Upload folder using huggingface_hub

checkpoint-1000/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 160,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32011
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "max_new_tokens": 1024,
+  "pad_token_id": 3,
+  "renormalize_logits": true,
+  "repetition_penalty": 1.2,
+  "temperature": 0.1,
+  "transformers_version": "4.57.3"
+}

checkpoint-1000/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff046422c81face82edba8b3759897821bc57bf45050b44703db778b30d8a7a9
+size 4954892968

checkpoint-1000/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2c20e2c0f0b978d47749206082b7dc1728dfb8231d91835b8ccb995521a5cc
+size 4823830448

checkpoint-1000/model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_parameters": 2444674560,
+    "total_size": 9778698240
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0149a9d17df5604c73b64de22296c4b74c6cd52ca8022740b256c00ea602ff
+size 5455855719

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6d8fafcd1ee268414be5acf0366296af5b03d60871978712eac1979cb42d65
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669b3f3f6d1eb2f1313f44a64b2e912f13d88d408410c1b03f7cd47188f855b4
+size 1465

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "</instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "</system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "</user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<assistant>"
+  ],
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "pad_token_id": 3,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e2e1cd324af6f3da873648f27a3f5158e140e99069c3ac742829ee4798ae63
+size 6033

checkpoint-1250/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 160,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32011
+}

checkpoint-1250/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "max_new_tokens": 1024,
+  "pad_token_id": 3,
+  "renormalize_logits": true,
+  "repetition_penalty": 1.2,
+  "temperature": 0.1,
+  "transformers_version": "4.57.3"
+}

checkpoint-1250/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abf676e18ecd9f1c27086332e138dde887394c02227ca7586c9a210971c0baf
+size 4954892968

checkpoint-1250/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d1839a3469bbc535c810366eafebf824e69f02eca351bda8ea0a3689994333
+size 4823830448

checkpoint-1250/model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_parameters": 2444674560,
+    "total_size": 9778698240
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b78b86e7e5cc60bc379aae05956aa494b63b05e13ccf4a8ef839ee76b26d64
+size 5455855719

checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89645f9f6a2a8823b334e0748e4f5ea683a27b3d02632f0a241397db55d82fad
+size 14645

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149613c522fb20c719da4556156e70073e5e848f79b5b3e8448635d9c634cbfc
+size 1465

checkpoint-1250/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1250/tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "</instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "</system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "</user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<assistant>"
+  ],
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "pad_token_id": 3,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e2e1cd324af6f3da873648f27a3f5158e140e99069c3ac742829ee4798ae63
+size 6033

checkpoint-500/config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 160,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32011
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "max_new_tokens": 1024,
+  "pad_token_id": 3,
+  "renormalize_logits": true,
+  "repetition_penalty": 1.2,
+  "temperature": 0.1,
+  "transformers_version": "4.57.3"
+}

checkpoint-500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdedf295254ea0efa743c174b3e4f72fe6b42b492ac684738d4d4315e09a358
+size 4954892968

checkpoint-500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90375b0a16a011eaa3372db8ee4bd9599801c029515ee6e5a821c3187a1dde05
+size 4823830448

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_parameters": 2444674560,
+    "total_size": 9778698240
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33ae691e47c35b0f542624e038a6832553baf829c47e8ca86a11db72fcb928c
+size 5455855719

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ca251c3c305c7a7ce79c2dc0f4e1a678a9c1a0377549141b524ac0056f418a
+size 1465

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "</instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "</system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "</user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<assistant>"
+  ],
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "pad_token_id": 3,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,3534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 53.62602615356445,
+      "learning_rate": 0.0,
+      "loss": 2.6634,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 56.597415924072266,
+      "learning_rate": 4e-05,
+      "loss": 2.8566,
+      "step": 2
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 18.571365356445312,
+      "learning_rate": 8e-05,
+      "loss": 2.2954,
+      "step": 3
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 14.36034870147705,
+      "learning_rate": 0.00012,
+      "loss": 1.7081,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 11.160177230834961,
+      "learning_rate": 0.00016,
+      "loss": 2.5655,
+      "step": 5
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 8.574136734008789,
+      "learning_rate": 0.0002,
+      "loss": 2.1856,
+      "step": 6
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 49.43375015258789,
+      "learning_rate": 0.00019983935742971887,
+      "loss": 5.0621,
+      "step": 7
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 6.4875264167785645,
+      "learning_rate": 0.00019967871485943777,
+      "loss": 2.483,
+      "step": 8
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 7.637119293212891,
+      "learning_rate": 0.00019951807228915663,
+      "loss": 1.7483,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 85.20454406738281,
+      "learning_rate": 0.00019935742971887552,
+      "loss": 2.4572,
+      "step": 10
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 7.181873321533203,
+      "learning_rate": 0.0001991967871485944,
+      "loss": 2.5813,
+      "step": 11
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 12.063413619995117,
+      "learning_rate": 0.00019903614457831325,
+      "loss": 2.7932,
+      "step": 12
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 5.665294647216797,
+      "learning_rate": 0.00019887550200803214,
+      "loss": 2.2602,
+      "step": 13
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 6.583767890930176,
+      "learning_rate": 0.000198714859437751,
+      "loss": 1.9798,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.831912994384766,
+      "learning_rate": 0.0001985542168674699,
+      "loss": 2.0948,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 3.0658581256866455,
+      "learning_rate": 0.00019839357429718877,
+      "loss": 1.8011,
+      "step": 16
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 5.012989521026611,
+      "learning_rate": 0.00019823293172690763,
+      "loss": 1.7872,
+      "step": 17
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 8.948102951049805,
+      "learning_rate": 0.00019807228915662652,
+      "loss": 1.5447,
+      "step": 18
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 3.127945899963379,
+      "learning_rate": 0.0001979116465863454,
+      "loss": 1.7418,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.089815378189087,
+      "learning_rate": 0.00019775100401606425,
+      "loss": 1.6188,
+      "step": 20
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 2.5238707065582275,
+      "learning_rate": 0.00019759036144578314,
+      "loss": 1.7317,
+      "step": 21
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.0600812435150146,
+      "learning_rate": 0.000197429718875502,
+      "loss": 1.5302,
+      "step": 22
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 1.7607418298721313,
+      "learning_rate": 0.0001972690763052209,
+      "loss": 1.5289,
+      "step": 23
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.142132520675659,
+      "learning_rate": 0.00019710843373493977,
+      "loss": 1.5467,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.0176613330841064,
+      "learning_rate": 0.00019694779116465866,
+      "loss": 1.4259,
+      "step": 25
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 3.156802177429199,
+      "learning_rate": 0.00019678714859437752,
+      "loss": 1.4209,
+      "step": 26
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 2.4216420650482178,
+      "learning_rate": 0.00019662650602409642,
+      "loss": 1.2682,
+      "step": 27
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.4433507919311523,
+      "learning_rate": 0.00019646586345381528,
+      "loss": 1.213,
+      "step": 28
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 1.8319810628890991,
+      "learning_rate": 0.00019630522088353415,
+      "loss": 1.4232,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.235199213027954,
+      "learning_rate": 0.000196144578313253,
+      "loss": 1.6956,
+      "step": 30
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 1.8305765390396118,
+      "learning_rate": 0.0001959839357429719,
+      "loss": 1.74,
+      "step": 31
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 2.391343355178833,
+      "learning_rate": 0.00019582329317269077,
+      "loss": 1.8977,
+      "step": 32
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 1.895875096321106,
+      "learning_rate": 0.00019566265060240966,
+      "loss": 1.6746,
+      "step": 33
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.8806582689285278,
+      "learning_rate": 0.00019550200803212852,
+      "loss": 1.4103,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.172238349914551,
+      "learning_rate": 0.00019534136546184742,
+      "loss": 1.5264,
+      "step": 35
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.6594462394714355,
+      "learning_rate": 0.00019518072289156628,
+      "loss": 1.765,
+      "step": 36
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 1.4864526987075806,
+      "learning_rate": 0.00019502008032128517,
+      "loss": 1.2829,
+      "step": 37
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1.9694857597351074,
+      "learning_rate": 0.000194859437751004,
+      "loss": 1.2313,
+      "step": 38
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 1.7664475440979004,
+      "learning_rate": 0.0001946987951807229,
+      "loss": 1.3123,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.8405388593673706,
+      "learning_rate": 0.00019453815261044177,
+      "loss": 1.3633,
+      "step": 40
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 1.8729100227355957,
+      "learning_rate": 0.00019437751004016066,
+      "loss": 1.1224,
+      "step": 41
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 2.137784719467163,
+      "learning_rate": 0.00019421686746987952,
+      "loss": 1.3406,
+      "step": 42
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 2.243258476257324,
+      "learning_rate": 0.00019405622489959842,
+      "loss": 1.4217,
+      "step": 43
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.537698745727539,
+      "learning_rate": 0.00019389558232931728,
+      "loss": 1.5952,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.616498589515686,
+      "learning_rate": 0.00019373493975903617,
+      "loss": 1.3245,
+      "step": 45
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 2.2073936462402344,
+      "learning_rate": 0.00019357429718875504,
+      "loss": 1.5001,
+      "step": 46
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 1.604514241218567,
+      "learning_rate": 0.0001934136546184739,
+      "loss": 1.3424,
+      "step": 47
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.5252907276153564,
+      "learning_rate": 0.00019325301204819277,
+      "loss": 1.4048,
+      "step": 48
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 2.1352715492248535,
+      "learning_rate": 0.00019309236947791166,
+      "loss": 1.3334,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.3604182004928589,
+      "learning_rate": 0.00019293172690763052,
+      "loss": 1.2671,
+      "step": 50
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 1.331368088722229,
+      "learning_rate": 0.00019277108433734942,
+      "loss": 1.4675,
+      "step": 51
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 1.2005531787872314,
+      "learning_rate": 0.00019261044176706828,
+      "loss": 1.1761,
+      "step": 52
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 1.3100972175598145,
+      "learning_rate": 0.00019244979919678717,
+      "loss": 1.2128,
+      "step": 53
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 1.3570109605789185,
+      "learning_rate": 0.00019228915662650604,
+      "loss": 1.3544,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.415779709815979,
+      "learning_rate": 0.00019212851405622493,
+      "loss": 1.3442,
+      "step": 55
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 1.674559473991394,
+      "learning_rate": 0.00019196787148594377,
+      "loss": 1.2802,
+      "step": 56
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 1.595314860343933,
+      "learning_rate": 0.00019180722891566266,
+      "loss": 1.3848,
+      "step": 57
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 1.4688509702682495,
+      "learning_rate": 0.00019164658634538152,
+      "loss": 1.3805,
+      "step": 58
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 1.6602617502212524,
+      "learning_rate": 0.00019148594377510042,
+      "loss": 1.4224,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.401511549949646,
+      "learning_rate": 0.00019132530120481928,
+      "loss": 1.224,
+      "step": 60
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 1.4535855054855347,
+      "learning_rate": 0.00019116465863453817,
+      "loss": 1.4971,
+      "step": 61
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 1.3600229024887085,
+      "learning_rate": 0.00019100401606425704,
+      "loss": 1.5681,
+      "step": 62
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 1.9019396305084229,
+      "learning_rate": 0.00019084337349397593,
+      "loss": 1.2084,
+      "step": 63
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.5218498706817627,
+      "learning_rate": 0.0001906827309236948,
+      "loss": 1.3234,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.520909070968628,
+      "learning_rate": 0.00019052208835341369,
+      "loss": 1.4138,
+      "step": 65
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 1.470320463180542,
+      "learning_rate": 0.00019036144578313252,
+      "loss": 1.4415,
+      "step": 66
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 1.2709641456604004,
+      "learning_rate": 0.00019020080321285142,
+      "loss": 1.1838,
+      "step": 67
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 1.2124229669570923,
+      "learning_rate": 0.00019004016064257028,
+      "loss": 1.1472,
+      "step": 68
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 1.2890123128890991,
+      "learning_rate": 0.00018987951807228917,
+      "loss": 1.2021,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.2100738286972046,
+      "learning_rate": 0.00018971887550200804,
+      "loss": 1.3469,
+      "step": 70
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 1.3904210329055786,
+      "learning_rate": 0.00018955823293172693,
+      "loss": 1.424,
+      "step": 71
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 1.6965813636779785,
+      "learning_rate": 0.0001893975903614458,
+      "loss": 1.4242,
+      "step": 72
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 1.2555180788040161,
+      "learning_rate": 0.00018923694779116469,
+      "loss": 1.2068,
+      "step": 73
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 3.076178789138794,
+      "learning_rate": 0.00018907630522088355,
+      "loss": 1.5091,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.2407095432281494,
+      "learning_rate": 0.00018891566265060242,
+      "loss": 1.3181,
+      "step": 75
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 1.0690617561340332,
+      "learning_rate": 0.00018875502008032128,
+      "loss": 1.2277,
+      "step": 76
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 1.5141525268554688,
+      "learning_rate": 0.00018859437751004017,
+      "loss": 1.4033,
+      "step": 77
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 1.625349521636963,
+      "learning_rate": 0.00018843373493975904,
+      "loss": 1.4013,
+      "step": 78
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 2.1738834381103516,
+      "learning_rate": 0.00018827309236947793,
+      "loss": 1.3481,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.544585704803467,
+      "learning_rate": 0.0001881124497991968,
+      "loss": 1.7825,
+      "step": 80
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 1.7910398244857788,
+      "learning_rate": 0.00018795180722891569,
+      "loss": 1.6193,
+      "step": 81
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 2.022350311279297,
+      "learning_rate": 0.00018779116465863455,
+      "loss": 1.5582,
+      "step": 82
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 2.3843116760253906,
+      "learning_rate": 0.00018763052208835344,
+      "loss": 1.2264,
+      "step": 83
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 1.6636406183242798,
+      "learning_rate": 0.00018746987951807228,
+      "loss": 1.544,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.3896743059158325,
+      "learning_rate": 0.00018730923694779117,
+      "loss": 1.1049,
+      "step": 85
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 1.1019163131713867,
+      "learning_rate": 0.00018714859437751004,
+      "loss": 1.153,
+      "step": 86
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 1.2334790229797363,
+      "learning_rate": 0.00018698795180722893,
+      "loss": 1.1182,
+      "step": 87
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 1.9984495639801025,
+      "learning_rate": 0.0001868273092369478,
+      "loss": 1.1323,
+      "step": 88
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 1.2791403532028198,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.1596,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.3124949932098389,
+      "learning_rate": 0.00018650602409638555,
+      "loss": 1.7198,
+      "step": 90
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 1.7484452724456787,
+      "learning_rate": 0.00018634538152610444,
+      "loss": 1.4512,
+      "step": 91
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 1.2766470909118652,
+      "learning_rate": 0.0001861847389558233,
+      "loss": 1.1965,
+      "step": 92
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 3.73681640625,
+      "learning_rate": 0.00018602409638554217,
+      "loss": 1.343,
+      "step": 93
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 1.3174450397491455,
+      "learning_rate": 0.00018586345381526104,
+      "loss": 1.4324,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.3149890899658203,
+      "learning_rate": 0.00018570281124497993,
+      "loss": 1.2592,
+      "step": 95
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 1.2797366380691528,
+      "learning_rate": 0.0001855421686746988,
+      "loss": 1.1681,
+      "step": 96
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 1.327673077583313,
+      "learning_rate": 0.0001853815261044177,
+      "loss": 1.3348,
+      "step": 97
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 1.2754827737808228,
+      "learning_rate": 0.00018522088353413655,
+      "loss": 1.439,
+      "step": 98
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 1.3751404285430908,
+      "learning_rate": 0.00018506024096385544,
+      "loss": 1.4628,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.2144503593444824,
+      "learning_rate": 0.0001848995983935743,
+      "loss": 1.3091,
+      "step": 100
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 1.4492264986038208,
+      "learning_rate": 0.0001847389558232932,
+      "loss": 1.5574,
+      "step": 101
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 1.3323545455932617,
+      "learning_rate": 0.00018457831325301204,
+      "loss": 1.5781,
+      "step": 102
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 1.0985736846923828,
+      "learning_rate": 0.00018441767068273093,
+      "loss": 1.2636,
+      "step": 103
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 1.2735247611999512,
+      "learning_rate": 0.0001842570281124498,
+      "loss": 1.1101,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.0848711729049683,
+      "learning_rate": 0.0001840963855421687,
+      "loss": 1.0969,
+      "step": 105
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 1.517270565032959,
+      "learning_rate": 0.00018393574297188755,
+      "loss": 1.1304,
+      "step": 106
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 1.597000241279602,
+      "learning_rate": 0.00018377510040160644,
+      "loss": 1.204,
+      "step": 107
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 1.940949559211731,
+      "learning_rate": 0.0001836144578313253,
+      "loss": 1.3689,
+      "step": 108
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 2.093283176422119,
+      "learning_rate": 0.0001834538152610442,
+      "loss": 1.2159,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.9808330535888672,
+      "learning_rate": 0.00018329317269076307,
+      "loss": 1.0677,
+      "step": 110
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 2.8766942024230957,
+      "learning_rate": 0.00018313253012048193,
+      "loss": 1.3891,
+      "step": 111
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 2.7085304260253906,
+      "learning_rate": 0.0001829718875502008,
+      "loss": 1.4037,
+      "step": 112
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 1.8437902927398682,
+      "learning_rate": 0.0001828112449799197,
+      "loss": 1.1203,
+      "step": 113
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 1.6266216039657593,
+      "learning_rate": 0.00018265060240963855,
+      "loss": 1.0703,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.7318757772445679,
+      "learning_rate": 0.00018248995983935744,
+      "loss": 1.1141,
+      "step": 115
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 1.5244029760360718,
+      "learning_rate": 0.0001823293172690763,
+      "loss": 1.3516,
+      "step": 116
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 1.3941713571548462,
+      "learning_rate": 0.0001821686746987952,
+      "loss": 1.1322,
+      "step": 117
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 1.3192192316055298,
+      "learning_rate": 0.00018200803212851407,
+      "loss": 1.5634,
+      "step": 118
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 2.4823129177093506,
+      "learning_rate": 0.00018184738955823296,
+      "loss": 1.0845,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.8886570930480957,
+      "learning_rate": 0.0001816867469879518,
+      "loss": 1.3589,
+      "step": 120
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 1.498052954673767,
+      "learning_rate": 0.0001815261044176707,
+      "loss": 1.0942,
+      "step": 121
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 2.839603900909424,
+      "learning_rate": 0.00018136546184738955,
+      "loss": 1.6815,
+      "step": 122
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 1.6304397583007812,
+      "learning_rate": 0.00018120481927710844,
+      "loss": 1.2761,
+      "step": 123
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 1.3449641466140747,
+      "learning_rate": 0.0001810441767068273,
+      "loss": 1.1928,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.4226500988006592,
+      "learning_rate": 0.0001808835341365462,
+      "loss": 1.1144,
+      "step": 125
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.9882439970970154,
+      "learning_rate": 0.00018072289156626507,
+      "loss": 1.1953,
+      "step": 126
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 1.08316969871521,
+      "learning_rate": 0.00018056224899598396,
+      "loss": 1.3752,
+      "step": 127
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 1.519068717956543,
+      "learning_rate": 0.00018040160642570282,
+      "loss": 1.0254,
+      "step": 128
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 1.1192545890808105,
+      "learning_rate": 0.0001802409638554217,
+      "loss": 1.168,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.1827452182769775,
+      "learning_rate": 0.00018008032128514055,
+      "loss": 1.0406,
+      "step": 130
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 1.2685647010803223,
+      "learning_rate": 0.00017991967871485944,
+      "loss": 1.3304,
+      "step": 131
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 1.6803406476974487,
+      "learning_rate": 0.0001797590361445783,
+      "loss": 1.2852,
+      "step": 132
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 1.3566769361495972,
+      "learning_rate": 0.0001795983935742972,
+      "loss": 1.4319,
+      "step": 133
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 1.1238553524017334,
+      "learning_rate": 0.00017943775100401607,
+      "loss": 1.2313,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.106919765472412,
+      "learning_rate": 0.00017927710843373496,
+      "loss": 1.619,
+      "step": 135
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.9259321689605713,
+      "learning_rate": 0.00017911646586345382,
+      "loss": 0.963,
+      "step": 136
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 1.3067266941070557,
+      "learning_rate": 0.00017895582329317271,
+      "loss": 1.251,
+      "step": 137
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 1.0804563760757446,
+      "learning_rate": 0.00017879518072289155,
+      "loss": 1.1884,
+      "step": 138
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.971161961555481,
+      "learning_rate": 0.00017863453815261044,
+      "loss": 1.0359,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.9346293807029724,
+      "learning_rate": 0.0001784738955823293,
+      "loss": 1.0063,
+      "step": 140
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 1.213650107383728,
+      "learning_rate": 0.0001783132530120482,
+      "loss": 1.2189,
+      "step": 141
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 1.2014150619506836,
+      "learning_rate": 0.00017815261044176707,
+      "loss": 1.4506,
+      "step": 142
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 1.1013990640640259,
+      "learning_rate": 0.00017799196787148596,
+      "loss": 0.9083,
+      "step": 143
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 1.0296562910079956,
+      "learning_rate": 0.00017783132530120482,
+      "loss": 1.3195,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.830122947692871,
+      "learning_rate": 0.00017767068273092371,
+      "loss": 0.9511,
+      "step": 145
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 1.3256480693817139,
+      "learning_rate": 0.00017751004016064258,
+      "loss": 1.0048,
+      "step": 146
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 1.270775556564331,
+      "learning_rate": 0.00017734939759036144,
+      "loss": 1.4066,
+      "step": 147
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 1.2674766778945923,
+      "learning_rate": 0.0001771887550200803,
+      "loss": 1.2001,
+      "step": 148
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 1.1187313795089722,
+      "learning_rate": 0.0001770281124497992,
+      "loss": 1.2907,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.8587852120399475,
+      "learning_rate": 0.00017686746987951807,
+      "loss": 0.9537,
+      "step": 150
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 1.307936429977417,
+      "learning_rate": 0.00017670682730923696,
+      "loss": 1.9246,
+      "step": 151
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 1.3011741638183594,
+      "learning_rate": 0.00017654618473895582,
+      "loss": 1.2492,
+      "step": 152
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 1.712490439414978,
+      "learning_rate": 0.00017638554216867471,
+      "loss": 1.6788,
+      "step": 153
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 1.2269988059997559,
+      "learning_rate": 0.00017622489959839358,
+      "loss": 1.1549,
+      "step": 154
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.006116271018982,
+      "learning_rate": 0.00017606425702811247,
+      "loss": 1.29,
+      "step": 155
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 1.0913758277893066,
+      "learning_rate": 0.00017590361445783134,
+      "loss": 1.2436,
+      "step": 156
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 1.3754626512527466,
+      "learning_rate": 0.0001757429718875502,
+      "loss": 1.0517,
+      "step": 157
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.9338424801826477,
+      "learning_rate": 0.00017558232931726907,
+      "loss": 0.9792,
+      "step": 158
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 1.1045053005218506,
+      "learning_rate": 0.00017542168674698796,
+      "loss": 1.1625,
+      "step": 159
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2580407857894897,
+      "learning_rate": 0.00017526104417670682,
+      "loss": 1.2485,
+      "step": 160
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 0.9033818244934082,
+      "learning_rate": 0.00017510040160642571,
+      "loss": 1.043,
+      "step": 161
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 1.4151123762130737,
+      "learning_rate": 0.00017493975903614458,
+      "loss": 1.4235,
+      "step": 162
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 0.9332399964332581,
+      "learning_rate": 0.00017477911646586347,
+      "loss": 0.8602,
+      "step": 163
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 1.2299081087112427,
+      "learning_rate": 0.00017461847389558234,
+      "loss": 1.3964,
+      "step": 164
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.1637903451919556,
+      "learning_rate": 0.00017445783132530123,
+      "loss": 1.1491,
+      "step": 165
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 1.0534940958023071,
+      "learning_rate": 0.0001742971887550201,
+      "loss": 1.0291,
+      "step": 166
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 1.1674387454986572,
+      "learning_rate": 0.00017413654618473896,
+      "loss": 1.4838,
+      "step": 167
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.9993395805358887,
+      "learning_rate": 0.00017397590361445782,
+      "loss": 1.1238,
+      "step": 168
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 0.9013456702232361,
+      "learning_rate": 0.00017381526104417671,
+      "loss": 1.0283,
+      "step": 169
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8159250020980835,
+      "learning_rate": 0.00017365461847389558,
+      "loss": 0.8425,
+      "step": 170
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 1.7490507364273071,
+      "learning_rate": 0.00017349397590361447,
+      "loss": 1.3741,
+      "step": 171
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.8009415864944458,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.8598,
+      "step": 172
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 1.0610826015472412,
+      "learning_rate": 0.00017317269076305223,
+      "loss": 1.3108,
+      "step": 173
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.9217771291732788,
+      "learning_rate": 0.0001730120481927711,
+      "loss": 1.1902,
+      "step": 174
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.1737595796585083,
+      "learning_rate": 0.00017285140562248996,
+      "loss": 1.15,
+      "step": 175
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.9864694476127625,
+      "learning_rate": 0.00017269076305220885,
+      "loss": 1.1637,
+      "step": 176
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 1.4145147800445557,
+      "learning_rate": 0.00017253012048192771,
+      "loss": 1.274,
+      "step": 177
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.9762219786643982,
+      "learning_rate": 0.00017236947791164658,
+      "loss": 0.9479,
+      "step": 178
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 1.3985542058944702,
+      "learning_rate": 0.00017220883534136547,
+      "loss": 1.2225,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1241815090179443,
+      "learning_rate": 0.00017204819277108434,
+      "loss": 1.2974,
+      "step": 180
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 0.7787443995475769,
+      "learning_rate": 0.00017188755020080323,
+      "loss": 0.8893,
+      "step": 181
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.9060066342353821,
+      "learning_rate": 0.0001717269076305221,
+      "loss": 1.2636,
+      "step": 182
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 0.8992155194282532,
+      "learning_rate": 0.00017156626506024099,
+      "loss": 0.9306,
+      "step": 183
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.9462528824806213,
+      "learning_rate": 0.00017140562248995985,
+      "loss": 0.9943,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1034131050109863,
+      "learning_rate": 0.00017124497991967871,
+      "loss": 0.928,
+      "step": 185
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.9784576296806335,
+      "learning_rate": 0.0001710843373493976,
+      "loss": 1.122,
+      "step": 186
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 2.408193349838257,
+      "learning_rate": 0.00017092369477911647,
+      "loss": 1.3427,
+      "step": 187
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 1.3843070268630981,
+      "learning_rate": 0.00017076305220883536,
+      "loss": 1.2355,
+      "step": 188
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 1.0028448104858398,
+      "learning_rate": 0.00017060240963855423,
+      "loss": 1.1471,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.4489953517913818,
+      "learning_rate": 0.0001704417670682731,
+      "loss": 1.502,
+      "step": 190
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 1.1279592514038086,
+      "learning_rate": 0.00017028112449799199,
+      "loss": 1.0933,
+      "step": 191
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 1.1093401908874512,
+      "learning_rate": 0.00017012048192771085,
+      "loss": 1.1714,
+      "step": 192
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 1.755867600440979,
+      "learning_rate": 0.00016995983935742971,
+      "loss": 1.4923,
+      "step": 193
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 1.3312938213348389,
+      "learning_rate": 0.0001697991967871486,
+      "loss": 1.0584,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1019108295440674,
+      "learning_rate": 0.00016963855421686747,
+      "loss": 1.2232,
+      "step": 195
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 1.1801754236221313,
+      "learning_rate": 0.00016947791164658636,
+      "loss": 0.86,
+      "step": 196
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 2.1799583435058594,
+      "learning_rate": 0.00016931726907630523,
+      "loss": 0.8954,
+      "step": 197
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 1.1106112003326416,
+      "learning_rate": 0.00016915662650602412,
+      "loss": 0.9685,
+      "step": 198
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 1.48722505569458,
+      "learning_rate": 0.00016899598393574299,
+      "loss": 1.2157,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.360235333442688,
+      "learning_rate": 0.00016883534136546185,
+      "loss": 1.1383,
+      "step": 200
+    },
+    {
+      "epoch": 0.804,
+      "grad_norm": 1.1038031578063965,
+      "learning_rate": 0.00016867469879518074,
+      "loss": 1.0757,
+      "step": 201
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.9019837379455566,
+      "learning_rate": 0.0001685140562248996,
+      "loss": 1.0136,
+      "step": 202
+    },
+    {
+      "epoch": 0.812,
+      "grad_norm": 0.9879880547523499,
+      "learning_rate": 0.00016835341365461847,
+      "loss": 1.0105,
+      "step": 203
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.905677080154419,
+      "learning_rate": 0.00016819277108433736,
+      "loss": 0.8366,
+      "step": 204
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1222323179244995,
+      "learning_rate": 0.00016803212851405623,
+      "loss": 1.3458,
+      "step": 205
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 1.1519650220870972,
+      "learning_rate": 0.00016787148594377512,
+      "loss": 1.0641,
+      "step": 206
+    },
+    {
+      "epoch": 0.828,
+      "grad_norm": 1.0652623176574707,
+      "learning_rate": 0.00016771084337349399,
+      "loss": 1.062,
+      "step": 207
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 1.2038804292678833,
+      "learning_rate": 0.00016755020080321288,
+      "loss": 0.9731,
+      "step": 208
+    },
+    {
+      "epoch": 0.836,
+      "grad_norm": 1.1437853574752808,
+      "learning_rate": 0.00016738955823293174,
+      "loss": 1.4292,
+      "step": 209
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9734582901000977,
+      "learning_rate": 0.0001672289156626506,
+      "loss": 1.1455,
+      "step": 210
+    },
+    {
+      "epoch": 0.844,
+      "grad_norm": 0.9625353813171387,
+      "learning_rate": 0.00016706827309236947,
+      "loss": 0.8748,
+      "step": 211
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 1.0549144744873047,
+      "learning_rate": 0.00016690763052208836,
+      "loss": 1.416,
+      "step": 212
+    },
+    {
+      "epoch": 0.852,
+      "grad_norm": 1.0628703832626343,
+      "learning_rate": 0.00016674698795180723,
+      "loss": 0.9798,
+      "step": 213
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 1.1408172845840454,
+      "learning_rate": 0.00016658634538152612,
+      "loss": 1.0589,
+      "step": 214
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.12384831905365,
+      "learning_rate": 0.00016642570281124499,
+      "loss": 1.112,
+      "step": 215
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 1.1331861019134521,
+      "learning_rate": 0.00016626506024096388,
+      "loss": 1.1844,
+      "step": 216
+    },
+    {
+      "epoch": 0.868,
+      "grad_norm": 1.4460475444793701,
+      "learning_rate": 0.00016610441767068274,
+      "loss": 1.4064,
+      "step": 217
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 1.2119053602218628,
+      "learning_rate": 0.00016594377510040163,
+      "loss": 1.1563,
+      "step": 218
+    },
+    {
+      "epoch": 0.876,
+      "grad_norm": 1.214340329170227,
+      "learning_rate": 0.0001657831325301205,
+      "loss": 1.2214,
+      "step": 219
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.2477388381958008,
+      "learning_rate": 0.00016562248995983936,
+      "loss": 1.18,
+      "step": 220
+    },
+    {
+      "epoch": 0.884,
+      "grad_norm": 1.0218065977096558,
+      "learning_rate": 0.00016546184738955823,
+      "loss": 0.9725,
+      "step": 221
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 1.042024850845337,
+      "learning_rate": 0.00016530120481927712,
+      "loss": 1.0288,
+      "step": 222
+    },
+    {
+      "epoch": 0.892,
+      "grad_norm": 0.8950498700141907,
+      "learning_rate": 0.00016514056224899599,
+      "loss": 0.9153,
+      "step": 223
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 1.2319512367248535,
+      "learning_rate": 0.00016497991967871488,
+      "loss": 1.19,
+      "step": 224
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0612848997116089,
+      "learning_rate": 0.00016481927710843374,
+      "loss": 1.3144,
+      "step": 225
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 1.051899790763855,
+      "learning_rate": 0.00016465863453815263,
+      "loss": 1.1371,
+      "step": 226
+    },
+    {
+      "epoch": 0.908,
+      "grad_norm": 0.9681085348129272,
+      "learning_rate": 0.0001644979919678715,
+      "loss": 0.9856,
+      "step": 227
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.9124426245689392,
+      "learning_rate": 0.0001643373493975904,
+      "loss": 1.0323,
+      "step": 228
+    },
+    {
+      "epoch": 0.916,
+      "grad_norm": 1.3986107110977173,
+      "learning_rate": 0.00016417670682730923,
+      "loss": 1.164,
+      "step": 229
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.0733290910720825,
+      "learning_rate": 0.00016401606425702812,
+      "loss": 0.9883,
+      "step": 230
+    },
+    {
+      "epoch": 0.924,
+      "grad_norm": 0.9436154961585999,
+      "learning_rate": 0.00016385542168674699,
+      "loss": 1.1265,
+      "step": 231
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.9259563684463501,
+      "learning_rate": 0.00016369477911646588,
+      "loss": 1.1864,
+      "step": 232
+    },
+    {
+      "epoch": 0.932,
+      "grad_norm": 1.9417387247085571,
+      "learning_rate": 0.00016353413654618474,
+      "loss": 1.1545,
+      "step": 233
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 1.162505030632019,
+      "learning_rate": 0.00016337349397590363,
+      "loss": 1.3507,
+      "step": 234
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 2.540339946746826,
+      "learning_rate": 0.0001632128514056225,
+      "loss": 1.0578,
+      "step": 235
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.9945997595787048,
+      "learning_rate": 0.0001630522088353414,
+      "loss": 1.2593,
+      "step": 236
+    },
+    {
+      "epoch": 0.948,
+      "grad_norm": 1.125874400138855,
+      "learning_rate": 0.00016289156626506026,
+      "loss": 0.793,
+      "step": 237
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 1.0723917484283447,
+      "learning_rate": 0.00016273092369477912,
+      "loss": 1.0918,
+      "step": 238
+    },
+    {
+      "epoch": 0.956,
+      "grad_norm": 1.113118290901184,
+      "learning_rate": 0.00016257028112449799,
+      "loss": 1.3632,
+      "step": 239
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.718297004699707,
+      "learning_rate": 0.00016240963855421688,
+      "loss": 1.9874,
+      "step": 240
+    },
+    {
+      "epoch": 0.964,
+      "grad_norm": 1.1292189359664917,
+      "learning_rate": 0.00016224899598393574,
+      "loss": 1.0951,
+      "step": 241
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 1.1281769275665283,
+      "learning_rate": 0.00016208835341365463,
+      "loss": 1.0857,
+      "step": 242
+    },
+    {
+      "epoch": 0.972,
+      "grad_norm": 1.5995818376541138,
+      "learning_rate": 0.0001619277108433735,
+      "loss": 1.1922,
+      "step": 243
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 1.4334827661514282,
+      "learning_rate": 0.0001617670682730924,
+      "loss": 1.4897,
+      "step": 244
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.8789055943489075,
+      "learning_rate": 0.00016160642570281126,
+      "loss": 1.203,
+      "step": 245
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.7583382725715637,
+      "learning_rate": 0.00016144578313253015,
+      "loss": 0.8718,
+      "step": 246
+    },
+    {
+      "epoch": 0.988,
+      "grad_norm": 3.5140089988708496,
+      "learning_rate": 0.00016128514056224899,
+      "loss": 1.3685,
+      "step": 247
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 2.6061456203460693,
+      "learning_rate": 0.00016112449799196788,
+      "loss": 1.1047,
+      "step": 248
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 1.0015108585357666,
+      "learning_rate": 0.00016096385542168674,
+      "loss": 1.1716,
+      "step": 249
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9369361996650696,
+      "learning_rate": 0.00016080321285140563,
+      "loss": 1.4799,
+      "step": 250
+    },
+    {
+      "epoch": 1.004,
+      "grad_norm": 1.3471037149429321,
+      "learning_rate": 0.0001606425702811245,
+      "loss": 1.2607,
+      "step": 251
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 2.2761526107788086,
+      "learning_rate": 0.0001604819277108434,
+      "loss": 1.2795,
+      "step": 252
+    },
+    {
+      "epoch": 1.012,
+      "grad_norm": 0.945418119430542,
+      "learning_rate": 0.00016032128514056226,
+      "loss": 0.9472,
+      "step": 253
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.8474368453025818,
+      "learning_rate": 0.00016016064257028115,
+      "loss": 0.9468,
+      "step": 254
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.8622311353683472,
+      "learning_rate": 0.00016,
+      "loss": 0.9775,
+      "step": 255
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 1.0259979963302612,
+      "learning_rate": 0.00015983935742971888,
+      "loss": 0.7778,
+      "step": 256
+    },
+    {
+      "epoch": 1.028,
+      "grad_norm": 1.5519331693649292,
+      "learning_rate": 0.00015967871485943774,
+      "loss": 1.1989,
+      "step": 257
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.9531280994415283,
+      "learning_rate": 0.00015951807228915663,
+      "loss": 0.881,
+      "step": 258
+    },
+    {
+      "epoch": 1.036,
+      "grad_norm": 1.215177059173584,
+      "learning_rate": 0.0001593574297188755,
+      "loss": 0.8421,
+      "step": 259
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.929236114025116,
+      "learning_rate": 0.0001591967871485944,
+      "loss": 0.9044,
+      "step": 260
+    },
+    {
+      "epoch": 1.044,
+      "grad_norm": 0.8656697273254395,
+      "learning_rate": 0.00015903614457831326,
+      "loss": 0.8928,
+      "step": 261
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.8103016018867493,
+      "learning_rate": 0.00015887550200803215,
+      "loss": 0.8062,
+      "step": 262
+    },
+    {
+      "epoch": 1.052,
+      "grad_norm": 1.8430039882659912,
+      "learning_rate": 0.000158714859437751,
+      "loss": 0.84,
+      "step": 263
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.9667379260063171,
+      "learning_rate": 0.0001585542168674699,
+      "loss": 0.8823,
+      "step": 264
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.8082267045974731,
+      "learning_rate": 0.00015839357429718874,
+      "loss": 0.7855,
+      "step": 265
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.8546954393386841,
+      "learning_rate": 0.00015823293172690763,
+      "loss": 0.8074,
+      "step": 266
+    },
+    {
+      "epoch": 1.068,
+      "grad_norm": 0.9033096432685852,
+      "learning_rate": 0.0001580722891566265,
+      "loss": 0.8165,
+      "step": 267
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.9829176068305969,
+      "learning_rate": 0.0001579116465863454,
+      "loss": 0.9718,
+      "step": 268
+    },
+    {
+      "epoch": 1.076,
+      "grad_norm": 0.8669388294219971,
+      "learning_rate": 0.00015775100401606426,
+      "loss": 1.0347,
+      "step": 269
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.969390869140625,
+      "learning_rate": 0.00015759036144578315,
+      "loss": 0.9423,
+      "step": 270
+    },
+    {
+      "epoch": 1.084,
+      "grad_norm": 1.3548946380615234,
+      "learning_rate": 0.000157429718875502,
+      "loss": 1.1337,
+      "step": 271
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.8762166500091553,
+      "learning_rate": 0.0001572690763052209,
+      "loss": 0.8895,
+      "step": 272
+    },
+    {
+      "epoch": 1.092,
+      "grad_norm": 0.7425119876861572,
+      "learning_rate": 0.00015710843373493977,
+      "loss": 0.699,
+      "step": 273
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.9042136669158936,
+      "learning_rate": 0.00015694779116465866,
+      "loss": 0.8775,
+      "step": 274
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.8177143931388855,
+      "learning_rate": 0.0001567871485943775,
+      "loss": 0.9065,
+      "step": 275
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.8629148602485657,
+      "learning_rate": 0.0001566265060240964,
+      "loss": 0.9971,
+      "step": 276
+    },
+    {
+      "epoch": 1.108,
+      "grad_norm": 0.9605036377906799,
+      "learning_rate": 0.00015646586345381526,
+      "loss": 1.2588,
+      "step": 277
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.8671557307243347,
+      "learning_rate": 0.00015630522088353415,
+      "loss": 0.9142,
+      "step": 278
+    },
+    {
+      "epoch": 1.116,
+      "grad_norm": 0.931540310382843,
+      "learning_rate": 0.000156144578313253,
+      "loss": 0.7296,
+      "step": 279
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.0139037370681763,
+      "learning_rate": 0.0001559839357429719,
+      "loss": 1.0284,
+      "step": 280
+    },
+    {
+      "epoch": 1.124,
+      "grad_norm": 1.0189025402069092,
+      "learning_rate": 0.00015582329317269077,
+      "loss": 0.7597,
+      "step": 281
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 1.0193121433258057,
+      "learning_rate": 0.00015566265060240966,
+      "loss": 0.6853,
+      "step": 282
+    },
+    {
+      "epoch": 1.1320000000000001,
+      "grad_norm": 1.0432549715042114,
+      "learning_rate": 0.00015550200803212853,
+      "loss": 0.7334,
+      "step": 283
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.8273834586143494,
+      "learning_rate": 0.0001553413654618474,
+      "loss": 0.8607,
+      "step": 284
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.8880547881126404,
+      "learning_rate": 0.00015518072289156626,
+      "loss": 0.9101,
+      "step": 285
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 1.1600521802902222,
+      "learning_rate": 0.00015502008032128515,
+      "loss": 0.9726,
+      "step": 286
+    },
+    {
+      "epoch": 1.148,
+      "grad_norm": 0.7886917591094971,
+      "learning_rate": 0.000154859437751004,
+      "loss": 0.6512,
+      "step": 287
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.8275341391563416,
+      "learning_rate": 0.0001546987951807229,
+      "loss": 0.6601,
+      "step": 288
+    },
+    {
+      "epoch": 1.156,
+      "grad_norm": 0.9149451851844788,
+      "learning_rate": 0.00015453815261044177,
+      "loss": 0.9482,
+      "step": 289
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.0810786485671997,
+      "learning_rate": 0.00015437751004016066,
+      "loss": 1.0865,
+      "step": 290
+    },
+    {
+      "epoch": 1.164,
+      "grad_norm": 1.0616602897644043,
+      "learning_rate": 0.00015421686746987953,
+      "loss": 0.8068,
+      "step": 291
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 1.0869910717010498,
+      "learning_rate": 0.00015405622489959842,
+      "loss": 0.8159,
+      "step": 292
+    },
+    {
+      "epoch": 1.172,
+      "grad_norm": 0.9603747725486755,
+      "learning_rate": 0.00015389558232931726,
+      "loss": 0.8849,
+      "step": 293
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 1.032436490058899,
+      "learning_rate": 0.00015373493975903615,
+      "loss": 1.0918,
+      "step": 294
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.0083870887756348,
+      "learning_rate": 0.00015357429718875501,
+      "loss": 1.2848,
+      "step": 295
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.8619980812072754,
+      "learning_rate": 0.0001534136546184739,
+      "loss": 0.9018,
+      "step": 296
+    },
+    {
+      "epoch": 1.188,
+      "grad_norm": 0.8633701801300049,
+      "learning_rate": 0.00015325301204819277,
+      "loss": 1.0218,
+      "step": 297
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.9050300717353821,
+      "learning_rate": 0.00015309236947791166,
+      "loss": 0.9092,
+      "step": 298
+    },
+    {
+      "epoch": 1.196,
+      "grad_norm": 0.6374917030334473,
+      "learning_rate": 0.00015293172690763053,
+      "loss": 0.8162,
+      "step": 299
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.825060248374939,
+      "learning_rate": 0.00015277108433734942,
+      "loss": 0.8482,
+      "step": 300
+    },
+    {
+      "epoch": 1.204,
+      "grad_norm": 0.9437833428382874,
+      "learning_rate": 0.00015261044176706828,
+      "loss": 0.8045,
+      "step": 301
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 1.089831829071045,
+      "learning_rate": 0.00015244979919678715,
+      "loss": 1.2077,
+      "step": 302
+    },
+    {
+      "epoch": 1.212,
+      "grad_norm": 0.8222481608390808,
+      "learning_rate": 0.00015228915662650601,
+      "loss": 0.8253,
+      "step": 303
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.8154776096343994,
+      "learning_rate": 0.0001521285140562249,
+      "loss": 0.8029,
+      "step": 304
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.6961467862129211,
+      "learning_rate": 0.00015196787148594377,
+      "loss": 0.7633,
+      "step": 305
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 1.2669425010681152,
+      "learning_rate": 0.00015180722891566266,
+      "loss": 1.1726,
+      "step": 306
+    },
+    {
+      "epoch": 1.228,
+      "grad_norm": 0.9348741769790649,
+      "learning_rate": 0.00015164658634538153,
+      "loss": 1.0063,
+      "step": 307
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.6843699812889099,
+      "learning_rate": 0.00015148594377510042,
+      "loss": 0.6519,
+      "step": 308
+    },
+    {
+      "epoch": 1.236,
+      "grad_norm": 0.7433460354804993,
+      "learning_rate": 0.00015132530120481928,
+      "loss": 0.8903,
+      "step": 309
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.7592901587486267,
+      "learning_rate": 0.00015116465863453818,
+      "loss": 0.9527,
+      "step": 310
+    },
+    {
+      "epoch": 1.244,
+      "grad_norm": 1.1880371570587158,
+      "learning_rate": 0.00015100401606425701,
+      "loss": 1.0092,
+      "step": 311
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.8044797778129578,
+      "learning_rate": 0.0001508433734939759,
+      "loss": 0.9151,
+      "step": 312
+    },
+    {
+      "epoch": 1.252,
+      "grad_norm": 0.7369490265846252,
+      "learning_rate": 0.00015068273092369477,
+      "loss": 0.7088,
+      "step": 313
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.8025039434432983,
+      "learning_rate": 0.00015052208835341366,
+      "loss": 0.8486,
+      "step": 314
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 1.1078802347183228,
+      "learning_rate": 0.00015036144578313253,
+      "loss": 1.0376,
+      "step": 315
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.6546642184257507,
+      "learning_rate": 0.00015020080321285142,
+      "loss": 0.859,
+      "step": 316
+    },
+    {
+      "epoch": 1.268,
+      "grad_norm": 0.8622590899467468,
+      "learning_rate": 0.00015004016064257028,
+      "loss": 1.1371,
+      "step": 317
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 1.182067632675171,
+      "learning_rate": 0.00014987951807228918,
+      "loss": 1.024,
+      "step": 318
+    },
+    {
+      "epoch": 1.276,
+      "grad_norm": 0.6173505187034607,
+      "learning_rate": 0.00014971887550200804,
+      "loss": 0.6438,
+      "step": 319
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.7465916872024536,
+      "learning_rate": 0.0001495582329317269,
+      "loss": 0.6666,
+      "step": 320
+    },
+    {
+      "epoch": 1.284,
+      "grad_norm": 1.1481876373291016,
+      "learning_rate": 0.00014939759036144577,
+      "loss": 0.9966,
+      "step": 321
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 1.4288729429244995,
+      "learning_rate": 0.00014923694779116466,
+      "loss": 0.8963,
+      "step": 322
+    },
+    {
+      "epoch": 1.292,
+      "grad_norm": 0.7680599093437195,
+      "learning_rate": 0.00014907630522088353,
+      "loss": 0.8645,
+      "step": 323
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.8282861113548279,
+      "learning_rate": 0.00014891566265060242,
+      "loss": 0.9313,
+      "step": 324
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.9906266927719116,
+      "learning_rate": 0.00014875502008032128,
+      "loss": 0.9032,
+      "step": 325
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.7492703795433044,
+      "learning_rate": 0.00014859437751004018,
+      "loss": 0.8764,
+      "step": 326
+    },
+    {
+      "epoch": 1.308,
+      "grad_norm": 0.8717472553253174,
+      "learning_rate": 0.00014843373493975904,
+      "loss": 1.1408,
+      "step": 327
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.9089136123657227,
+      "learning_rate": 0.00014827309236947793,
+      "loss": 1.0363,
+      "step": 328
+    },
+    {
+      "epoch": 1.316,
+      "grad_norm": 1.2482575178146362,
+      "learning_rate": 0.00014811244979919677,
+      "loss": 1.2944,
+      "step": 329
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.8029852509498596,
+      "learning_rate": 0.00014795180722891566,
+      "loss": 0.9289,
+      "step": 330
+    },
+    {
+      "epoch": 1.324,
+      "grad_norm": 1.0169625282287598,
+      "learning_rate": 0.00014779116465863453,
+      "loss": 1.0628,
+      "step": 331
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.8372910022735596,
+      "learning_rate": 0.00014763052208835342,
+      "loss": 0.9419,
+      "step": 332
+    },
+    {
+      "epoch": 1.332,
+      "grad_norm": 0.8126416206359863,
+      "learning_rate": 0.00014746987951807228,
+      "loss": 0.9299,
+      "step": 333
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.8730321526527405,
+      "learning_rate": 0.00014730923694779118,
+      "loss": 0.8397,
+      "step": 334
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.6801149845123291,
+      "learning_rate": 0.00014714859437751004,
+      "loss": 0.7707,
+      "step": 335
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 1.0491434335708618,
+      "learning_rate": 0.00014698795180722893,
+      "loss": 0.8701,
+      "step": 336
+    },
+    {
+      "epoch": 1.3479999999999999,
+      "grad_norm": 0.7750973701477051,
+      "learning_rate": 0.0001468273092369478,
+      "loss": 0.7335,
+      "step": 337
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 1.2532795667648315,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 1.046,
+      "step": 338
+    },
+    {
+      "epoch": 1.3559999999999999,
+      "grad_norm": 0.6481201648712158,
+      "learning_rate": 0.00014650602409638555,
+      "loss": 0.693,
+      "step": 339
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.7169057130813599,
+      "learning_rate": 0.00014634538152610442,
+      "loss": 0.8042,
+      "step": 340
+    },
+    {
+      "epoch": 1.3639999999999999,
+      "grad_norm": 0.7652644515037537,
+      "learning_rate": 0.00014618473895582328,
+      "loss": 0.6721,
+      "step": 341
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.7672556638717651,
+      "learning_rate": 0.00014602409638554218,
+      "loss": 0.9337,
+      "step": 342
+    },
+    {
+      "epoch": 1.3719999999999999,
+      "grad_norm": 0.8816798329353333,
+      "learning_rate": 0.00014586345381526104,
+      "loss": 0.8517,
+      "step": 343
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.7136399745941162,
+      "learning_rate": 0.00014570281124497993,
+      "loss": 0.7629,
+      "step": 344
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.6615918874740601,
+      "learning_rate": 0.0001455421686746988,
+      "loss": 0.6994,
+      "step": 345
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.7544054985046387,
+      "learning_rate": 0.0001453815261044177,
+      "loss": 0.7939,
+      "step": 346
+    },
+    {
+      "epoch": 1.388,
+      "grad_norm": 0.6896859407424927,
+      "learning_rate": 0.00014522088353413655,
+      "loss": 0.8282,
+      "step": 347
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.8159996271133423,
+      "learning_rate": 0.00014506024096385542,
+      "loss": 0.922,
+      "step": 348
+    },
+    {
+      "epoch": 1.396,
+      "grad_norm": 0.706908643245697,
+      "learning_rate": 0.0001448995983935743,
+      "loss": 0.7648,
+      "step": 349
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.6972529292106628,
+      "learning_rate": 0.00014473895582329318,
+      "loss": 0.67,
+      "step": 350
+    },
+    {
+      "epoch": 1.404,
+      "grad_norm": 1.0812041759490967,
+      "learning_rate": 0.00014457831325301204,
+      "loss": 1.1073,
+      "step": 351
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.8693597316741943,
+      "learning_rate": 0.00014441767068273093,
+      "loss": 0.942,
+      "step": 352
+    },
+    {
+      "epoch": 1.412,
+      "grad_norm": 0.8040415048599243,
+      "learning_rate": 0.0001442570281124498,
+      "loss": 0.8984,
+      "step": 353
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.9060348272323608,
+      "learning_rate": 0.0001440963855421687,
+      "loss": 0.9079,
+      "step": 354
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.678812563419342,
+      "learning_rate": 0.00014393574297188756,
+      "loss": 0.805,
+      "step": 355
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.7688775658607483,
+      "learning_rate": 0.00014377510040160642,
+      "loss": 0.7974,
+      "step": 356
+    },
+    {
+      "epoch": 1.428,
+      "grad_norm": 0.6476112604141235,
+      "learning_rate": 0.0001436144578313253,
+      "loss": 0.766,
+      "step": 357
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.8048977851867676,
+      "learning_rate": 0.00014345381526104418,
+      "loss": 0.9942,
+      "step": 358
+    },
+    {
+      "epoch": 1.436,
+      "grad_norm": 0.743240237236023,
+      "learning_rate": 0.00014329317269076307,
+      "loss": 0.8387,
+      "step": 359
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.6526162624359131,
+      "learning_rate": 0.00014313253012048193,
+      "loss": 0.7151,
+      "step": 360
+    },
+    {
+      "epoch": 1.444,
+      "grad_norm": 0.6290627121925354,
+      "learning_rate": 0.0001429718875502008,
+      "loss": 0.7649,
+      "step": 361
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 1.0089125633239746,
+      "learning_rate": 0.0001428112449799197,
+      "loss": 0.8418,
+      "step": 362
+    },
+    {
+      "epoch": 1.452,
+      "grad_norm": 0.7626731991767883,
+      "learning_rate": 0.00014265060240963856,
+      "loss": 0.9555,
+      "step": 363
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.8644378185272217,
+      "learning_rate": 0.00014248995983935745,
+      "loss": 0.9028,
+      "step": 364
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.7513160109519958,
+      "learning_rate": 0.0001423293172690763,
+      "loss": 0.8954,
+      "step": 365
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 1.4129043817520142,
+      "learning_rate": 0.00014216867469879518,
+      "loss": 1.3206,
+      "step": 366
+    },
+    {
+      "epoch": 1.468,
+      "grad_norm": 0.6813162565231323,
+      "learning_rate": 0.00014200803212851407,
+      "loss": 0.7671,
+      "step": 367
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.6487876772880554,
+      "learning_rate": 0.00014184738955823293,
+      "loss": 0.7017,
+      "step": 368
+    },
+    {
+      "epoch": 1.476,
+      "grad_norm": 0.7245473861694336,
+      "learning_rate": 0.00014168674698795183,
+      "loss": 0.9018,
+      "step": 369
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.7619637250900269,
+      "learning_rate": 0.0001415261044176707,
+      "loss": 0.7841,
+      "step": 370
+    },
+    {
+      "epoch": 1.484,
+      "grad_norm": 0.8355472683906555,
+      "learning_rate": 0.00014136546184738956,
+      "loss": 0.8861,
+      "step": 371
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 1.0889995098114014,
+      "learning_rate": 0.00014120481927710845,
+      "loss": 1.2424,
+      "step": 372
+    },
+    {
+      "epoch": 1.492,
+      "grad_norm": 0.7690643072128296,
+      "learning_rate": 0.0001410441767068273,
+      "loss": 0.6255,
+      "step": 373
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 1.1891568899154663,
+      "learning_rate": 0.0001408835341365462,
+      "loss": 1.3604,
+      "step": 374
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.8731479644775391,
+      "learning_rate": 0.00014072289156626507,
+      "loss": 0.8409,
+      "step": 375
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.8019016981124878,
+      "learning_rate": 0.00014056224899598393,
+      "loss": 1.0422,
+      "step": 376
+    },
+    {
+      "epoch": 1.508,
+      "grad_norm": 0.8114858865737915,
+      "learning_rate": 0.00014040160642570283,
+      "loss": 0.9324,
+      "step": 377
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.6787622570991516,
+      "learning_rate": 0.0001402409638554217,
+      "loss": 0.8048,
+      "step": 378
+    },
+    {
+      "epoch": 1.516,
+      "grad_norm": 0.7218673229217529,
+      "learning_rate": 0.00014008032128514058,
+      "loss": 0.8457,
+      "step": 379
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 1.1293416023254395,
+      "learning_rate": 0.00013991967871485945,
+      "loss": 0.8746,
+      "step": 380
+    },
+    {
+      "epoch": 1.524,
+      "grad_norm": 0.6414135098457336,
+      "learning_rate": 0.00013975903614457834,
+      "loss": 0.9826,
+      "step": 381
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.77522212266922,
+      "learning_rate": 0.0001395983935742972,
+      "loss": 1.1097,
+      "step": 382
+    },
+    {
+      "epoch": 1.532,
+      "grad_norm": 0.9271252751350403,
+      "learning_rate": 0.00013943775100401607,
+      "loss": 0.9861,
+      "step": 383
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.7062183022499084,
+      "learning_rate": 0.00013927710843373493,
+      "loss": 0.7497,
+      "step": 384
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 1.0994640588760376,
+      "learning_rate": 0.00013911646586345383,
+      "loss": 0.9824,
+      "step": 385
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.8089779615402222,
+      "learning_rate": 0.0001389558232931727,
+      "loss": 0.7932,
+      "step": 386
+    },
+    {
+      "epoch": 1.548,
+      "grad_norm": 1.2140672206878662,
+      "learning_rate": 0.00013879518072289158,
+      "loss": 0.8651,
+      "step": 387
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.6962442398071289,
+      "learning_rate": 0.00013863453815261045,
+      "loss": 0.8586,
+      "step": 388
+    },
+    {
+      "epoch": 1.556,
+      "grad_norm": 0.6319010853767395,
+      "learning_rate": 0.00013847389558232934,
+      "loss": 0.8466,
+      "step": 389
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.7792989611625671,
+      "learning_rate": 0.0001383132530120482,
+      "loss": 0.8083,
+      "step": 390
+    },
+    {
+      "epoch": 1.564,
+      "grad_norm": 0.8208686113357544,
+      "learning_rate": 0.0001381526104417671,
+      "loss": 0.776,
+      "step": 391
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 1.5805881023406982,
+      "learning_rate": 0.00013799196787148596,
+      "loss": 1.1759,
+      "step": 392
+    },
+    {
+      "epoch": 1.572,
+      "grad_norm": 0.7143644094467163,
+      "learning_rate": 0.00013783132530120483,
+      "loss": 0.793,
+      "step": 393
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.8467019200325012,
+      "learning_rate": 0.0001376706827309237,
+      "loss": 0.7705,
+      "step": 394
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.7845149040222168,
+      "learning_rate": 0.00013751004016064258,
+      "loss": 0.7657,
+      "step": 395
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.7105388045310974,
+      "learning_rate": 0.00013734939759036145,
+      "loss": 0.8318,
+      "step": 396
+    },
+    {
+      "epoch": 1.588,
+      "grad_norm": 0.6616787314414978,
+      "learning_rate": 0.00013718875502008034,
+      "loss": 0.874,
+      "step": 397
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.7203574776649475,
+      "learning_rate": 0.0001370281124497992,
+      "loss": 0.7921,
+      "step": 398
+    },
+    {
+      "epoch": 1.596,
+      "grad_norm": 0.5877785086631775,
+      "learning_rate": 0.0001368674698795181,
+      "loss": 0.5557,
+      "step": 399
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7124444842338562,
+      "learning_rate": 0.00013670682730923696,
+      "loss": 0.8414,
+      "step": 400
+    },
+    {
+      "epoch": 1.604,
+      "grad_norm": 0.8725327253341675,
+      "learning_rate": 0.00013654618473895585,
+      "loss": 0.9948,
+      "step": 401
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.7394019365310669,
+      "learning_rate": 0.0001363855421686747,
+      "loss": 0.7611,
+      "step": 402
+    },
+    {
+      "epoch": 1.612,
+      "grad_norm": 1.5251446962356567,
+      "learning_rate": 0.00013622489959839358,
+      "loss": 0.9427,
+      "step": 403
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.6957426071166992,
+      "learning_rate": 0.00013606425702811245,
+      "loss": 0.6364,
+      "step": 404
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.8293634057044983,
+      "learning_rate": 0.00013590361445783134,
+      "loss": 0.9117,
+      "step": 405
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.8335710167884827,
+      "learning_rate": 0.0001357429718875502,
+      "loss": 0.9922,
+      "step": 406
+    },
+    {
+      "epoch": 1.6280000000000001,
+      "grad_norm": 0.9837871789932251,
+      "learning_rate": 0.0001355823293172691,
+      "loss": 1.0687,
+      "step": 407
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.5891956686973572,
+      "learning_rate": 0.00013542168674698796,
+      "loss": 0.7394,
+      "step": 408
+    },
+    {
+      "epoch": 1.6360000000000001,
+      "grad_norm": 1.4837820529937744,
+      "learning_rate": 0.00013526104417670685,
+      "loss": 1.1259,
+      "step": 409
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.6613463759422302,
+      "learning_rate": 0.00013510040160642572,
+      "loss": 0.7917,
+      "step": 410
+    },
+    {
+      "epoch": 1.6440000000000001,
+      "grad_norm": 0.749727189540863,
+      "learning_rate": 0.00013493975903614458,
+      "loss": 0.7739,
+      "step": 411
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.6761593222618103,
+      "learning_rate": 0.00013477911646586345,
+      "loss": 0.7993,
+      "step": 412
+    },
+    {
+      "epoch": 1.6520000000000001,
+      "grad_norm": 0.78187096118927,
+      "learning_rate": 0.00013461847389558234,
+      "loss": 0.8419,
+      "step": 413
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.8375416994094849,
+      "learning_rate": 0.0001344578313253012,
+      "loss": 0.9412,
+      "step": 414
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 1.3472225666046143,
+      "learning_rate": 0.0001342971887550201,
+      "loss": 1.2644,
+      "step": 415
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.7117773294448853,
+      "learning_rate": 0.00013413654618473896,
+      "loss": 0.8858,
+      "step": 416
+    },
+    {
+      "epoch": 1.6680000000000001,
+      "grad_norm": 0.7051294445991516,
+      "learning_rate": 0.00013397590361445785,
+      "loss": 0.8847,
+      "step": 417
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 1.3902690410614014,
+      "learning_rate": 0.00013381526104417672,
+      "loss": 0.7813,
+      "step": 418
+    },
+    {
+      "epoch": 1.6760000000000002,
+      "grad_norm": 0.816811740398407,
+      "learning_rate": 0.0001336546184738956,
+      "loss": 0.9038,
+      "step": 419
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.7157453298568726,
+      "learning_rate": 0.00013349397590361445,
+      "loss": 0.7009,
+      "step": 420
+    },
+    {
+      "epoch": 1.6840000000000002,
+      "grad_norm": 0.940537691116333,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.033,
+      "step": 421
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.8775190711021423,
+      "learning_rate": 0.0001331726907630522,
+      "loss": 1.1525,
+      "step": 422
+    },
+    {
+      "epoch": 1.692,
+      "grad_norm": 0.7041211128234863,
+      "learning_rate": 0.0001330120481927711,
+      "loss": 0.8335,
+      "step": 423
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.7167043089866638,
+      "learning_rate": 0.00013285140562248996,
+      "loss": 0.8497,
+      "step": 424
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.6443823575973511,
+      "learning_rate": 0.00013269076305220885,
+      "loss": 0.7869,
+      "step": 425
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.9639602899551392,
+      "learning_rate": 0.00013253012048192772,
+      "loss": 1.0133,
+      "step": 426
+    },
+    {
+      "epoch": 1.708,
+      "grad_norm": 0.8470444679260254,
+      "learning_rate": 0.0001323694779116466,
+      "loss": 0.97,
+      "step": 427
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.6778219938278198,
+      "learning_rate": 0.00013220883534136547,
+      "loss": 0.9366,
+      "step": 428
+    },
+    {
+      "epoch": 1.716,
+      "grad_norm": 0.6757046580314636,
+      "learning_rate": 0.00013204819277108434,
+      "loss": 0.7596,
+      "step": 429
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.8285611867904663,
+      "learning_rate": 0.0001318875502008032,
+      "loss": 0.8584,
+      "step": 430
+    },
+    {
+      "epoch": 1.724,
+      "grad_norm": 2.1439242362976074,
+      "learning_rate": 0.0001317269076305221,
+      "loss": 1.235,
+      "step": 431
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.7422643303871155,
+      "learning_rate": 0.00013156626506024096,
+      "loss": 0.9639,
+      "step": 432
+    },
+    {
+      "epoch": 1.732,
+      "grad_norm": 0.7402743697166443,
+      "learning_rate": 0.00013140562248995985,
+      "loss": 0.7532,
+      "step": 433
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.6638180017471313,
+      "learning_rate": 0.00013124497991967872,
+      "loss": 0.8766,
+      "step": 434
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.836703360080719,
+      "learning_rate": 0.0001310843373493976,
+      "loss": 0.9691,
+      "step": 435
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.771128237247467,
+      "learning_rate": 0.00013092369477911648,
+      "loss": 0.7835,
+      "step": 436
+    },
+    {
+      "epoch": 1.748,
+      "grad_norm": 1.5005141496658325,
+      "learning_rate": 0.00013076305220883537,
+      "loss": 0.8249,
+      "step": 437
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 1.2309819459915161,
+      "learning_rate": 0.0001306024096385542,
+      "loss": 1.2059,
+      "step": 438
+    },
+    {
+      "epoch": 1.756,
+      "grad_norm": 0.6882178783416748,
+      "learning_rate": 0.0001304417670682731,
+      "loss": 0.861,
+      "step": 439
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.6188068985939026,
+      "learning_rate": 0.00013028112449799196,
+      "loss": 0.7622,
+      "step": 440
+    },
+    {
+      "epoch": 1.764,
+      "grad_norm": 1.066043734550476,
+      "learning_rate": 0.00013012048192771085,
+      "loss": 0.8741,
+      "step": 441
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.708234429359436,
+      "learning_rate": 0.00012995983935742972,
+      "loss": 0.6397,
+      "step": 442
+    },
+    {
+      "epoch": 1.772,
+      "grad_norm": 1.0144734382629395,
+      "learning_rate": 0.0001297991967871486,
+      "loss": 0.9161,
+      "step": 443
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.7630588412284851,
+      "learning_rate": 0.00012963855421686748,
+      "loss": 0.8234,
+      "step": 444
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.7031102776527405,
+      "learning_rate": 0.00012947791164658637,
+      "loss": 0.8321,
+      "step": 445
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 1.6880744695663452,
+      "learning_rate": 0.00012931726907630523,
+      "loss": 0.7158,
+      "step": 446
+    },
+    {
+      "epoch": 1.788,
+      "grad_norm": 3.172560691833496,
+      "learning_rate": 0.0001291566265060241,
+      "loss": 0.9714,
+      "step": 447
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.5778412222862244,
+      "learning_rate": 0.00012899598393574296,
+      "loss": 0.7475,
+      "step": 448
+    },
+    {
+      "epoch": 1.796,
+      "grad_norm": 0.8628131151199341,
+      "learning_rate": 0.00012883534136546185,
+      "loss": 0.8382,
+      "step": 449
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.893858015537262,
+      "learning_rate": 0.00012867469879518072,
+      "loss": 1.0551,
+      "step": 450
+    },
+    {
+      "epoch": 1.804,
+      "grad_norm": 0.7229635715484619,
+      "learning_rate": 0.0001285140562248996,
+      "loss": 0.9537,
+      "step": 451
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.6020472049713135,
+      "learning_rate": 0.00012835341365461848,
+      "loss": 0.7383,
+      "step": 452
+    },
+    {
+      "epoch": 1.812,
+      "grad_norm": 0.8743824362754822,
+      "learning_rate": 0.00012819277108433737,
+      "loss": 1.1131,
+      "step": 453
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.9010409116744995,
+      "learning_rate": 0.00012803212851405623,
+      "loss": 0.8598,
+      "step": 454
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.8469566702842712,
+      "learning_rate": 0.00012787148594377512,
+      "loss": 0.847,
+      "step": 455
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 1.0219815969467163,
+      "learning_rate": 0.00012771084337349396,
+      "loss": 1.1406,
+      "step": 456
+    },
+    {
+      "epoch": 1.8279999999999998,
+      "grad_norm": 0.5638225078582764,
+      "learning_rate": 0.00012755020080321285,
+      "loss": 0.787,
+      "step": 457
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.6885621547698975,
+      "learning_rate": 0.00012738955823293172,
+      "loss": 0.8867,
+      "step": 458
+    },
+    {
+      "epoch": 1.8359999999999999,
+      "grad_norm": 0.6208215951919556,
+      "learning_rate": 0.0001272289156626506,
+      "loss": 0.7313,
+      "step": 459
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.6271224021911621,
+      "learning_rate": 0.00012706827309236948,
+      "loss": 0.8027,
+      "step": 460
+    },
+    {
+      "epoch": 1.8439999999999999,
+      "grad_norm": 0.6228848695755005,
+      "learning_rate": 0.00012690763052208837,
+      "loss": 0.9234,
+      "step": 461
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.6752040386199951,
+      "learning_rate": 0.00012674698795180723,
+      "loss": 0.6518,
+      "step": 462
+    },
+    {
+      "epoch": 1.8519999999999999,
+      "grad_norm": 0.9900215268135071,
+      "learning_rate": 0.00012658634538152612,
+      "loss": 1.1848,
+      "step": 463
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.8529555797576904,
+      "learning_rate": 0.000126425702811245,
+      "loss": 0.937,
+      "step": 464
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.5829982757568359,
+      "learning_rate": 0.00012626506024096385,
+      "loss": 0.6394,
+      "step": 465
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.5278028845787048,
+      "learning_rate": 0.00012610441767068272,
+      "loss": 0.6841,
+      "step": 466
+    },
+    {
+      "epoch": 1.8679999999999999,
+      "grad_norm": 0.5858290791511536,
+      "learning_rate": 0.0001259437751004016,
+      "loss": 0.786,
+      "step": 467
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.6995992064476013,
+      "learning_rate": 0.00012578313253012048,
+      "loss": 0.8194,
+      "step": 468
+    },
+    {
+      "epoch": 1.876,
+      "grad_norm": 0.7144771218299866,
+      "learning_rate": 0.00012562248995983937,
+      "loss": 0.9484,
+      "step": 469
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.686037003993988,
+      "learning_rate": 0.00012546184738955823,
+      "loss": 0.8524,
+      "step": 470
+    },
+    {
+      "epoch": 1.884,
+      "grad_norm": 1.8440570831298828,
+      "learning_rate": 0.00012530120481927712,
+      "loss": 0.8145,
+      "step": 471
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.7659666538238525,
+      "learning_rate": 0.000125140562248996,
+      "loss": 0.933,
+      "step": 472
+    },
+    {
+      "epoch": 1.892,
+      "grad_norm": 0.6825807094573975,
+      "learning_rate": 0.00012497991967871488,
+      "loss": 0.7887,
+      "step": 473
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.6191357970237732,
+      "learning_rate": 0.00012481927710843375,
+      "loss": 0.8107,
+      "step": 474
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 1.2772804498672485,
+      "learning_rate": 0.0001246586345381526,
+      "loss": 1.2145,
+      "step": 475
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.7044898271560669,
+      "learning_rate": 0.00012449799196787148,
+      "loss": 0.8349,
+      "step": 476
+    },
+    {
+      "epoch": 1.908,
+      "grad_norm": 0.502620279788971,
+      "learning_rate": 0.00012433734939759037,
+      "loss": 0.603,
+      "step": 477
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 0.6033430695533752,
+      "learning_rate": 0.00012417670682730923,
+      "loss": 0.7943,
+      "step": 478
+    },
+    {
+      "epoch": 1.916,
+      "grad_norm": 0.667544424533844,
+      "learning_rate": 0.00012401606425702812,
+      "loss": 0.8167,
+      "step": 479
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.695097804069519,
+      "learning_rate": 0.000123855421686747,
+      "loss": 0.7597,
+      "step": 480
+    },
+    {
+      "epoch": 1.924,
+      "grad_norm": 0.8369432091712952,
+      "learning_rate": 0.00012369477911646588,
+      "loss": 1.1304,
+      "step": 481
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.8287705183029175,
+      "learning_rate": 0.00012353413654618475,
+      "loss": 0.9468,
+      "step": 482
+    },
+    {
+      "epoch": 1.932,
+      "grad_norm": 0.7005383372306824,
+      "learning_rate": 0.00012337349397590364,
+      "loss": 0.7497,
+      "step": 483
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.5681748986244202,
+      "learning_rate": 0.00012321285140562248,
+      "loss": 0.6681,
+      "step": 484
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.7493687868118286,
+      "learning_rate": 0.00012305220883534137,
+      "loss": 0.7238,
+      "step": 485
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.8571154475212097,
+      "learning_rate": 0.00012289156626506023,
+      "loss": 0.9938,
+      "step": 486
+    },
+    {
+      "epoch": 1.948,
+      "grad_norm": 0.5937163233757019,
+      "learning_rate": 0.00012273092369477912,
+      "loss": 0.7312,
+      "step": 487
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.7879194021224976,
+      "learning_rate": 0.000122570281124498,
+      "loss": 0.7997,
+      "step": 488
+    },
+    {
+      "epoch": 1.956,
+      "grad_norm": 0.8399389386177063,
+      "learning_rate": 0.00012240963855421688,
+      "loss": 0.9446,
+      "step": 489
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.6027688384056091,
+      "learning_rate": 0.00012224899598393575,
+      "loss": 0.8842,
+      "step": 490
+    },
+    {
+      "epoch": 1.964,
+      "grad_norm": 0.6966837048530579,
+      "learning_rate": 0.00012208835341365464,
+      "loss": 0.8665,
+      "step": 491
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 0.7084407210350037,
+      "learning_rate": 0.00012192771084337352,
+      "loss": 1.0899,
+      "step": 492
+    },
+    {
+      "epoch": 1.972,
+      "grad_norm": 1.2559723854064941,
+      "learning_rate": 0.00012176706827309237,
+      "loss": 1.3685,
+      "step": 493
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.7012714743614197,
+      "learning_rate": 0.00012160642570281125,
+      "loss": 0.7168,
+      "step": 494
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.6182236671447754,
+      "learning_rate": 0.00012144578313253012,
+      "loss": 0.7936,
+      "step": 495
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.6419587731361389,
+      "learning_rate": 0.000121285140562249,
+      "loss": 0.7696,
+      "step": 496
+    },
+    {
+      "epoch": 1.988,
+      "grad_norm": 0.6741763949394226,
+      "learning_rate": 0.00012112449799196788,
+      "loss": 0.6699,
+      "step": 497
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.7472107410430908,
+      "learning_rate": 0.00012096385542168676,
+      "loss": 0.8932,
+      "step": 498
+    },
+    {
+      "epoch": 1.996,
+      "grad_norm": 0.4978902041912079,
+      "learning_rate": 0.00012080321285140564,
+      "loss": 0.5985,
+      "step": 499
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7552313208580017,
+      "learning_rate": 0.00012064257028112452,
+      "loss": 1.0158,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.547117877663744e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e2e1cd324af6f3da873648f27a3f5158e140e99069c3ac742829ee4798ae63
+size 6033

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,146 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "</instruction>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "</system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "</user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<assistant>"
+  ],
+  "bos_token": "<s>",
+  "bos_token_id": 1,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "pad_token_id": 3,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": "<unk>",
+  "unk_token_id": 0,
+  "use_default_system_prompt": false
+}