Upload folder using huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "unsloth/llama-3-8b",
+  "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,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128255,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 8192,
+  "pad_token_id": 128255,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

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"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a4c28729905261024fbcaaf31f2121f2c87a417d0ca41bd32e99533da6b4d5
+size 1064

trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0024989691752152236,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.4989691752152238e-05,
+      "grad_norm": 9.5625,
+      "learning_rate": 1.9998e-05,
+      "loss": 6.0983,
+      "step": 10
+    },
+    {
+      "epoch": 4.9979383504304475e-05,
+      "grad_norm": 11.125,
+      "learning_rate": 1.9996000000000003e-05,
+      "loss": 5.5915,
+      "step": 20
+    },
+    {
+      "epoch": 7.496907525645671e-05,
+      "grad_norm": 11.0625,
+      "learning_rate": 1.9994000000000002e-05,
+      "loss": 5.6105,
+      "step": 30
+    },
+    {
+      "epoch": 9.995876700860895e-05,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.9992e-05,
+      "loss": 5.593,
+      "step": 40
+    },
+    {
+      "epoch": 0.00012494845876076117,
+      "grad_norm": 9.125,
+      "learning_rate": 1.9990000000000003e-05,
+      "loss": 5.6984,
+      "step": 50
+    },
+    {
+      "epoch": 0.00014993815051291343,
+      "grad_norm": 9.75,
+      "learning_rate": 1.9988000000000002e-05,
+      "loss": 5.6445,
+      "step": 60
+    },
+    {
+      "epoch": 0.00017492784226506565,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.9986e-05,
+      "loss": 5.6131,
+      "step": 70
+    },
+    {
+      "epoch": 0.0001999175340172179,
+      "grad_norm": 12.9375,
+      "learning_rate": 1.9984e-05,
+      "loss": 5.5871,
+      "step": 80
+    },
+    {
+      "epoch": 0.00022490722576937012,
+      "grad_norm": 7.375,
+      "learning_rate": 1.9982000000000003e-05,
+      "loss": 5.6247,
+      "step": 90
+    },
+    {
+      "epoch": 0.00024989691752152235,
+      "grad_norm": 6.6875,
+      "learning_rate": 1.9980000000000002e-05,
+      "loss": 5.6734,
+      "step": 100
+    },
+    {
+      "epoch": 0.0002748866092736746,
+      "grad_norm": 7.9375,
+      "learning_rate": 1.9978e-05,
+      "loss": 5.5597,
+      "step": 110
+    },
+    {
+      "epoch": 0.00029987630102582685,
+      "grad_norm": 9.125,
+      "learning_rate": 1.9976000000000003e-05,
+      "loss": 5.5558,
+      "step": 120
+    },
+    {
+      "epoch": 0.0003248659927779791,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.9974000000000002e-05,
+      "loss": 5.6126,
+      "step": 130
+    },
+    {
+      "epoch": 0.0003498556845301313,
+      "grad_norm": 12.8125,
+      "learning_rate": 1.9972e-05,
+      "loss": 5.4829,
+      "step": 140
+    },
+    {
+      "epoch": 0.00037484537628228355,
+      "grad_norm": 7.75,
+      "learning_rate": 1.9970000000000004e-05,
+      "loss": 5.5903,
+      "step": 150
+    },
+    {
+      "epoch": 0.0003998350680344358,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.9968e-05,
+      "loss": 5.6543,
+      "step": 160
+    },
+    {
+      "epoch": 0.00042482475978658805,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.9966e-05,
+      "loss": 5.6299,
+      "step": 170
+    },
+    {
+      "epoch": 0.00044981445153874025,
+      "grad_norm": 8.875,
+      "learning_rate": 1.9964e-05,
+      "loss": 5.6187,
+      "step": 180
+    },
+    {
+      "epoch": 0.0004748041432908925,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.9962000000000003e-05,
+      "loss": 5.5635,
+      "step": 190
+    },
+    {
+      "epoch": 0.0004997938350430447,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.9960000000000002e-05,
+      "loss": 5.4657,
+      "step": 200
+    },
+    {
+      "epoch": 0.000524783526795197,
+      "grad_norm": 8.3125,
+      "learning_rate": 1.9958e-05,
+      "loss": 5.5554,
+      "step": 210
+    },
+    {
+      "epoch": 0.0005497732185473492,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9956000000000003e-05,
+      "loss": 5.6229,
+      "step": 220
+    },
+    {
+      "epoch": 0.0005747629102995015,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.9954000000000002e-05,
+      "loss": 5.4991,
+      "step": 230
+    },
+    {
+      "epoch": 0.0005997526020516537,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.9952e-05,
+      "loss": 5.5635,
+      "step": 240
+    },
+    {
+      "epoch": 0.0006247422938038059,
+      "grad_norm": 7.125,
+      "learning_rate": 1.9950000000000004e-05,
+      "loss": 5.6043,
+      "step": 250
+    },
+    {
+      "epoch": 0.0006497319855559582,
+      "grad_norm": 11.0625,
+      "learning_rate": 1.9948e-05,
+      "loss": 5.6521,
+      "step": 260
+    },
+    {
+      "epoch": 0.0006747216773081104,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.9946000000000002e-05,
+      "loss": 5.5403,
+      "step": 270
+    },
+    {
+      "epoch": 0.0006997113690602626,
+      "grad_norm": 8.8125,
+      "learning_rate": 1.9944e-05,
+      "loss": 5.5962,
+      "step": 280
+    },
+    {
+      "epoch": 0.0007247010608124149,
+      "grad_norm": 8.25,
+      "learning_rate": 1.9942e-05,
+      "loss": 5.6138,
+      "step": 290
+    },
+    {
+      "epoch": 0.0007496907525645671,
+      "grad_norm": 7.625,
+      "learning_rate": 1.9940000000000002e-05,
+      "loss": 5.6668,
+      "step": 300
+    },
+    {
+      "epoch": 0.0007746804443167194,
+      "grad_norm": 9.75,
+      "learning_rate": 1.9938e-05,
+      "loss": 5.5858,
+      "step": 310
+    },
+    {
+      "epoch": 0.0007996701360688716,
+      "grad_norm": 8.875,
+      "learning_rate": 1.9936000000000004e-05,
+      "loss": 5.6348,
+      "step": 320
+    },
+    {
+      "epoch": 0.0008246598278210238,
+      "grad_norm": 8.5,
+      "learning_rate": 1.9934000000000003e-05,
+      "loss": 5.48,
+      "step": 330
+    },
+    {
+      "epoch": 0.0008496495195731761,
+      "grad_norm": 7.25,
+      "learning_rate": 1.9932e-05,
+      "loss": 5.5633,
+      "step": 340
+    },
+    {
+      "epoch": 0.0008746392113253283,
+      "grad_norm": 10.75,
+      "learning_rate": 1.9930000000000004e-05,
+      "loss": 5.5039,
+      "step": 350
+    },
+    {
+      "epoch": 0.0008996289030774805,
+      "grad_norm": 6.40625,
+      "learning_rate": 1.9928e-05,
+      "loss": 5.6185,
+      "step": 360
+    },
+    {
+      "epoch": 0.0009246185948296328,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.9926000000000002e-05,
+      "loss": 5.6497,
+      "step": 370
+    },
+    {
+      "epoch": 0.000949608286581785,
+      "grad_norm": 8.5,
+      "learning_rate": 1.9924e-05,
+      "loss": 5.6076,
+      "step": 380
+    },
+    {
+      "epoch": 0.0009745979783339372,
+      "grad_norm": 7.6875,
+      "learning_rate": 1.9922e-05,
+      "loss": 5.549,
+      "step": 390
+    },
+    {
+      "epoch": 0.0009995876700860894,
+      "grad_norm": 7.03125,
+      "learning_rate": 1.9920000000000002e-05,
+      "loss": 5.537,
+      "step": 400
+    },
+    {
+      "epoch": 0.0010245773618382417,
+      "grad_norm": 8.25,
+      "learning_rate": 1.9918e-05,
+      "loss": 5.5424,
+      "step": 410
+    },
+    {
+      "epoch": 0.001049567053590394,
+      "grad_norm": 9.3125,
+      "learning_rate": 1.9916e-05,
+      "loss": 5.6549,
+      "step": 420
+    },
+    {
+      "epoch": 0.001074556745342546,
+      "grad_norm": 6.15625,
+      "learning_rate": 1.9914000000000003e-05,
+      "loss": 5.4906,
+      "step": 430
+    },
+    {
+      "epoch": 0.0010995464370946984,
+      "grad_norm": 8.875,
+      "learning_rate": 1.9912000000000002e-05,
+      "loss": 5.6258,
+      "step": 440
+    },
+    {
+      "epoch": 0.0011245361288468507,
+      "grad_norm": 7.78125,
+      "learning_rate": 1.9910000000000004e-05,
+      "loss": 5.5201,
+      "step": 450
+    },
+    {
+      "epoch": 0.001149525820599003,
+      "grad_norm": 7.0,
+      "learning_rate": 1.9908e-05,
+      "loss": 5.6204,
+      "step": 460
+    },
+    {
+      "epoch": 0.001174515512351155,
+      "grad_norm": 9.125,
+      "learning_rate": 1.9906000000000002e-05,
+      "loss": 5.5345,
+      "step": 470
+    },
+    {
+      "epoch": 0.0011995052041033074,
+      "grad_norm": 6.25,
+      "learning_rate": 1.9904e-05,
+      "loss": 5.5461,
+      "step": 480
+    },
+    {
+      "epoch": 0.0012244948958554597,
+      "grad_norm": 6.84375,
+      "learning_rate": 1.9902e-05,
+      "loss": 5.6241,
+      "step": 490
+    },
+    {
+      "epoch": 0.0012494845876076118,
+      "grad_norm": 7.34375,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 5.5851,
+      "step": 500
+    },
+    {
+      "epoch": 0.001274474279359764,
+      "grad_norm": 6.25,
+      "learning_rate": 1.9898e-05,
+      "loss": 5.415,
+      "step": 510
+    },
+    {
+      "epoch": 0.0012994639711119164,
+      "grad_norm": 6.46875,
+      "learning_rate": 1.9896e-05,
+      "loss": 5.4773,
+      "step": 520
+    },
+    {
+      "epoch": 0.0013244536628640685,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.9894000000000003e-05,
+      "loss": 5.6274,
+      "step": 530
+    },
+    {
+      "epoch": 0.0013494433546162208,
+      "grad_norm": 6.875,
+      "learning_rate": 1.9892000000000002e-05,
+      "loss": 5.5787,
+      "step": 540
+    },
+    {
+      "epoch": 0.001374433046368373,
+      "grad_norm": 7.15625,
+      "learning_rate": 1.989e-05,
+      "loss": 5.5155,
+      "step": 550
+    },
+    {
+      "epoch": 0.0013994227381205252,
+      "grad_norm": 7.875,
+      "learning_rate": 1.9888e-05,
+      "loss": 5.6302,
+      "step": 560
+    },
+    {
+      "epoch": 0.0014244124298726775,
+      "grad_norm": 6.90625,
+      "learning_rate": 1.9886000000000002e-05,
+      "loss": 5.6188,
+      "step": 570
+    },
+    {
+      "epoch": 0.0014494021216248298,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.9884e-05,
+      "loss": 5.6807,
+      "step": 580
+    },
+    {
+      "epoch": 0.001474391813376982,
+      "grad_norm": 6.625,
+      "learning_rate": 1.9882e-05,
+      "loss": 5.5243,
+      "step": 590
+    },
+    {
+      "epoch": 0.0014993815051291342,
+      "grad_norm": 7.4375,
+      "learning_rate": 1.9880000000000003e-05,
+      "loss": 5.6199,
+      "step": 600
+    },
+    {
+      "epoch": 0.0015243711968812865,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.9878000000000002e-05,
+      "loss": 5.5931,
+      "step": 610
+    },
+    {
+      "epoch": 0.0015493608886334388,
+      "grad_norm": 7.75,
+      "learning_rate": 1.9876e-05,
+      "loss": 5.4432,
+      "step": 620
+    },
+    {
+      "epoch": 0.001574350580385591,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.9874000000000003e-05,
+      "loss": 5.5082,
+      "step": 630
+    },
+    {
+      "epoch": 0.0015993402721377432,
+      "grad_norm": 9.0625,
+      "learning_rate": 1.9872000000000002e-05,
+      "loss": 5.5388,
+      "step": 640
+    },
+    {
+      "epoch": 0.0016243299638898955,
+      "grad_norm": 6.40625,
+      "learning_rate": 1.987e-05,
+      "loss": 5.6473,
+      "step": 650
+    },
+    {
+      "epoch": 0.0016493196556420476,
+      "grad_norm": 7.375,
+      "learning_rate": 1.9868e-05,
+      "loss": 5.5754,
+      "step": 660
+    },
+    {
+      "epoch": 0.0016743093473942,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.9866e-05,
+      "loss": 5.6752,
+      "step": 670
+    },
+    {
+      "epoch": 0.0016992990391463522,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.9864e-05,
+      "loss": 5.6575,
+      "step": 680
+    },
+    {
+      "epoch": 0.0017242887308985043,
+      "grad_norm": 7.5,
+      "learning_rate": 1.9862e-05,
+      "loss": 5.4459,
+      "step": 690
+    },
+    {
+      "epoch": 0.0017492784226506566,
+      "grad_norm": 8.8125,
+      "learning_rate": 1.9860000000000003e-05,
+      "loss": 5.5611,
+      "step": 700
+    },
+    {
+      "epoch": 0.001774268114402809,
+      "grad_norm": 7.46875,
+      "learning_rate": 1.9858000000000002e-05,
+      "loss": 5.532,
+      "step": 710
+    },
+    {
+      "epoch": 0.001799257806154961,
+      "grad_norm": 7.90625,
+      "learning_rate": 1.9856e-05,
+      "loss": 5.5263,
+      "step": 720
+    },
+    {
+      "epoch": 0.0018242474979071133,
+      "grad_norm": 7.375,
+      "learning_rate": 1.9854000000000003e-05,
+      "loss": 5.6173,
+      "step": 730
+    },
+    {
+      "epoch": 0.0018492371896592656,
+      "grad_norm": 5.34375,
+      "learning_rate": 1.9852000000000002e-05,
+      "loss": 5.4807,
+      "step": 740
+    },
+    {
+      "epoch": 0.0018742268814114177,
+      "grad_norm": 6.5625,
+      "learning_rate": 1.985e-05,
+      "loss": 5.5658,
+      "step": 750
+    },
+    {
+      "epoch": 0.00189921657316357,
+      "grad_norm": 7.09375,
+      "learning_rate": 1.9848e-05,
+      "loss": 5.4922,
+      "step": 760
+    },
+    {
+      "epoch": 0.0019242062649157223,
+      "grad_norm": 6.875,
+      "learning_rate": 1.9846e-05,
+      "loss": 5.5456,
+      "step": 770
+    },
+    {
+      "epoch": 0.0019491959566678744,
+      "grad_norm": 6.5625,
+      "learning_rate": 1.9844000000000002e-05,
+      "loss": 5.5476,
+      "step": 780
+    },
+    {
+      "epoch": 0.0019741856484200267,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.9842e-05,
+      "loss": 5.5522,
+      "step": 790
+    },
+    {
+      "epoch": 0.001999175340172179,
+      "grad_norm": 7.375,
+      "learning_rate": 1.9840000000000003e-05,
+      "loss": 5.6347,
+      "step": 800
+    },
+    {
+      "epoch": 0.0020241650319243313,
+      "grad_norm": 8.5,
+      "learning_rate": 1.9838000000000002e-05,
+      "loss": 5.5714,
+      "step": 810
+    },
+    {
+      "epoch": 0.0020491547236764834,
+      "grad_norm": 7.125,
+      "learning_rate": 1.9836e-05,
+      "loss": 5.5227,
+      "step": 820
+    },
+    {
+      "epoch": 0.0020741444154286355,
+      "grad_norm": 8.125,
+      "learning_rate": 1.9834000000000004e-05,
+      "loss": 5.5476,
+      "step": 830
+    },
+    {
+      "epoch": 0.002099134107180788,
+      "grad_norm": 5.96875,
+      "learning_rate": 1.9832000000000003e-05,
+      "loss": 5.5645,
+      "step": 840
+    },
+    {
+      "epoch": 0.00212412379893294,
+      "grad_norm": 5.84375,
+      "learning_rate": 1.983e-05,
+      "loss": 5.5257,
+      "step": 850
+    },
+    {
+      "epoch": 0.002149113490685092,
+      "grad_norm": 7.5,
+      "learning_rate": 1.9828e-05,
+      "loss": 5.5988,
+      "step": 860
+    },
+    {
+      "epoch": 0.0021741031824372447,
+      "grad_norm": 7.625,
+      "learning_rate": 1.9826e-05,
+      "loss": 5.466,
+      "step": 870
+    },
+    {
+      "epoch": 0.002199092874189397,
+      "grad_norm": 6.0625,
+      "learning_rate": 1.9824000000000002e-05,
+      "loss": 5.5425,
+      "step": 880
+    },
+    {
+      "epoch": 0.0022240825659415493,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.9822e-05,
+      "loss": 5.5708,
+      "step": 890
+    },
+    {
+      "epoch": 0.0022490722576937014,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.982e-05,
+      "loss": 5.6318,
+      "step": 900
+    },
+    {
+      "epoch": 0.0022740619494458535,
+      "grad_norm": 7.25,
+      "learning_rate": 1.9818000000000002e-05,
+      "loss": 5.5574,
+      "step": 910
+    },
+    {
+      "epoch": 0.002299051641198006,
+      "grad_norm": 7.3125,
+      "learning_rate": 1.9816e-05,
+      "loss": 5.4384,
+      "step": 920
+    },
+    {
+      "epoch": 0.002324041332950158,
+      "grad_norm": 6.4375,
+      "learning_rate": 1.9814000000000004e-05,
+      "loss": 5.5454,
+      "step": 930
+    },
+    {
+      "epoch": 0.00234903102470231,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.9812000000000003e-05,
+      "loss": 5.6111,
+      "step": 940
+    },
+    {
+      "epoch": 0.0023740207164544627,
+      "grad_norm": 6.84375,
+      "learning_rate": 1.9810000000000002e-05,
+      "loss": 5.4391,
+      "step": 950
+    },
+    {
+      "epoch": 0.002399010408206615,
+      "grad_norm": 7.875,
+      "learning_rate": 1.9808e-05,
+      "loss": 5.5132,
+      "step": 960
+    },
+    {
+      "epoch": 0.002424000099958767,
+      "grad_norm": 6.53125,
+      "learning_rate": 1.9806e-05,
+      "loss": 5.5817,
+      "step": 970
+    },
+    {
+      "epoch": 0.0024489897917109194,
+      "grad_norm": 6.90625,
+      "learning_rate": 1.9804000000000002e-05,
+      "loss": 5.5528,
+      "step": 980
+    },
+    {
+      "epoch": 0.0024739794834630715,
+      "grad_norm": 5.6875,
+      "learning_rate": 1.9802e-05,
+      "loss": 5.6482,
+      "step": 990
+    },
+    {
+      "epoch": 0.0024989691752152236,
+      "grad_norm": 6.84375,
+      "learning_rate": 1.98e-05,
+      "loss": 5.6296,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 7.37764114956288e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e54eabf354f43ea877cb1eaea121898030e49516639ec84ed1b319abb594bc
+size 4984