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-13b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "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:b79d9db69d675b29b064d84a96b20f43a4178b951d801133fc3ffa1abf92c924
+size 13015909885

checkpoint-500/pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58684c7edfd5c4bd53e01de1894fb14ce6615b3ab1a0fd8df900be09a0ecd8e
+size 9956566923

checkpoint-500/pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceefc5873e4ac2e96300758b609e367f0958be3fc40f95ed2bec645abd52a519
+size 9940859009

checkpoint-500/pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7716e523c8063c50d60975a65802535b7a7f6b3726f215e302da3eac8f9fd28
+size 9940859567

checkpoint-500/pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04373d989db0a014666863484b03b7bf14e44717c25240e056114eb7b03700e5
+size 9867417913

checkpoint-500/pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159defb65003e027d6bd1f2675665d4ee60b42e67ef1e7eb34d845f3a31a748c
+size 9867459649

checkpoint-500/pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd2767d3ad81d9ca37719df0174d0bcb5de8a5cdc8c542e6d4db2560f48d7cb
+size 2490497199

checkpoint-500/pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063508480
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.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/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e672460daa959a080f877d7c4d9b69e426aee58d68fadf7c7b1606bd41fb8b2
+size 14583

checkpoint-500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c802d6db3aceebae672c04998fd328369189deed851c3d0535ae9327dbd586
+size 14583

checkpoint-500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812c89bb64ec7378ed47cc6eab99147f0771a5315960b29e97b311b64542216d
+size 14583

checkpoint-500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b125372e27c9d41b3d47a27d6dbb797aa6dc4d9224fa71a3adab0f45eb362eb5
+size 14583

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56d1b07ea4ddc70ceb7b5ff691f736ebe50b8a164cb81e1fec4e7c35f4fc7a7
+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-13b-hf/snapshots/438770a656712a5072229b62256521845d4de5ce/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": 0.6534879921581441,
+  "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": 2.8985507246376816e-07,
+      "loss": 2.3988,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.797101449275363e-07,
+      "loss": 2.2096,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.8346,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1594202898550726e-06,
+      "loss": 1.8346,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4492753623188408e-06,
+      "loss": 1.9785,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.8236,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.028985507246377e-06,
+      "loss": 1.8187,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3188405797101453e-06,
+      "loss": 1.8793,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.928,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8985507246376816e-06,
+      "loss": 1.76,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.188405797101449e-06,
+      "loss": 1.7108,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.7712,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.768115942028986e-06,
+      "loss": 1.8288,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.057971014492754e-06,
+      "loss": 1.8112,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.7858,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.637681159420291e-06,
+      "loss": 1.7692,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.927536231884059e-06,
+      "loss": 1.6936,
+      "step": 17
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.8671,
+      "step": 18
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.507246376811595e-06,
+      "loss": 1.7851,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.797101449275363e-06,
+      "loss": 1.8736,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 1.828,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.376811594202898e-06,
+      "loss": 1.6725,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.6799,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 1.9097,
+      "step": 24
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.246376811594203e-06,
+      "loss": 1.8499,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.536231884057972e-06,
+      "loss": 1.7507,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 1.6498,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.115942028985508e-06,
+      "loss": 1.6504,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.405797101449275e-06,
+      "loss": 1.5428,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 1.7138,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.985507246376812e-06,
+      "loss": 1.6575,
+      "step": 31
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.275362318840581e-06,
+      "loss": 1.8043,
+      "step": 32
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 1.7853,
+      "step": 33
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.855072463768118e-06,
+      "loss": 1.6425,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0144927536231885e-05,
+      "loss": 1.7267,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 1.6063,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0724637681159422e-05,
+      "loss": 1.7126,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.101449275362319e-05,
+      "loss": 1.6379,
+      "step": 38
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 1.7932,
+      "step": 39
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1594202898550726e-05,
+      "loss": 1.5776,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1884057971014494e-05,
+      "loss": 1.6716,
+      "step": 41
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 1.5683,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2463768115942029e-05,
+      "loss": 1.7941,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2753623188405797e-05,
+      "loss": 1.6677,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 1.6677,
+      "step": 45
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.8042,
+      "step": 46
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3623188405797103e-05,
+      "loss": 1.6045,
+      "step": 47
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 1.6353,
+      "step": 48
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.420289855072464e-05,
+      "loss": 1.6586,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4492753623188407e-05,
+      "loss": 1.626,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 1.6165,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5072463768115944e-05,
+      "loss": 1.6579,
+      "step": 52
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.536231884057971e-05,
+      "loss": 1.585,
+      "step": 53
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 1.585,
+      "step": 54
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5942028985507246e-05,
+      "loss": 1.594,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6231884057971015e-05,
+      "loss": 1.6924,
+      "step": 56
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 1.8485,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.681159420289855e-05,
+      "loss": 1.6987,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.710144927536232e-05,
+      "loss": 1.5926,
+      "step": 59
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 1.6222,
+      "step": 60
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7681159420289858e-05,
+      "loss": 1.6906,
+      "step": 61
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7971014492753624e-05,
+      "loss": 1.6466,
+      "step": 62
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 1.6629,
+      "step": 63
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8550724637681162e-05,
+      "loss": 1.7639,
+      "step": 64
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8840579710144928e-05,
+      "loss": 1.5877,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 1.6888,
+      "step": 66
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9420289855072467e-05,
+      "loss": 1.6415,
+      "step": 67
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9710144927536236e-05,
+      "loss": 1.6959,
+      "step": 68
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 1.6053,
+      "step": 69
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999999004091687e-05,
+      "loss": 1.5844,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999960163687307e-05,
+      "loss": 1.7203,
+      "step": 71
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9999910368370826e-05,
+      "loss": 1.6762,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999840655066608e-05,
+      "loss": 1.7704,
+      "step": 73
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999751023913506e-05,
+      "loss": 1.8186,
+      "step": 74
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999964147509006e-05,
+      "loss": 1.816,
+      "step": 75
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.999951200881446e-05,
+      "loss": 1.6055,
+      "step": 76
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999362625344584e-05,
+      "loss": 1.7048,
+      "step": 77
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999193324977974e-05,
+      "loss": 1.6125,
+      "step": 78
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999004108051846e-05,
+      "loss": 1.7239,
+      "step": 79
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9998794974943087e-05,
+      "loss": 1.7377,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998565926068253e-05,
+      "loss": 1.6942,
+      "step": 81
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998316961883563e-05,
+      "loss": 1.6398,
+      "step": 82
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999804808288491e-05,
+      "loss": 1.5898,
+      "step": 83
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997759289607854e-05,
+      "loss": 1.6926,
+      "step": 84
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997450582627614e-05,
+      "loss": 1.5962,
+      "step": 85
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999712196255908e-05,
+      "loss": 1.7171,
+      "step": 86
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9996773430056806e-05,
+      "loss": 1.6443,
+      "step": 87
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996404985814998e-05,
+      "loss": 1.7252,
+      "step": 88
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9996016630567535e-05,
+      "loss": 1.6777,
+      "step": 89
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995608365087945e-05,
+      "loss": 1.6758,
+      "step": 90
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995180190189424e-05,
+      "loss": 1.6416,
+      "step": 91
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999473210672481e-05,
+      "loss": 1.6161,
+      "step": 92
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999426411558661e-05,
+      "loss": 1.8361,
+      "step": 93
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993776217706972e-05,
+      "loss": 1.6755,
+      "step": 94
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9993268414057704e-05,
+      "loss": 1.5446,
+      "step": 95
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992740705650252e-05,
+      "loss": 1.6776,
+      "step": 96
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999219309353572e-05,
+      "loss": 1.5742,
+      "step": 97
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999162557880485e-05,
+      "loss": 1.7124,
+      "step": 98
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991038162588018e-05,
+      "loss": 1.6711,
+      "step": 99
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999043084605526e-05,
+      "loss": 1.5564,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.998980363041624e-05,
+      "loss": 1.666,
+      "step": 101
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9989156516920248e-05,
+      "loss": 1.7261,
+      "step": 102
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9988489506856218e-05,
+      "loss": 1.5975,
+      "step": 103
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987802601552717e-05,
+      "loss": 1.5775,
+      "step": 104
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987095802377933e-05,
+      "loss": 1.6664,
+      "step": 105
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986369110739675e-05,
+      "loss": 1.6425,
+      "step": 106
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9985622528085382e-05,
+      "loss": 1.7126,
+      "step": 107
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998485605590211e-05,
+      "loss": 1.5268,
+      "step": 108
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9984069695716534e-05,
+      "loss": 1.7186,
+      "step": 109
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.998326344909494e-05,
+      "loss": 1.5536,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 1.743,
+      "step": 111
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998159130300687e-05,
+      "loss": 1.7855,
+      "step": 112
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9980725406871007e-05,
+      "loss": 1.6741,
+      "step": 113
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9979839630960333e-05,
+      "loss": 1.6982,
+      "step": 114
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.997893397703915e-05,
+      "loss": 1.9001,
+      "step": 115
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9978008446911354e-05,
+      "loss": 1.8314,
+      "step": 116
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9977063042420438e-05,
+      "loss": 1.6957,
+      "step": 117
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9976097765449463e-05,
+      "loss": 1.6764,
+      "step": 118
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975112617921097e-05,
+      "loss": 1.6958,
+      "step": 119
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997410760179756e-05,
+      "loss": 1.6011,
+      "step": 120
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9973082719080673e-05,
+      "loss": 1.665,
+      "step": 121
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9972037971811802e-05,
+      "loss": 1.6208,
+      "step": 122
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.99709733620719e-05,
+      "loss": 1.6691,
+      "step": 123
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9969888891981473e-05,
+      "loss": 1.8241,
+      "step": 124
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9968784563700586e-05,
+      "loss": 1.7574,
+      "step": 125
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9967660379428855e-05,
+      "loss": 1.6484,
+      "step": 126
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9966516341405452e-05,
+      "loss": 1.5869,
+      "step": 127
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996535245190909e-05,
+      "loss": 1.7188,
+      "step": 128
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996416871325803e-05,
+      "loss": 1.6428,
+      "step": 129
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996296512781005e-05,
+      "loss": 1.7432,
+      "step": 130
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996174169796248e-05,
+      "loss": 1.6332,
+      "step": 131
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996049842615217e-05,
+      "loss": 1.7188,
+      "step": 132
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9959235314855485e-05,
+      "loss": 1.7858,
+      "step": 133
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9957952366588307e-05,
+      "loss": 1.5635,
+      "step": 134
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995664958390604e-05,
+      "loss": 1.7286,
+      "step": 135
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9955326969403587e-05,
+      "loss": 1.5419,
+      "step": 136
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9953984525715354e-05,
+      "loss": 1.6727,
+      "step": 137
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995262225551524e-05,
+      "loss": 1.6839,
+      "step": 138
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9951240161516643e-05,
+      "loss": 1.5626,
+      "step": 139
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9949838246472436e-05,
+      "loss": 1.6662,
+      "step": 140
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9948416513174976e-05,
+      "loss": 1.6306,
+      "step": 141
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9946974964456094e-05,
+      "loss": 1.6706,
+      "step": 142
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9945513603187096e-05,
+      "loss": 1.8325,
+      "step": 143
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9944032432278743e-05,
+      "loss": 1.7128,
+      "step": 144
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9942531454681254e-05,
+      "loss": 1.6979,
+      "step": 145
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9941010673384307e-05,
+      "loss": 1.6811,
+      "step": 146
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9939470091417012e-05,
+      "loss": 1.5436,
+      "step": 147
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.993790971184793e-05,
+      "loss": 1.705,
+      "step": 148
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9936329537785054e-05,
+      "loss": 1.5621,
+      "step": 149
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9934729572375792e-05,
+      "loss": 1.7562,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.993310981880699e-05,
+      "loss": 1.6263,
+      "step": 151
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9931470280304895e-05,
+      "loss": 1.6247,
+      "step": 152
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 1.6521,
+      "step": 153
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9928131861602878e-05,
+      "loss": 1.5587,
+      "step": 154
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992643298805247e-05,
+      "loss": 1.6085,
+      "step": 155
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992471434286779e-05,
+      "loss": 1.5774,
+      "step": 156
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9922975929472076e-05,
+      "loss": 1.731,
+      "step": 157
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9921217751327916e-05,
+      "loss": 1.5823,
+      "step": 158
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9919439811937283e-05,
+      "loss": 1.5621,
+      "step": 159
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9917642114841505e-05,
+      "loss": 1.6566,
+      "step": 160
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9915824663621267e-05,
+      "loss": 1.5214,
+      "step": 161
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9913987461896597e-05,
+      "loss": 1.7257,
+      "step": 162
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9912130513326863e-05,
+      "loss": 1.7401,
+      "step": 163
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.991025382161077e-05,
+      "loss": 1.5845,
+      "step": 164
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9908357390486342e-05,
+      "loss": 1.6235,
+      "step": 165
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990644122373092e-05,
+      "loss": 1.571,
+      "step": 166
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990450532516116e-05,
+      "loss": 1.8406,
+      "step": 167
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990254969863301e-05,
+      "loss": 1.8326,
+      "step": 168
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9900574348041728e-05,
+      "loss": 1.6099,
+      "step": 169
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9898579277321845e-05,
+      "loss": 1.4999,
+      "step": 170
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.989656449044718e-05,
+      "loss": 1.6982,
+      "step": 171
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9894529991430814e-05,
+      "loss": 1.7241,
+      "step": 172
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.98924757843251e-05,
+      "loss": 1.6838,
+      "step": 173
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9890401873221642e-05,
+      "loss": 1.5703,
+      "step": 174
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 1.6669,
+      "step": 175
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9886194955584126e-05,
+      "loss": 1.682,
+      "step": 176
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988406195742948e-05,
+      "loss": 1.7266,
+      "step": 177
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9881909272035888e-05,
+      "loss": 1.7065,
+      "step": 178
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9879736903691107e-05,
+      "loss": 1.6784,
+      "step": 179
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9877544856722094e-05,
+      "loss": 1.8589,
+      "step": 180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9875333135495e-05,
+      "loss": 1.7492,
+      "step": 181
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987310174441518e-05,
+      "loss": 1.6953,
+      "step": 182
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987085068792715e-05,
+      "loss": 1.6772,
+      "step": 183
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.98685799705146e-05,
+      "loss": 1.6507,
+      "step": 184
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9866289596700383e-05,
+      "loss": 1.6677,
+      "step": 185
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.98639795710465e-05,
+      "loss": 1.5531,
+      "step": 186
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9861649898154107e-05,
+      "loss": 1.692,
+      "step": 187
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985930058266348e-05,
+      "loss": 1.5314,
+      "step": 188
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9856931629254032e-05,
+      "loss": 1.5806,
+      "step": 189
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985454304264427e-05,
+      "loss": 1.6998,
+      "step": 190
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.985213482759183e-05,
+      "loss": 1.532,
+      "step": 191
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9849706988893433e-05,
+      "loss": 1.4833,
+      "step": 192
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984725953138489e-05,
+      "loss": 1.6384,
+      "step": 193
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984479245994108e-05,
+      "loss": 1.602,
+      "step": 194
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 1.6837,
+      "step": 195
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983979949494256e-05,
+      "loss": 1.6221,
+      "step": 196
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9837273611332918e-05,
+      "loss": 1.5824,
+      "step": 197
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983472813367813e-05,
+      "loss": 1.5726,
+      "step": 198
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9832163067048335e-05,
+      "loss": 1.8058,
+      "step": 199
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.982957841655266e-05,
+      "loss": 1.6665,
+      "step": 200
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9826974187339267e-05,
+      "loss": 1.6163,
+      "step": 201
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9824350384595295e-05,
+      "loss": 1.6621,
+      "step": 202
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9821707013546885e-05,
+      "loss": 1.6097,
+      "step": 203
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9819044079459142e-05,
+      "loss": 1.6398,
+      "step": 204
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9816361587636143e-05,
+      "loss": 1.5231,
+      "step": 205
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9813659543420924e-05,
+      "loss": 1.5495,
+      "step": 206
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.981093795219546e-05,
+      "loss": 1.6761,
+      "step": 207
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9808196819380656e-05,
+      "loss": 1.5347,
+      "step": 208
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9805436150436352e-05,
+      "loss": 1.5175,
+      "step": 209
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.980265595086129e-05,
+      "loss": 1.6109,
+      "step": 210
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9799856226193125e-05,
+      "loss": 1.5862,
+      "step": 211
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9797036982008385e-05,
+      "loss": 1.6155,
+      "step": 212
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9794198223922496e-05,
+      "loss": 1.6225,
+      "step": 213
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.979133995758974e-05,
+      "loss": 1.7578,
+      "step": 214
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978846218870326e-05,
+      "loss": 1.6944,
+      "step": 215
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9785564922995042e-05,
+      "loss": 1.5978,
+      "step": 216
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978264816623591e-05,
+      "loss": 1.4836,
+      "step": 217
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.977971192423551e-05,
+      "loss": 1.7529,
+      "step": 218
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9776756202842297e-05,
+      "loss": 1.5821,
+      "step": 219
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977378100794352e-05,
+      "loss": 1.5954,
+      "step": 220
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.977078634546523e-05,
+      "loss": 1.5528,
+      "step": 221
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976777222137224e-05,
+      "loss": 1.7068,
+      "step": 222
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9764738641668137e-05,
+      "loss": 1.6066,
+      "step": 223
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9761685612395253e-05,
+      "loss": 1.639,
+      "step": 224
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9758613139634662e-05,
+      "loss": 1.5999,
+      "step": 225
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9755521229506164e-05,
+      "loss": 1.6008,
+      "step": 226
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9752409888168285e-05,
+      "loss": 1.7106,
+      "step": 227
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 1.6942,
+      "step": 228
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.974612893669194e-05,
+      "loss": 1.7407,
+      "step": 229
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9742959339063977e-05,
+      "loss": 1.6449,
+      "step": 230
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9739770335247616e-05,
+      "loss": 1.5437,
+      "step": 231
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.973656193159476e-05,
+      "loss": 1.5952,
+      "step": 232
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9733334134495963e-05,
+      "loss": 1.7003,
+      "step": 233
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9730086950380404e-05,
+      "loss": 1.5441,
+      "step": 234
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9726820385715877e-05,
+      "loss": 1.5202,
+      "step": 235
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9723534447008785e-05,
+      "loss": 1.6691,
+      "step": 236
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 1.6877,
+      "step": 237
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9716904473685417e-05,
+      "loss": 1.5395,
+      "step": 238
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971356045227484e-05,
+      "loss": 1.6574,
+      "step": 239
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9710197083233044e-05,
+      "loss": 1.5122,
+      "step": 240
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.970681437325925e-05,
+      "loss": 1.4915,
+      "step": 241
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.97034123290912e-05,
+      "loss": 1.5517,
+      "step": 242
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9699990957505136e-05,
+      "loss": 1.7456,
+      "step": 243
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9696550265315805e-05,
+      "loss": 1.4699,
+      "step": 244
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9693090259376436e-05,
+      "loss": 1.5823,
+      "step": 245
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9689610946578725e-05,
+      "loss": 1.7989,
+      "step": 246
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9686112333852826e-05,
+      "loss": 1.4173,
+      "step": 247
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.968259442816733e-05,
+      "loss": 1.605,
+      "step": 248
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9679057236529266e-05,
+      "loss": 1.6035,
+      "step": 249
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9675500765984066e-05,
+      "loss": 1.5451,
+      "step": 250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9671925023615572e-05,
+      "loss": 1.8563,
+      "step": 251
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9668330016546004e-05,
+      "loss": 1.464,
+      "step": 252
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9664715751935958e-05,
+      "loss": 1.5198,
+      "step": 253
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9661082236984387e-05,
+      "loss": 1.4562,
+      "step": 254
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.965742947892858e-05,
+      "loss": 1.6719,
+      "step": 255
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.965375748504417e-05,
+      "loss": 1.629,
+      "step": 256
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9650066262645097e-05,
+      "loss": 1.5683,
+      "step": 257
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.964635581908359e-05,
+      "loss": 1.6081,
+      "step": 258
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9642626161750176e-05,
+      "loss": 1.5387,
+      "step": 259
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9638877298073645e-05,
+      "loss": 1.5545,
+      "step": 260
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9635109235521057e-05,
+      "loss": 1.5341,
+      "step": 261
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.963132198159769e-05,
+      "loss": 1.5831,
+      "step": 262
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9627515543847068e-05,
+      "loss": 1.6099,
+      "step": 263
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.962368992985091e-05,
+      "loss": 1.5442,
+      "step": 264
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961984514722914e-05,
+      "loss": 1.6946,
+      "step": 265
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961598120363986e-05,
+      "loss": 1.6732,
+      "step": 266
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.961209810677934e-05,
+      "loss": 1.6603,
+      "step": 267
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9608195864381994e-05,
+      "loss": 1.4686,
+      "step": 268
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.960427448422037e-05,
+      "loss": 1.7164,
+      "step": 269
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9600333974105145e-05,
+      "loss": 1.6552,
+      "step": 270
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9596374341885093e-05,
+      "loss": 1.4366,
+      "step": 271
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9592395595447064e-05,
+      "loss": 1.6662,
+      "step": 272
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9588397742716004e-05,
+      "loss": 1.6731,
+      "step": 273
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9584380791654896e-05,
+      "loss": 1.4749,
+      "step": 274
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.958034475026477e-05,
+      "loss": 1.5257,
+      "step": 275
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9576289626584685e-05,
+      "loss": 1.5007,
+      "step": 276
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.95722154286917e-05,
+      "loss": 1.5079,
+      "step": 277
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9568122164700867e-05,
+      "loss": 1.5105,
+      "step": 278
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 1.5288,
+      "step": 279
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9559878471075763e-05,
+      "loss": 1.4527,
+      "step": 280
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.955572805786141e-05,
+      "loss": 1.5178,
+      "step": 281
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.955155861138903e-05,
+      "loss": 1.5058,
+      "step": 282
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9547370139963406e-05,
+      "loss": 1.4538,
+      "step": 283
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.954316265192719e-05,
+      "loss": 1.6261,
+      "step": 284
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9538936155660934e-05,
+      "loss": 1.578,
+      "step": 285
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9534690659583045e-05,
+      "loss": 1.4569,
+      "step": 286
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.953042617214977e-05,
+      "loss": 1.5795,
+      "step": 287
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9526142701855187e-05,
+      "loss": 1.625,
+      "step": 288
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9521840257231183e-05,
+      "loss": 1.6226,
+      "step": 289
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9517518846847437e-05,
+      "loss": 1.5874,
+      "step": 290
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.951317847931141e-05,
+      "loss": 1.5774,
+      "step": 291
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9508819163268315e-05,
+      "loss": 1.525,
+      "step": 292
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9504440907401113e-05,
+      "loss": 1.6432,
+      "step": 293
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9500043720430484e-05,
+      "loss": 1.6038,
+      "step": 294
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9495627611114817e-05,
+      "loss": 1.6018,
+      "step": 295
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9491192588250198e-05,
+      "loss": 1.5559,
+      "step": 296
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9486738660670373e-05,
+      "loss": 1.6093,
+      "step": 297
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.948226583724675e-05,
+      "loss": 1.4772,
+      "step": 298
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.947777412688838e-05,
+      "loss": 1.6215,
+      "step": 299
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9473263538541916e-05,
+      "loss": 1.6031,
+      "step": 300
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9468734081191627e-05,
+      "loss": 1.6468,
+      "step": 301
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9464185763859365e-05,
+      "loss": 1.5391,
+      "step": 302
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.945961859560454e-05,
+      "loss": 1.5916,
+      "step": 303
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9455032585524115e-05,
+      "loss": 1.5238,
+      "step": 304
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9450427742752583e-05,
+      "loss": 1.5679,
+      "step": 305
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9445804076461946e-05,
+      "loss": 1.4694,
+      "step": 306
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.944116159586169e-05,
+      "loss": 1.7224,
+      "step": 307
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.94365003101988e-05,
+      "loss": 1.5224,
+      "step": 308
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.943182022875769e-05,
+      "loss": 1.4027,
+      "step": 309
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9427121360860233e-05,
+      "loss": 1.6428,
+      "step": 310
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9422403715865708e-05,
+      "loss": 1.5872,
+      "step": 311
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9417667303170803e-05,
+      "loss": 1.5616,
+      "step": 312
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9412912132209573e-05,
+      "loss": 1.7097,
+      "step": 313
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9408138212453456e-05,
+      "loss": 1.5574,
+      "step": 314
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.940334555341122e-05,
+      "loss": 1.6133,
+      "step": 315
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9398534164628968e-05,
+      "loss": 1.5629,
+      "step": 316
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.93937040556901e-05,
+      "loss": 1.4919,
+      "step": 317
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.938885523621531e-05,
+      "loss": 1.4721,
+      "step": 318
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9383987715862554e-05,
+      "loss": 1.7848,
+      "step": 319
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9379101504327044e-05,
+      "loss": 1.5623,
+      "step": 320
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 1.6131,
+      "step": 321
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9369273046674708e-05,
+      "loss": 1.6132,
+      "step": 322
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.936433082013437e-05,
+      "loss": 1.5333,
+      "step": 323
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.935936994156421e-05,
+      "loss": 1.554,
+      "step": 324
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9354390420845387e-05,
+      "loss": 1.5865,
+      "step": 325
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.934939226789619e-05,
+      "loss": 1.5857,
+      "step": 326
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9344375492672024e-05,
+      "loss": 1.5555,
+      "step": 327
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.933934010516539e-05,
+      "loss": 1.5558,
+      "step": 328
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.933428611540585e-05,
+      "loss": 1.6296,
+      "step": 329
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932921353346003e-05,
+      "loss": 1.5004,
+      "step": 330
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932412236943158e-05,
+      "loss": 1.6247,
+      "step": 331
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9319012633461164e-05,
+      "loss": 1.6277,
+      "step": 332
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9313884335726443e-05,
+      "loss": 1.7737,
+      "step": 333
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9308737486442045e-05,
+      "loss": 1.5115,
+      "step": 334
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9303572095859545e-05,
+      "loss": 1.5231,
+      "step": 335
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9298388174267463e-05,
+      "loss": 1.5685,
+      "step": 336
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9293185731991212e-05,
+      "loss": 1.4307,
+      "step": 337
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9287964779393105e-05,
+      "loss": 1.6424,
+      "step": 338
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9282725326872324e-05,
+      "loss": 1.5317,
+      "step": 339
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.92774673848649e-05,
+      "loss": 1.5713,
+      "step": 340
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.927219096384368e-05,
+      "loss": 1.4465,
+      "step": 341
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9266896074318335e-05,
+      "loss": 1.4761,
+      "step": 342
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9261582726835316e-05,
+      "loss": 1.6569,
+      "step": 343
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.925625093197783e-05,
+      "loss": 1.588,
+      "step": 344
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9250900700365837e-05,
+      "loss": 1.6713,
+      "step": 345
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.924553204265602e-05,
+      "loss": 1.6163,
+      "step": 346
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9240144969541754e-05,
+      "loss": 1.5906,
+      "step": 347
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.923473949175311e-05,
+      "loss": 1.561,
+      "step": 348
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9229315620056805e-05,
+      "loss": 1.4219,
+      "step": 349
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9223873365256192e-05,
+      "loss": 1.5169,
+      "step": 350
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.921841273819125e-05,
+      "loss": 1.6726,
+      "step": 351
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9212933749738546e-05,
+      "loss": 1.4714,
+      "step": 352
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.920743641081122e-05,
+      "loss": 1.5211,
+      "step": 353
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.920192073235896e-05,
+      "loss": 1.6119,
+      "step": 354
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.919638672536799e-05,
+      "loss": 1.5366,
+      "step": 355
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9190834400861035e-05,
+      "loss": 1.4784,
+      "step": 356
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.918526376989731e-05,
+      "loss": 1.5361,
+      "step": 357
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9179674843572487e-05,
+      "loss": 1.734,
+      "step": 358
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9174067633018682e-05,
+      "loss": 1.5957,
+      "step": 359
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9168442149404438e-05,
+      "loss": 1.5167,
+      "step": 360
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.916279840393467e-05,
+      "loss": 1.4856,
+      "step": 361
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9157136407850706e-05,
+      "loss": 1.5079,
+      "step": 362
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 1.6342,
+      "step": 363
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9145757708987103e-05,
+      "loss": 1.6238,
+      "step": 364
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.914004102887176e-05,
+      "loss": 1.602,
+      "step": 365
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9134306143470722e-05,
+      "loss": 1.6316,
+      "step": 366
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9128553064206835e-05,
+      "loss": 1.3469,
+      "step": 367
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.912278180253918e-05,
+      "loss": 1.5529,
+      "step": 368
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.911699236996305e-05,
+      "loss": 1.4857,
+      "step": 369
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9111184778009934e-05,
+      "loss": 1.5868,
+      "step": 370
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9105359038247484e-05,
+      "loss": 1.5045,
+      "step": 371
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9099515162279515e-05,
+      "loss": 1.6578,
+      "step": 372
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.909365316174595e-05,
+      "loss": 1.4851,
+      "step": 373
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.908777304832282e-05,
+      "loss": 1.4573,
+      "step": 374
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9081874833722234e-05,
+      "loss": 1.5313,
+      "step": 375
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9075958529692355e-05,
+      "loss": 1.4284,
+      "step": 376
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9070024148017375e-05,
+      "loss": 1.3889,
+      "step": 377
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.906407170051749e-05,
+      "loss": 1.5237,
+      "step": 378
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.905810119904889e-05,
+      "loss": 1.5036,
+      "step": 379
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9052112655503713e-05,
+      "loss": 1.6423,
+      "step": 380
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9046106081810047e-05,
+      "loss": 1.5939,
+      "step": 381
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.904008148993188e-05,
+      "loss": 1.643,
+      "step": 382
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.903403889186909e-05,
+      "loss": 1.5539,
+      "step": 383
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9027978299657436e-05,
+      "loss": 1.5466,
+      "step": 384
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9021899725368498e-05,
+      "loss": 1.4804,
+      "step": 385
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9015803181109685e-05,
+      "loss": 1.6738,
+      "step": 386
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 1.6189,
+      "step": 387
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9003556231290988e-05,
+      "loss": 1.3754,
+      "step": 388
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8997405850124786e-05,
+      "loss": 1.4995,
+      "step": 389
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8991237547776014e-05,
+      "loss": 1.7472,
+      "step": 390
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.89850513365308e-05,
+      "loss": 1.5819,
+      "step": 391
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.897884722871094e-05,
+      "loss": 1.4441,
+      "step": 392
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8972625236673887e-05,
+      "loss": 1.4998,
+      "step": 393
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8966385372812703e-05,
+      "loss": 1.7693,
+      "step": 394
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.896012764955605e-05,
+      "loss": 1.5972,
+      "step": 395
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.895385207936817e-05,
+      "loss": 1.4894,
+      "step": 396
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8947558674748844e-05,
+      "loss": 1.6153,
+      "step": 397
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8941247448233386e-05,
+      "loss": 1.5506,
+      "step": 398
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8934918412392596e-05,
+      "loss": 1.4783,
+      "step": 399
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8928571579832756e-05,
+      "loss": 1.6733,
+      "step": 400
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.892220696319559e-05,
+      "loss": 1.4514,
+      "step": 401
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.891582457515825e-05,
+      "loss": 1.6588,
+      "step": 402
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8909424428433278e-05,
+      "loss": 1.5374,
+      "step": 403
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.89030065357686e-05,
+      "loss": 1.5054,
+      "step": 404
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 1.5964,
+      "step": 405
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.889011756378849e-05,
+      "loss": 1.5827,
+      "step": 406
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.888364651014553e-05,
+      "loss": 1.4867,
+      "step": 407
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.887715776190775e-05,
+      "loss": 1.5016,
+      "step": 408
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8870651331999542e-05,
+      "loss": 1.6249,
+      "step": 409
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.886412723338052e-05,
+      "loss": 1.6036,
+      "step": 410
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8857585479045493e-05,
+      "loss": 1.6172,
+      "step": 411
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.885102608202444e-05,
+      "loss": 1.5305,
+      "step": 412
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8844449055382473e-05,
+      "loss": 1.5793,
+      "step": 413
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8837854412219828e-05,
+      "loss": 1.6235,
+      "step": 414
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8831242165671816e-05,
+      "loss": 1.6813,
+      "step": 415
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8824612328908828e-05,
+      "loss": 1.553,
+      "step": 416
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8817964915136277e-05,
+      "loss": 1.5233,
+      "step": 417
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8811299937594598e-05,
+      "loss": 1.5602,
+      "step": 418
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.88046174095592e-05,
+      "loss": 1.6497,
+      "step": 419
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8797917344340453e-05,
+      "loss": 1.5556,
+      "step": 420
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8791199755283664e-05,
+      "loss": 1.4972,
+      "step": 421
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8784464655769033e-05,
+      "loss": 1.4895,
+      "step": 422
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8777712059211643e-05,
+      "loss": 1.4853,
+      "step": 423
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8770941979061432e-05,
+      "loss": 1.5,
+      "step": 424
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8764154428803155e-05,
+      "loss": 1.5266,
+      "step": 425
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.875734942195637e-05,
+      "loss": 1.6001,
+      "step": 426
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.87505269720754e-05,
+      "loss": 1.6224,
+      "step": 427
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8743687092749318e-05,
+      "loss": 1.8942,
+      "step": 428
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8736829797601903e-05,
+      "loss": 1.597,
+      "step": 429
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8729955100291634e-05,
+      "loss": 1.4492,
+      "step": 430
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.872306301451165e-05,
+      "loss": 1.553,
+      "step": 431
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8716153553989716e-05,
+      "loss": 1.6568,
+      "step": 432
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8709226732488216e-05,
+      "loss": 1.6419,
+      "step": 433
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.87022825638041e-05,
+      "loss": 1.4201,
+      "step": 434
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8695321061768886e-05,
+      "loss": 1.5144,
+      "step": 435
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.868834224024861e-05,
+      "loss": 1.6008,
+      "step": 436
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.86813461131438e-05,
+      "loss": 1.5232,
+      "step": 437
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8674332694389464e-05,
+      "loss": 1.5325,
+      "step": 438
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8667301997955038e-05,
+      "loss": 1.5205,
+      "step": 439
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.5523,
+      "step": 440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8653188828095754e-05,
+      "loss": 1.6117,
+      "step": 441
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8646106382781738e-05,
+      "loss": 1.5324,
+      "step": 442
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8639006716009275e-05,
+      "loss": 1.5437,
+      "step": 443
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8631889841919596e-05,
+      "loss": 1.646,
+      "step": 444
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.862475577468821e-05,
+      "loss": 1.4662,
+      "step": 445
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8617604528524876e-05,
+      "loss": 1.6842,
+      "step": 446
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 1.6015,
+      "step": 447
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8603250556412418e-05,
+      "loss": 1.4642,
+      "step": 448
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8596047859053776e-05,
+      "loss": 1.5905,
+      "step": 449
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8588828039944086e-05,
+      "loss": 1.3811,
+      "step": 450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8581591113463903e-05,
+      "loss": 1.477,
+      "step": 451
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8574337094027858e-05,
+      "loss": 1.5653,
+      "step": 452
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8567065996084628e-05,
+      "loss": 1.6238,
+      "step": 453
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8559777834116906e-05,
+      "loss": 1.5427,
+      "step": 454
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8552472622641372e-05,
+      "loss": 1.478,
+      "step": 455
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.854515037620867e-05,
+      "loss": 1.4926,
+      "step": 456
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8537811109403372e-05,
+      "loss": 1.5102,
+      "step": 457
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8530454836843953e-05,
+      "loss": 1.5598,
+      "step": 458
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8523081573182754e-05,
+      "loss": 1.6468,
+      "step": 459
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.851569133310597e-05,
+      "loss": 1.5438,
+      "step": 460
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8508284131333604e-05,
+      "loss": 1.4735,
+      "step": 461
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8500859982619438e-05,
+      "loss": 1.4544,
+      "step": 462
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8493418901751016e-05,
+      "loss": 1.5896,
+      "step": 463
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8485960903549614e-05,
+      "loss": 1.5448,
+      "step": 464
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.847848600287019e-05,
+      "loss": 1.48,
+      "step": 465
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8470994214601378e-05,
+      "loss": 1.5051,
+      "step": 466
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.846348555366544e-05,
+      "loss": 1.4919,
+      "step": 467
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.845596003501826e-05,
+      "loss": 1.4351,
+      "step": 468
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8448417673649292e-05,
+      "loss": 1.5142,
+      "step": 469
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.844085848458153e-05,
+      "loss": 1.5037,
+      "step": 470
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8433282482871497e-05,
+      "loss": 1.4373,
+      "step": 471
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8425689683609198e-05,
+      "loss": 1.3986,
+      "step": 472
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8418080101918095e-05,
+      "loss": 1.5879,
+      "step": 473
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.841045375295508e-05,
+      "loss": 1.5525,
+      "step": 474
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8402810651910444e-05,
+      "loss": 1.4899,
+      "step": 475
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.839515081400784e-05,
+      "loss": 1.5907,
+      "step": 476
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8387474254504265e-05,
+      "loss": 1.4677,
+      "step": 477
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8379780988690014e-05,
+      "loss": 1.451,
+      "step": 478
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.837207103188866e-05,
+      "loss": 1.3821,
+      "step": 479
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8364344399457028e-05,
+      "loss": 1.5024,
+      "step": 480
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8356601106785148e-05,
+      "loss": 1.5263,
+      "step": 481
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8348841169296247e-05,
+      "loss": 1.5388,
+      "step": 482
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8341064602446686e-05,
+      "loss": 1.6173,
+      "step": 483
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8333271421725968e-05,
+      "loss": 1.5454,
+      "step": 484
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8325461642656676e-05,
+      "loss": 1.4468,
+      "step": 485
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8317635280794466e-05,
+      "loss": 1.3626,
+      "step": 486
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8309792351728006e-05,
+      "loss": 1.4551,
+      "step": 487
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8301932871078975e-05,
+      "loss": 1.3878,
+      "step": 488
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 1.525,
+      "step": 489
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.828616431768472e-05,
+      "loss": 1.4175,
+      "step": 490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8278255276347563e-05,
+      "loss": 1.5459,
+      "step": 491
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8270329746243903e-05,
+      "loss": 1.612,
+      "step": 492
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.826238774315995e-05,
+      "loss": 1.4209,
+      "step": 493
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8254429282914715e-05,
+      "loss": 1.5253,
+      "step": 494
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.824645438135999e-05,
+      "loss": 1.4988,
+      "step": 495
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.823846305438032e-05,
+      "loss": 1.4734,
+      "step": 496
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8230455317892957e-05,
+      "loss": 1.5854,
+      "step": 497
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.822243118784785e-05,
+      "loss": 1.3589,
+      "step": 498
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8214390680227588e-05,
+      "loss": 1.5336,
+      "step": 499
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.82063338110474e-05,
+      "loss": 1.4623,
+      "step": 500
+    }
+  ],
+  "max_steps": 2295,
+  "num_train_epochs": 3,
+  "total_flos": 1.169292903139246e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90426bc5af867fb9415efe861f9c4807e7889b32503350eedff624f9a50641e4
+size 3707

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "decapoda-research/llama-13b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "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-13b-hf/snapshots/438770a656712a5072229b62256521845d4de5ce/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 sha256:90426bc5af867fb9415efe861f9c4807e7889b32503350eedff624f9a50641e4
+size 3707