Upload folder using huggingface_hub

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/workspace/llama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_seq_len": 4096,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa4f3a56efca67a31e83a3306b0047391994df3a1802fd12a14cca9f17b5fae5
+size 9877989586

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ef6cdd2c2b29cec07abfede67890ac1b35a15ab7a8e6d4a18ddc0050e749c6
+size 9894801014

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91a490d897baf14e60123f390d1af71d91e4d512fdaa223cc4d85bba5e5386c
+size 7180990649

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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,1807 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 297,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6895,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.7129,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-06,
+      "loss": 0.7467,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.6553,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6908,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1e-05,
+      "loss": 0.6292,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.648,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6291,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6205,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5143,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.5343,
+      "step": 11
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 0.6127,
+      "step": 12
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9999392458943432e-05,
+      "loss": 0.5313,
+      "step": 13
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9997569909594948e-05,
+      "loss": 0.486,
+      "step": 14
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.999453257340926e-05,
+      "loss": 0.5457,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9990280819447662e-05,
+      "loss": 0.5688,
+      "step": 16
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9984815164333163e-05,
+      "loss": 0.5523,
+      "step": 17
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9978136272187745e-05,
+      "loss": 0.5291,
+      "step": 18
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9970244954551648e-05,
+      "loss": 0.4995,
+      "step": 19
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9961142170284762e-05,
+      "loss": 0.4819,
+      "step": 20
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9950829025450116e-05,
+      "loss": 0.485,
+      "step": 21
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9939306773179498e-05,
+      "loss": 0.5592,
+      "step": 22
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9926576813521167e-05,
+      "loss": 0.5018,
+      "step": 23
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9912640693269754e-05,
+      "loss": 0.5148,
+      "step": 24
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.98975001057783e-05,
+      "loss": 0.4703,
+      "step": 25
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9881156890752517e-05,
+      "loss": 0.46,
+      "step": 26
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.4772,
+      "step": 27
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9844870667325073e-05,
+      "loss": 0.4644,
+      "step": 28
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9824932067997516e-05,
+      "loss": 0.43,
+      "step": 29
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9803799658748096e-05,
+      "loss": 0.4792,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.4879,
+      "step": 31
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9757963826274357e-05,
+      "loss": 0.466,
+      "step": 32
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.973326597248006e-05,
+      "loss": 0.4972,
+      "step": 33
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.97073854469472e-05,
+      "loss": 0.4756,
+      "step": 34
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.968032539437215e-05,
+      "loss": 0.5015,
+      "step": 35
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9652089102773487e-05,
+      "loss": 0.4449,
+      "step": 36
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9622680003092503e-05,
+      "loss": 0.411,
+      "step": 37
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.95921016687763e-05,
+      "loss": 0.4184,
+      "step": 38
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9560357815343577e-05,
+      "loss": 0.4779,
+      "step": 39
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9527452299933192e-05,
+      "loss": 0.4778,
+      "step": 40
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9493389120835462e-05,
+      "loss": 0.3891,
+      "step": 41
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.4235,
+      "step": 42
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9421806467564546e-05,
+      "loss": 0.4597,
+      "step": 43
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9384295691271523e-05,
+      "loss": 0.4506,
+      "step": 44
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.934564464599461e-05,
+      "loss": 0.4283,
+      "step": 45
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9305858028153186e-05,
+      "loss": 0.414,
+      "step": 46
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9264940672148018e-05,
+      "loss": 0.3809,
+      "step": 47
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.922289754977385e-05,
+      "loss": 0.4041,
+      "step": 48
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9179733769615273e-05,
+      "loss": 0.4192,
+      "step": 49
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.4638,
+      "step": 50
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.909006535049163e-05,
+      "loss": 0.3532,
+      "step": 51
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9043571606975776e-05,
+      "loss": 0.3824,
+      "step": 52
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.899597899525007e-05,
+      "loss": 0.4066,
+      "step": 53
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8947293298207637e-05,
+      "loss": 0.4117,
+      "step": 54
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8897520431560435e-05,
+      "loss": 0.4037,
+      "step": 55
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.884666644312046e-05,
+      "loss": 0.4009,
+      "step": 56
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.3139,
+      "step": 57
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8741739948185256e-05,
+      "loss": 0.4352,
+      "step": 58
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8687680191120746e-05,
+      "loss": 0.4189,
+      "step": 59
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.863256480957574e-05,
+      "loss": 0.4013,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8576400500521673e-05,
+      "loss": 0.416,
+      "step": 61
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.851919408838327e-05,
+      "loss": 0.4034,
+      "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8460952524209355e-05,
+      "loss": 0.3081,
+      "step": 63
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8401682884828212e-05,
+      "loss": 0.4454,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.83413923719877e-05,
+      "loss": 0.4245,
+      "step": 65
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8280088311480203e-05,
+      "loss": 0.4159,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.821777815225245e-05,
+      "loss": 0.3682,
+      "step": 67
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8154469465500447e-05,
+      "loss": 0.3361,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.4249,
+      "step": 69
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.802488739991941e-05,
+      "loss": 0.3483,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7958629766375387e-05,
+      "loss": 0.3563,
+      "step": 71
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.3829,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7823221551034766e-05,
+      "loss": 0.333,
+      "step": 73
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7754087422448217e-05,
+      "loss": 0.3394,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7684011108568593e-05,
+      "loss": 0.2989,
+      "step": 75
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7613001124243448e-05,
+      "loss": 0.3513,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7541066097768965e-05,
+      "loss": 0.4423,
+      "step": 77
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7468214769841542e-05,
+      "loss": 0.3345,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7394455992495722e-05,
+      "loss": 0.3538,
+      "step": 79
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7319798728028617e-05,
+      "loss": 0.311,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7244252047910893e-05,
+      "loss": 0.3137,
+      "step": 81
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7167825131684516e-05,
+      "loss": 0.2986,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7090527265847375e-05,
+      "loss": 0.3376,
+      "step": 83
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7012367842724887e-05,
+      "loss": 0.2555,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6933356359328756e-05,
+      "loss": 0.2784,
+      "step": 85
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6853502416203e-05,
+      "loss": 0.4175,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.402,
+      "step": 87
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.3356,
+      "step": 88
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6608983362288612e-05,
+      "loss": 0.3317,
+      "step": 89
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6525857615241686e-05,
+      "loss": 0.3149,
+      "step": 90
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6441938922908644e-05,
+      "loss": 0.291,
+      "step": 91
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6357237482099682e-05,
+      "loss": 0.3862,
+      "step": 92
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6271763584735373e-05,
+      "loss": 0.3611,
+      "step": 93
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6185527616596096e-05,
+      "loss": 0.3326,
+      "step": 94
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.609854005606009e-05,
+      "loss": 0.4092,
+      "step": 95
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6010811472830253e-05,
+      "loss": 0.313,
+      "step": 96
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5922352526649803e-05,
+      "loss": 0.3875,
+      "step": 97
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.583317396600707e-05,
+      "loss": 0.3525,
+      "step": 98
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5743286626829437e-05,
+      "loss": 0.3531,
+      "step": 99
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.565270143116672e-05,
+      "loss": 0.3013,
+      "step": 100
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5561429385864005e-05,
+      "loss": 0.3702,
+      "step": 101
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.3134,
+      "step": 102
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5376869189660784e-05,
+      "loss": 0.334,
+      "step": 103
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.528360346433959e-05,
+      "loss": 0.3265,
+      "step": 104
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5189695737812153e-05,
+      "loss": 0.2694,
+      "step": 105
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5095157420638349e-05,
+      "loss": 0.3163,
+      "step": 106
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.273,
+      "step": 107
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4904235038305084e-05,
+      "loss": 0.2774,
+      "step": 108
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4807874171782795e-05,
+      "loss": 0.3119,
+      "step": 109
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4710929109069674e-05,
+      "loss": 0.3072,
+      "step": 110
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.461341162978688e-05,
+      "loss": 0.2993,
+      "step": 111
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4515333583108896e-05,
+      "loss": 0.2969,
+      "step": 112
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4416706886323741e-05,
+      "loss": 0.2728,
+      "step": 113
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4317543523384928e-05,
+      "loss": 0.282,
+      "step": 114
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4217855543455323e-05,
+      "loss": 0.2412,
+      "step": 115
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4117655059443052e-05,
+      "loss": 0.2805,
+      "step": 116
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.2515,
+      "step": 117
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3915765340690916e-05,
+      "loss": 0.246,
+      "step": 118
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3814100637209663e-05,
+      "loss": 0.272,
+      "step": 119
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3711972489182208e-05,
+      "loss": 0.2769,
+      "step": 120
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3609393306017149e-05,
+      "loss": 0.2189,
+      "step": 121
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3506375551927546e-05,
+      "loss": 0.2174,
+      "step": 122
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3402931744416432e-05,
+      "loss": 0.2252,
+      "step": 123
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3299074452755829e-05,
+      "loss": 0.2361,
+      "step": 124
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3194816296459483e-05,
+      "loss": 0.2545,
+      "step": 125
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.2656,
+      "step": 126
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2985148110016947e-05,
+      "loss": 0.2973,
+      "step": 127
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2879763556277062e-05,
+      "loss": 0.2965,
+      "step": 128
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2774029087618448e-05,
+      "loss": 0.2444,
+      "step": 129
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2667957551647263e-05,
+      "loss": 0.2817,
+      "step": 130
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2561561836926115e-05,
+      "loss": 0.2908,
+      "step": 131
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.2854,
+      "step": 132
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.234784962086541e-05,
+      "loss": 0.2955,
+      "step": 133
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.224055908731496e-05,
+      "loss": 0.3027,
+      "step": 134
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.213299630743747e-05,
+      "loss": 0.2459,
+      "step": 135
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.2025174350993923e-05,
+      "loss": 0.2663,
+      "step": 136
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1917106319237386e-05,
+      "loss": 0.22,
+      "step": 137
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1808805343321102e-05,
+      "loss": 0.2549,
+      "step": 138
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1700284582702933e-05,
+      "loss": 0.2712,
+      "step": 139
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1591557223546394e-05,
+      "loss": 0.2347,
+      "step": 140
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.148263647711842e-05,
+      "loss": 0.2478,
+      "step": 141
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1373535578184083e-05,
+      "loss": 0.2049,
+      "step": 142
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1264267783398463e-05,
+      "loss": 0.2375,
+      "step": 143
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1154846369695864e-05,
+      "loss": 0.2893,
+      "step": 144
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.2361,
+      "step": 145
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.093559588499118e-05,
+      "loss": 0.1738,
+      "step": 146
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.2037,
+      "step": 147
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0715890683769872e-05,
+      "loss": 0.2048,
+      "step": 148
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.060590092621994e-05,
+      "loss": 0.1777,
+      "step": 149
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0495837546732224e-05,
+      "loss": 0.2889,
+      "step": 150
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0385713918911104e-05,
+      "loss": 0.2363,
+      "step": 151
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0275543423681622e-05,
+      "loss": 0.2456,
+      "step": 152
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.0165339447663586e-05,
+      "loss": 0.236,
+      "step": 153
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.0055115381545006e-05,
+      "loss": 0.2409,
+      "step": 154
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.944884618454996e-06,
+      "loss": 0.2758,
+      "step": 155
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.834660552336415e-06,
+      "loss": 0.1752,
+      "step": 156
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.724456576318383e-06,
+      "loss": 0.2372,
+      "step": 157
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.614286081088895e-06,
+      "loss": 0.2148,
+      "step": 158
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.504162453267776e-06,
+      "loss": 0.1684,
+      "step": 159
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.394099073780066e-06,
+      "loss": 0.2243,
+      "step": 160
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.284109316230133e-06,
+      "loss": 0.2365,
+      "step": 161
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.2333,
+      "step": 162
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.064404115008824e-06,
+      "loss": 0.2108,
+      "step": 163
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.283,
+      "step": 164
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.84515363030414e-06,
+      "loss": 0.2383,
+      "step": 165
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.735732216601538e-06,
+      "loss": 0.1921,
+      "step": 166
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.626464421815919e-06,
+      "loss": 0.2585,
+      "step": 167
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.51736352288158e-06,
+      "loss": 0.2201,
+      "step": 168
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.408442776453606e-06,
+      "loss": 0.2088,
+      "step": 169
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.299715417297072e-06,
+      "loss": 0.1736,
+      "step": 170
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.191194656678905e-06,
+      "loss": 0.2028,
+      "step": 171
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 8.082893680762619e-06,
+      "loss": 0.2331,
+      "step": 172
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.974825649006082e-06,
+      "loss": 0.2313,
+      "step": 173
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.867003692562533e-06,
+      "loss": 0.3048,
+      "step": 174
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.759440912685043e-06,
+      "loss": 0.2014,
+      "step": 175
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.652150379134593e-06,
+      "loss": 0.2098,
+      "step": 176
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.2076,
+      "step": 177
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.438438163073884e-06,
+      "loss": 0.1652,
+      "step": 178
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.3320424483527385e-06,
+      "loss": 0.1559,
+      "step": 179
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.225970912381557e-06,
+      "loss": 0.2062,
+      "step": 180
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.120236443722941e-06,
+      "loss": 0.2017,
+      "step": 181
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.014851889983058e-06,
+      "loss": 0.1794,
+      "step": 182
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.1932,
+      "step": 183
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.80518370354052e-06,
+      "loss": 0.2138,
+      "step": 184
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.700925547244173e-06,
+      "loss": 0.1776,
+      "step": 185
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.59706825558357e-06,
+      "loss": 0.1961,
+      "step": 186
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.4936244480724575e-06,
+      "loss": 0.2006,
+      "step": 187
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.3906066939828546e-06,
+      "loss": 0.263,
+      "step": 188
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.2880275108177915e-06,
+      "loss": 0.201,
+      "step": 189
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.18589936279034e-06,
+      "loss": 0.1588,
+      "step": 190
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 6.084234659309088e-06,
+      "loss": 0.216,
+      "step": 191
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.1918,
+      "step": 192
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.8823449405569525e-06,
+      "loss": 0.184,
+      "step": 193
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.782144456544681e-06,
+      "loss": 0.1564,
+      "step": 194
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.6824564766150724e-06,
+      "loss": 0.1936,
+      "step": 195
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.58329311367626e-06,
+      "loss": 0.1495,
+      "step": 196
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.484666416891109e-06,
+      "loss": 0.2793,
+      "step": 197
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.386588370213124e-06,
+      "loss": 0.1719,
+      "step": 198
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.289070890930328e-06,
+      "loss": 0.194,
+      "step": 199
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.192125828217203e-06,
+      "loss": 0.1358,
+      "step": 200
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.095764961694923e-06,
+      "loss": 0.16,
+      "step": 201
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1797,
+      "step": 202
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.904842579361653e-06,
+      "loss": 0.1968,
+      "step": 203
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.8103042621878515e-06,
+      "loss": 0.1639,
+      "step": 204
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.716396535660412e-06,
+      "loss": 0.1747,
+      "step": 205
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.623130810339219e-06,
+      "loss": 0.2478,
+      "step": 206
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.1603,
+      "step": 207
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.438570614135994e-06,
+      "loss": 0.1551,
+      "step": 208
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.347298568833281e-06,
+      "loss": 0.1762,
+      "step": 209
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 4.256713373170565e-06,
+      "loss": 0.1881,
+      "step": 210
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.166826033992939e-06,
+      "loss": 0.1405,
+      "step": 211
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.077647473350201e-06,
+      "loss": 0.1996,
+      "step": 212
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.989188527169749e-06,
+      "loss": 0.1252,
+      "step": 213
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.90145994393991e-06,
+      "loss": 0.1156,
+      "step": 214
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 3.8144723834039076e-06,
+      "loss": 0.1462,
+      "step": 215
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.72823641526463e-06,
+      "loss": 0.2174,
+      "step": 216
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.6427625179003223e-06,
+      "loss": 0.2678,
+      "step": 217
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.5580610770913593e-06,
+      "loss": 0.1681,
+      "step": 218
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.4741423847583134e-06,
+      "loss": 0.2125,
+      "step": 219
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.3910166377113894e-06,
+      "loss": 0.1816,
+      "step": 220
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.1421,
+      "step": 221
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.1898,
+      "step": 222
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.1464975837970035e-06,
+      "loss": 0.1321,
+      "step": 223
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.0666436406712485e-06,
+      "loss": 0.1529,
+      "step": 224
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9876321572751143e-06,
+      "loss": 0.1399,
+      "step": 225
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.9094727341526275e-06,
+      "loss": 0.1596,
+      "step": 226
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.8321748683154893e-06,
+      "loss": 0.1354,
+      "step": 227
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.7557479520891104e-06,
+      "loss": 0.1474,
+      "step": 228
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.680201271971383e-06,
+      "loss": 0.1558,
+      "step": 229
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.6055440075042793e-06,
+      "loss": 0.1595,
+      "step": 230
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.5317852301584642e-06,
+      "loss": 0.1791,
+      "step": 231
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.4589339022310386e-06,
+      "loss": 0.1387,
+      "step": 232
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.386998875756554e-06,
+      "loss": 0.1032,
+      "step": 233
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.315988891431412e-06,
+      "loss": 0.1711,
+      "step": 234
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.2459125775517854e-06,
+      "loss": 0.1274,
+      "step": 235
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.1767784489652345e-06,
+      "loss": 0.1584,
+      "step": 236
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.1374,
+      "step": 237
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0413702336246156e-06,
+      "loss": 0.1403,
+      "step": 238
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.97511260008059e-06,
+      "loss": 0.1533,
+      "step": 239
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1528,
+      "step": 240
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.8455305344995523e-06,
+      "loss": 0.1275,
+      "step": 241
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.7822218477475496e-06,
+      "loss": 0.209,
+      "step": 242
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7199116885197996e-06,
+      "loss": 0.1208,
+      "step": 243
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.6586076280123032e-06,
+      "loss": 0.0937,
+      "step": 244
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5983171151717924e-06,
+      "loss": 0.1244,
+      "step": 245
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.5390474757906449e-06,
+      "loss": 0.1131,
+      "step": 246
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4808059116167306e-06,
+      "loss": 0.1315,
+      "step": 247
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.4235994994783297e-06,
+      "loss": 0.1891,
+      "step": 248
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.367435190424261e-06,
+      "loss": 0.1316,
+      "step": 249
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.3123198088792577e-06,
+      "loss": 0.155,
+      "step": 250
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.2582600518147448e-06,
+      "loss": 0.1472,
+      "step": 251
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.1732,
+      "step": 252
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1533335568795412e-06,
+      "loss": 0.1536,
+      "step": 253
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.1024795684395695e-06,
+      "loss": 0.1176,
+      "step": 254
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0527067017923654e-06,
+      "loss": 0.1502,
+      "step": 255
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.0040210047499289e-06,
+      "loss": 0.1859,
+      "step": 256
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.564283930242258e-07,
+      "loss": 0.1167,
+      "step": 257
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 9.09934649508375e-07,
+      "loss": 0.1391,
+      "step": 258
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.1438,
+      "step": 259
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 8.202662303847298e-07,
+      "loss": 0.1527,
+      "step": 260
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.771024502261526e-07,
+      "loss": 0.1238,
+      "step": 261
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.350593278519824e-07,
+      "loss": 0.1709,
+      "step": 262
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.941419718468168e-07,
+      "loss": 0.1836,
+      "step": 263
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.543553540053926e-07,
+      "loss": 0.1866,
+      "step": 264
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.157043087284797e-07,
+      "loss": 0.1365,
+      "step": 265
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.781935324354571e-07,
+      "loss": 0.1835,
+      "step": 266
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.1197,
+      "step": 267
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.066108791645407e-07,
+      "loss": 0.1345,
+      "step": 268
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.7254770006681105e-07,
+      "loss": 0.1644,
+      "step": 269
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.396421846564236e-07,
+      "loss": 0.1511,
+      "step": 270
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.078983312237017e-07,
+      "loss": 0.179,
+      "step": 271
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.773199969074959e-07,
+      "loss": 0.1191,
+      "step": 272
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.4791089722651437e-07,
+      "loss": 0.127,
+      "step": 273
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.1967460562785325e-07,
+      "loss": 0.1226,
+      "step": 274
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.926145530528002e-07,
+      "loss": 0.1787,
+      "step": 275
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.667340275199426e-07,
+      "loss": 0.1438,
+      "step": 276
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.420361737256438e-07,
+      "loss": 0.1226,
+      "step": 277
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.1422,
+      "step": 278
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.9620034125190645e-07,
+      "loss": 0.1451,
+      "step": 279
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.7506793200248507e-07,
+      "loss": 0.1726,
+      "step": 280
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.5512933267492813e-07,
+      "loss": 0.1418,
+      "step": 281
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.1239,
+      "step": 282
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 1.18843109247484e-07,
+      "loss": 0.1554,
+      "step": 283
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.0249989422169926e-07,
+      "loss": 0.1818,
+      "step": 284
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.735930673024806e-08,
+      "loss": 0.1633,
+      "step": 285
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.342318647883595e-08,
+      "loss": 0.1912,
+      "step": 286
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 6.069322682050516e-08,
+      "loss": 0.1301,
+      "step": 287
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.9170974549885844e-08,
+      "loss": 0.1728,
+      "step": 288
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.885782971524088e-08,
+      "loss": 0.1156,
+      "step": 289
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.9755045448351948e-08,
+      "loss": 0.1304,
+      "step": 290
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 2.1863727812254653e-08,
+      "loss": 0.1408,
+      "step": 291
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.518483566683826e-08,
+      "loss": 0.2036,
+      "step": 292
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 9.719180552341113e-09,
+      "loss": 0.1597,
+      "step": 293
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.467426590739511e-09,
+      "loss": 0.1618,
+      "step": 294
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.430090405054486e-09,
+      "loss": 0.1651,
+      "step": 295
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 6.075410565697937e-10,
+      "loss": 0.1322,
+      "step": 296
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1284,
+      "step": 297
+    },
+    {
+      "epoch": 3.0,
+      "step": 297,
+      "total_flos": 7.834692227086418e+17,
+      "train_loss": 0.27782333958329575,
+      "train_runtime": 6854.2409,
+      "train_samples_per_second": 5.521,
+      "train_steps_per_second": 0.043
+    }
+  ],
+  "max_steps": 297,
+  "num_train_epochs": 3,
+  "total_flos": 7.834692227086418e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88e487e3ec731ca0983617b8b7922fedadc7e30ccb71f07203cdc9e1a046b07
+size 4091