Upload 15 files

.gitattributes

@@ -40,3 +40,4 @@ flan_v2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gpt4_alpaca/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 oasst1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 open_orca/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+science_literature/tokenizer.json filter=lfs diff=lfs merge=lfs -text

science_literature/README.md

@@ -0,0 +1,67 @@
+---
+base_model: /cpfs01/user/zhangyiqun/models/gemma-2-2b-it
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: science_literature
+  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. -->
+
+# science_literature
+
+This model is a fine-tuned version of [/cpfs01/user/zhangyiqun/models/gemma-2-2b-it](https://huggingface.co//cpfs01/user/zhangyiqun/models/gemma-2-2b-it) on the science_literature dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9926
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2189        | 4.5045 | 1000 | 0.9809          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

science_literature/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/cpfs01/user/zhangyiqun/models/gemma-2-2b-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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

science_literature/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e6363f21baf24bea7eebd0cbcea2763e8eb004a6cfd4a3abc1999546ed236d
+size 41581360

science_literature/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.9926027059555054,
+    "eval_runtime": 10.4574,
+    "eval_samples_per_second": 35.764,
+    "eval_steps_per_second": 4.494,
+    "total_flos": 1.01086802968209e+18,
+    "train_loss": 0.36593411194311604,
+    "train_runtime": 2755.6936,
+    "train_samples_per_second": 12.872,
+    "train_steps_per_second": 0.403
+}

science_literature/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.9926027059555054,
+    "eval_runtime": 10.4574,
+    "eval_samples_per_second": 35.764,
+    "eval_steps_per_second": 4.494
+}

science_literature/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
+  }
+}

science_literature/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

science_literature/tokenizer.model

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

science_literature/tokenizer_config.json

@@ -0,0 +1,2015 @@
+{
+  "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
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "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": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "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
+}

science_literature/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.01086802968209e+18,
+    "train_loss": 0.36593411194311604,
+    "train_runtime": 2755.6936,
+    "train_samples_per_second": 12.872,
+    "train_steps_per_second": 0.403
+}

science_literature/trainer_log.jsonl

@@ -0,0 +1,113 @@
+{"current_steps": 10, "total_steps": 1110, "loss": 1.2791, "learning_rate": 1.801801801801802e-05, "epoch": 0.04504504504504504, "percentage": 0.9, "elapsed_time": "0:00:25", "remaining_time": "0:46:35"}
+{"current_steps": 20, "total_steps": 1110, "loss": 1.0799, "learning_rate": 3.603603603603604e-05, "epoch": 0.09009009009009009, "percentage": 1.8, "elapsed_time": "0:00:49", "remaining_time": "0:44:41"}
+{"current_steps": 30, "total_steps": 1110, "loss": 0.7657, "learning_rate": 5.405405405405406e-05, "epoch": 0.13513513513513514, "percentage": 2.7, "elapsed_time": "0:01:15", "remaining_time": "0:45:34"}
+{"current_steps": 40, "total_steps": 1110, "loss": 0.5807, "learning_rate": 7.207207207207208e-05, "epoch": 0.18018018018018017, "percentage": 3.6, "elapsed_time": "0:01:41", "remaining_time": "0:45:12"}
+{"current_steps": 50, "total_steps": 1110, "loss": 0.6035, "learning_rate": 9.009009009009009e-05, "epoch": 0.22522522522522523, "percentage": 4.5, "elapsed_time": "0:02:07", "remaining_time": "0:44:56"}
+{"current_steps": 60, "total_steps": 1110, "loss": 0.5441, "learning_rate": 0.00010810810810810812, "epoch": 0.2702702702702703, "percentage": 5.41, "elapsed_time": "0:02:31", "remaining_time": "0:44:13"}
+{"current_steps": 70, "total_steps": 1110, "loss": 0.6031, "learning_rate": 0.00012612612612612612, "epoch": 0.3153153153153153, "percentage": 6.31, "elapsed_time": "0:02:54", "remaining_time": "0:43:17"}
+{"current_steps": 80, "total_steps": 1110, "loss": 0.5686, "learning_rate": 0.00014414414414414415, "epoch": 0.36036036036036034, "percentage": 7.21, "elapsed_time": "0:03:19", "remaining_time": "0:42:42"}
+{"current_steps": 90, "total_steps": 1110, "loss": 0.4978, "learning_rate": 0.00016216216216216218, "epoch": 0.40540540540540543, "percentage": 8.11, "elapsed_time": "0:03:44", "remaining_time": "0:42:21"}
+{"current_steps": 100, "total_steps": 1110, "loss": 0.473, "learning_rate": 0.00018018018018018018, "epoch": 0.45045045045045046, "percentage": 9.01, "elapsed_time": "0:04:09", "remaining_time": "0:42:00"}
+{"current_steps": 110, "total_steps": 1110, "loss": 0.5892, "learning_rate": 0.0001981981981981982, "epoch": 0.4954954954954955, "percentage": 9.91, "elapsed_time": "0:04:34", "remaining_time": "0:41:39"}
+{"current_steps": 120, "total_steps": 1110, "loss": 0.5117, "learning_rate": 0.0001999599507118322, "epoch": 0.5405405405405406, "percentage": 10.81, "elapsed_time": "0:04:59", "remaining_time": "0:41:14"}
+{"current_steps": 130, "total_steps": 1110, "loss": 0.4759, "learning_rate": 0.00019982154991201608, "epoch": 0.5855855855855856, "percentage": 11.71, "elapsed_time": "0:05:26", "remaining_time": "0:40:59"}
+{"current_steps": 140, "total_steps": 1110, "loss": 0.3928, "learning_rate": 0.00019958443999073397, "epoch": 0.6306306306306306, "percentage": 12.61, "elapsed_time": "0:05:50", "remaining_time": "0:40:25"}
+{"current_steps": 150, "total_steps": 1110, "loss": 0.4507, "learning_rate": 0.0001992488554155135, "epoch": 0.6756756756756757, "percentage": 13.51, "elapsed_time": "0:06:15", "remaining_time": "0:40:03"}
+{"current_steps": 160, "total_steps": 1110, "loss": 0.4766, "learning_rate": 0.00019881512803111796, "epoch": 0.7207207207207207, "percentage": 14.41, "elapsed_time": "0:06:41", "remaining_time": "0:39:40"}
+{"current_steps": 170, "total_steps": 1110, "loss": 0.5236, "learning_rate": 0.00019828368673139947, "epoch": 0.7657657657657657, "percentage": 15.32, "elapsed_time": "0:07:06", "remaining_time": "0:39:17"}
+{"current_steps": 180, "total_steps": 1110, "loss": 0.4454, "learning_rate": 0.00019765505703518496, "epoch": 0.8108108108108109, "percentage": 16.22, "elapsed_time": "0:07:31", "remaining_time": "0:38:51"}
+{"current_steps": 190, "total_steps": 1110, "loss": 0.508, "learning_rate": 0.00019692986056661356, "epoch": 0.8558558558558559, "percentage": 17.12, "elapsed_time": "0:07:56", "remaining_time": "0:38:27"}
+{"current_steps": 200, "total_steps": 1110, "loss": 0.5896, "learning_rate": 0.0001961088144404403, "epoch": 0.9009009009009009, "percentage": 18.02, "elapsed_time": "0:08:21", "remaining_time": "0:38:01"}
+{"current_steps": 210, "total_steps": 1110, "loss": 0.4729, "learning_rate": 0.00019519273055291266, "epoch": 0.9459459459459459, "percentage": 18.92, "elapsed_time": "0:08:45", "remaining_time": "0:37:31"}
+{"current_steps": 220, "total_steps": 1110, "loss": 0.45, "learning_rate": 0.0001941825147789225, "epoch": 0.990990990990991, "percentage": 19.82, "elapsed_time": "0:09:10", "remaining_time": "0:37:08"}
+{"current_steps": 230, "total_steps": 1110, "loss": 0.4162, "learning_rate": 0.0001930791660762262, "epoch": 1.0360360360360361, "percentage": 20.72, "elapsed_time": "0:09:35", "remaining_time": "0:36:41"}
+{"current_steps": 240, "total_steps": 1110, "loss": 0.4445, "learning_rate": 0.00019188377549761963, "epoch": 1.0810810810810811, "percentage": 21.62, "elapsed_time": "0:10:00", "remaining_time": "0:36:17"}
+{"current_steps": 250, "total_steps": 1110, "loss": 0.3849, "learning_rate": 0.000190597525112044, "epoch": 1.1261261261261262, "percentage": 22.52, "elapsed_time": "0:10:25", "remaining_time": "0:35:52"}
+{"current_steps": 260, "total_steps": 1110, "loss": 0.4652, "learning_rate": 0.0001892216868356904, "epoch": 1.1711711711711712, "percentage": 23.42, "elapsed_time": "0:10:50", "remaining_time": "0:35:26"}
+{"current_steps": 270, "total_steps": 1110, "loss": 0.4648, "learning_rate": 0.00018775762117425777, "epoch": 1.2162162162162162, "percentage": 24.32, "elapsed_time": "0:11:15", "remaining_time": "0:35:00"}
+{"current_steps": 280, "total_steps": 1110, "loss": 0.3848, "learning_rate": 0.00018620677587760916, "epoch": 1.2612612612612613, "percentage": 25.23, "elapsed_time": "0:11:40", "remaining_time": "0:34:35"}
+{"current_steps": 290, "total_steps": 1110, "loss": 0.4532, "learning_rate": 0.00018457068450815562, "epoch": 1.3063063063063063, "percentage": 26.13, "elapsed_time": "0:12:04", "remaining_time": "0:34:08"}
+{"current_steps": 300, "total_steps": 1110, "loss": 0.5282, "learning_rate": 0.00018285096492438424, "epoch": 1.3513513513513513, "percentage": 27.03, "elapsed_time": "0:12:29", "remaining_time": "0:33:42"}
+{"current_steps": 310, "total_steps": 1110, "loss": 0.4369, "learning_rate": 0.0001810493176810292, "epoch": 1.3963963963963963, "percentage": 27.93, "elapsed_time": "0:12:54", "remaining_time": "0:33:17"}
+{"current_steps": 320, "total_steps": 1110, "loss": 0.4434, "learning_rate": 0.00017916752434746856, "epoch": 1.4414414414414414, "percentage": 28.83, "elapsed_time": "0:13:17", "remaining_time": "0:32:49"}
+{"current_steps": 330, "total_steps": 1110, "loss": 0.4434, "learning_rate": 0.00017720744574600863, "epoch": 1.4864864864864864, "percentage": 29.73, "elapsed_time": "0:13:42", "remaining_time": "0:32:23"}
+{"current_steps": 340, "total_steps": 1110, "loss": 0.4226, "learning_rate": 0.00017517102011179933, "epoch": 1.5315315315315314, "percentage": 30.63, "elapsed_time": "0:14:07", "remaining_time": "0:31:58"}
+{"current_steps": 350, "total_steps": 1110, "loss": 0.4126, "learning_rate": 0.00017306026117619889, "epoch": 1.5765765765765765, "percentage": 31.53, "elapsed_time": "0:14:33", "remaining_time": "0:31:35"}
+{"current_steps": 360, "total_steps": 1110, "loss": 0.3926, "learning_rate": 0.00017087725617548385, "epoch": 1.6216216216216215, "percentage": 32.43, "elapsed_time": "0:14:58", "remaining_time": "0:31:11"}
+{"current_steps": 370, "total_steps": 1110, "loss": 0.4437, "learning_rate": 0.0001686241637868734, "epoch": 1.6666666666666665, "percentage": 33.33, "elapsed_time": "0:15:22", "remaining_time": "0:30:45"}
+{"current_steps": 380, "total_steps": 1110, "loss": 0.3932, "learning_rate": 0.00016630321199390867, "epoch": 1.7117117117117115, "percentage": 34.23, "elapsed_time": "0:15:47", "remaining_time": "0:30:20"}
+{"current_steps": 390, "total_steps": 1110, "loss": 0.3883, "learning_rate": 0.0001639166958832985, "epoch": 1.7567567567567568, "percentage": 35.14, "elapsed_time": "0:16:11", "remaining_time": "0:29:54"}
+{"current_steps": 400, "total_steps": 1110, "loss": 0.4453, "learning_rate": 0.00016146697537540924, "epoch": 1.8018018018018018, "percentage": 36.04, "elapsed_time": "0:16:36", "remaining_time": "0:29:29"}
+{"current_steps": 410, "total_steps": 1110, "loss": 0.48, "learning_rate": 0.00015895647289064396, "epoch": 1.8468468468468469, "percentage": 36.94, "elapsed_time": "0:17:01", "remaining_time": "0:29:03"}
+{"current_steps": 420, "total_steps": 1110, "loss": 0.4874, "learning_rate": 0.0001563876709540178, "epoch": 1.8918918918918919, "percentage": 37.84, "elapsed_time": "0:17:25", "remaining_time": "0:28:37"}
+{"current_steps": 430, "total_steps": 1110, "loss": 0.4075, "learning_rate": 0.00015376310974029873, "epoch": 1.936936936936937, "percentage": 38.74, "elapsed_time": "0:17:50", "remaining_time": "0:28:12"}
+{"current_steps": 440, "total_steps": 1110, "loss": 0.504, "learning_rate": 0.0001510853845621409, "epoch": 1.981981981981982, "percentage": 39.64, "elapsed_time": "0:18:14", "remaining_time": "0:27:45"}
+{"current_steps": 450, "total_steps": 1110, "loss": 0.3732, "learning_rate": 0.00014835714330369446, "epoch": 2.027027027027027, "percentage": 40.54, "elapsed_time": "0:18:38", "remaining_time": "0:27:20"}
+{"current_steps": 460, "total_steps": 1110, "loss": 0.3317, "learning_rate": 0.00014558108380223012, "epoch": 2.0720720720720722, "percentage": 41.44, "elapsed_time": "0:19:03", "remaining_time": "0:26:55"}
+{"current_steps": 470, "total_steps": 1110, "loss": 0.3896, "learning_rate": 0.00014275995118036693, "epoch": 2.1171171171171173, "percentage": 42.34, "elapsed_time": "0:19:28", "remaining_time": "0:26:30"}
+{"current_steps": 480, "total_steps": 1110, "loss": 0.3478, "learning_rate": 0.00013989653513154165, "epoch": 2.1621621621621623, "percentage": 43.24, "elapsed_time": "0:19:52", "remaining_time": "0:26:05"}
+{"current_steps": 490, "total_steps": 1110, "loss": 0.3712, "learning_rate": 0.00013699366716140435, "epoch": 2.2072072072072073, "percentage": 44.14, "elapsed_time": "0:20:16", "remaining_time": "0:25:39"}
+{"current_steps": 500, "total_steps": 1110, "loss": 0.3548, "learning_rate": 0.00013405421778786737, "epoch": 2.2522522522522523, "percentage": 45.05, "elapsed_time": "0:20:41", "remaining_time": "0:25:14"}
+{"current_steps": 510, "total_steps": 1110, "loss": 0.3404, "learning_rate": 0.00013108109370257712, "epoch": 2.2972972972972974, "percentage": 45.95, "elapsed_time": "0:21:05", "remaining_time": "0:24:48"}
+{"current_steps": 520, "total_steps": 1110, "loss": 0.374, "learning_rate": 0.00012807723489661495, "epoch": 2.3423423423423424, "percentage": 46.85, "elapsed_time": "0:21:30", "remaining_time": "0:24:24"}
+{"current_steps": 530, "total_steps": 1110, "loss": 0.3127, "learning_rate": 0.00012504561175326985, "epoch": 2.3873873873873874, "percentage": 47.75, "elapsed_time": "0:21:56", "remaining_time": "0:24:00"}
+{"current_steps": 540, "total_steps": 1110, "loss": 0.353, "learning_rate": 0.00012198922211075778, "epoch": 2.4324324324324325, "percentage": 48.65, "elapsed_time": "0:22:20", "remaining_time": "0:23:35"}
+{"current_steps": 550, "total_steps": 1110, "loss": 0.3531, "learning_rate": 0.00011891108829779165, "epoch": 2.4774774774774775, "percentage": 49.55, "elapsed_time": "0:22:45", "remaining_time": "0:23:09"}
+{"current_steps": 560, "total_steps": 1110, "loss": 0.3695, "learning_rate": 0.0001158142541449341, "epoch": 2.5225225225225225, "percentage": 50.45, "elapsed_time": "0:23:09", "remaining_time": "0:22:45"}
+{"current_steps": 570, "total_steps": 1110, "loss": 0.3606, "learning_rate": 0.00011270178197468789, "epoch": 2.5675675675675675, "percentage": 51.35, "elapsed_time": "0:23:34", "remaining_time": "0:22:20"}
+{"current_steps": 580, "total_steps": 1110, "loss": 0.312, "learning_rate": 0.00010957674957330042, "epoch": 2.6126126126126126, "percentage": 52.25, "elapsed_time": "0:23:58", "remaining_time": "0:21:54"}
+{"current_steps": 590, "total_steps": 1110, "loss": 0.4027, "learning_rate": 0.00010644224714727681, "epoch": 2.6576576576576576, "percentage": 53.15, "elapsed_time": "0:24:23", "remaining_time": "0:21:30"}
+{"current_steps": 600, "total_steps": 1110, "loss": 0.3496, "learning_rate": 0.00010330137426761135, "epoch": 2.7027027027027026, "percentage": 54.05, "elapsed_time": "0:24:48", "remaining_time": "0:21:05"}
+{"current_steps": 610, "total_steps": 1110, "loss": 0.3489, "learning_rate": 0.00010015723680475846, "epoch": 2.7477477477477477, "percentage": 54.95, "elapsed_time": "0:25:13", "remaining_time": "0:20:40"}
+{"current_steps": 620, "total_steps": 1110, "loss": 0.3296, "learning_rate": 9.70129438573747e-05, "epoch": 2.7927927927927927, "percentage": 55.86, "elapsed_time": "0:25:36", "remaining_time": "0:20:14"}
+{"current_steps": 630, "total_steps": 1110, "loss": 0.3004, "learning_rate": 9.38716046778684e-05, "epoch": 2.8378378378378377, "percentage": 56.76, "elapsed_time": "0:26:01", "remaining_time": "0:19:49"}
+{"current_steps": 640, "total_steps": 1110, "loss": 0.3716, "learning_rate": 9.07363255977973e-05, "epoch": 2.8828828828828827, "percentage": 57.66, "elapsed_time": "0:26:25", "remaining_time": "0:19:24"}
+{"current_steps": 650, "total_steps": 1110, "loss": 0.311, "learning_rate": 8.76102069561545e-05, "epoch": 2.9279279279279278, "percentage": 58.56, "elapsed_time": "0:26:50", "remaining_time": "0:18:59"}
+{"current_steps": 660, "total_steps": 1110, "loss": 0.3488, "learning_rate": 8.449634003358022e-05, "epoch": 2.972972972972973, "percentage": 59.46, "elapsed_time": "0:27:14", "remaining_time": "0:18:34"}
+{"current_steps": 670, "total_steps": 1110, "loss": 0.2858, "learning_rate": 8.13978039955308e-05, "epoch": 3.018018018018018, "percentage": 60.36, "elapsed_time": "0:27:40", "remaining_time": "0:18:10"}
+{"current_steps": 680, "total_steps": 1110, "loss": 0.2565, "learning_rate": 7.831766284742807e-05, "epoch": 3.063063063063063, "percentage": 61.26, "elapsed_time": "0:28:05", "remaining_time": "0:17:45"}
+{"current_steps": 690, "total_steps": 1110, "loss": 0.2173, "learning_rate": 7.525896240479976e-05, "epoch": 3.108108108108108, "percentage": 62.16, "elapsed_time": "0:28:28", "remaining_time": "0:17:19"}
+{"current_steps": 700, "total_steps": 1110, "loss": 0.2548, "learning_rate": 7.222472728140695e-05, "epoch": 3.153153153153153, "percentage": 63.06, "elapsed_time": "0:28:52", "remaining_time": "0:16:54"}
+{"current_steps": 710, "total_steps": 1110, "loss": 0.2638, "learning_rate": 6.921795789833723e-05, "epoch": 3.1981981981981984, "percentage": 63.96, "elapsed_time": "0:29:16", "remaining_time": "0:16:29"}
+{"current_steps": 720, "total_steps": 1110, "loss": 0.2623, "learning_rate": 6.624162751702076e-05, "epoch": 3.2432432432432434, "percentage": 64.86, "elapsed_time": "0:29:41", "remaining_time": "0:16:05"}
+{"current_steps": 730, "total_steps": 1110, "loss": 0.2938, "learning_rate": 6.329867929910347e-05, "epoch": 3.2882882882882885, "percentage": 65.77, "elapsed_time": "0:30:07", "remaining_time": "0:15:40"}
+{"current_steps": 740, "total_steps": 1110, "loss": 0.2443, "learning_rate": 6.039202339608432e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:30:32", "remaining_time": "0:15:16"}
+{"current_steps": 750, "total_steps": 1110, "loss": 0.2359, "learning_rate": 5.752453407159522e-05, "epoch": 3.3783783783783785, "percentage": 67.57, "elapsed_time": "0:30:57", "remaining_time": "0:14:51"}
+{"current_steps": 760, "total_steps": 1110, "loss": 0.2465, "learning_rate": 5.469904685916861e-05, "epoch": 3.4234234234234235, "percentage": 68.47, "elapsed_time": "0:31:21", "remaining_time": "0:14:26"}
+{"current_steps": 770, "total_steps": 1110, "loss": 0.3042, "learning_rate": 5.191835575830352e-05, "epoch": 3.4684684684684686, "percentage": 69.37, "elapsed_time": "0:31:46", "remaining_time": "0:14:01"}
+{"current_steps": 780, "total_steps": 1110, "loss": 0.2885, "learning_rate": 4.918521047160308e-05, "epoch": 3.5135135135135136, "percentage": 70.27, "elapsed_time": "0:32:10", "remaining_time": "0:13:36"}
+{"current_steps": 790, "total_steps": 1110, "loss": 0.2728, "learning_rate": 4.650231368571486e-05, "epoch": 3.5585585585585586, "percentage": 71.17, "elapsed_time": "0:32:35", "remaining_time": "0:13:12"}
+{"current_steps": 800, "total_steps": 1110, "loss": 0.258, "learning_rate": 4.387231839876349e-05, "epoch": 3.6036036036036037, "percentage": 72.07, "elapsed_time": "0:33:00", "remaining_time": "0:12:47"}
+{"current_steps": 810, "total_steps": 1110, "loss": 0.3219, "learning_rate": 4.129782529691815e-05, "epoch": 3.6486486486486487, "percentage": 72.97, "elapsed_time": "0:33:24", "remaining_time": "0:12:22"}
+{"current_steps": 820, "total_steps": 1110, "loss": 0.2318, "learning_rate": 3.878138018268866e-05, "epoch": 3.6936936936936937, "percentage": 73.87, "elapsed_time": "0:33:49", "remaining_time": "0:11:57"}
+{"current_steps": 830, "total_steps": 1110, "loss": 0.3025, "learning_rate": 3.632547145749395e-05, "epoch": 3.7387387387387387, "percentage": 74.77, "elapsed_time": "0:34:14", "remaining_time": "0:11:32"}
+{"current_steps": 840, "total_steps": 1110, "loss": 0.2744, "learning_rate": 3.393252766099187e-05, "epoch": 3.7837837837837838, "percentage": 75.68, "elapsed_time": "0:34:38", "remaining_time": "0:11:08"}
+{"current_steps": 850, "total_steps": 1110, "loss": 0.2663, "learning_rate": 3.1604915069603436e-05, "epoch": 3.828828828828829, "percentage": 76.58, "elapsed_time": "0:35:03", "remaining_time": "0:10:43"}
+{"current_steps": 860, "total_steps": 1110, "loss": 0.2058, "learning_rate": 2.9344935356606773e-05, "epoch": 3.873873873873874, "percentage": 77.48, "elapsed_time": "0:35:27", "remaining_time": "0:10:18"}
+{"current_steps": 870, "total_steps": 1110, "loss": 0.2466, "learning_rate": 2.7154823316113932e-05, "epoch": 3.918918918918919, "percentage": 78.38, "elapsed_time": "0:35:52", "remaining_time": "0:09:53"}
+{"current_steps": 880, "total_steps": 1110, "loss": 0.2695, "learning_rate": 2.5036744653181753e-05, "epoch": 3.963963963963964, "percentage": 79.28, "elapsed_time": "0:36:16", "remaining_time": "0:09:28"}
+{"current_steps": 890, "total_steps": 1110, "loss": 0.2252, "learning_rate": 2.29927938422419e-05, "epoch": 4.009009009009009, "percentage": 80.18, "elapsed_time": "0:36:41", "remaining_time": "0:09:04"}
+{"current_steps": 900, "total_steps": 1110, "loss": 0.2067, "learning_rate": 2.102499205596743e-05, "epoch": 4.054054054054054, "percentage": 81.08, "elapsed_time": "0:37:06", "remaining_time": "0:08:39"}
+{"current_steps": 910, "total_steps": 1110, "loss": 0.2165, "learning_rate": 1.913528516662452e-05, "epoch": 4.099099099099099, "percentage": 81.98, "elapsed_time": "0:37:30", "remaining_time": "0:08:14"}
+{"current_steps": 920, "total_steps": 1110, "loss": 0.2102, "learning_rate": 1.7325541821885384e-05, "epoch": 4.1441441441441444, "percentage": 82.88, "elapsed_time": "0:37:55", "remaining_time": "0:07:50"}
+{"current_steps": 930, "total_steps": 1110, "loss": 0.1765, "learning_rate": 1.5597551597004966e-05, "epoch": 4.1891891891891895, "percentage": 83.78, "elapsed_time": "0:38:19", "remaining_time": "0:07:25"}
+{"current_steps": 940, "total_steps": 1110, "loss": 0.2147, "learning_rate": 1.3953023225189243e-05, "epoch": 4.2342342342342345, "percentage": 84.68, "elapsed_time": "0:38:45", "remaining_time": "0:07:00"}
+{"current_steps": 950, "total_steps": 1110, "loss": 0.2068, "learning_rate": 1.23935829079042e-05, "epoch": 4.2792792792792795, "percentage": 85.59, "elapsed_time": "0:39:08", "remaining_time": "0:06:35"}
+{"current_steps": 960, "total_steps": 1110, "loss": 0.1884, "learning_rate": 1.0920772706797167e-05, "epoch": 4.324324324324325, "percentage": 86.49, "elapsed_time": "0:39:34", "remaining_time": "0:06:11"}
+{"current_steps": 970, "total_steps": 1110, "loss": 0.2135, "learning_rate": 9.536049018820192e-06, "epoch": 4.36936936936937, "percentage": 87.39, "elapsed_time": "0:39:59", "remaining_time": "0:05:46"}
+{"current_steps": 980, "total_steps": 1110, "loss": 0.1831, "learning_rate": 8.240781136063346e-06, "epoch": 4.414414414414415, "percentage": 88.29, "elapsed_time": "0:40:23", "remaining_time": "0:05:21"}
+{"current_steps": 990, "total_steps": 1110, "loss": 0.198, "learning_rate": 7.03624989172228e-06, "epoch": 4.45945945945946, "percentage": 89.19, "elapsed_time": "0:40:47", "remaining_time": "0:04:56"}
+{"current_steps": 1000, "total_steps": 1110, "loss": 0.2189, "learning_rate": 5.9236463935389065e-06, "epoch": 4.504504504504505, "percentage": 90.09, "elapsed_time": "0:41:13", "remaining_time": "0:04:32"}
+{"current_steps": 1000, "total_steps": 1110, "eval_loss": 0.9809222221374512, "epoch": 4.504504504504505, "percentage": 90.09, "elapsed_time": "0:41:24", "remaining_time": "0:04:33"}
+{"current_steps": 1010, "total_steps": 1110, "loss": 0.1889, "learning_rate": 4.904070845967468e-06, "epoch": 4.54954954954955, "percentage": 90.99, "elapsed_time": "0:41:49", "remaining_time": "0:04:08"}
+{"current_steps": 1020, "total_steps": 1110, "loss": 0.1891, "learning_rate": 3.9785314622310495e-06, "epoch": 4.594594594594595, "percentage": 91.89, "elapsed_time": "0:42:13", "remaining_time": "0:03:43"}
+{"current_steps": 1030, "total_steps": 1110, "loss": 0.1879, "learning_rate": 3.1479434673440167e-06, "epoch": 4.63963963963964, "percentage": 92.79, "elapsed_time": "0:42:38", "remaining_time": "0:03:18"}
+{"current_steps": 1040, "total_steps": 1110, "loss": 0.1972, "learning_rate": 2.4131281930864002e-06, "epoch": 4.684684684684685, "percentage": 93.69, "elapsed_time": "0:43:02", "remaining_time": "0:02:53"}
+{"current_steps": 1050, "total_steps": 1110, "loss": 0.201, "learning_rate": 1.7748122658251876e-06, "epoch": 4.72972972972973, "percentage": 94.59, "elapsed_time": "0:43:27", "remaining_time": "0:02:29"}
+{"current_steps": 1060, "total_steps": 1110, "loss": 0.1876, "learning_rate": 1.2336268879856727e-06, "epoch": 4.774774774774775, "percentage": 95.5, "elapsed_time": "0:43:52", "remaining_time": "0:02:04"}
+{"current_steps": 1070, "total_steps": 1110, "loss": 0.1722, "learning_rate": 7.901072138831511e-07, "epoch": 4.81981981981982, "percentage": 96.4, "elapsed_time": "0:44:16", "remaining_time": "0:01:39"}
+{"current_steps": 1080, "total_steps": 1110, "loss": 0.1917, "learning_rate": 4.44691820532539e-07, "epoch": 4.864864864864865, "percentage": 97.3, "elapsed_time": "0:44:41", "remaining_time": "0:01:14"}
+{"current_steps": 1090, "total_steps": 1110, "loss": 0.2082, "learning_rate": 1.977222739588891e-07, "epoch": 4.90990990990991, "percentage": 98.2, "elapsed_time": "0:45:05", "remaining_time": "0:00:49"}
+{"current_steps": 1100, "total_steps": 1110, "loss": 0.2052, "learning_rate": 4.9442791437848136e-08, "epoch": 4.954954954954955, "percentage": 99.1, "elapsed_time": "0:45:30", "remaining_time": "0:00:24"}
+{"current_steps": 1110, "total_steps": 1110, "loss": 0.197, "learning_rate": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:45:54", "remaining_time": "0:00:00"}
+{"current_steps": 1110, "total_steps": 1110, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:45:55", "remaining_time": "0:00:00"}

science_literature/trainer_state.json

@@ -0,0 +1,827 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 1000,
+  "global_step": 1110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04504504504504504,
+      "grad_norm": 3.3412909507751465,
+      "learning_rate": 1.801801801801802e-05,
+      "loss": 1.2791,
+      "step": 10
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": 1.4792481660842896,
+      "learning_rate": 3.603603603603604e-05,
+      "loss": 1.0799,
+      "step": 20
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 1.3788402080535889,
+      "learning_rate": 5.405405405405406e-05,
+      "loss": 0.7657,
+      "step": 30
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.7668061256408691,
+      "learning_rate": 7.207207207207208e-05,
+      "loss": 0.5807,
+      "step": 40
+    },
+    {
+      "epoch": 0.22522522522522523,
+      "grad_norm": 0.7166613936424255,
+      "learning_rate": 9.009009009009009e-05,
+      "loss": 0.6035,
+      "step": 50
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.9661350846290588,
+      "learning_rate": 0.00010810810810810812,
+      "loss": 0.5441,
+      "step": 60
+    },
+    {
+      "epoch": 0.3153153153153153,
+      "grad_norm": 0.7341681122779846,
+      "learning_rate": 0.00012612612612612612,
+      "loss": 0.6031,
+      "step": 70
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 1.3319752216339111,
+      "learning_rate": 0.00014414414414414415,
+      "loss": 0.5686,
+      "step": 80
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.7269447445869446,
+      "learning_rate": 0.00016216216216216218,
+      "loss": 0.4978,
+      "step": 90
+    },
+    {
+      "epoch": 0.45045045045045046,
+      "grad_norm": 0.46780362725257874,
+      "learning_rate": 0.00018018018018018018,
+      "loss": 0.473,
+      "step": 100
+    },
+    {
+      "epoch": 0.4954954954954955,
+      "grad_norm": 0.728823184967041,
+      "learning_rate": 0.0001981981981981982,
+      "loss": 0.5892,
+      "step": 110
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.5054831504821777,
+      "learning_rate": 0.0001999599507118322,
+      "loss": 0.5117,
+      "step": 120
+    },
+    {
+      "epoch": 0.5855855855855856,
+      "grad_norm": 0.6193355321884155,
+      "learning_rate": 0.00019982154991201608,
+      "loss": 0.4759,
+      "step": 130
+    },
+    {
+      "epoch": 0.6306306306306306,
+      "grad_norm": 0.3995501399040222,
+      "learning_rate": 0.00019958443999073397,
+      "loss": 0.3928,
+      "step": 140
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.5497131943702698,
+      "learning_rate": 0.0001992488554155135,
+      "loss": 0.4507,
+      "step": 150
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 1.0290075540542603,
+      "learning_rate": 0.00019881512803111796,
+      "loss": 0.4766,
+      "step": 160
+    },
+    {
+      "epoch": 0.7657657657657657,
+      "grad_norm": 0.6826834678649902,
+      "learning_rate": 0.00019828368673139947,
+      "loss": 0.5236,
+      "step": 170
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.6135373711585999,
+      "learning_rate": 0.00019765505703518496,
+      "loss": 0.4454,
+      "step": 180
+    },
+    {
+      "epoch": 0.8558558558558559,
+      "grad_norm": 0.6352598667144775,
+      "learning_rate": 0.00019692986056661356,
+      "loss": 0.508,
+      "step": 190
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.5680545568466187,
+      "learning_rate": 0.0001961088144404403,
+      "loss": 0.5896,
+      "step": 200
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.3386252820491791,
+      "learning_rate": 0.00019519273055291266,
+      "loss": 0.4729,
+      "step": 210
+    },
+    {
+      "epoch": 0.990990990990991,
+      "grad_norm": 0.358553409576416,
+      "learning_rate": 0.0001941825147789225,
+      "loss": 0.45,
+      "step": 220
+    },
+    {
+      "epoch": 1.0360360360360361,
+      "grad_norm": 0.668021023273468,
+      "learning_rate": 0.0001930791660762262,
+      "loss": 0.4162,
+      "step": 230
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.5463367700576782,
+      "learning_rate": 0.00019188377549761963,
+      "loss": 0.4445,
+      "step": 240
+    },
+    {
+      "epoch": 1.1261261261261262,
+      "grad_norm": 0.7385880351066589,
+      "learning_rate": 0.000190597525112044,
+      "loss": 0.3849,
+      "step": 250
+    },
+    {
+      "epoch": 1.1711711711711712,
+      "grad_norm": 0.6837536692619324,
+      "learning_rate": 0.0001892216868356904,
+      "loss": 0.4652,
+      "step": 260
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.866578221321106,
+      "learning_rate": 0.00018775762117425777,
+      "loss": 0.4648,
+      "step": 270
+    },
+    {
+      "epoch": 1.2612612612612613,
+      "grad_norm": 0.6583455204963684,
+      "learning_rate": 0.00018620677587760916,
+      "loss": 0.3848,
+      "step": 280
+    },
+    {
+      "epoch": 1.3063063063063063,
+      "grad_norm": 0.6937561631202698,
+      "learning_rate": 0.00018457068450815562,
+      "loss": 0.4532,
+      "step": 290
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.5930050611495972,
+      "learning_rate": 0.00018285096492438424,
+      "loss": 0.5282,
+      "step": 300
+    },
+    {
+      "epoch": 1.3963963963963963,
+      "grad_norm": 1.1432991027832031,
+      "learning_rate": 0.0001810493176810292,
+      "loss": 0.4369,
+      "step": 310
+    },
+    {
+      "epoch": 1.4414414414414414,
+      "grad_norm": 0.5736434459686279,
+      "learning_rate": 0.00017916752434746856,
+      "loss": 0.4434,
+      "step": 320
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.5792914032936096,
+      "learning_rate": 0.00017720744574600863,
+      "loss": 0.4434,
+      "step": 330
+    },
+    {
+      "epoch": 1.5315315315315314,
+      "grad_norm": 0.7626290917396545,
+      "learning_rate": 0.00017517102011179933,
+      "loss": 0.4226,
+      "step": 340
+    },
+    {
+      "epoch": 1.5765765765765765,
+      "grad_norm": 0.6746386289596558,
+      "learning_rate": 0.00017306026117619889,
+      "loss": 0.4126,
+      "step": 350
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.5064342617988586,
+      "learning_rate": 0.00017087725617548385,
+      "loss": 0.3926,
+      "step": 360
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.793991208076477,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 0.4437,
+      "step": 370
+    },
+    {
+      "epoch": 1.7117117117117115,
+      "grad_norm": 0.6197868585586548,
+      "learning_rate": 0.00016630321199390867,
+      "loss": 0.3932,
+      "step": 380
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.5004612803459167,
+      "learning_rate": 0.0001639166958832985,
+      "loss": 0.3883,
+      "step": 390
+    },
+    {
+      "epoch": 1.8018018018018018,
+      "grad_norm": 0.7265865206718445,
+      "learning_rate": 0.00016146697537540924,
+      "loss": 0.4453,
+      "step": 400
+    },
+    {
+      "epoch": 1.8468468468468469,
+      "grad_norm": 0.5155379772186279,
+      "learning_rate": 0.00015895647289064396,
+      "loss": 0.48,
+      "step": 410
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.5756716132164001,
+      "learning_rate": 0.0001563876709540178,
+      "loss": 0.4874,
+      "step": 420
+    },
+    {
+      "epoch": 1.936936936936937,
+      "grad_norm": 0.7919459342956543,
+      "learning_rate": 0.00015376310974029873,
+      "loss": 0.4075,
+      "step": 430
+    },
+    {
+      "epoch": 1.981981981981982,
+      "grad_norm": 0.5977569818496704,
+      "learning_rate": 0.0001510853845621409,
+      "loss": 0.504,
+      "step": 440
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.601466178894043,
+      "learning_rate": 0.00014835714330369446,
+      "loss": 0.3732,
+      "step": 450
+    },
+    {
+      "epoch": 2.0720720720720722,
+      "grad_norm": 0.575406014919281,
+      "learning_rate": 0.00014558108380223012,
+      "loss": 0.3317,
+      "step": 460
+    },
+    {
+      "epoch": 2.1171171171171173,
+      "grad_norm": 1.0440267324447632,
+      "learning_rate": 0.00014275995118036693,
+      "loss": 0.3896,
+      "step": 470
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.6646713614463806,
+      "learning_rate": 0.00013989653513154165,
+      "loss": 0.3478,
+      "step": 480
+    },
+    {
+      "epoch": 2.2072072072072073,
+      "grad_norm": 0.7202288508415222,
+      "learning_rate": 0.00013699366716140435,
+      "loss": 0.3712,
+      "step": 490
+    },
+    {
+      "epoch": 2.2522522522522523,
+      "grad_norm": 0.6566169261932373,
+      "learning_rate": 0.00013405421778786737,
+      "loss": 0.3548,
+      "step": 500
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 1.0158584117889404,
+      "learning_rate": 0.00013108109370257712,
+      "loss": 0.3404,
+      "step": 510
+    },
+    {
+      "epoch": 2.3423423423423424,
+      "grad_norm": 0.7582752108573914,
+      "learning_rate": 0.00012807723489661495,
+      "loss": 0.374,
+      "step": 520
+    },
+    {
+      "epoch": 2.3873873873873874,
+      "grad_norm": 0.7685467600822449,
+      "learning_rate": 0.00012504561175326985,
+      "loss": 0.3127,
+      "step": 530
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.9077286124229431,
+      "learning_rate": 0.00012198922211075778,
+      "loss": 0.353,
+      "step": 540
+    },
+    {
+      "epoch": 2.4774774774774775,
+      "grad_norm": 0.9107437133789062,
+      "learning_rate": 0.00011891108829779165,
+      "loss": 0.3531,
+      "step": 550
+    },
+    {
+      "epoch": 2.5225225225225225,
+      "grad_norm": 1.1385325193405151,
+      "learning_rate": 0.0001158142541449341,
+      "loss": 0.3695,
+      "step": 560
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.9225629568099976,
+      "learning_rate": 0.00011270178197468789,
+      "loss": 0.3606,
+      "step": 570
+    },
+    {
+      "epoch": 2.6126126126126126,
+      "grad_norm": 0.6338076591491699,
+      "learning_rate": 0.00010957674957330042,
+      "loss": 0.312,
+      "step": 580
+    },
+    {
+      "epoch": 2.6576576576576576,
+      "grad_norm": 1.3998136520385742,
+      "learning_rate": 0.00010644224714727681,
+      "loss": 0.4027,
+      "step": 590
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.598822832107544,
+      "learning_rate": 0.00010330137426761135,
+      "loss": 0.3496,
+      "step": 600
+    },
+    {
+      "epoch": 2.7477477477477477,
+      "grad_norm": 0.9068642854690552,
+      "learning_rate": 0.00010015723680475846,
+      "loss": 0.3489,
+      "step": 610
+    },
+    {
+      "epoch": 2.7927927927927927,
+      "grad_norm": 0.4025176167488098,
+      "learning_rate": 9.70129438573747e-05,
+      "loss": 0.3296,
+      "step": 620
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.6708613634109497,
+      "learning_rate": 9.38716046778684e-05,
+      "loss": 0.3004,
+      "step": 630
+    },
+    {
+      "epoch": 2.8828828828828827,
+      "grad_norm": 0.7858556509017944,
+      "learning_rate": 9.07363255977973e-05,
+      "loss": 0.3716,
+      "step": 640
+    },
+    {
+      "epoch": 2.9279279279279278,
+      "grad_norm": 0.6855165958404541,
+      "learning_rate": 8.76102069561545e-05,
+      "loss": 0.311,
+      "step": 650
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.6526620388031006,
+      "learning_rate": 8.449634003358022e-05,
+      "loss": 0.3488,
+      "step": 660
+    },
+    {
+      "epoch": 3.018018018018018,
+      "grad_norm": 0.3698066174983978,
+      "learning_rate": 8.13978039955308e-05,
+      "loss": 0.2858,
+      "step": 670
+    },
+    {
+      "epoch": 3.063063063063063,
+      "grad_norm": 0.8586738705635071,
+      "learning_rate": 7.831766284742807e-05,
+      "loss": 0.2565,
+      "step": 680
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.8718597292900085,
+      "learning_rate": 7.525896240479976e-05,
+      "loss": 0.2173,
+      "step": 690
+    },
+    {
+      "epoch": 3.153153153153153,
+      "grad_norm": 0.7671772241592407,
+      "learning_rate": 7.222472728140695e-05,
+      "loss": 0.2548,
+      "step": 700
+    },
+    {
+      "epoch": 3.1981981981981984,
+      "grad_norm": 1.2702572345733643,
+      "learning_rate": 6.921795789833723e-05,
+      "loss": 0.2638,
+      "step": 710
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 1.4898873567581177,
+      "learning_rate": 6.624162751702076e-05,
+      "loss": 0.2623,
+      "step": 720
+    },
+    {
+      "epoch": 3.2882882882882885,
+      "grad_norm": 1.0137726068496704,
+      "learning_rate": 6.329867929910347e-05,
+      "loss": 0.2938,
+      "step": 730
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.9631416201591492,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 0.2443,
+      "step": 740
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.8912140130996704,
+      "learning_rate": 5.752453407159522e-05,
+      "loss": 0.2359,
+      "step": 750
+    },
+    {
+      "epoch": 3.4234234234234235,
+      "grad_norm": 0.9686083793640137,
+      "learning_rate": 5.469904685916861e-05,
+      "loss": 0.2465,
+      "step": 760
+    },
+    {
+      "epoch": 3.4684684684684686,
+      "grad_norm": 1.942658543586731,
+      "learning_rate": 5.191835575830352e-05,
+      "loss": 0.3042,
+      "step": 770
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 1.2755067348480225,
+      "learning_rate": 4.918521047160308e-05,
+      "loss": 0.2885,
+      "step": 780
+    },
+    {
+      "epoch": 3.5585585585585586,
+      "grad_norm": 0.8992679715156555,
+      "learning_rate": 4.650231368571486e-05,
+      "loss": 0.2728,
+      "step": 790
+    },
+    {
+      "epoch": 3.6036036036036037,
+      "grad_norm": 2.1154401302337646,
+      "learning_rate": 4.387231839876349e-05,
+      "loss": 0.258,
+      "step": 800
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.6957826018333435,
+      "learning_rate": 4.129782529691815e-05,
+      "loss": 0.3219,
+      "step": 810
+    },
+    {
+      "epoch": 3.6936936936936937,
+      "grad_norm": 0.8093072175979614,
+      "learning_rate": 3.878138018268866e-05,
+      "loss": 0.2318,
+      "step": 820
+    },
+    {
+      "epoch": 3.7387387387387387,
+      "grad_norm": 0.900164008140564,
+      "learning_rate": 3.632547145749395e-05,
+      "loss": 0.3025,
+      "step": 830
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 1.3732051849365234,
+      "learning_rate": 3.393252766099187e-05,
+      "loss": 0.2744,
+      "step": 840
+    },
+    {
+      "epoch": 3.828828828828829,
+      "grad_norm": 1.3438997268676758,
+      "learning_rate": 3.1604915069603436e-05,
+      "loss": 0.2663,
+      "step": 850
+    },
+    {
+      "epoch": 3.873873873873874,
+      "grad_norm": 0.7277224063873291,
+      "learning_rate": 2.9344935356606773e-05,
+      "loss": 0.2058,
+      "step": 860
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.9671199321746826,
+      "learning_rate": 2.7154823316113932e-05,
+      "loss": 0.2466,
+      "step": 870
+    },
+    {
+      "epoch": 3.963963963963964,
+      "grad_norm": 1.0856068134307861,
+      "learning_rate": 2.5036744653181753e-05,
+      "loss": 0.2695,
+      "step": 880
+    },
+    {
+      "epoch": 4.009009009009009,
+      "grad_norm": 0.7191686034202576,
+      "learning_rate": 2.29927938422419e-05,
+      "loss": 0.2252,
+      "step": 890
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 0.9094095826148987,
+      "learning_rate": 2.102499205596743e-05,
+      "loss": 0.2067,
+      "step": 900
+    },
+    {
+      "epoch": 4.099099099099099,
+      "grad_norm": 1.2016669511795044,
+      "learning_rate": 1.913528516662452e-05,
+      "loss": 0.2165,
+      "step": 910
+    },
+    {
+      "epoch": 4.1441441441441444,
+      "grad_norm": 1.6922552585601807,
+      "learning_rate": 1.7325541821885384e-05,
+      "loss": 0.2102,
+      "step": 920
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 1.52359139919281,
+      "learning_rate": 1.5597551597004966e-05,
+      "loss": 0.1765,
+      "step": 930
+    },
+    {
+      "epoch": 4.2342342342342345,
+      "grad_norm": 1.333765983581543,
+      "learning_rate": 1.3953023225189243e-05,
+      "loss": 0.2147,
+      "step": 940
+    },
+    {
+      "epoch": 4.2792792792792795,
+      "grad_norm": 0.9832772016525269,
+      "learning_rate": 1.23935829079042e-05,
+      "loss": 0.2068,
+      "step": 950
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.7258216738700867,
+      "learning_rate": 1.0920772706797167e-05,
+      "loss": 0.1884,
+      "step": 960
+    },
+    {
+      "epoch": 4.36936936936937,
+      "grad_norm": 1.0229756832122803,
+      "learning_rate": 9.536049018820192e-06,
+      "loss": 0.2135,
+      "step": 970
+    },
+    {
+      "epoch": 4.414414414414415,
+      "grad_norm": 1.0085179805755615,
+      "learning_rate": 8.240781136063346e-06,
+      "loss": 0.1831,
+      "step": 980
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 0.7446288466453552,
+      "learning_rate": 7.03624989172228e-06,
+      "loss": 0.198,
+      "step": 990
+    },
+    {
+      "epoch": 4.504504504504505,
+      "grad_norm": 0.8291650414466858,
+      "learning_rate": 5.9236463935389065e-06,
+      "loss": 0.2189,
+      "step": 1000
+    },
+    {
+      "epoch": 4.504504504504505,
+      "eval_loss": 0.9809222221374512,
+      "eval_runtime": 10.6739,
+      "eval_samples_per_second": 35.039,
+      "eval_steps_per_second": 4.403,
+      "step": 1000
+    },
+    {
+      "epoch": 4.54954954954955,
+      "grad_norm": 1.1298563480377197,
+      "learning_rate": 4.904070845967468e-06,
+      "loss": 0.1889,
+      "step": 1010
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 1.0232703685760498,
+      "learning_rate": 3.9785314622310495e-06,
+      "loss": 0.1891,
+      "step": 1020
+    },
+    {
+      "epoch": 4.63963963963964,
+      "grad_norm": 1.2712104320526123,
+      "learning_rate": 3.1479434673440167e-06,
+      "loss": 0.1879,
+      "step": 1030
+    },
+    {
+      "epoch": 4.684684684684685,
+      "grad_norm": 1.564489722251892,
+      "learning_rate": 2.4131281930864002e-06,
+      "loss": 0.1972,
+      "step": 1040
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 1.4100459814071655,
+      "learning_rate": 1.7748122658251876e-06,
+      "loss": 0.201,
+      "step": 1050
+    },
+    {
+      "epoch": 4.774774774774775,
+      "grad_norm": 1.3149417638778687,
+      "learning_rate": 1.2336268879856727e-06,
+      "loss": 0.1876,
+      "step": 1060
+    },
+    {
+      "epoch": 4.81981981981982,
+      "grad_norm": 0.8505904674530029,
+      "learning_rate": 7.901072138831511e-07,
+      "loss": 0.1722,
+      "step": 1070
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 2.1957037448883057,
+      "learning_rate": 4.44691820532539e-07,
+      "loss": 0.1917,
+      "step": 1080
+    },
+    {
+      "epoch": 4.90990990990991,
+      "grad_norm": 1.9867583513259888,
+      "learning_rate": 1.977222739588891e-07,
+      "loss": 0.2082,
+      "step": 1090
+    },
+    {
+      "epoch": 4.954954954954955,
+      "grad_norm": 1.539480447769165,
+      "learning_rate": 4.9442791437848136e-08,
+      "loss": 0.2052,
+      "step": 1100
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6789027452468872,
+      "learning_rate": 0.0,
+      "loss": 0.197,
+      "step": 1110
+    },
+    {
+      "epoch": 5.0,
+      "step": 1110,
+      "total_flos": 1.01086802968209e+18,
+      "train_loss": 0.36593411194311604,
+      "train_runtime": 2755.6936,
+      "train_samples_per_second": 12.872,
+      "train_steps_per_second": 0.403
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.01086802968209e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

science_literature/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb3e563f1c3231df77b046eb3291b4a6a65e0565d6175f18d015a67a45f55ef
+size 5496