Upload folder using huggingface_hub

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "huggyllama/llama-7b",
+  "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": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e58fa21b802c1a0b2a0c75f37c266463af58b130387c328056d45fb5d21c2b
+size 13476859646

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b9ad91fdc9f51cd72e45ae3f5d5a2cec0ce89f50b969fac93276b158b69886
+size 9877989650

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa84aab9ba936e1d2ad2bfb3ab68920e0a803b0c7b7f6d4a7c7659a65967abb
+size 9894801206

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8658ec14f5fd9db2c4ae9773f8acd5078a09602a15a5484c91a7c83423099458
+size 7180990841

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953666560
+  },
+  "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 sha256:7e3c5cb412e12159a59afe5657ce4b5e0a06e7fb420bedbb5228fe1245702762
+size 14583

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741230672078323886b763e522c728741456a587860909fc529ce815a7aca5ec
+size 14583

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea587886b41579993bb5d20c79047b968ae2d71d22ba4c739b07ce31d7486a6
+size 14583

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab727740f74dd67e60283d27b4339609a1dda888b067cc06520e2f1d7dc17db
+size 14583

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e43b372746f1c43e6b8e3b0d9739066714de8bc4930ffc8a745bcec6595d691
+size 627

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": 2048,
+  "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 +1,2904 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6783216783216783,
+  "global_step": 480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 6.3448,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 6.3545,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 5.8293,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 5.7241,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 5.7151,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 5.759,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 5.7633,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 5.5305,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 5.9615,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 5.8986,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 5.9003,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 5.4062,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 5.8606,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 5.4724,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1538461538461538e-05,
+      "loss": 5.4155,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 5.1616,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3076923076923078e-05,
+      "loss": 5.0633,
+      "step": 17
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 5.918,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 5.4574,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 4.5698,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 4.9255,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 4.7709,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7692307692307694e-05,
+      "loss": 4.5418,
+      "step": 23
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 4.3907,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 3.796,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 3.9047,
+      "step": 26
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999928710990414e-05,
+      "loss": 3.6515,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999971484497808e-05,
+      "loss": 3.4483,
+      "step": 28
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999935840501225e-05,
+      "loss": 2.9432,
+      "step": 29
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9998859396174982e-05,
+      "loss": 2.694,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998217825581043e-05,
+      "loss": 2.9966,
+      "step": 31
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999743370237782e-05,
+      "loss": 2.437,
+      "step": 32
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996507037745184e-05,
+      "loss": 2.3988,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995437844895337e-05,
+      "loss": 2.1954,
+      "step": 34
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999422613907262e-05,
+      "loss": 2.0812,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992871937553292e-05,
+      "loss": 1.884,
+      "step": 36
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991375259645293e-05,
+      "loss": 1.8956,
+      "step": 37
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.998973612668796e-05,
+      "loss": 1.8294,
+      "step": 38
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987954562051724e-05,
+      "loss": 1.5839,
+      "step": 39
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986030591137785e-05,
+      "loss": 1.5102,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998396424137773e-05,
+      "loss": 1.3267,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9981755542233175e-05,
+      "loss": 1.1175,
+      "step": 42
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9979404525195313e-05,
+      "loss": 1.0045,
+      "step": 43
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9976911223784473e-05,
+      "loss": 0.846,
+      "step": 44
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9974275673549654e-05,
+      "loss": 0.7292,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9971497912068014e-05,
+      "loss": 0.613,
+      "step": 46
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9968577978944323e-05,
+      "loss": 0.5431,
+      "step": 47
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9965515915810408e-05,
+      "loss": 0.4976,
+      "step": 48
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9962311766324562e-05,
+      "loss": 0.4278,
+      "step": 49
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.995896557617091e-05,
+      "loss": 0.4254,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9955477393058774e-05,
+      "loss": 0.4062,
+      "step": 51
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 0.3502,
+      "step": 52
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9948075248918126e-05,
+      "loss": 0.3671,
+      "step": 53
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9944161393427923e-05,
+      "loss": 0.3904,
+      "step": 54
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9940105756054337e-05,
+      "loss": 0.3622,
+      "step": 55
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9935908394621844e-05,
+      "loss": 0.3523,
+      "step": 56
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9931569368975588e-05,
+      "loss": 0.3344,
+      "step": 57
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992708874098054e-05,
+      "loss": 0.3586,
+      "step": 58
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.992246657452061e-05,
+      "loss": 0.3559,
+      "step": 59
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9917702935497725e-05,
+      "loss": 0.3494,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991279789183091e-05,
+      "loss": 0.3458,
+      "step": 61
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.99077515134553e-05,
+      "loss": 0.3344,
+      "step": 62
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9902563872321174e-05,
+      "loss": 0.3354,
+      "step": 63
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9897235042392876e-05,
+      "loss": 0.3404,
+      "step": 64
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989176509964781e-05,
+      "loss": 0.3622,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9886154122075344e-05,
+      "loss": 0.3428,
+      "step": 66
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9880402189675677e-05,
+      "loss": 0.3557,
+      "step": 67
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9874509384458726e-05,
+      "loss": 0.3492,
+      "step": 68
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986847579044294e-05,
+      "loss": 0.3463,
+      "step": 69
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986230149365411e-05,
+      "loss": 0.3409,
+      "step": 70
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9855986582124128e-05,
+      "loss": 0.344,
+      "step": 71
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9849531145889758e-05,
+      "loss": 0.3085,
+      "step": 72
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9842935276991332e-05,
+      "loss": 0.332,
+      "step": 73
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983619906947144e-05,
+      "loss": 0.3198,
+      "step": 74
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.982932261937359e-05,
+      "loss": 0.331,
+      "step": 75
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9822306024740855e-05,
+      "loss": 0.3298,
+      "step": 76
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9815149385614446e-05,
+      "loss": 0.3223,
+      "step": 77
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 0.3082,
+      "step": 78
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.980041638402765e-05,
+      "loss": 0.342,
+      "step": 79
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9792840231627482e-05,
+      "loss": 0.3217,
+      "step": 80
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9785124454851082e-05,
+      "loss": 0.3222,
+      "step": 81
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977726916370847e-05,
+      "loss": 0.3533,
+      "step": 82
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9769274470198827e-05,
+      "loss": 0.3269,
+      "step": 83
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976114048830891e-05,
+      "loss": 0.3448,
+      "step": 84
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9752867334011422e-05,
+      "loss": 0.3524,
+      "step": 85
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974445512526336e-05,
+      "loss": 0.338,
+      "step": 86
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9735903982004324e-05,
+      "loss": 0.3146,
+      "step": 87
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9727214026154827e-05,
+      "loss": 0.3093,
+      "step": 88
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971838538161454e-05,
+      "loss": 0.3247,
+      "step": 89
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9709418174260523e-05,
+      "loss": 0.3215,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9700312531945444e-05,
+      "loss": 0.324,
+      "step": 91
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9691068584495744e-05,
+      "loss": 0.3608,
+      "step": 92
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.96816864637098e-05,
+      "loss": 0.3412,
+      "step": 93
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.967216630335603e-05,
+      "loss": 0.3461,
+      "step": 94
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9662508239170993e-05,
+      "loss": 0.3355,
+      "step": 95
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9652712408857452e-05,
+      "loss": 0.3223,
+      "step": 96
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9642778952082425e-05,
+      "loss": 0.3196,
+      "step": 97
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9632708010475166e-05,
+      "loss": 0.3386,
+      "step": 98
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9622499727625162e-05,
+      "loss": 0.3265,
+      "step": 99
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961215424908009e-05,
+      "loss": 0.3304,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9601671722343737e-05,
+      "loss": 0.33,
+      "step": 101
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.959105229687389e-05,
+      "loss": 0.3344,
+      "step": 102
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9580296124080215e-05,
+      "loss": 0.3304,
+      "step": 103
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 0.3467,
+      "step": 104
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.955837415190643e-05,
+      "loss": 0.3317,
+      "step": 105
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.954720866508546e-05,
+      "loss": 0.309,
+      "step": 106
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9535907056054475e-05,
+      "loss": 0.328,
+      "step": 107
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9524469485949586e-05,
+      "loss": 0.3443,
+      "step": 108
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9512896117845393e-05,
+      "loss": 0.3142,
+      "step": 109
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9501187116752694e-05,
+      "loss": 0.3182,
+      "step": 110
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.94893426496161e-05,
+      "loss": 0.3485,
+      "step": 111
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9477362885311684e-05,
+      "loss": 0.328,
+      "step": 112
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.946524799464455e-05,
+      "loss": 0.321,
+      "step": 113
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9452998150346403e-05,
+      "loss": 0.3118,
+      "step": 114
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9440613527073106e-05,
+      "loss": 0.3362,
+      "step": 115
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9428094301402164e-05,
+      "loss": 0.3339,
+      "step": 116
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.941544065183021e-05,
+      "loss": 0.328,
+      "step": 117
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9402652758770476e-05,
+      "loss": 0.3226,
+      "step": 118
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.938973080455021e-05,
+      "loss": 0.3083,
+      "step": 119
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9376674973408077e-05,
+      "loss": 0.3247,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9363485451491523e-05,
+      "loss": 0.3234,
+      "step": 121
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9350162426854152e-05,
+      "loss": 0.3004,
+      "step": 122
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9336706089452995e-05,
+      "loss": 0.3346,
+      "step": 123
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932311663114586e-05,
+      "loss": 0.3407,
+      "step": 124
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.930939424568854e-05,
+      "loss": 0.3201,
+      "step": 125
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9295539128732096e-05,
+      "loss": 0.3362,
+      "step": 126
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9281551477820038e-05,
+      "loss": 0.3295,
+      "step": 127
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9267431492385524e-05,
+      "loss": 0.3507,
+      "step": 128
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9253179373748504e-05,
+      "loss": 0.3482,
+      "step": 129
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.3215,
+      "step": 130
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9224279551563533e-05,
+      "loss": 0.3517,
+      "step": 131
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.920963226006352e-05,
+      "loss": 0.3089,
+      "step": 132
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.919485365945101e-05,
+      "loss": 0.3251,
+      "step": 133
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.917994396043636e-05,
+      "loss": 0.3404,
+      "step": 134
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9164903375599113e-05,
+      "loss": 0.3213,
+      "step": 135
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9149732119384942e-05,
+      "loss": 0.3384,
+      "step": 136
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9134430408102615e-05,
+      "loss": 0.3019,
+      "step": 137
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.91189984599209e-05,
+      "loss": 0.3008,
+      "step": 138
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9103436494865463e-05,
+      "loss": 0.3201,
+      "step": 139
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.908774473481571e-05,
+      "loss": 0.3281,
+      "step": 140
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.907192340350165e-05,
+      "loss": 0.3266,
+      "step": 141
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9055972726500696e-05,
+      "loss": 0.3099,
+      "step": 142
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9039892931234434e-05,
+      "loss": 0.3302,
+      "step": 143
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9023684246965407e-05,
+      "loss": 0.3064,
+      "step": 144
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9007346904793817e-05,
+      "loss": 0.3015,
+      "step": 145
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.899088113765426e-05,
+      "loss": 0.3221,
+      "step": 146
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.897428718031238e-05,
+      "loss": 0.2858,
+      "step": 147
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.895756526936153e-05,
+      "loss": 0.3266,
+      "step": 148
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8940715643219406e-05,
+      "loss": 0.3145,
+      "step": 149
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8923738542124644e-05,
+      "loss": 0.3107,
+      "step": 150
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8906634208133386e-05,
+      "loss": 0.3132,
+      "step": 151
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8889402885115834e-05,
+      "loss": 0.3041,
+      "step": 152
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8872044818752782e-05,
+      "loss": 0.3207,
+      "step": 153
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8854560256532098e-05,
+      "loss": 0.3468,
+      "step": 154
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8836949447745217e-05,
+      "loss": 0.3361,
+      "step": 155
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 0.3132,
+      "step": 156
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8801350096634946e-05,
+      "loss": 0.3392,
+      "step": 157
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8783362061880063e-05,
+      "loss": 0.2692,
+      "step": 158
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8765248795688726e-05,
+      "loss": 0.2989,
+      "step": 159
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8747010556316304e-05,
+      "loss": 0.3209,
+      "step": 160
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8728647603800004e-05,
+      "loss": 0.3125,
+      "step": 161
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8710160199955158e-05,
+      "loss": 0.2904,
+      "step": 162
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.869154860837151e-05,
+      "loss": 0.3057,
+      "step": 163
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8672813094409453e-05,
+      "loss": 0.3337,
+      "step": 164
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8653953925196225e-05,
+      "loss": 0.3283,
+      "step": 165
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.863497136962213e-05,
+      "loss": 0.3011,
+      "step": 166
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8615865698336683e-05,
+      "loss": 0.3222,
+      "step": 167
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8596637183744762e-05,
+      "loss": 0.3322,
+      "step": 168
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8577286100002723e-05,
+      "loss": 0.3321,
+      "step": 169
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8557812723014476e-05,
+      "loss": 0.3174,
+      "step": 170
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.853821733042758e-05,
+      "loss": 0.2946,
+      "step": 171
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.851850020162926e-05,
+      "loss": 0.2985,
+      "step": 172
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8498661617742426e-05,
+      "loss": 0.3402,
+      "step": 173
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8478701861621686e-05,
+      "loss": 0.3113,
+      "step": 174
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8458621217849285e-05,
+      "loss": 0.3225,
+      "step": 175
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8438419972731066e-05,
+      "loss": 0.3239,
+      "step": 176
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.841809841429238e-05,
+      "loss": 0.3042,
+      "step": 177
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8397656832273982e-05,
+      "loss": 0.3129,
+      "step": 178
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8377095518127896e-05,
+      "loss": 0.3148,
+      "step": 179
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8356414765013267e-05,
+      "loss": 0.3144,
+      "step": 180
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8335614867792183e-05,
+      "loss": 0.3121,
+      "step": 181
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 0.3249,
+      "step": 182
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8293658828968397e-05,
+      "loss": 0.2985,
+      "step": 183
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8272503285566587e-05,
+      "loss": 0.3251,
+      "step": 184
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.825122979445157e-05,
+      "loss": 0.3253,
+      "step": 185
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.3189,
+      "step": 186
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.820833018401215e-05,
+      "loss": 0.3205,
+      "step": 187
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.81867046763419e-05,
+      "loss": 0.2983,
+      "step": 188
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8164962444258016e-05,
+      "loss": 0.2948,
+      "step": 189
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8143103797756942e-05,
+      "loss": 0.2961,
+      "step": 190
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.812112904849492e-05,
+      "loss": 0.2914,
+      "step": 191
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8099038509783586e-05,
+      "loss": 0.3055,
+      "step": 192
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.807683249658545e-05,
+      "loss": 0.306,
+      "step": 193
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.805451132550946e-05,
+      "loss": 0.3117,
+      "step": 194
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.803207531480645e-05,
+      "loss": 0.3164,
+      "step": 195
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.8009524784364615e-05,
+      "loss": 0.322,
+      "step": 196
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7986860055704952e-05,
+      "loss": 0.3073,
+      "step": 197
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7964081451976673e-05,
+      "loss": 0.3275,
+      "step": 198
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7941189297952598e-05,
+      "loss": 0.3176,
+      "step": 199
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.791818392002452e-05,
+      "loss": 0.3147,
+      "step": 200
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7895065646198567e-05,
+      "loss": 0.2904,
+      "step": 201
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7871834806090502e-05,
+      "loss": 0.3099,
+      "step": 202
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7848491730921046e-05,
+      "loss": 0.2985,
+      "step": 203
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7825036753511143e-05,
+      "loss": 0.32,
+      "step": 204
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.780147020827721e-05,
+      "loss": 0.3185,
+      "step": 205
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7777792431226384e-05,
+      "loss": 0.3074,
+      "step": 206
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7754003759951714e-05,
+      "loss": 0.3202,
+      "step": 207
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 0.3039,
+      "step": 208
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7706095093003787e-05,
+      "loss": 0.3006,
+      "step": 209
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7681975780402807e-05,
+      "loss": 0.3183,
+      "step": 210
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7657746939712817e-05,
+      "loss": 0.3519,
+      "step": 211
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7633408916383826e-05,
+      "loss": 0.3174,
+      "step": 212
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.760896205742255e-05,
+      "loss": 0.2977,
+      "step": 213
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7584406711387462e-05,
+      "loss": 0.2996,
+      "step": 214
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.755974322838382e-05,
+      "loss": 0.313,
+      "step": 215
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7534971960058684e-05,
+      "loss": 0.304,
+      "step": 216
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7510093259595887e-05,
+      "loss": 0.2892,
+      "step": 217
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.3173,
+      "step": 218
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7460014982646334e-05,
+      "loss": 0.3111,
+      "step": 219
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.743481612016573e-05,
+      "loss": 0.3033,
+      "step": 220
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7409511253549592e-05,
+      "loss": 0.3089,
+      "step": 221
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7384100743589698e-05,
+      "loss": 0.306,
+      "step": 222
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.735858495258406e-05,
+      "loss": 0.3195,
+      "step": 223
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.733296424433178e-05,
+      "loss": 0.3039,
+      "step": 224
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7307238984127832e-05,
+      "loss": 0.3149,
+      "step": 225
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7281409538757886e-05,
+      "loss": 0.329,
+      "step": 226
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7255476276493057e-05,
+      "loss": 0.2977,
+      "step": 227
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.722943956708466e-05,
+      "loss": 0.3077,
+      "step": 228
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.720329978175894e-05,
+      "loss": 0.3393,
+      "step": 229
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7177057293211786e-05,
+      "loss": 0.3094,
+      "step": 230
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.715071247560339e-05,
+      "loss": 0.303,
+      "step": 231
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7124265704552948e-05,
+      "loss": 0.301,
+      "step": 232
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7097717357133286e-05,
+      "loss": 0.3235,
+      "step": 233
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.3173,
+      "step": 234
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.704431744871346e-05,
+      "loss": 0.2904,
+      "step": 235
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.701746664907862e-05,
+      "loss": 0.305,
+      "step": 236
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6990515795794332e-05,
+      "loss": 0.3235,
+      "step": 237
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.696346527312053e-05,
+      "loss": 0.3007,
+      "step": 238
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6936315466738204e-05,
+      "loss": 0.3199,
+      "step": 239
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6909066763743914e-05,
+      "loss": 0.3113,
+      "step": 240
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6881719552644275e-05,
+      "loss": 0.2918,
+      "step": 241
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.68542742233504e-05,
+      "loss": 0.2935,
+      "step": 242
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.682673116717236e-05,
+      "loss": 0.2945,
+      "step": 243
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6799090776813597e-05,
+      "loss": 0.3153,
+      "step": 244
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.677135344636532e-05,
+      "loss": 0.3163,
+      "step": 245
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.674351957130089e-05,
+      "loss": 0.2929,
+      "step": 246
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6715589548470187e-05,
+      "loss": 0.3227,
+      "step": 247
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6687563776093943e-05,
+      "loss": 0.2947,
+      "step": 248
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6659442653758064e-05,
+      "loss": 0.3437,
+      "step": 249
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 0.3386,
+      "step": 250
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.660291596434276e-05,
+      "loss": 0.3186,
+      "step": 251
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6574511203209667e-05,
+      "loss": 0.3302,
+      "step": 252
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.654601270399814e-05,
+      "loss": 0.3249,
+      "step": 253
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.651742087303412e-05,
+      "loss": 0.3012,
+      "step": 254
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.648873611797429e-05,
+      "loss": 0.2925,
+      "step": 255
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.645995884780019e-05,
+      "loss": 0.3111,
+      "step": 256
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6431089472812445e-05,
+      "loss": 0.3074,
+      "step": 257
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.640212840462488e-05,
+      "loss": 0.3157,
+      "step": 258
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6373076056158676e-05,
+      "loss": 0.3237,
+      "step": 259
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 0.2834,
+      "step": 260
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6314699176576404e-05,
+      "loss": 0.3072,
+      "step": 261
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6285375477786322e-05,
+      "loss": 0.2928,
+      "step": 262
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.62559621633577e-05,
+      "loss": 0.3005,
+      "step": 263
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6226459652659752e-05,
+      "loss": 0.3014,
+      "step": 264
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.619686836633343e-05,
+      "loss": 0.3053,
+      "step": 265
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6167188726285433e-05,
+      "loss": 0.3024,
+      "step": 266
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6137421155682186e-05,
+      "loss": 0.3018,
+      "step": 267
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6107566078943818e-05,
+      "loss": 0.3139,
+      "step": 268
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6077623921738102e-05,
+      "loss": 0.2872,
+      "step": 269
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6047595110974376e-05,
+      "loss": 0.2917,
+      "step": 270
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6017480074797484e-05,
+      "loss": 0.2947,
+      "step": 271
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.598727924258164e-05,
+      "loss": 0.2684,
+      "step": 272
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5956993044924334e-05,
+      "loss": 0.3185,
+      "step": 273
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.592662191364017e-05,
+      "loss": 0.3205,
+      "step": 274
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.589616628175472e-05,
+      "loss": 0.304,
+      "step": 275
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5865626583498355e-05,
+      "loss": 0.2973,
+      "step": 276
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5835003254300038e-05,
+      "loss": 0.3054,
+      "step": 277
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5804296730781134e-05,
+      "loss": 0.3002,
+      "step": 278
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5773507450749172e-05,
+      "loss": 0.3246,
+      "step": 279
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.574263585319161e-05,
+      "loss": 0.2929,
+      "step": 280
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5711682378269567e-05,
+      "loss": 0.3271,
+      "step": 281
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.568064746731156e-05,
+      "loss": 0.3068,
+      "step": 282
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.56495315628072e-05,
+      "loss": 0.2965,
+      "step": 283
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5618335108400893e-05,
+      "loss": 0.3142,
+      "step": 284
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5587058548885505e-05,
+      "loss": 0.3324,
+      "step": 285
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 0.3296,
+      "step": 286
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.301243394613266,
+      "eval_runtime": 40.9753,
+      "eval_samples_per_second": 18.231,
+      "eval_steps_per_second": 0.586,
+      "step": 286
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5524266899403206e-05,
+      "loss": 0.256,
+      "step": 287
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5492752704707198e-05,
+      "loss": 0.2517,
+      "step": 288
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.546116019543115e-05,
+      "loss": 0.2426,
+      "step": 289
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.542948982201479e-05,
+      "loss": 0.236,
+      "step": 290
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5397742036008033e-05,
+      "loss": 0.2415,
+      "step": 291
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.536591729006453e-05,
+      "loss": 0.2506,
+      "step": 292
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5334016037935197e-05,
+      "loss": 0.2427,
+      "step": 293
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.530203873446177e-05,
+      "loss": 0.2154,
+      "step": 294
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.526998583557031e-05,
+      "loss": 0.2462,
+      "step": 295
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5237857798264701e-05,
+      "loss": 0.2327,
+      "step": 296
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.520565508062013e-05,
+      "loss": 0.2352,
+      "step": 297
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5173378141776569e-05,
+      "loss": 0.2478,
+      "step": 298
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5141027441932217e-05,
+      "loss": 0.2364,
+      "step": 299
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5108603442336949e-05,
+      "loss": 0.2393,
+      "step": 300
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5076106605285725e-05,
+      "loss": 0.25,
+      "step": 301
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5043537394112008e-05,
+      "loss": 0.2348,
+      "step": 302
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5010896273181166e-05,
+      "loss": 0.2279,
+      "step": 303
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4978183707883828e-05,
+      "loss": 0.2225,
+      "step": 304
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4945400164629277e-05,
+      "loss": 0.2349,
+      "step": 305
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4912546110838775e-05,
+      "loss": 0.24,
+      "step": 306
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4879622014938914e-05,
+      "loss": 0.2254,
+      "step": 307
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4846628346354934e-05,
+      "loss": 0.2321,
+      "step": 308
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4813565575504023e-05,
+      "loss": 0.2375,
+      "step": 309
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4780434173788617e-05,
+      "loss": 0.2294,
+      "step": 310
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4747234613589688e-05,
+      "loss": 0.2424,
+      "step": 311
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 0.2402,
+      "step": 312
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4680632912117287e-05,
+      "loss": 0.2424,
+      "step": 313
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4647231720437687e-05,
+      "loss": 0.2394,
+      "step": 314
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4613764269448752e-05,
+      "loss": 0.254,
+      "step": 315
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.458023103632277e-05,
+      "loss": 0.2367,
+      "step": 316
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4546632499169938e-05,
+      "loss": 0.2392,
+      "step": 317
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4512969137031538e-05,
+      "loss": 0.2214,
+      "step": 318
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4479241429873121e-05,
+      "loss": 0.2439,
+      "step": 319
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.444544985857766e-05,
+      "loss": 0.2445,
+      "step": 320
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4411594904938682e-05,
+      "loss": 0.241,
+      "step": 321
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4377677051653404e-05,
+      "loss": 0.2244,
+      "step": 322
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.434369678231587e-05,
+      "loss": 0.245,
+      "step": 323
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4309654581410024e-05,
+      "loss": 0.2158,
+      "step": 324
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4275550934302822e-05,
+      "loss": 0.2378,
+      "step": 325
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4241386327237312e-05,
+      "loss": 0.2303,
+      "step": 326
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.420716124732569e-05,
+      "loss": 0.2329,
+      "step": 327
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4172876182542372e-05,
+      "loss": 0.2388,
+      "step": 328
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4138531621717018e-05,
+      "loss": 0.2242,
+      "step": 329
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.410412805452757e-05,
+      "loss": 0.2396,
+      "step": 330
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4069665971493276e-05,
+      "loss": 0.244,
+      "step": 331
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4035145863967692e-05,
+      "loss": 0.2335,
+      "step": 332
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4000568224131672e-05,
+      "loss": 0.2326,
+      "step": 333
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3965933544986351e-05,
+      "loss": 0.2299,
+      "step": 334
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3931242320346132e-05,
+      "loss": 0.2377,
+      "step": 335
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3896495044831622e-05,
+      "loss": 0.2347,
+      "step": 336
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3861692213862585e-05,
+      "loss": 0.23,
+      "step": 337
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.2336,
+      "step": 338
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3791921871193456e-05,
+      "loss": 0.2382,
+      "step": 339
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3756955354265085e-05,
+      "loss": 0.2595,
+      "step": 340
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3721935271411464e-05,
+      "loss": 0.2497,
+      "step": 341
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.368686212194199e-05,
+      "loss": 0.2245,
+      "step": 342
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.3651736405922686e-05,
+      "loss": 0.2213,
+      "step": 343
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.361655862416905e-05,
+      "loss": 0.2231,
+      "step": 344
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3581329278238928e-05,
+      "loss": 0.2354,
+      "step": 345
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.2328,
+      "step": 346
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3510717903749402e-05,
+      "loss": 0.2189,
+      "step": 347
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3475336881952988e-05,
+      "loss": 0.248,
+      "step": 348
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3439906309491713e-05,
+      "loss": 0.2427,
+      "step": 349
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.340442669152766e-05,
+      "loss": 0.2249,
+      "step": 350
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3368898533922202e-05,
+      "loss": 0.2513,
+      "step": 351
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3333322343228763e-05,
+      "loss": 0.2323,
+      "step": 352
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3297698626685631e-05,
+      "loss": 0.231,
+      "step": 353
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3262027892208696e-05,
+      "loss": 0.24,
+      "step": 354
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3226310648384222e-05,
+      "loss": 0.2334,
+      "step": 355
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.31905474044616e-05,
+      "loss": 0.246,
+      "step": 356
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.315473867034608e-05,
+      "loss": 0.2309,
+      "step": 357
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.311888495659149e-05,
+      "loss": 0.2425,
+      "step": 358
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3082986774392992e-05,
+      "loss": 0.2362,
+      "step": 359
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3047044635579748e-05,
+      "loss": 0.2358,
+      "step": 360
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3011059052607657e-05,
+      "loss": 0.2245,
+      "step": 361
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.297503053855203e-05,
+      "loss": 0.2274,
+      "step": 362
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2938959607100288e-05,
+      "loss": 0.2404,
+      "step": 363
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 0.2283,
+      "step": 364
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2866692549774683e-05,
+      "loss": 0.2378,
+      "step": 365
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2830497454270206e-05,
+      "loss": 0.2299,
+      "step": 366
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2794262002093698e-05,
+      "loss": 0.2334,
+      "step": 367
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2757986709883059e-05,
+      "loss": 0.2416,
+      "step": 368
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2721672094844221e-05,
+      "loss": 0.2301,
+      "step": 369
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.2685318674743769e-05,
+      "loss": 0.2263,
+      "step": 370
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2648926967901567e-05,
+      "loss": 0.231,
+      "step": 371
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2612497493183365e-05,
+      "loss": 0.2387,
+      "step": 372
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2576030769993393e-05,
+      "loss": 0.2397,
+      "step": 373
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2539527318266971e-05,
+      "loss": 0.2244,
+      "step": 374
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2502987658463077e-05,
+      "loss": 0.2308,
+      "step": 375
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2466412311556952e-05,
+      "loss": 0.238,
+      "step": 376
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.242980179903264e-05,
+      "loss": 0.2455,
+      "step": 377
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2393156642875579e-05,
+      "loss": 0.2362,
+      "step": 378
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2356477365565147e-05,
+      "loss": 0.2286,
+      "step": 379
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2319764490067212e-05,
+      "loss": 0.2353,
+      "step": 380
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.2283018539826686e-05,
+      "loss": 0.2215,
+      "step": 381
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2246240038760042e-05,
+      "loss": 0.2211,
+      "step": 382
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2209429511247865e-05,
+      "loss": 0.226,
+      "step": 383
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.217258748212737e-05,
+      "loss": 0.2359,
+      "step": 384
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2135714476684902e-05,
+      "loss": 0.2251,
+      "step": 385
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2098811020648475e-05,
+      "loss": 0.2377,
+      "step": 386
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.2061877640180255e-05,
+      "loss": 0.2235,
+      "step": 387
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.2024914861869064e-05,
+      "loss": 0.2436,
+      "step": 388
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1987923212722872e-05,
+      "loss": 0.2262,
+      "step": 389
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 0.2168,
+      "step": 390
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1913855412008025e-05,
+      "loss": 0.2366,
+      "step": 391
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1876780316483401e-05,
+      "loss": 0.2478,
+      "step": 392
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1839678462196785e-05,
+      "loss": 0.2349,
+      "step": 393
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.180255037813906e-05,
+      "loss": 0.2293,
+      "step": 394
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1765396593675098e-05,
+      "loss": 0.2381,
+      "step": 395
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1728217638536196e-05,
+      "loss": 0.2567,
+      "step": 396
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1691014042812537e-05,
+      "loss": 0.2463,
+      "step": 397
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1653786336945614e-05,
+      "loss": 0.2293,
+      "step": 398
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1616535051720686e-05,
+      "loss": 0.2422,
+      "step": 399
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1579260718259197e-05,
+      "loss": 0.2443,
+      "step": 400
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.1541963868011212e-05,
+      "loss": 0.2423,
+      "step": 401
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1504645032747832e-05,
+      "loss": 0.2475,
+      "step": 402
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1467304744553618e-05,
+      "loss": 0.2264,
+      "step": 403
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1429943535819005e-05,
+      "loss": 0.2289,
+      "step": 404
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1392561939232707e-05,
+      "loss": 0.2275,
+      "step": 405
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1355160487774119e-05,
+      "loss": 0.2271,
+      "step": 406
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1317739714705732e-05,
+      "loss": 0.2301,
+      "step": 407
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.128030015356551e-05,
+      "loss": 0.2282,
+      "step": 408
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.124284233815931e-05,
+      "loss": 0.2382,
+      "step": 409
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1205366802553231e-05,
+      "loss": 0.245,
+      "step": 410
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1167874081066046e-05,
+      "loss": 0.231,
+      "step": 411
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1130364708261552e-05,
+      "loss": 0.2351,
+      "step": 412
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1092839218940949e-05,
+      "loss": 0.2352,
+      "step": 413
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1055298148135236e-05,
+      "loss": 0.2297,
+      "step": 414
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1017742031097562e-05,
+      "loss": 0.225,
+      "step": 415
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 0.2324,
+      "step": 416
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.094258680040394e-05,
+      "loss": 0.2435,
+      "step": 417
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.090498875829638e-05,
+      "loss": 0.2341,
+      "step": 418
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0867377813038367e-05,
+      "loss": 0.2323,
+      "step": 419
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0829754500879308e-05,
+      "loss": 0.2324,
+      "step": 420
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.079211935824494e-05,
+      "loss": 0.2287,
+      "step": 421
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0754472921729661e-05,
+      "loss": 0.2339,
+      "step": 422
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0716815728088911e-05,
+      "loss": 0.2426,
+      "step": 423
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0679148314231504e-05,
+      "loss": 0.2523,
+      "step": 424
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0641471217211959e-05,
+      "loss": 0.2467,
+      "step": 425
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0603784974222862e-05,
+      "loss": 0.2384,
+      "step": 426
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.05660901225872e-05,
+      "loss": 0.2311,
+      "step": 427
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0528387199750706e-05,
+      "loss": 0.2375,
+      "step": 428
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0490676743274181e-05,
+      "loss": 0.2319,
+      "step": 429
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0452959290825846e-05,
+      "loss": 0.223,
+      "step": 430
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0415235380173663e-05,
+      "loss": 0.2497,
+      "step": 431
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.0377505549177683e-05,
+      "loss": 0.2572,
+      "step": 432
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.033977033578236e-05,
+      "loss": 0.2269,
+      "step": 433
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.030203027800889e-05,
+      "loss": 0.2383,
+      "step": 434
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0264285913947545e-05,
+      "loss": 0.2434,
+      "step": 435
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0226537781749988e-05,
+      "loss": 0.2184,
+      "step": 436
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0188786419621613e-05,
+      "loss": 0.2272,
+      "step": 437
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.015103236581386e-05,
+      "loss": 0.2362,
+      "step": 438
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.0113276158616555e-05,
+      "loss": 0.2336,
+      "step": 439
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0075518336350218e-05,
+      "loss": 0.2342,
+      "step": 440
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.0037759437358398e-05,
+      "loss": 0.2301,
+      "step": 441
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1e-05,
+      "loss": 0.2445,
+      "step": 442
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.962240562641602e-06,
+      "loss": 0.2292,
+      "step": 443
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.924481663649785e-06,
+      "loss": 0.236,
+      "step": 444
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.886723841383447e-06,
+      "loss": 0.236,
+      "step": 445
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.848967634186142e-06,
+      "loss": 0.2292,
+      "step": 446
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.811213580378389e-06,
+      "loss": 0.2351,
+      "step": 447
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.773462218250014e-06,
+      "loss": 0.2272,
+      "step": 448
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.735714086052458e-06,
+      "loss": 0.248,
+      "step": 449
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.697969721991114e-06,
+      "loss": 0.2421,
+      "step": 450
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.660229664217644e-06,
+      "loss": 0.2322,
+      "step": 451
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.62249445082232e-06,
+      "loss": 0.2393,
+      "step": 452
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.584764619826339e-06,
+      "loss": 0.2368,
+      "step": 453
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.547040709174159e-06,
+      "loss": 0.2274,
+      "step": 454
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.50932325672582e-06,
+      "loss": 0.228,
+      "step": 455
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.471612800249295e-06,
+      "loss": 0.2388,
+      "step": 456
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.433909877412801e-06,
+      "loss": 0.2501,
+      "step": 457
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.39621502577714e-06,
+      "loss": 0.2353,
+      "step": 458
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.358528782788045e-06,
+      "loss": 0.2394,
+      "step": 459
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.320851685768498e-06,
+      "loss": 0.2354,
+      "step": 460
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.28318427191109e-06,
+      "loss": 0.251,
+      "step": 461
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.24552707827034e-06,
+      "loss": 0.2306,
+      "step": 462
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.207880641755065e-06,
+      "loss": 0.2397,
+      "step": 463
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.170245499120694e-06,
+      "loss": 0.2174,
+      "step": 464
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.132622186961637e-06,
+      "loss": 0.2045,
+      "step": 465
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.095011241703623e-06,
+      "loss": 0.2372,
+      "step": 466
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 9.057413199596066e-06,
+      "loss": 0.2527,
+      "step": 467
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 0.2497,
+      "step": 468
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.982257968902438e-06,
+      "loss": 0.2511,
+      "step": 469
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.944701851864767e-06,
+      "loss": 0.2455,
+      "step": 470
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.907160781059053e-06,
+      "loss": 0.2305,
+      "step": 471
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.869635291738452e-06,
+      "loss": 0.2327,
+      "step": 472
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.832125918933955e-06,
+      "loss": 0.2469,
+      "step": 473
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.79463319744677e-06,
+      "loss": 0.2562,
+      "step": 474
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.757157661840693e-06,
+      "loss": 0.2452,
+      "step": 475
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.719699846434493e-06,
+      "loss": 0.226,
+      "step": 476
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.682260285294272e-06,
+      "loss": 0.2434,
+      "step": 477
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.644839512225886e-06,
+      "loss": 0.2321,
+      "step": 478
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.607438060767296e-06,
+      "loss": 0.2233,
+      "step": 479
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.570056464180998e-06,
+      "loss": 0.2311,
+      "step": 480
+    }
+  ],
+  "max_steps": 858,
+  "num_train_epochs": 3,
+  "total_flos": 1.2217975017622733e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad37d6021448042f80ac382a39a9060255e5455ef072913943d8baae0d450b7
+size 3707