.6455,
+      "step": 89
+    },
+    {
+      "epoch": 0.7658556043079378,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 0.6042,
+      "step": 90
+    },
+    {
+      "epoch": 0.7743651110224704,
+      "learning_rate": 1.2745098039215686e-05,
+      "loss": 0.639,
+      "step": 91
+    },
+    {
+      "epoch": 0.7828746177370031,
+      "learning_rate": 1.2254901960784313e-05,
+      "loss": 0.6496,
+      "step": 92
+    },
+    {
+      "epoch": 0.7913841244515357,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.6474,
+      "step": 93
+    },
+    {
+      "epoch": 0.7998936311660684,
+      "learning_rate": 1.1274509803921569e-05,
+      "loss": 0.6418,
+      "step": 94
+    },
+    {
+      "epoch": 0.808403137880601,
+      "learning_rate": 1.0784313725490197e-05,
+      "loss": 0.6434,
+      "step": 95
+    },
+    {
+      "epoch": 0.8169126445951336,
+      "learning_rate": 1.0294117647058824e-05,
+      "loss": 0.659,
+      "step": 96
+    },
+    {
+      "epoch": 0.8254221513096662,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.6342,
+      "step": 97
+    },
+    {
+      "epoch": 0.8339316580241989,
+      "learning_rate": 9.31372549019608e-06,
+      "loss": 0.647,
+      "step": 98
+    },
+    {
+      "epoch": 0.8424411647387315,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.6306,
+      "step": 99
+    },
+    {
+      "epoch": 0.8509506714532642,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6724,
+      "step": 100
+    },
+    {
+      "epoch": 0.8594601781677969,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.6455,
+      "step": 101
+    },
+    {
+      "epoch": 0.8679696848823295,
+      "learning_rate": 7.3529411764705884e-06,
+      "loss": 0.634,
+      "step": 102
+    },
+    {
+      "epoch": 0.8764791915968622,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.6353,
+      "step": 103
+    },
+    {
+      "epoch": 0.8849886983113947,
+      "learning_rate": 6.372549019607843e-06,
+      "loss": 0.6632,
+      "step": 104
+    },
+    {
+      "epoch": 0.8934982050259274,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.6616,
+      "step": 105
+    },
+    {
+      "epoch": 0.90200771174046,
+      "learning_rate": 5.392156862745099e-06,
+      "loss": 0.6312,
+      "step": 106
+    },
+    {
+      "epoch": 0.9105172184549927,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.6592,
+      "step": 107
+    },
+    {
+      "epoch": 0.9190267251695253,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.6634,
+      "step": 108
+    },
+    {
+      "epoch": 0.927536231884058,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.6428,
+      "step": 109
+    },
+    {
+      "epoch": 0.9360457385985906,
+      "learning_rate": 3.431372549019608e-06,
+      "loss": 0.6261,
+      "step": 110
+    },
+    {
+      "epoch": 0.9445552453131233,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.6425,
+      "step": 111
+    },
+    {
+      "epoch": 0.953064752027656,
+      "learning_rate": 2.450980392156863e-06,
+      "loss": 0.6614,
+      "step": 112
+    },
+    {
+      "epoch": 0.9615742587421885,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.6545,
+      "step": 113
+    },
+    {
+      "epoch": 0.9700837654567211,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 0.6184,
+      "step": 114
+    },
+    {
+      "epoch": 0.9785932721712538,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.6671,
+      "step": 115
+    },
+    {
+      "epoch": 0.9871027788857865,
+      "learning_rate": 4.901960784313725e-07,
+      "loss": 0.65,
+      "step": 116
+    },
+    {
+      "epoch": 0.9956122856003191,
+      "learning_rate": 0.0,
+      "loss": 0.6446,
+      "step": 117
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 117,
+  "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": 2.689042619882799e+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 sha256:8e15f41f6e98922492a05ed9a8b6ffd96cd1e257cf8e068a9fe8c14287e0128b
+size 4923