update project

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "scutcyr/SoulChat",
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
+  },
+  "bos_token_id": 130004,
+  "eos_token_id": 130005,
+  "gmask_token_id": 130001,
+  "hidden_size": 4096,
+  "inner_hidden_size": 16384,
+  "layernorm_epsilon": 1e-05,
+  "mask_token_id": 130000,
+  "max_sequence_length": 2048,
+  "model_type": "chatglm",
+  "num_attention_heads": 32,
+  "num_layers": 28,
+  "pad_token_id": 3,
+  "position_encoding_2d": true,
+  "pre_seq_len": null,
+  "prefix_projection": false,
+  "quantization_bit": 0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 130528
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 130004,
+  "eos_token_id": 130005,
+  "pad_token_id": 3,
+  "transformers_version": "4.28.0"
+}

pytorch_model.bin.index.json

@@ -0,0 +1,375 @@
+{
+  "metadata": {
+    "total_size": 13415859968
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.22.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<sop>",
+  "eos_token": "<eop>",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_chatglm.ChatGLMTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<sop>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "end_token": "</s>",
+  "eos_token": "<eop>",
+  "gmask_token": "[gMASK]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "num_image_tokens": 0,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLMTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 5148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.955322455322455e-05,
+      "loss": 4.3405,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.906759906759907e-05,
+      "loss": 3.3274,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.858197358197358e-05,
+      "loss": 3.3008,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.80963480963481e-05,
+      "loss": 3.2864,
+      "step": 400
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.761072261072261e-05,
+      "loss": 3.2596,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.712509712509713e-05,
+      "loss": 3.2282,
+      "step": 600
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.663947163947164e-05,
+      "loss": 3.2515,
+      "step": 700
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.615384615384617e-05,
+      "loss": 3.24,
+      "step": 800
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.566822066822068e-05,
+      "loss": 3.2679,
+      "step": 900
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.51825951825952e-05,
+      "loss": 3.2357,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.469696969696971e-05,
+      "loss": 3.2323,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.421134421134422e-05,
+      "loss": 3.2238,
+      "step": 1200
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.372571872571873e-05,
+      "loss": 3.1898,
+      "step": 1300
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.324009324009324e-05,
+      "loss": 3.2354,
+      "step": 1400
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.275446775446775e-05,
+      "loss": 3.1935,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.226884226884227e-05,
+      "loss": 3.2049,
+      "step": 1600
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.178321678321678e-05,
+      "loss": 3.1813,
+      "step": 1700
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.12975912975913e-05,
+      "loss": 3.1799,
+      "step": 1800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.081196581196581e-05,
+      "loss": 3.1848,
+      "step": 1900
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.032634032634033e-05,
+      "loss": 3.2137,
+      "step": 2000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.984071484071484e-05,
+      "loss": 3.186,
+      "step": 2100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.935508935508936e-05,
+      "loss": 3.1948,
+      "step": 2200
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.886946386946387e-05,
+      "loss": 3.1564,
+      "step": 2300
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 8.83838383838384e-05,
+      "loss": 3.173,
+      "step": 2400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 8.789821289821291e-05,
+      "loss": 3.1713,
+      "step": 2500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.741258741258743e-05,
+      "loss": 3.1565,
+      "step": 2600
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 8.692696192696194e-05,
+      "loss": 3.19,
+      "step": 2700
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.644133644133644e-05,
+      "loss": 3.1557,
+      "step": 2800
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.595571095571096e-05,
+      "loss": 3.1731,
+      "step": 2900
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.547008547008547e-05,
+      "loss": 3.1801,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.498445998445998e-05,
+      "loss": 3.1607,
+      "step": 3100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.44988344988345e-05,
+      "loss": 3.1505,
+      "step": 3200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.401320901320901e-05,
+      "loss": 3.163,
+      "step": 3300
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.352758352758353e-05,
+      "loss": 3.1526,
+      "step": 3400
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 8.304195804195804e-05,
+      "loss": 3.1508,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.255633255633256e-05,
+      "loss": 3.1673,
+      "step": 3600
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.207070707070707e-05,
+      "loss": 3.1417,
+      "step": 3700
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.158508158508159e-05,
+      "loss": 3.1682,
+      "step": 3800
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.10994560994561e-05,
+      "loss": 3.1461,
+      "step": 3900
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 8.061383061383063e-05,
+      "loss": 3.1476,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.012820512820514e-05,
+      "loss": 3.1342,
+      "step": 4100
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 7.964257964257966e-05,
+      "loss": 3.1473,
+      "step": 4200
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 7.915695415695417e-05,
+      "loss": 3.1348,
+      "step": 4300
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.867132867132867e-05,
+      "loss": 3.1287,
+      "step": 4400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.818570318570319e-05,
+      "loss": 3.1278,
+      "step": 4500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.77000777000777e-05,
+      "loss": 3.1179,
+      "step": 4600
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.721445221445221e-05,
+      "loss": 3.1255,
+      "step": 4700
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.672882672882673e-05,
+      "loss": 3.121,
+      "step": 4800
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.624320124320124e-05,
+      "loss": 3.1312,
+      "step": 4900
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.575757575757576e-05,
+      "loss": 3.0984,
+      "step": 5000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.528166278166279e-05,
+      "loss": 3.1285,
+      "step": 5100
+    }
+  ],
+  "max_steps": 20592,
+  "num_train_epochs": 4,
+  "total_flos": 2.8530438570084663e+19,
+  "trial_name": null,
+  "trial_params": null
+}