Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6883ba9310b093598db52ce1bc20f29ce0d9ca9ff99f59f1aa879d2692ddb1a0
+size 9877993490

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf45388fc1482acbc549d8e283b0c3667ba047df11749474f9432bd20e7f9a1
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca440fe83523a802b1e275c3f555e4ca1855508dc578ca17068fb5df17facad2
+size 7180993529

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953670656
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6bc3b332b1d7b34dd8e7d7ed0389c868155059ddb1d908e9ac3feb6672b23c
+size 14583

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de5e0c7dadcd828a8d62fffc136e170202022509240a895985c7bc45cabbced
+size 14583

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c420d12d8aa09a561480241f19154d4aedd8a866de54ed145d69f860bae6f94
+size 14583

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec873fd7c31f869e7956f098c0d1e17d2296924b3c55e4971a059dd097690b6f
+size 14583

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d5fc232bce9c2eb5e24d72a450ba62964cae1c2b04a2bf29a3b93eb08b152c
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789a1cd85c716451dfe8f848f692c67fa7d96da5bcb99c3ed256c2e3ee0e93e5
+size 627

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1816 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.123711340206185,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 0.238,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 0.2949,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.2922,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 0.1945,
+      "step": 4
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 0.1929,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.1124,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5925925925925925e-06,
+      "loss": 0.0661,
+      "step": 7
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 0.0261,
+      "step": 8
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.008,
+      "step": 9
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.0013,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 0.0008,
+      "step": 11
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.0001,
+      "step": 12
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.814814814814815e-06,
+      "loss": 0.0001,
+      "step": 13
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 0.0002,
+      "step": 14
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 6.296296296296297e-06,
+      "loss": 0.0001,
+      "step": 17
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 7.0370370370370375e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.518518518518519e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.037037037037037e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.0740740740740742e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.1481481481481482e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1851851851851852e-05,
+      "loss": 0.0005,
+      "step": 32
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2592592592592593e-05,
+      "loss": 0.0783,
+      "step": 34
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2962962962962964e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.3703703703703706e-05,
+      "loss": 0.0004,
+      "step": 37
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.0005,
+      "step": 38
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 0.0003,
+      "step": 39
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.0006,
+      "step": 40
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.5185185185185187e-05,
+      "loss": 0.0039,
+      "step": 41
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.0048,
+      "step": 42
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.5925925925925926e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.6296296296296297e-05,
+      "loss": 0.0004,
+      "step": 44
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0048,
+      "step": 45
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.740740740740741e-05,
+      "loss": 0.0167,
+      "step": 47
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.0228,
+      "step": 48
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.814814814814815e-05,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.0008,
+      "step": 50
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.0009,
+      "step": 51
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.925925925925926e-05,
+      "loss": 0.1318,
+      "step": 52
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.962962962962963e-05,
+      "loss": 0.0004,
+      "step": 53
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2e-05,
+      "loss": 0.0016,
+      "step": 54
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.9999983812448848e-05,
+      "loss": 0.0055,
+      "step": 55
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.9999935249847798e-05,
+      "loss": 0.0008,
+      "step": 56
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.9999854312354064e-05,
+      "loss": 0.0007,
+      "step": 57
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.9999741000229695e-05,
+      "loss": 0.0017,
+      "step": 58
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.999959531384153e-05,
+      "loss": 0.0004,
+      "step": 59
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9999417253661235e-05,
+      "loss": 0.0004,
+      "step": 60
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.9999206820265283e-05,
+      "loss": 0.0005,
+      "step": 61
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.9998964014334946e-05,
+      "loss": 0.0003,
+      "step": 62
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.9998688836656322e-05,
+      "loss": 0.0003,
+      "step": 63
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9998381288120296e-05,
+      "loss": 0.0023,
+      "step": 64
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.9998041369722556e-05,
+      "loss": 0.0001,
+      "step": 65
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9997669082563597e-05,
+      "loss": 0.0001,
+      "step": 66
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.9997264427848702e-05,
+      "loss": 0.0001,
+      "step": 67
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.999682740688794e-05,
+      "loss": 0.0006,
+      "step": 68
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.9996358021096174e-05,
+      "loss": 0.0153,
+      "step": 69
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.999585627199305e-05,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.9995322161202975e-05,
+      "loss": 0.0001,
+      "step": 71
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9994755690455154e-05,
+      "loss": 0.0002,
+      "step": 72
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9994156861583522e-05,
+      "loss": 0.0005,
+      "step": 73
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9993525676526807e-05,
+      "loss": 0.0003,
+      "step": 74
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.9992862137328475e-05,
+      "loss": 0.0004,
+      "step": 75
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9992166246136738e-05,
+      "loss": 0.0002,
+      "step": 76
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.9991438005204557e-05,
+      "loss": 0.0002,
+      "step": 77
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.999067741688961e-05,
+      "loss": 0.0002,
+      "step": 78
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.9989884483654315e-05,
+      "loss": 0.0007,
+      "step": 79
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.9989059208065803e-05,
+      "loss": 0.0002,
+      "step": 80
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.998820159279591e-05,
+      "loss": 0.0001,
+      "step": 81
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.9987311640621173e-05,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.9986389354422823e-05,
+      "loss": 0.0001,
+      "step": 83
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.998543473718677e-05,
+      "loss": 0.0486,
+      "step": 84
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.9984447792003602e-05,
+      "loss": 0.0001,
+      "step": 85
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.9983428522068556e-05,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.998237693068153e-05,
+      "loss": 0.0006,
+      "step": 87
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.998129302124707e-05,
+      "loss": 0.0005,
+      "step": 88
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9980176797274335e-05,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.997902826237712e-05,
+      "loss": 0.0002,
+      "step": 90
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.9977847420273807e-05,
+      "loss": 0.0001,
+      "step": 91
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.9976634274787396e-05,
+      "loss": 0.0001,
+      "step": 92
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.997538882984545e-05,
+      "loss": 0.0008,
+      "step": 93
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.9974111089480112e-05,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.997280105782808e-05,
+      "loss": 0.0007,
+      "step": 95
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.9971458739130598e-05,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.997008413773343e-05,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.9968677258086868e-05,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.9967238104745695e-05,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.9965766682369188e-05,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.9964262995721088e-05,
+      "loss": 0.0011,
+      "step": 101
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.99627270496696e-05,
+      "loss": 0.0,
+      "step": 102
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.996115884918736e-05,
+      "loss": 0.0001,
+      "step": 103
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.9959558399351443e-05,
+      "loss": 0.0023,
+      "step": 104
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.995792570534331e-05,
+      "loss": 0.0091,
+      "step": 105
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.9956260772448835e-05,
+      "loss": 0.04,
+      "step": 106
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.9954563606058246e-05,
+      "loss": 0.0001,
+      "step": 107
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.995283421166614e-05,
+      "loss": 0.0003,
+      "step": 108
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.9951072594871452e-05,
+      "loss": 0.0007,
+      "step": 109
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.994927876137743e-05,
+      "loss": 0.0454,
+      "step": 110
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.994745271699163e-05,
+      "loss": 0.0023,
+      "step": 111
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.9945594467625895e-05,
+      "loss": 0.0061,
+      "step": 112
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.9943704019296316e-05,
+      "loss": 0.0008,
+      "step": 113
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.9941781378123244e-05,
+      "loss": 0.0063,
+      "step": 114
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.993982655033125e-05,
+      "loss": 0.0001,
+      "step": 115
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.9937839542249108e-05,
+      "loss": 0.0004,
+      "step": 116
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.993582036030978e-05,
+      "loss": 0.0002,
+      "step": 117
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9933769011050382e-05,
+      "loss": 0.0001,
+      "step": 118
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.9931685501112183e-05,
+      "loss": 0.0006,
+      "step": 119
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.9929569837240567e-05,
+      "loss": 0.0013,
+      "step": 120
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.9927422026285016e-05,
+      "loss": 0.0001,
+      "step": 121
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.992524207519909e-05,
+      "loss": 0.0002,
+      "step": 122
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.9923029991040405e-05,
+      "loss": 0.0001,
+      "step": 123
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9920785780970604e-05,
+      "loss": 0.0008,
+      "step": 124
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.991850945225534e-05,
+      "loss": 0.003,
+      "step": 125
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.9916201012264255e-05,
+      "loss": 0.0176,
+      "step": 126
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.9913860468470938e-05,
+      "loss": 0.0,
+      "step": 127
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.9911487828452932e-05,
+      "loss": 0.0079,
+      "step": 128
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.9909083099891682e-05,
+      "loss": 0.0004,
+      "step": 129
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.9906646290572514e-05,
+      "loss": 0.0004,
+      "step": 130
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.9904177408384635e-05,
+      "loss": 0.0003,
+      "step": 131
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.990167646132107e-05,
+      "loss": 0.0021,
+      "step": 132
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.9899143457478658e-05,
+      "loss": 0.0132,
+      "step": 133
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.9896578405058028e-05,
+      "loss": 0.0022,
+      "step": 134
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.9893981312363563e-05,
+      "loss": 0.0002,
+      "step": 135
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9893981312363563e-05,
+      "loss": 0.0132,
+      "step": 136
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.9891352187803375e-05,
+      "loss": 0.0008,
+      "step": 137
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.988869103988929e-05,
+      "loss": 0.0077,
+      "step": 138
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.9885997877236788e-05,
+      "loss": 0.0003,
+      "step": 139
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.9883272708565022e-05,
+      "loss": 0.0019,
+      "step": 140
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.988051554269675e-05,
+      "loss": 0.0115,
+      "step": 141
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.9877726388558325e-05,
+      "loss": 0.0012,
+      "step": 142
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.987490525517966e-05,
+      "loss": 0.0023,
+      "step": 143
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.9872052151694203e-05,
+      "loss": 0.0006,
+      "step": 144
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.9869167087338908e-05,
+      "loss": 0.0011,
+      "step": 145
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.98662500714542e-05,
+      "loss": 0.0004,
+      "step": 146
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.986330111348395e-05,
+      "loss": 0.0058,
+      "step": 147
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.9860320222975435e-05,
+      "loss": 0.0004,
+      "step": 148
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.985730740957932e-05,
+      "loss": 0.0001,
+      "step": 149
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.985426268304962e-05,
+      "loss": 0.0153,
+      "step": 150
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.9851186053243667e-05,
+      "loss": 0.0008,
+      "step": 151
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.0,
+      "step": 152
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.9844937123748744e-05,
+      "loss": 0.0026,
+      "step": 153
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.9841764844290744e-05,
+      "loss": 0.0002,
+      "step": 154
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.9838560702018373e-05,
+      "loss": 0.0002,
+      "step": 155
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.9835324707305076e-05,
+      "loss": 0.0108,
+      "step": 156
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.983205687062742e-05,
+      "loss": 0.0001,
+      "step": 157
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.982875720256505e-05,
+      "loss": 0.0001,
+      "step": 158
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.982542571380069e-05,
+      "loss": 0.0011,
+      "step": 159
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.9822062415120053e-05,
+      "loss": 0.0001,
+      "step": 160
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.9818667317411865e-05,
+      "loss": 0.0001,
+      "step": 161
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.9815240431667786e-05,
+      "loss": 0.0004,
+      "step": 162
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.9811781768982392e-05,
+      "loss": 0.0001,
+      "step": 163
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.980829134055314e-05,
+      "loss": 0.0006,
+      "step": 164
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.980476915768033e-05,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.9801215231767056e-05,
+      "loss": 0.0001,
+      "step": 166
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.9797629574319202e-05,
+      "loss": 0.0313,
+      "step": 167
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.9794012196945362e-05,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.9790363111356838e-05,
+      "loss": 0.0,
+      "step": 169
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.9786682329367578e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.978296986289415e-05,
+      "loss": 0.0001,
+      "step": 171
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.977922572395571e-05,
+      "loss": 0.0128,
+      "step": 172
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.9775449924673937e-05,
+      "loss": 0.0003,
+      "step": 173
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.977164247727302e-05,
+      "loss": 0.0003,
+      "step": 174
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.9767803394079618e-05,
+      "loss": 0.0002,
+      "step": 175
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9763932687522796e-05,
+      "loss": 0.0045,
+      "step": 176
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.9760030370134004e-05,
+      "loss": 0.0012,
+      "step": 177
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.975609645454704e-05,
+      "loss": 0.0001,
+      "step": 178
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.975213095349799e-05,
+      "loss": 0.0001,
+      "step": 179
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.974813387982521e-05,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.9744105246469264e-05,
+      "loss": 0.0001,
+      "step": 181
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.974004506647289e-05,
+      "loss": 0.0097,
+      "step": 182
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.973595335298097e-05,
+      "loss": 0.0001,
+      "step": 183
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.9731830119240465e-05,
+      "loss": 0.0008,
+      "step": 184
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.9727675378600382e-05,
+      "loss": 0.0002,
+      "step": 185
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.9723489144511744e-05,
+      "loss": 0.0002,
+      "step": 186
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.971927143052752e-05,
+      "loss": 0.0002,
+      "step": 187
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.971502225030261e-05,
+      "loss": 0.0023,
+      "step": 188
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.9710741617593768e-05,
+      "loss": 0.0003,
+      "step": 189
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.9706429546259592e-05,
+      "loss": 0.0008,
+      "step": 190
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.970208605026046e-05,
+      "loss": 0.0003,
+      "step": 191
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 1.969771114365848e-05,
+      "loss": 0.0,
+      "step": 192
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 1.9693304840617456e-05,
+      "loss": 0.0001,
+      "step": 193
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.9688867155402845e-05,
+      "loss": 0.0,
+      "step": 194
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.9684398102381694e-05,
+      "loss": 0.0057,
+      "step": 195
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.967989769602261e-05,
+      "loss": 0.0001,
+      "step": 196
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.9675365950895703e-05,
+      "loss": 0.0001,
+      "step": 197
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.9670802881672543e-05,
+      "loss": 0.0017,
+      "step": 198
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 1.9666208503126115e-05,
+      "loss": 0.0003,
+      "step": 199
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.9661582830130766e-05,
+      "loss": 0.0009,
+      "step": 200
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.965692587766216e-05,
+      "loss": 0.0003,
+      "step": 201
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.965223766079723e-05,
+      "loss": 0.0264,
+      "step": 202
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.9647518194714125e-05,
+      "loss": 0.0,
+      "step": 203
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.964276749469216e-05,
+      "loss": 0.0001,
+      "step": 204
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.963798557611178e-05,
+      "loss": 0.0,
+      "step": 205
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.9633172454454498e-05,
+      "loss": 0.0,
+      "step": 206
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.9628328145302837e-05,
+      "loss": 0.0003,
+      "step": 207
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.9623452664340305e-05,
+      "loss": 0.0,
+      "step": 208
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.9618546027351315e-05,
+      "loss": 0.0,
+      "step": 209
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.961360825022116e-05,
+      "loss": 0.0001,
+      "step": 210
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.9608639348935938e-05,
+      "loss": 0.0001,
+      "step": 211
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.9603639339582522e-05,
+      "loss": 0.0001,
+      "step": 212
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.9598608238348493e-05,
+      "loss": 0.0002,
+      "step": 213
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.9593546061522094e-05,
+      "loss": 0.0054,
+      "step": 214
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 1.958845282549217e-05,
+      "loss": 0.0001,
+      "step": 215
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.958332854674813e-05,
+      "loss": 0.0001,
+      "step": 216
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.957817324187987e-05,
+      "loss": 0.0001,
+      "step": 217
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.9572986927577756e-05,
+      "loss": 0.0091,
+      "step": 218
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 1.956776962063252e-05,
+      "loss": 0.0011,
+      "step": 219
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 1.9562521337935255e-05,
+      "loss": 0.0005,
+      "step": 220
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.955724209647733e-05,
+      "loss": 0.0005,
+      "step": 221
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 1.9551931913350338e-05,
+      "loss": 0.0002,
+      "step": 222
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.9546590805746054e-05,
+      "loss": 0.0001,
+      "step": 223
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.954121879095637e-05,
+      "loss": 0.0001,
+      "step": 224
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 1.953581588637323e-05,
+      "loss": 0.0033,
+      "step": 225
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 1.953038210948861e-05,
+      "loss": 0.0002,
+      "step": 226
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 1.9524917477894406e-05,
+      "loss": 0.0006,
+      "step": 227
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 1.951942200928242e-05,
+      "loss": 0.0003,
+      "step": 228
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 1.9513895721444286e-05,
+      "loss": 0.0002,
+      "step": 229
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.9508338632271425e-05,
+      "loss": 0.0081,
+      "step": 230
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 1.9502750759754963e-05,
+      "loss": 0.0001,
+      "step": 231
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.9497132121985695e-05,
+      "loss": 0.0002,
+      "step": 232
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 1.9491482737154023e-05,
+      "loss": 0.0193,
+      "step": 233
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 1.948580262354988e-05,
+      "loss": 0.0002,
+      "step": 234
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 1.9480091799562706e-05,
+      "loss": 0.0033,
+      "step": 235
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.9474350283681337e-05,
+      "loss": 0.0035,
+      "step": 236
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.9468578094493998e-05,
+      "loss": 0.0127,
+      "step": 237
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 1.9462775250688208e-05,
+      "loss": 0.0,
+      "step": 238
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1.9456941771050733e-05,
+      "loss": 0.0002,
+      "step": 239
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 1.9451077674467526e-05,
+      "loss": 0.0014,
+      "step": 240
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 1.9445182979923657e-05,
+      "loss": 0.0035,
+      "step": 241
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 1.9439257706503257e-05,
+      "loss": 0.0002,
+      "step": 242
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.9433301873389463e-05,
+      "loss": 0.0003,
+      "step": 243
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 1.9427315499864345e-05,
+      "loss": 0.0009,
+      "step": 244
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 1.9421298605308847e-05,
+      "loss": 0.0022,
+      "step": 245
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 1.941525120920273e-05,
+      "loss": 0.0226,
+      "step": 246
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 1.94091733311245e-05,
+      "loss": 0.0057,
+      "step": 247
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.9403064990751347e-05,
+      "loss": 0.0025,
+      "step": 248
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.0088,
+      "step": 249
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 1.939075700232209e-05,
+      "loss": 0.0001,
+      "step": 250
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 1.938455739411323e-05,
+      "loss": 0.0324,
+      "step": 251
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.937832740330379e-05,
+      "loss": 0.019,
+      "step": 252
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.937206705006344e-05,
+      "loss": 0.0001,
+      "step": 253
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 1.936577635466013e-05,
+      "loss": 0.0364,
+      "step": 254
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.9359455337460054e-05,
+      "loss": 0.0002,
+      "step": 255
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 1.9353104018927568e-05,
+      "loss": 0.0009,
+      "step": 256
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.9346722419625136e-05,
+      "loss": 0.0014,
+      "step": 257
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.934031056021325e-05,
+      "loss": 0.02,
+      "step": 258
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.933386846145036e-05,
+      "loss": 0.0063,
+      "step": 259
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 1.9327396144192837e-05,
+      "loss": 0.0015,
+      "step": 260
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 1.9320893629394876e-05,
+      "loss": 0.0016,
+      "step": 261
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.9314360938108427e-05,
+      "loss": 0.0008,
+      "step": 262
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.9307798091483146e-05,
+      "loss": 0.0272,
+      "step": 263
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.9301205110766323e-05,
+      "loss": 0.0018,
+      "step": 264
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.9294582017302797e-05,
+      "loss": 0.0168,
+      "step": 265
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.9287928832534896e-05,
+      "loss": 0.0009,
+      "step": 266
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.9281245578002382e-05,
+      "loss": 0.0006,
+      "step": 267
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.9274532275342355e-05,
+      "loss": 0.0005,
+      "step": 268
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.9267788946289202e-05,
+      "loss": 0.0008,
+      "step": 269
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.9261015612674518e-05,
+      "loss": 0.0012,
+      "step": 270
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.9254212296427043e-05,
+      "loss": 0.0006,
+      "step": 271
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.9247379019572584e-05,
+      "loss": 0.0008,
+      "step": 272
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.924051580423394e-05,
+      "loss": 0.0004,
+      "step": 273
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.923362267263084e-05,
+      "loss": 0.0003,
+      "step": 274
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.9226699647079874e-05,
+      "loss": 0.0013,
+      "step": 275
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.9219746749994404e-05,
+      "loss": 0.0209,
+      "step": 276
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.921276400388451e-05,
+      "loss": 0.0002,
+      "step": 277
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 1.92057514313569e-05,
+      "loss": 0.0073,
+      "step": 278
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.919870905511485e-05,
+      "loss": 0.0056,
+      "step": 279
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 1.9191636897958123e-05,
+      "loss": 0.0057,
+      "step": 280
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 1.91845349827829e-05,
+      "loss": 0.0146,
+      "step": 281
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.9177403332581715e-05,
+      "loss": 0.0,
+      "step": 282
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.9170241970443344e-05,
+      "loss": 0.0003,
+      "step": 283
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.9163050919552777e-05,
+      "loss": 0.0017,
+      "step": 284
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 1.915583020319111e-05,
+      "loss": 0.0015,
+      "step": 285
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 1.9148579844735497e-05,
+      "loss": 0.0082,
+      "step": 286
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 1.9141299867659036e-05,
+      "loss": 0.0002,
+      "step": 287
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 1.9133990295530737e-05,
+      "loss": 0.0021,
+      "step": 288
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 1.9126651152015404e-05,
+      "loss": 0.0001,
+      "step": 289
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.9119282460873597e-05,
+      "loss": 0.0001,
+      "step": 290
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9111884245961524e-05,
+      "loss": 0.0002,
+      "step": 291
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 1.9104456531230986e-05,
+      "loss": 0.0002,
+      "step": 292
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.9096999340729284e-05,
+      "loss": 0.0002,
+      "step": 293
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 1.9089512698599148e-05,
+      "loss": 0.0001,
+      "step": 294
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 1.9081996629078655e-05,
+      "loss": 0.0219,
+      "step": 295
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 1.9074451156501163e-05,
+      "loss": 0.0001,
+      "step": 296
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 1.9066876305295218e-05,
+      "loss": 0.0003,
+      "step": 297
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 1.905927209998447e-05,
+      "loss": 0.0,
+      "step": 298
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 1.905163856518762e-05,
+      "loss": 0.0019,
+      "step": 299
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.9043975725618304e-05,
+      "loss": 0.0068,
+      "step": 300
+    }
+  ],
+  "max_steps": 1800,
+  "num_train_epochs": 25,
+  "total_flos": 9.93619813072896e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c7db536e000ff9dd6b04d925a492468dc541269ec0f5e45b9c17a2a5039443
+size 3771