Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Llama-3.1-8B
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: llama3-1-ox-llms-8b-sft-only-germany-data-and-ultrafeedback
+  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. -->
+
+# llama3-1-ox-llms-8b-sft-only-germany-data-and-ultrafeedback
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0782
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.895         | 1.0   | 404  | 1.0630          |
+| 0.6941        | 2.0   | 808  | 1.0782          |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 169178761789440.0,
+    "train_loss": 0.8271688128461933,
+    "train_runtime": 2411.6836,
+    "train_samples": 179306,
+    "train_samples_per_second": 21.427,
+    "train_steps_per_second": 0.335
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b5fb9309efc8af51ad5aefe42db5ee4eef6e8ef72d2d4bf84a7df78528fa04
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7865a50ccc3e9fcdb21261359655f57a004dc9bca144adf120ee775d6696a0a
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b854b55c473eee4ce6b25c4bc12fc43f189a61c987c03d1f743174795ef5efb
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dc8d57a307721022bfa43a5ed085b364f7c91f78fb90aa523fe1e32a852207
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 169178761789440.0,
+    "train_loss": 0.8271688128461933,
+    "train_runtime": 2411.6836,
+    "train_samples": 179306,
+    "train_samples_per_second": 21.427,
+    "train_steps_per_second": 0.335
+}

trainer_state.json

@@ -0,0 +1,1192 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 808,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0024752475247524753,
+      "grad_norm": 38.88609991114745,
+      "learning_rate": 2.469135802469136e-07,
+      "loss": 1.8604,
+      "step": 1
+    },
+    {
+      "epoch": 0.012376237623762377,
+      "grad_norm": 41.27939914036261,
+      "learning_rate": 1.234567901234568e-06,
+      "loss": 1.8561,
+      "step": 5
+    },
+    {
+      "epoch": 0.024752475247524754,
+      "grad_norm": 5.095317934955837,
+      "learning_rate": 2.469135802469136e-06,
+      "loss": 1.6195,
+      "step": 10
+    },
+    {
+      "epoch": 0.03712871287128713,
+      "grad_norm": 2.761116338631256,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 1.3811,
+      "step": 15
+    },
+    {
+      "epoch": 0.04950495049504951,
+      "grad_norm": 1.6927067748367093,
+      "learning_rate": 4.938271604938272e-06,
+      "loss": 1.1736,
+      "step": 20
+    },
+    {
+      "epoch": 0.06188118811881188,
+      "grad_norm": 1.637997489475765,
+      "learning_rate": 6.17283950617284e-06,
+      "loss": 1.0247,
+      "step": 25
+    },
+    {
+      "epoch": 0.07425742574257425,
+      "grad_norm": 0.9921453622709451,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.0275,
+      "step": 30
+    },
+    {
+      "epoch": 0.08663366336633663,
+      "grad_norm": 0.9409275181475548,
+      "learning_rate": 8.641975308641975e-06,
+      "loss": 0.9832,
+      "step": 35
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 1.0325275844641013,
+      "learning_rate": 9.876543209876543e-06,
+      "loss": 0.9685,
+      "step": 40
+    },
+    {
+      "epoch": 0.11138613861386139,
+      "grad_norm": 1.1218773632200145,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.9528,
+      "step": 45
+    },
+    {
+      "epoch": 0.12376237623762376,
+      "grad_norm": 0.9572180193224005,
+      "learning_rate": 1.234567901234568e-05,
+      "loss": 0.9201,
+      "step": 50
+    },
+    {
+      "epoch": 0.13613861386138615,
+      "grad_norm": 1.0009650827934435,
+      "learning_rate": 1.3580246913580248e-05,
+      "loss": 0.9542,
+      "step": 55
+    },
+    {
+      "epoch": 0.1485148514851485,
+      "grad_norm": 1.3065165374147407,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.9437,
+      "step": 60
+    },
+    {
+      "epoch": 0.1608910891089109,
+      "grad_norm": 1.0022123167697776,
+      "learning_rate": 1.6049382716049385e-05,
+      "loss": 0.9228,
+      "step": 65
+    },
+    {
+      "epoch": 0.17326732673267325,
+      "grad_norm": 1.2184130543835685,
+      "learning_rate": 1.728395061728395e-05,
+      "loss": 0.9772,
+      "step": 70
+    },
+    {
+      "epoch": 0.18564356435643564,
+      "grad_norm": 0.9408942641640691,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.9284,
+      "step": 75
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 0.9712584145776969,
+      "learning_rate": 1.9753086419753087e-05,
+      "loss": 0.9484,
+      "step": 80
+    },
+    {
+      "epoch": 0.2103960396039604,
+      "grad_norm": 0.9980192527761912,
+      "learning_rate": 1.999850613931615e-05,
+      "loss": 0.9536,
+      "step": 85
+    },
+    {
+      "epoch": 0.22277227722772278,
+      "grad_norm": 0.9890748697192007,
+      "learning_rate": 1.9992438095219886e-05,
+      "loss": 0.9539,
+      "step": 90
+    },
+    {
+      "epoch": 0.23514851485148514,
+      "grad_norm": 0.9155960993755162,
+      "learning_rate": 1.9981705331953295e-05,
+      "loss": 0.936,
+      "step": 95
+    },
+    {
+      "epoch": 0.24752475247524752,
+      "grad_norm": 0.8051611539712368,
+      "learning_rate": 1.996631285983779e-05,
+      "loss": 0.9456,
+      "step": 100
+    },
+    {
+      "epoch": 0.2599009900990099,
+      "grad_norm": 0.9230091255662991,
+      "learning_rate": 1.9946267864463027e-05,
+      "loss": 0.9136,
+      "step": 105
+    },
+    {
+      "epoch": 0.2722772277227723,
+      "grad_norm": 0.8382334460112006,
+      "learning_rate": 1.9921579703332475e-05,
+      "loss": 0.93,
+      "step": 110
+    },
+    {
+      "epoch": 0.28465346534653463,
+      "grad_norm": 0.8774240428827245,
+      "learning_rate": 1.989225990149512e-05,
+      "loss": 0.9245,
+      "step": 115
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 0.8987251464829349,
+      "learning_rate": 1.9858322146165272e-05,
+      "loss": 0.9341,
+      "step": 120
+    },
+    {
+      "epoch": 0.3094059405940594,
+      "grad_norm": 0.9049306018652525,
+      "learning_rate": 1.981978228033304e-05,
+      "loss": 0.9257,
+      "step": 125
+    },
+    {
+      "epoch": 0.3217821782178218,
+      "grad_norm": 0.9029524926074908,
+      "learning_rate": 1.977665829536842e-05,
+      "loss": 0.916,
+      "step": 130
+    },
+    {
+      "epoch": 0.3341584158415842,
+      "grad_norm": 0.8591727043131795,
+      "learning_rate": 1.9728970322622485e-05,
+      "loss": 0.9168,
+      "step": 135
+    },
+    {
+      "epoch": 0.3465346534653465,
+      "grad_norm": 0.8712548282993846,
+      "learning_rate": 1.9676740624029566e-05,
+      "loss": 0.9347,
+      "step": 140
+    },
+    {
+      "epoch": 0.3589108910891089,
+      "grad_norm": 0.8442378198048982,
+      "learning_rate": 1.961999358171482e-05,
+      "loss": 0.9286,
+      "step": 145
+    },
+    {
+      "epoch": 0.3712871287128713,
+      "grad_norm": 0.8448891617644472,
+      "learning_rate": 1.955875568661206e-05,
+      "loss": 0.9247,
+      "step": 150
+    },
+    {
+      "epoch": 0.38366336633663367,
+      "grad_norm": 0.8506188708401377,
+      "learning_rate": 1.94930555260971e-05,
+      "loss": 0.9089,
+      "step": 155
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.7615649650166222,
+      "learning_rate": 1.9422923770642494e-05,
+      "loss": 0.9121,
+      "step": 160
+    },
+    {
+      "epoch": 0.4084158415841584,
+      "grad_norm": 0.8438076926475072,
+      "learning_rate": 1.934839315949976e-05,
+      "loss": 0.9133,
+      "step": 165
+    },
+    {
+      "epoch": 0.4207920792079208,
+      "grad_norm": 0.9246754527016784,
+      "learning_rate": 1.9269498485415897e-05,
+      "loss": 0.9298,
+      "step": 170
+    },
+    {
+      "epoch": 0.43316831683168316,
+      "grad_norm": 0.9627433039386685,
+      "learning_rate": 1.9186276578391268e-05,
+      "loss": 0.9421,
+      "step": 175
+    },
+    {
+      "epoch": 0.44554455445544555,
+      "grad_norm": 0.8087976752191404,
+      "learning_rate": 1.9098766288486426e-05,
+      "loss": 0.9261,
+      "step": 180
+    },
+    {
+      "epoch": 0.45792079207920794,
+      "grad_norm": 0.774521835464554,
+      "learning_rate": 1.9007008467685947e-05,
+      "loss": 0.9328,
+      "step": 185
+    },
+    {
+      "epoch": 0.47029702970297027,
+      "grad_norm": 0.7725284205468596,
+      "learning_rate": 1.8911045950827693e-05,
+      "loss": 0.9093,
+      "step": 190
+    },
+    {
+      "epoch": 0.48267326732673266,
+      "grad_norm": 0.8054030551821266,
+      "learning_rate": 1.881092353560646e-05,
+      "loss": 0.9013,
+      "step": 195
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 0.7758400337225813,
+      "learning_rate": 1.870668796166129e-05,
+      "loss": 0.9142,
+      "step": 200
+    },
+    {
+      "epoch": 0.5074257425742574,
+      "grad_norm": 0.8158556574805117,
+      "learning_rate": 1.8598387888756224e-05,
+      "loss": 0.9222,
+      "step": 205
+    },
+    {
+      "epoch": 0.5198019801980198,
+      "grad_norm": 0.7595417385088049,
+      "learning_rate": 1.8486073874064745e-05,
+      "loss": 0.9061,
+      "step": 210
+    },
+    {
+      "epoch": 0.5321782178217822,
+      "grad_norm": 0.7472799231884507,
+      "learning_rate": 1.8369798348568403e-05,
+      "loss": 0.9083,
+      "step": 215
+    },
+    {
+      "epoch": 0.5445544554455446,
+      "grad_norm": 0.7606289538163604,
+      "learning_rate": 1.8249615592580733e-05,
+      "loss": 0.9328,
+      "step": 220
+    },
+    {
+      "epoch": 0.556930693069307,
+      "grad_norm": 0.805186253739664,
+      "learning_rate": 1.8125581710407864e-05,
+      "loss": 0.9138,
+      "step": 225
+    },
+    {
+      "epoch": 0.5693069306930693,
+      "grad_norm": 0.767139039892534,
+      "learning_rate": 1.7997754604157607e-05,
+      "loss": 0.9075,
+      "step": 230
+    },
+    {
+      "epoch": 0.5816831683168316,
+      "grad_norm": 0.7674924368854081,
+      "learning_rate": 1.786619394670933e-05,
+      "loss": 0.9094,
+      "step": 235
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.7416157345263308,
+      "learning_rate": 1.7730961153857155e-05,
+      "loss": 0.9146,
+      "step": 240
+    },
+    {
+      "epoch": 0.6064356435643564,
+      "grad_norm": 0.7972512834290945,
+      "learning_rate": 1.7592119355639545e-05,
+      "loss": 0.8986,
+      "step": 245
+    },
+    {
+      "epoch": 0.6188118811881188,
+      "grad_norm": 0.7413943937305464,
+      "learning_rate": 1.744973336686862e-05,
+      "loss": 0.9261,
+      "step": 250
+    },
+    {
+      "epoch": 0.6311881188118812,
+      "grad_norm": 0.7288799636758897,
+      "learning_rate": 1.7303869656872994e-05,
+      "loss": 0.9004,
+      "step": 255
+    },
+    {
+      "epoch": 0.6435643564356436,
+      "grad_norm": 0.7554557666231643,
+      "learning_rate": 1.715459631846824e-05,
+      "loss": 0.9097,
+      "step": 260
+    },
+    {
+      "epoch": 0.655940594059406,
+      "grad_norm": 0.7267320540898269,
+      "learning_rate": 1.700198303616944e-05,
+      "loss": 0.902,
+      "step": 265
+    },
+    {
+      "epoch": 0.6683168316831684,
+      "grad_norm": 0.6823040717527771,
+      "learning_rate": 1.684610105366076e-05,
+      "loss": 0.8913,
+      "step": 270
+    },
+    {
+      "epoch": 0.6806930693069307,
+      "grad_norm": 0.6787438356187852,
+      "learning_rate": 1.6687023140537082e-05,
+      "loss": 0.882,
+      "step": 275
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 0.7420049831517054,
+      "learning_rate": 1.6524823558333362e-05,
+      "loss": 0.8985,
+      "step": 280
+    },
+    {
+      "epoch": 0.7054455445544554,
+      "grad_norm": 0.7627405635266166,
+      "learning_rate": 1.6359578025857495e-05,
+      "loss": 0.8836,
+      "step": 285
+    },
+    {
+      "epoch": 0.7178217821782178,
+      "grad_norm": 0.8778998231303615,
+      "learning_rate": 1.6191363683842883e-05,
+      "loss": 0.8871,
+      "step": 290
+    },
+    {
+      "epoch": 0.7301980198019802,
+      "grad_norm": 0.8167069067691852,
+      "learning_rate": 1.6020259058937228e-05,
+      "loss": 0.8866,
+      "step": 295
+    },
+    {
+      "epoch": 0.7425742574257426,
+      "grad_norm": 0.7980390861743758,
+      "learning_rate": 1.5846344027044307e-05,
+      "loss": 0.9047,
+      "step": 300
+    },
+    {
+      "epoch": 0.754950495049505,
+      "grad_norm": 0.7563819762216695,
+      "learning_rate": 1.5669699776035958e-05,
+      "loss": 0.921,
+      "step": 305
+    },
+    {
+      "epoch": 0.7673267326732673,
+      "grad_norm": 0.7797762078681911,
+      "learning_rate": 1.5490408767851506e-05,
+      "loss": 0.8869,
+      "step": 310
+    },
+    {
+      "epoch": 0.7797029702970297,
+      "grad_norm": 0.7666252485199382,
+      "learning_rate": 1.530855470000251e-05,
+      "loss": 0.9151,
+      "step": 315
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.7051563046414802,
+      "learning_rate": 1.5124222466500665e-05,
+      "loss": 0.9024,
+      "step": 320
+    },
+    {
+      "epoch": 0.8044554455445545,
+      "grad_norm": 0.7203691895762679,
+      "learning_rate": 1.4937498118227156e-05,
+      "loss": 0.9098,
+      "step": 325
+    },
+    {
+      "epoch": 0.8168316831683168,
+      "grad_norm": 0.7125293698622911,
+      "learning_rate": 1.4748468822761974e-05,
+      "loss": 0.9076,
+      "step": 330
+    },
+    {
+      "epoch": 0.8292079207920792,
+      "grad_norm": 0.7428102709759479,
+      "learning_rate": 1.4557222823691913e-05,
+      "loss": 0.9082,
+      "step": 335
+    },
+    {
+      "epoch": 0.8415841584158416,
+      "grad_norm": 0.7230219909417678,
+      "learning_rate": 1.4363849399416254e-05,
+      "loss": 0.9004,
+      "step": 340
+    },
+    {
+      "epoch": 0.8539603960396039,
+      "grad_norm": 0.788928114591889,
+      "learning_rate": 1.4168438821469402e-05,
+      "loss": 0.8845,
+      "step": 345
+    },
+    {
+      "epoch": 0.8663366336633663,
+      "grad_norm": 0.7456926963995498,
+      "learning_rate": 1.3971082312379864e-05,
+      "loss": 0.9013,
+      "step": 350
+    },
+    {
+      "epoch": 0.8787128712871287,
+      "grad_norm": 0.7757067249831519,
+      "learning_rate": 1.3771872003085315e-05,
+      "loss": 0.8913,
+      "step": 355
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.7040237849520753,
+      "learning_rate": 1.3570900889923566e-05,
+      "loss": 0.9178,
+      "step": 360
+    },
+    {
+      "epoch": 0.9034653465346535,
+      "grad_norm": 0.7028463213970978,
+      "learning_rate": 1.3368262791219568e-05,
+      "loss": 0.8864,
+      "step": 365
+    },
+    {
+      "epoch": 0.9158415841584159,
+      "grad_norm": 0.6865489126472716,
+      "learning_rate": 1.3164052303488673e-05,
+      "loss": 0.8958,
+      "step": 370
+    },
+    {
+      "epoch": 0.9282178217821783,
+      "grad_norm": 0.7124826316517546,
+      "learning_rate": 1.2958364757276616e-05,
+      "loss": 0.8927,
+      "step": 375
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "grad_norm": 0.71875227320249,
+      "learning_rate": 1.2751296172656862e-05,
+      "loss": 0.897,
+      "step": 380
+    },
+    {
+      "epoch": 0.9529702970297029,
+      "grad_norm": 0.7298632107047348,
+      "learning_rate": 1.2542943214406012e-05,
+      "loss": 0.9051,
+      "step": 385
+    },
+    {
+      "epoch": 0.9653465346534653,
+      "grad_norm": 0.6885898822393058,
+      "learning_rate": 1.23334031468783e-05,
+      "loss": 0.8546,
+      "step": 390
+    },
+    {
+      "epoch": 0.9777227722772277,
+      "grad_norm": 0.7078778884772863,
+      "learning_rate": 1.2122773788600164e-05,
+      "loss": 0.9019,
+      "step": 395
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.7533302944336393,
+      "learning_rate": 1.1911153466606105e-05,
+      "loss": 0.895,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.06302809715271,
+      "eval_runtime": 43.2706,
+      "eval_samples_per_second": 75.871,
+      "eval_steps_per_second": 1.202,
+      "step": 404
+    },
+    {
+      "epoch": 1.0024752475247525,
+      "grad_norm": 1.3960472434954319,
+      "learning_rate": 1.1698640970537195e-05,
+      "loss": 0.8479,
+      "step": 405
+    },
+    {
+      "epoch": 1.0148514851485149,
+      "grad_norm": 0.8222898474391185,
+      "learning_rate": 1.14853355065236e-05,
+      "loss": 0.7492,
+      "step": 410
+    },
+    {
+      "epoch": 1.0272277227722773,
+      "grad_norm": 1.146533181549737,
+      "learning_rate": 1.1271336650872687e-05,
+      "loss": 0.7352,
+      "step": 415
+    },
+    {
+      "epoch": 1.0396039603960396,
+      "grad_norm": 1.2500390362477898,
+      "learning_rate": 1.1056744303584322e-05,
+      "loss": 0.7107,
+      "step": 420
+    },
+    {
+      "epoch": 1.051980198019802,
+      "grad_norm": 0.8882156471951722,
+      "learning_rate": 1.0841658641715064e-05,
+      "loss": 0.7027,
+      "step": 425
+    },
+    {
+      "epoch": 1.0643564356435644,
+      "grad_norm": 0.8783518588023339,
+      "learning_rate": 1.0626180072613011e-05,
+      "loss": 0.7199,
+      "step": 430
+    },
+    {
+      "epoch": 1.0767326732673268,
+      "grad_norm": 0.7956936034755372,
+      "learning_rate": 1.0410409187045145e-05,
+      "loss": 0.6972,
+      "step": 435
+    },
+    {
+      "epoch": 1.0891089108910892,
+      "grad_norm": 0.7957451930016578,
+      "learning_rate": 1.0194446712239076e-05,
+      "loss": 0.7194,
+      "step": 440
+    },
+    {
+      "epoch": 1.1014851485148516,
+      "grad_norm": 0.8085539993808099,
+      "learning_rate": 9.978393464861036e-06,
+      "loss": 0.7085,
+      "step": 445
+    },
+    {
+      "epoch": 1.113861386138614,
+      "grad_norm": 0.7629426599829563,
+      "learning_rate": 9.76235030395215e-06,
+      "loss": 0.7221,
+      "step": 450
+    },
+    {
+      "epoch": 1.1262376237623761,
+      "grad_norm": 0.7099439929036686,
+      "learning_rate": 9.546418083844944e-06,
+      "loss": 0.7228,
+      "step": 455
+    },
+    {
+      "epoch": 1.1386138613861387,
+      "grad_norm": 0.768143602885412,
+      "learning_rate": 9.330697607081995e-06,
+      "loss": 0.7055,
+      "step": 460
+    },
+    {
+      "epoch": 1.150990099009901,
+      "grad_norm": 0.7399932448725586,
+      "learning_rate": 9.115289577358826e-06,
+      "loss": 0.7126,
+      "step": 465
+    },
+    {
+      "epoch": 1.1633663366336633,
+      "grad_norm": 0.7720020506192959,
+      "learning_rate": 8.900294552512878e-06,
+      "loss": 0.7095,
+      "step": 470
+    },
+    {
+      "epoch": 1.1757425742574257,
+      "grad_norm": 0.7452407090275405,
+      "learning_rate": 8.68581289758063e-06,
+      "loss": 0.7028,
+      "step": 475
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.7571246453363882,
+      "learning_rate": 8.471944737944687e-06,
+      "loss": 0.7184,
+      "step": 480
+    },
+    {
+      "epoch": 1.2004950495049505,
+      "grad_norm": 0.7494453898237526,
+      "learning_rate": 8.25878991259276e-06,
+      "loss": 0.6982,
+      "step": 485
+    },
+    {
+      "epoch": 1.2128712871287128,
+      "grad_norm": 0.7254138409040641,
+      "learning_rate": 8.046447927510335e-06,
+      "loss": 0.7175,
+      "step": 490
+    },
+    {
+      "epoch": 1.2252475247524752,
+      "grad_norm": 0.7709180774648441,
+      "learning_rate": 7.835017909228801e-06,
+      "loss": 0.7075,
+      "step": 495
+    },
+    {
+      "epoch": 1.2376237623762376,
+      "grad_norm": 0.760113272357165,
+      "learning_rate": 7.624598558550707e-06,
+      "loss": 0.7224,
+      "step": 500
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.7251746178009261,
+      "learning_rate": 7.415288104473774e-06,
+      "loss": 0.7059,
+      "step": 505
+    },
+    {
+      "epoch": 1.2623762376237624,
+      "grad_norm": 0.7604221994294873,
+      "learning_rate": 7.207184258335163e-06,
+      "loss": 0.7022,
+      "step": 510
+    },
+    {
+      "epoch": 1.2747524752475248,
+      "grad_norm": 0.7947902441474564,
+      "learning_rate": 7.000384168197354e-06,
+      "loss": 0.7076,
+      "step": 515
+    },
+    {
+      "epoch": 1.2871287128712872,
+      "grad_norm": 0.7054449499686205,
+      "learning_rate": 6.7949843734970475e-06,
+      "loss": 0.7133,
+      "step": 520
+    },
+    {
+      "epoch": 1.2995049504950495,
+      "grad_norm": 0.708545411017501,
+      "learning_rate": 6.5910807599781135e-06,
+      "loss": 0.7106,
+      "step": 525
+    },
+    {
+      "epoch": 1.311881188118812,
+      "grad_norm": 0.7262363459114348,
+      "learning_rate": 6.388768514929768e-06,
+      "loss": 0.7114,
+      "step": 530
+    },
+    {
+      "epoch": 1.3242574257425743,
+      "grad_norm": 0.6998186137578639,
+      "learning_rate": 6.18814208275075e-06,
+      "loss": 0.7122,
+      "step": 535
+    },
+    {
+      "epoch": 1.3366336633663367,
+      "grad_norm": 0.7095860494984699,
+      "learning_rate": 5.989295120860334e-06,
+      "loss": 0.7252,
+      "step": 540
+    },
+    {
+      "epoch": 1.349009900990099,
+      "grad_norm": 0.6915165561447487,
+      "learning_rate": 5.792320455976714e-06,
+      "loss": 0.7048,
+      "step": 545
+    },
+    {
+      "epoch": 1.3613861386138613,
+      "grad_norm": 0.7119909691342722,
+      "learning_rate": 5.597310040783161e-06,
+      "loss": 0.6962,
+      "step": 550
+    },
+    {
+      "epoch": 1.3737623762376239,
+      "grad_norm": 0.7504970044336818,
+      "learning_rate": 5.404354911002243e-06,
+      "loss": 0.707,
+      "step": 555
+    },
+    {
+      "epoch": 1.386138613861386,
+      "grad_norm": 0.7146866752363458,
+      "learning_rate": 5.213545142898061e-06,
+      "loss": 0.7223,
+      "step": 560
+    },
+    {
+      "epoch": 1.3985148514851486,
+      "grad_norm": 0.7356980622491117,
+      "learning_rate": 5.024969811226419e-06,
+      "loss": 0.6998,
+      "step": 565
+    },
+    {
+      "epoch": 1.4108910891089108,
+      "grad_norm": 0.7061674308512749,
+      "learning_rate": 4.838716947652485e-06,
+      "loss": 0.6958,
+      "step": 570
+    },
+    {
+      "epoch": 1.4232673267326732,
+      "grad_norm": 0.7284088021218859,
+      "learning_rate": 4.654873499655449e-06,
+      "loss": 0.6964,
+      "step": 575
+    },
+    {
+      "epoch": 1.4356435643564356,
+      "grad_norm": 0.6886931942419792,
+      "learning_rate": 4.4735252899392335e-06,
+      "loss": 0.7023,
+      "step": 580
+    },
+    {
+      "epoch": 1.448019801980198,
+      "grad_norm": 0.7166576506174707,
+      "learning_rate": 4.294756976368351e-06,
+      "loss": 0.7069,
+      "step": 585
+    },
+    {
+      "epoch": 1.4603960396039604,
+      "grad_norm": 0.7032864356512767,
+      "learning_rate": 4.118652012447486e-06,
+      "loss": 0.7211,
+      "step": 590
+    },
+    {
+      "epoch": 1.4727722772277227,
+      "grad_norm": 0.7242483728321348,
+      "learning_rate": 3.945292608363312e-06,
+      "loss": 0.7119,
+      "step": 595
+    },
+    {
+      "epoch": 1.4851485148514851,
+      "grad_norm": 0.6918844982337927,
+      "learning_rate": 3.7747596926067485e-06,
+      "loss": 0.7221,
+      "step": 600
+    },
+    {
+      "epoch": 1.4975247524752475,
+      "grad_norm": 0.7132050642871574,
+      "learning_rate": 3.6071328741934985e-06,
+      "loss": 0.7022,
+      "step": 605
+    },
+    {
+      "epoch": 1.50990099009901,
+      "grad_norm": 0.7347264550601227,
+      "learning_rate": 3.442490405500598e-06,
+      "loss": 0.6975,
+      "step": 610
+    },
+    {
+      "epoch": 1.5222772277227723,
+      "grad_norm": 0.6602507777994507,
+      "learning_rate": 3.2809091457362464e-06,
+      "loss": 0.7065,
+      "step": 615
+    },
+    {
+      "epoch": 1.5346534653465347,
+      "grad_norm": 0.6740627682629335,
+      "learning_rate": 3.122464525060013e-06,
+      "loss": 0.6978,
+      "step": 620
+    },
+    {
+      "epoch": 1.547029702970297,
+      "grad_norm": 0.7142221920558823,
+      "learning_rate": 2.96723050937015e-06,
+      "loss": 0.709,
+      "step": 625
+    },
+    {
+      "epoch": 1.5594059405940595,
+      "grad_norm": 0.7335799725765082,
+      "learning_rate": 2.8152795657744882e-06,
+      "loss": 0.6893,
+      "step": 630
+    },
+    {
+      "epoch": 1.5717821782178216,
+      "grad_norm": 0.7032104638603995,
+      "learning_rate": 2.666682628760958e-06,
+      "loss": 0.6961,
+      "step": 635
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.6921897923437655,
+      "learning_rate": 2.521509067083631e-06,
+      "loss": 0.6938,
+      "step": 640
+    },
+    {
+      "epoch": 1.5965346534653464,
+      "grad_norm": 0.6863228632248336,
+      "learning_rate": 2.379826651379632e-06,
+      "loss": 0.7033,
+      "step": 645
+    },
+    {
+      "epoch": 1.608910891089109,
+      "grad_norm": 0.6778666475373859,
+      "learning_rate": 2.241701522532136e-06,
+      "loss": 0.7077,
+      "step": 650
+    },
+    {
+      "epoch": 1.6212871287128712,
+      "grad_norm": 0.978566748682469,
+      "learning_rate": 2.107198160794136e-06,
+      "loss": 0.7102,
+      "step": 655
+    },
+    {
+      "epoch": 1.6336633663366338,
+      "grad_norm": 0.7103004954900359,
+      "learning_rate": 1.9763793556874655e-06,
+      "loss": 0.6983,
+      "step": 660
+    },
+    {
+      "epoch": 1.646039603960396,
+      "grad_norm": 0.676195777058198,
+      "learning_rate": 1.849306176691088e-06,
+      "loss": 0.7176,
+      "step": 665
+    },
+    {
+      "epoch": 1.6584158415841586,
+      "grad_norm": 0.7079808939239,
+      "learning_rate": 1.7260379447323327e-06,
+      "loss": 0.6998,
+      "step": 670
+    },
+    {
+      "epoch": 1.6707920792079207,
+      "grad_norm": 0.6910118308885802,
+      "learning_rate": 1.6066322044944126e-06,
+      "loss": 0.6847,
+      "step": 675
+    },
+    {
+      "epoch": 1.6831683168316833,
+      "grad_norm": 0.6904569392825494,
+      "learning_rate": 1.4911446975531329e-06,
+      "loss": 0.7014,
+      "step": 680
+    },
+    {
+      "epoch": 1.6955445544554455,
+      "grad_norm": 0.6979836145792466,
+      "learning_rate": 1.3796293363553259e-06,
+      "loss": 0.7252,
+      "step": 685
+    },
+    {
+      "epoch": 1.7079207920792079,
+      "grad_norm": 0.6898195721719471,
+      "learning_rate": 1.2721381790511832e-06,
+      "loss": 0.7096,
+      "step": 690
+    },
+    {
+      "epoch": 1.7202970297029703,
+      "grad_norm": 0.7872710836498652,
+      "learning_rate": 1.168721405192218e-06,
+      "loss": 0.7118,
+      "step": 695
+    },
+    {
+      "epoch": 1.7326732673267327,
+      "grad_norm": 0.6351928901398578,
+      "learning_rate": 1.0694272923061933e-06,
+      "loss": 0.7073,
+      "step": 700
+    },
+    {
+      "epoch": 1.745049504950495,
+      "grad_norm": 0.6550150479810684,
+      "learning_rate": 9.743021933599695e-07,
+      "loss": 0.6879,
+      "step": 705
+    },
+    {
+      "epoch": 1.7574257425742574,
+      "grad_norm": 0.6762595095414403,
+      "learning_rate": 8.833905151207833e-07,
+      "loss": 0.6972,
+      "step": 710
+    },
+    {
+      "epoch": 1.7698019801980198,
+      "grad_norm": 0.7046793104440422,
+      "learning_rate": 7.967346974260626e-07,
+      "loss": 0.7119,
+      "step": 715
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.6803563399348503,
+      "learning_rate": 7.143751933714583e-07,
+      "loss": 0.7064,
+      "step": 720
+    },
+    {
+      "epoch": 1.7945544554455446,
+      "grad_norm": 0.6569063272572411,
+      "learning_rate": 6.363504504263207e-07,
+      "loss": 0.694,
+      "step": 725
+    },
+    {
+      "epoch": 1.806930693069307,
+      "grad_norm": 0.672487356470194,
+      "learning_rate": 5.626968924854714e-07,
+      "loss": 0.7133,
+      "step": 730
+    },
+    {
+      "epoch": 1.8193069306930694,
+      "grad_norm": 0.6612411849360775,
+      "learning_rate": 4.934489028656164e-07,
+      "loss": 0.6933,
+      "step": 735
+    },
+    {
+      "epoch": 1.8316831683168315,
+      "grad_norm": 0.7156254594176831,
+      "learning_rate": 4.2863880825435687e-07,
+      "loss": 0.7057,
+      "step": 740
+    },
+    {
+      "epoch": 1.8440594059405941,
+      "grad_norm": 0.6833411888683371,
+      "learning_rate": 3.682968636192863e-07,
+      "loss": 0.7112,
+      "step": 745
+    },
+    {
+      "epoch": 1.8564356435643563,
+      "grad_norm": 0.6969326586876218,
+      "learning_rate": 3.124512380842204e-07,
+      "loss": 0.6912,
+      "step": 750
+    },
+    {
+      "epoch": 1.868811881188119,
+      "grad_norm": 0.6742873155450232,
+      "learning_rate": 2.61128001779144e-07,
+      "loss": 0.6823,
+      "step": 755
+    },
+    {
+      "epoch": 1.881188118811881,
+      "grad_norm": 0.6414949104474531,
+      "learning_rate": 2.1435111367002826e-07,
+      "loss": 0.7126,
+      "step": 760
+    },
+    {
+      "epoch": 1.8935643564356437,
+      "grad_norm": 0.6525583867438978,
+      "learning_rate": 1.7214241037418312e-07,
+      "loss": 0.6969,
+      "step": 765
+    },
+    {
+      "epoch": 1.9059405940594059,
+      "grad_norm": 0.65521211994519,
+      "learning_rate": 1.345215959663837e-07,
+      "loss": 0.6903,
+      "step": 770
+    },
+    {
+      "epoch": 1.9183168316831685,
+      "grad_norm": 0.6944361037558262,
+      "learning_rate": 1.0150623278051719e-07,
+      "loss": 0.6912,
+      "step": 775
+    },
+    {
+      "epoch": 1.9306930693069306,
+      "grad_norm": 0.648743159889204,
+      "learning_rate": 7.311173321104648e-08,
+      "loss": 0.683,
+      "step": 780
+    },
+    {
+      "epoch": 1.943069306930693,
+      "grad_norm": 0.6925205112702544,
+      "learning_rate": 4.935135251811995e-08,
+      "loss": 0.6934,
+      "step": 785
+    },
+    {
+      "epoch": 1.9554455445544554,
+      "grad_norm": 0.6504666964480196,
+      "learning_rate": 3.023618263968797e-08,
+      "loss": 0.7186,
+      "step": 790
+    },
+    {
+      "epoch": 1.9678217821782178,
+      "grad_norm": 0.7265261251377658,
+      "learning_rate": 1.577514701350591e-08,
+      "loss": 0.7216,
+      "step": 795
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "grad_norm": 0.6739382260611008,
+      "learning_rate": 5.97499641145416e-09,
+      "loss": 0.6928,
+      "step": 800
+    },
+    {
+      "epoch": 1.9925742574257426,
+      "grad_norm": 0.6660006595388417,
+      "learning_rate": 8.403057881067877e-10,
+      "loss": 0.6941,
+      "step": 805
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.07817542552948,
+      "eval_runtime": 43.2932,
+      "eval_samples_per_second": 75.832,
+      "eval_steps_per_second": 1.201,
+      "step": 808
+    },
+    {
+      "epoch": 2.0,
+      "step": 808,
+      "total_flos": 169178761789440.0,
+      "train_loss": 0.8271688128461933,
+      "train_runtime": 2411.6836,
+      "train_samples_per_second": 21.427,
+      "train_steps_per_second": 0.335
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 808,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 169178761789440.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1badd7c0fb787977876b66171a2f8458368e65f8a09ac77ba17124f501ffd61
+size 7224