Upload 10 files

.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

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0864c4f2603e2bb42e122c8ea11cd41f8debb7e402f28d09828d7116a388a2
+size 39256456

llamaboard_config.yaml

@@ -0,0 +1,63 @@
+top.booster: none
+top.checkpoint_path: null
+top.finetuning_type: lora
+top.model_name: Gemma-2B-Chat
+top.quantization_bit: '4'
+top.rope_scaling: none
+top.template: gemma
+top.visual_inputs: false
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: fp16
+train.create_new_adapter: false
+train.cutoff_len: 4096
+train.dataset:
+- claimver_kgllm
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+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.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neftune_alpha: 0
+train.num_train_epochs: '2'
+train.optim: adamw_torch
+train.packing: false
+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: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.training_stage: Supervised Fine-Tuning
+train.upcast_layernorm: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,1759 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<bos>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,715 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9952941176470587,
+  "eval_steps": 500,
+  "global_step": 424,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023529411764705882,
+      "grad_norm": 2.0912532806396484,
+      "learning_rate": 4.998284588246634e-05,
+      "loss": 1.5824,
+      "num_input_tokens_seen": 47376,
+      "step": 5
+    },
+    {
+      "epoch": 0.047058823529411764,
+      "grad_norm": 1.2301002740859985,
+      "learning_rate": 4.9931407070965254e-05,
+      "loss": 1.1238,
+      "num_input_tokens_seen": 97888,
+      "step": 10
+    },
+    {
+      "epoch": 0.07058823529411765,
+      "grad_norm": 1.0708130598068237,
+      "learning_rate": 4.984575415649019e-05,
+      "loss": 0.9474,
+      "num_input_tokens_seen": 145664,
+      "step": 15
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 0.8778848648071289,
+      "learning_rate": 4.97260046830541e-05,
+      "loss": 0.7893,
+      "num_input_tokens_seen": 192544,
+      "step": 20
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.9257701635360718,
+      "learning_rate": 4.957232298638036e-05,
+      "loss": 0.7478,
+      "num_input_tokens_seen": 241760,
+      "step": 25
+    },
+    {
+      "epoch": 0.1411764705882353,
+      "grad_norm": 0.8825921416282654,
+      "learning_rate": 4.9384919968379945e-05,
+      "loss": 0.6895,
+      "num_input_tokens_seen": 289600,
+      "step": 30
+    },
+    {
+      "epoch": 0.16470588235294117,
+      "grad_norm": 0.8157197833061218,
+      "learning_rate": 4.916405280772462e-05,
+      "loss": 0.6936,
+      "num_input_tokens_seen": 340816,
+      "step": 35
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 0.8392460346221924,
+      "learning_rate": 4.891002460691306e-05,
+      "loss": 0.6835,
+      "num_input_tokens_seen": 389424,
+      "step": 40
+    },
+    {
+      "epoch": 0.21176470588235294,
+      "grad_norm": 0.7645203471183777,
+      "learning_rate": 4.862318397631434e-05,
+      "loss": 0.6284,
+      "num_input_tokens_seen": 438224,
+      "step": 45
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.0171334743499756,
+      "learning_rate": 4.83039245557597e-05,
+      "loss": 0.6165,
+      "num_input_tokens_seen": 486496,
+      "step": 50
+    },
+    {
+      "epoch": 0.25882352941176473,
+      "grad_norm": 0.7693806290626526,
+      "learning_rate": 4.795268447433907e-05,
+      "loss": 0.5757,
+      "num_input_tokens_seen": 537520,
+      "step": 55
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 0.8031296133995056,
+      "learning_rate": 4.756994574914359e-05,
+      "loss": 0.5638,
+      "num_input_tokens_seen": 584288,
+      "step": 60
+    },
+    {
+      "epoch": 0.3058823529411765,
+      "grad_norm": 0.7544689774513245,
+      "learning_rate": 4.715623362377939e-05,
+      "loss": 0.5522,
+      "num_input_tokens_seen": 633984,
+      "step": 65
+    },
+    {
+      "epoch": 0.32941176470588235,
+      "grad_norm": 0.8555608987808228,
+      "learning_rate": 4.6712115847560355e-05,
+      "loss": 0.5217,
+      "num_input_tokens_seen": 685600,
+      "step": 70
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.8717510104179382,
+      "learning_rate": 4.6238201896369055e-05,
+      "loss": 0.5436,
+      "num_input_tokens_seen": 734496,
+      "step": 75
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 0.9173887372016907,
+      "learning_rate": 4.573514213625505e-05,
+      "loss": 0.514,
+      "num_input_tokens_seen": 784720,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8762289881706238,
+      "learning_rate": 4.5203626930918455e-05,
+      "loss": 0.5073,
+      "num_input_tokens_seen": 837808,
+      "step": 85
+    },
+    {
+      "epoch": 0.4235294117647059,
+      "grad_norm": 0.9715367555618286,
+      "learning_rate": 4.464438569430354e-05,
+      "loss": 0.5384,
+      "num_input_tokens_seen": 888032,
+      "step": 90
+    },
+    {
+      "epoch": 0.4470588235294118,
+      "grad_norm": 0.9435672163963318,
+      "learning_rate": 4.40581858896025e-05,
+      "loss": 0.521,
+      "num_input_tokens_seen": 938032,
+      "step": 95
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.8672516345977783,
+      "learning_rate": 4.344583197604318e-05,
+      "loss": 0.4765,
+      "num_input_tokens_seen": 988176,
+      "step": 100
+    },
+    {
+      "epoch": 0.49411764705882355,
+      "grad_norm": 1.0466370582580566,
+      "learning_rate": 4.2808164304906026e-05,
+      "loss": 0.5121,
+      "num_input_tokens_seen": 1040016,
+      "step": 105
+    },
+    {
+      "epoch": 0.5176470588235295,
+      "grad_norm": 0.9898332953453064,
+      "learning_rate": 4.214605796628527e-05,
+      "loss": 0.4972,
+      "num_input_tokens_seen": 1090624,
+      "step": 110
+    },
+    {
+      "epoch": 0.5411764705882353,
+      "grad_norm": 1.0176562070846558,
+      "learning_rate": 4.14604215881771e-05,
+      "loss": 0.488,
+      "num_input_tokens_seen": 1143280,
+      "step": 115
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 0.9806397557258606,
+      "learning_rate": 4.075219608954278e-05,
+      "loss": 0.489,
+      "num_input_tokens_seen": 1191616,
+      "step": 120
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.9629871249198914,
+      "learning_rate": 4.00223533890578e-05,
+      "loss": 0.4853,
+      "num_input_tokens_seen": 1240144,
+      "step": 125
+    },
+    {
+      "epoch": 0.611764705882353,
+      "grad_norm": 0.9678134918212891,
+      "learning_rate": 3.927189507131938e-05,
+      "loss": 0.4718,
+      "num_input_tokens_seen": 1288912,
+      "step": 130
+    },
+    {
+      "epoch": 0.6352941176470588,
+      "grad_norm": 1.0481890439987183,
+      "learning_rate": 3.8501851012342446e-05,
+      "loss": 0.4936,
+      "num_input_tokens_seen": 1335472,
+      "step": 135
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.9465301632881165,
+      "learning_rate": 3.7713277966230514e-05,
+      "loss": 0.4673,
+      "num_input_tokens_seen": 1385568,
+      "step": 140
+    },
+    {
+      "epoch": 0.6823529411764706,
+      "grad_norm": 1.0117136240005493,
+      "learning_rate": 3.690725811496092e-05,
+      "loss": 0.4676,
+      "num_input_tokens_seen": 1434384,
+      "step": 145
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.9891406297683716,
+      "learning_rate": 3.608489758327472e-05,
+      "loss": 0.5079,
+      "num_input_tokens_seen": 1488448,
+      "step": 150
+    },
+    {
+      "epoch": 0.7294117647058823,
+      "grad_norm": 0.9826067090034485,
+      "learning_rate": 3.524732492070915e-05,
+      "loss": 0.4713,
+      "num_input_tokens_seen": 1537472,
+      "step": 155
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 0.9447062611579895,
+      "learning_rate": 3.4395689552855955e-05,
+      "loss": 0.4616,
+      "num_input_tokens_seen": 1587072,
+      "step": 160
+    },
+    {
+      "epoch": 0.7764705882352941,
+      "grad_norm": 1.0301213264465332,
+      "learning_rate": 3.3531160203970805e-05,
+      "loss": 0.4445,
+      "num_input_tokens_seen": 1636624,
+      "step": 165
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1652017831802368,
+      "learning_rate": 3.265492329309867e-05,
+      "loss": 0.4762,
+      "num_input_tokens_seen": 1687904,
+      "step": 170
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 1.1255770921707153,
+      "learning_rate": 3.1768181305916066e-05,
+      "loss": 0.4626,
+      "num_input_tokens_seen": 1734544,
+      "step": 175
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 1.0519174337387085,
+      "learning_rate": 3.0872151144524595e-05,
+      "loss": 0.4554,
+      "num_input_tokens_seen": 1781216,
+      "step": 180
+    },
+    {
+      "epoch": 0.8705882352941177,
+      "grad_norm": 1.1458220481872559,
+      "learning_rate": 2.996806245746044e-05,
+      "loss": 0.4418,
+      "num_input_tokens_seen": 1830144,
+      "step": 185
+    },
+    {
+      "epoch": 0.8941176470588236,
+      "grad_norm": 1.2313694953918457,
+      "learning_rate": 2.9057155952211502e-05,
+      "loss": 0.4676,
+      "num_input_tokens_seen": 1876288,
+      "step": 190
+    },
+    {
+      "epoch": 0.9176470588235294,
+      "grad_norm": 1.2109845876693726,
+      "learning_rate": 2.8140681692558035e-05,
+      "loss": 0.4425,
+      "num_input_tokens_seen": 1925792,
+      "step": 195
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.0616289377212524,
+      "learning_rate": 2.7219897383073373e-05,
+      "loss": 0.4548,
+      "num_input_tokens_seen": 1974368,
+      "step": 200
+    },
+    {
+      "epoch": 0.9647058823529412,
+      "grad_norm": 1.1032544374465942,
+      "learning_rate": 2.629606664313896e-05,
+      "loss": 0.4302,
+      "num_input_tokens_seen": 2022080,
+      "step": 205
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "grad_norm": 1.2024751901626587,
+      "learning_rate": 2.537045727284232e-05,
+      "loss": 0.4132,
+      "num_input_tokens_seen": 2069920,
+      "step": 210
+    },
+    {
+      "epoch": 1.011764705882353,
+      "grad_norm": 1.0001943111419678,
+      "learning_rate": 2.444433951313772e-05,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 2120704,
+      "step": 215
+    },
+    {
+      "epoch": 1.035294117647059,
+      "grad_norm": 1.0397372245788574,
+      "learning_rate": 2.3518984302657146e-05,
+      "loss": 0.4088,
+      "num_input_tokens_seen": 2171968,
+      "step": 220
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 1.1281183958053589,
+      "learning_rate": 2.259566153356389e-05,
+      "loss": 0.4199,
+      "num_input_tokens_seen": 2223472,
+      "step": 225
+    },
+    {
+      "epoch": 1.0823529411764705,
+      "grad_norm": 1.1637018918991089,
+      "learning_rate": 2.1675638308842145e-05,
+      "loss": 0.4273,
+      "num_input_tokens_seen": 2273296,
+      "step": 230
+    },
+    {
+      "epoch": 1.1058823529411765,
+      "grad_norm": 1.2093477249145508,
+      "learning_rate": 2.0760177203414368e-05,
+      "loss": 0.4042,
+      "num_input_tokens_seen": 2323008,
+      "step": 235
+    },
+    {
+      "epoch": 1.1294117647058823,
+      "grad_norm": 1.1976971626281738,
+      "learning_rate": 1.9850534531472546e-05,
+      "loss": 0.4275,
+      "num_input_tokens_seen": 2373744,
+      "step": 240
+    },
+    {
+      "epoch": 1.1529411764705881,
+      "grad_norm": 1.1152101755142212,
+      "learning_rate": 1.8947958622401328e-05,
+      "loss": 0.4483,
+      "num_input_tokens_seen": 2425216,
+      "step": 245
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 1.0972641706466675,
+      "learning_rate": 1.8053688107658908e-05,
+      "loss": 0.4024,
+      "num_input_tokens_seen": 2472864,
+      "step": 250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.12717604637146,
+      "learning_rate": 1.7168950220966614e-05,
+      "loss": 0.4363,
+      "num_input_tokens_seen": 2523344,
+      "step": 255
+    },
+    {
+      "epoch": 1.223529411764706,
+      "grad_norm": 1.2230875492095947,
+      "learning_rate": 1.6294959114140034e-05,
+      "loss": 0.383,
+      "num_input_tokens_seen": 2571936,
+      "step": 260
+    },
+    {
+      "epoch": 1.2470588235294118,
+      "grad_norm": 1.2656056880950928,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.4287,
+      "num_input_tokens_seen": 2622560,
+      "step": 265
+    },
+    {
+      "epoch": 1.2705882352941176,
+      "grad_norm": 1.186041235923767,
+      "learning_rate": 1.4583998460759424e-05,
+      "loss": 0.3686,
+      "num_input_tokens_seen": 2669232,
+      "step": 270
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 1.2343655824661255,
+      "learning_rate": 1.3749376915816886e-05,
+      "loss": 0.4059,
+      "num_input_tokens_seen": 2718128,
+      "step": 275
+    },
+    {
+      "epoch": 1.3176470588235294,
+      "grad_norm": 1.131495714187622,
+      "learning_rate": 1.2930194931731382e-05,
+      "loss": 0.4242,
+      "num_input_tokens_seen": 2766432,
+      "step": 280
+    },
+    {
+      "epoch": 1.3411764705882354,
+      "grad_norm": 1.0469223260879517,
+      "learning_rate": 1.2127576696025828e-05,
+      "loss": 0.4326,
+      "num_input_tokens_seen": 2819760,
+      "step": 285
+    },
+    {
+      "epoch": 1.3647058823529412,
+      "grad_norm": 1.315108060836792,
+      "learning_rate": 1.1342623665304209e-05,
+      "loss": 0.4266,
+      "num_input_tokens_seen": 2867920,
+      "step": 290
+    },
+    {
+      "epoch": 1.388235294117647,
+      "grad_norm": 1.168626308441162,
+      "learning_rate": 1.0576413053690327e-05,
+      "loss": 0.4049,
+      "num_input_tokens_seen": 2914944,
+      "step": 295
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 1.13846755027771,
+      "learning_rate": 9.829996354535172e-06,
+      "loss": 0.4102,
+      "num_input_tokens_seen": 2965600,
+      "step": 300
+    },
+    {
+      "epoch": 1.4352941176470588,
+      "grad_norm": 1.24168062210083,
+      "learning_rate": 9.104397897421623e-06,
+      "loss": 0.4261,
+      "num_input_tokens_seen": 3015728,
+      "step": 305
+    },
+    {
+      "epoch": 1.4588235294117646,
+      "grad_norm": 1.1973497867584229,
+      "learning_rate": 8.400613442446948e-06,
+      "loss": 0.4109,
+      "num_input_tokens_seen": 3065328,
+      "step": 310
+    },
+    {
+      "epoch": 1.4823529411764707,
+      "grad_norm": 1.0736428499221802,
+      "learning_rate": 7.719608813711848e-06,
+      "loss": 0.3982,
+      "num_input_tokens_seen": 3114720,
+      "step": 315
+    },
+    {
+      "epoch": 1.5058823529411764,
+      "grad_norm": 1.2293542623519897,
+      "learning_rate": 7.062318573891716e-06,
+      "loss": 0.4265,
+      "num_input_tokens_seen": 3163008,
+      "step": 320
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 1.2456164360046387,
+      "learning_rate": 6.429644741708779e-06,
+      "loss": 0.4014,
+      "num_input_tokens_seen": 3211408,
+      "step": 325
+    },
+    {
+      "epoch": 1.5529411764705883,
+      "grad_norm": 1.1817117929458618,
+      "learning_rate": 5.822455554065217e-06,
+      "loss": 0.425,
+      "num_input_tokens_seen": 3263808,
+      "step": 330
+    },
+    {
+      "epoch": 1.576470588235294,
+      "grad_norm": 1.2817317247390747,
+      "learning_rate": 5.241584274536259e-06,
+      "loss": 0.3785,
+      "num_input_tokens_seen": 3311056,
+      "step": 335
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2116546630859375,
+      "learning_rate": 4.687828049857967e-06,
+      "loss": 0.4034,
+      "num_input_tokens_seen": 3358224,
+      "step": 340
+    },
+    {
+      "epoch": 1.6235294117647059,
+      "grad_norm": 1.3325591087341309,
+      "learning_rate": 4.161946815979403e-06,
+      "loss": 0.4075,
+      "num_input_tokens_seen": 3409024,
+      "step": 345
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 1.0810184478759766,
+      "learning_rate": 3.6646622551801345e-06,
+      "loss": 0.3496,
+      "num_input_tokens_seen": 3457616,
+      "step": 350
+    },
+    {
+      "epoch": 1.6705882352941175,
+      "grad_norm": 1.0979664325714111,
+      "learning_rate": 3.19665680568445e-06,
+      "loss": 0.4106,
+      "num_input_tokens_seen": 3510768,
+      "step": 355
+    },
+    {
+      "epoch": 1.6941176470588235,
+      "grad_norm": 1.143621563911438,
+      "learning_rate": 2.75857272513132e-06,
+      "loss": 0.4093,
+      "num_input_tokens_seen": 3556912,
+      "step": 360
+    },
+    {
+      "epoch": 1.7176470588235295,
+      "grad_norm": 1.2018797397613525,
+      "learning_rate": 2.351011209185336e-06,
+      "loss": 0.379,
+      "num_input_tokens_seen": 3606016,
+      "step": 365
+    },
+    {
+      "epoch": 1.7411764705882353,
+      "grad_norm": 1.0897295475006104,
+      "learning_rate": 1.9745315664982276e-06,
+      "loss": 0.3996,
+      "num_input_tokens_seen": 3654256,
+      "step": 370
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 1.2107083797454834,
+      "learning_rate": 1.6296504511531836e-06,
+      "loss": 0.4016,
+      "num_input_tokens_seen": 3704528,
+      "step": 375
+    },
+    {
+      "epoch": 1.788235294117647,
+      "grad_norm": 1.1322784423828125,
+      "learning_rate": 1.3168411536452152e-06,
+      "loss": 0.3769,
+      "num_input_tokens_seen": 3752208,
+      "step": 380
+    },
+    {
+      "epoch": 1.811764705882353,
+      "grad_norm": 1.1542903184890747,
+      "learning_rate": 1.036532951370736e-06,
+      "loss": 0.4045,
+      "num_input_tokens_seen": 3805232,
+      "step": 385
+    },
+    {
+      "epoch": 1.835294117647059,
+      "grad_norm": 1.2877768278121948,
+      "learning_rate": 7.891105195175358e-07,
+      "loss": 0.4051,
+      "num_input_tokens_seen": 3854864,
+      "step": 390
+    },
+    {
+      "epoch": 1.8588235294117648,
+      "grad_norm": 1.2475833892822266,
+      "learning_rate": 5.749134031637349e-07,
+      "loss": 0.3934,
+      "num_input_tokens_seen": 3904880,
+      "step": 395
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 1.152550458908081,
+      "learning_rate": 3.9423555131007925e-07,
+      "loss": 0.41,
+      "num_input_tokens_seen": 3953728,
+      "step": 400
+    },
+    {
+      "epoch": 1.9058823529411764,
+      "grad_norm": 1.1438477039337158,
+      "learning_rate": 2.473249134850808e-07,
+      "loss": 0.3902,
+      "num_input_tokens_seen": 4002944,
+      "step": 405
+    },
+    {
+      "epoch": 1.9294117647058824,
+      "grad_norm": 1.143480896949768,
+      "learning_rate": 1.343830994765982e-07,
+      "loss": 0.3766,
+      "num_input_tokens_seen": 4050880,
+      "step": 410
+    },
+    {
+      "epoch": 1.9529411764705882,
+      "grad_norm": 1.2639435529708862,
+      "learning_rate": 5.5565102656787714e-08,
+      "loss": 0.3826,
+      "num_input_tokens_seen": 4098064,
+      "step": 415
+    },
+    {
+      "epoch": 1.9764705882352942,
+      "grad_norm": 1.1847045421600342,
+      "learning_rate": 1.0979087280141298e-08,
+      "loss": 0.4366,
+      "num_input_tokens_seen": 4147296,
+      "step": 420
+    },
+    {
+      "epoch": 1.9952941176470587,
+      "num_input_tokens_seen": 4186528,
+      "step": 424,
+      "total_flos": 5.002960174252032e+16,
+      "train_loss": 0.48991220936460317,
+      "train_runtime": 1751.8031,
+      "train_samples_per_second": 3.882,
+      "train_steps_per_second": 0.242
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 424,
+  "num_input_tokens_seen": 4186528,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.002960174252032e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd60fc98d6adcbdfa8e79f4d038cedca2989d6ab8323acd7bdf83e02be75baa7
+size 5304

training_args.yaml

@@ -0,0 +1,33 @@
+cutoff_len: 4096
+dataset: claimver_kgllm
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+fp16: true
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: google/gemma-2b-it
+num_train_epochs: 2.0
+optim: adamw_torch
+output_dir: saves/Gemma-2B-Chat/lora/gemma-2b-it-chat_claimver_run2
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+report_to: none
+save_steps: 100
+stage: sft
+template: gemma
+warmup_steps: 0