upload

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.2920420169830322,
+    "eval_runtime": 271.2161,
+    "eval_samples": 5066,
+    "eval_samples_per_second": 18.679,
+    "eval_steps_per_second": 2.338,
+    "perplexity": 3.640212346810755,
+    "train_loss": 1.2596230482321824,
+    "train_runtime": 116835.9972,
+    "train_samples": 96253,
+    "train_samples_per_second": 4.119,
+    "train_steps_per_second": 0.103
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/zju-7B",
+  "architectures": [
+    "BaiChuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_baichuan.BaiChuanConfig",
+    "AutoModelForCausalLM": "modeling_baichuan.BaiChuanForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "baichuan",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.0",
+  "use_cache": true,
+  "vocab_size": 64000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.2920420169830322,
+    "eval_runtime": 271.2161,
+    "eval_samples": 5066,
+    "eval_samples_per_second": 18.679,
+    "eval_steps_per_second": 2.338,
+    "perplexity": 3.640212346810755
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0"
+}

pytorch_model.bin.index.json

@@ -0,0 +1,266 @@
+{
+  "metadata": {
+    "total_size": 14001123328
+  },
+  "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "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.W_pack.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.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

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_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_baichuan.BaiChuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "models/zju-7B/special_tokens_map.json",
+  "tokenizer_class": "BaiChuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.2596230482321824,
+    "train_runtime": 116835.9972,
+    "train_samples": 96253,
+    "train_samples_per_second": 4.119,
+    "train_steps_per_second": 0.103
+}

trainer_state.json

@@ -0,0 +1,937 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.999168882978723,
+  "global_step": 12030,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.492946524638607e-06,
+      "loss": 1.601,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7.470232356717817e-06,
+      "loss": 1.4225,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.041907920970229e-06,
+      "loss": 1.4184,
+      "step": 300
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.447518188797028e-06,
+      "loss": 1.3869,
+      "step": 400
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.762133954878699e-06,
+      "loss": 1.3759,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 1.3726129531860352,
+      "eval_runtime": 272.1193,
+      "eval_samples_per_second": 18.617,
+      "eval_steps_per_second": 2.33,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.019193753049438e-06,
+      "loss": 1.3454,
+      "step": 600
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.236534715583339e-06,
+      "loss": 1.358,
+      "step": 700
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.42480402087624e-06,
+      "loss": 1.3487,
+      "step": 800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.59086931730185e-06,
+      "loss": 1.3397,
+      "step": 900
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.73941978695791e-06,
+      "loss": 1.3515,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 1.346224069595337,
+      "eval_runtime": 272.1001,
+      "eval_samples_per_second": 18.618,
+      "eval_steps_per_second": 2.33,
+      "step": 1000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.873800032579688e-06,
+      "loss": 1.3469,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.99647958512865e-06,
+      "loss": 1.3331,
+      "step": 1200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.911332779163204e-06,
+      "loss": 1.3336,
+      "step": 1300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.81897109079154e-06,
+      "loss": 1.3345,
+      "step": 1400
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.726609402419877e-06,
+      "loss": 1.3207,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.328342080116272,
+      "eval_runtime": 272.126,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.634247714048214e-06,
+      "loss": 1.3345,
+      "step": 1600
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.54188602567655e-06,
+      "loss": 1.3151,
+      "step": 1700
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 9.449524337304887e-06,
+      "loss": 1.3387,
+      "step": 1800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 9.357162648933224e-06,
+      "loss": 1.3183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.264800960561559e-06,
+      "loss": 1.3172,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 1.3202550411224365,
+      "eval_runtime": 272.1379,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 2000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.172439272189896e-06,
+      "loss": 1.2997,
+      "step": 2100
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.080077583818233e-06,
+      "loss": 1.3338,
+      "step": 2200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.987715895446569e-06,
+      "loss": 1.3199,
+      "step": 2300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.895354207074907e-06,
+      "loss": 1.3067,
+      "step": 2400
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.802992518703243e-06,
+      "loss": 1.2836,
+      "step": 2500
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 1.310795545578003,
+      "eval_runtime": 272.0952,
+      "eval_samples_per_second": 18.618,
+      "eval_steps_per_second": 2.33,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 8.710630830331578e-06,
+      "loss": 1.2834,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.618269141959917e-06,
+      "loss": 1.2902,
+      "step": 2700
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.525907453588252e-06,
+      "loss": 1.2755,
+      "step": 2800
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 8.43354576521659e-06,
+      "loss": 1.2887,
+      "step": 2900
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 8.341184076844926e-06,
+      "loss": 1.2734,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 1.3082149028778076,
+      "eval_runtime": 272.1154,
+      "eval_samples_per_second": 18.617,
+      "eval_steps_per_second": 2.33,
+      "step": 3000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 8.248822388473262e-06,
+      "loss": 1.282,
+      "step": 3100
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 8.156460700101599e-06,
+      "loss": 1.2855,
+      "step": 3200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 8.064099011729936e-06,
+      "loss": 1.2793,
+      "step": 3300
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 7.971737323358271e-06,
+      "loss": 1.2811,
+      "step": 3400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 7.879375634986609e-06,
+      "loss": 1.261,
+      "step": 3500
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 1.3000493049621582,
+      "eval_runtime": 272.083,
+      "eval_samples_per_second": 18.619,
+      "eval_steps_per_second": 2.33,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.787013946614946e-06,
+      "loss": 1.2742,
+      "step": 3600
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.694652258243281e-06,
+      "loss": 1.2837,
+      "step": 3700
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 7.602290569871617e-06,
+      "loss": 1.2663,
+      "step": 3800
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 7.509928881499955e-06,
+      "loss": 1.2719,
+      "step": 3900
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.4175671931282914e-06,
+      "loss": 1.2703,
+      "step": 4000
+    },
+    {
+      "epoch": 1.66,
+      "eval_loss": 1.2987574338912964,
+      "eval_runtime": 272.1184,
+      "eval_samples_per_second": 18.617,
+      "eval_steps_per_second": 2.33,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 7.325205504756628e-06,
+      "loss": 1.2695,
+      "step": 4100
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.232843816384965e-06,
+      "loss": 1.262,
+      "step": 4200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.140482128013301e-06,
+      "loss": 1.2584,
+      "step": 4300
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.048120439641637e-06,
+      "loss": 1.2707,
+      "step": 4400
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.955758751269974e-06,
+      "loss": 1.2579,
+      "step": 4500
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.2950292825698853,
+      "eval_runtime": 272.1448,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 4500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.8633970628983106e-06,
+      "loss": 1.2784,
+      "step": 4600
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.771035374526647e-06,
+      "loss": 1.2573,
+      "step": 4700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 6.678673686154984e-06,
+      "loss": 1.2722,
+      "step": 4800
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 6.58631199778332e-06,
+      "loss": 1.2396,
+      "step": 4900
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 6.493950309411656e-06,
+      "loss": 1.2447,
+      "step": 5000
+    },
+    {
+      "epoch": 2.08,
+      "eval_loss": 1.297192096710205,
+      "eval_runtime": 272.1306,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 5000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 6.4015886210399935e-06,
+      "loss": 1.2418,
+      "step": 5100
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 6.30922693266833e-06,
+      "loss": 1.2523,
+      "step": 5200
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 6.216865244296666e-06,
+      "loss": 1.2309,
+      "step": 5300
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 6.124503555925003e-06,
+      "loss": 1.2442,
+      "step": 5400
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 6.032141867553339e-06,
+      "loss": 1.2261,
+      "step": 5500
+    },
+    {
+      "epoch": 2.29,
+      "eval_loss": 1.2935367822647095,
+      "eval_runtime": 272.1527,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 5500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5.9397801791816755e-06,
+      "loss": 1.2561,
+      "step": 5600
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5.847418490810013e-06,
+      "loss": 1.234,
+      "step": 5700
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 5.755056802438349e-06,
+      "loss": 1.2314,
+      "step": 5800
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 5.662695114066685e-06,
+      "loss": 1.24,
+      "step": 5900
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 5.570333425695022e-06,
+      "loss": 1.2388,
+      "step": 6000
+    },
+    {
+      "epoch": 2.49,
+      "eval_loss": 1.2919647693634033,
+      "eval_runtime": 272.1268,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 6000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 5.477971737323358e-06,
+      "loss": 1.2416,
+      "step": 6100
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 5.385610048951695e-06,
+      "loss": 1.2527,
+      "step": 6200
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 5.2932483605800326e-06,
+      "loss": 1.2331,
+      "step": 6300
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.200886672208369e-06,
+      "loss": 1.2483,
+      "step": 6400
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.108524983836704e-06,
+      "loss": 1.2467,
+      "step": 6500
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 1.2915822267532349,
+      "eval_runtime": 272.1288,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 6500
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 5.016163295465042e-06,
+      "loss": 1.2528,
+      "step": 6600
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 4.923801607093378e-06,
+      "loss": 1.2373,
+      "step": 6700
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 4.831439918721715e-06,
+      "loss": 1.2357,
+      "step": 6800
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.739078230350051e-06,
+      "loss": 1.2423,
+      "step": 6900
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.646716541978388e-06,
+      "loss": 1.2358,
+      "step": 7000
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 1.2892886400222778,
+      "eval_runtime": 272.1494,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 7000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 4.554354853606724e-06,
+      "loss": 1.2398,
+      "step": 7100
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 4.4619931652350604e-06,
+      "loss": 1.2271,
+      "step": 7200
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.3696314768633975e-06,
+      "loss": 1.2167,
+      "step": 7300
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.277269788491734e-06,
+      "loss": 1.2298,
+      "step": 7400
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.18490810012007e-06,
+      "loss": 1.2121,
+      "step": 7500
+    },
+    {
+      "epoch": 3.12,
+      "eval_loss": 1.2931495904922485,
+      "eval_runtime": 272.1691,
+      "eval_samples_per_second": 18.613,
+      "eval_steps_per_second": 2.329,
+      "step": 7500
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.092546411748407e-06,
+      "loss": 1.2265,
+      "step": 7600
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4.000184723376744e-06,
+      "loss": 1.216,
+      "step": 7700
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 3.9078230350050796e-06,
+      "loss": 1.2243,
+      "step": 7800
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.815461346633417e-06,
+      "loss": 1.2047,
+      "step": 7900
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.7230996582617533e-06,
+      "loss": 1.2274,
+      "step": 8000
+    },
+    {
+      "epoch": 3.32,
+      "eval_loss": 1.2907688617706299,
+      "eval_runtime": 272.1306,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 8000
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 3.6307379698900895e-06,
+      "loss": 1.2214,
+      "step": 8100
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.538376281518426e-06,
+      "loss": 1.2215,
+      "step": 8200
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 3.4460145931467633e-06,
+      "loss": 1.2221,
+      "step": 8300
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 3.353652904775099e-06,
+      "loss": 1.2179,
+      "step": 8400
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 3.261291216403436e-06,
+      "loss": 1.2229,
+      "step": 8500
+    },
+    {
+      "epoch": 3.53,
+      "eval_loss": 1.290418267250061,
+      "eval_runtime": 272.1197,
+      "eval_samples_per_second": 18.617,
+      "eval_steps_per_second": 2.33,
+      "step": 8500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 3.168929528031773e-06,
+      "loss": 1.2174,
+      "step": 8600
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 3.076567839660109e-06,
+      "loss": 1.2101,
+      "step": 8700
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 2.9842061512884458e-06,
+      "loss": 1.2199,
+      "step": 8800
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 2.8918444629167824e-06,
+      "loss": 1.2365,
+      "step": 8900
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 2.799482774545119e-06,
+      "loss": 1.218,
+      "step": 9000
+    },
+    {
+      "epoch": 3.74,
+      "eval_loss": 1.2891569137573242,
+      "eval_runtime": 272.1682,
+      "eval_samples_per_second": 18.613,
+      "eval_steps_per_second": 2.329,
+      "step": 9000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.7071210861734553e-06,
+      "loss": 1.2228,
+      "step": 9100
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 2.614759397801792e-06,
+      "loss": 1.2309,
+      "step": 9200
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 2.5223977094301287e-06,
+      "loss": 1.2271,
+      "step": 9300
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.430036021058465e-06,
+      "loss": 1.2194,
+      "step": 9400
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 2.3376743326868016e-06,
+      "loss": 1.214,
+      "step": 9500
+    },
+    {
+      "epoch": 3.95,
+      "eval_loss": 1.2882676124572754,
+      "eval_runtime": 272.1318,
+      "eval_samples_per_second": 18.616,
+      "eval_steps_per_second": 2.33,
+      "step": 9500
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 2.2453126443151382e-06,
+      "loss": 1.2166,
+      "step": 9600
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 2.152950955943475e-06,
+      "loss": 1.2048,
+      "step": 9700
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 2.0605892675718116e-06,
+      "loss": 1.2171,
+      "step": 9800
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 1.968227579200148e-06,
+      "loss": 1.2093,
+      "step": 9900
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.8758658908284845e-06,
+      "loss": 1.1948,
+      "step": 10000
+    },
+    {
+      "epoch": 4.16,
+      "eval_loss": 1.2930774688720703,
+      "eval_runtime": 272.152,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 10000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 1.7835042024568211e-06,
+      "loss": 1.2097,
+      "step": 10100
+    },
+    {
+      "epoch": 4.24,
+      "learning_rate": 1.6911425140851576e-06,
+      "loss": 1.2187,
+      "step": 10200
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 1.5987808257134942e-06,
+      "loss": 1.1994,
+      "step": 10300
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 1.5064191373418307e-06,
+      "loss": 1.2129,
+      "step": 10400
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 1.4140574489701671e-06,
+      "loss": 1.2067,
+      "step": 10500
+    },
+    {
+      "epoch": 4.36,
+      "eval_loss": 1.292514681816101,
+      "eval_runtime": 272.1549,
+      "eval_samples_per_second": 18.614,
+      "eval_steps_per_second": 2.33,
+      "step": 10500
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.321695760598504e-06,
+      "loss": 1.2075,
+      "step": 10600
+    },
+    {
+      "epoch": 4.45,
+      "learning_rate": 1.2293340722268405e-06,
+      "loss": 1.2224,
+      "step": 10700
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 1.1369723838551771e-06,
+      "loss": 1.212,
+      "step": 10800
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.0446106954835136e-06,
+      "loss": 1.2171,
+      "step": 10900
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 9.522490071118501e-07,
+      "loss": 1.2106,
+      "step": 11000
+    },
+    {
+      "epoch": 4.57,
+      "eval_loss": 1.2926254272460938,
+      "eval_runtime": 272.1417,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 11000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 8.598873187401867e-07,
+      "loss": 1.2025,
+      "step": 11100
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 7.675256303685231e-07,
+      "loss": 1.2081,
+      "step": 11200
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 6.751639419968597e-07,
+      "loss": 1.1977,
+      "step": 11300
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 5.828022536251963e-07,
+      "loss": 1.2217,
+      "step": 11400
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 4.904405652535329e-07,
+      "loss": 1.2026,
+      "step": 11500
+    },
+    {
+      "epoch": 4.78,
+      "eval_loss": 1.2920366525650024,
+      "eval_runtime": 272.1179,
+      "eval_samples_per_second": 18.617,
+      "eval_steps_per_second": 2.33,
+      "step": 11500
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 3.9807887688186943e-07,
+      "loss": 1.214,
+      "step": 11600
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 3.05717188510206e-07,
+      "loss": 1.2025,
+      "step": 11700
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 2.1335550013854254e-07,
+      "loss": 1.225,
+      "step": 11800
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 1.209938117668791e-07,
+      "loss": 1.2101,
+      "step": 11900
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 2.8632123395215668e-08,
+      "loss": 1.1956,
+      "step": 12000
+    },
+    {
+      "epoch": 4.99,
+      "eval_loss": 1.2920278310775757,
+      "eval_runtime": 272.1447,
+      "eval_samples_per_second": 18.615,
+      "eval_steps_per_second": 2.33,
+      "step": 12000
+    },
+    {
+      "epoch": 5.0,
+      "step": 12030,
+      "total_flos": 1.5667694787731915e+19,
+      "train_loss": 1.2596230482321824,
+      "train_runtime": 116835.9972,
+      "train_samples_per_second": 4.119,
+      "train_steps_per_second": 0.103
+    }
+  ],
+  "max_steps": 12030,
+  "num_train_epochs": 5,
+  "total_flos": 1.5667694787731915e+19,
+  "trial_name": null,
+  "trial_params": null
+}