update

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.3547392290249433,
+    "eval_loss": 4.010603904724121,
+    "eval_runtime": 10.1127,
+    "eval_samples": 35,
+    "eval_samples_per_second": 3.461,
+    "eval_steps_per_second": 0.198,
+    "perplexity": 55.18018407719929,
+    "train_loss": 3.63210295110708,
+    "train_runtime": 159180.7121,
+    "train_samples": 311198,
+    "train_samples_per_second": 1.955,
+    "train_steps_per_second": 0.031
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/data/searchgpt/pretrained_models/Llama-2-13b-chat-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 68419
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.3547392290249433,
+    "eval_loss": 4.010603904724121,
+    "eval_runtime": 10.1127,
+    "eval_samples": 35,
+    "eval_samples_per_second": 3.461,
+    "eval_steps_per_second": 0.198,
+    "perplexity": 55.18018407719929
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a678d79fb7dffaa8936e31cae0eb9fb648d18589ba5136071b18b15861a46cc
+size 10634274292

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0790bf6547ae35d4b3a45038195add7b296eee571471ab20096d09a0838be7
+size 9956615018

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5041c0ad3c0a0fd58fc97fe9d94538a624d936303834287fe2c002a8fe02da1e
+size 6186849391

pytorch_model.bin.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26076984320
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

runs/Jul29_19-31-21_715436/events.out.tfevents.1690631549.715436.69585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a44ec1f3b1b520c46ac59ec5228b7f1bc4c9f348f08af3c62712fba192a8f34
+size 112352

runs/Jul29_19-31-21_715436/events.out.tfevents.1690790904.715436.69585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be619c22858b9a12daedc56ced1b237f5783914cbf8e31fb13546267a630a40
+size 411

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5ab2c18ed07a14f3aa55518dcf08bbee4fe86c9423e86ba61f60a82ab31fa7
+size 1077901

tokenizer_config.json

@@ -0,0 +1,36 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 3.63210295110708,
+    "train_runtime": 159180.7121,
+    "train_samples": 311198,
+    "train_samples_per_second": 1.955,
+    "train_steps_per_second": 0.031
+}

trainer_state.json

@@ -0,0 +1,3820 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998971722365039,
+  "global_step": 4862,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0,
+      "loss": 10.4794,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.855516318488718e-05,
+      "loss": 10.195,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.852528029402888e-05,
+      "loss": 9.0314,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00011711032636977435,
+      "loss": 8.3018,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012935198326770444,
+      "loss": 8.0744,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013849539740317057,
+      "loss": 7.8706,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.11661608233036805,
+      "eval_loss": 7.881457328796387,
+      "eval_runtime": 10.388,
+      "eval_samples_per_second": 3.369,
+      "eval_steps_per_second": 0.193,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014579627258973804,
+      "loss": 7.6597,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001518740958549795,
+      "loss": 7.4752,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015708044347891603,
+      "loss": 7.3497,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001616341750666857,
+      "loss": 7.256,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001656808271083118,
+      "loss": 7.1325,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.1523669980812838,
+      "eval_loss": 7.2515740394592285,
+      "eval_runtime": 10.3168,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016932210037684612,
+      "loss": 7.052,
+      "step": 110
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001723141171704594,
+      "loss": 6.9402,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017537326012423199,
+      "loss": 6.8498,
+      "step": 130
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001781950123852968,
+      "loss": 6.7319,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00018056004207494319,
+      "loss": 6.6609,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.17777080062794348,
+      "eval_loss": 6.819276809692383,
+      "eval_runtime": 10.3083,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00018301924610008189,
+      "loss": 6.5659,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00018532269677939782,
+      "loss": 6.4576,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00018748895370481112,
+      "loss": 6.4062,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00018953344483335556,
+      "loss": 6.2343,
+      "step": 190
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019146913367833817,
+      "loss": 6.0795,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.2014233385661957,
+      "eval_loss": 6.384451389312744,
+      "eval_runtime": 10.3147,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019330701776944063,
+      "loss": 6.0014,
+      "step": 210
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019505650713185044,
+      "loss": 5.9148,
+      "step": 220
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019672571585424665,
+      "loss": 5.7346,
+      "step": 230
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019832168964685297,
+      "loss": 5.6229,
+      "step": 240
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001998505855457085,
+      "loss": 5.5911,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.2269108669108669,
+      "eval_loss": 5.930122375488281,
+      "eval_runtime": 10.2989,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.194,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001996535296665223,
+      "loss": 5.4576,
+      "step": 260
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001992204417496752,
+      "loss": 5.4233,
+      "step": 270
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019878735383282807,
+      "loss": 5.3452,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019835426591598097,
+      "loss": 5.2178,
+      "step": 290
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019792117799913384,
+      "loss": 5.0416,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.25283097854526426,
+      "eval_loss": 5.53858757019043,
+      "eval_runtime": 10.2964,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001974880900822867,
+      "loss": 4.9763,
+      "step": 310
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019705500216543958,
+      "loss": 4.9485,
+      "step": 320
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019662191424859245,
+      "loss": 4.7805,
+      "step": 330
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019618882633174535,
+      "loss": 4.7348,
+      "step": 340
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019575573841489822,
+      "loss": 4.6488,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.280118611547183,
+      "eval_loss": 5.200571060180664,
+      "eval_runtime": 10.3088,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019532265049805112,
+      "loss": 4.5881,
+      "step": 360
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000194889562581204,
+      "loss": 4.5292,
+      "step": 370
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001944564746643569,
+      "loss": 4.4588,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019402338674750976,
+      "loss": 4.3398,
+      "step": 390
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019359029883066263,
+      "loss": 4.2704,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.2968986568986569,
+      "eval_loss": 4.920831680297852,
+      "eval_runtime": 10.3195,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001931572109138155,
+      "loss": 4.3331,
+      "step": 410
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001927241229969684,
+      "loss": 4.2611,
+      "step": 420
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019229103508012127,
+      "loss": 4.1317,
+      "step": 430
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019185794716327414,
+      "loss": 4.1948,
+      "step": 440
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019142485924642704,
+      "loss": 4.1254,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.306959706959707,
+      "eval_loss": 4.744773864746094,
+      "eval_runtime": 10.2994,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.194,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001909917713295799,
+      "loss": 4.1134,
+      "step": 460
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001905586834127328,
+      "loss": 4.0577,
+      "step": 470
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019012559549588568,
+      "loss": 4.0536,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018969250757903855,
+      "loss": 4.0161,
+      "step": 490
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018925941966219142,
+      "loss": 3.9946,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.3148438862724577,
+      "eval_loss": 4.626054286956787,
+      "eval_runtime": 10.2947,
+      "eval_samples_per_second": 3.4,
+      "eval_steps_per_second": 0.194,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00018882633174534431,
+      "loss": 4.0105,
+      "step": 510
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018839324382849718,
+      "loss": 3.9675,
+      "step": 520
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018796015591165008,
+      "loss": 3.9762,
+      "step": 530
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018752706799480295,
+      "loss": 3.8776,
+      "step": 540
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00018709398007795585,
+      "loss": 3.9233,
+      "step": 550
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.3190301761730333,
+      "eval_loss": 4.543696880340576,
+      "eval_runtime": 10.3044,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 550
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00018666089216110872,
+      "loss": 3.9052,
+      "step": 560
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001862278042442616,
+      "loss": 3.8801,
+      "step": 570
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00018579471632741446,
+      "loss": 3.8455,
+      "step": 580
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00018536162841056733,
+      "loss": 3.8847,
+      "step": 590
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00018492854049372023,
+      "loss": 3.8564,
+      "step": 600
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.3223233908948195,
+      "eval_loss": 4.484829425811768,
+      "eval_runtime": 10.3163,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 600
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001844954525768731,
+      "loss": 3.8747,
+      "step": 610
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000184062364660026,
+      "loss": 3.8457,
+      "step": 620
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018362927674317887,
+      "loss": 3.8098,
+      "step": 630
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018319618882633177,
+      "loss": 3.8504,
+      "step": 640
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00018276310090948464,
+      "loss": 3.8044,
+      "step": 650
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.3253096110238967,
+      "eval_loss": 4.4368672370910645,
+      "eval_runtime": 10.3128,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 650
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00018233001299263754,
+      "loss": 3.8319,
+      "step": 660
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00018189692507579038,
+      "loss": 3.7511,
+      "step": 670
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00018146383715894328,
+      "loss": 3.7444,
+      "step": 680
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00018103074924209615,
+      "loss": 3.7481,
+      "step": 690
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00018059766132524902,
+      "loss": 3.7818,
+      "step": 700
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.32684458398744115,
+      "eval_loss": 4.409779071807861,
+      "eval_runtime": 10.3206,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 700
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018016457340840192,
+      "loss": 3.7294,
+      "step": 710
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017973148549155479,
+      "loss": 3.6994,
+      "step": 720
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017929839757470768,
+      "loss": 3.8228,
+      "step": 730
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017886530965786055,
+      "loss": 3.7021,
+      "step": 740
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017843222174101345,
+      "loss": 3.7394,
+      "step": 750
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.3294819466248038,
+      "eval_loss": 4.378809928894043,
+      "eval_runtime": 10.3201,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 750
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017799913382416632,
+      "loss": 3.723,
+      "step": 760
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001775660459073192,
+      "loss": 3.7536,
+      "step": 770
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017713295799047206,
+      "loss": 3.6932,
+      "step": 780
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017669987007362496,
+      "loss": 3.675,
+      "step": 790
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00017626678215677783,
+      "loss": 3.6735,
+      "step": 800
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.3317425431711146,
+      "eval_loss": 4.348150253295898,
+      "eval_runtime": 10.3035,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 800
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00017583369423993073,
+      "loss": 3.6496,
+      "step": 810
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001754006063230836,
+      "loss": 3.6922,
+      "step": 820
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00017496751840623647,
+      "loss": 3.6704,
+      "step": 830
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00017453443048938937,
+      "loss": 3.5991,
+      "step": 840
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00017410134257254224,
+      "loss": 3.6736,
+      "step": 850
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.3330821559392988,
+      "eval_loss": 4.325968265533447,
+      "eval_runtime": 10.3042,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 850
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001736682546556951,
+      "loss": 3.6847,
+      "step": 860
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00017323516673884798,
+      "loss": 3.6526,
+      "step": 870
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00017280207882200088,
+      "loss": 3.6376,
+      "step": 880
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00017236899090515375,
+      "loss": 3.6258,
+      "step": 890
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00017193590298830665,
+      "loss": 3.5848,
+      "step": 900
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.3351753008895866,
+      "eval_loss": 4.298619747161865,
+      "eval_runtime": 10.2928,
+      "eval_samples_per_second": 3.4,
+      "eval_steps_per_second": 0.194,
+      "step": 900
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00017150281507145952,
+      "loss": 3.6342,
+      "step": 910
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00017106972715461241,
+      "loss": 3.5997,
+      "step": 920
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00017063663923776528,
+      "loss": 3.6412,
+      "step": 930
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00017020355132091815,
+      "loss": 3.6093,
+      "step": 940
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016977046340407103,
+      "loss": 3.6733,
+      "step": 950
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.33535670678527824,
+      "eval_loss": 4.287267208099365,
+      "eval_runtime": 10.2981,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 950
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001693373754872239,
+      "loss": 3.6504,
+      "step": 960
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001689042875703768,
+      "loss": 3.6471,
+      "step": 970
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016847119965352966,
+      "loss": 3.652,
+      "step": 980
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00016803811173668256,
+      "loss": 3.585,
+      "step": 990
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016760502381983543,
+      "loss": 3.5897,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.33716378859236,
+      "eval_loss": 4.26666784286499,
+      "eval_runtime": 10.2978,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016717193590298833,
+      "loss": 3.6133,
+      "step": 1010
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001667388479861412,
+      "loss": 3.6513,
+      "step": 1020
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016630576006929407,
+      "loss": 3.5812,
+      "step": 1030
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016587267215244694,
+      "loss": 3.5337,
+      "step": 1040
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00016543958423559984,
+      "loss": 3.5743,
+      "step": 1050
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.3382243153671725,
+      "eval_loss": 4.2522406578063965,
+      "eval_runtime": 10.3129,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 1050
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001650064963187527,
+      "loss": 3.5491,
+      "step": 1060
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001645734084019056,
+      "loss": 3.6083,
+      "step": 1070
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00016414032048505848,
+      "loss": 3.5326,
+      "step": 1080
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00016370723256821135,
+      "loss": 3.4979,
+      "step": 1090
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00016327414465136425,
+      "loss": 3.5075,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23,
+      "eval_accuracy": 0.33963369963369966,
+      "eval_loss": 4.232938289642334,
+      "eval_runtime": 10.3143,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00016284105673451712,
+      "loss": 3.5368,
+      "step": 1110
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00016240796881767,
+      "loss": 3.5292,
+      "step": 1120
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00016197488090082286,
+      "loss": 3.5705,
+      "step": 1130
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00016154179298397576,
+      "loss": 3.568,
+      "step": 1140
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00016110870506712863,
+      "loss": 3.5513,
+      "step": 1150
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.3409802895517181,
+      "eval_loss": 4.225428581237793,
+      "eval_runtime": 10.3106,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 1150
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00016067561715028152,
+      "loss": 3.5785,
+      "step": 1160
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001602425292334344,
+      "loss": 3.4841,
+      "step": 1170
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001598094413165873,
+      "loss": 3.4861,
+      "step": 1180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00015937635339974016,
+      "loss": 3.5064,
+      "step": 1190
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015894326548289303,
+      "loss": 3.5034,
+      "step": 1200
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.3416082330368045,
+      "eval_loss": 4.212094783782959,
+      "eval_runtime": 10.3174,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 1200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001585101775660459,
+      "loss": 3.5208,
+      "step": 1210
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015807708964919877,
+      "loss": 3.544,
+      "step": 1220
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00015764400173235167,
+      "loss": 3.5995,
+      "step": 1230
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015721091381550454,
+      "loss": 3.5096,
+      "step": 1240
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015677782589865744,
+      "loss": 3.4953,
+      "step": 1250
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.34162218733647304,
+      "eval_loss": 4.200605869293213,
+      "eval_runtime": 10.3079,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 1250
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001563447379818103,
+      "loss": 3.4903,
+      "step": 1260
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001559116500649632,
+      "loss": 3.5847,
+      "step": 1270
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00015547856214811608,
+      "loss": 3.5003,
+      "step": 1280
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00015504547423126895,
+      "loss": 3.465,
+      "step": 1290
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00015461238631442182,
+      "loss": 3.5375,
+      "step": 1300
+    },
+    {
+      "epoch": 0.27,
+      "eval_accuracy": 0.3420408163265306,
+      "eval_loss": 4.193361282348633,
+      "eval_runtime": 10.3166,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 1300
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00015417929839757472,
+      "loss": 3.479,
+      "step": 1310
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001537462104807276,
+      "loss": 3.5274,
+      "step": 1320
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00015331312256388049,
+      "loss": 3.4944,
+      "step": 1330
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00015288003464703336,
+      "loss": 3.52,
+      "step": 1340
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00015244694673018623,
+      "loss": 3.5105,
+      "step": 1350
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.3424524681667539,
+      "eval_loss": 4.182863235473633,
+      "eval_runtime": 10.2862,
+      "eval_samples_per_second": 3.403,
+      "eval_steps_per_second": 0.194,
+      "step": 1350
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00015201385881333913,
+      "loss": 3.5494,
+      "step": 1360
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000151580770896492,
+      "loss": 3.4345,
+      "step": 1370
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00015114768297964487,
+      "loss": 3.4243,
+      "step": 1380
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00015071459506279774,
+      "loss": 3.5167,
+      "step": 1390
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00015028150714595063,
+      "loss": 3.4764,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.3427803942089656,
+      "eval_loss": 4.173154830932617,
+      "eval_runtime": 10.3105,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001498484192291035,
+      "loss": 3.4447,
+      "step": 1410
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001494153313122564,
+      "loss": 3.5027,
+      "step": 1420
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00014898224339540927,
+      "loss": 3.4461,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014854915547856217,
+      "loss": 3.4238,
+      "step": 1440
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014811606756171504,
+      "loss": 3.4558,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.34314320600034887,
+      "eval_loss": 4.165927886962891,
+      "eval_runtime": 10.3072,
+      "eval_samples_per_second": 3.396,
+      "eval_steps_per_second": 0.194,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001476829796448679,
+      "loss": 3.502,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014724989172802078,
+      "loss": 3.5107,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00014681680381117365,
+      "loss": 3.5175,
+      "step": 1480
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014638371589432655,
+      "loss": 3.4825,
+      "step": 1490
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014595062797747942,
+      "loss": 3.4698,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "eval_accuracy": 0.34391766963195536,
+      "eval_loss": 4.1588826179504395,
+      "eval_runtime": 10.3017,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014551754006063232,
+      "loss": 3.4971,
+      "step": 1510
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001450844521437852,
+      "loss": 3.4639,
+      "step": 1520
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001446513642269381,
+      "loss": 3.485,
+      "step": 1530
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014421827631009096,
+      "loss": 3.5071,
+      "step": 1540
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014378518839324383,
+      "loss": 3.3979,
+      "step": 1550
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.3454038025466597,
+      "eval_loss": 4.149387359619141,
+      "eval_runtime": 10.2957,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 1550
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001433521004763967,
+      "loss": 3.4136,
+      "step": 1560
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001429190125595496,
+      "loss": 3.4406,
+      "step": 1570
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014248592464270247,
+      "loss": 3.4546,
+      "step": 1580
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014205283672585536,
+      "loss": 3.4742,
+      "step": 1590
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014161974880900824,
+      "loss": 3.4233,
+      "step": 1600
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.34525728240013953,
+      "eval_loss": 4.142571449279785,
+      "eval_runtime": 10.3075,
+      "eval_samples_per_second": 3.396,
+      "eval_steps_per_second": 0.194,
+      "step": 1600
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001411866608921611,
+      "loss": 3.4348,
+      "step": 1610
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000140753572975314,
+      "loss": 3.4015,
+      "step": 1620
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00014032048505846687,
+      "loss": 3.4459,
+      "step": 1630
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013988739714161974,
+      "loss": 3.4866,
+      "step": 1640
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013945430922477262,
+      "loss": 3.4162,
+      "step": 1650
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.34582243153671727,
+      "eval_loss": 4.141883373260498,
+      "eval_runtime": 10.3186,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 1650
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001390212213079255,
+      "loss": 3.4257,
+      "step": 1660
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00013858813339107838,
+      "loss": 3.386,
+      "step": 1670
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013815504547423128,
+      "loss": 3.4398,
+      "step": 1680
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013772195755738415,
+      "loss": 3.4502,
+      "step": 1690
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013728886964053705,
+      "loss": 3.4454,
+      "step": 1700
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.3463945578231293,
+      "eval_loss": 4.1352057456970215,
+      "eval_runtime": 10.3113,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 1700
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013685578172368992,
+      "loss": 3.4493,
+      "step": 1710
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00013642269380684282,
+      "loss": 3.4085,
+      "step": 1720
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00013598960588999566,
+      "loss": 3.4486,
+      "step": 1730
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00013555651797314853,
+      "loss": 3.4503,
+      "step": 1740
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00013512343005630143,
+      "loss": 3.4127,
+      "step": 1750
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.34649921507064363,
+      "eval_loss": 4.134985446929932,
+      "eval_runtime": 10.2957,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 1750
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001346903421394543,
+      "loss": 3.4014,
+      "step": 1760
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001342572542226072,
+      "loss": 3.4282,
+      "step": 1770
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00013382416630576007,
+      "loss": 3.4109,
+      "step": 1780
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00013339107838891297,
+      "loss": 3.4397,
+      "step": 1790
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00013295799047206584,
+      "loss": 3.4347,
+      "step": 1800
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.3448456305599163,
+      "eval_loss": 4.133869171142578,
+      "eval_runtime": 10.3119,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 1800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00013252490255521873,
+      "loss": 3.413,
+      "step": 1810
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001320918146383716,
+      "loss": 3.3894,
+      "step": 1820
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00013165872672152448,
+      "loss": 3.3624,
+      "step": 1830
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00013122563880467735,
+      "loss": 3.397,
+      "step": 1840
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00013079255088783024,
+      "loss": 3.4176,
+      "step": 1850
+    },
+    {
+      "epoch": 0.38,
+      "eval_accuracy": 0.3472178615035758,
+      "eval_loss": 4.122106552124023,
+      "eval_runtime": 10.3021,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 1850
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00013035946297098311,
+      "loss": 3.4136,
+      "step": 1860
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00012992637505413598,
+      "loss": 3.4338,
+      "step": 1870
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012949328713728888,
+      "loss": 3.3931,
+      "step": 1880
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012906019922044175,
+      "loss": 3.4306,
+      "step": 1890
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012862711130359465,
+      "loss": 3.4145,
+      "step": 1900
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.3480830280830281,
+      "eval_loss": 4.11691427230835,
+      "eval_runtime": 10.3007,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.194,
+      "step": 1900
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00012819402338674752,
+      "loss": 3.4272,
+      "step": 1910
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001277609354699004,
+      "loss": 3.4037,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012732784755305326,
+      "loss": 3.4358,
+      "step": 1930
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012689475963620616,
+      "loss": 3.3797,
+      "step": 1940
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012646167171935903,
+      "loss": 3.407,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.34714111285539856,
+      "eval_loss": 4.114504814147949,
+      "eval_runtime": 10.2981,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 0.194,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00012602858380251193,
+      "loss": 3.3906,
+      "step": 1960
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001255954958856648,
+      "loss": 3.4079,
+      "step": 1970
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001251624079688177,
+      "loss": 3.3355,
+      "step": 1980
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00012472932005197057,
+      "loss": 3.3968,
+      "step": 1990
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00012429623213512344,
+      "loss": 3.3351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.34764346764346765,
+      "eval_loss": 4.10912561416626,
+      "eval_runtime": 10.3006,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.194,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001238631442182763,
+      "loss": 3.3782,
+      "step": 2010
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00012347336509311392,
+      "loss": 3.4039,
+      "step": 2020
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001230402771762668,
+      "loss": 3.3794,
+      "step": 2030
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001226071892594197,
+      "loss": 3.4188,
+      "step": 2040
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00012217410134257256,
+      "loss": 3.4255,
+      "step": 2050
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.34798534798534797,
+      "eval_loss": 4.109765529632568,
+      "eval_runtime": 10.3054,
+      "eval_samples_per_second": 3.396,
+      "eval_steps_per_second": 0.194,
+      "step": 2050
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00012174101342572544,
+      "loss": 3.3917,
+      "step": 2060
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012130792550887831,
+      "loss": 3.4352,
+      "step": 2070
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001208748375920312,
+      "loss": 3.384,
+      "step": 2080
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012044174967518407,
+      "loss": 3.389,
+      "step": 2090
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012000866175833694,
+      "loss": 3.396,
+      "step": 2100
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.34839699982557126,
+      "eval_loss": 4.104307651519775,
+      "eval_runtime": 10.3168,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 2100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00011957557384148984,
+      "loss": 3.3757,
+      "step": 2110
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001191424859246427,
+      "loss": 3.397,
+      "step": 2120
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011870939800779559,
+      "loss": 3.3469,
+      "step": 2130
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011827631009094846,
+      "loss": 3.3529,
+      "step": 2140
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011784322217410136,
+      "loss": 3.3477,
+      "step": 2150
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.34870399441828015,
+      "eval_loss": 4.099356651306152,
+      "eval_runtime": 10.3017,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 2150
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00011741013425725423,
+      "loss": 3.3823,
+      "step": 2160
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011697704634040711,
+      "loss": 3.362,
+      "step": 2170
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011654395842355998,
+      "loss": 3.3482,
+      "step": 2180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011611087050671288,
+      "loss": 3.3491,
+      "step": 2190
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011567778258986575,
+      "loss": 3.3604,
+      "step": 2200
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.3493040293040293,
+      "eval_loss": 4.094115734100342,
+      "eval_runtime": 10.3156,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 2200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011524469467301864,
+      "loss": 3.3527,
+      "step": 2210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001148116067561715,
+      "loss": 3.3814,
+      "step": 2220
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011437851883932438,
+      "loss": 3.36,
+      "step": 2230
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011394543092247727,
+      "loss": 3.3149,
+      "step": 2240
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011351234300563015,
+      "loss": 3.3521,
+      "step": 2250
+    },
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.34838304552590266,
+      "eval_loss": 4.095041751861572,
+      "eval_runtime": 10.3028,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 2250
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011307925508878303,
+      "loss": 3.3846,
+      "step": 2260
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001126461671719359,
+      "loss": 3.3441,
+      "step": 2270
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001122130792550888,
+      "loss": 3.3527,
+      "step": 2280
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011177999133824167,
+      "loss": 3.361,
+      "step": 2290
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011134690342139455,
+      "loss": 3.3027,
+      "step": 2300
+    },
+    {
+      "epoch": 0.47,
+      "eval_accuracy": 0.34924821210535495,
+      "eval_loss": 4.090921878814697,
+      "eval_runtime": 10.2945,
+      "eval_samples_per_second": 3.4,
+      "eval_steps_per_second": 0.194,
+      "step": 2300
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011091381550454742,
+      "loss": 3.3337,
+      "step": 2310
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011048072758770032,
+      "loss": 3.3423,
+      "step": 2320
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011004763967085319,
+      "loss": 3.3161,
+      "step": 2330
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010961455175400607,
+      "loss": 3.3455,
+      "step": 2340
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00010918146383715895,
+      "loss": 3.3831,
+      "step": 2350
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.3492412349555207,
+      "eval_loss": 4.084415435791016,
+      "eval_runtime": 10.3139,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 2350
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010874837592031182,
+      "loss": 3.3531,
+      "step": 2360
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010831528800346471,
+      "loss": 3.3944,
+      "step": 2370
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010788220008661758,
+      "loss": 3.3476,
+      "step": 2380
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010744911216977047,
+      "loss": 3.3656,
+      "step": 2390
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010701602425292334,
+      "loss": 3.3175,
+      "step": 2400
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.34965986394557824,
+      "eval_loss": 4.080374717712402,
+      "eval_runtime": 10.3156,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010658293633607624,
+      "loss": 3.3493,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010614984841922911,
+      "loss": 3.37,
+      "step": 2420
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010571676050238199,
+      "loss": 3.3488,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010528367258553486,
+      "loss": 3.3135,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010485058466868776,
+      "loss": 3.3065,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.35118785975928835,
+      "eval_loss": 4.075130939483643,
+      "eval_runtime": 10.3192,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 2450
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010441749675184063,
+      "loss": 3.3313,
+      "step": 2460
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010398440883499351,
+      "loss": 3.3206,
+      "step": 2470
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010355132091814638,
+      "loss": 3.3532,
+      "step": 2480
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010311823300129926,
+      "loss": 3.3202,
+      "step": 2490
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010268514508445215,
+      "loss": 3.3148,
+      "step": 2500
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.3493319379033665,
+      "eval_loss": 4.077237606048584,
+      "eval_runtime": 10.3211,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 2500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010225205716760502,
+      "loss": 3.3322,
+      "step": 2510
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010181896925075791,
+      "loss": 3.359,
+      "step": 2520
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010138588133391078,
+      "loss": 3.3148,
+      "step": 2530
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010095279341706368,
+      "loss": 3.3384,
+      "step": 2540
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010051970550021655,
+      "loss": 3.3136,
+      "step": 2550
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.35003663003663005,
+      "eval_loss": 4.075963973999023,
+      "eval_runtime": 10.3206,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 2550
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00010008661758336943,
+      "loss": 3.3407,
+      "step": 2560
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.96535296665223e-05,
+      "loss": 3.346,
+      "step": 2570
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.922044174967519e-05,
+      "loss": 3.3429,
+      "step": 2580
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.878735383282807e-05,
+      "loss": 3.3453,
+      "step": 2590
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.835426591598095e-05,
+      "loss": 3.3299,
+      "step": 2600
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.3503715332286761,
+      "eval_loss": 4.069892406463623,
+      "eval_runtime": 10.3115,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 2600
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.792117799913382e-05,
+      "loss": 3.2616,
+      "step": 2610
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.748809008228671e-05,
+      "loss": 3.2649,
+      "step": 2620
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.705500216543959e-05,
+      "loss": 3.2806,
+      "step": 2630
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.662191424859248e-05,
+      "loss": 3.3751,
+      "step": 2640
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.618882633174535e-05,
+      "loss": 3.3089,
+      "step": 2650
+    },
+    {
+      "epoch": 0.54,
+      "eval_accuracy": 0.3509227280655852,
+      "eval_loss": 4.068863868713379,
+      "eval_runtime": 10.3195,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 2650
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.575573841489823e-05,
+      "loss": 3.3234,
+      "step": 2660
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.532265049805112e-05,
+      "loss": 3.353,
+      "step": 2670
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.488956258120399e-05,
+      "loss": 3.3036,
+      "step": 2680
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.445647466435687e-05,
+      "loss": 3.3596,
+      "step": 2690
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.402338674750974e-05,
+      "loss": 3.3414,
+      "step": 2700
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.3499529042386185,
+      "eval_loss": 4.066127300262451,
+      "eval_runtime": 10.3126,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 2700
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.359029883066262e-05,
+      "loss": 3.362,
+      "step": 2710
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.315721091381551e-05,
+      "loss": 3.3545,
+      "step": 2720
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.272412299696839e-05,
+      "loss": 3.3639,
+      "step": 2730
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.229103508012126e-05,
+      "loss": 3.2914,
+      "step": 2740
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.185794716327415e-05,
+      "loss": 3.3434,
+      "step": 2750
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy": 0.35164137449851735,
+      "eval_loss": 4.059126377105713,
+      "eval_runtime": 10.3025,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 2750
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.142485924642703e-05,
+      "loss": 3.2933,
+      "step": 2760
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.099177132957992e-05,
+      "loss": 3.2918,
+      "step": 2770
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.055868341273279e-05,
+      "loss": 3.3093,
+      "step": 2780
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.012559549588567e-05,
+      "loss": 3.307,
+      "step": 2790
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.969250757903855e-05,
+      "loss": 3.2961,
+      "step": 2800
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.35194139194139196,
+      "eval_loss": 4.059094429016113,
+      "eval_runtime": 10.3044,
+      "eval_samples_per_second": 3.397,
+      "eval_steps_per_second": 0.194,
+      "step": 2800
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.925941966219143e-05,
+      "loss": 3.317,
+      "step": 2810
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.882633174534431e-05,
+      "loss": 3.2903,
+      "step": 2820
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.839324382849718e-05,
+      "loss": 3.3317,
+      "step": 2830
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.796015591165006e-05,
+      "loss": 3.2929,
+      "step": 2840
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.752706799480295e-05,
+      "loss": 3.3354,
+      "step": 2850
+    },
+    {
+      "epoch": 0.59,
+      "eval_accuracy": 0.3513064713064713,
+      "eval_loss": 4.057965278625488,
+      "eval_runtime": 10.3079,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 2850
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.709398007795583e-05,
+      "loss": 3.3293,
+      "step": 2860
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.66608921611087e-05,
+      "loss": 3.2948,
+      "step": 2870
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.622780424426159e-05,
+      "loss": 3.2694,
+      "step": 2880
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.579471632741447e-05,
+      "loss": 3.3123,
+      "step": 2890
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.536162841056736e-05,
+      "loss": 3.3188,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.3508041165184022,
+      "eval_loss": 4.052666664123535,
+      "eval_runtime": 10.314,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.492854049372023e-05,
+      "loss": 3.3388,
+      "step": 2910
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.449545257687311e-05,
+      "loss": 3.2808,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.4062364660026e-05,
+      "loss": 3.3221,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.362927674317888e-05,
+      "loss": 3.3259,
+      "step": 2940
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.319618882633175e-05,
+      "loss": 3.3485,
+      "step": 2950
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.3516623059480202,
+      "eval_loss": 4.051156044006348,
+      "eval_runtime": 10.3078,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 2950
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.276310090948462e-05,
+      "loss": 3.3199,
+      "step": 2960
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.23300129926375e-05,
+      "loss": 3.3162,
+      "step": 2970
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.189692507579039e-05,
+      "loss": 3.305,
+      "step": 2980
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.146383715894327e-05,
+      "loss": 3.3509,
+      "step": 2990
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.103074924209616e-05,
+      "loss": 3.2905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.3514878772021629,
+      "eval_loss": 4.0494561195373535,
+      "eval_runtime": 10.3082,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.059766132524903e-05,
+      "loss": 3.3209,
+      "step": 3010
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.016457340840191e-05,
+      "loss": 3.2824,
+      "step": 3020
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.97314854915548e-05,
+      "loss": 3.3032,
+      "step": 3030
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.929839757470768e-05,
+      "loss": 3.3071,
+      "step": 3040
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.886530965786055e-05,
+      "loss": 3.3421,
+      "step": 3050
+    },
+    {
+      "epoch": 0.63,
+      "eval_accuracy": 0.3516832373975231,
+      "eval_loss": 4.0482659339904785,
+      "eval_runtime": 10.3201,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3050
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.843222174101343e-05,
+      "loss": 3.3453,
+      "step": 3060
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.799913382416632e-05,
+      "loss": 3.3165,
+      "step": 3070
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.756604590731919e-05,
+      "loss": 3.3095,
+      "step": 3080
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.713295799047207e-05,
+      "loss": 3.2814,
+      "step": 3090
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.669987007362494e-05,
+      "loss": 3.3219,
+      "step": 3100
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.3521018663875807,
+      "eval_loss": 4.049413681030273,
+      "eval_runtime": 10.33,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.194,
+      "step": 3100
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.626678215677783e-05,
+      "loss": 3.3019,
+      "step": 3110
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.583369423993071e-05,
+      "loss": 3.3186,
+      "step": 3120
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.54006063230836e-05,
+      "loss": 3.2792,
+      "step": 3130
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.496751840623647e-05,
+      "loss": 3.2745,
+      "step": 3140
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.453443048938935e-05,
+      "loss": 3.2681,
+      "step": 3150
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.35144601430315714,
+      "eval_loss": 4.050104141235352,
+      "eval_runtime": 10.3142,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 3150
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.410134257254223e-05,
+      "loss": 3.3041,
+      "step": 3160
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.366825465569512e-05,
+      "loss": 3.3226,
+      "step": 3170
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 7.323516673884799e-05,
+      "loss": 3.2969,
+      "step": 3180
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.280207882200087e-05,
+      "loss": 3.2724,
+      "step": 3190
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.236899090515376e-05,
+      "loss": 3.3439,
+      "step": 3200
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.35251351822780397,
+      "eval_loss": 4.041363716125488,
+      "eval_runtime": 10.3183,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 3200
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.193590298830663e-05,
+      "loss": 3.3006,
+      "step": 3210
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.150281507145951e-05,
+      "loss": 3.3029,
+      "step": 3220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.106972715461238e-05,
+      "loss": 3.3077,
+      "step": 3230
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.063663923776527e-05,
+      "loss": 3.2692,
+      "step": 3240
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.020355132091815e-05,
+      "loss": 3.283,
+      "step": 3250
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.3523460666317809,
+      "eval_loss": 4.042195796966553,
+      "eval_runtime": 10.3212,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3250
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.977046340407103e-05,
+      "loss": 3.2465,
+      "step": 3260
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.93373754872239e-05,
+      "loss": 3.3109,
+      "step": 3270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.890428757037679e-05,
+      "loss": 3.27,
+      "step": 3280
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.847119965352967e-05,
+      "loss": 3.269,
+      "step": 3290
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.803811173668256e-05,
+      "loss": 3.2974,
+      "step": 3300
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.35278562707134137,
+      "eval_loss": 4.040924072265625,
+      "eval_runtime": 10.3185,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 3300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.760502381983543e-05,
+      "loss": 3.2892,
+      "step": 3310
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.717193590298831e-05,
+      "loss": 3.3283,
+      "step": 3320
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 6.67388479861412e-05,
+      "loss": 3.337,
+      "step": 3330
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.630576006929407e-05,
+      "loss": 3.2781,
+      "step": 3340
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.587267215244695e-05,
+      "loss": 3.2924,
+      "step": 3350
+    },
+    {
+      "epoch": 0.69,
+      "eval_accuracy": 0.35347636490493634,
+      "eval_loss": 4.039037227630615,
+      "eval_runtime": 10.3117,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 3350
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.543958423559982e-05,
+      "loss": 3.2447,
+      "step": 3360
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.50064963187527e-05,
+      "loss": 3.2743,
+      "step": 3370
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.457340840190559e-05,
+      "loss": 3.2559,
+      "step": 3380
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.414032048505847e-05,
+      "loss": 3.3076,
+      "step": 3390
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.370723256821134e-05,
+      "loss": 3.2148,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.3530507587650445,
+      "eval_loss": 4.033644199371338,
+      "eval_runtime": 10.313,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 3400
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.327414465136423e-05,
+      "loss": 3.2583,
+      "step": 3410
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.284105673451711e-05,
+      "loss": 3.2855,
+      "step": 3420
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.240796881767e-05,
+      "loss": 3.2763,
+      "step": 3430
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.201818969250758e-05,
+      "loss": 3.2905,
+      "step": 3440
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.158510177566046e-05,
+      "loss": 3.305,
+      "step": 3450
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy": 0.35271585557299845,
+      "eval_loss": 4.036759853363037,
+      "eval_runtime": 10.3081,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 3450
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.115201385881333e-05,
+      "loss": 3.3214,
+      "step": 3460
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 6.071892594196622e-05,
+      "loss": 3.2726,
+      "step": 3470
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 6.02858380251191e-05,
+      "loss": 3.3296,
+      "step": 3480
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.985275010827198e-05,
+      "loss": 3.3195,
+      "step": 3490
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.9419662191424864e-05,
+      "loss": 3.3217,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.3529112157683586,
+      "eval_loss": 4.034041404724121,
+      "eval_runtime": 10.3239,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.194,
+      "step": 3500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.898657427457774e-05,
+      "loss": 3.283,
+      "step": 3510
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.8553486357730626e-05,
+      "loss": 3.305,
+      "step": 3520
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.81203984408835e-05,
+      "loss": 3.2853,
+      "step": 3530
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.768731052403639e-05,
+      "loss": 3.2876,
+      "step": 3540
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.7254222607189265e-05,
+      "loss": 3.2529,
+      "step": 3550
+    },
+    {
+      "epoch": 0.73,
+      "eval_accuracy": 0.35336473050758765,
+      "eval_loss": 4.0340142250061035,
+      "eval_runtime": 10.3209,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3550
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.6821134690342135e-05,
+      "loss": 3.2383,
+      "step": 3560
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.638804677349502e-05,
+      "loss": 3.2793,
+      "step": 3570
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.59549588566479e-05,
+      "loss": 3.2438,
+      "step": 3580
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.552187093980078e-05,
+      "loss": 3.3002,
+      "step": 3590
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.508878302295366e-05,
+      "loss": 3.2654,
+      "step": 3600
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.3537205651491366,
+      "eval_loss": 4.02842378616333,
+      "eval_runtime": 10.3228,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3600
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.465569510610654e-05,
+      "loss": 3.2249,
+      "step": 3610
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 5.422260718925942e-05,
+      "loss": 3.3054,
+      "step": 3620
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.3789519272412304e-05,
+      "loss": 3.3084,
+      "step": 3630
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.335643135556518e-05,
+      "loss": 3.2655,
+      "step": 3640
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.2923343438718065e-05,
+      "loss": 3.2954,
+      "step": 3650
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.35309959881388453,
+      "eval_loss": 4.030717372894287,
+      "eval_runtime": 10.3217,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3650
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.249025552187094e-05,
+      "loss": 3.2667,
+      "step": 3660
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.2057167605023827e-05,
+      "loss": 3.2486,
+      "step": 3670
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.162407968817671e-05,
+      "loss": 3.2722,
+      "step": 3680
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.1190991771329574e-05,
+      "loss": 3.2465,
+      "step": 3690
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.075790385448246e-05,
+      "loss": 3.2247,
+      "step": 3700
+    },
+    {
+      "epoch": 0.76,
+      "eval_accuracy": 0.3532461189604047,
+      "eval_loss": 4.029253005981445,
+      "eval_runtime": 10.324,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.194,
+      "step": 3700
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.0324815937635336e-05,
+      "loss": 3.2807,
+      "step": 3710
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.989172802078822e-05,
+      "loss": 3.3076,
+      "step": 3720
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.94586401039411e-05,
+      "loss": 3.2756,
+      "step": 3730
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.902555218709398e-05,
+      "loss": 3.2565,
+      "step": 3740
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.8592464270246866e-05,
+      "loss": 3.2489,
+      "step": 3750
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.3537694051979766,
+      "eval_loss": 4.025887489318848,
+      "eval_runtime": 10.3294,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.194,
+      "step": 3750
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.815937635339974e-05,
+      "loss": 3.2754,
+      "step": 3760
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.772628843655263e-05,
+      "loss": 3.2691,
+      "step": 3770
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.7293200519705504e-05,
+      "loss": 3.2651,
+      "step": 3780
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.686011260285838e-05,
+      "loss": 3.2549,
+      "step": 3790
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.642702468601126e-05,
+      "loss": 3.2887,
+      "step": 3800
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.35346938775510206,
+      "eval_loss": 4.026332855224609,
+      "eval_runtime": 10.328,
+      "eval_samples_per_second": 3.389,
+      "eval_steps_per_second": 0.194,
+      "step": 3800
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.599393676916414e-05,
+      "loss": 3.2463,
+      "step": 3810
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.556084885231702e-05,
+      "loss": 3.2388,
+      "step": 3820
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.5127760935469905e-05,
+      "loss": 3.2527,
+      "step": 3830
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.469467301862278e-05,
+      "loss": 3.2754,
+      "step": 3840
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.426158510177566e-05,
+      "loss": 3.2275,
+      "step": 3850
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.3544531658817373,
+      "eval_loss": 4.022998809814453,
+      "eval_runtime": 10.3111,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 3850
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.3828497184928543e-05,
+      "loss": 3.2682,
+      "step": 3860
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.339540926808142e-05,
+      "loss": 3.3002,
+      "step": 3870
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.2962321351234305e-05,
+      "loss": 3.3368,
+      "step": 3880
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.252923343438718e-05,
+      "loss": 3.2938,
+      "step": 3890
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.2096145517540066e-05,
+      "loss": 3.2666,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.35355311355311353,
+      "eval_loss": 4.022049903869629,
+      "eval_runtime": 10.3226,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 3900
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.1663057600692944e-05,
+      "loss": 3.2478,
+      "step": 3910
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.122996968384582e-05,
+      "loss": 3.2521,
+      "step": 3920
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.07968817669987e-05,
+      "loss": 3.2966,
+      "step": 3930
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.036379385015158e-05,
+      "loss": 3.312,
+      "step": 3940
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.993070593330446e-05,
+      "loss": 3.2608,
+      "step": 3950
+    },
+    {
+      "epoch": 0.81,
+      "eval_accuracy": 0.35442525728240015,
+      "eval_loss": 4.020759582519531,
+      "eval_runtime": 10.3237,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.194,
+      "step": 3950
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.9497618016457344e-05,
+      "loss": 3.2372,
+      "step": 3960
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.906453009961023e-05,
+      "loss": 3.2765,
+      "step": 3970
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.86314421827631e-05,
+      "loss": 3.2758,
+      "step": 3980
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.819835426591598e-05,
+      "loss": 3.2194,
+      "step": 3990
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.776526634906886e-05,
+      "loss": 3.2701,
+      "step": 4000
+    },
+    {
+      "epoch": 0.82,
+      "eval_accuracy": 0.35390894819466245,
+      "eval_loss": 4.0217413902282715,
+      "eval_runtime": 10.3215,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 4000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.7332178432221744e-05,
+      "loss": 3.284,
+      "step": 4010
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.689909051537462e-05,
+      "loss": 3.2948,
+      "step": 4020
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.6466002598527506e-05,
+      "loss": 3.25,
+      "step": 4030
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.603291468168038e-05,
+      "loss": 3.285,
+      "step": 4040
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.559982676483326e-05,
+      "loss": 3.276,
+      "step": 4050
+    },
+    {
+      "epoch": 0.83,
+      "eval_accuracy": 0.35459270887842315,
+      "eval_loss": 4.0179877281188965,
+      "eval_runtime": 10.3103,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 4050
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.521004763967086e-05,
+      "loss": 3.2278,
+      "step": 4060
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.4776959722823735e-05,
+      "loss": 3.2552,
+      "step": 4070
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.434387180597661e-05,
+      "loss": 3.2346,
+      "step": 4080
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3910783889129496e-05,
+      "loss": 3.2365,
+      "step": 4090
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3477695972282374e-05,
+      "loss": 3.3152,
+      "step": 4100
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.3540763997906855,
+      "eval_loss": 4.020029067993164,
+      "eval_runtime": 10.3176,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 4100
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.304460805543526e-05,
+      "loss": 3.3036,
+      "step": 4110
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.2611520138588135e-05,
+      "loss": 3.2688,
+      "step": 4120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.217843222174102e-05,
+      "loss": 3.2507,
+      "step": 4130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.174534430489389e-05,
+      "loss": 3.2347,
+      "step": 4140
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1312256388046774e-05,
+      "loss": 3.2647,
+      "step": 4150
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.35356706785278214,
+      "eval_loss": 4.020448684692383,
+      "eval_runtime": 10.3118,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 4150
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.087916847119965e-05,
+      "loss": 3.2171,
+      "step": 4160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.0446080554352535e-05,
+      "loss": 3.2578,
+      "step": 4170
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.0012992637505416e-05,
+      "loss": 3.234,
+      "step": 4180
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.9579904720658297e-05,
+      "loss": 3.2092,
+      "step": 4190
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.9146816803811177e-05,
+      "loss": 3.23,
+      "step": 4200
+    },
+    {
+      "epoch": 0.86,
+      "eval_accuracy": 0.3542926914355486,
+      "eval_loss": 4.017209053039551,
+      "eval_runtime": 10.3231,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.194,
+      "step": 4200
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.871372888696405e-05,
+      "loss": 3.312,
+      "step": 4210
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.8280640970116936e-05,
+      "loss": 3.2474,
+      "step": 4220
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.7847553053269816e-05,
+      "loss": 3.1625,
+      "step": 4230
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.7414465136422697e-05,
+      "loss": 3.2238,
+      "step": 4240
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.6981377219575578e-05,
+      "loss": 3.2393,
+      "step": 4250
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.3541740798883656,
+      "eval_loss": 4.018671989440918,
+      "eval_runtime": 10.3185,
+      "eval_samples_per_second": 3.392,
+      "eval_steps_per_second": 0.194,
+      "step": 4250
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.654828930272846e-05,
+      "loss": 3.3045,
+      "step": 4260
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.6115201385881332e-05,
+      "loss": 3.235,
+      "step": 4270
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.5682113469034213e-05,
+      "loss": 3.2841,
+      "step": 4280
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.5249025552187094e-05,
+      "loss": 3.2213,
+      "step": 4290
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.4815937635339975e-05,
+      "loss": 3.2716,
+      "step": 4300
+    },
+    {
+      "epoch": 0.88,
+      "eval_accuracy": 0.35403453689167974,
+      "eval_loss": 4.0169243812561035,
+      "eval_runtime": 10.3295,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.194,
+      "step": 4300
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.4382849718492855e-05,
+      "loss": 3.2722,
+      "step": 4310
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.3949761801645733e-05,
+      "loss": 3.2522,
+      "step": 4320
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.3516673884798617e-05,
+      "loss": 3.2488,
+      "step": 4330
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.3083585967951497e-05,
+      "loss": 3.242,
+      "step": 4340
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.2650498051104375e-05,
+      "loss": 3.2383,
+      "step": 4350
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.35424385138670855,
+      "eval_loss": 4.014565467834473,
+      "eval_runtime": 10.3078,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 4350
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.2217410134257256e-05,
+      "loss": 3.2143,
+      "step": 4360
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.1784322217410136e-05,
+      "loss": 3.2828,
+      "step": 4370
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.1351234300563017e-05,
+      "loss": 3.2291,
+      "step": 4380
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0918146383715894e-05,
+      "loss": 3.243,
+      "step": 4390
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.0485058466868775e-05,
+      "loss": 3.3085,
+      "step": 4400
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.35441130298273155,
+      "eval_loss": 4.013179779052734,
+      "eval_runtime": 10.2995,
+      "eval_samples_per_second": 3.398,
+      "eval_steps_per_second": 0.194,
+      "step": 4400
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.0051970550021656e-05,
+      "loss": 3.2461,
+      "step": 4410
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9618882633174533e-05,
+      "loss": 3.2922,
+      "step": 4420
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.9185794716327414e-05,
+      "loss": 3.228,
+      "step": 4430
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.8752706799480295e-05,
+      "loss": 3.2603,
+      "step": 4440
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.8319618882633175e-05,
+      "loss": 3.249,
+      "step": 4450
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.354850863422292,
+      "eval_loss": 4.012799263000488,
+      "eval_runtime": 10.3085,
+      "eval_samples_per_second": 3.395,
+      "eval_steps_per_second": 0.194,
+      "step": 4450
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.7886530965786056e-05,
+      "loss": 3.2295,
+      "step": 4460
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.7453443048938937e-05,
+      "loss": 3.2927,
+      "step": 4470
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.7020355132091814e-05,
+      "loss": 3.2776,
+      "step": 4480
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6587267215244695e-05,
+      "loss": 3.2344,
+      "step": 4490
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6154179298397576e-05,
+      "loss": 3.2313,
+      "step": 4500
+    },
+    {
+      "epoch": 0.93,
+      "eval_accuracy": 0.35491365777080064,
+      "eval_loss": 4.013089656829834,
+      "eval_runtime": 10.3145,
+      "eval_samples_per_second": 3.393,
+      "eval_steps_per_second": 0.194,
+      "step": 4500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5721091381550456e-05,
+      "loss": 3.2486,
+      "step": 4510
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5288003464703334e-05,
+      "loss": 3.2489,
+      "step": 4520
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4854915547856216e-05,
+      "loss": 3.246,
+      "step": 4530
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4421827631009097e-05,
+      "loss": 3.1958,
+      "step": 4540
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3988739714161974e-05,
+      "loss": 3.2908,
+      "step": 4550
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.3545229373800802,
+      "eval_loss": 4.011632442474365,
+      "eval_runtime": 10.3115,
+      "eval_samples_per_second": 3.394,
+      "eval_steps_per_second": 0.194,
+      "step": 4550
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3555651797314855e-05,
+      "loss": 3.2766,
+      "step": 4560
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3122563880467736e-05,
+      "loss": 3.2029,
+      "step": 4570
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.2689475963620615e-05,
+      "loss": 3.2499,
+      "step": 4580
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.2299696838458208e-05,
+      "loss": 3.2521,
+      "step": 4590
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1866608921611087e-05,
+      "loss": 3.2715,
+      "step": 4600
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.3545089830804117,
+      "eval_loss": 4.0114569664001465,
+      "eval_runtime": 10.3298,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.194,
+      "step": 4600
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1433521004763968e-05,
+      "loss": 3.2073,
+      "step": 4610
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1000433087916847e-05,
+      "loss": 3.2471,
+      "step": 4620
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0567345171069728e-05,
+      "loss": 3.247,
+      "step": 4630
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0134257254222609e-05,
+      "loss": 3.27,
+      "step": 4640
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.701169337375488e-06,
+      "loss": 3.21,
+      "step": 4650
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.354613640327926,
+      "eval_loss": 4.011072158813477,
+      "eval_runtime": 10.3358,
+      "eval_samples_per_second": 3.386,
+      "eval_steps_per_second": 0.194,
+      "step": 4650
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.268081420528368e-06,
+      "loss": 3.2566,
+      "step": 4660
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.834993503681247e-06,
+      "loss": 3.2382,
+      "step": 4670
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.401905586834128e-06,
+      "loss": 3.2606,
+      "step": 4680
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.968817669987009e-06,
+      "loss": 3.2536,
+      "step": 4690
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.535729753139888e-06,
+      "loss": 3.2846,
+      "step": 4700
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.3547252747252747,
+      "eval_loss": 4.011029243469238,
+      "eval_runtime": 10.3241,
+      "eval_samples_per_second": 3.39,
+      "eval_steps_per_second": 0.194,
+      "step": 4700
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.102641836292767e-06,
+      "loss": 3.2191,
+      "step": 4710
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.669553919445648e-06,
+      "loss": 3.2743,
+      "step": 4720
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.2364660025985275e-06,
+      "loss": 3.2955,
+      "step": 4730
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.803378085751407e-06,
+      "loss": 3.2061,
+      "step": 4740
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.370290168904288e-06,
+      "loss": 3.2913,
+      "step": 4750
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.3547392290249433,
+      "eval_loss": 4.011110782623291,
+      "eval_runtime": 10.3213,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 0.194,
+      "step": 4750
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.937202252057168e-06,
+      "loss": 3.1993,
+      "step": 4760
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.504114335210048e-06,
+      "loss": 3.1921,
+      "step": 4770
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.071026418362928e-06,
+      "loss": 3.231,
+      "step": 4780
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6379385015158076e-06,
+      "loss": 3.268,
+      "step": 4790
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.204850584668688e-06,
+      "loss": 3.2902,
+      "step": 4800
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.3546694575266004,
+      "eval_loss": 4.011045455932617,
+      "eval_runtime": 10.3382,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 0.193,
+      "step": 4800
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.771762667821568e-06,
+      "loss": 3.2694,
+      "step": 4810
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.338674750974448e-06,
+      "loss": 3.226,
+      "step": 4820
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9055868341273278e-06,
+      "loss": 3.2843,
+      "step": 4830
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.472498917280208e-06,
+      "loss": 3.1971,
+      "step": 4840
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.039411000433088e-06,
+      "loss": 3.2593,
+      "step": 4850
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3547252747252747,
+      "eval_loss": 4.01063871383667,
+      "eval_runtime": 10.3267,
+      "eval_samples_per_second": 3.389,
+      "eval_steps_per_second": 0.194,
+      "step": 4850
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.06323083585968e-07,
+      "loss": 3.2748,
+      "step": 4860
+    },
+    {
+      "epoch": 1.0,
+      "step": 4862,
+      "total_flos": 9.97087842226311e+19,
+      "train_loss": 3.63210295110708,
+      "train_runtime": 159180.7121,
+      "train_samples_per_second": 1.955,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "max_steps": 4862,
+  "num_train_epochs": 1,
+  "total_flos": 9.97087842226311e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc50d6bc1e11bff0dce3375a4119ee233f71c5b1cfeaf94643a68af6aed2626
+size 5563