Upload 11 files

README.md

@@ -0,0 +1,57 @@
+---
+license: other
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: finetune_with_lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# finetune_with_lora
+
+This model is a fine-tuned version of [ruibin-wang/llama-7b-hf](https://huggingface.co/ruibin-wang/llama-7b-hf) on the customized dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.10.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.4033946073105007,
+    "train_runtime": 2282.7571,
+    "train_samples": 1437,
+    "train_samples_per_second": 6.295,
+    "train_steps_per_second": 3.15
+}

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "ruibin-wang/llama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee85c254efe3b49ff1e4ae48892d53dbf12334a78e9320ce84af0de8e57c5844
+size 3500315603

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13476835328
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "",
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--ruibin-wang--llama-7b-hf/snapshots/d2e4e3c6c145809f570bb9ada33e2734d305cecd/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.4033946073105007,
+    "train_runtime": 2282.7571,
+    "train_samples": 1437,
+    "train_samples_per_second": 6.295,
+    "train_steps_per_second": 3.15
+}

trainer_state.json

@@ -0,0 +1,2179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 7190,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.972183588317107e-05,
+      "loss": 1.5922,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.944367176634215e-05,
+      "loss": 1.0766,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.916550764951322e-05,
+      "loss": 0.7023,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.888734353268429e-05,
+      "loss": 0.6458,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.860917941585536e-05,
+      "loss": 0.6244,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.833101529902643e-05,
+      "loss": 0.5692,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.805285118219751e-05,
+      "loss": 0.5318,
+      "step": 140
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.777468706536858e-05,
+      "loss": 0.6218,
+      "step": 160
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.749652294853965e-05,
+      "loss": 0.5794,
+      "step": 180
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.721835883171071e-05,
+      "loss": 0.591,
+      "step": 200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.694019471488178e-05,
+      "loss": 0.582,
+      "step": 220
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.666203059805285e-05,
+      "loss": 0.6104,
+      "step": 240
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.638386648122393e-05,
+      "loss": 0.5706,
+      "step": 260
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.6105702364395e-05,
+      "loss": 0.6002,
+      "step": 280
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.582753824756607e-05,
+      "loss": 0.5189,
+      "step": 300
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.554937413073714e-05,
+      "loss": 0.5508,
+      "step": 320
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.52712100139082e-05,
+      "loss": 0.5644,
+      "step": 340
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.499304589707929e-05,
+      "loss": 0.5367,
+      "step": 360
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.471488178025035e-05,
+      "loss": 0.5947,
+      "step": 380
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.443671766342142e-05,
+      "loss": 0.5636,
+      "step": 400
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.41585535465925e-05,
+      "loss": 0.5824,
+      "step": 420
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.388038942976356e-05,
+      "loss": 0.6374,
+      "step": 440
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.360222531293463e-05,
+      "loss": 0.5929,
+      "step": 460
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.332406119610571e-05,
+      "loss": 0.5689,
+      "step": 480
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.304589707927678e-05,
+      "loss": 0.5719,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.276773296244784e-05,
+      "loss": 0.5469,
+      "step": 520
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 9.248956884561893e-05,
+      "loss": 0.5986,
+      "step": 540
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.221140472878998e-05,
+      "loss": 0.5868,
+      "step": 560
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.193324061196106e-05,
+      "loss": 0.596,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.165507649513213e-05,
+      "loss": 0.5653,
+      "step": 600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.13769123783032e-05,
+      "loss": 0.5527,
+      "step": 620
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 9.109874826147428e-05,
+      "loss": 0.5296,
+      "step": 640
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.082058414464535e-05,
+      "loss": 0.5399,
+      "step": 660
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.054242002781642e-05,
+      "loss": 0.6171,
+      "step": 680
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.026425591098748e-05,
+      "loss": 0.5256,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.998609179415855e-05,
+      "loss": 0.5679,
+      "step": 720
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 8.970792767732963e-05,
+      "loss": 0.5813,
+      "step": 740
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.94297635605007e-05,
+      "loss": 0.5831,
+      "step": 760
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.915159944367177e-05,
+      "loss": 0.5042,
+      "step": 780
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.887343532684285e-05,
+      "loss": 0.4984,
+      "step": 800
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.859527121001391e-05,
+      "loss": 0.5397,
+      "step": 820
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 8.831710709318498e-05,
+      "loss": 0.4707,
+      "step": 840
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 8.803894297635606e-05,
+      "loss": 0.5099,
+      "step": 860
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 8.776077885952713e-05,
+      "loss": 0.508,
+      "step": 880
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8.74826147426982e-05,
+      "loss": 0.5305,
+      "step": 900
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 8.720445062586928e-05,
+      "loss": 0.5146,
+      "step": 920
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 8.692628650904033e-05,
+      "loss": 0.5567,
+      "step": 940
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 8.664812239221141e-05,
+      "loss": 0.4569,
+      "step": 960
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 8.636995827538248e-05,
+      "loss": 0.5321,
+      "step": 980
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 8.609179415855355e-05,
+      "loss": 0.5039,
+      "step": 1000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.581363004172463e-05,
+      "loss": 0.5198,
+      "step": 1020
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.55354659248957e-05,
+      "loss": 0.5124,
+      "step": 1040
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 8.525730180806675e-05,
+      "loss": 0.4706,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 8.497913769123783e-05,
+      "loss": 0.5389,
+      "step": 1080
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 8.47009735744089e-05,
+      "loss": 0.5279,
+      "step": 1100
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.442280945757997e-05,
+      "loss": 0.5317,
+      "step": 1120
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.414464534075105e-05,
+      "loss": 0.549,
+      "step": 1140
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 8.386648122392212e-05,
+      "loss": 0.5743,
+      "step": 1160
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.358831710709319e-05,
+      "loss": 0.5269,
+      "step": 1180
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.331015299026426e-05,
+      "loss": 0.4979,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.303198887343532e-05,
+      "loss": 0.525,
+      "step": 1220
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.27538247566064e-05,
+      "loss": 0.5036,
+      "step": 1240
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.247566063977747e-05,
+      "loss": 0.5357,
+      "step": 1260
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 8.219749652294854e-05,
+      "loss": 0.5345,
+      "step": 1280
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 8.191933240611962e-05,
+      "loss": 0.499,
+      "step": 1300
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 8.164116828929068e-05,
+      "loss": 0.4976,
+      "step": 1320
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 8.136300417246176e-05,
+      "loss": 0.504,
+      "step": 1340
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 8.108484005563283e-05,
+      "loss": 0.4888,
+      "step": 1360
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.08066759388039e-05,
+      "loss": 0.5083,
+      "step": 1380
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 8.052851182197498e-05,
+      "loss": 0.5361,
+      "step": 1400
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 8.025034770514605e-05,
+      "loss": 0.5412,
+      "step": 1420
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.99721835883171e-05,
+      "loss": 0.471,
+      "step": 1440
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 7.969401947148818e-05,
+      "loss": 0.4617,
+      "step": 1460
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 7.941585535465925e-05,
+      "loss": 0.468,
+      "step": 1480
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 7.913769123783032e-05,
+      "loss": 0.4843,
+      "step": 1500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 7.88595271210014e-05,
+      "loss": 0.4567,
+      "step": 1520
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 7.858136300417247e-05,
+      "loss": 0.515,
+      "step": 1540
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 7.830319888734354e-05,
+      "loss": 0.4594,
+      "step": 1560
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 7.80250347705146e-05,
+      "loss": 0.4375,
+      "step": 1580
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 7.774687065368567e-05,
+      "loss": 0.4916,
+      "step": 1600
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 7.746870653685676e-05,
+      "loss": 0.5439,
+      "step": 1620
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 7.719054242002782e-05,
+      "loss": 0.5093,
+      "step": 1640
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 7.691237830319889e-05,
+      "loss": 0.5126,
+      "step": 1660
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 7.663421418636996e-05,
+      "loss": 0.4866,
+      "step": 1680
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 7.635605006954103e-05,
+      "loss": 0.4732,
+      "step": 1700
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 7.60778859527121e-05,
+      "loss": 0.4682,
+      "step": 1720
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.579972183588318e-05,
+      "loss": 0.5212,
+      "step": 1740
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.552155771905425e-05,
+      "loss": 0.4307,
+      "step": 1760
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.524339360222531e-05,
+      "loss": 0.4613,
+      "step": 1780
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.496522948539638e-05,
+      "loss": 0.4379,
+      "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.468706536856745e-05,
+      "loss": 0.4572,
+      "step": 1820
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.440890125173853e-05,
+      "loss": 0.4637,
+      "step": 1840
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.41307371349096e-05,
+      "loss": 0.4752,
+      "step": 1860
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.385257301808067e-05,
+      "loss": 0.4982,
+      "step": 1880
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.357440890125175e-05,
+      "loss": 0.4163,
+      "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.329624478442282e-05,
+      "loss": 0.4906,
+      "step": 1920
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 7.301808066759389e-05,
+      "loss": 0.4375,
+      "step": 1940
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 7.273991655076495e-05,
+      "loss": 0.4402,
+      "step": 1960
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 7.246175243393602e-05,
+      "loss": 0.52,
+      "step": 1980
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 7.21835883171071e-05,
+      "loss": 0.4718,
+      "step": 2000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.190542420027817e-05,
+      "loss": 0.5179,
+      "step": 2020
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 7.162726008344924e-05,
+      "loss": 0.4774,
+      "step": 2040
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 7.134909596662031e-05,
+      "loss": 0.477,
+      "step": 2060
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.107093184979138e-05,
+      "loss": 0.4805,
+      "step": 2080
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 7.079276773296244e-05,
+      "loss": 0.4507,
+      "step": 2100
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 7.051460361613353e-05,
+      "loss": 0.451,
+      "step": 2120
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 7.02364394993046e-05,
+      "loss": 0.4698,
+      "step": 2140
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 6.995827538247566e-05,
+      "loss": 0.4611,
+      "step": 2160
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 6.968011126564673e-05,
+      "loss": 0.4324,
+      "step": 2180
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.94019471488178e-05,
+      "loss": 0.4085,
+      "step": 2200
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 6.912378303198888e-05,
+      "loss": 0.406,
+      "step": 2220
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 6.884561891515995e-05,
+      "loss": 0.4395,
+      "step": 2240
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 6.856745479833102e-05,
+      "loss": 0.4557,
+      "step": 2260
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 6.82892906815021e-05,
+      "loss": 0.4331,
+      "step": 2280
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 6.801112656467315e-05,
+      "loss": 0.4544,
+      "step": 2300
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 6.773296244784422e-05,
+      "loss": 0.4419,
+      "step": 2320
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 6.74547983310153e-05,
+      "loss": 0.4362,
+      "step": 2340
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.717663421418637e-05,
+      "loss": 0.4392,
+      "step": 2360
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 6.689847009735744e-05,
+      "loss": 0.4633,
+      "step": 2380
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 6.662030598052852e-05,
+      "loss": 0.3991,
+      "step": 2400
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 6.634214186369958e-05,
+      "loss": 0.451,
+      "step": 2420
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 6.606397774687066e-05,
+      "loss": 0.3981,
+      "step": 2440
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 6.578581363004173e-05,
+      "loss": 0.4091,
+      "step": 2460
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 6.55076495132128e-05,
+      "loss": 0.4431,
+      "step": 2480
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 6.522948539638388e-05,
+      "loss": 0.4432,
+      "step": 2500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 6.495132127955494e-05,
+      "loss": 0.4572,
+      "step": 2520
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 6.467315716272601e-05,
+      "loss": 0.4288,
+      "step": 2540
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 6.439499304589708e-05,
+      "loss": 0.4195,
+      "step": 2560
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 6.411682892906815e-05,
+      "loss": 0.4456,
+      "step": 2580
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 6.383866481223923e-05,
+      "loss": 0.4164,
+      "step": 2600
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 6.35605006954103e-05,
+      "loss": 0.4597,
+      "step": 2620
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 6.328233657858137e-05,
+      "loss": 0.4074,
+      "step": 2640
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 6.300417246175245e-05,
+      "loss": 0.449,
+      "step": 2660
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 6.27260083449235e-05,
+      "loss": 0.4322,
+      "step": 2680
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 6.244784422809457e-05,
+      "loss": 0.411,
+      "step": 2700
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 6.216968011126565e-05,
+      "loss": 0.4289,
+      "step": 2720
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 6.189151599443672e-05,
+      "loss": 0.4298,
+      "step": 2740
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 6.161335187760779e-05,
+      "loss": 0.4303,
+      "step": 2760
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 6.133518776077887e-05,
+      "loss": 0.4422,
+      "step": 2780
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 6.105702364394992e-05,
+      "loss": 0.4473,
+      "step": 2800
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 6.0778859527121e-05,
+      "loss": 0.4164,
+      "step": 2820
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 6.0500695410292075e-05,
+      "loss": 0.4325,
+      "step": 2840
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 6.022253129346315e-05,
+      "loss": 0.4368,
+      "step": 2860
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 5.994436717663422e-05,
+      "loss": 0.4469,
+      "step": 2880
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 5.966620305980529e-05,
+      "loss": 0.4146,
+      "step": 2900
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 5.9388038942976354e-05,
+      "loss": 0.4111,
+      "step": 2920
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 5.910987482614743e-05,
+      "loss": 0.444,
+      "step": 2940
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 5.88317107093185e-05,
+      "loss": 0.4195,
+      "step": 2960
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 5.855354659248957e-05,
+      "loss": 0.3457,
+      "step": 2980
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 5.827538247566065e-05,
+      "loss": 0.3783,
+      "step": 3000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 5.7997218358831715e-05,
+      "loss": 0.407,
+      "step": 3020
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 5.7719054242002777e-05,
+      "loss": 0.4187,
+      "step": 3040
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 5.744089012517385e-05,
+      "loss": 0.3938,
+      "step": 3060
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 5.7162726008344926e-05,
+      "loss": 0.3947,
+      "step": 3080
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 5.6884561891515995e-05,
+      "loss": 0.4367,
+      "step": 3100
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 5.660639777468707e-05,
+      "loss": 0.3908,
+      "step": 3120
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 5.6328233657858144e-05,
+      "loss": 0.4016,
+      "step": 3140
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 5.605006954102921e-05,
+      "loss": 0.3862,
+      "step": 3160
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 5.5771905424200274e-05,
+      "loss": 0.3971,
+      "step": 3180
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 5.549374130737135e-05,
+      "loss": 0.3688,
+      "step": 3200
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 5.5215577190542424e-05,
+      "loss": 0.3961,
+      "step": 3220
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 5.493741307371349e-05,
+      "loss": 0.4247,
+      "step": 3240
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 5.465924895688457e-05,
+      "loss": 0.4154,
+      "step": 3260
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 5.438108484005564e-05,
+      "loss": 0.3502,
+      "step": 3280
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 5.41029207232267e-05,
+      "loss": 0.3485,
+      "step": 3300
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 5.382475660639778e-05,
+      "loss": 0.4089,
+      "step": 3320
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 5.3546592489568846e-05,
+      "loss": 0.3659,
+      "step": 3340
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 5.326842837273992e-05,
+      "loss": 0.3838,
+      "step": 3360
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 5.2990264255910996e-05,
+      "loss": 0.3694,
+      "step": 3380
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 5.2712100139082064e-05,
+      "loss": 0.4135,
+      "step": 3400
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 5.2433936022253126e-05,
+      "loss": 0.3949,
+      "step": 3420
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 5.21557719054242e-05,
+      "loss": 0.4358,
+      "step": 3440
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 5.1877607788595275e-05,
+      "loss": 0.4285,
+      "step": 3460
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 5.1599443671766344e-05,
+      "loss": 0.374,
+      "step": 3480
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 5.132127955493742e-05,
+      "loss": 0.4047,
+      "step": 3500
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 5.1043115438108493e-05,
+      "loss": 0.3886,
+      "step": 3520
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 5.0764951321279555e-05,
+      "loss": 0.3783,
+      "step": 3540
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 5.048678720445062e-05,
+      "loss": 0.4301,
+      "step": 3560
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 5.02086230876217e-05,
+      "loss": 0.371,
+      "step": 3580
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 4.993045897079277e-05,
+      "loss": 0.3834,
+      "step": 3600
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 4.965229485396384e-05,
+      "loss": 0.382,
+      "step": 3620
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.937413073713491e-05,
+      "loss": 0.3744,
+      "step": 3640
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 4.9095966620305984e-05,
+      "loss": 0.3819,
+      "step": 3660
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 4.881780250347706e-05,
+      "loss": 0.3857,
+      "step": 3680
+    },
+    {
+      "epoch": 5.15,
+      "learning_rate": 4.853963838664812e-05,
+      "loss": 0.4152,
+      "step": 3700
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 4.8261474269819195e-05,
+      "loss": 0.4125,
+      "step": 3720
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 4.798331015299027e-05,
+      "loss": 0.3337,
+      "step": 3740
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 4.770514603616134e-05,
+      "loss": 0.3294,
+      "step": 3760
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 4.7426981919332406e-05,
+      "loss": 0.3155,
+      "step": 3780
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 4.714881780250348e-05,
+      "loss": 0.3058,
+      "step": 3800
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 4.687065368567455e-05,
+      "loss": 0.3816,
+      "step": 3820
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 4.659248956884562e-05,
+      "loss": 0.3308,
+      "step": 3840
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 4.631432545201669e-05,
+      "loss": 0.3203,
+      "step": 3860
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 4.603616133518776e-05,
+      "loss": 0.3219,
+      "step": 3880
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 4.5757997218358836e-05,
+      "loss": 0.4005,
+      "step": 3900
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 4.5479833101529904e-05,
+      "loss": 0.3508,
+      "step": 3920
+    },
+    {
+      "epoch": 5.48,
+      "learning_rate": 4.520166898470097e-05,
+      "loss": 0.3329,
+      "step": 3940
+    },
+    {
+      "epoch": 5.51,
+      "learning_rate": 4.492350486787205e-05,
+      "loss": 0.3915,
+      "step": 3960
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 4.464534075104312e-05,
+      "loss": 0.3336,
+      "step": 3980
+    },
+    {
+      "epoch": 5.56,
+      "learning_rate": 4.436717663421418e-05,
+      "loss": 0.3497,
+      "step": 4000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 4.408901251738526e-05,
+      "loss": 0.4179,
+      "step": 4020
+    },
+    {
+      "epoch": 5.62,
+      "learning_rate": 4.381084840055633e-05,
+      "loss": 0.3408,
+      "step": 4040
+    },
+    {
+      "epoch": 5.65,
+      "learning_rate": 4.35326842837274e-05,
+      "loss": 0.349,
+      "step": 4060
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 4.325452016689847e-05,
+      "loss": 0.395,
+      "step": 4080
+    },
+    {
+      "epoch": 5.7,
+      "learning_rate": 4.2976356050069544e-05,
+      "loss": 0.3605,
+      "step": 4100
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 4.269819193324062e-05,
+      "loss": 0.4124,
+      "step": 4120
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 4.242002781641168e-05,
+      "loss": 0.3448,
+      "step": 4140
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 4.2141863699582755e-05,
+      "loss": 0.3499,
+      "step": 4160
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 4.186369958275383e-05,
+      "loss": 0.4002,
+      "step": 4180
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 4.15855354659249e-05,
+      "loss": 0.368,
+      "step": 4200
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 4.130737134909597e-05,
+      "loss": 0.3582,
+      "step": 4220
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 4.102920723226704e-05,
+      "loss": 0.3684,
+      "step": 4240
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 4.075104311543811e-05,
+      "loss": 0.3802,
+      "step": 4260
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 4.0472878998609185e-05,
+      "loss": 0.3775,
+      "step": 4280
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 4.019471488178025e-05,
+      "loss": 0.3537,
+      "step": 4300
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 3.991655076495132e-05,
+      "loss": 0.3692,
+      "step": 4320
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 3.9638386648122396e-05,
+      "loss": 0.3038,
+      "step": 4340
+    },
+    {
+      "epoch": 6.06,
+      "learning_rate": 3.9360222531293464e-05,
+      "loss": 0.2944,
+      "step": 4360
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 3.908205841446453e-05,
+      "loss": 0.3075,
+      "step": 4380
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 3.880389429763561e-05,
+      "loss": 0.2942,
+      "step": 4400
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 3.852573018080668e-05,
+      "loss": 0.3304,
+      "step": 4420
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 3.8247566063977743e-05,
+      "loss": 0.3522,
+      "step": 4440
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 3.796940194714882e-05,
+      "loss": 0.3178,
+      "step": 4460
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 3.769123783031989e-05,
+      "loss": 0.3312,
+      "step": 4480
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 3.741307371349096e-05,
+      "loss": 0.3769,
+      "step": 4500
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 3.713490959666203e-05,
+      "loss": 0.3356,
+      "step": 4520
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 3.6856745479833105e-05,
+      "loss": 0.3059,
+      "step": 4540
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 3.657858136300417e-05,
+      "loss": 0.3415,
+      "step": 4560
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 3.630041724617525e-05,
+      "loss": 0.351,
+      "step": 4580
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 3.6022253129346316e-05,
+      "loss": 0.326,
+      "step": 4600
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 3.5744089012517384e-05,
+      "loss": 0.3225,
+      "step": 4620
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 3.546592489568846e-05,
+      "loss": 0.3527,
+      "step": 4640
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 3.518776077885953e-05,
+      "loss": 0.3962,
+      "step": 4660
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 3.4909596662030595e-05,
+      "loss": 0.3648,
+      "step": 4680
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 3.463143254520167e-05,
+      "loss": 0.3316,
+      "step": 4700
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 3.4353268428372745e-05,
+      "loss": 0.3111,
+      "step": 4720
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 3.407510431154381e-05,
+      "loss": 0.2905,
+      "step": 4740
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 3.379694019471488e-05,
+      "loss": 0.3172,
+      "step": 4760
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 3.3518776077885956e-05,
+      "loss": 0.3378,
+      "step": 4780
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 3.3240611961057024e-05,
+      "loss": 0.3621,
+      "step": 4800
+    },
+    {
+      "epoch": 6.7,
+      "learning_rate": 3.296244784422809e-05,
+      "loss": 0.3366,
+      "step": 4820
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 3.268428372739917e-05,
+      "loss": 0.3122,
+      "step": 4840
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 3.240611961057024e-05,
+      "loss": 0.3339,
+      "step": 4860
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 3.212795549374131e-05,
+      "loss": 0.3554,
+      "step": 4880
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 3.184979137691238e-05,
+      "loss": 0.3583,
+      "step": 4900
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 3.1571627260083454e-05,
+      "loss": 0.3682,
+      "step": 4920
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 3.129346314325452e-05,
+      "loss": 0.3189,
+      "step": 4940
+    },
+    {
+      "epoch": 6.9,
+      "learning_rate": 3.101529902642559e-05,
+      "loss": 0.3654,
+      "step": 4960
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 3.0737134909596665e-05,
+      "loss": 0.3703,
+      "step": 4980
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 3.0458970792767733e-05,
+      "loss": 0.3582,
+      "step": 5000
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 3.0180806675938804e-05,
+      "loss": 0.3698,
+      "step": 5020
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 2.990264255910988e-05,
+      "loss": 0.3144,
+      "step": 5040
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 2.9624478442280944e-05,
+      "loss": 0.291,
+      "step": 5060
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 2.934631432545202e-05,
+      "loss": 0.3118,
+      "step": 5080
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 2.906815020862309e-05,
+      "loss": 0.3471,
+      "step": 5100
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 2.878998609179416e-05,
+      "loss": 0.3224,
+      "step": 5120
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 2.851182197496523e-05,
+      "loss": 0.3167,
+      "step": 5140
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 2.8233657858136302e-05,
+      "loss": 0.3203,
+      "step": 5160
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 2.795549374130737e-05,
+      "loss": 0.2913,
+      "step": 5180
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 2.767732962447844e-05,
+      "loss": 0.2995,
+      "step": 5200
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 2.7399165507649516e-05,
+      "loss": 0.3112,
+      "step": 5220
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 2.7121001390820585e-05,
+      "loss": 0.3293,
+      "step": 5240
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 2.6842837273991656e-05,
+      "loss": 0.2808,
+      "step": 5260
+    },
+    {
+      "epoch": 7.34,
+      "learning_rate": 2.6564673157162728e-05,
+      "loss": 0.3126,
+      "step": 5280
+    },
+    {
+      "epoch": 7.37,
+      "learning_rate": 2.6286509040333796e-05,
+      "loss": 0.2832,
+      "step": 5300
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 2.6008344923504867e-05,
+      "loss": 0.3096,
+      "step": 5320
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 2.5730180806675942e-05,
+      "loss": 0.3065,
+      "step": 5340
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 2.5452016689847014e-05,
+      "loss": 0.3326,
+      "step": 5360
+    },
+    {
+      "epoch": 7.48,
+      "learning_rate": 2.5173852573018082e-05,
+      "loss": 0.326,
+      "step": 5380
+    },
+    {
+      "epoch": 7.51,
+      "learning_rate": 2.4895688456189153e-05,
+      "loss": 0.3477,
+      "step": 5400
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 2.4617524339360225e-05,
+      "loss": 0.2976,
+      "step": 5420
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 2.4339360222531293e-05,
+      "loss": 0.3201,
+      "step": 5440
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 2.4061196105702365e-05,
+      "loss": 0.3338,
+      "step": 5460
+    },
+    {
+      "epoch": 7.62,
+      "learning_rate": 2.3783031988873436e-05,
+      "loss": 0.324,
+      "step": 5480
+    },
+    {
+      "epoch": 7.65,
+      "learning_rate": 2.3504867872044508e-05,
+      "loss": 0.3004,
+      "step": 5500
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 2.322670375521558e-05,
+      "loss": 0.3271,
+      "step": 5520
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 2.2948539638386647e-05,
+      "loss": 0.3379,
+      "step": 5540
+    },
+    {
+      "epoch": 7.73,
+      "learning_rate": 2.2670375521557722e-05,
+      "loss": 0.284,
+      "step": 5560
+    },
+    {
+      "epoch": 7.76,
+      "learning_rate": 2.239221140472879e-05,
+      "loss": 0.3185,
+      "step": 5580
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 2.2114047287899862e-05,
+      "loss": 0.3303,
+      "step": 5600
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 2.1835883171070934e-05,
+      "loss": 0.3107,
+      "step": 5620
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 2.1557719054242005e-05,
+      "loss": 0.3747,
+      "step": 5640
+    },
+    {
+      "epoch": 7.87,
+      "learning_rate": 2.1279554937413073e-05,
+      "loss": 0.3003,
+      "step": 5660
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 2.1001390820584145e-05,
+      "loss": 0.3176,
+      "step": 5680
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 2.0723226703755216e-05,
+      "loss": 0.2942,
+      "step": 5700
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 2.0445062586926288e-05,
+      "loss": 0.2932,
+      "step": 5720
+    },
+    {
+      "epoch": 7.98,
+      "learning_rate": 2.016689847009736e-05,
+      "loss": 0.2919,
+      "step": 5740
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 1.9888734353268428e-05,
+      "loss": 0.2664,
+      "step": 5760
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 1.96105702364395e-05,
+      "loss": 0.2788,
+      "step": 5780
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 1.933240611961057e-05,
+      "loss": 0.2737,
+      "step": 5800
+    },
+    {
+      "epoch": 8.09,
+      "learning_rate": 1.9054242002781642e-05,
+      "loss": 0.287,
+      "step": 5820
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 1.8776077885952714e-05,
+      "loss": 0.2771,
+      "step": 5840
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 1.8497913769123785e-05,
+      "loss": 0.2956,
+      "step": 5860
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 1.8219749652294853e-05,
+      "loss": 0.2837,
+      "step": 5880
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 1.7941585535465928e-05,
+      "loss": 0.3363,
+      "step": 5900
+    },
+    {
+      "epoch": 8.23,
+      "learning_rate": 1.7663421418636996e-05,
+      "loss": 0.3007,
+      "step": 5920
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 1.7385257301808068e-05,
+      "loss": 0.3177,
+      "step": 5940
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 1.710709318497914e-05,
+      "loss": 0.3089,
+      "step": 5960
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 1.6828929068150208e-05,
+      "loss": 0.2654,
+      "step": 5980
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 1.655076495132128e-05,
+      "loss": 0.2763,
+      "step": 6000
+    },
+    {
+      "epoch": 8.37,
+      "learning_rate": 1.627260083449235e-05,
+      "loss": 0.3078,
+      "step": 6020
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 1.5994436717663422e-05,
+      "loss": 0.2756,
+      "step": 6040
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 1.571627260083449e-05,
+      "loss": 0.2902,
+      "step": 6060
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 1.5438108484005565e-05,
+      "loss": 0.2787,
+      "step": 6080
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 1.5159944367176635e-05,
+      "loss": 0.2727,
+      "step": 6100
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 1.4881780250347707e-05,
+      "loss": 0.2758,
+      "step": 6120
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 1.4603616133518777e-05,
+      "loss": 0.3012,
+      "step": 6140
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 1.4325452016689846e-05,
+      "loss": 0.3084,
+      "step": 6160
+    },
+    {
+      "epoch": 8.6,
+      "learning_rate": 1.404728789986092e-05,
+      "loss": 0.2817,
+      "step": 6180
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 1.376912378303199e-05,
+      "loss": 0.3026,
+      "step": 6200
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 1.349095966620306e-05,
+      "loss": 0.3288,
+      "step": 6220
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 1.3212795549374133e-05,
+      "loss": 0.297,
+      "step": 6240
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 1.2934631432545202e-05,
+      "loss": 0.3321,
+      "step": 6260
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 1.2656467315716272e-05,
+      "loss": 0.2587,
+      "step": 6280
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 1.2378303198887344e-05,
+      "loss": 0.3322,
+      "step": 6300
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 1.2100139082058415e-05,
+      "loss": 0.2704,
+      "step": 6320
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 1.1821974965229487e-05,
+      "loss": 0.304,
+      "step": 6340
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 1.1543810848400557e-05,
+      "loss": 0.2947,
+      "step": 6360
+    },
+    {
+      "epoch": 8.87,
+      "learning_rate": 1.1265646731571628e-05,
+      "loss": 0.2906,
+      "step": 6380
+    },
+    {
+      "epoch": 8.9,
+      "learning_rate": 1.0987482614742698e-05,
+      "loss": 0.2907,
+      "step": 6400
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 1.070931849791377e-05,
+      "loss": 0.3304,
+      "step": 6420
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 1.043115438108484e-05,
+      "loss": 0.3089,
+      "step": 6440
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 1.0152990264255911e-05,
+      "loss": 0.2724,
+      "step": 6460
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 9.874826147426983e-06,
+      "loss": 0.286,
+      "step": 6480
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 9.596662030598054e-06,
+      "loss": 0.2835,
+      "step": 6500
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 9.318497913769124e-06,
+      "loss": 0.262,
+      "step": 6520
+    },
+    {
+      "epoch": 9.1,
+      "learning_rate": 9.040333796940195e-06,
+      "loss": 0.2772,
+      "step": 6540
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 8.762169680111267e-06,
+      "loss": 0.2801,
+      "step": 6560
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 8.484005563282337e-06,
+      "loss": 0.2681,
+      "step": 6580
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 8.205841446453408e-06,
+      "loss": 0.2686,
+      "step": 6600
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 7.92767732962448e-06,
+      "loss": 0.2838,
+      "step": 6620
+    },
+    {
+      "epoch": 9.24,
+      "learning_rate": 7.64951321279555e-06,
+      "loss": 0.2886,
+      "step": 6640
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 7.37134909596662e-06,
+      "loss": 0.2428,
+      "step": 6660
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 7.093184979137692e-06,
+      "loss": 0.2765,
+      "step": 6680
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 6.815020862308763e-06,
+      "loss": 0.2936,
+      "step": 6700
+    },
+    {
+      "epoch": 9.35,
+      "learning_rate": 6.536856745479833e-06,
+      "loss": 0.3004,
+      "step": 6720
+    },
+    {
+      "epoch": 9.37,
+      "learning_rate": 6.258692628650904e-06,
+      "loss": 0.26,
+      "step": 6740
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 5.980528511821975e-06,
+      "loss": 0.2806,
+      "step": 6760
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 5.702364394993046e-06,
+      "loss": 0.2628,
+      "step": 6780
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 5.424200278164117e-06,
+      "loss": 0.2636,
+      "step": 6800
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 5.1460361613351884e-06,
+      "loss": 0.2652,
+      "step": 6820
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 4.867872044506259e-06,
+      "loss": 0.2831,
+      "step": 6840
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 4.58970792767733e-06,
+      "loss": 0.2661,
+      "step": 6860
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 4.3115438108484005e-06,
+      "loss": 0.2653,
+      "step": 6880
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 4.033379694019471e-06,
+      "loss": 0.2693,
+      "step": 6900
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 3.7552155771905427e-06,
+      "loss": 0.2632,
+      "step": 6920
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 3.4770514603616134e-06,
+      "loss": 0.2788,
+      "step": 6940
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 3.1988873435326845e-06,
+      "loss": 0.3019,
+      "step": 6960
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 2.9207232267037552e-06,
+      "loss": 0.2778,
+      "step": 6980
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 2.6425591098748263e-06,
+      "loss": 0.3145,
+      "step": 7000
+    },
+    {
+      "epoch": 9.76,
+      "learning_rate": 2.364394993045897e-06,
+      "loss": 0.2991,
+      "step": 7020
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 2.086230876216968e-06,
+      "loss": 0.2819,
+      "step": 7040
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 1.8080667593880393e-06,
+      "loss": 0.2817,
+      "step": 7060
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 1.52990264255911e-06,
+      "loss": 0.2689,
+      "step": 7080
+    },
+    {
+      "epoch": 9.87,
+      "learning_rate": 1.2517385257301808e-06,
+      "loss": 0.2703,
+      "step": 7100
+    },
+    {
+      "epoch": 9.9,
+      "learning_rate": 9.735744089012517e-07,
+      "loss": 0.2763,
+      "step": 7120
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 6.954102920723227e-07,
+      "loss": 0.2825,
+      "step": 7140
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 4.1724617524339365e-07,
+      "loss": 0.2849,
+      "step": 7160
+    },
+    {
+      "epoch": 9.99,
+      "learning_rate": 1.3908205841446452e-07,
+      "loss": 0.3184,
+      "step": 7180
+    },
+    {
+      "epoch": 10.0,
+      "step": 7190,
+      "total_flos": 2.920670798324695e+17,
+      "train_loss": 0.4033946073105007,
+      "train_runtime": 2282.7571,
+      "train_samples_per_second": 6.295,
+      "train_steps_per_second": 3.15
+    }
+  ],
+  "max_steps": 7190,
+  "num_train_epochs": 10,
+  "total_flos": 2.920670798324695e+17,
+  "trial_name": null,
+  "trial_params": null
+}