Training in progress, step 500

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-500/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

checkpoint-500/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2523108b68eebcb4bd6aee3eac0da01da4e12659b2ef0e6905a8fa1201a654f2
+size 13476876030

checkpoint-500/pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212b8ae977e9a2ce54cfa859ad06a565be4dd09f1b18f19882186bf85fb1b5b8
+size 9878006034

checkpoint-500/pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425f5339e90b5292669df59af4080d3298fedbcaac5eb890d48add653656846e
+size 9894801206

checkpoint-500/pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82fdd32d48d2fe40a5644ab93c53be9b0941cb398618b4bf34c3f92c06f4d21
+size 7181007225

checkpoint-500/pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953699328
+  },
+  "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"
+  }
+}

checkpoint-500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
+size 14583

checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
+size 14583

checkpoint-500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
+size 14583

checkpoint-500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
+size 14583

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5167f88af64ce34a6729ed6f08c193f36406df493c8a4619b5e8d4e9c94c890d
+size 627

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

checkpoint-500/tokenizer.model

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 1024,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
+  "tokenizer_class": "LLaMATokenizer",
+  "unk_token": ""
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,3016 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32674399607907206,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.4492753623188408e-07,
+      "loss": 2.5958,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.8985507246376816e-07,
+      "loss": 2.4792,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 1.9376,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 2.0731,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.246376811594204e-07,
+      "loss": 1.7538,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.8296,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0144927536231885e-06,
+      "loss": 1.9283,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 1.8517,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 1.7672,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 1.7437,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5942028985507246e-06,
+      "loss": 1.7038,
+      "step": 11
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 2.0155,
+      "step": 12
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.884057971014493e-06,
+      "loss": 2.0078,
+      "step": 13
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 1.9901,
+      "step": 14
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 1.7954,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 1.7183,
+      "step": 16
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4637681159420295e-06,
+      "loss": 1.842,
+      "step": 17
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.7957,
+      "step": 18
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.7536231884057974e-06,
+      "loss": 1.7775,
+      "step": 19
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 1.8612,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 1.68,
+      "step": 21
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 1.928,
+      "step": 22
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7262,
+      "step": 23
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.9312,
+      "step": 24
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6231884057971017e-06,
+      "loss": 1.9374,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 1.5449,
+      "step": 26
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 1.7894,
+      "step": 27
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 2.0061,
+      "step": 28
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.202898550724638e-06,
+      "loss": 1.775,
+      "step": 29
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.856,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.492753623188406e-06,
+      "loss": 1.7222,
+      "step": 31
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 2.0042,
+      "step": 32
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 1.7216,
+      "step": 33
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 1.6443,
+      "step": 34
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.072463768115943e-06,
+      "loss": 1.6971,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.7971,
+      "step": 36
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.362318840579711e-06,
+      "loss": 1.771,
+      "step": 37
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 1.7365,
+      "step": 38
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 1.9443,
+      "step": 39
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.797101449275363e-06,
+      "loss": 1.8931,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.942028985507247e-06,
+      "loss": 1.7748,
+      "step": 41
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 1.8616,
+      "step": 42
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.2318840579710145e-06,
+      "loss": 1.8224,
+      "step": 43
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.376811594202898e-06,
+      "loss": 1.5656,
+      "step": 44
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 1.6967,
+      "step": 45
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7999,
+      "step": 46
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.811594202898551e-06,
+      "loss": 1.7706,
+      "step": 47
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 1.732,
+      "step": 48
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.10144927536232e-06,
+      "loss": 1.9167,
+      "step": 49
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 1.7641,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 1.5833,
+      "step": 51
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.536231884057972e-06,
+      "loss": 1.7085,
+      "step": 52
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.681159420289856e-06,
+      "loss": 1.7761,
+      "step": 53
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 1.7624,
+      "step": 54
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.971014492753623e-06,
+      "loss": 1.7813,
+      "step": 55
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.115942028985508e-06,
+      "loss": 1.6884,
+      "step": 56
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 1.7478,
+      "step": 57
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 1.6749,
+      "step": 58
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.55072463768116e-06,
+      "loss": 1.5301,
+      "step": 59
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 1.6166,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.840579710144929e-06,
+      "loss": 1.5818,
+      "step": 61
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 1.7006,
+      "step": 62
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 1.7545,
+      "step": 63
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 1.7942,
+      "step": 64
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.420289855072464e-06,
+      "loss": 1.8001,
+      "step": 65
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 1.8964,
+      "step": 66
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.710144927536233e-06,
+      "loss": 1.8787,
+      "step": 67
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 1.6214,
+      "step": 68
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 1.7235,
+      "step": 69
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0144927536231885e-05,
+      "loss": 1.6727,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0289855072463768e-05,
+      "loss": 1.5962,
+      "step": 71
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 1.5443,
+      "step": 72
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0579710144927538e-05,
+      "loss": 1.8079,
+      "step": 73
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0724637681159422e-05,
+      "loss": 1.7635,
+      "step": 74
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 1.6006,
+      "step": 75
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.101449275362319e-05,
+      "loss": 1.8047,
+      "step": 76
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1159420289855074e-05,
+      "loss": 1.7687,
+      "step": 77
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 1.6998,
+      "step": 78
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1449275362318842e-05,
+      "loss": 1.717,
+      "step": 79
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1594202898550726e-05,
+      "loss": 1.6178,
+      "step": 80
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1739130434782611e-05,
+      "loss": 1.9585,
+      "step": 81
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1884057971014494e-05,
+      "loss": 1.6892,
+      "step": 82
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2028985507246379e-05,
+      "loss": 1.6169,
+      "step": 83
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 2.0966,
+      "step": 84
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2318840579710144e-05,
+      "loss": 2.0971,
+      "step": 85
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2463768115942029e-05,
+      "loss": 1.6939,
+      "step": 86
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2608695652173915e-05,
+      "loss": 1.7684,
+      "step": 87
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2753623188405797e-05,
+      "loss": 1.5717,
+      "step": 88
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2898550724637681e-05,
+      "loss": 1.7117,
+      "step": 89
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 1.9092,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.318840579710145e-05,
+      "loss": 1.9193,
+      "step": 91
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.8541,
+      "step": 92
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3478260869565218e-05,
+      "loss": 2.1758,
+      "step": 93
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3623188405797103e-05,
+      "loss": 1.897,
+      "step": 94
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 1.6832,
+      "step": 95
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 1.7025,
+      "step": 96
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4057971014492755e-05,
+      "loss": 1.6876,
+      "step": 97
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.420289855072464e-05,
+      "loss": 1.7254,
+      "step": 98
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4347826086956522e-05,
+      "loss": 1.7035,
+      "step": 99
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 1.6701,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4637681159420291e-05,
+      "loss": 1.755,
+      "step": 101
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 1.8233,
+      "step": 102
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4927536231884059e-05,
+      "loss": 1.5721,
+      "step": 103
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5072463768115944e-05,
+      "loss": 1.92,
+      "step": 104
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5217391304347828e-05,
+      "loss": 1.7907,
+      "step": 105
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.536231884057971e-05,
+      "loss": 1.7155,
+      "step": 106
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5507246376811594e-05,
+      "loss": 1.5529,
+      "step": 107
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 1.6133,
+      "step": 108
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5797101449275363e-05,
+      "loss": 1.6704,
+      "step": 109
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5942028985507246e-05,
+      "loss": 1.5658,
+      "step": 110
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6086956521739132e-05,
+      "loss": 1.638,
+      "step": 111
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6231884057971015e-05,
+      "loss": 1.9667,
+      "step": 112
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6376811594202898e-05,
+      "loss": 1.5857,
+      "step": 113
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 1.8468,
+      "step": 114
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.8011,
+      "step": 115
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.681159420289855e-05,
+      "loss": 1.5584,
+      "step": 116
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6956521739130437e-05,
+      "loss": 1.5325,
+      "step": 117
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.710144927536232e-05,
+      "loss": 1.6412,
+      "step": 118
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7246376811594206e-05,
+      "loss": 1.7962,
+      "step": 119
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 1.771,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7536231884057972e-05,
+      "loss": 1.619,
+      "step": 121
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7681159420289858e-05,
+      "loss": 1.7047,
+      "step": 122
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.782608695652174e-05,
+      "loss": 1.7217,
+      "step": 123
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7971014492753624e-05,
+      "loss": 1.819,
+      "step": 124
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.811594202898551e-05,
+      "loss": 1.5605,
+      "step": 125
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 1.7051,
+      "step": 126
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8405797101449276e-05,
+      "loss": 1.6241,
+      "step": 127
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8550724637681162e-05,
+      "loss": 1.7919,
+      "step": 128
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8695652173913045e-05,
+      "loss": 1.971,
+      "step": 129
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8840579710144928e-05,
+      "loss": 1.8275,
+      "step": 130
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8985507246376814e-05,
+      "loss": 1.6933,
+      "step": 131
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 1.7722,
+      "step": 132
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.927536231884058e-05,
+      "loss": 1.7086,
+      "step": 133
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9420289855072467e-05,
+      "loss": 1.6655,
+      "step": 134
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.956521739130435e-05,
+      "loss": 1.7234,
+      "step": 135
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9710144927536236e-05,
+      "loss": 1.729,
+      "step": 136
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9855072463768115e-05,
+      "loss": 1.6154,
+      "step": 137
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 1.8506,
+      "step": 138
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999997510228907e-05,
+      "loss": 1.886,
+      "step": 139
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999999004091687e-05,
+      "loss": 1.768,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999977592067603e-05,
+      "loss": 1.6536,
+      "step": 141
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999960163687307e-05,
+      "loss": 1.8171,
+      "step": 142
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999993775578466e-05,
+      "loss": 1.62,
+      "step": 143
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999910368370826e-05,
+      "loss": 1.9765,
+      "step": 144
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999878001459436e-05,
+      "loss": 1.7381,
+      "step": 145
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999840655066608e-05,
+      "loss": 1.8361,
+      "step": 146
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999798329210938e-05,
+      "loss": 1.7863,
+      "step": 147
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999751023913506e-05,
+      "loss": 1.8941,
+      "step": 148
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999969873919787e-05,
+      "loss": 1.8171,
+      "step": 149
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999964147509006e-05,
+      "loss": 1.5924,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999579231618588e-05,
+      "loss": 1.6363,
+      "step": 151
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999951200881446e-05,
+      "loss": 1.6188,
+      "step": 152
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999439806711137e-05,
+      "loss": 1.6399,
+      "step": 153
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999362625344584e-05,
+      "loss": 1.7759,
+      "step": 154
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999928046475322e-05,
+      "loss": 1.7508,
+      "step": 155
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999193324977974e-05,
+      "loss": 1.7955,
+      "step": 156
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999101206062224e-05,
+      "loss": 1.9154,
+      "step": 157
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999004108051846e-05,
+      "loss": 1.7574,
+      "step": 158
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999890203099519e-05,
+      "loss": 1.6867,
+      "step": 159
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9998794974943087e-05,
+      "loss": 1.8837,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998682939948843e-05,
+      "loss": 1.7995,
+      "step": 161
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998565926068253e-05,
+      "loss": 1.7261,
+      "step": 162
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998443933359576e-05,
+      "loss": 1.7059,
+      "step": 163
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998316961883563e-05,
+      "loss": 1.8152,
+      "step": 164
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999818501170344e-05,
+      "loss": 1.7966,
+      "step": 165
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999804808288491e-05,
+      "loss": 1.4982,
+      "step": 166
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999790617549616e-05,
+      "loss": 1.9083,
+      "step": 167
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997759289607854e-05,
+      "loss": 1.6917,
+      "step": 168
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999760742529313e-05,
+      "loss": 1.7672,
+      "step": 169
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997450582627614e-05,
+      "loss": 1.8419,
+      "step": 170
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997288761689404e-05,
+      "loss": 1.7393,
+      "step": 171
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999712196255908e-05,
+      "loss": 1.9489,
+      "step": 172
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.99969501853197e-05,
+      "loss": 1.6927,
+      "step": 173
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9996773430056806e-05,
+      "loss": 1.729,
+      "step": 174
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9996591696858407e-05,
+      "loss": 1.8146,
+      "step": 175
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996404985814998e-05,
+      "loss": 1.5406,
+      "step": 176
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996213297019556e-05,
+      "loss": 1.834,
+      "step": 177
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996016630567535e-05,
+      "loss": 1.8505,
+      "step": 178
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999581498655686e-05,
+      "loss": 1.5933,
+      "step": 179
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995608365087945e-05,
+      "loss": 1.7946,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995396766263677e-05,
+      "loss": 1.6388,
+      "step": 181
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995180190189424e-05,
+      "loss": 1.9924,
+      "step": 182
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9994958636973024e-05,
+      "loss": 1.5948,
+      "step": 183
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999473210672481e-05,
+      "loss": 1.5846,
+      "step": 184
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9994500599557577e-05,
+      "loss": 1.6471,
+      "step": 185
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999426411558661e-05,
+      "loss": 1.9565,
+      "step": 186
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9994022654929665e-05,
+      "loss": 1.6896,
+      "step": 187
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993776217706972e-05,
+      "loss": 1.9445,
+      "step": 188
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993524804041255e-05,
+      "loss": 1.714,
+      "step": 189
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993268414057704e-05,
+      "loss": 1.7137,
+      "step": 190
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993007047883988e-05,
+      "loss": 1.6729,
+      "step": 191
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992740705650252e-05,
+      "loss": 1.691,
+      "step": 192
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992469387489127e-05,
+      "loss": 1.7324,
+      "step": 193
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999219309353572e-05,
+      "loss": 1.57,
+      "step": 194
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991911823927607e-05,
+      "loss": 2.0345,
+      "step": 195
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999162557880485e-05,
+      "loss": 1.5059,
+      "step": 196
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999133435830998e-05,
+      "loss": 1.8392,
+      "step": 197
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991038162588018e-05,
+      "loss": 1.7923,
+      "step": 198
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9990736991786453e-05,
+      "loss": 1.78,
+      "step": 199
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999043084605526e-05,
+      "loss": 1.8779,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999011972554688e-05,
+      "loss": 1.6544,
+      "step": 201
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.998980363041624e-05,
+      "loss": 1.8014,
+      "step": 202
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9989482560820734e-05,
+      "loss": 1.6421,
+      "step": 203
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9989156516920248e-05,
+      "loss": 1.8874,
+      "step": 204
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.998882549887713e-05,
+      "loss": 1.7511,
+      "step": 205
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9988489506856218e-05,
+      "loss": 1.7904,
+      "step": 206
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998814854102482e-05,
+      "loss": 1.7859,
+      "step": 207
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987802601552717e-05,
+      "loss": 1.7957,
+      "step": 208
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987451688612176e-05,
+      "loss": 1.6068,
+      "step": 209
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987095802377933e-05,
+      "loss": 1.7852,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.99867349430272e-05,
+      "loss": 1.7431,
+      "step": 211
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986369110739675e-05,
+      "loss": 1.8569,
+      "step": 212
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998599830569752e-05,
+      "loss": 1.6872,
+      "step": 213
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9985622528085382e-05,
+      "loss": 1.7792,
+      "step": 214
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998524177809038e-05,
+      "loss": 1.9195,
+      "step": 215
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998485605590211e-05,
+      "loss": 1.6664,
+      "step": 216
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998446536171265e-05,
+      "loss": 1.6921,
+      "step": 217
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9984069695716534e-05,
+      "loss": 1.7893,
+      "step": 218
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.99836690581108e-05,
+      "loss": 1.8192,
+      "step": 219
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998326344909494e-05,
+      "loss": 1.885,
+      "step": 220
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9982852868870927e-05,
+      "loss": 1.556,
+      "step": 221
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 1.7575,
+      "step": 222
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998201679561873e-05,
+      "loss": 1.7023,
+      "step": 223
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998159130300687e-05,
+      "loss": 1.6913,
+      "step": 224
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9981160840019513e-05,
+      "loss": 1.7819,
+      "step": 225
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9980725406871007e-05,
+      "loss": 1.5825,
+      "step": 226
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998028500377818e-05,
+      "loss": 1.9634,
+      "step": 227
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9979839630960333e-05,
+      "loss": 1.8114,
+      "step": 228
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9979389288639237e-05,
+      "loss": 1.6686,
+      "step": 229
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.997893397703915e-05,
+      "loss": 1.8282,
+      "step": 230
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9978473696386787e-05,
+      "loss": 1.7462,
+      "step": 231
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9978008446911354e-05,
+      "loss": 1.7526,
+      "step": 232
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.997753822884452e-05,
+      "loss": 1.6126,
+      "step": 233
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9977063042420438e-05,
+      "loss": 1.8654,
+      "step": 234
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.997658288787572e-05,
+      "loss": 1.5399,
+      "step": 235
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9976097765449463e-05,
+      "loss": 1.8716,
+      "step": 236
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9975607675383243e-05,
+      "loss": 1.9406,
+      "step": 237
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975112617921097e-05,
+      "loss": 1.7728,
+      "step": 238
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997461259330954e-05,
+      "loss": 1.8756,
+      "step": 239
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997410760179756e-05,
+      "loss": 1.8006,
+      "step": 240
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997359764363663e-05,
+      "loss": 1.7244,
+      "step": 241
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9973082719080673e-05,
+      "loss": 1.8612,
+      "step": 242
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.99725628283861e-05,
+      "loss": 1.7037,
+      "step": 243
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 1.939,
+      "step": 244
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9971508149619126e-05,
+      "loss": 1.5057,
+      "step": 245
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.99709733620719e-05,
+      "loss": 1.9402,
+      "step": 246
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9970433609436426e-05,
+      "loss": 1.6762,
+      "step": 247
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9969888891981473e-05,
+      "loss": 1.8236,
+      "step": 248
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9969339209978287e-05,
+      "loss": 1.7346,
+      "step": 249
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9968784563700586e-05,
+      "loss": 1.5757,
+      "step": 250
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9968224953424553e-05,
+      "loss": 1.7573,
+      "step": 251
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9967660379428855e-05,
+      "loss": 1.5817,
+      "step": 252
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996709084199462e-05,
+      "loss": 1.5974,
+      "step": 253
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9966516341405452e-05,
+      "loss": 1.8537,
+      "step": 254
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996593687794743e-05,
+      "loss": 1.71,
+      "step": 255
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996535245190909e-05,
+      "loss": 1.7969,
+      "step": 256
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9964763063581465e-05,
+      "loss": 1.8761,
+      "step": 257
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996416871325803e-05,
+      "loss": 1.8265,
+      "step": 258
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996356940123475e-05,
+      "loss": 1.5745,
+      "step": 259
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996296512781005e-05,
+      "loss": 1.575,
+      "step": 260
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996235589328484e-05,
+      "loss": 1.537,
+      "step": 261
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996174169796248e-05,
+      "loss": 1.6117,
+      "step": 262
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9961122542148823e-05,
+      "loss": 1.7155,
+      "step": 263
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996049842615217e-05,
+      "loss": 1.6558,
+      "step": 264
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9959869350283306e-05,
+      "loss": 1.6215,
+      "step": 265
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9959235314855485e-05,
+      "loss": 1.877,
+      "step": 266
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.995859632018442e-05,
+      "loss": 1.7136,
+      "step": 267
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9957952366588307e-05,
+      "loss": 1.6772,
+      "step": 268
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9957303454387803e-05,
+      "loss": 1.6511,
+      "step": 269
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995664958390604e-05,
+      "loss": 1.717,
+      "step": 270
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9955990755468614e-05,
+      "loss": 1.9313,
+      "step": 271
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9955326969403587e-05,
+      "loss": 1.8296,
+      "step": 272
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.99546582260415e-05,
+      "loss": 1.7657,
+      "step": 273
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9953984525715354e-05,
+      "loss": 1.6089,
+      "step": 274
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995330586876062e-05,
+      "loss": 1.6183,
+      "step": 275
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995262225551524e-05,
+      "loss": 1.8083,
+      "step": 276
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9951933686319624e-05,
+      "loss": 1.7245,
+      "step": 277
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9951240161516643e-05,
+      "loss": 1.9381,
+      "step": 278
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9950541681451644e-05,
+      "loss": 1.6028,
+      "step": 279
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9949838246472436e-05,
+      "loss": 1.6434,
+      "step": 280
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9949129856929295e-05,
+      "loss": 1.7555,
+      "step": 281
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9948416513174976e-05,
+      "loss": 1.7311,
+      "step": 282
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.994769821556468e-05,
+      "loss": 1.6387,
+      "step": 283
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9946974964456094e-05,
+      "loss": 1.8235,
+      "step": 284
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994624676020936e-05,
+      "loss": 1.9122,
+      "step": 285
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9945513603187096e-05,
+      "loss": 1.838,
+      "step": 286
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9944775493754374e-05,
+      "loss": 1.6418,
+      "step": 287
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9944032432278743e-05,
+      "loss": 1.5999,
+      "step": 288
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994328441913021e-05,
+      "loss": 1.8707,
+      "step": 289
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9942531454681254e-05,
+      "loss": 1.7181,
+      "step": 290
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9941773539306818e-05,
+      "loss": 1.999,
+      "step": 291
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9941010673384307e-05,
+      "loss": 1.7784,
+      "step": 292
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9940242857293594e-05,
+      "loss": 1.6533,
+      "step": 293
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9939470091417012e-05,
+      "loss": 1.7313,
+      "step": 294
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.993869237613937e-05,
+      "loss": 1.6005,
+      "step": 295
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.993790971184793e-05,
+      "loss": 1.8541,
+      "step": 296
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 1.7487,
+      "step": 297
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9936329537785054e-05,
+      "loss": 1.9028,
+      "step": 298
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9935532028800465e-05,
+      "loss": 1.7109,
+      "step": 299
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9934729572375792e-05,
+      "loss": 1.5248,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9933922168910617e-05,
+      "loss": 1.7893,
+      "step": 301
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.993310981880699e-05,
+      "loss": 1.6346,
+      "step": 302
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9932292522469424e-05,
+      "loss": 1.6256,
+      "step": 303
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9931470280304895e-05,
+      "loss": 1.8888,
+      "step": 304
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9930643092722843e-05,
+      "loss": 1.6717,
+      "step": 305
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 1.9557,
+      "step": 306
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992897388295624e-05,
+      "loss": 1.9722,
+      "step": 307
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9928131861602878e-05,
+      "loss": 1.7194,
+      "step": 308
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992728489649437e-05,
+      "loss": 1.7614,
+      "step": 309
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992643298805247e-05,
+      "loss": 1.7441,
+      "step": 310
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9925576136701386e-05,
+      "loss": 1.728,
+      "step": 311
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992471434286779e-05,
+      "loss": 1.7892,
+      "step": 312
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9923847606980824e-05,
+      "loss": 1.6874,
+      "step": 313
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9922975929472076e-05,
+      "loss": 1.8102,
+      "step": 314
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.99220993107756e-05,
+      "loss": 1.682,
+      "step": 315
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9921217751327916e-05,
+      "loss": 1.9336,
+      "step": 316
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9920331251568e-05,
+      "loss": 1.6113,
+      "step": 317
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9919439811937283e-05,
+      "loss": 1.9143,
+      "step": 318
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9918543432879667e-05,
+      "loss": 1.7181,
+      "step": 319
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9917642114841505e-05,
+      "loss": 1.6744,
+      "step": 320
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9916735858271615e-05,
+      "loss": 1.7523,
+      "step": 321
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9915824663621267e-05,
+      "loss": 1.78,
+      "step": 322
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9914908531344198e-05,
+      "loss": 1.9025,
+      "step": 323
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9913987461896597e-05,
+      "loss": 1.7448,
+      "step": 324
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9913061455737116e-05,
+      "loss": 1.8273,
+      "step": 325
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9912130513326863e-05,
+      "loss": 1.6921,
+      "step": 326
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991119463512941e-05,
+      "loss": 1.7164,
+      "step": 327
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991025382161077e-05,
+      "loss": 1.6556,
+      "step": 328
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9909308073239433e-05,
+      "loss": 1.6554,
+      "step": 329
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9908357390486342e-05,
+      "loss": 1.7639,
+      "step": 330
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9907401773824887e-05,
+      "loss": 1.7496,
+      "step": 331
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990644122373092e-05,
+      "loss": 1.8797,
+      "step": 332
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9905475740682756e-05,
+      "loss": 1.5464,
+      "step": 333
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990450532516116e-05,
+      "loss": 1.7168,
+      "step": 334
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990352997764935e-05,
+      "loss": 1.7238,
+      "step": 335
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990254969863301e-05,
+      "loss": 1.983,
+      "step": 336
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9901564488600274e-05,
+      "loss": 1.6583,
+      "step": 337
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9900574348041728e-05,
+      "loss": 1.9771,
+      "step": 338
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9899579277450417e-05,
+      "loss": 1.7111,
+      "step": 339
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9898579277321845e-05,
+      "loss": 1.8824,
+      "step": 340
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9897574348153963e-05,
+      "loss": 1.7126,
+      "step": 341
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.989656449044718e-05,
+      "loss": 1.6109,
+      "step": 342
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9895549704704358e-05,
+      "loss": 1.6111,
+      "step": 343
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9894529991430814e-05,
+      "loss": 1.5684,
+      "step": 344
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9893505351134322e-05,
+      "loss": 1.7286,
+      "step": 345
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.98924757843251e-05,
+      "loss": 1.6518,
+      "step": 346
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989144129151583e-05,
+      "loss": 1.6504,
+      "step": 347
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9890401873221642e-05,
+      "loss": 1.4915,
+      "step": 348
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9889357529960114e-05,
+      "loss": 1.7182,
+      "step": 349
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 1.6,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9887254070617644e-05,
+      "loss": 1.6773,
+      "step": 351
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9886194955584126e-05,
+      "loss": 1.7222,
+      "step": 352
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9885130917678123e-05,
+      "loss": 1.799,
+      "step": 353
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988406195742948e-05,
+      "loss": 1.9064,
+      "step": 354
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988298807537049e-05,
+      "loss": 1.652,
+      "step": 355
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9881909272035888e-05,
+      "loss": 1.8517,
+      "step": 356
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9880825547962882e-05,
+      "loss": 1.7441,
+      "step": 357
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9879736903691107e-05,
+      "loss": 1.6021,
+      "step": 358
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9878643339762663e-05,
+      "loss": 1.7011,
+      "step": 359
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9877544856722094e-05,
+      "loss": 1.6778,
+      "step": 360
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9876441455116393e-05,
+      "loss": 1.7144,
+      "step": 361
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9875333135495e-05,
+      "loss": 2.0308,
+      "step": 362
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987421989840982e-05,
+      "loss": 1.7471,
+      "step": 363
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987310174441518e-05,
+      "loss": 1.5851,
+      "step": 364
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987197867406788e-05,
+      "loss": 1.873,
+      "step": 365
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987085068792715e-05,
+      "loss": 1.7713,
+      "step": 366
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986971778655468e-05,
+      "loss": 1.6572,
+      "step": 367
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.98685799705146e-05,
+      "loss": 1.7438,
+      "step": 368
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986743724037349e-05,
+      "loss": 1.7512,
+      "step": 369
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9866289596700383e-05,
+      "loss": 1.7058,
+      "step": 370
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9865137040066744e-05,
+      "loss": 1.7243,
+      "step": 371
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.98639795710465e-05,
+      "loss": 1.5387,
+      "step": 372
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.986281719021602e-05,
+      "loss": 1.8603,
+      "step": 373
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9861649898154107e-05,
+      "loss": 1.7283,
+      "step": 374
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.986047769544203e-05,
+      "loss": 1.6644,
+      "step": 375
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985930058266348e-05,
+      "loss": 1.455,
+      "step": 376
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985811856040462e-05,
+      "loss": 1.6884,
+      "step": 377
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9856931629254032e-05,
+      "loss": 1.7179,
+      "step": 378
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9855739789802753e-05,
+      "loss": 1.9469,
+      "step": 379
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985454304264427e-05,
+      "loss": 1.6094,
+      "step": 380
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9853341388374504e-05,
+      "loss": 1.6679,
+      "step": 381
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985213482759183e-05,
+      "loss": 1.5478,
+      "step": 382
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9850923360897055e-05,
+      "loss": 1.6236,
+      "step": 383
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9849706988893433e-05,
+      "loss": 1.8009,
+      "step": 384
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9848485712186665e-05,
+      "loss": 1.4946,
+      "step": 385
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984725953138489e-05,
+      "loss": 1.6641,
+      "step": 386
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9846028447098687e-05,
+      "loss": 1.6904,
+      "step": 387
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984479245994108e-05,
+      "loss": 1.6803,
+      "step": 388
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9843551570527543e-05,
+      "loss": 1.8788,
+      "step": 389
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 1.8476,
+      "step": 390
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9841055087406715e-05,
+      "loss": 1.5684,
+      "step": 391
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983979949494256e-05,
+      "loss": 1.4454,
+      "step": 392
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983853900270874e-05,
+      "loss": 1.6985,
+      "step": 393
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9837273611332918e-05,
+      "loss": 1.9378,
+      "step": 394
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9836003321445198e-05,
+      "loss": 1.5318,
+      "step": 395
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983472813367813e-05,
+      "loss": 1.7142,
+      "step": 396
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.98334480486667e-05,
+      "loss": 1.7121,
+      "step": 397
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9832163067048335e-05,
+      "loss": 1.7841,
+      "step": 398
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9830873189462886e-05,
+      "loss": 1.6868,
+      "step": 399
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.982957841655266e-05,
+      "loss": 1.9112,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9828278748962396e-05,
+      "loss": 1.5438,
+      "step": 401
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9826974187339267e-05,
+      "loss": 1.8109,
+      "step": 402
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9825664732332886e-05,
+      "loss": 1.784,
+      "step": 403
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9824350384595295e-05,
+      "loss": 1.5111,
+      "step": 404
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.982303114478099e-05,
+      "loss": 1.5256,
+      "step": 405
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9821707013546885e-05,
+      "loss": 1.6807,
+      "step": 406
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9820377991552338e-05,
+      "loss": 1.606,
+      "step": 407
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9819044079459142e-05,
+      "loss": 1.5803,
+      "step": 408
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9817705277931526e-05,
+      "loss": 1.7415,
+      "step": 409
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9816361587636143e-05,
+      "loss": 1.7781,
+      "step": 410
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9815013009242103e-05,
+      "loss": 1.679,
+      "step": 411
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9813659543420924e-05,
+      "loss": 1.7402,
+      "step": 412
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.981230119084658e-05,
+      "loss": 1.6561,
+      "step": 413
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.981093795219546e-05,
+      "loss": 1.4753,
+      "step": 414
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9809569828146396e-05,
+      "loss": 1.8676,
+      "step": 415
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9808196819380656e-05,
+      "loss": 1.5367,
+      "step": 416
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.980681892658193e-05,
+      "loss": 1.7324,
+      "step": 417
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9805436150436352e-05,
+      "loss": 1.6161,
+      "step": 418
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9804048491632475e-05,
+      "loss": 1.5056,
+      "step": 419
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.980265595086129e-05,
+      "loss": 1.7321,
+      "step": 420
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9801258528816223e-05,
+      "loss": 1.5752,
+      "step": 421
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9799856226193125e-05,
+      "loss": 1.8505,
+      "step": 422
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9798449043690272e-05,
+      "loss": 1.7899,
+      "step": 423
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9797036982008385e-05,
+      "loss": 1.8264,
+      "step": 424
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9795620041850602e-05,
+      "loss": 1.9919,
+      "step": 425
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9794198223922496e-05,
+      "loss": 1.6524,
+      "step": 426
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9792771528932064e-05,
+      "loss": 1.7086,
+      "step": 427
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.979133995758974e-05,
+      "loss": 1.8144,
+      "step": 428
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9789903510608374e-05,
+      "loss": 1.5938,
+      "step": 429
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978846218870326e-05,
+      "loss": 1.8841,
+      "step": 430
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.97870159925921e-05,
+      "loss": 1.6414,
+      "step": 431
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9785564922995042e-05,
+      "loss": 1.6442,
+      "step": 432
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978410898063465e-05,
+      "loss": 1.6781,
+      "step": 433
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978264816623591e-05,
+      "loss": 1.6857,
+      "step": 434
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978118248052625e-05,
+      "loss": 1.6302,
+      "step": 435
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.977971192423551e-05,
+      "loss": 1.7229,
+      "step": 436
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977823649809596e-05,
+      "loss": 1.8492,
+      "step": 437
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9776756202842297e-05,
+      "loss": 1.7095,
+      "step": 438
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9775271039211633e-05,
+      "loss": 1.8962,
+      "step": 439
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977378100794352e-05,
+      "loss": 1.809,
+      "step": 440
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977228610977992e-05,
+      "loss": 1.5157,
+      "step": 441
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977078634546523e-05,
+      "loss": 1.8447,
+      "step": 442
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9769281715746258e-05,
+      "loss": 1.5596,
+      "step": 443
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976777222137224e-05,
+      "loss": 1.6913,
+      "step": 444
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9766257863094843e-05,
+      "loss": 1.5567,
+      "step": 445
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9764738641668137e-05,
+      "loss": 1.7594,
+      "step": 446
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9763214557848634e-05,
+      "loss": 1.8343,
+      "step": 447
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9761685612395253e-05,
+      "loss": 1.8573,
+      "step": 448
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976015180606934e-05,
+      "loss": 1.6969,
+      "step": 449
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9758613139634662e-05,
+      "loss": 1.6318,
+      "step": 450
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9757069613857404e-05,
+      "loss": 1.7388,
+      "step": 451
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9755521229506164e-05,
+      "loss": 1.7768,
+      "step": 452
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.975396798735198e-05,
+      "loss": 1.684,
+      "step": 453
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9752409888168285e-05,
+      "loss": 1.6109,
+      "step": 454
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9750846932730947e-05,
+      "loss": 1.8364,
+      "step": 455
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 1.8766,
+      "step": 456
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9747706456210865e-05,
+      "loss": 1.5277,
+      "step": 457
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974612893669194e-05,
+      "loss": 1.8831,
+      "step": 458
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9744546564046995e-05,
+      "loss": 1.8072,
+      "step": 459
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9742959339063977e-05,
+      "loss": 1.7829,
+      "step": 460
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974136726253326e-05,
+      "loss": 1.708,
+      "step": 461
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9739770335247616e-05,
+      "loss": 1.6817,
+      "step": 462
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9738168558002245e-05,
+      "loss": 1.8286,
+      "step": 463
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.973656193159476e-05,
+      "loss": 1.8612,
+      "step": 464
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9734950456825187e-05,
+      "loss": 1.7412,
+      "step": 465
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9733334134495963e-05,
+      "loss": 1.6253,
+      "step": 466
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9731712965411947e-05,
+      "loss": 1.8272,
+      "step": 467
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9730086950380404e-05,
+      "loss": 1.6659,
+      "step": 468
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9728456090211017e-05,
+      "loss": 1.7135,
+      "step": 469
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9726820385715877e-05,
+      "loss": 1.9411,
+      "step": 470
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9725179837709494e-05,
+      "loss": 1.7032,
+      "step": 471
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9723534447008785e-05,
+      "loss": 1.7129,
+      "step": 472
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9721884214433077e-05,
+      "loss": 1.8704,
+      "step": 473
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 1.667,
+      "step": 474
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9718569226946035e-05,
+      "loss": 1.5918,
+      "step": 475
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9716904473685417e-05,
+      "loss": 1.5348,
+      "step": 476
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9715234881851226e-05,
+      "loss": 1.7724,
+      "step": 477
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971356045227484e-05,
+      "loss": 1.927,
+      "step": 478
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971188118579004e-05,
+      "loss": 1.8668,
+      "step": 479
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9710197083233044e-05,
+      "loss": 1.8976,
+      "step": 480
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9708508145442443e-05,
+      "loss": 1.7757,
+      "step": 481
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.970681437325925e-05,
+      "loss": 1.8585,
+      "step": 482
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9705115767526894e-05,
+      "loss": 1.7761,
+      "step": 483
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.97034123290912e-05,
+      "loss": 1.7709,
+      "step": 484
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.97017040588004e-05,
+      "loss": 1.6896,
+      "step": 485
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9699990957505136e-05,
+      "loss": 1.7458,
+      "step": 486
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9698273026058454e-05,
+      "loss": 1.7141,
+      "step": 487
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9696550265315805e-05,
+      "loss": 1.6869,
+      "step": 488
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9694822676135045e-05,
+      "loss": 1.7167,
+      "step": 489
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9693090259376436e-05,
+      "loss": 1.8046,
+      "step": 490
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9691353015902638e-05,
+      "loss": 1.9046,
+      "step": 491
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9689610946578725e-05,
+      "loss": 1.5962,
+      "step": 492
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.968786405227216e-05,
+      "loss": 1.7309,
+      "step": 493
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9686112333852826e-05,
+      "loss": 1.6692,
+      "step": 494
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.968435579219299e-05,
+      "loss": 1.6645,
+      "step": 495
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.968259442816733e-05,
+      "loss": 1.9673,
+      "step": 496
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.968082824265293e-05,
+      "loss": 1.8449,
+      "step": 497
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9679057236529266e-05,
+      "loss": 1.4464,
+      "step": 498
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9677281410678216e-05,
+      "loss": 1.6464,
+      "step": 499
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9675500765984066e-05,
+      "loss": 1.6744,
+      "step": 500
+    }
+  ],
+  "max_steps": 4590,
+  "num_train_epochs": 3,
+  "total_flos": 5.83550496627753e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df894649adb3ab0936fc0591fa74c9be713740610268e9b0f1d0141762a1e86
+size 3707

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 1024,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
+  "tokenizer_class": "LLaMATokenizer",
+  "unk_token": ""
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4df894649adb3ab0936fc0591fa74c9be713740610268e9b0f1d0141762a1e86
+size 3707