Upload 14 files

README.md

@@ -0,0 +1,71 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+base_model: unsloth/llama-3-70b-Instruct-bnb-4bit
+model-index:
+- name: A61K
+  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. -->
+
+# A61K
+
+This model is a fine-tuned version of [unsloth/llama-3-70b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-70b-Instruct-bnb-4bit) on the patents_A61K_cla_abs_det_sample_2100_balance_train_llama-factory dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3432
+
+## 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: 3e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5658        | 0.4938 | 100  | 0.4336          |
+| 0.361         | 0.9877 | 200  | 0.3438          |
+| 0.3343        | 1.4815 | 300  | 0.3503          |
+| 0.3275        | 1.9753 | 400  | 0.3462          |
+| 0.2916        | 2.4691 | 500  | 0.3432          |
+| 0.291         | 2.9630 | 600  | 0.3441          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3-70b-Instruct-bnb-4bit",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:31acdfdbad716650fdfb76f3272827f4002e2dd42b55481469ef7e3cc58f9099
+size 65578776

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9925925925925925,
+    "eval_loss": 0.34317871928215027,
+    "eval_runtime": 640.5638,
+    "eval_samples_per_second": 0.281,
+    "eval_steps_per_second": 0.281,
+    "total_flos": 1.4871334589840622e+19,
+    "train_loss": 1.6824197243935992,
+    "train_runtime": 45546.3315,
+    "train_samples_per_second": 0.107,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9925925925925925,
+    "eval_loss": 0.34317871928215027,
+    "eval_runtime": 640.5638,
+    "eval_samples_per_second": 0.281,
+    "eval_steps_per_second": 0.281
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|reserved_special_token_250|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "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": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "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": "<|reserved_special_token_4|>",
+      "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": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|reserved_special_token_250|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9925925925925925,
+    "total_flos": 1.4871334589840622e+19,
+    "train_loss": 1.6824197243935992,
+    "train_runtime": 45546.3315,
+    "train_samples_per_second": 0.107,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,68 @@
+{"current_steps": 10, "total_steps": 606, "loss": 12.2914, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9e-07, "epoch": 0.04938271604938271, "percentage": 1.65, "elapsed_time": "0:11:40", "remaining_time": "11:36:07"}
+{"current_steps": 20, "total_steps": 606, "loss": 12.285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6e-06, "epoch": 0.09876543209876543, "percentage": 3.3, "elapsed_time": "0:23:12", "remaining_time": "11:20:03"}
+{"current_steps": 30, "total_steps": 606, "loss": 12.0986, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.3e-06, "epoch": 0.14814814814814814, "percentage": 4.95, "elapsed_time": "0:34:36", "remaining_time": "11:04:27"}
+{"current_steps": 40, "total_steps": 606, "loss": 11.846, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.3e-06, "epoch": 0.19753086419753085, "percentage": 6.6, "elapsed_time": "0:46:25", "remaining_time": "10:56:57"}
+{"current_steps": 50, "total_steps": 606, "loss": 10.9695, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2299999999999999e-05, "epoch": 0.24691358024691357, "percentage": 8.25, "elapsed_time": "0:57:56", "remaining_time": "10:44:22"}
+{"current_steps": 60, "total_steps": 606, "loss": 9.6625, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.53e-05, "epoch": 0.2962962962962963, "percentage": 9.9, "elapsed_time": "1:09:38", "remaining_time": "10:33:40"}
+{"current_steps": 70, "total_steps": 606, "loss": 7.6763, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.83e-05, "epoch": 0.345679012345679, "percentage": 11.55, "elapsed_time": "1:21:08", "remaining_time": "10:21:20"}
+{"current_steps": 80, "total_steps": 606, "loss": 5.599, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.13e-05, "epoch": 0.3950617283950617, "percentage": 13.2, "elapsed_time": "1:32:53", "remaining_time": "10:10:48"}
+{"current_steps": 90, "total_steps": 606, "loss": 2.2361, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.43e-05, "epoch": 0.4444444444444444, "percentage": 14.85, "elapsed_time": "1:44:24", "remaining_time": "9:58:34"}
+{"current_steps": 100, "total_steps": 606, "loss": 0.5658, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7300000000000003e-05, "epoch": 0.49382716049382713, "percentage": 16.5, "elapsed_time": "1:55:50", "remaining_time": "9:46:10"}
+{"current_steps": 100, "total_steps": 606, "loss": null, "eval_loss": 0.43361854553222656, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.49382716049382713, "percentage": 16.5, "elapsed_time": "1:55:50", "remaining_time": "9:46:10"}
+{"current_steps": 110, "total_steps": 606, "loss": 0.3497, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9999710893018065e-05, "epoch": 0.5432098765432098, "percentage": 18.15, "elapsed_time": "2:17:47", "remaining_time": "10:21:17"}
+{"current_steps": 120, "total_steps": 606, "loss": 0.3664, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9965031537858088e-05, "epoch": 0.5925925925925926, "percentage": 19.8, "elapsed_time": "2:29:35", "remaining_time": "10:05:51"}
+{"current_steps": 130, "total_steps": 606, "loss": 0.3909, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9872683924428126e-05, "epoch": 0.6419753086419753, "percentage": 21.45, "elapsed_time": "2:40:59", "remaining_time": "9:49:29"}
+{"current_steps": 140, "total_steps": 606, "loss": 0.391, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9723023917398982e-05, "epoch": 0.691358024691358, "percentage": 23.1, "elapsed_time": "2:52:52", "remaining_time": "9:35:24"}
+{"current_steps": 150, "total_steps": 606, "loss": 0.3285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9516628236700468e-05, "epoch": 0.7407407407407407, "percentage": 24.75, "elapsed_time": "3:03:56", "remaining_time": "9:19:12"}
+{"current_steps": 160, "total_steps": 606, "loss": 0.3513, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9254292235111508e-05, "epoch": 0.7901234567901234, "percentage": 26.4, "elapsed_time": "3:15:08", "remaining_time": "9:03:57"}
+{"current_steps": 170, "total_steps": 606, "loss": 0.382, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.8937026833341146e-05, "epoch": 0.8395061728395061, "percentage": 28.05, "elapsed_time": "3:26:42", "remaining_time": "8:50:09"}
+{"current_steps": 180, "total_steps": 606, "loss": 0.3862, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.85660546244112e-05, "epoch": 0.8888888888888888, "percentage": 29.7, "elapsed_time": "3:38:24", "remaining_time": "8:36:55"}
+{"current_steps": 190, "total_steps": 606, "loss": 0.4923, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.814280516235244e-05, "epoch": 0.9382716049382716, "percentage": 31.35, "elapsed_time": "3:49:20", "remaining_time": "8:22:07"}
+{"current_steps": 200, "total_steps": 606, "loss": 0.361, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7668909453369486e-05, "epoch": 0.9876543209876543, "percentage": 33.0, "elapsed_time": "4:00:42", "remaining_time": "8:08:39"}
+{"current_steps": 200, "total_steps": 606, "loss": null, "eval_loss": 0.3438129127025604, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9876543209876543, "percentage": 33.0, "elapsed_time": "4:00:42", "remaining_time": "8:08:39"}
+{"current_steps": 210, "total_steps": 606, "loss": 0.3862, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7146193670702906e-05, "epoch": 1.037037037037037, "percentage": 34.65, "elapsed_time": "4:22:59", "remaining_time": "8:15:55"}
+{"current_steps": 220, "total_steps": 606, "loss": 0.3276, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.6576672117408486e-05, "epoch": 1.0864197530864197, "percentage": 36.3, "elapsed_time": "4:34:09", "remaining_time": "8:01:01"}
+{"current_steps": 230, "total_steps": 606, "loss": 0.3845, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5962539464171864e-05, "epoch": 1.1358024691358024, "percentage": 37.95, "elapsed_time": "4:45:48", "remaining_time": "7:47:14"}
+{"current_steps": 240, "total_steps": 606, "loss": 0.3431, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.530616229207034e-05, "epoch": 1.1851851851851851, "percentage": 39.6, "elapsed_time": "4:57:21", "remaining_time": "7:33:27"}
+{"current_steps": 250, "total_steps": 606, "loss": 0.3262, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.4610069972872206e-05, "epoch": 1.2345679012345678, "percentage": 41.25, "elapsed_time": "5:08:53", "remaining_time": "7:19:51"}
+{"current_steps": 260, "total_steps": 606, "loss": 0.3465, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3876944922016517e-05, "epoch": 1.2839506172839505, "percentage": 42.9, "elapsed_time": "5:20:12", "remaining_time": "7:06:07"}
+{"current_steps": 270, "total_steps": 606, "loss": 0.3217, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3109612261833967e-05, "epoch": 1.3333333333333333, "percentage": 44.55, "elapsed_time": "5:31:37", "remaining_time": "6:52:41"}
+{"current_steps": 280, "total_steps": 606, "loss": 0.3276, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2311028934841804e-05, "epoch": 1.382716049382716, "percentage": 46.2, "elapsed_time": "5:43:27", "remaining_time": "6:39:53"}
+{"current_steps": 290, "total_steps": 606, "loss": 0.3561, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.1484272309065257e-05, "epoch": 1.4320987654320987, "percentage": 47.85, "elapsed_time": "5:54:55", "remaining_time": "6:26:44"}
+{"current_steps": 300, "total_steps": 606, "loss": 0.3343, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0632528319295113e-05, "epoch": 1.4814814814814814, "percentage": 49.5, "elapsed_time": "6:06:35", "remaining_time": "6:13:55"}
+{"current_steps": 300, "total_steps": 606, "loss": null, "eval_loss": 0.3502769470214844, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.4814814814814814, "percentage": 49.5, "elapsed_time": "6:06:35", "remaining_time": "6:13:55"}
+{"current_steps": 310, "total_steps": 606, "loss": 0.3471, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9759079189979598e-05, "epoch": 1.5308641975308643, "percentage": 51.16, "elapsed_time": "6:28:41", "remaining_time": "6:11:08"}
+{"current_steps": 320, "total_steps": 606, "loss": 0.3365, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8867290787060762e-05, "epoch": 1.5802469135802468, "percentage": 52.81, "elapsed_time": "6:40:15", "remaining_time": "5:57:43"}
+{"current_steps": 330, "total_steps": 606, "loss": 0.3332, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7960599647495552e-05, "epoch": 1.6296296296296298, "percentage": 54.46, "elapsed_time": "6:51:37", "remaining_time": "5:44:15"}
+{"current_steps": 340, "total_steps": 606, "loss": 0.3339, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.713472257409928e-05, "epoch": 1.6790123456790123, "percentage": 56.11, "elapsed_time": "7:02:54", "remaining_time": "5:30:51"}
+{"current_steps": 350, "total_steps": 606, "loss": 0.3225, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.6209378726328168e-05, "epoch": 1.7283950617283952, "percentage": 57.76, "elapsed_time": "7:14:10", "remaining_time": "5:17:34"}
+{"current_steps": 360, "total_steps": 606, "loss": 0.3359, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5279374496481708e-05, "epoch": 1.7777777777777777, "percentage": 59.41, "elapsed_time": "7:25:37", "remaining_time": "5:04:30"}
+{"current_steps": 370, "total_steps": 606, "loss": 0.3253, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.434829368750633e-05, "epoch": 1.8271604938271606, "percentage": 61.06, "elapsed_time": "7:37:13", "remaining_time": "4:51:38"}
+{"current_steps": 380, "total_steps": 606, "loss": 0.3561, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3419724250982795e-05, "epoch": 1.876543209876543, "percentage": 62.71, "elapsed_time": "7:48:32", "remaining_time": "4:38:39"}
+{"current_steps": 390, "total_steps": 606, "loss": 0.3276, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2497244460832644e-05, "epoch": 1.925925925925926, "percentage": 64.36, "elapsed_time": "8:00:02", "remaining_time": "4:25:52"}
+{"current_steps": 400, "total_steps": 606, "loss": 0.3275, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.1584409124317906e-05, "epoch": 1.9753086419753085, "percentage": 66.01, "elapsed_time": "8:11:25", "remaining_time": "4:13:04"}
+{"current_steps": 400, "total_steps": 606, "loss": null, "eval_loss": 0.3461529314517975, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.9753086419753085, "percentage": 66.01, "elapsed_time": "8:11:25", "remaining_time": "4:13:04"}
+{"current_steps": 410, "total_steps": 606, "loss": 0.3025, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.0684735883470333e-05, "epoch": 2.0246913580246915, "percentage": 67.66, "elapsed_time": "8:33:17", "remaining_time": "4:05:22"}
+{"current_steps": 420, "total_steps": 606, "loss": 0.2947, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.80169165973814e-06, "epoch": 2.074074074074074, "percentage": 69.31, "elapsed_time": "8:44:53", "remaining_time": "3:52:27"}
+{"current_steps": 430, "total_steps": 606, "loss": 0.2596, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.938679294086226e-06, "epoch": 2.123456790123457, "percentage": 70.96, "elapsed_time": "8:56:15", "remaining_time": "3:39:29"}
+{"current_steps": 440, "total_steps": 606, "loss": 0.3097, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.099024434032719e-06, "epoch": 2.1728395061728394, "percentage": 72.61, "elapsed_time": "9:07:49", "remaining_time": "3:26:40"}
+{"current_steps": 450, "total_steps": 606, "loss": 0.306, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.285962718153099e-06, "epoch": 2.2222222222222223, "percentage": 74.26, "elapsed_time": "9:19:11", "remaining_time": "3:13:51"}
+{"current_steps": 460, "total_steps": 606, "loss": 0.313, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.5026273074368575e-06, "epoch": 2.271604938271605, "percentage": 75.91, "elapsed_time": "9:30:41", "remaining_time": "3:01:08"}
+{"current_steps": 470, "total_steps": 606, "loss": 0.3078, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.752036811544973e-06, "epoch": 2.3209876543209877, "percentage": 77.56, "elapsed_time": "9:41:59", "remaining_time": "2:48:24"}
+{"current_steps": 480, "total_steps": 606, "loss": 0.3034, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.03708365649491e-06, "epoch": 2.3703703703703702, "percentage": 79.21, "elapsed_time": "9:53:11", "remaining_time": "2:35:42"}
+{"current_steps": 490, "total_steps": 606, "loss": 0.3052, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3605229385984915e-06, "epoch": 2.419753086419753, "percentage": 80.86, "elapsed_time": "10:05:01", "remaining_time": "2:23:13"}
+{"current_steps": 500, "total_steps": 606, "loss": 0.2916, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7249618076045316e-06, "epoch": 2.4691358024691357, "percentage": 82.51, "elapsed_time": "10:16:35", "remaining_time": "2:10:43"}
+{"current_steps": 500, "total_steps": 606, "loss": null, "eval_loss": 0.34317871928215027, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.4691358024691357, "percentage": 82.51, "elapsed_time": "10:16:35", "remaining_time": "2:10:43"}
+{"current_steps": 510, "total_steps": 606, "loss": 0.2849, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1328494199585704e-06, "epoch": 2.5185185185185186, "percentage": 84.16, "elapsed_time": "10:38:41", "remaining_time": "2:00:13"}
+{"current_steps": 520, "total_steps": 606, "loss": 0.2827, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5864675008951393e-06, "epoch": 2.567901234567901, "percentage": 85.81, "elapsed_time": "10:49:42", "remaining_time": "1:47:27"}
+{"current_steps": 530, "total_steps": 606, "loss": 0.3025, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0879215517319634e-06, "epoch": 2.617283950617284, "percentage": 87.46, "elapsed_time": "11:01:21", "remaining_time": "1:34:50"}
+{"current_steps": 540, "total_steps": 606, "loss": 0.2994, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.639132736248945e-06, "epoch": 2.6666666666666665, "percentage": 89.11, "elapsed_time": "11:13:03", "remaining_time": "1:22:15"}
+{"current_steps": 550, "total_steps": 606, "loss": 0.3024, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2418304774182077e-06, "epoch": 2.7160493827160495, "percentage": 90.76, "elapsed_time": "11:24:23", "remaining_time": "1:09:41"}
+{"current_steps": 560, "total_steps": 606, "loss": 0.3267, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.975457930137787e-07, "epoch": 2.765432098765432, "percentage": 92.41, "elapsed_time": "11:35:57", "remaining_time": "0:57:10"}
+{"current_steps": 570, "total_steps": 606, "loss": 0.2997, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.076053957825411e-07, "epoch": 2.814814814814815, "percentage": 94.06, "elapsed_time": "11:47:26", "remaining_time": "0:44:40"}
+{"current_steps": 580, "total_steps": 606, "loss": 0.2949, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7312658091147976e-07, "epoch": 2.8641975308641974, "percentage": 95.71, "elapsed_time": "11:58:38", "remaining_time": "0:32:12"}
+{"current_steps": 590, "total_steps": 606, "loss": 0.282, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9501292049268593e-07, "epoch": 2.9135802469135803, "percentage": 97.36, "elapsed_time": "12:10:14", "remaining_time": "0:19:48"}
+{"current_steps": 600, "total_steps": 606, "loss": 0.291, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.395078157753921e-08, "epoch": 2.962962962962963, "percentage": 99.01, "elapsed_time": "12:21:36", "remaining_time": "0:07:24"}
+{"current_steps": 600, "total_steps": 606, "loss": null, "eval_loss": 0.34410154819488525, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.962962962962963, "percentage": 99.01, "elapsed_time": "12:21:36", "remaining_time": "0:07:24"}
+{"current_steps": 606, "total_steps": 606, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.9925925925925925, "percentage": 100.0, "elapsed_time": "12:39:06", "remaining_time": "0:00:00"}
+{"current_steps": 180, "total_steps": 180, "loss": null, "eval_loss": 0.34317871928215027, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.9925925925925925, "percentage": 100.0, "elapsed_time": "12:49:47", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,498 @@
+{
+  "best_metric": 0.34317871928215027,
+  "best_model_checkpoint": "../../saves/LLaMA3-70B-qlora-bnb/lora/sft/A61K/checkpoint-500",
+  "epoch": 2.9925925925925925,
+  "eval_steps": 100,
+  "global_step": 606,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04938271604938271,
+      "grad_norm": 15.14680004119873,
+      "learning_rate": 9e-07,
+      "loss": 12.2914,
+      "step": 10
+    },
+    {
+      "epoch": 0.09876543209876543,
+      "grad_norm": 16.71466636657715,
+      "learning_rate": 3.6e-06,
+      "loss": 12.285,
+      "step": 20
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": NaN,
+      "learning_rate": 6.3e-06,
+      "loss": 12.0986,
+      "step": 30
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 15.837638854980469,
+      "learning_rate": 9.3e-06,
+      "loss": 11.846,
+      "step": 40
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 19.359682083129883,
+      "learning_rate": 1.2299999999999999e-05,
+      "loss": 10.9695,
+      "step": 50
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 33.46400451660156,
+      "learning_rate": 1.53e-05,
+      "loss": 9.6625,
+      "step": 60
+    },
+    {
+      "epoch": 0.345679012345679,
+      "grad_norm": 18.000560760498047,
+      "learning_rate": 1.83e-05,
+      "loss": 7.6763,
+      "step": 70
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 23.49736976623535,
+      "learning_rate": 2.13e-05,
+      "loss": 5.599,
+      "step": 80
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 24.056060791015625,
+      "learning_rate": 2.43e-05,
+      "loss": 2.2361,
+      "step": 90
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 9.21530532836914,
+      "learning_rate": 2.7300000000000003e-05,
+      "loss": 0.5658,
+      "step": 100
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "eval_loss": 0.43361854553222656,
+      "eval_runtime": 640.3211,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 100
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 11.147759437561035,
+      "learning_rate": 2.9999710893018065e-05,
+      "loss": 0.3497,
+      "step": 110
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 8.447771072387695,
+      "learning_rate": 2.9965031537858088e-05,
+      "loss": 0.3664,
+      "step": 120
+    },
+    {
+      "epoch": 0.6419753086419753,
+      "grad_norm": 5.72174596786499,
+      "learning_rate": 2.9872683924428126e-05,
+      "loss": 0.3909,
+      "step": 130
+    },
+    {
+      "epoch": 0.691358024691358,
+      "grad_norm": 8.332149505615234,
+      "learning_rate": 2.9723023917398982e-05,
+      "loss": 0.391,
+      "step": 140
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 6.015285491943359,
+      "learning_rate": 2.9516628236700468e-05,
+      "loss": 0.3285,
+      "step": 150
+    },
+    {
+      "epoch": 0.7901234567901234,
+      "grad_norm": 8.486276626586914,
+      "learning_rate": 2.9254292235111508e-05,
+      "loss": 0.3513,
+      "step": 160
+    },
+    {
+      "epoch": 0.8395061728395061,
+      "grad_norm": 19.51106834411621,
+      "learning_rate": 2.8937026833341146e-05,
+      "loss": 0.382,
+      "step": 170
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 9.629849433898926,
+      "learning_rate": 2.85660546244112e-05,
+      "loss": 0.3862,
+      "step": 180
+    },
+    {
+      "epoch": 0.9382716049382716,
+      "grad_norm": 6.940722942352295,
+      "learning_rate": 2.814280516235244e-05,
+      "loss": 0.4923,
+      "step": 190
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 7.83641242980957,
+      "learning_rate": 2.7668909453369486e-05,
+      "loss": 0.361,
+      "step": 200
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_loss": 0.3438129127025604,
+      "eval_runtime": 641.0521,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 200
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 8.031428337097168,
+      "learning_rate": 2.7146193670702906e-05,
+      "loss": 0.3862,
+      "step": 210
+    },
+    {
+      "epoch": 1.0864197530864197,
+      "grad_norm": 4.103025436401367,
+      "learning_rate": 2.6576672117408486e-05,
+      "loss": 0.3276,
+      "step": 220
+    },
+    {
+      "epoch": 1.1358024691358024,
+      "grad_norm": 6.102336883544922,
+      "learning_rate": 2.5962539464171864e-05,
+      "loss": 0.3845,
+      "step": 230
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 11.080580711364746,
+      "learning_rate": 2.530616229207034e-05,
+      "loss": 0.3431,
+      "step": 240
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 7.723226547241211,
+      "learning_rate": 2.4610069972872206e-05,
+      "loss": 0.3262,
+      "step": 250
+    },
+    {
+      "epoch": 1.2839506172839505,
+      "grad_norm": 5.732240200042725,
+      "learning_rate": 2.3876944922016517e-05,
+      "loss": 0.3465,
+      "step": 260
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 6.469529151916504,
+      "learning_rate": 2.3109612261833967e-05,
+      "loss": 0.3217,
+      "step": 270
+    },
+    {
+      "epoch": 1.382716049382716,
+      "grad_norm": 3.8795225620269775,
+      "learning_rate": 2.2311028934841804e-05,
+      "loss": 0.3276,
+      "step": 280
+    },
+    {
+      "epoch": 1.4320987654320987,
+      "grad_norm": 4.8721466064453125,
+      "learning_rate": 2.1484272309065257e-05,
+      "loss": 0.3561,
+      "step": 290
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 6.701916217803955,
+      "learning_rate": 2.0632528319295113e-05,
+      "loss": 0.3343,
+      "step": 300
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "eval_loss": 0.3502769470214844,
+      "eval_runtime": 641.2195,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 300
+    },
+    {
+      "epoch": 1.5308641975308643,
+      "grad_norm": 4.695794582366943,
+      "learning_rate": 1.9759079189979598e-05,
+      "loss": 0.3471,
+      "step": 310
+    },
+    {
+      "epoch": 1.5802469135802468,
+      "grad_norm": 4.3271870613098145,
+      "learning_rate": 1.8867290787060762e-05,
+      "loss": 0.3365,
+      "step": 320
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 4.225152969360352,
+      "learning_rate": 1.7960599647495552e-05,
+      "loss": 0.3332,
+      "step": 330
+    },
+    {
+      "epoch": 1.6790123456790123,
+      "grad_norm": 5.201157093048096,
+      "learning_rate": 1.713472257409928e-05,
+      "loss": 0.3339,
+      "step": 340
+    },
+    {
+      "epoch": 1.7283950617283952,
+      "grad_norm": 5.604823589324951,
+      "learning_rate": 1.6209378726328168e-05,
+      "loss": 0.3225,
+      "step": 350
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 4.6840715408325195,
+      "learning_rate": 1.5279374496481708e-05,
+      "loss": 0.3359,
+      "step": 360
+    },
+    {
+      "epoch": 1.8271604938271606,
+      "grad_norm": 7.939080715179443,
+      "learning_rate": 1.434829368750633e-05,
+      "loss": 0.3253,
+      "step": 370
+    },
+    {
+      "epoch": 1.876543209876543,
+      "grad_norm": 9.724854469299316,
+      "learning_rate": 1.3419724250982795e-05,
+      "loss": 0.3561,
+      "step": 380
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 5.289661407470703,
+      "learning_rate": 1.2497244460832644e-05,
+      "loss": 0.3276,
+      "step": 390
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "grad_norm": 5.043463230133057,
+      "learning_rate": 1.1584409124317906e-05,
+      "loss": 0.3275,
+      "step": 400
+    },
+    {
+      "epoch": 1.9753086419753085,
+      "eval_loss": 0.3461529314517975,
+      "eval_runtime": 641.2613,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 400
+    },
+    {
+      "epoch": 2.0246913580246915,
+      "grad_norm": 7.275540828704834,
+      "learning_rate": 1.0684735883470333e-05,
+      "loss": 0.3025,
+      "step": 410
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 9.59693717956543,
+      "learning_rate": 9.80169165973814e-06,
+      "loss": 0.2947,
+      "step": 420
+    },
+    {
+      "epoch": 2.123456790123457,
+      "grad_norm": 11.817838668823242,
+      "learning_rate": 8.938679294086226e-06,
+      "loss": 0.2596,
+      "step": 430
+    },
+    {
+      "epoch": 2.1728395061728394,
+      "grad_norm": 5.468794822692871,
+      "learning_rate": 8.099024434032719e-06,
+      "loss": 0.3097,
+      "step": 440
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 8.117734909057617,
+      "learning_rate": 7.285962718153099e-06,
+      "loss": 0.306,
+      "step": 450
+    },
+    {
+      "epoch": 2.271604938271605,
+      "grad_norm": 5.816110134124756,
+      "learning_rate": 6.5026273074368575e-06,
+      "loss": 0.313,
+      "step": 460
+    },
+    {
+      "epoch": 2.3209876543209877,
+      "grad_norm": 7.187597751617432,
+      "learning_rate": 5.752036811544973e-06,
+      "loss": 0.3078,
+      "step": 470
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 17.781335830688477,
+      "learning_rate": 5.03708365649491e-06,
+      "loss": 0.3034,
+      "step": 480
+    },
+    {
+      "epoch": 2.419753086419753,
+      "grad_norm": 6.449460506439209,
+      "learning_rate": 4.3605229385984915e-06,
+      "loss": 0.3052,
+      "step": 490
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 8.452071189880371,
+      "learning_rate": 3.7249618076045316e-06,
+      "loss": 0.2916,
+      "step": 500
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "eval_loss": 0.34317871928215027,
+      "eval_runtime": 641.0511,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 500
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 7.553008079528809,
+      "learning_rate": 3.1328494199585704e-06,
+      "loss": 0.2849,
+      "step": 510
+    },
+    {
+      "epoch": 2.567901234567901,
+      "grad_norm": 7.099052906036377,
+      "learning_rate": 2.5864675008951393e-06,
+      "loss": 0.2827,
+      "step": 520
+    },
+    {
+      "epoch": 2.617283950617284,
+      "grad_norm": 11.348811149597168,
+      "learning_rate": 2.0879215517319634e-06,
+      "loss": 0.3025,
+      "step": 530
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 11.900992393493652,
+      "learning_rate": 1.639132736248945e-06,
+      "loss": 0.2994,
+      "step": 540
+    },
+    {
+      "epoch": 2.7160493827160495,
+      "grad_norm": 8.492768287658691,
+      "learning_rate": 1.2418304774182077e-06,
+      "loss": 0.3024,
+      "step": 550
+    },
+    {
+      "epoch": 2.765432098765432,
+      "grad_norm": 4.38970422744751,
+      "learning_rate": 8.975457930137787e-07,
+      "loss": 0.3267,
+      "step": 560
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 5.739566326141357,
+      "learning_rate": 6.076053957825411e-07,
+      "loss": 0.2997,
+      "step": 570
+    },
+    {
+      "epoch": 2.8641975308641974,
+      "grad_norm": 7.524597644805908,
+      "learning_rate": 3.7312658091147976e-07,
+      "loss": 0.2949,
+      "step": 580
+    },
+    {
+      "epoch": 2.9135802469135803,
+      "grad_norm": 5.539340019226074,
+      "learning_rate": 1.9501292049268593e-07,
+      "loss": 0.282,
+      "step": 590
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 7.615926742553711,
+      "learning_rate": 7.395078157753921e-08,
+      "loss": 0.291,
+      "step": 600
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_loss": 0.34410154819488525,
+      "eval_runtime": 641.306,
+      "eval_samples_per_second": 0.281,
+      "eval_steps_per_second": 0.281,
+      "step": 600
+    },
+    {
+      "epoch": 2.9925925925925925,
+      "step": 606,
+      "total_flos": 1.4871334589840622e+19,
+      "train_loss": 1.6824197243935992,
+      "train_runtime": 45546.3315,
+      "train_samples_per_second": 0.107,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 606,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.4871334589840622e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736786a4ef1f4c91385ffcf28ee89a15011d2efe87803cbc82b74a8249166638
+size 5176