Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd4f0ced6eaaa81ced74d2adc1e1926a33b9baaa11baacfb4f813d3e8c4301a
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44aca46d6e6a471e919a511ce1cd1d0d3dcf5cc4828f6a4b2a433dbcd54852aa
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0f2c83c62767ceaa9c46884ad08df1dca13d266dd2e8e6523fd25c5d9b1ed30
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79925407cc9b3988886d6011c475b5fd3fcf1c064542da277d1a04a3f7722445
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,934 @@
+{
+  "best_metric": 0.82,
+  "best_model_checkpoint": "/workspace/finetuning/models/sqlcoder_8b_fullft_ds_001_600_mgn10/checkpoint-500",
+  "epoch": 0.9166666666666666,
+  "eval_steps": 50,
+  "global_step": 550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008333333333333333,
+      "grad_norm": 8.25,
+      "learning_rate": 9.99830375862901e-06,
+      "loss": 0.6079,
+      "step": 5
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 6.0,
+      "learning_rate": 9.99321619703514e-06,
+      "loss": 0.3417,
+      "step": 10
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 5.5,
+      "learning_rate": 9.984740801978986e-06,
+      "loss": 0.3039,
+      "step": 15
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 5.875,
+      "learning_rate": 9.972883382072955e-06,
+      "loss": 0.3035,
+      "step": 20
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 6.15625,
+      "learning_rate": 9.957652063800363e-06,
+      "loss": 0.2822,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.90625,
+      "learning_rate": 9.939057285945933e-06,
+      "loss": 0.2703,
+      "step": 30
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.917111792441576e-06,
+      "loss": 0.2598,
+      "step": 35
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.891830623632339e-06,
+      "loss": 0.267,
+      "step": 40
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.8632311059685e-06,
+      "loss": 0.2431,
+      "step": 45
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.831332840130889e-06,
+      "loss": 0.2533,
+      "step": 50
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "eval_count_mismatch_i_diff_avg": 2.25,
+      "eval_first_index_mismatch_avg": 8.25,
+      "eval_loss": 0.15123993158340454,
+      "eval_mean_mismatch_i_diff_avg": 8.4375,
+      "eval_runtime": 1.4309,
+      "eval_samples_per_second": 2.795,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.699,
+      "eval_tokens_match_avg": 0.9552213461413188,
+      "step": 50
+    },
+    {
+      "epoch": 0.09166666666666666,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.796157687597557e-06,
+      "loss": 0.261,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.5,
+      "learning_rate": 9.757729755661012e-06,
+      "loss": 0.2309,
+      "step": 60
+    },
+    {
+      "epoch": 0.10833333333333334,
+      "grad_norm": 4.6875,
+      "learning_rate": 9.716075380906285e-06,
+      "loss": 0.2418,
+      "step": 65
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 4.84375,
+      "learning_rate": 9.671223111161151e-06,
+      "loss": 0.2142,
+      "step": 70
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 5.625,
+      "learning_rate": 9.623203685930872e-06,
+      "loss": 0.23,
+      "step": 75
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 4.125,
+      "learning_rate": 9.572050015330875e-06,
+      "loss": 0.2205,
+      "step": 80
+    },
+    {
+      "epoch": 0.14166666666666666,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.517797157531813e-06,
+      "loss": 0.2112,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.460482294732423e-06,
+      "loss": 0.206,
+      "step": 90
+    },
+    {
+      "epoch": 0.15833333333333333,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.40014470767673e-06,
+      "loss": 0.2323,
+      "step": 95
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 5.25,
+      "learning_rate": 9.336825748732973e-06,
+      "loss": 0.2046,
+      "step": 100
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "eval_count_mismatch_i_diff_avg": 1.5,
+      "eval_first_index_mismatch_avg": 19.25,
+      "eval_loss": 0.12254643440246582,
+      "eval_mean_mismatch_i_diff_avg": 19.4375,
+      "eval_runtime": 1.4476,
+      "eval_samples_per_second": 2.763,
+      "eval_sql_exact_match_string": 1,
+      "eval_steps_per_second": 0.691,
+      "eval_tokens_match_avg": 0.9684337464860721,
+      "step": 100
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.270568813552757e-06,
+      "loss": 0.209,
+      "step": 105
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 5.5,
+      "learning_rate": 9.201419311329848e-06,
+      "loss": 0.2209,
+      "step": 110
+    },
+    {
+      "epoch": 0.19166666666666668,
+      "grad_norm": 5.25,
+      "learning_rate": 9.129424633678977e-06,
+      "loss": 0.1959,
+      "step": 115
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.15625,
+      "learning_rate": 9.054634122155991e-06,
+      "loss": 0.19,
+      "step": 120
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 4.4375,
+      "learning_rate": 8.977099034441616e-06,
+      "loss": 0.2103,
+      "step": 125
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.896872509212006e-06,
+      "loss": 0.2035,
+      "step": 130
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 5.53125,
+      "learning_rate": 8.814009529720153e-06,
+      "loss": 0.1997,
+      "step": 135
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 5.03125,
+      "learning_rate": 8.728566886113101e-06,
+      "loss": 0.198,
+      "step": 140
+    },
+    {
+      "epoch": 0.24166666666666667,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.640603136510823e-06,
+      "loss": 0.184,
+      "step": 145
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.34375,
+      "learning_rate": 8.55017856687341e-06,
+      "loss": 0.1826,
+      "step": 150
+    },
+    {
+      "epoch": 0.25,
+      "eval_count_mismatch_i_diff_avg": 1.75,
+      "eval_first_index_mismatch_avg": 9.25,
+      "eval_loss": 0.11601436883211136,
+      "eval_mean_mismatch_i_diff_avg": 9.583333333333334,
+      "eval_runtime": 1.4309,
+      "eval_samples_per_second": 2.795,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.699,
+      "eval_tokens_match_avg": 0.9654995853439766,
+      "step": 150
+    },
+    {
+      "epoch": 0.25833333333333336,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.45735514968408e-06,
+      "loss": 0.1722,
+      "step": 155
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 5.4375,
+      "learning_rate": 8.362196501476348e-06,
+      "loss": 0.1735,
+      "step": 160
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 5.15625,
+      "learning_rate": 8.26476783923441e-06,
+      "loss": 0.178,
+      "step": 165
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 5.46875,
+      "learning_rate": 8.165135935696693e-06,
+      "loss": 0.1929,
+      "step": 170
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 4.3125,
+      "learning_rate": 8.063369073593167e-06,
+      "loss": 0.1815,
+      "step": 175
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.21875,
+      "learning_rate": 7.959536998847742e-06,
+      "loss": 0.195,
+      "step": 180
+    },
+    {
+      "epoch": 0.30833333333333335,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.853710872777922e-06,
+      "loss": 0.1765,
+      "step": 185
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 4.84375,
+      "learning_rate": 7.745963223324384e-06,
+      "loss": 0.1772,
+      "step": 190
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 4.75,
+      "learning_rate": 7.636367895343949e-06,
+      "loss": 0.1641,
+      "step": 195
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 4.8125,
+      "learning_rate": 7.525000000000003e-06,
+      "loss": 0.1889,
+      "step": 200
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_count_mismatch_i_diff_avg": 1.5,
+      "eval_first_index_mismatch_avg": 9.25,
+      "eval_loss": 0.10480775684118271,
+      "eval_mean_mismatch_i_diff_avg": 9.083333333333334,
+      "eval_runtime": 1.4264,
+      "eval_samples_per_second": 2.804,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.701,
+      "eval_tokens_match_avg": 0.9693457391901305,
+      "step": 200
+    },
+    {
+      "epoch": 0.3416666666666667,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.411935863285065e-06,
+      "loss": 0.1786,
+      "step": 205
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.1875,
+      "learning_rate": 7.297252973710758e-06,
+      "loss": 0.1706,
+      "step": 210
+    },
+    {
+      "epoch": 0.35833333333333334,
+      "grad_norm": 4.75,
+      "learning_rate": 7.181029929201061e-06,
+      "loss": 0.1916,
+      "step": 215
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 5.53125,
+      "learning_rate": 7.063346383225212e-06,
+      "loss": 0.1701,
+      "step": 220
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 4.75,
+      "learning_rate": 6.944282990207196e-06,
+      "loss": 0.1628,
+      "step": 225
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 5.3125,
+      "learning_rate": 6.823921350249237e-06,
+      "loss": 0.1801,
+      "step": 230
+    },
+    {
+      "epoch": 0.39166666666666666,
+      "grad_norm": 4.6875,
+      "learning_rate": 6.702343953207167e-06,
+      "loss": 0.1492,
+      "step": 235
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.625,
+      "learning_rate": 6.579634122155992e-06,
+      "loss": 0.1608,
+      "step": 240
+    },
+    {
+      "epoch": 0.4083333333333333,
+      "grad_norm": 4.59375,
+      "learning_rate": 6.455875956284421e-06,
+      "loss": 0.1515,
+      "step": 245
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 4.59375,
+      "learning_rate": 6.331154273257482e-06,
+      "loss": 0.1597,
+      "step": 250
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "eval_count_mismatch_i_diff_avg": 1.75,
+      "eval_first_index_mismatch_avg": 21.0,
+      "eval_loss": 0.11433370411396027,
+      "eval_mean_mismatch_i_diff_avg": 19.583333333333336,
+      "eval_runtime": 1.4735,
+      "eval_samples_per_second": 2.715,
+      "eval_sql_exact_match_string": 1,
+      "eval_steps_per_second": 0.679,
+      "eval_tokens_match_avg": 0.9659372604140046,
+      "step": 250
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 3.890625,
+      "learning_rate": 6.205554551086736e-06,
+      "loss": 0.1339,
+      "step": 255
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 5.25,
+      "learning_rate": 6.079162869547913e-06,
+      "loss": 0.17,
+      "step": 260
+    },
+    {
+      "epoch": 0.44166666666666665,
+      "grad_norm": 5.28125,
+      "learning_rate": 5.952065851186132e-06,
+      "loss": 0.1598,
+      "step": 265
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.5,
+      "learning_rate": 5.824350601949145e-06,
+      "loss": 0.1545,
+      "step": 270
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 6.71875,
+      "learning_rate": 5.696104651489257e-06,
+      "loss": 0.1552,
+      "step": 275
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 4.875,
+      "learning_rate": 5.567415893174889e-06,
+      "loss": 0.1642,
+      "step": 280
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 4.25,
+      "learning_rate": 5.438372523852835e-06,
+      "loss": 0.1581,
+      "step": 285
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 5.03125,
+      "learning_rate": 5.309062983402575e-06,
+      "loss": 0.1632,
+      "step": 290
+    },
+    {
+      "epoch": 0.49166666666666664,
+      "grad_norm": 4.59375,
+      "learning_rate": 5.179575894123973e-06,
+      "loss": 0.1493,
+      "step": 295
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.125,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 0.149,
+      "step": 300
+    },
+    {
+      "epoch": 0.5,
+      "eval_count_mismatch_i_diff_avg": 2.0,
+      "eval_first_index_mismatch_avg": 20.0,
+      "eval_loss": 0.11815375089645386,
+      "eval_mean_mismatch_i_diff_avg": 18.9375,
+      "eval_runtime": 1.3387,
+      "eval_samples_per_second": 2.988,
+      "eval_sql_exact_match_string": 1,
+      "eval_steps_per_second": 0.747,
+      "eval_tokens_match_avg": 0.9601233069256325,
+      "step": 300
+    },
+    {
+      "epoch": 0.5083333333333333,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.9204241058760295e-06,
+      "loss": 0.155,
+      "step": 305
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 4.28125,
+      "learning_rate": 4.79093701659743e-06,
+      "loss": 0.1646,
+      "step": 310
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 4.65625,
+      "learning_rate": 4.661627476147171e-06,
+      "loss": 0.1413,
+      "step": 315
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.03125,
+      "learning_rate": 4.5325841068251195e-06,
+      "loss": 0.1476,
+      "step": 320
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 4.75,
+      "learning_rate": 4.403895348510749e-06,
+      "loss": 0.147,
+      "step": 325
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.875,
+      "learning_rate": 4.27564939805086e-06,
+      "loss": 0.1412,
+      "step": 330
+    },
+    {
+      "epoch": 0.5583333333333333,
+      "grad_norm": 4.65625,
+      "learning_rate": 4.1479341488138745e-06,
+      "loss": 0.1325,
+      "step": 335
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 4.9375,
+      "learning_rate": 4.020837130452094e-06,
+      "loss": 0.1462,
+      "step": 340
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 5.28125,
+      "learning_rate": 3.894445448913271e-06,
+      "loss": 0.1454,
+      "step": 345
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.7688457267425276e-06,
+      "loss": 0.1476,
+      "step": 350
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "eval_count_mismatch_i_diff_avg": 2.25,
+      "eval_first_index_mismatch_avg": 8.25,
+      "eval_loss": 0.11698409914970398,
+      "eval_mean_mismatch_i_diff_avg": 10.4375,
+      "eval_runtime": 1.2608,
+      "eval_samples_per_second": 3.173,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.793,
+      "eval_tokens_match_avg": 0.9547836710712908,
+      "step": 350
+    },
+    {
+      "epoch": 0.5916666666666667,
+      "grad_norm": 4.875,
+      "learning_rate": 3.6441240437155883e-06,
+      "loss": 0.1504,
+      "step": 355
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.5203658778440145e-06,
+      "loss": 0.1616,
+      "step": 360
+    },
+    {
+      "epoch": 0.6083333333333333,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.397656046792837e-06,
+      "loss": 0.16,
+      "step": 365
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.2760786497507687e-06,
+      "loss": 0.1393,
+      "step": 370
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 5.0,
+      "learning_rate": 3.155717009792809e-06,
+      "loss": 0.1526,
+      "step": 375
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 6.15625,
+      "learning_rate": 3.036653616774792e-06,
+      "loss": 0.1619,
+      "step": 380
+    },
+    {
+      "epoch": 0.6416666666666667,
+      "grad_norm": 4.75,
+      "learning_rate": 2.9189700707989414e-06,
+      "loss": 0.1428,
+      "step": 385
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.46875,
+      "learning_rate": 2.8027470262892473e-06,
+      "loss": 0.1377,
+      "step": 390
+    },
+    {
+      "epoch": 0.6583333333333333,
+      "grad_norm": 4.3125,
+      "learning_rate": 2.688064136714942e-06,
+      "loss": 0.1382,
+      "step": 395
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.575000000000003e-06,
+      "loss": 0.1465,
+      "step": 400
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_count_mismatch_i_diff_avg": 2.25,
+      "eval_first_index_mismatch_avg": 10.75,
+      "eval_loss": 0.11492403596639633,
+      "eval_mean_mismatch_i_diff_avg": 9.6875,
+      "eval_runtime": 1.4356,
+      "eval_samples_per_second": 2.786,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.697,
+      "eval_tokens_match_avg": 0.9552213461413188,
+      "step": 400
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 4.90625,
+      "learning_rate": 2.4636321046560575e-06,
+      "loss": 0.146,
+      "step": 405
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 4.78125,
+      "learning_rate": 2.3540367766756217e-06,
+      "loss": 0.1496,
+      "step": 410
+    },
+    {
+      "epoch": 0.6916666666666667,
+      "grad_norm": 4.75,
+      "learning_rate": 2.2462891272220828e-06,
+      "loss": 0.1534,
+      "step": 415
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.4375,
+      "learning_rate": 2.140463001152263e-06,
+      "loss": 0.139,
+      "step": 420
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 4.71875,
+      "learning_rate": 2.0366309264068387e-06,
+      "loss": 0.1495,
+      "step": 425
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 5.15625,
+      "learning_rate": 1.9348640643033098e-06,
+      "loss": 0.1434,
+      "step": 430
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.8352321607655958e-06,
+      "loss": 0.1494,
+      "step": 435
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.7378034985236564e-06,
+      "loss": 0.155,
+      "step": 440
+    },
+    {
+      "epoch": 0.7416666666666667,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.6426448503159242e-06,
+      "loss": 0.1418,
+      "step": 445
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.0,
+      "learning_rate": 1.5498214331265955e-06,
+      "loss": 0.1542,
+      "step": 450
+    },
+    {
+      "epoch": 0.75,
+      "eval_count_mismatch_i_diff_avg": 2.0,
+      "eval_first_index_mismatch_avg": 10.75,
+      "eval_loss": 0.11669360101222992,
+      "eval_mean_mismatch_i_diff_avg": 9.6875,
+      "eval_runtime": 1.4248,
+      "eval_samples_per_second": 2.807,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.702,
+      "eval_tokens_match_avg": 0.9590674999874726,
+      "step": 450
+    },
+    {
+      "epoch": 0.7583333333333333,
+      "grad_norm": 5.0,
+      "learning_rate": 1.4593968634891815e-06,
+      "loss": 0.1502,
+      "step": 455
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 5.96875,
+      "learning_rate": 1.371433113886903e-06,
+      "loss": 0.1481,
+      "step": 460
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 4.75,
+      "learning_rate": 1.285990470279852e-06,
+      "loss": 0.1467,
+      "step": 465
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 4.5,
+      "learning_rate": 1.2031274907879994e-06,
+      "loss": 0.1242,
+      "step": 470
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 3.75,
+      "learning_rate": 1.122900965558391e-06,
+      "loss": 0.14,
+      "step": 475
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.34375,
+      "learning_rate": 1.0453658778440162e-06,
+      "loss": 0.1634,
+      "step": 480
+    },
+    {
+      "epoch": 0.8083333333333333,
+      "grad_norm": 4.125,
+      "learning_rate": 9.705753663210283e-07,
+      "loss": 0.139,
+      "step": 485
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 5.15625,
+      "learning_rate": 8.98580688670156e-07,
+      "loss": 0.1546,
+      "step": 490
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 5.46875,
+      "learning_rate": 8.294311864472477e-07,
+      "loss": 0.1471,
+      "step": 495
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 5.09375,
+      "learning_rate": 7.631742512670332e-07,
+      "loss": 0.1442,
+      "step": 500
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_count_mismatch_i_diff_avg": 2.25,
+      "eval_first_index_mismatch_avg": 10.75,
+      "eval_loss": 0.11715836822986603,
+      "eval_mean_mismatch_i_diff_avg": 9.6875,
+      "eval_runtime": 1.4332,
+      "eval_samples_per_second": 2.791,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.698,
+      "eval_tokens_match_avg": 0.9552213461413188,
+      "step": 500
+    },
+    {
+      "epoch": 0.8416666666666667,
+      "grad_norm": 4.78125,
+      "learning_rate": 6.998552923232753e-07,
+      "loss": 0.1397,
+      "step": 505
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.75,
+      "learning_rate": 6.395177052675824e-07,
+      "loss": 0.1494,
+      "step": 510
+    },
+    {
+      "epoch": 0.8583333333333333,
+      "grad_norm": 4.375,
+      "learning_rate": 5.822028424681925e-07,
+      "loss": 0.1493,
+      "step": 515
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 5.125,
+      "learning_rate": 5.279499846691286e-07,
+      "loss": 0.132,
+      "step": 520
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.767963140691326e-07,
+      "loss": 0.1523,
+      "step": 525
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 4.375,
+      "learning_rate": 4.287768888388531e-07,
+      "loss": 0.1229,
+      "step": 530
+    },
+    {
+      "epoch": 0.8916666666666667,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.839246190937183e-07,
+      "loss": 0.1671,
+      "step": 535
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.25,
+      "learning_rate": 3.4227024433899137e-07,
+      "loss": 0.1304,
+      "step": 540
+    },
+    {
+      "epoch": 0.9083333333333333,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.0384231240244555e-07,
+      "loss": 0.1528,
+      "step": 545
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 4.125,
+      "learning_rate": 2.686671598691128e-07,
+      "loss": 0.1556,
+      "step": 550
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "eval_count_mismatch_i_diff_avg": 2.25,
+      "eval_first_index_mismatch_avg": 10.75,
+      "eval_loss": 0.11767315864562988,
+      "eval_mean_mismatch_i_diff_avg": 9.6875,
+      "eval_runtime": 1.4395,
+      "eval_samples_per_second": 2.779,
+      "eval_sql_exact_match_string": 0,
+      "eval_steps_per_second": 0.695,
+      "eval_tokens_match_avg": 0.9552213461413188,
+      "step": 550
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "total_flos": 5.255573265461084e+17,
+  "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:a5b830ad96e6ef339827c8f2f199064d80617e6d5143ed38868d24ee5802a509
+size 5112