Upload folder using huggingface_hub

.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 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Llama-3.1-8B-Instruct
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: llama_nsx
+  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. -->
+
+# llama_nsx
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the codes_330k_nsx dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9975786924939467,
+    "num_input_tokens_seen": 216006656,
+    "total_flos": 9.7266820915837e+18,
+    "train_loss": 0.9181526060243255,
+    "train_runtime": 17720.4517,
+    "train_samples_per_second": 2.983,
+    "train_steps_per_second": 0.006
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": 1.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 131072,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.48.2"
+}

llamaboard_config.yaml

@@ -0,0 +1,77 @@
+top.booster: liger_kernel
+top.checkpoint_path: null
+top.finetuning_type: freeze
+top.model_name: Llama-3.1-8B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: llama3
+top.template: llama3
+train.additional_target: ''
+train.apollo_rank: 256
+train.apollo_scale: 1
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 16
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 4096
+train.dataset:
+- codes_330k_nsx
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 1
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '50000000'
+train.neat_packing: true
+train.neftune_alpha: 0
+train.num_train_epochs: '1'
+train.packing: true
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to:
+- none
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 500
+train.swanlab_api_key: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: true
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: true
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1879f356aed350030bb40eb45ad362c89d9891096f79a3ab323d3ba5607668
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9f6c09073da00dc447e0fe6a3e3e3b8aa309968efdbce8a175fe10d8c4e2fa
+size 4999801680

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab936aa358eb625777816bfd869c70c82fef3224e2606d6b4391cbc9ecf2742b
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f89781af21cf616b8c39d9e152072ebe9324b54f2c099d60e9e36f845d48ac
+size 2040587824

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16932970496
+  },
+  "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-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"
+  }
+}

running_log.txt

@@ -0,0 +1,486 @@
+[INFO|2025-04-28 22:00:30] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/config.json
+
+[INFO|2025-04-28 22:00:30] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/tokenizer.json
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/special_tokens_map.json
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/tokenizer_config.json
+
+[INFO|2025-04-28 22:00:30] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-28 22:00:31] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-04-28 22:00:32] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/config.json
+
+[INFO|2025-04-28 22:00:32] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file tokenizer.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/tokenizer.json
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file special_tokens_map.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/special_tokens_map.json
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file tokenizer_config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/tokenizer_config.json
+
+[INFO|2025-04-28 22:00:34] tokenization_utils_base.py:2034 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-04-28 22:00:35] tokenization_utils_base.py:2304 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-04-28 22:00:35] logging.py:157 >> Add pad token: <|eot_id|>
+
+[INFO|2025-04-28 22:00:35] logging.py:157 >> Add <|eot_id|>,<|eom_id|> to stop words.
+
+[INFO|2025-04-28 22:00:35] logging.py:157 >> Loading dataset Codes_query_filtered_330k_ns.json...
+
+[INFO|2025-04-28 22:01:31] configuration_utils.py:696 >> loading configuration file config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/config.json
+
+[INFO|2025-04-28 22:01:31] configuration_utils.py:768 >> Model config LlamaConfig {
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": "4.48.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}
+
+
+[WARNING|2025-04-28 22:01:31] logging.py:162 >> Input length is smaller than max length. Consider increase input length.
+
+[INFO|2025-04-28 22:01:31] logging.py:157 >> Using llama3 scaling strategy and setting scaling factor to 1.0.
+
+[INFO|2025-04-28 22:01:31] logging.py:157 >> Using block diagonal attention for sequence packing without cross-attention.
+
+[INFO|2025-04-28 22:01:32] logging.py:157 >> Liger kernel has been applied to the model.
+
+[INFO|2025-04-28 22:01:32] modeling_utils.py:3904 >> loading weights file model.safetensors from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/model.safetensors.index.json
+
+[INFO|2025-04-28 22:01:32] modeling_utils.py:1582 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-04-28 22:01:32] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ]
+}
+
+
+[INFO|2025-04-28 22:01:45] modeling_utils.py:4888 >> All model checkpoint weights were used when initializing LlamaForCausalLM.
+
+
+[INFO|2025-04-28 22:01:45] modeling_utils.py:4896 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Llama-3.1-8B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
+
+[INFO|2025-04-28 22:01:45] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /home/kiho/.cache/huggingface/hub/models--meta-llama--Llama-3.1-8B-Instruct/snapshots/0e9e39f249a16976918f6564b8830bc894c89659/generation_config.json
+
+[INFO|2025-04-28 22:01:45] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9
+}
+
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> Fine-tuning method: Freeze
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> Set trainable layers: .15.,.31.
+
+[INFO|2025-04-28 22:01:45] logging.py:157 >> trainable params: 436,224,000 || all params: 8,030,261,248 || trainable%: 5.4323
+
+[INFO|2025-04-28 22:01:45] trainer.py:741 >> Using auto half precision backend
+
+[INFO|2025-04-28 22:01:46] logging.py:157 >> Found linear modules: q_proj,k_proj,o_proj,up_proj,gate_proj,v_proj,down_proj
+
+[INFO|2025-04-28 22:01:46] logging.py:157 >> Using APOLLO optimizer with args: {'rank': 256, 'proj': 'random', 'proj_type': 'std', 'update_proj_gap': 200, 'scale': 1, 'scale_type': 'channel', 'scale_front': False}.
+
+[INFO|2025-04-28 22:01:46] trainer.py:2369 >> ***** Running training *****
+
+[INFO|2025-04-28 22:01:46] trainer.py:2370 >>   Num examples = 52,860
+
+[INFO|2025-04-28 22:01:46] trainer.py:2371 >>   Num Epochs = 1
+
+[INFO|2025-04-28 22:01:46] trainer.py:2372 >>   Instantaneous batch size per device = 16
+
+[INFO|2025-04-28 22:01:46] trainer.py:2375 >>   Total train batch size (w. parallel, distributed & accumulation) = 512
+
+[INFO|2025-04-28 22:01:46] trainer.py:2376 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-04-28 22:01:46] trainer.py:2377 >>   Total optimization steps = 103
+
+[INFO|2025-04-28 22:01:46] trainer.py:2378 >>   Number of trainable parameters = 436,224,000
+
+[INFO|2025-04-28 22:04:48] logging.py:157 >> {'loss': 1.2027, 'learning_rate': 4.9988e-05, 'epoch': 0.01, 'throughput': 11584.80}
+
+[INFO|2025-04-28 22:07:41] logging.py:157 >> {'loss': 1.0647, 'learning_rate': 4.9953e-05, 'epoch': 0.02, 'throughput': 11850.11}
+
+[INFO|2025-04-28 22:10:33] logging.py:157 >> {'loss': 1.0243, 'learning_rate': 4.9895e-05, 'epoch': 0.03, 'throughput': 11957.01}
+
+[INFO|2025-04-28 22:13:25] logging.py:157 >> {'loss': 0.9974, 'learning_rate': 4.9814e-05, 'epoch': 0.04, 'throughput': 12012.50}
+
+[INFO|2025-04-28 22:16:17] logging.py:157 >> {'loss': 0.9874, 'learning_rate': 4.9710e-05, 'epoch': 0.05, 'throughput': 12050.19}
+
+[INFO|2025-04-28 22:19:09] logging.py:157 >> {'loss': 0.9478, 'learning_rate': 4.9583e-05, 'epoch': 0.06, 'throughput': 12071.84}
+
+[INFO|2025-04-28 22:22:01] logging.py:157 >> {'loss': 0.9761, 'learning_rate': 4.9432e-05, 'epoch': 0.07, 'throughput': 12087.55}
+
+[INFO|2025-04-28 22:24:54] logging.py:157 >> {'loss': 0.9698, 'learning_rate': 4.9259e-05, 'epoch': 0.08, 'throughput': 12096.64}
+
+[INFO|2025-04-28 22:27:46] logging.py:157 >> {'loss': 0.9804, 'learning_rate': 4.9064e-05, 'epoch': 0.09, 'throughput': 12106.38}
+
+[INFO|2025-04-28 22:30:38] logging.py:157 >> {'loss': 0.9562, 'learning_rate': 4.8846e-05, 'epoch': 0.10, 'throughput': 12115.60}
+
+[INFO|2025-04-28 22:33:30] logging.py:157 >> {'loss': 0.9649, 'learning_rate': 4.8606e-05, 'epoch': 0.11, 'throughput': 12121.46}
+
+[INFO|2025-04-28 22:36:23] logging.py:157 >> {'loss': 0.9300, 'learning_rate': 4.8344e-05, 'epoch': 0.12, 'throughput': 12123.79}
+
+[INFO|2025-04-28 22:39:16] logging.py:157 >> {'loss': 0.9356, 'learning_rate': 4.8060e-05, 'epoch': 0.13, 'throughput': 12124.38}
+
+[INFO|2025-04-28 22:42:08] logging.py:157 >> {'loss': 0.9279, 'learning_rate': 4.7755e-05, 'epoch': 0.14, 'throughput': 12125.60}
+
+[INFO|2025-04-28 22:45:00] logging.py:157 >> {'loss': 0.9311, 'learning_rate': 4.7429e-05, 'epoch': 0.15, 'throughput': 12130.58}
+
+[INFO|2025-04-28 22:47:52] logging.py:157 >> {'loss': 0.9311, 'learning_rate': 4.7082e-05, 'epoch': 0.15, 'throughput': 12134.17}
+
+[INFO|2025-04-28 22:50:45] logging.py:157 >> {'loss': 0.9381, 'learning_rate': 4.6714e-05, 'epoch': 0.16, 'throughput': 12136.31}
+
+[INFO|2025-04-28 22:53:37] logging.py:157 >> {'loss': 0.9354, 'learning_rate': 4.6326e-05, 'epoch': 0.17, 'throughput': 12138.18}
+
+[INFO|2025-04-28 22:56:29] logging.py:157 >> {'loss': 0.9574, 'learning_rate': 4.5918e-05, 'epoch': 0.18, 'throughput': 12139.11}
+
+[INFO|2025-04-28 22:59:22] logging.py:157 >> {'loss': 0.9124, 'learning_rate': 4.5491e-05, 'epoch': 0.19, 'throughput': 12140.73}
+
+[INFO|2025-04-28 23:02:14] logging.py:157 >> {'loss': 0.9500, 'learning_rate': 4.5045e-05, 'epoch': 0.20, 'throughput': 12142.69}
+
+[INFO|2025-04-28 23:05:06] logging.py:157 >> {'loss': 0.9179, 'learning_rate': 4.4580e-05, 'epoch': 0.21, 'throughput': 12143.43}
+
+[INFO|2025-04-28 23:07:59] logging.py:157 >> {'loss': 0.9414, 'learning_rate': 4.4097e-05, 'epoch': 0.22, 'throughput': 12144.94}
+
+[INFO|2025-04-28 23:10:50] logging.py:157 >> {'loss': 0.9348, 'learning_rate': 4.3596e-05, 'epoch': 0.23, 'throughput': 12148.22}
+
+[INFO|2025-04-28 23:13:43] logging.py:157 >> {'loss': 0.9260, 'learning_rate': 4.3077e-05, 'epoch': 0.24, 'throughput': 12148.04}
+
+[INFO|2025-04-28 23:16:35] logging.py:157 >> {'loss': 0.9323, 'learning_rate': 4.2542e-05, 'epoch': 0.25, 'throughput': 12150.35}
+
+[INFO|2025-04-28 23:19:28] logging.py:157 >> {'loss': 0.9218, 'learning_rate': 4.1991e-05, 'epoch': 0.26, 'throughput': 12149.24}
+
+[INFO|2025-04-28 23:22:20] logging.py:157 >> {'loss': 0.9319, 'learning_rate': 4.1424e-05, 'epoch': 0.27, 'throughput': 12149.20}
+
+[INFO|2025-04-28 23:25:12] logging.py:157 >> {'loss': 0.9202, 'learning_rate': 4.0841e-05, 'epoch': 0.28, 'throughput': 12150.25}
+
+[INFO|2025-04-28 23:28:04] logging.py:157 >> {'loss': 0.9141, 'learning_rate': 4.0244e-05, 'epoch': 0.29, 'throughput': 12152.71}
+
+[INFO|2025-04-28 23:30:56] logging.py:157 >> {'loss': 0.9145, 'learning_rate': 3.9633e-05, 'epoch': 0.30, 'throughput': 12153.01}
+
+[INFO|2025-04-28 23:33:47] logging.py:157 >> {'loss': 0.8975, 'learning_rate': 3.9008e-05, 'epoch': 0.31, 'throughput': 12156.93}
+
+[INFO|2025-04-28 23:36:39] logging.py:157 >> {'loss': 0.9614, 'learning_rate': 3.8370e-05, 'epoch': 0.32, 'throughput': 12159.26}
+
+[INFO|2025-04-28 23:39:30] logging.py:157 >> {'loss': 0.9327, 'learning_rate': 3.7719e-05, 'epoch': 0.33, 'throughput': 12161.37}
+
+[INFO|2025-04-28 23:42:21] logging.py:157 >> {'loss': 0.9153, 'learning_rate': 3.7057e-05, 'epoch': 0.34, 'throughput': 12164.47}
+
+[INFO|2025-04-28 23:45:12] logging.py:157 >> {'loss': 0.8977, 'learning_rate': 3.6384e-05, 'epoch': 0.35, 'throughput': 12166.53}
+
+[INFO|2025-04-28 23:48:04] logging.py:157 >> {'loss': 0.9147, 'learning_rate': 3.5700e-05, 'epoch': 0.36, 'throughput': 12168.64}
+
+[INFO|2025-04-28 23:50:55] logging.py:157 >> {'loss': 0.9264, 'learning_rate': 3.5006e-05, 'epoch': 0.37, 'throughput': 12170.33}
+
+[INFO|2025-04-28 23:53:46] logging.py:157 >> {'loss': 0.9041, 'learning_rate': 3.4302e-05, 'epoch': 0.38, 'throughput': 12173.21}
+
+[INFO|2025-04-28 23:56:37] logging.py:157 >> {'loss': 0.9322, 'learning_rate': 3.3590e-05, 'epoch': 0.39, 'throughput': 12175.56}
+
+[INFO|2025-04-28 23:59:28] logging.py:157 >> {'loss': 0.9257, 'learning_rate': 3.2870e-05, 'epoch': 0.40, 'throughput': 12176.34}
+
+[INFO|2025-04-29 00:02:19] logging.py:157 >> {'loss': 0.8952, 'learning_rate': 3.2143e-05, 'epoch': 0.41, 'throughput': 12178.42}
+
+[INFO|2025-04-29 00:05:11] logging.py:157 >> {'loss': 0.9072, 'learning_rate': 3.1409e-05, 'epoch': 0.42, 'throughput': 12179.30}
+
+[INFO|2025-04-29 00:08:02] logging.py:157 >> {'loss': 0.9166, 'learning_rate': 3.0669e-05, 'epoch': 0.43, 'throughput': 12181.27}
+
+[INFO|2025-04-29 00:10:53] logging.py:157 >> {'loss': 0.8924, 'learning_rate': 2.9924e-05, 'epoch': 0.44, 'throughput': 12182.88}
+
+[INFO|2025-04-29 00:13:45] logging.py:157 >> {'loss': 0.8871, 'learning_rate': 2.9174e-05, 'epoch': 0.45, 'throughput': 12184.12}
+
+[INFO|2025-04-29 00:16:36] logging.py:157 >> {'loss': 0.9263, 'learning_rate': 2.8421e-05, 'epoch': 0.46, 'throughput': 12185.10}
+
+[INFO|2025-04-29 00:19:27] logging.py:157 >> {'loss': 0.9158, 'learning_rate': 2.7664e-05, 'epoch': 0.46, 'throughput': 12186.29}
+
+[INFO|2025-04-29 00:22:19] logging.py:157 >> {'loss': 0.9034, 'learning_rate': 2.6904e-05, 'epoch': 0.47, 'throughput': 12187.37}
+
+[INFO|2025-04-29 00:25:10] logging.py:157 >> {'loss': 0.9044, 'learning_rate': 2.6143e-05, 'epoch': 0.48, 'throughput': 12187.76}
+
+[INFO|2025-04-29 00:28:02] logging.py:157 >> {'loss': 0.9173, 'learning_rate': 2.5381e-05, 'epoch': 0.49, 'throughput': 12188.76}
+
+[INFO|2025-04-29 00:30:53] logging.py:157 >> {'loss': 0.9349, 'learning_rate': 2.4619e-05, 'epoch': 0.50, 'throughput': 12190.37}
+
+[INFO|2025-04-29 00:33:44] logging.py:157 >> {'loss': 0.8996, 'learning_rate': 2.3857e-05, 'epoch': 0.51, 'throughput': 12191.00}
+
+[INFO|2025-04-29 00:36:35] logging.py:157 >> {'loss': 0.9018, 'learning_rate': 2.3096e-05, 'epoch': 0.52, 'throughput': 12192.15}
+
+[INFO|2025-04-29 00:39:27] logging.py:157 >> {'loss': 0.8797, 'learning_rate': 2.2336e-05, 'epoch': 0.53, 'throughput': 12192.73}
+
+[INFO|2025-04-29 00:42:19] logging.py:157 >> {'loss': 0.9075, 'learning_rate': 2.1579e-05, 'epoch': 0.54, 'throughput': 12193.09}
+
+[INFO|2025-04-29 00:45:10] logging.py:157 >> {'loss': 0.9068, 'learning_rate': 2.0826e-05, 'epoch': 0.55, 'throughput': 12194.01}
+
+[INFO|2025-04-29 00:48:02] logging.py:157 >> {'loss': 0.9154, 'learning_rate': 2.0076e-05, 'epoch': 0.56, 'throughput': 12194.06}
+
+[INFO|2025-04-29 00:50:54] logging.py:157 >> {'loss': 0.8895, 'learning_rate': 1.9331e-05, 'epoch': 0.57, 'throughput': 12194.36}
+
+[INFO|2025-04-29 00:53:45] logging.py:157 >> {'loss': 0.8910, 'learning_rate': 1.8591e-05, 'epoch': 0.58, 'throughput': 12194.93}
+
+[INFO|2025-04-29 00:56:37] logging.py:157 >> {'loss': 0.8928, 'learning_rate': 1.7857e-05, 'epoch': 0.59, 'throughput': 12195.08}
+
+[INFO|2025-04-29 00:59:29] logging.py:157 >> {'loss': 0.8918, 'learning_rate': 1.7130e-05, 'epoch': 0.60, 'throughput': 12195.46}
+
+[INFO|2025-04-29 01:02:20] logging.py:157 >> {'loss': 0.8807, 'learning_rate': 1.6410e-05, 'epoch': 0.61, 'throughput': 12195.62}
+
+[INFO|2025-04-29 01:05:12] logging.py:157 >> {'loss': 0.8934, 'learning_rate': 1.5698e-05, 'epoch': 0.62, 'throughput': 12196.25}
+
+[INFO|2025-04-29 01:08:03] logging.py:157 >> {'loss': 0.8809, 'learning_rate': 1.4994e-05, 'epoch': 0.63, 'throughput': 12196.80}
+
+[INFO|2025-04-29 01:10:55] logging.py:157 >> {'loss': 0.8856, 'learning_rate': 1.4300e-05, 'epoch': 0.64, 'throughput': 12197.24}
+
+[INFO|2025-04-29 01:13:46] logging.py:157 >> {'loss': 0.9117, 'learning_rate': 1.3616e-05, 'epoch': 0.65, 'throughput': 12197.76}
+
+[INFO|2025-04-29 01:16:38] logging.py:157 >> {'loss': 0.8993, 'learning_rate': 1.2943e-05, 'epoch': 0.66, 'throughput': 12198.14}
+
+[INFO|2025-04-29 01:19:29] logging.py:157 >> {'loss': 0.9215, 'learning_rate': 1.2281e-05, 'epoch': 0.67, 'throughput': 12198.43}
+
+[INFO|2025-04-29 01:22:21] logging.py:157 >> {'loss': 0.8916, 'learning_rate': 1.1630e-05, 'epoch': 0.68, 'throughput': 12199.00}
+
+[INFO|2025-04-29 01:25:12] logging.py:157 >> {'loss': 0.8913, 'learning_rate': 1.0992e-05, 'epoch': 0.69, 'throughput': 12199.79}
+
+[INFO|2025-04-29 01:28:03] logging.py:157 >> {'loss': 0.8973, 'learning_rate': 1.0367e-05, 'epoch': 0.70, 'throughput': 12200.41}
+
+[INFO|2025-04-29 01:30:54] logging.py:157 >> {'loss': 0.9136, 'learning_rate': 9.7558e-06, 'epoch': 0.71, 'throughput': 12201.41}
+
+[INFO|2025-04-29 01:33:45] logging.py:157 >> {'loss': 0.9217, 'learning_rate': 9.1586e-06, 'epoch': 0.72, 'throughput': 12201.98}
+
+[INFO|2025-04-29 01:36:37] logging.py:157 >> {'loss': 0.8926, 'learning_rate': 8.5762e-06, 'epoch': 0.73, 'throughput': 12202.13}
+
+[INFO|2025-04-29 01:39:28] logging.py:157 >> {'loss': 0.8828, 'learning_rate': 8.0090e-06, 'epoch': 0.74, 'throughput': 12202.67}
+
+[INFO|2025-04-29 01:42:20] logging.py:157 >> {'loss': 0.8944, 'learning_rate': 7.4576e-06, 'epoch': 0.75, 'throughput': 12202.71}
+
+[INFO|2025-04-29 01:45:12] logging.py:157 >> {'loss': 0.9085, 'learning_rate': 6.9226e-06, 'epoch': 0.76, 'throughput': 12203.07}
+
+[INFO|2025-04-29 01:48:04] logging.py:157 >> {'loss': 0.8926, 'learning_rate': 6.4044e-06, 'epoch': 0.77, 'throughput': 12202.71}
+
+[INFO|2025-04-29 01:50:55] logging.py:157 >> {'loss': 0.9022, 'learning_rate': 5.9035e-06, 'epoch': 0.77, 'throughput': 12203.40}
+
+[INFO|2025-04-29 01:53:46] logging.py:157 >> {'loss': 0.9081, 'learning_rate': 5.4203e-06, 'epoch': 0.78, 'throughput': 12203.86}
+
+[INFO|2025-04-29 01:56:38] logging.py:157 >> {'loss': 0.8964, 'learning_rate': 4.9554e-06, 'epoch': 0.79, 'throughput': 12203.74}
+
+[INFO|2025-04-29 01:59:30] logging.py:157 >> {'loss': 0.8872, 'learning_rate': 4.5091e-06, 'epoch': 0.80, 'throughput': 12204.10}
+
+[INFO|2025-04-29 02:02:21] logging.py:157 >> {'loss': 0.9052, 'learning_rate': 4.0818e-06, 'epoch': 0.81, 'throughput': 12204.57}
+
+[INFO|2025-04-29 02:05:13] logging.py:157 >> {'loss': 0.8887, 'learning_rate': 3.6740e-06, 'epoch': 0.82, 'throughput': 12204.65}
+
+[INFO|2025-04-29 02:08:04] logging.py:157 >> {'loss': 0.9228, 'learning_rate': 3.2861e-06, 'epoch': 0.83, 'throughput': 12205.11}
+
+[INFO|2025-04-29 02:10:55] logging.py:157 >> {'loss': 0.9070, 'learning_rate': 2.9184e-06, 'epoch': 0.84, 'throughput': 12205.63}
+
+[INFO|2025-04-29 02:13:46] logging.py:157 >> {'loss': 0.8912, 'learning_rate': 2.5712e-06, 'epoch': 0.85, 'throughput': 12206.01}
+
+[INFO|2025-04-29 02:16:38] logging.py:157 >> {'loss': 0.9100, 'learning_rate': 2.2448e-06, 'epoch': 0.86, 'throughput': 12206.13}
+
+[INFO|2025-04-29 02:19:30] logging.py:157 >> {'loss': 0.8817, 'learning_rate': 1.9397e-06, 'epoch': 0.87, 'throughput': 12206.42}
+
+[INFO|2025-04-29 02:22:21] logging.py:157 >> {'loss': 0.8795, 'learning_rate': 1.6559e-06, 'epoch': 0.88, 'throughput': 12206.66}
+
+[INFO|2025-04-29 02:25:13] logging.py:157 >> {'loss': 0.8945, 'learning_rate': 1.3939e-06, 'epoch': 0.89, 'throughput': 12206.32}
+
+[INFO|2025-04-29 02:28:05] logging.py:157 >> {'loss': 0.8941, 'learning_rate': 1.1539e-06, 'epoch': 0.90, 'throughput': 12206.23}
+
+[INFO|2025-04-29 02:30:57] logging.py:157 >> {'loss': 0.8771, 'learning_rate': 9.3603e-07, 'epoch': 0.91, 'throughput': 12206.25}
+
+[INFO|2025-04-29 02:33:48] logging.py:157 >> {'loss': 0.8779, 'learning_rate': 7.4056e-07, 'epoch': 0.92, 'throughput': 12206.55}
+
+[INFO|2025-04-29 02:36:40] logging.py:157 >> {'loss': 0.8978, 'learning_rate': 5.6765e-07, 'epoch': 0.93, 'throughput': 12207.07}
+
+[INFO|2025-04-29 02:39:31] logging.py:157 >> {'loss': 0.8858, 'learning_rate': 4.1747e-07, 'epoch': 0.94, 'throughput': 12207.47}
+
+[INFO|2025-04-29 02:42:22] logging.py:157 >> {'loss': 0.8983, 'learning_rate': 2.9016e-07, 'epoch': 0.95, 'throughput': 12207.74}
+
+[INFO|2025-04-29 02:45:13] logging.py:157 >> {'loss': 0.9030, 'learning_rate': 1.8583e-07, 'epoch': 0.96, 'throughput': 12208.21}
+
+[INFO|2025-04-29 02:48:05] logging.py:157 >> {'loss': 0.8660, 'learning_rate': 1.0459e-07, 'epoch': 0.97, 'throughput': 12208.23}
+
+[INFO|2025-04-29 02:50:57] logging.py:157 >> {'loss': 0.9024, 'learning_rate': 4.6501e-08, 'epoch': 0.98, 'throughput': 12208.43}
+
+[INFO|2025-04-29 02:53:48] logging.py:157 >> {'loss': 0.8841, 'learning_rate': 1.1628e-08, 'epoch': 0.99, 'throughput': 12208.72}
+
+[INFO|2025-04-29 02:56:40] logging.py:157 >> {'loss': 0.8893, 'learning_rate': 0.0000e+00, 'epoch': 1.00, 'throughput': 12208.75}
+
+[INFO|2025-04-29 02:56:40] trainer.py:3910 >> Saving model checkpoint to saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103
+
+[INFO|2025-04-29 02:56:40] configuration_utils.py:420 >> Configuration saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103/config.json
+
+[INFO|2025-04-29 02:56:40] configuration_utils.py:909 >> Configuration saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103/generation_config.json
+
+[INFO|2025-04-29 02:57:06] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103/model.safetensors.index.json.
+
+[INFO|2025-04-29 02:57:06] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103/tokenizer_config.json
+
+[INFO|2025-04-29 02:57:06] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/checkpoint-103/special_tokens_map.json
+
+[INFO|2025-04-29 02:57:06] trainer.py:2643 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-04-29 02:57:06] trainer.py:3910 >> Saving model checkpoint to saves/Llama-3.1-8B-Instruct/freeze/llama_nsx
+
+[INFO|2025-04-29 02:57:06] configuration_utils.py:420 >> Configuration saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/config.json
+
+[INFO|2025-04-29 02:57:06] configuration_utils.py:909 >> Configuration saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/generation_config.json
+
+[INFO|2025-04-29 02:57:36] modeling_utils.py:2996 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/model.safetensors.index.json.
+
+[INFO|2025-04-29 02:57:36] tokenization_utils_base.py:2491 >> tokenizer config file saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/tokenizer_config.json
+
+[INFO|2025-04-29 02:57:36] tokenization_utils_base.py:2500 >> Special tokens file saved in saves/Llama-3.1-8B-Instruct/freeze/llama_nsx/special_tokens_map.json
+
+[WARNING|2025-04-29 02:57:36] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-04-29 02:57:36] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-04-29 02:57:36] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,2070 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|eot_id|>",
+    "<|eom_id|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9975786924939467,
+    "num_input_tokens_seen": 216006656,
+    "total_flos": 9.7266820915837e+18,
+    "train_loss": 0.9181526060243255,
+    "train_runtime": 17720.4517,
+    "train_samples_per_second": 2.983,
+    "train_steps_per_second": 0.006
+}

trainer_log.jsonl

@@ -0,0 +1,104 @@
+{"current_steps": 1, "total_steps": 103, "loss": 1.2027, "lr": 4.998837209058379e-05, "epoch": 0.009685230024213076, "percentage": 0.97, "elapsed_time": "0:03:01", "remaining_time": "5:07:44", "throughput": 11584.8, "total_tokens": 2097152}
+{"current_steps": 2, "total_steps": 103, "loss": 1.0647, "lr": 4.9953499178997346e-05, "epoch": 0.01937046004842615, "percentage": 1.94, "elapsed_time": "0:05:53", "remaining_time": "4:57:54", "throughput": 11850.11, "total_tokens": 4194304}
+{"current_steps": 3, "total_steps": 103, "loss": 1.0243, "lr": 4.9895413705165234e-05, "epoch": 0.029055690072639227, "percentage": 2.91, "elapsed_time": "0:08:46", "remaining_time": "4:52:19", "throughput": 11957.01, "total_tokens": 6291456}
+{"current_steps": 4, "total_steps": 103, "loss": 0.9974, "lr": 4.98141697020977e-05, "epoch": 0.0387409200968523, "percentage": 3.88, "elapsed_time": "0:11:38", "remaining_time": "4:48:03", "throughput": 12012.5, "total_tokens": 8388608}
+{"current_steps": 5, "total_steps": 103, "loss": 0.9874, "lr": 4.970984274562741e-05, "epoch": 0.048426150121065374, "percentage": 4.85, "elapsed_time": "0:14:30", "remaining_time": "4:44:15", "throughput": 12050.19, "total_tokens": 10485760}
+{"current_steps": 6, "total_steps": 103, "loss": 0.9478, "lr": 4.958252988410631e-05, "epoch": 0.05811138014527845, "percentage": 5.83, "elapsed_time": "0:17:22", "remaining_time": "4:40:51", "throughput": 12071.84, "total_tokens": 12582912}
+{"current_steps": 7, "total_steps": 103, "loss": 0.9761, "lr": 4.9432349548128124e-05, "epoch": 0.06779661016949153, "percentage": 6.8, "elapsed_time": "0:20:14", "remaining_time": "4:37:35", "throughput": 12087.55, "total_tokens": 14680064}
+{"current_steps": 8, "total_steps": 103, "loss": 0.9698, "lr": 4.925944144036026e-05, "epoch": 0.0774818401937046, "percentage": 7.77, "elapsed_time": "0:23:06", "remaining_time": "4:34:29", "throughput": 12096.64, "total_tokens": 16777216}
+{"current_steps": 9, "total_steps": 103, "loss": 0.9804, "lr": 4.90639664055879e-05, "epoch": 0.08716707021791767, "percentage": 8.74, "elapsed_time": "0:25:59", "remaining_time": "4:31:23", "throughput": 12106.38, "total_tokens": 18874368}
+{"current_steps": 10, "total_steps": 103, "loss": 0.9562, "lr": 4.884610628109082e-05, "epoch": 0.09685230024213075, "percentage": 9.71, "elapsed_time": "0:28:50", "remaining_time": "4:28:17", "throughput": 12115.6, "total_tokens": 20971520}
+{"current_steps": 11, "total_steps": 103, "loss": 0.9649, "lr": 4.860606372749247e-05, "epoch": 0.10653753026634383, "percentage": 10.68, "elapsed_time": "0:31:43", "remaining_time": "4:25:17", "throughput": 12121.46, "total_tokens": 23068672}
+{"current_steps": 12, "total_steps": 103, "loss": 0.93, "lr": 4.8344062040238395e-05, "epoch": 0.1162227602905569, "percentage": 11.65, "elapsed_time": "0:34:35", "remaining_time": "4:22:21", "throughput": 12123.79, "total_tokens": 25165824}
+{"current_steps": 13, "total_steps": 103, "loss": 0.9356, "lr": 4.806034494187949e-05, "epoch": 0.12590799031476999, "percentage": 12.62, "elapsed_time": "0:37:28", "remaining_time": "4:19:27", "throughput": 12124.38, "total_tokens": 27262976}
+{"current_steps": 14, "total_steps": 103, "loss": 0.9279, "lr": 4.775517635535332e-05, "epoch": 0.13559322033898305, "percentage": 13.59, "elapsed_time": "0:40:21", "remaining_time": "4:16:32", "throughput": 12125.6, "total_tokens": 29360128}
+{"current_steps": 15, "total_steps": 103, "loss": 0.9311, "lr": 4.742884015847436e-05, "epoch": 0.14527845036319612, "percentage": 14.56, "elapsed_time": "0:43:13", "remaining_time": "4:13:33", "throughput": 12130.58, "total_tokens": 31457280}
+{"current_steps": 16, "total_steps": 103, "loss": 0.9311, "lr": 4.708163991986152e-05, "epoch": 0.1549636803874092, "percentage": 15.53, "elapsed_time": "0:46:05", "remaining_time": "4:10:36", "throughput": 12134.17, "total_tokens": 33554432}
+{"current_steps": 17, "total_steps": 103, "loss": 0.9381, "lr": 4.6713898616548724e-05, "epoch": 0.16464891041162227, "percentage": 16.5, "elapsed_time": "0:48:57", "remaining_time": "4:07:40", "throughput": 12136.31, "total_tokens": 35651584}
+{"current_steps": 18, "total_steps": 103, "loss": 0.9354, "lr": 4.6325958333541044e-05, "epoch": 0.17433414043583534, "percentage": 17.48, "elapsed_time": "0:51:49", "remaining_time": "4:04:45", "throughput": 12138.18, "total_tokens": 37748736}
+{"current_steps": 19, "total_steps": 103, "loss": 0.9574, "lr": 4.591817994559605e-05, "epoch": 0.18401937046004843, "percentage": 18.45, "elapsed_time": "0:54:42", "remaining_time": "4:01:51", "throughput": 12139.11, "total_tokens": 39845888}
+{"current_steps": 20, "total_steps": 103, "loss": 0.9124, "lr": 4.5490942781526316e-05, "epoch": 0.1937046004842615, "percentage": 19.42, "elapsed_time": "0:57:34", "remaining_time": "3:58:57", "throughput": 12140.73, "total_tokens": 41943040}
+{"current_steps": 21, "total_steps": 103, "loss": 0.95, "lr": 4.504464427133527e-05, "epoch": 0.2033898305084746, "percentage": 20.39, "elapsed_time": "1:00:26", "remaining_time": "3:56:02", "throughput": 12142.69, "total_tokens": 44040192}
+{"current_steps": 22, "total_steps": 103, "loss": 0.9179, "lr": 4.457969957651484e-05, "epoch": 0.21307506053268765, "percentage": 21.36, "elapsed_time": "1:03:19", "remaining_time": "3:53:08", "throughput": 12143.43, "total_tokens": 46137344}
+{"current_steps": 23, "total_steps": 103, "loss": 0.9414, "lr": 4.409654120384862e-05, "epoch": 0.22276029055690072, "percentage": 22.33, "elapsed_time": "1:06:11", "remaining_time": "3:50:14", "throughput": 12144.94, "total_tokens": 48234496}
+{"current_steps": 24, "total_steps": 103, "loss": 0.9348, "lr": 4.35956186030799e-05, "epoch": 0.2324455205811138, "percentage": 23.3, "elapsed_time": "1:09:03", "remaining_time": "3:47:17", "throughput": 12148.22, "total_tokens": 50331648}
+{"current_steps": 25, "total_steps": 103, "loss": 0.926, "lr": 4.307739774881878e-05, "epoch": 0.24213075060532688, "percentage": 24.27, "elapsed_time": "1:11:55", "remaining_time": "3:44:25", "throughput": 12148.04, "total_tokens": 52428800}
+{"current_steps": 26, "total_steps": 103, "loss": 0.9323, "lr": 4.254236070707733e-05, "epoch": 0.25181598062953997, "percentage": 25.24, "elapsed_time": "1:14:47", "remaining_time": "3:41:30", "throughput": 12150.35, "total_tokens": 54525952}
+{"current_steps": 27, "total_steps": 103, "loss": 0.9218, "lr": 4.1991005186836005e-05, "epoch": 0.26150121065375304, "percentage": 26.21, "elapsed_time": "1:17:40", "remaining_time": "3:38:38", "throughput": 12149.24, "total_tokens": 56623104}
+{"current_steps": 28, "total_steps": 103, "loss": 0.9319, "lr": 4.142384407705846e-05, "epoch": 0.2711864406779661, "percentage": 27.18, "elapsed_time": "1:20:33", "remaining_time": "3:35:46", "throughput": 12149.2, "total_tokens": 58720256}
+{"current_steps": 29, "total_steps": 103, "loss": 0.9202, "lr": 4.084140496958538e-05, "epoch": 0.28087167070217917, "percentage": 28.16, "elapsed_time": "1:23:25", "remaining_time": "3:32:52", "throughput": 12150.25, "total_tokens": 60817408}
+{"current_steps": 30, "total_steps": 103, "loss": 0.9141, "lr": 4.024422966835136e-05, "epoch": 0.29055690072639223, "percentage": 29.13, "elapsed_time": "1:26:16", "remaining_time": "3:29:57", "throughput": 12152.71, "total_tokens": 62914560}
+{"current_steps": 31, "total_steps": 103, "loss": 0.9145, "lr": 3.963287368538106e-05, "epoch": 0.30024213075060535, "percentage": 30.1, "elapsed_time": "1:29:09", "remaining_time": "3:27:04", "throughput": 12153.01, "total_tokens": 65011712}
+{"current_steps": 32, "total_steps": 103, "loss": 0.8975, "lr": 3.900790572403376e-05, "epoch": 0.3099273607748184, "percentage": 31.07, "elapsed_time": "1:32:00", "remaining_time": "3:24:07", "throughput": 12156.93, "total_tokens": 67108864}
+{"current_steps": 33, "total_steps": 103, "loss": 0.9614, "lr": 3.836990714997686e-05, "epoch": 0.3196125907990315, "percentage": 32.04, "elapsed_time": "1:34:51", "remaining_time": "3:21:13", "throughput": 12159.26, "total_tokens": 69206016}
+{"current_steps": 34, "total_steps": 103, "loss": 0.9327, "lr": 3.7719471450380514e-05, "epoch": 0.32929782082324455, "percentage": 33.01, "elapsed_time": "1:37:43", "remaining_time": "3:18:18", "throughput": 12161.37, "total_tokens": 71303168}
+{"current_steps": 35, "total_steps": 103, "loss": 0.9153, "lr": 3.7057203681836406e-05, "epoch": 0.3389830508474576, "percentage": 33.98, "elapsed_time": "1:40:33", "remaining_time": "3:15:23", "throughput": 12164.47, "total_tokens": 73400320}
+{"current_steps": 36, "total_steps": 103, "loss": 0.8977, "lr": 3.638371990751428e-05, "epoch": 0.3486682808716707, "percentage": 34.95, "elapsed_time": "1:43:25", "remaining_time": "3:12:28", "throughput": 12166.53, "total_tokens": 75497472}
+{"current_steps": 37, "total_steps": 103, "loss": 0.9147, "lr": 3.569964662407983e-05, "epoch": 0.3583535108958838, "percentage": 35.92, "elapsed_time": "1:46:16", "remaining_time": "3:09:34", "throughput": 12168.64, "total_tokens": 77594624}
+{"current_steps": 38, "total_steps": 103, "loss": 0.9264, "lr": 3.500562017890695e-05, "epoch": 0.36803874092009686, "percentage": 36.89, "elapsed_time": "1:49:08", "remaining_time": "3:06:40", "throughput": 12170.33, "total_tokens": 79691776}
+{"current_steps": 39, "total_steps": 103, "loss": 0.9041, "lr": 3.430228617812661e-05, "epoch": 0.37772397094430993, "percentage": 37.86, "elapsed_time": "1:51:58", "remaining_time": "3:03:45", "throughput": 12173.21, "total_tokens": 81788928}
+{"current_steps": 40, "total_steps": 103, "loss": 0.9322, "lr": 3.3590298886062833e-05, "epoch": 0.387409200968523, "percentage": 38.83, "elapsed_time": "1:54:49", "remaining_time": "3:00:51", "throughput": 12175.56, "total_tokens": 83886080}
+{"current_steps": 41, "total_steps": 103, "loss": 0.9257, "lr": 3.2870320616614626e-05, "epoch": 0.39709443099273606, "percentage": 39.81, "elapsed_time": "1:57:41", "remaining_time": "2:57:58", "throughput": 12176.34, "total_tokens": 85983232}
+{"current_steps": 42, "total_steps": 103, "loss": 0.8952, "lr": 3.21430211171499e-05, "epoch": 0.4067796610169492, "percentage": 40.78, "elapsed_time": "2:00:32", "remaining_time": "2:55:04", "throughput": 12178.42, "total_tokens": 88080384}
+{"current_steps": 43, "total_steps": 103, "loss": 0.9072, "lr": 3.140907694548451e-05, "epoch": 0.41646489104116224, "percentage": 41.75, "elapsed_time": "2:03:24", "remaining_time": "2:52:11", "throughput": 12179.3, "total_tokens": 90177536}
+{"current_steps": 44, "total_steps": 103, "loss": 0.9166, "lr": 3.066917084052603e-05, "epoch": 0.4261501210653753, "percentage": 42.72, "elapsed_time": "2:06:15", "remaining_time": "2:49:17", "throughput": 12181.27, "total_tokens": 92274688}
+{"current_steps": 45, "total_steps": 103, "loss": 0.8924, "lr": 2.9923991087167658e-05, "epoch": 0.4358353510895884, "percentage": 43.69, "elapsed_time": "2:09:06", "remaining_time": "2:46:24", "throughput": 12182.88, "total_tokens": 94371840}
+{"current_steps": 46, "total_steps": 103, "loss": 0.8871, "lr": 2.9174230876023058e-05, "epoch": 0.44552058111380144, "percentage": 44.66, "elapsed_time": "2:11:57", "remaining_time": "2:43:30", "throughput": 12184.12, "total_tokens": 96468992}
+{"current_steps": 47, "total_steps": 103, "loss": 0.9263, "lr": 2.8420587658597757e-05, "epoch": 0.4552058111380145, "percentage": 45.63, "elapsed_time": "2:14:49", "remaining_time": "2:40:38", "throughput": 12185.1, "total_tokens": 98566144}
+{"current_steps": 48, "total_steps": 103, "loss": 0.9158, "lr": 2.7663762498496905e-05, "epoch": 0.4648910411622276, "percentage": 46.6, "elapsed_time": "2:17:40", "remaining_time": "2:37:45", "throughput": 12186.29, "total_tokens": 100663296}
+{"current_steps": 49, "total_steps": 103, "loss": 0.9034, "lr": 2.6904459419272955e-05, "epoch": 0.4745762711864407, "percentage": 47.57, "elapsed_time": "2:20:31", "remaining_time": "2:34:52", "throughput": 12187.37, "total_tokens": 102760448}
+{"current_steps": 50, "total_steps": 103, "loss": 0.9044, "lr": 2.6143384749519866e-05, "epoch": 0.48426150121065376, "percentage": 48.54, "elapsed_time": "2:23:23", "remaining_time": "2:31:59", "throughput": 12187.76, "total_tokens": 104857600}
+{"current_steps": 51, "total_steps": 103, "loss": 0.9173, "lr": 2.538124646582315e-05, "epoch": 0.4939467312348668, "percentage": 49.51, "elapsed_time": "2:26:14", "remaining_time": "2:29:06", "throughput": 12188.76, "total_tokens": 106954752}
+{"current_steps": 52, "total_steps": 103, "loss": 0.9349, "lr": 2.4618753534176856e-05, "epoch": 0.5036319612590799, "percentage": 50.49, "elapsed_time": "2:29:05", "remaining_time": "2:26:13", "throughput": 12190.37, "total_tokens": 109051904}
+{"current_steps": 53, "total_steps": 103, "loss": 0.8996, "lr": 2.385661525048014e-05, "epoch": 0.513317191283293, "percentage": 51.46, "elapsed_time": "2:31:57", "remaining_time": "2:23:21", "throughput": 12191.0, "total_tokens": 111149056}
+{"current_steps": 54, "total_steps": 103, "loss": 0.9018, "lr": 2.3095540580727055e-05, "epoch": 0.5230024213075061, "percentage": 52.43, "elapsed_time": "2:34:48", "remaining_time": "2:20:28", "throughput": 12192.15, "total_tokens": 113246208}
+{"current_steps": 55, "total_steps": 103, "loss": 0.8797, "lr": 2.23362375015031e-05, "epoch": 0.5326876513317191, "percentage": 53.4, "elapsed_time": "2:37:40", "remaining_time": "2:17:36", "throughput": 12192.73, "total_tokens": 115343360}
+{"current_steps": 56, "total_steps": 103, "loss": 0.9075, "lr": 2.157941234140225e-05, "epoch": 0.5423728813559322, "percentage": 54.37, "elapsed_time": "2:40:31", "remaining_time": "2:14:43", "throughput": 12193.09, "total_tokens": 117440512}
+{"current_steps": 57, "total_steps": 103, "loss": 0.9068, "lr": 2.082576912397695e-05, "epoch": 0.5520581113801453, "percentage": 55.34, "elapsed_time": "2:43:22", "remaining_time": "2:11:51", "throughput": 12194.01, "total_tokens": 119537664}
+{"current_steps": 58, "total_steps": 103, "loss": 0.9154, "lr": 2.0076008912832355e-05, "epoch": 0.5617433414043583, "percentage": 56.31, "elapsed_time": "2:46:14", "remaining_time": "2:08:59", "throughput": 12194.06, "total_tokens": 121634816}
+{"current_steps": 59, "total_steps": 103, "loss": 0.8895, "lr": 1.933082915947398e-05, "epoch": 0.5714285714285714, "percentage": 57.28, "elapsed_time": "2:49:06", "remaining_time": "2:06:06", "throughput": 12194.36, "total_tokens": 123731968}
+{"current_steps": 60, "total_steps": 103, "loss": 0.891, "lr": 1.8590923054515503e-05, "epoch": 0.5811138014527845, "percentage": 58.25, "elapsed_time": "2:51:58", "remaining_time": "2:03:14", "throughput": 12194.93, "total_tokens": 125829120}
+{"current_steps": 61, "total_steps": 103, "loss": 0.8928, "lr": 1.7856978882850113e-05, "epoch": 0.5907990314769975, "percentage": 59.22, "elapsed_time": "2:54:49", "remaining_time": "2:00:22", "throughput": 12195.08, "total_tokens": 127926272}
+{"current_steps": 62, "total_steps": 103, "loss": 0.8918, "lr": 1.7129679383385383e-05, "epoch": 0.6004842615012107, "percentage": 60.19, "elapsed_time": "2:57:41", "remaining_time": "1:57:30", "throughput": 12195.46, "total_tokens": 130023424}
+{"current_steps": 63, "total_steps": 103, "loss": 0.8807, "lr": 1.6409701113937183e-05, "epoch": 0.6101694915254238, "percentage": 61.17, "elapsed_time": "3:00:33", "remaining_time": "1:54:38", "throughput": 12195.62, "total_tokens": 132120576}
+{"current_steps": 64, "total_steps": 103, "loss": 0.8934, "lr": 1.5697713821873398e-05, "epoch": 0.6198547215496368, "percentage": 62.14, "elapsed_time": "3:03:24", "remaining_time": "1:51:46", "throughput": 12196.25, "total_tokens": 134217728}
+{"current_steps": 65, "total_steps": 103, "loss": 0.8809, "lr": 1.4994379821093049e-05, "epoch": 0.6295399515738499, "percentage": 63.11, "elapsed_time": "3:06:16", "remaining_time": "1:48:53", "throughput": 12196.8, "total_tokens": 136314880}
+{"current_steps": 66, "total_steps": 103, "loss": 0.8856, "lr": 1.430035337592018e-05, "epoch": 0.639225181598063, "percentage": 64.08, "elapsed_time": "3:09:07", "remaining_time": "1:46:01", "throughput": 12197.24, "total_tokens": 138412032}
+{"current_steps": 67, "total_steps": 103, "loss": 0.9117, "lr": 1.3616280092485717e-05, "epoch": 0.648910411622276, "percentage": 65.05, "elapsed_time": "3:11:59", "remaining_time": "1:43:09", "throughput": 12197.76, "total_tokens": 140509184}
+{"current_steps": 68, "total_steps": 103, "loss": 0.8993, "lr": 1.2942796318163595e-05, "epoch": 0.6585956416464891, "percentage": 66.02, "elapsed_time": "3:14:50", "remaining_time": "1:40:17", "throughput": 12198.14, "total_tokens": 142606336}
+{"current_steps": 69, "total_steps": 103, "loss": 0.9215, "lr": 1.2280528549619485e-05, "epoch": 0.6682808716707022, "percentage": 66.99, "elapsed_time": "3:17:42", "remaining_time": "1:37:25", "throughput": 12198.43, "total_tokens": 144703488}
+{"current_steps": 70, "total_steps": 103, "loss": 0.8916, "lr": 1.1630092850023147e-05, "epoch": 0.6779661016949152, "percentage": 67.96, "elapsed_time": "3:20:33", "remaining_time": "1:34:33", "throughput": 12199.0, "total_tokens": 146800640}
+{"current_steps": 71, "total_steps": 103, "loss": 0.8913, "lr": 1.0992094275966256e-05, "epoch": 0.6876513317191283, "percentage": 68.93, "elapsed_time": "3:23:24", "remaining_time": "1:31:40", "throughput": 12199.79, "total_tokens": 148897792}
+{"current_steps": 72, "total_steps": 103, "loss": 0.8973, "lr": 1.0367126314618947e-05, "epoch": 0.6973365617433414, "percentage": 69.9, "elapsed_time": "3:26:16", "remaining_time": "1:28:48", "throughput": 12200.41, "total_tokens": 150994944}
+{"current_steps": 73, "total_steps": 103, "loss": 0.9136, "lr": 9.755770331648642e-06, "epoch": 0.7070217917675545, "percentage": 70.87, "elapsed_time": "3:29:07", "remaining_time": "1:25:56", "throughput": 12201.41, "total_tokens": 153092096}
+{"current_steps": 74, "total_steps": 103, "loss": 0.9217, "lr": 9.15859503041462e-06, "epoch": 0.7167070217917676, "percentage": 71.84, "elapsed_time": "3:31:58", "remaining_time": "1:23:04", "throughput": 12201.98, "total_tokens": 155189248}
+{"current_steps": 75, "total_steps": 103, "loss": 0.8926, "lr": 8.576155922941548e-06, "epoch": 0.7263922518159807, "percentage": 72.82, "elapsed_time": "3:34:50", "remaining_time": "1:20:12", "throughput": 12202.13, "total_tokens": 157286400}
+{"current_steps": 76, "total_steps": 103, "loss": 0.8828, "lr": 8.008994813163995e-06, "epoch": 0.7360774818401937, "percentage": 73.79, "elapsed_time": "3:37:41", "remaining_time": "1:17:20", "throughput": 12202.67, "total_tokens": 159383552}
+{"current_steps": 77, "total_steps": 103, "loss": 0.8944, "lr": 7.457639292922675e-06, "epoch": 0.7457627118644068, "percentage": 74.76, "elapsed_time": "3:40:33", "remaining_time": "1:14:28", "throughput": 12202.71, "total_tokens": 161480704}
+{"current_steps": 78, "total_steps": 103, "loss": 0.9085, "lr": 6.92260225118122e-06, "epoch": 0.7554479418886199, "percentage": 75.73, "elapsed_time": "3:43:24", "remaining_time": "1:11:36", "throughput": 12203.07, "total_tokens": 163577856}
+{"current_steps": 79, "total_steps": 103, "loss": 0.8926, "lr": 6.4043813969201004e-06, "epoch": 0.7651331719128329, "percentage": 76.7, "elapsed_time": "3:46:16", "remaining_time": "1:08:44", "throughput": 12202.71, "total_tokens": 165675008}
+{"current_steps": 80, "total_steps": 103, "loss": 0.9022, "lr": 5.903458796151381e-06, "epoch": 0.774818401937046, "percentage": 77.67, "elapsed_time": "3:49:07", "remaining_time": "1:05:52", "throughput": 12203.4, "total_tokens": 167772160}
+{"current_steps": 81, "total_steps": 103, "loss": 0.9081, "lr": 5.420300423485167e-06, "epoch": 0.784503631961259, "percentage": 78.64, "elapsed_time": "3:51:59", "remaining_time": "1:03:00", "throughput": 12203.86, "total_tokens": 169869312}
+{"current_steps": 82, "total_steps": 103, "loss": 0.8964, "lr": 4.95535572866474e-06, "epoch": 0.7941888619854721, "percentage": 79.61, "elapsed_time": "3:54:51", "remaining_time": "1:00:08", "throughput": 12203.74, "total_tokens": 171966464}
+{"current_steps": 83, "total_steps": 103, "loss": 0.8872, "lr": 4.5090572184736864e-06, "epoch": 0.8038740920096852, "percentage": 80.58, "elapsed_time": "3:57:42", "remaining_time": "0:57:16", "throughput": 12204.1, "total_tokens": 174063616}
+{"current_steps": 84, "total_steps": 103, "loss": 0.9052, "lr": 4.081820054403948e-06, "epoch": 0.8135593220338984, "percentage": 81.55, "elapsed_time": "4:00:34", "remaining_time": "0:54:24", "throughput": 12204.57, "total_tokens": 176160768}
+{"current_steps": 85, "total_steps": 103, "loss": 0.8887, "lr": 3.674041666458963e-06, "epoch": 0.8232445520581114, "percentage": 82.52, "elapsed_time": "4:03:25", "remaining_time": "0:51:32", "throughput": 12204.65, "total_tokens": 178257920}
+{"current_steps": 86, "total_steps": 103, "loss": 0.9228, "lr": 3.2861013834512846e-06, "epoch": 0.8329297820823245, "percentage": 83.5, "elapsed_time": "4:06:17", "remaining_time": "0:48:41", "throughput": 12205.11, "total_tokens": 180355072}
+{"current_steps": 87, "total_steps": 103, "loss": 0.907, "lr": 2.918360080138485e-06, "epoch": 0.8426150121065376, "percentage": 84.47, "elapsed_time": "4:09:08", "remaining_time": "0:45:49", "throughput": 12205.63, "total_tokens": 182452224}
+{"current_steps": 88, "total_steps": 103, "loss": 0.8912, "lr": 2.57115984152565e-06, "epoch": 0.8523002421307506, "percentage": 85.44, "elapsed_time": "4:11:59", "remaining_time": "0:42:57", "throughput": 12206.01, "total_tokens": 184549376}
+{"current_steps": 89, "total_steps": 103, "loss": 0.91, "lr": 2.2448236446466846e-06, "epoch": 0.8619854721549637, "percentage": 86.41, "elapsed_time": "4:14:51", "remaining_time": "0:40:05", "throughput": 12206.13, "total_tokens": 186646528}
+{"current_steps": 90, "total_steps": 103, "loss": 0.8817, "lr": 1.939655058120521e-06, "epoch": 0.8716707021791767, "percentage": 87.38, "elapsed_time": "4:17:42", "remaining_time": "0:37:13", "throughput": 12206.42, "total_tokens": 188743680}
+{"current_steps": 91, "total_steps": 103, "loss": 0.8795, "lr": 1.6559379597616137e-06, "epoch": 0.8813559322033898, "percentage": 88.35, "elapsed_time": "4:20:34", "remaining_time": "0:34:21", "throughput": 12206.66, "total_tokens": 190840832}
+{"current_steps": 92, "total_steps": 103, "loss": 0.8945, "lr": 1.3939362725075345e-06, "epoch": 0.8910411622276029, "percentage": 89.32, "elapsed_time": "4:23:26", "remaining_time": "0:31:29", "throughput": 12206.32, "total_tokens": 192937984}
+{"current_steps": 93, "total_steps": 103, "loss": 0.8941, "lr": 1.1538937189091825e-06, "epoch": 0.9007263922518159, "percentage": 90.29, "elapsed_time": "4:26:18", "remaining_time": "0:28:38", "throughput": 12206.23, "total_tokens": 195035136}
+{"current_steps": 94, "total_steps": 103, "loss": 0.8771, "lr": 9.360335944121029e-07, "epoch": 0.910411622276029, "percentage": 91.26, "elapsed_time": "4:29:10", "remaining_time": "0:25:46", "throughput": 12206.25, "total_tokens": 197132288}
+{"current_steps": 95, "total_steps": 103, "loss": 0.8779, "lr": 7.405585596397313e-07, "epoch": 0.9200968523002422, "percentage": 92.23, "elapsed_time": "4:32:01", "remaining_time": "0:22:54", "throughput": 12206.55, "total_tokens": 199229440}
+{"current_steps": 96, "total_steps": 103, "loss": 0.8978, "lr": 5.676504518718761e-07, "epoch": 0.9297820823244553, "percentage": 93.2, "elapsed_time": "4:34:52", "remaining_time": "0:20:02", "throughput": 12207.07, "total_tokens": 201326592}
+{"current_steps": 97, "total_steps": 103, "loss": 0.8858, "lr": 4.1747011589368947e-07, "epoch": 0.9394673123486683, "percentage": 94.17, "elapsed_time": "4:37:43", "remaining_time": "0:17:10", "throughput": 12207.47, "total_tokens": 203423744}
+{"current_steps": 98, "total_steps": 103, "loss": 0.8983, "lr": 2.9015725437259724e-07, "epoch": 0.9491525423728814, "percentage": 95.15, "elapsed_time": "4:40:35", "remaining_time": "0:14:18", "throughput": 12207.74, "total_tokens": 205520896}
+{"current_steps": 99, "total_steps": 103, "loss": 0.903, "lr": 1.8583029790230355e-07, "epoch": 0.9588377723970944, "percentage": 96.12, "elapsed_time": "4:43:26", "remaining_time": "0:11:27", "throughput": 12208.21, "total_tokens": 207618048}
+{"current_steps": 100, "total_steps": 103, "loss": 0.866, "lr": 1.0458629483476867e-07, "epoch": 0.9685230024213075, "percentage": 97.09, "elapsed_time": "4:46:18", "remaining_time": "0:08:35", "throughput": 12208.23, "total_tokens": 209715200}
+{"current_steps": 101, "total_steps": 103, "loss": 0.9024, "lr": 4.650082100265407e-08, "epoch": 0.9782082324455206, "percentage": 98.06, "elapsed_time": "4:49:09", "remaining_time": "0:05:43", "throughput": 12208.43, "total_tokens": 211812352}
+{"current_steps": 102, "total_steps": 103, "loss": 0.8841, "lr": 1.1627909416211947e-08, "epoch": 0.9878934624697336, "percentage": 99.03, "elapsed_time": "4:52:01", "remaining_time": "0:02:51", "throughput": 12208.72, "total_tokens": 213909504}
+{"current_steps": 103, "total_steps": 103, "loss": 0.8893, "lr": 0.0, "epoch": 0.9975786924939467, "percentage": 100.0, "elapsed_time": "4:54:52", "remaining_time": "0:00:00", "throughput": 12208.75, "total_tokens": 216006656}
+{"current_steps": 103, "total_steps": 103, "epoch": 0.9975786924939467, "percentage": 100.0, "elapsed_time": "4:55:19", "remaining_time": "0:00:00", "throughput": 12190.49, "total_tokens": 216006656}

trainer_state.json

@@ -0,0 +1,867 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9975786924939467,
+  "eval_steps": 500,
+  "global_step": 103,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009685230024213076,
+      "grad_norm": 1.9685195684432983,
+      "learning_rate": 4.998837209058379e-05,
+      "loss": 1.2027,
+      "num_input_tokens_seen": 2097152,
+      "step": 1
+    },
+    {
+      "epoch": 0.01937046004842615,
+      "grad_norm": 1.0660535097122192,
+      "learning_rate": 4.9953499178997346e-05,
+      "loss": 1.0647,
+      "num_input_tokens_seen": 4194304,
+      "step": 2
+    },
+    {
+      "epoch": 0.029055690072639227,
+      "grad_norm": 0.5073350667953491,
+      "learning_rate": 4.9895413705165234e-05,
+      "loss": 1.0243,
+      "num_input_tokens_seen": 6291456,
+      "step": 3
+    },
+    {
+      "epoch": 0.0387409200968523,
+      "grad_norm": 1.3782298564910889,
+      "learning_rate": 4.98141697020977e-05,
+      "loss": 0.9974,
+      "num_input_tokens_seen": 8388608,
+      "step": 4
+    },
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 1.2407922744750977,
+      "learning_rate": 4.970984274562741e-05,
+      "loss": 0.9874,
+      "num_input_tokens_seen": 10485760,
+      "step": 5
+    },
+    {
+      "epoch": 0.05811138014527845,
+      "grad_norm": 0.5964860320091248,
+      "learning_rate": 4.958252988410631e-05,
+      "loss": 0.9478,
+      "num_input_tokens_seen": 12582912,
+      "step": 6
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 0.9311421513557434,
+      "learning_rate": 4.9432349548128124e-05,
+      "loss": 0.9761,
+      "num_input_tokens_seen": 14680064,
+      "step": 7
+    },
+    {
+      "epoch": 0.0774818401937046,
+      "grad_norm": 0.6549746990203857,
+      "learning_rate": 4.925944144036026e-05,
+      "loss": 0.9698,
+      "num_input_tokens_seen": 16777216,
+      "step": 8
+    },
+    {
+      "epoch": 0.08716707021791767,
+      "grad_norm": 0.6450162529945374,
+      "learning_rate": 4.90639664055879e-05,
+      "loss": 0.9804,
+      "num_input_tokens_seen": 18874368,
+      "step": 9
+    },
+    {
+      "epoch": 0.09685230024213075,
+      "grad_norm": 0.6533230543136597,
+      "learning_rate": 4.884610628109082e-05,
+      "loss": 0.9562,
+      "num_input_tokens_seen": 20971520,
+      "step": 10
+    },
+    {
+      "epoch": 0.10653753026634383,
+      "grad_norm": 0.549923300743103,
+      "learning_rate": 4.860606372749247e-05,
+      "loss": 0.9649,
+      "num_input_tokens_seen": 23068672,
+      "step": 11
+    },
+    {
+      "epoch": 0.1162227602905569,
+      "grad_norm": 0.6160269975662231,
+      "learning_rate": 4.8344062040238395e-05,
+      "loss": 0.93,
+      "num_input_tokens_seen": 25165824,
+      "step": 12
+    },
+    {
+      "epoch": 0.12590799031476999,
+      "grad_norm": 0.502126932144165,
+      "learning_rate": 4.806034494187949e-05,
+      "loss": 0.9356,
+      "num_input_tokens_seen": 27262976,
+      "step": 13
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 0.5611276626586914,
+      "learning_rate": 4.775517635535332e-05,
+      "loss": 0.9279,
+      "num_input_tokens_seen": 29360128,
+      "step": 14
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 0.5306870341300964,
+      "learning_rate": 4.742884015847436e-05,
+      "loss": 0.9311,
+      "num_input_tokens_seen": 31457280,
+      "step": 15
+    },
+    {
+      "epoch": 0.1549636803874092,
+      "grad_norm": 0.518638014793396,
+      "learning_rate": 4.708163991986152e-05,
+      "loss": 0.9311,
+      "num_input_tokens_seen": 33554432,
+      "step": 16
+    },
+    {
+      "epoch": 0.16464891041162227,
+      "grad_norm": 0.4844534993171692,
+      "learning_rate": 4.6713898616548724e-05,
+      "loss": 0.9381,
+      "num_input_tokens_seen": 35651584,
+      "step": 17
+    },
+    {
+      "epoch": 0.17433414043583534,
+      "grad_norm": 0.503509521484375,
+      "learning_rate": 4.6325958333541044e-05,
+      "loss": 0.9354,
+      "num_input_tokens_seen": 37748736,
+      "step": 18
+    },
+    {
+      "epoch": 0.18401937046004843,
+      "grad_norm": 0.4676899015903473,
+      "learning_rate": 4.591817994559605e-05,
+      "loss": 0.9574,
+      "num_input_tokens_seen": 39845888,
+      "step": 19
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 0.42765048146247864,
+      "learning_rate": 4.5490942781526316e-05,
+      "loss": 0.9124,
+      "num_input_tokens_seen": 41943040,
+      "step": 20
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 0.44725504517555237,
+      "learning_rate": 4.504464427133527e-05,
+      "loss": 0.95,
+      "num_input_tokens_seen": 44040192,
+      "step": 21
+    },
+    {
+      "epoch": 0.21307506053268765,
+      "grad_norm": 0.4458858072757721,
+      "learning_rate": 4.457969957651484e-05,
+      "loss": 0.9179,
+      "num_input_tokens_seen": 46137344,
+      "step": 22
+    },
+    {
+      "epoch": 0.22276029055690072,
+      "grad_norm": 0.48520275950431824,
+      "learning_rate": 4.409654120384862e-05,
+      "loss": 0.9414,
+      "num_input_tokens_seen": 48234496,
+      "step": 23
+    },
+    {
+      "epoch": 0.2324455205811138,
+      "grad_norm": 0.3971172571182251,
+      "learning_rate": 4.35956186030799e-05,
+      "loss": 0.9348,
+      "num_input_tokens_seen": 50331648,
+      "step": 24
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 0.4044610559940338,
+      "learning_rate": 4.307739774881878e-05,
+      "loss": 0.926,
+      "num_input_tokens_seen": 52428800,
+      "step": 25
+    },
+    {
+      "epoch": 0.25181598062953997,
+      "grad_norm": 0.43942683935165405,
+      "learning_rate": 4.254236070707733e-05,
+      "loss": 0.9323,
+      "num_input_tokens_seen": 54525952,
+      "step": 26
+    },
+    {
+      "epoch": 0.26150121065375304,
+      "grad_norm": 0.39789262413978577,
+      "learning_rate": 4.1991005186836005e-05,
+      "loss": 0.9218,
+      "num_input_tokens_seen": 56623104,
+      "step": 27
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.4076980650424957,
+      "learning_rate": 4.142384407705846e-05,
+      "loss": 0.9319,
+      "num_input_tokens_seen": 58720256,
+      "step": 28
+    },
+    {
+      "epoch": 0.28087167070217917,
+      "grad_norm": 0.3844672441482544,
+      "learning_rate": 4.084140496958538e-05,
+      "loss": 0.9202,
+      "num_input_tokens_seen": 60817408,
+      "step": 29
+    },
+    {
+      "epoch": 0.29055690072639223,
+      "grad_norm": 0.3762418031692505,
+      "learning_rate": 4.024422966835136e-05,
+      "loss": 0.9141,
+      "num_input_tokens_seen": 62914560,
+      "step": 30
+    },
+    {
+      "epoch": 0.30024213075060535,
+      "grad_norm": 0.3833739459514618,
+      "learning_rate": 3.963287368538106e-05,
+      "loss": 0.9145,
+      "num_input_tokens_seen": 65011712,
+      "step": 31
+    },
+    {
+      "epoch": 0.3099273607748184,
+      "grad_norm": 0.33625665307044983,
+      "learning_rate": 3.900790572403376e-05,
+      "loss": 0.8975,
+      "num_input_tokens_seen": 67108864,
+      "step": 32
+    },
+    {
+      "epoch": 0.3196125907990315,
+      "grad_norm": 0.3306196928024292,
+      "learning_rate": 3.836990714997686e-05,
+      "loss": 0.9614,
+      "num_input_tokens_seen": 69206016,
+      "step": 33
+    },
+    {
+      "epoch": 0.32929782082324455,
+      "grad_norm": 0.34520208835601807,
+      "learning_rate": 3.7719471450380514e-05,
+      "loss": 0.9327,
+      "num_input_tokens_seen": 71303168,
+      "step": 34
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.31201523542404175,
+      "learning_rate": 3.7057203681836406e-05,
+      "loss": 0.9153,
+      "num_input_tokens_seen": 73400320,
+      "step": 35
+    },
+    {
+      "epoch": 0.3486682808716707,
+      "grad_norm": 0.30785471200942993,
+      "learning_rate": 3.638371990751428e-05,
+      "loss": 0.8977,
+      "num_input_tokens_seen": 75497472,
+      "step": 36
+    },
+    {
+      "epoch": 0.3583535108958838,
+      "grad_norm": 0.32537877559661865,
+      "learning_rate": 3.569964662407983e-05,
+      "loss": 0.9147,
+      "num_input_tokens_seen": 77594624,
+      "step": 37
+    },
+    {
+      "epoch": 0.36803874092009686,
+      "grad_norm": 0.2987798750400543,
+      "learning_rate": 3.500562017890695e-05,
+      "loss": 0.9264,
+      "num_input_tokens_seen": 79691776,
+      "step": 38
+    },
+    {
+      "epoch": 0.37772397094430993,
+      "grad_norm": 0.2951103150844574,
+      "learning_rate": 3.430228617812661e-05,
+      "loss": 0.9041,
+      "num_input_tokens_seen": 81788928,
+      "step": 39
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 0.30589672923088074,
+      "learning_rate": 3.3590298886062833e-05,
+      "loss": 0.9322,
+      "num_input_tokens_seen": 83886080,
+      "step": 40
+    },
+    {
+      "epoch": 0.39709443099273606,
+      "grad_norm": 0.30754590034484863,
+      "learning_rate": 3.2870320616614626e-05,
+      "loss": 0.9257,
+      "num_input_tokens_seen": 85983232,
+      "step": 41
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 0.2994811534881592,
+      "learning_rate": 3.21430211171499e-05,
+      "loss": 0.8952,
+      "num_input_tokens_seen": 88080384,
+      "step": 42
+    },
+    {
+      "epoch": 0.41646489104116224,
+      "grad_norm": 0.2752488851547241,
+      "learning_rate": 3.140907694548451e-05,
+      "loss": 0.9072,
+      "num_input_tokens_seen": 90177536,
+      "step": 43
+    },
+    {
+      "epoch": 0.4261501210653753,
+      "grad_norm": 0.2599559426307678,
+      "learning_rate": 3.066917084052603e-05,
+      "loss": 0.9166,
+      "num_input_tokens_seen": 92274688,
+      "step": 44
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 0.2565292418003082,
+      "learning_rate": 2.9923991087167658e-05,
+      "loss": 0.8924,
+      "num_input_tokens_seen": 94371840,
+      "step": 45
+    },
+    {
+      "epoch": 0.44552058111380144,
+      "grad_norm": 0.3102430999279022,
+      "learning_rate": 2.9174230876023058e-05,
+      "loss": 0.8871,
+      "num_input_tokens_seen": 96468992,
+      "step": 46
+    },
+    {
+      "epoch": 0.4552058111380145,
+      "grad_norm": 0.2583513557910919,
+      "learning_rate": 2.8420587658597757e-05,
+      "loss": 0.9263,
+      "num_input_tokens_seen": 98566144,
+      "step": 47
+    },
+    {
+      "epoch": 0.4648910411622276,
+      "grad_norm": 0.23033802211284637,
+      "learning_rate": 2.7663762498496905e-05,
+      "loss": 0.9158,
+      "num_input_tokens_seen": 100663296,
+      "step": 48
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 0.23797494173049927,
+      "learning_rate": 2.6904459419272955e-05,
+      "loss": 0.9034,
+      "num_input_tokens_seen": 102760448,
+      "step": 49
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 0.22934052348136902,
+      "learning_rate": 2.6143384749519866e-05,
+      "loss": 0.9044,
+      "num_input_tokens_seen": 104857600,
+      "step": 50
+    },
+    {
+      "epoch": 0.4939467312348668,
+      "grad_norm": 0.23668517172336578,
+      "learning_rate": 2.538124646582315e-05,
+      "loss": 0.9173,
+      "num_input_tokens_seen": 106954752,
+      "step": 51
+    },
+    {
+      "epoch": 0.5036319612590799,
+      "grad_norm": 0.22859163582324982,
+      "learning_rate": 2.4618753534176856e-05,
+      "loss": 0.9349,
+      "num_input_tokens_seen": 109051904,
+      "step": 52
+    },
+    {
+      "epoch": 0.513317191283293,
+      "grad_norm": 0.2197035849094391,
+      "learning_rate": 2.385661525048014e-05,
+      "loss": 0.8996,
+      "num_input_tokens_seen": 111149056,
+      "step": 53
+    },
+    {
+      "epoch": 0.5230024213075061,
+      "grad_norm": 0.18276314437389374,
+      "learning_rate": 2.3095540580727055e-05,
+      "loss": 0.9018,
+      "num_input_tokens_seen": 113246208,
+      "step": 54
+    },
+    {
+      "epoch": 0.5326876513317191,
+      "grad_norm": 0.1825525313615799,
+      "learning_rate": 2.23362375015031e-05,
+      "loss": 0.8797,
+      "num_input_tokens_seen": 115343360,
+      "step": 55
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.19028963148593903,
+      "learning_rate": 2.157941234140225e-05,
+      "loss": 0.9075,
+      "num_input_tokens_seen": 117440512,
+      "step": 56
+    },
+    {
+      "epoch": 0.5520581113801453,
+      "grad_norm": 0.19303017854690552,
+      "learning_rate": 2.082576912397695e-05,
+      "loss": 0.9068,
+      "num_input_tokens_seen": 119537664,
+      "step": 57
+    },
+    {
+      "epoch": 0.5617433414043583,
+      "grad_norm": 0.1868184506893158,
+      "learning_rate": 2.0076008912832355e-05,
+      "loss": 0.9154,
+      "num_input_tokens_seen": 121634816,
+      "step": 58
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.15938569605350494,
+      "learning_rate": 1.933082915947398e-05,
+      "loss": 0.8895,
+      "num_input_tokens_seen": 123731968,
+      "step": 59
+    },
+    {
+      "epoch": 0.5811138014527845,
+      "grad_norm": 0.17814385890960693,
+      "learning_rate": 1.8590923054515503e-05,
+      "loss": 0.891,
+      "num_input_tokens_seen": 125829120,
+      "step": 60
+    },
+    {
+      "epoch": 0.5907990314769975,
+      "grad_norm": 0.17275391519069672,
+      "learning_rate": 1.7856978882850113e-05,
+      "loss": 0.8928,
+      "num_input_tokens_seen": 127926272,
+      "step": 61
+    },
+    {
+      "epoch": 0.6004842615012107,
+      "grad_norm": 0.14000782370567322,
+      "learning_rate": 1.7129679383385383e-05,
+      "loss": 0.8918,
+      "num_input_tokens_seen": 130023424,
+      "step": 62
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 0.15500731766223907,
+      "learning_rate": 1.6409701113937183e-05,
+      "loss": 0.8807,
+      "num_input_tokens_seen": 132120576,
+      "step": 63
+    },
+    {
+      "epoch": 0.6198547215496368,
+      "grad_norm": 0.1355552226305008,
+      "learning_rate": 1.5697713821873398e-05,
+      "loss": 0.8934,
+      "num_input_tokens_seen": 134217728,
+      "step": 64
+    },
+    {
+      "epoch": 0.6295399515738499,
+      "grad_norm": 0.14123253524303436,
+      "learning_rate": 1.4994379821093049e-05,
+      "loss": 0.8809,
+      "num_input_tokens_seen": 136314880,
+      "step": 65
+    },
+    {
+      "epoch": 0.639225181598063,
+      "grad_norm": 0.12774570286273956,
+      "learning_rate": 1.430035337592018e-05,
+      "loss": 0.8856,
+      "num_input_tokens_seen": 138412032,
+      "step": 66
+    },
+    {
+      "epoch": 0.648910411622276,
+      "grad_norm": 0.12434564530849457,
+      "learning_rate": 1.3616280092485717e-05,
+      "loss": 0.9117,
+      "num_input_tokens_seen": 140509184,
+      "step": 67
+    },
+    {
+      "epoch": 0.6585956416464891,
+      "grad_norm": 0.12732358276844025,
+      "learning_rate": 1.2942796318163595e-05,
+      "loss": 0.8993,
+      "num_input_tokens_seen": 142606336,
+      "step": 68
+    },
+    {
+      "epoch": 0.6682808716707022,
+      "grad_norm": 0.12411068379878998,
+      "learning_rate": 1.2280528549619485e-05,
+      "loss": 0.9215,
+      "num_input_tokens_seen": 144703488,
+      "step": 69
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 0.1309666633605957,
+      "learning_rate": 1.1630092850023147e-05,
+      "loss": 0.8916,
+      "num_input_tokens_seen": 146800640,
+      "step": 70
+    },
+    {
+      "epoch": 0.6876513317191283,
+      "grad_norm": 0.14672118425369263,
+      "learning_rate": 1.0992094275966256e-05,
+      "loss": 0.8913,
+      "num_input_tokens_seen": 148897792,
+      "step": 71
+    },
+    {
+      "epoch": 0.6973365617433414,
+      "grad_norm": 0.1352979987859726,
+      "learning_rate": 1.0367126314618947e-05,
+      "loss": 0.8973,
+      "num_input_tokens_seen": 150994944,
+      "step": 72
+    },
+    {
+      "epoch": 0.7070217917675545,
+      "grad_norm": 0.12073559314012527,
+      "learning_rate": 9.755770331648642e-06,
+      "loss": 0.9136,
+      "num_input_tokens_seen": 153092096,
+      "step": 73
+    },
+    {
+      "epoch": 0.7167070217917676,
+      "grad_norm": 0.12179349362850189,
+      "learning_rate": 9.15859503041462e-06,
+      "loss": 0.9217,
+      "num_input_tokens_seen": 155189248,
+      "step": 74
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 0.12360276281833649,
+      "learning_rate": 8.576155922941548e-06,
+      "loss": 0.8926,
+      "num_input_tokens_seen": 157286400,
+      "step": 75
+    },
+    {
+      "epoch": 0.7360774818401937,
+      "grad_norm": 0.1345692127943039,
+      "learning_rate": 8.008994813163995e-06,
+      "loss": 0.8828,
+      "num_input_tokens_seen": 159383552,
+      "step": 76
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 0.12099383026361465,
+      "learning_rate": 7.457639292922675e-06,
+      "loss": 0.8944,
+      "num_input_tokens_seen": 161480704,
+      "step": 77
+    },
+    {
+      "epoch": 0.7554479418886199,
+      "grad_norm": 0.11634839326143265,
+      "learning_rate": 6.92260225118122e-06,
+      "loss": 0.9085,
+      "num_input_tokens_seen": 163577856,
+      "step": 78
+    },
+    {
+      "epoch": 0.7651331719128329,
+      "grad_norm": 0.11679349094629288,
+      "learning_rate": 6.4043813969201004e-06,
+      "loss": 0.8926,
+      "num_input_tokens_seen": 165675008,
+      "step": 79
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 0.11818551272153854,
+      "learning_rate": 5.903458796151381e-06,
+      "loss": 0.9022,
+      "num_input_tokens_seen": 167772160,
+      "step": 80
+    },
+    {
+      "epoch": 0.784503631961259,
+      "grad_norm": 0.11871389299631119,
+      "learning_rate": 5.420300423485167e-06,
+      "loss": 0.9081,
+      "num_input_tokens_seen": 169869312,
+      "step": 81
+    },
+    {
+      "epoch": 0.7941888619854721,
+      "grad_norm": 0.11701155453920364,
+      "learning_rate": 4.95535572866474e-06,
+      "loss": 0.8964,
+      "num_input_tokens_seen": 171966464,
+      "step": 82
+    },
+    {
+      "epoch": 0.8038740920096852,
+      "grad_norm": 0.11006560176610947,
+      "learning_rate": 4.5090572184736864e-06,
+      "loss": 0.8872,
+      "num_input_tokens_seen": 174063616,
+      "step": 83
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 0.12146145850419998,
+      "learning_rate": 4.081820054403948e-06,
+      "loss": 0.9052,
+      "num_input_tokens_seen": 176160768,
+      "step": 84
+    },
+    {
+      "epoch": 0.8232445520581114,
+      "grad_norm": 0.12446972727775574,
+      "learning_rate": 3.674041666458963e-06,
+      "loss": 0.8887,
+      "num_input_tokens_seen": 178257920,
+      "step": 85
+    },
+    {
+      "epoch": 0.8329297820823245,
+      "grad_norm": 0.1250552088022232,
+      "learning_rate": 3.2861013834512846e-06,
+      "loss": 0.9228,
+      "num_input_tokens_seen": 180355072,
+      "step": 86
+    },
+    {
+      "epoch": 0.8426150121065376,
+      "grad_norm": 0.11696241050958633,
+      "learning_rate": 2.918360080138485e-06,
+      "loss": 0.907,
+      "num_input_tokens_seen": 182452224,
+      "step": 87
+    },
+    {
+      "epoch": 0.8523002421307506,
+      "grad_norm": 0.12368214130401611,
+      "learning_rate": 2.57115984152565e-06,
+      "loss": 0.8912,
+      "num_input_tokens_seen": 184549376,
+      "step": 88
+    },
+    {
+      "epoch": 0.8619854721549637,
+      "grad_norm": 0.12887972593307495,
+      "learning_rate": 2.2448236446466846e-06,
+      "loss": 0.91,
+      "num_input_tokens_seen": 186646528,
+      "step": 89
+    },
+    {
+      "epoch": 0.8716707021791767,
+      "grad_norm": 0.12058700621128082,
+      "learning_rate": 1.939655058120521e-06,
+      "loss": 0.8817,
+      "num_input_tokens_seen": 188743680,
+      "step": 90
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 0.12237603217363358,
+      "learning_rate": 1.6559379597616137e-06,
+      "loss": 0.8795,
+      "num_input_tokens_seen": 190840832,
+      "step": 91
+    },
+    {
+      "epoch": 0.8910411622276029,
+      "grad_norm": 0.11371732503175735,
+      "learning_rate": 1.3939362725075345e-06,
+      "loss": 0.8945,
+      "num_input_tokens_seen": 192937984,
+      "step": 92
+    },
+    {
+      "epoch": 0.9007263922518159,
+      "grad_norm": 0.11676651239395142,
+      "learning_rate": 1.1538937189091825e-06,
+      "loss": 0.8941,
+      "num_input_tokens_seen": 195035136,
+      "step": 93
+    },
+    {
+      "epoch": 0.910411622276029,
+      "grad_norm": 0.12232819199562073,
+      "learning_rate": 9.360335944121029e-07,
+      "loss": 0.8771,
+      "num_input_tokens_seen": 197132288,
+      "step": 94
+    },
+    {
+      "epoch": 0.9200968523002422,
+      "grad_norm": 0.12525516748428345,
+      "learning_rate": 7.405585596397313e-07,
+      "loss": 0.8779,
+      "num_input_tokens_seen": 199229440,
+      "step": 95
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 0.11555425822734833,
+      "learning_rate": 5.676504518718761e-07,
+      "loss": 0.8978,
+      "num_input_tokens_seen": 201326592,
+      "step": 96
+    },
+    {
+      "epoch": 0.9394673123486683,
+      "grad_norm": 0.11837372183799744,
+      "learning_rate": 4.1747011589368947e-07,
+      "loss": 0.8858,
+      "num_input_tokens_seen": 203423744,
+      "step": 97
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 0.12683407962322235,
+      "learning_rate": 2.9015725437259724e-07,
+      "loss": 0.8983,
+      "num_input_tokens_seen": 205520896,
+      "step": 98
+    },
+    {
+      "epoch": 0.9588377723970944,
+      "grad_norm": 0.1122291162610054,
+      "learning_rate": 1.8583029790230355e-07,
+      "loss": 0.903,
+      "num_input_tokens_seen": 207618048,
+      "step": 99
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 0.11563855409622192,
+      "learning_rate": 1.0458629483476867e-07,
+      "loss": 0.866,
+      "num_input_tokens_seen": 209715200,
+      "step": 100
+    },
+    {
+      "epoch": 0.9782082324455206,
+      "grad_norm": 0.11408016085624695,
+      "learning_rate": 4.650082100265407e-08,
+      "loss": 0.9024,
+      "num_input_tokens_seen": 211812352,
+      "step": 101
+    },
+    {
+      "epoch": 0.9878934624697336,
+      "grad_norm": 0.11875565350055695,
+      "learning_rate": 1.1627909416211947e-08,
+      "loss": 0.8841,
+      "num_input_tokens_seen": 213909504,
+      "step": 102
+    },
+    {
+      "epoch": 0.9975786924939467,
+      "grad_norm": 0.12518461048603058,
+      "learning_rate": 0.0,
+      "loss": 0.8893,
+      "num_input_tokens_seen": 216006656,
+      "step": 103
+    },
+    {
+      "epoch": 0.9975786924939467,
+      "num_input_tokens_seen": 216006656,
+      "step": 103,
+      "total_flos": 9.7266820915837e+18,
+      "train_loss": 0.9181526060243255,
+      "train_runtime": 17720.4517,
+      "train_samples_per_second": 2.983,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 103,
+  "num_input_tokens_seen": 216006656,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.7266820915837e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803d7018ab917037cbaa9960f06664527f898f080e8ac7306d92cc97e2e1aa32
+size 5624

training_args.yaml

@@ -0,0 +1,39 @@
+apollo_rank: 256
+apollo_scale: 1
+apollo_target: all
+apollo_update_interval: 200
+bf16: true
+cutoff_len: 4096
+dataset: codes_330k_nsx
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+enable_liger_kernel: true
+finetuning_type: freeze
+flash_attn: auto
+freeze_trainable_layers: 2
+freeze_trainable_modules: all
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 1
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 50000000
+model_name_or_path: meta-llama/Llama-3.1-8B-Instruct
+neat_packing: true
+num_train_epochs: 1.0
+output_dir: saves/Llama-3.1-8B-Instruct/freeze/llama_nsx
+packing: true
+per_device_train_batch_size: 16
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+rope_scaling: llama3
+save_steps: 500
+stage: sft
+template: llama3
+trust_remote_code: true
+use_apollo: true
+use_llama_pro: true
+warmup_steps: 0