Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,5 @@ checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 my-model.F16.gguf filter=lfs diff=lfs merge=lfs -text
 my-model.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-590/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -33,12 +33,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
     "o_proj",
+    "k_proj",
     "v_proj",
     "up_proj",
     "down_proj",
+    "gate_proj",
     "q_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c1df6dcbf3b9a671c865ed4b00349d402b865ff2997448734180110541bdf4
+oid sha256:b37f718f2ceed7ae6002cd4d4ca4d0f15f032a9a674f0802ec8267f4a5bd0556
 size 332316480

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-2-2b-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-2-2b-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma2ForCausalLM",
+    "parent_library": "transformers.models.gemma2.modeling_gemma2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-2-2b-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b042466ca646d31cafe1de3931e09d17e9a740101ca0ff328f3479c9bab96c6
+size 332316480

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de19b9d5540647915693162769adea8fbd69b96e96bfc0f67639e112b8eafada
+size 664842070

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448594757d6de5d1e88c4f56dc0f856ce5b411ae6f4a9716f1743b750f7387d1
+size 14244

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
+size 988

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25be7dc9bb0a13f98a31019ff13235abfbbd39604b8155906e0d987c8ec44966
+size 1064

checkpoint-500/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
+  }
+}

checkpoint-500/tokenizer.json

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

checkpoint-500/tokenizer.model

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,2014 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.476595744680852,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 1.7628610134124756,
+      "learning_rate": 8e-05,
+      "loss": 1.8622,
+      "step": 5
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 1.8386660814285278,
+      "learning_rate": 0.00018,
+      "loss": 0.9707,
+      "step": 10
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 1.295538067817688,
+      "learning_rate": 0.00019862068965517243,
+      "loss": 0.5712,
+      "step": 15
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.5233324766159058,
+      "learning_rate": 0.00019689655172413795,
+      "loss": 0.4687,
+      "step": 20
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.7628127336502075,
+      "learning_rate": 0.00019517241379310345,
+      "loss": 0.5601,
+      "step": 25
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.5182906985282898,
+      "learning_rate": 0.00019344827586206898,
+      "loss": 0.4466,
+      "step": 30
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.3616418242454529,
+      "learning_rate": 0.0001917241379310345,
+      "loss": 0.5812,
+      "step": 35
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.48968932032585144,
+      "learning_rate": 0.00019,
+      "loss": 0.3477,
+      "step": 40
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.8994768261909485,
+      "learning_rate": 0.00018827586206896554,
+      "loss": 0.3383,
+      "step": 45
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.387116402387619,
+      "learning_rate": 0.00018655172413793104,
+      "loss": 0.4003,
+      "step": 50
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.8058916926383972,
+      "learning_rate": 0.00018482758620689654,
+      "loss": 0.3992,
+      "step": 55
+    },
+    {
+      "epoch": 1.0170212765957447,
+      "grad_norm": 0.4688344895839691,
+      "learning_rate": 0.00018310344827586207,
+      "loss": 0.3998,
+      "step": 60
+    },
+    {
+      "epoch": 1.102127659574468,
+      "grad_norm": 0.5960966944694519,
+      "learning_rate": 0.0001813793103448276,
+      "loss": 0.2818,
+      "step": 65
+    },
+    {
+      "epoch": 1.1872340425531915,
+      "grad_norm": 0.49853241443634033,
+      "learning_rate": 0.0001796551724137931,
+      "loss": 0.2186,
+      "step": 70
+    },
+    {
+      "epoch": 1.2723404255319148,
+      "grad_norm": 0.521017849445343,
+      "learning_rate": 0.00017793103448275862,
+      "loss": 0.322,
+      "step": 75
+    },
+    {
+      "epoch": 1.3574468085106384,
+      "grad_norm": 0.35342177748680115,
+      "learning_rate": 0.00017620689655172415,
+      "loss": 0.1905,
+      "step": 80
+    },
+    {
+      "epoch": 1.4425531914893617,
+      "grad_norm": 0.37390947341918945,
+      "learning_rate": 0.00017448275862068965,
+      "loss": 0.2582,
+      "step": 85
+    },
+    {
+      "epoch": 1.527659574468085,
+      "grad_norm": 0.42308491468429565,
+      "learning_rate": 0.00017275862068965518,
+      "loss": 0.2337,
+      "step": 90
+    },
+    {
+      "epoch": 1.6127659574468085,
+      "grad_norm": 0.8888659477233887,
+      "learning_rate": 0.0001710344827586207,
+      "loss": 0.2465,
+      "step": 95
+    },
+    {
+      "epoch": 1.697872340425532,
+      "grad_norm": 0.40344128012657166,
+      "learning_rate": 0.0001693103448275862,
+      "loss": 0.2591,
+      "step": 100
+    },
+    {
+      "epoch": 1.7829787234042553,
+      "grad_norm": 0.45671504735946655,
+      "learning_rate": 0.00016758620689655173,
+      "loss": 0.2269,
+      "step": 105
+    },
+    {
+      "epoch": 1.8680851063829786,
+      "grad_norm": 0.4616524577140808,
+      "learning_rate": 0.00016586206896551726,
+      "loss": 0.2033,
+      "step": 110
+    },
+    {
+      "epoch": 1.9531914893617022,
+      "grad_norm": 0.4471171200275421,
+      "learning_rate": 0.00016413793103448276,
+      "loss": 0.266,
+      "step": 115
+    },
+    {
+      "epoch": 2.0340425531914894,
+      "grad_norm": 0.7043401002883911,
+      "learning_rate": 0.0001624137931034483,
+      "loss": 0.1607,
+      "step": 120
+    },
+    {
+      "epoch": 2.119148936170213,
+      "grad_norm": 0.4361288845539093,
+      "learning_rate": 0.00016068965517241382,
+      "loss": 0.1493,
+      "step": 125
+    },
+    {
+      "epoch": 2.204255319148936,
+      "grad_norm": 0.45557570457458496,
+      "learning_rate": 0.00015896551724137932,
+      "loss": 0.1011,
+      "step": 130
+    },
+    {
+      "epoch": 2.2893617021276595,
+      "grad_norm": 0.3149248957633972,
+      "learning_rate": 0.00015724137931034485,
+      "loss": 0.1112,
+      "step": 135
+    },
+    {
+      "epoch": 2.374468085106383,
+      "grad_norm": 0.2783677279949188,
+      "learning_rate": 0.00015551724137931037,
+      "loss": 0.1278,
+      "step": 140
+    },
+    {
+      "epoch": 2.4595744680851066,
+      "grad_norm": 0.46953991055488586,
+      "learning_rate": 0.00015379310344827587,
+      "loss": 0.1157,
+      "step": 145
+    },
+    {
+      "epoch": 2.5446808510638297,
+      "grad_norm": 0.5183996558189392,
+      "learning_rate": 0.0001520689655172414,
+      "loss": 0.107,
+      "step": 150
+    },
+    {
+      "epoch": 2.629787234042553,
+      "grad_norm": 0.46928611397743225,
+      "learning_rate": 0.0001503448275862069,
+      "loss": 0.12,
+      "step": 155
+    },
+    {
+      "epoch": 2.7148936170212767,
+      "grad_norm": 0.4748971462249756,
+      "learning_rate": 0.00014862068965517243,
+      "loss": 0.1406,
+      "step": 160
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.7183696627616882,
+      "learning_rate": 0.00014689655172413793,
+      "loss": 0.1533,
+      "step": 165
+    },
+    {
+      "epoch": 2.8851063829787233,
+      "grad_norm": 0.575391948223114,
+      "learning_rate": 0.00014517241379310346,
+      "loss": 0.1365,
+      "step": 170
+    },
+    {
+      "epoch": 2.970212765957447,
+      "grad_norm": 0.33236995339393616,
+      "learning_rate": 0.00014344827586206896,
+      "loss": 0.1369,
+      "step": 175
+    },
+    {
+      "epoch": 3.051063829787234,
+      "grad_norm": 0.17017032206058502,
+      "learning_rate": 0.0001417241379310345,
+      "loss": 0.093,
+      "step": 180
+    },
+    {
+      "epoch": 3.1361702127659576,
+      "grad_norm": 0.8167087435722351,
+      "learning_rate": 0.00014,
+      "loss": 0.1297,
+      "step": 185
+    },
+    {
+      "epoch": 3.2212765957446807,
+      "grad_norm": 0.4695407748222351,
+      "learning_rate": 0.00013827586206896552,
+      "loss": 0.0794,
+      "step": 190
+    },
+    {
+      "epoch": 3.3063829787234043,
+      "grad_norm": 0.46323472261428833,
+      "learning_rate": 0.00013655172413793104,
+      "loss": 0.0909,
+      "step": 195
+    },
+    {
+      "epoch": 3.391489361702128,
+      "grad_norm": 0.4290667772293091,
+      "learning_rate": 0.00013482758620689654,
+      "loss": 0.0728,
+      "step": 200
+    },
+    {
+      "epoch": 3.476595744680851,
+      "grad_norm": 0.3602962791919708,
+      "learning_rate": 0.00013310344827586207,
+      "loss": 0.0713,
+      "step": 205
+    },
+    {
+      "epoch": 3.5617021276595744,
+      "grad_norm": 0.3129134476184845,
+      "learning_rate": 0.0001313793103448276,
+      "loss": 0.0878,
+      "step": 210
+    },
+    {
+      "epoch": 3.646808510638298,
+      "grad_norm": 0.4205905795097351,
+      "learning_rate": 0.0001296551724137931,
+      "loss": 0.0815,
+      "step": 215
+    },
+    {
+      "epoch": 3.731914893617021,
+      "grad_norm": 0.47979313135147095,
+      "learning_rate": 0.00012793103448275863,
+      "loss": 0.0696,
+      "step": 220
+    },
+    {
+      "epoch": 3.8170212765957445,
+      "grad_norm": 0.4063044786453247,
+      "learning_rate": 0.00012620689655172415,
+      "loss": 0.0661,
+      "step": 225
+    },
+    {
+      "epoch": 3.902127659574468,
+      "grad_norm": 0.363741934299469,
+      "learning_rate": 0.00012448275862068966,
+      "loss": 0.0972,
+      "step": 230
+    },
+    {
+      "epoch": 3.9872340425531916,
+      "grad_norm": 0.2973483204841614,
+      "learning_rate": 0.00012275862068965518,
+      "loss": 0.0807,
+      "step": 235
+    },
+    {
+      "epoch": 4.068085106382979,
+      "grad_norm": 0.481488436460495,
+      "learning_rate": 0.00012103448275862071,
+      "loss": 0.0678,
+      "step": 240
+    },
+    {
+      "epoch": 4.153191489361702,
+      "grad_norm": 0.18169716000556946,
+      "learning_rate": 0.00011931034482758621,
+      "loss": 0.0555,
+      "step": 245
+    },
+    {
+      "epoch": 4.238297872340426,
+      "grad_norm": 0.3210119307041168,
+      "learning_rate": 0.00011758620689655173,
+      "loss": 0.0506,
+      "step": 250
+    },
+    {
+      "epoch": 4.323404255319149,
+      "grad_norm": 0.3670145273208618,
+      "learning_rate": 0.00011586206896551725,
+      "loss": 0.0685,
+      "step": 255
+    },
+    {
+      "epoch": 4.408510638297872,
+      "grad_norm": 0.2257293462753296,
+      "learning_rate": 0.00011413793103448275,
+      "loss": 0.0592,
+      "step": 260
+    },
+    {
+      "epoch": 4.493617021276596,
+      "grad_norm": 0.16985096037387848,
+      "learning_rate": 0.00011241379310344828,
+      "loss": 0.0745,
+      "step": 265
+    },
+    {
+      "epoch": 4.578723404255319,
+      "grad_norm": 0.31408607959747314,
+      "learning_rate": 0.00011068965517241381,
+      "loss": 0.0866,
+      "step": 270
+    },
+    {
+      "epoch": 4.663829787234042,
+      "grad_norm": 0.2598167657852173,
+      "learning_rate": 0.00010896551724137931,
+      "loss": 0.0494,
+      "step": 275
+    },
+    {
+      "epoch": 4.748936170212766,
+      "grad_norm": 0.4023381471633911,
+      "learning_rate": 0.00010724137931034484,
+      "loss": 0.0632,
+      "step": 280
+    },
+    {
+      "epoch": 4.834042553191489,
+      "grad_norm": 0.24716579914093018,
+      "learning_rate": 0.00010551724137931037,
+      "loss": 0.0499,
+      "step": 285
+    },
+    {
+      "epoch": 4.919148936170213,
+      "grad_norm": 0.39397132396698,
+      "learning_rate": 0.00010379310344827587,
+      "loss": 0.0575,
+      "step": 290
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09666766971349716,
+      "learning_rate": 0.0001020689655172414,
+      "loss": 0.0609,
+      "step": 295
+    },
+    {
+      "epoch": 5.085106382978723,
+      "grad_norm": 0.1626937985420227,
+      "learning_rate": 0.0001003448275862069,
+      "loss": 0.0455,
+      "step": 300
+    },
+    {
+      "epoch": 5.170212765957447,
+      "grad_norm": 0.2916521728038788,
+      "learning_rate": 9.862068965517242e-05,
+      "loss": 0.0437,
+      "step": 305
+    },
+    {
+      "epoch": 5.25531914893617,
+      "grad_norm": 0.3213741183280945,
+      "learning_rate": 9.689655172413794e-05,
+      "loss": 0.0509,
+      "step": 310
+    },
+    {
+      "epoch": 5.340425531914893,
+      "grad_norm": 0.25438761711120605,
+      "learning_rate": 9.517241379310345e-05,
+      "loss": 0.0483,
+      "step": 315
+    },
+    {
+      "epoch": 5.425531914893617,
+      "grad_norm": 0.35173889994621277,
+      "learning_rate": 9.344827586206896e-05,
+      "loss": 0.0394,
+      "step": 320
+    },
+    {
+      "epoch": 5.51063829787234,
+      "grad_norm": 0.2214491218328476,
+      "learning_rate": 9.172413793103448e-05,
+      "loss": 0.0615,
+      "step": 325
+    },
+    {
+      "epoch": 5.595744680851064,
+      "grad_norm": 0.1461336314678192,
+      "learning_rate": 9e-05,
+      "loss": 0.0552,
+      "step": 330
+    },
+    {
+      "epoch": 5.680851063829787,
+      "grad_norm": 0.2651642858982086,
+      "learning_rate": 8.827586206896552e-05,
+      "loss": 0.0417,
+      "step": 335
+    },
+    {
+      "epoch": 5.76595744680851,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 8.655172413793103e-05,
+      "loss": 0.0502,
+      "step": 340
+    },
+    {
+      "epoch": 5.851063829787234,
+      "grad_norm": 0.19299010932445526,
+      "learning_rate": 8.482758620689656e-05,
+      "loss": 0.044,
+      "step": 345
+    },
+    {
+      "epoch": 5.9361702127659575,
+      "grad_norm": 0.120607890188694,
+      "learning_rate": 8.310344827586208e-05,
+      "loss": 0.0407,
+      "step": 350
+    },
+    {
+      "epoch": 6.017021276595744,
+      "grad_norm": 0.13520629703998566,
+      "learning_rate": 8.137931034482759e-05,
+      "loss": 0.0512,
+      "step": 355
+    },
+    {
+      "epoch": 6.102127659574468,
+      "grad_norm": 0.20564086735248566,
+      "learning_rate": 7.965517241379312e-05,
+      "loss": 0.0416,
+      "step": 360
+    },
+    {
+      "epoch": 6.187234042553191,
+      "grad_norm": 0.115450419485569,
+      "learning_rate": 7.793103448275862e-05,
+      "loss": 0.0424,
+      "step": 365
+    },
+    {
+      "epoch": 6.272340425531915,
+      "grad_norm": 0.1926778256893158,
+      "learning_rate": 7.620689655172413e-05,
+      "loss": 0.0378,
+      "step": 370
+    },
+    {
+      "epoch": 6.357446808510638,
+      "grad_norm": 0.25700807571411133,
+      "learning_rate": 7.448275862068966e-05,
+      "loss": 0.0453,
+      "step": 375
+    },
+    {
+      "epoch": 6.4425531914893615,
+      "grad_norm": 0.10704706609249115,
+      "learning_rate": 7.275862068965517e-05,
+      "loss": 0.0323,
+      "step": 380
+    },
+    {
+      "epoch": 6.527659574468085,
+      "grad_norm": 0.18126443028450012,
+      "learning_rate": 7.103448275862069e-05,
+      "loss": 0.0393,
+      "step": 385
+    },
+    {
+      "epoch": 6.6127659574468085,
+      "grad_norm": 0.13170169293880463,
+      "learning_rate": 6.931034482758622e-05,
+      "loss": 0.0458,
+      "step": 390
+    },
+    {
+      "epoch": 6.697872340425532,
+      "grad_norm": 0.10165558010339737,
+      "learning_rate": 6.758620689655173e-05,
+      "loss": 0.0359,
+      "step": 395
+    },
+    {
+      "epoch": 6.782978723404256,
+      "grad_norm": 0.20285525918006897,
+      "learning_rate": 6.586206896551724e-05,
+      "loss": 0.0411,
+      "step": 400
+    },
+    {
+      "epoch": 6.868085106382979,
+      "grad_norm": 0.17869718372821808,
+      "learning_rate": 6.413793103448276e-05,
+      "loss": 0.0454,
+      "step": 405
+    },
+    {
+      "epoch": 6.953191489361702,
+      "grad_norm": 0.1431434452533722,
+      "learning_rate": 6.241379310344829e-05,
+      "loss": 0.041,
+      "step": 410
+    },
+    {
+      "epoch": 7.034042553191489,
+      "grad_norm": 0.1481233537197113,
+      "learning_rate": 6.068965517241379e-05,
+      "loss": 0.0505,
+      "step": 415
+    },
+    {
+      "epoch": 7.1191489361702125,
+      "grad_norm": 0.10545721650123596,
+      "learning_rate": 5.896551724137931e-05,
+      "loss": 0.0361,
+      "step": 420
+    },
+    {
+      "epoch": 7.2042553191489365,
+      "grad_norm": 0.13733087480068207,
+      "learning_rate": 5.7241379310344835e-05,
+      "loss": 0.0361,
+      "step": 425
+    },
+    {
+      "epoch": 7.2893617021276595,
+      "grad_norm": 0.09701387584209442,
+      "learning_rate": 5.551724137931035e-05,
+      "loss": 0.0363,
+      "step": 430
+    },
+    {
+      "epoch": 7.374468085106383,
+      "grad_norm": 0.12478837370872498,
+      "learning_rate": 5.379310344827586e-05,
+      "loss": 0.0385,
+      "step": 435
+    },
+    {
+      "epoch": 7.459574468085107,
+      "grad_norm": 0.18108202517032623,
+      "learning_rate": 5.2068965517241384e-05,
+      "loss": 0.0307,
+      "step": 440
+    },
+    {
+      "epoch": 7.54468085106383,
+      "grad_norm": 0.1741178184747696,
+      "learning_rate": 5.03448275862069e-05,
+      "loss": 0.0349,
+      "step": 445
+    },
+    {
+      "epoch": 7.629787234042553,
+      "grad_norm": 0.18830710649490356,
+      "learning_rate": 4.862068965517241e-05,
+      "loss": 0.035,
+      "step": 450
+    },
+    {
+      "epoch": 7.714893617021277,
+      "grad_norm": 0.29267263412475586,
+      "learning_rate": 4.689655172413793e-05,
+      "loss": 0.0396,
+      "step": 455
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.1248115673661232,
+      "learning_rate": 4.5172413793103454e-05,
+      "loss": 0.0417,
+      "step": 460
+    },
+    {
+      "epoch": 7.885106382978723,
+      "grad_norm": 0.12826257944107056,
+      "learning_rate": 4.344827586206897e-05,
+      "loss": 0.0352,
+      "step": 465
+    },
+    {
+      "epoch": 7.970212765957447,
+      "grad_norm": 0.10185350477695465,
+      "learning_rate": 4.172413793103448e-05,
+      "loss": 0.0383,
+      "step": 470
+    },
+    {
+      "epoch": 8.051063829787234,
+      "grad_norm": 0.11523312330245972,
+      "learning_rate": 4e-05,
+      "loss": 0.0372,
+      "step": 475
+    },
+    {
+      "epoch": 8.136170212765958,
+      "grad_norm": 0.07264875620603561,
+      "learning_rate": 3.827586206896552e-05,
+      "loss": 0.0291,
+      "step": 480
+    },
+    {
+      "epoch": 8.221276595744682,
+      "grad_norm": 0.1880428045988083,
+      "learning_rate": 3.655172413793104e-05,
+      "loss": 0.029,
+      "step": 485
+    },
+    {
+      "epoch": 8.306382978723404,
+      "grad_norm": 0.19860832393169403,
+      "learning_rate": 3.482758620689655e-05,
+      "loss": 0.0298,
+      "step": 490
+    },
+    {
+      "epoch": 8.391489361702128,
+      "grad_norm": 0.1690095216035843,
+      "learning_rate": 3.310344827586207e-05,
+      "loss": 0.0371,
+      "step": 495
+    },
+    {
+      "epoch": 8.476595744680852,
+      "grad_norm": 0.171220064163208,
+      "learning_rate": 3.137931034482759e-05,
+      "loss": 0.0294,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.720005906851533e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb339cf1e256f09d287949096640e324e00ba969d1a72f017e68213fc1d4fa6
+size 5752

checkpoint-590/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-2-2b-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-2-2b-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-590/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma2ForCausalLM",
+    "parent_library": "transformers.models.gemma2.modeling_gemma2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-2-2b-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-590/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37f718f2ceed7ae6002cd4d4ca4d0f15f032a9a674f0802ec8267f4a5bd0556
+size 332316480

checkpoint-590/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763e183b23f53705dd5af33307e089b5f523c42971866ad9e4b06155f967a8b4
+size 664842070

checkpoint-590/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc46ebdf2786cf45a03ecdc2890904fdbf8f1b3e4c6aa053d7e714f2d7a72b2b
+size 14244

checkpoint-590/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748bbb62b94974a356dbe301fc73c8ffae7bdea31898ca54f31e03ce0b7673d7
+size 988

checkpoint-590/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5991c7d8be9ac14c559fb815818f27223800c50ca05686c7cdc2aa15d733ee8c
+size 1064

checkpoint-590/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
+  }
+}

checkpoint-590/tokenizer.json

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

checkpoint-590/tokenizer.model

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

checkpoint-590/tokenizer_config.json

@@ -0,0 +1,2014 @@
+{
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-590/trainer_state.json

@@ -0,0 +1,860 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 590,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 1.7628610134124756,
+      "learning_rate": 8e-05,
+      "loss": 1.8622,
+      "step": 5
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 1.8386660814285278,
+      "learning_rate": 0.00018,
+      "loss": 0.9707,
+      "step": 10
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 1.295538067817688,
+      "learning_rate": 0.00019862068965517243,
+      "loss": 0.5712,
+      "step": 15
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.5233324766159058,
+      "learning_rate": 0.00019689655172413795,
+      "loss": 0.4687,
+      "step": 20
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.7628127336502075,
+      "learning_rate": 0.00019517241379310345,
+      "loss": 0.5601,
+      "step": 25
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.5182906985282898,
+      "learning_rate": 0.00019344827586206898,
+      "loss": 0.4466,
+      "step": 30
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.3616418242454529,
+      "learning_rate": 0.0001917241379310345,
+      "loss": 0.5812,
+      "step": 35
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.48968932032585144,
+      "learning_rate": 0.00019,
+      "loss": 0.3477,
+      "step": 40
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.8994768261909485,
+      "learning_rate": 0.00018827586206896554,
+      "loss": 0.3383,
+      "step": 45
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.387116402387619,
+      "learning_rate": 0.00018655172413793104,
+      "loss": 0.4003,
+      "step": 50
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.8058916926383972,
+      "learning_rate": 0.00018482758620689654,
+      "loss": 0.3992,
+      "step": 55
+    },
+    {
+      "epoch": 1.0170212765957447,
+      "grad_norm": 0.4688344895839691,
+      "learning_rate": 0.00018310344827586207,
+      "loss": 0.3998,
+      "step": 60
+    },
+    {
+      "epoch": 1.102127659574468,
+      "grad_norm": 0.5960966944694519,
+      "learning_rate": 0.0001813793103448276,
+      "loss": 0.2818,
+      "step": 65
+    },
+    {
+      "epoch": 1.1872340425531915,
+      "grad_norm": 0.49853241443634033,
+      "learning_rate": 0.0001796551724137931,
+      "loss": 0.2186,
+      "step": 70
+    },
+    {
+      "epoch": 1.2723404255319148,
+      "grad_norm": 0.521017849445343,
+      "learning_rate": 0.00017793103448275862,
+      "loss": 0.322,
+      "step": 75
+    },
+    {
+      "epoch": 1.3574468085106384,
+      "grad_norm": 0.35342177748680115,
+      "learning_rate": 0.00017620689655172415,
+      "loss": 0.1905,
+      "step": 80
+    },
+    {
+      "epoch": 1.4425531914893617,
+      "grad_norm": 0.37390947341918945,
+      "learning_rate": 0.00017448275862068965,
+      "loss": 0.2582,
+      "step": 85
+    },
+    {
+      "epoch": 1.527659574468085,
+      "grad_norm": 0.42308491468429565,
+      "learning_rate": 0.00017275862068965518,
+      "loss": 0.2337,
+      "step": 90
+    },
+    {
+      "epoch": 1.6127659574468085,
+      "grad_norm": 0.8888659477233887,
+      "learning_rate": 0.0001710344827586207,
+      "loss": 0.2465,
+      "step": 95
+    },
+    {
+      "epoch": 1.697872340425532,
+      "grad_norm": 0.40344128012657166,
+      "learning_rate": 0.0001693103448275862,
+      "loss": 0.2591,
+      "step": 100
+    },
+    {
+      "epoch": 1.7829787234042553,
+      "grad_norm": 0.45671504735946655,
+      "learning_rate": 0.00016758620689655173,
+      "loss": 0.2269,
+      "step": 105
+    },
+    {
+      "epoch": 1.8680851063829786,
+      "grad_norm": 0.4616524577140808,
+      "learning_rate": 0.00016586206896551726,
+      "loss": 0.2033,
+      "step": 110
+    },
+    {
+      "epoch": 1.9531914893617022,
+      "grad_norm": 0.4471171200275421,
+      "learning_rate": 0.00016413793103448276,
+      "loss": 0.266,
+      "step": 115
+    },
+    {
+      "epoch": 2.0340425531914894,
+      "grad_norm": 0.7043401002883911,
+      "learning_rate": 0.0001624137931034483,
+      "loss": 0.1607,
+      "step": 120
+    },
+    {
+      "epoch": 2.119148936170213,
+      "grad_norm": 0.4361288845539093,
+      "learning_rate": 0.00016068965517241382,
+      "loss": 0.1493,
+      "step": 125
+    },
+    {
+      "epoch": 2.204255319148936,
+      "grad_norm": 0.45557570457458496,
+      "learning_rate": 0.00015896551724137932,
+      "loss": 0.1011,
+      "step": 130
+    },
+    {
+      "epoch": 2.2893617021276595,
+      "grad_norm": 0.3149248957633972,
+      "learning_rate": 0.00015724137931034485,
+      "loss": 0.1112,
+      "step": 135
+    },
+    {
+      "epoch": 2.374468085106383,
+      "grad_norm": 0.2783677279949188,
+      "learning_rate": 0.00015551724137931037,
+      "loss": 0.1278,
+      "step": 140
+    },
+    {
+      "epoch": 2.4595744680851066,
+      "grad_norm": 0.46953991055488586,
+      "learning_rate": 0.00015379310344827587,
+      "loss": 0.1157,
+      "step": 145
+    },
+    {
+      "epoch": 2.5446808510638297,
+      "grad_norm": 0.5183996558189392,
+      "learning_rate": 0.0001520689655172414,
+      "loss": 0.107,
+      "step": 150
+    },
+    {
+      "epoch": 2.629787234042553,
+      "grad_norm": 0.46928611397743225,
+      "learning_rate": 0.0001503448275862069,
+      "loss": 0.12,
+      "step": 155
+    },
+    {
+      "epoch": 2.7148936170212767,
+      "grad_norm": 0.4748971462249756,
+      "learning_rate": 0.00014862068965517243,
+      "loss": 0.1406,
+      "step": 160
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.7183696627616882,
+      "learning_rate": 0.00014689655172413793,
+      "loss": 0.1533,
+      "step": 165
+    },
+    {
+      "epoch": 2.8851063829787233,
+      "grad_norm": 0.575391948223114,
+      "learning_rate": 0.00014517241379310346,
+      "loss": 0.1365,
+      "step": 170
+    },
+    {
+      "epoch": 2.970212765957447,
+      "grad_norm": 0.33236995339393616,
+      "learning_rate": 0.00014344827586206896,
+      "loss": 0.1369,
+      "step": 175
+    },
+    {
+      "epoch": 3.051063829787234,
+      "grad_norm": 0.17017032206058502,
+      "learning_rate": 0.0001417241379310345,
+      "loss": 0.093,
+      "step": 180
+    },
+    {
+      "epoch": 3.1361702127659576,
+      "grad_norm": 0.8167087435722351,
+      "learning_rate": 0.00014,
+      "loss": 0.1297,
+      "step": 185
+    },
+    {
+      "epoch": 3.2212765957446807,
+      "grad_norm": 0.4695407748222351,
+      "learning_rate": 0.00013827586206896552,
+      "loss": 0.0794,
+      "step": 190
+    },
+    {
+      "epoch": 3.3063829787234043,
+      "grad_norm": 0.46323472261428833,
+      "learning_rate": 0.00013655172413793104,
+      "loss": 0.0909,
+      "step": 195
+    },
+    {
+      "epoch": 3.391489361702128,
+      "grad_norm": 0.4290667772293091,
+      "learning_rate": 0.00013482758620689654,
+      "loss": 0.0728,
+      "step": 200
+    },
+    {
+      "epoch": 3.476595744680851,
+      "grad_norm": 0.3602962791919708,
+      "learning_rate": 0.00013310344827586207,
+      "loss": 0.0713,
+      "step": 205
+    },
+    {
+      "epoch": 3.5617021276595744,
+      "grad_norm": 0.3129134476184845,
+      "learning_rate": 0.0001313793103448276,
+      "loss": 0.0878,
+      "step": 210
+    },
+    {
+      "epoch": 3.646808510638298,
+      "grad_norm": 0.4205905795097351,
+      "learning_rate": 0.0001296551724137931,
+      "loss": 0.0815,
+      "step": 215
+    },
+    {
+      "epoch": 3.731914893617021,
+      "grad_norm": 0.47979313135147095,
+      "learning_rate": 0.00012793103448275863,
+      "loss": 0.0696,
+      "step": 220
+    },
+    {
+      "epoch": 3.8170212765957445,
+      "grad_norm": 0.4063044786453247,
+      "learning_rate": 0.00012620689655172415,
+      "loss": 0.0661,
+      "step": 225
+    },
+    {
+      "epoch": 3.902127659574468,
+      "grad_norm": 0.363741934299469,
+      "learning_rate": 0.00012448275862068966,
+      "loss": 0.0972,
+      "step": 230
+    },
+    {
+      "epoch": 3.9872340425531916,
+      "grad_norm": 0.2973483204841614,
+      "learning_rate": 0.00012275862068965518,
+      "loss": 0.0807,
+      "step": 235
+    },
+    {
+      "epoch": 4.068085106382979,
+      "grad_norm": 0.481488436460495,
+      "learning_rate": 0.00012103448275862071,
+      "loss": 0.0678,
+      "step": 240
+    },
+    {
+      "epoch": 4.153191489361702,
+      "grad_norm": 0.18169716000556946,
+      "learning_rate": 0.00011931034482758621,
+      "loss": 0.0555,
+      "step": 245
+    },
+    {
+      "epoch": 4.238297872340426,
+      "grad_norm": 0.3210119307041168,
+      "learning_rate": 0.00011758620689655173,
+      "loss": 0.0506,
+      "step": 250
+    },
+    {
+      "epoch": 4.323404255319149,
+      "grad_norm": 0.3670145273208618,
+      "learning_rate": 0.00011586206896551725,
+      "loss": 0.0685,
+      "step": 255
+    },
+    {
+      "epoch": 4.408510638297872,
+      "grad_norm": 0.2257293462753296,
+      "learning_rate": 0.00011413793103448275,
+      "loss": 0.0592,
+      "step": 260
+    },
+    {
+      "epoch": 4.493617021276596,
+      "grad_norm": 0.16985096037387848,
+      "learning_rate": 0.00011241379310344828,
+      "loss": 0.0745,
+      "step": 265
+    },
+    {
+      "epoch": 4.578723404255319,
+      "grad_norm": 0.31408607959747314,
+      "learning_rate": 0.00011068965517241381,
+      "loss": 0.0866,
+      "step": 270
+    },
+    {
+      "epoch": 4.663829787234042,
+      "grad_norm": 0.2598167657852173,
+      "learning_rate": 0.00010896551724137931,
+      "loss": 0.0494,
+      "step": 275
+    },
+    {
+      "epoch": 4.748936170212766,
+      "grad_norm": 0.4023381471633911,
+      "learning_rate": 0.00010724137931034484,
+      "loss": 0.0632,
+      "step": 280
+    },
+    {
+      "epoch": 4.834042553191489,
+      "grad_norm": 0.24716579914093018,
+      "learning_rate": 0.00010551724137931037,
+      "loss": 0.0499,
+      "step": 285
+    },
+    {
+      "epoch": 4.919148936170213,
+      "grad_norm": 0.39397132396698,
+      "learning_rate": 0.00010379310344827587,
+      "loss": 0.0575,
+      "step": 290
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09666766971349716,
+      "learning_rate": 0.0001020689655172414,
+      "loss": 0.0609,
+      "step": 295
+    },
+    {
+      "epoch": 5.085106382978723,
+      "grad_norm": 0.1626937985420227,
+      "learning_rate": 0.0001003448275862069,
+      "loss": 0.0455,
+      "step": 300
+    },
+    {
+      "epoch": 5.170212765957447,
+      "grad_norm": 0.2916521728038788,
+      "learning_rate": 9.862068965517242e-05,
+      "loss": 0.0437,
+      "step": 305
+    },
+    {
+      "epoch": 5.25531914893617,
+      "grad_norm": 0.3213741183280945,
+      "learning_rate": 9.689655172413794e-05,
+      "loss": 0.0509,
+      "step": 310
+    },
+    {
+      "epoch": 5.340425531914893,
+      "grad_norm": 0.25438761711120605,
+      "learning_rate": 9.517241379310345e-05,
+      "loss": 0.0483,
+      "step": 315
+    },
+    {
+      "epoch": 5.425531914893617,
+      "grad_norm": 0.35173889994621277,
+      "learning_rate": 9.344827586206896e-05,
+      "loss": 0.0394,
+      "step": 320
+    },
+    {
+      "epoch": 5.51063829787234,
+      "grad_norm": 0.2214491218328476,
+      "learning_rate": 9.172413793103448e-05,
+      "loss": 0.0615,
+      "step": 325
+    },
+    {
+      "epoch": 5.595744680851064,
+      "grad_norm": 0.1461336314678192,
+      "learning_rate": 9e-05,
+      "loss": 0.0552,
+      "step": 330
+    },
+    {
+      "epoch": 5.680851063829787,
+      "grad_norm": 0.2651642858982086,
+      "learning_rate": 8.827586206896552e-05,
+      "loss": 0.0417,
+      "step": 335
+    },
+    {
+      "epoch": 5.76595744680851,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 8.655172413793103e-05,
+      "loss": 0.0502,
+      "step": 340
+    },
+    {
+      "epoch": 5.851063829787234,
+      "grad_norm": 0.19299010932445526,
+      "learning_rate": 8.482758620689656e-05,
+      "loss": 0.044,
+      "step": 345
+    },
+    {
+      "epoch": 5.9361702127659575,
+      "grad_norm": 0.120607890188694,
+      "learning_rate": 8.310344827586208e-05,
+      "loss": 0.0407,
+      "step": 350
+    },
+    {
+      "epoch": 6.017021276595744,
+      "grad_norm": 0.13520629703998566,
+      "learning_rate": 8.137931034482759e-05,
+      "loss": 0.0512,
+      "step": 355
+    },
+    {
+      "epoch": 6.102127659574468,
+      "grad_norm": 0.20564086735248566,
+      "learning_rate": 7.965517241379312e-05,
+      "loss": 0.0416,
+      "step": 360
+    },
+    {
+      "epoch": 6.187234042553191,
+      "grad_norm": 0.115450419485569,
+      "learning_rate": 7.793103448275862e-05,
+      "loss": 0.0424,
+      "step": 365
+    },
+    {
+      "epoch": 6.272340425531915,
+      "grad_norm": 0.1926778256893158,
+      "learning_rate": 7.620689655172413e-05,
+      "loss": 0.0378,
+      "step": 370
+    },
+    {
+      "epoch": 6.357446808510638,
+      "grad_norm": 0.25700807571411133,
+      "learning_rate": 7.448275862068966e-05,
+      "loss": 0.0453,
+      "step": 375
+    },
+    {
+      "epoch": 6.4425531914893615,
+      "grad_norm": 0.10704706609249115,
+      "learning_rate": 7.275862068965517e-05,
+      "loss": 0.0323,
+      "step": 380
+    },
+    {
+      "epoch": 6.527659574468085,
+      "grad_norm": 0.18126443028450012,
+      "learning_rate": 7.103448275862069e-05,
+      "loss": 0.0393,
+      "step": 385
+    },
+    {
+      "epoch": 6.6127659574468085,
+      "grad_norm": 0.13170169293880463,
+      "learning_rate": 6.931034482758622e-05,
+      "loss": 0.0458,
+      "step": 390
+    },
+    {
+      "epoch": 6.697872340425532,
+      "grad_norm": 0.10165558010339737,
+      "learning_rate": 6.758620689655173e-05,
+      "loss": 0.0359,
+      "step": 395
+    },
+    {
+      "epoch": 6.782978723404256,
+      "grad_norm": 0.20285525918006897,
+      "learning_rate": 6.586206896551724e-05,
+      "loss": 0.0411,
+      "step": 400
+    },
+    {
+      "epoch": 6.868085106382979,
+      "grad_norm": 0.17869718372821808,
+      "learning_rate": 6.413793103448276e-05,
+      "loss": 0.0454,
+      "step": 405
+    },
+    {
+      "epoch": 6.953191489361702,
+      "grad_norm": 0.1431434452533722,
+      "learning_rate": 6.241379310344829e-05,
+      "loss": 0.041,
+      "step": 410
+    },
+    {
+      "epoch": 7.034042553191489,
+      "grad_norm": 0.1481233537197113,
+      "learning_rate": 6.068965517241379e-05,
+      "loss": 0.0505,
+      "step": 415
+    },
+    {
+      "epoch": 7.1191489361702125,
+      "grad_norm": 0.10545721650123596,
+      "learning_rate": 5.896551724137931e-05,
+      "loss": 0.0361,
+      "step": 420
+    },
+    {
+      "epoch": 7.2042553191489365,
+      "grad_norm": 0.13733087480068207,
+      "learning_rate": 5.7241379310344835e-05,
+      "loss": 0.0361,
+      "step": 425
+    },
+    {
+      "epoch": 7.2893617021276595,
+      "grad_norm": 0.09701387584209442,
+      "learning_rate": 5.551724137931035e-05,
+      "loss": 0.0363,
+      "step": 430
+    },
+    {
+      "epoch": 7.374468085106383,
+      "grad_norm": 0.12478837370872498,
+      "learning_rate": 5.379310344827586e-05,
+      "loss": 0.0385,
+      "step": 435
+    },
+    {
+      "epoch": 7.459574468085107,
+      "grad_norm": 0.18108202517032623,
+      "learning_rate": 5.2068965517241384e-05,
+      "loss": 0.0307,
+      "step": 440
+    },
+    {
+      "epoch": 7.54468085106383,
+      "grad_norm": 0.1741178184747696,
+      "learning_rate": 5.03448275862069e-05,
+      "loss": 0.0349,
+      "step": 445
+    },
+    {
+      "epoch": 7.629787234042553,
+      "grad_norm": 0.18830710649490356,
+      "learning_rate": 4.862068965517241e-05,
+      "loss": 0.035,
+      "step": 450
+    },
+    {
+      "epoch": 7.714893617021277,
+      "grad_norm": 0.29267263412475586,
+      "learning_rate": 4.689655172413793e-05,
+      "loss": 0.0396,
+      "step": 455
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.1248115673661232,
+      "learning_rate": 4.5172413793103454e-05,
+      "loss": 0.0417,
+      "step": 460
+    },
+    {
+      "epoch": 7.885106382978723,
+      "grad_norm": 0.12826257944107056,
+      "learning_rate": 4.344827586206897e-05,
+      "loss": 0.0352,
+      "step": 465
+    },
+    {
+      "epoch": 7.970212765957447,
+      "grad_norm": 0.10185350477695465,
+      "learning_rate": 4.172413793103448e-05,
+      "loss": 0.0383,
+      "step": 470
+    },
+    {
+      "epoch": 8.051063829787234,
+      "grad_norm": 0.11523312330245972,
+      "learning_rate": 4e-05,
+      "loss": 0.0372,
+      "step": 475
+    },
+    {
+      "epoch": 8.136170212765958,
+      "grad_norm": 0.07264875620603561,
+      "learning_rate": 3.827586206896552e-05,
+      "loss": 0.0291,
+      "step": 480
+    },
+    {
+      "epoch": 8.221276595744682,
+      "grad_norm": 0.1880428045988083,
+      "learning_rate": 3.655172413793104e-05,
+      "loss": 0.029,
+      "step": 485
+    },
+    {
+      "epoch": 8.306382978723404,
+      "grad_norm": 0.19860832393169403,
+      "learning_rate": 3.482758620689655e-05,
+      "loss": 0.0298,
+      "step": 490
+    },
+    {
+      "epoch": 8.391489361702128,
+      "grad_norm": 0.1690095216035843,
+      "learning_rate": 3.310344827586207e-05,
+      "loss": 0.0371,
+      "step": 495
+    },
+    {
+      "epoch": 8.476595744680852,
+      "grad_norm": 0.171220064163208,
+      "learning_rate": 3.137931034482759e-05,
+      "loss": 0.0294,
+      "step": 500
+    },
+    {
+      "epoch": 8.561702127659574,
+      "grad_norm": 0.12849068641662598,
+      "learning_rate": 2.96551724137931e-05,
+      "loss": 0.0339,
+      "step": 505
+    },
+    {
+      "epoch": 8.646808510638298,
+      "grad_norm": 0.1075233593583107,
+      "learning_rate": 2.7931034482758622e-05,
+      "loss": 0.0346,
+      "step": 510
+    },
+    {
+      "epoch": 8.731914893617022,
+      "grad_norm": 0.14006929099559784,
+      "learning_rate": 2.620689655172414e-05,
+      "loss": 0.03,
+      "step": 515
+    },
+    {
+      "epoch": 8.817021276595744,
+      "grad_norm": 0.1683836579322815,
+      "learning_rate": 2.4482758620689654e-05,
+      "loss": 0.0321,
+      "step": 520
+    },
+    {
+      "epoch": 8.902127659574468,
+      "grad_norm": 0.12975075840950012,
+      "learning_rate": 2.2758620689655175e-05,
+      "loss": 0.0384,
+      "step": 525
+    },
+    {
+      "epoch": 8.987234042553192,
+      "grad_norm": 0.1698654145002365,
+      "learning_rate": 2.1034482758620692e-05,
+      "loss": 0.037,
+      "step": 530
+    },
+    {
+      "epoch": 9.068085106382979,
+      "grad_norm": 0.1573844850063324,
+      "learning_rate": 1.9310344827586207e-05,
+      "loss": 0.0328,
+      "step": 535
+    },
+    {
+      "epoch": 9.153191489361703,
+      "grad_norm": 0.14986495673656464,
+      "learning_rate": 1.7586206896551724e-05,
+      "loss": 0.0313,
+      "step": 540
+    },
+    {
+      "epoch": 9.238297872340425,
+      "grad_norm": 0.13991227746009827,
+      "learning_rate": 1.586206896551724e-05,
+      "loss": 0.0283,
+      "step": 545
+    },
+    {
+      "epoch": 9.323404255319149,
+      "grad_norm": 0.12908954918384552,
+      "learning_rate": 1.4137931034482759e-05,
+      "loss": 0.0283,
+      "step": 550
+    },
+    {
+      "epoch": 9.408510638297873,
+      "grad_norm": 0.1915467232465744,
+      "learning_rate": 1.2413793103448277e-05,
+      "loss": 0.0233,
+      "step": 555
+    },
+    {
+      "epoch": 9.493617021276595,
+      "grad_norm": 0.16341650485992432,
+      "learning_rate": 1.0689655172413794e-05,
+      "loss": 0.0265,
+      "step": 560
+    },
+    {
+      "epoch": 9.578723404255319,
+      "grad_norm": 0.1922847330570221,
+      "learning_rate": 8.96551724137931e-06,
+      "loss": 0.0314,
+      "step": 565
+    },
+    {
+      "epoch": 9.663829787234043,
+      "grad_norm": 0.2411348968744278,
+      "learning_rate": 7.241379310344828e-06,
+      "loss": 0.0334,
+      "step": 570
+    },
+    {
+      "epoch": 9.748936170212765,
+      "grad_norm": 0.20369961857795715,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 0.0336,
+      "step": 575
+    },
+    {
+      "epoch": 9.83404255319149,
+      "grad_norm": 0.19569233059883118,
+      "learning_rate": 3.793103448275862e-06,
+      "loss": 0.0286,
+      "step": 580
+    },
+    {
+      "epoch": 9.919148936170213,
+      "grad_norm": 0.19629313051700592,
+      "learning_rate": 2.0689655172413796e-06,
+      "loss": 0.029,
+      "step": 585
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.18082977831363678,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 0.0283,
+      "step": 590
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2063167604911104e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-590/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb339cf1e256f09d287949096640e324e00ba969d1a72f017e68213fc1d4fa6
+size 5752

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb3d6588272a88a027f1b8841b9382f52306c573c0c32a50735f589ce4c6d72
+oid sha256:0d55a35e30ff64375824aebad3534179c982b08fab46a86e762184005c3528e8
 size 5228717512

my-model.F16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73420b992a8c54dcb18f9d951dbf5765f485038aa78f9994a0b35685ce13bb60
+oid sha256:8d67f0c759a64406d92adccd8c951054bfb23391ff00070c48ffb8f609be46c8
 size 5235213568

my-model.Q4_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cf7fcf1401fc92ae51db99adb6695dcd6df7eabf71abf93e40ace8d0659fc1
+oid sha256:6db05d9e1adb70c82e90b4e15f7353852c5bb37cea1fd4427ce852149252614c
 size 5235213568

trainer_state.json

@@ -4,303 +4,849 @@
   "best_model_checkpoint": null,
   "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 590,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.2564102564102564,
-      "grad_norm": 0.8900398015975952,
+      "epoch": 0.0851063829787234,
+      "grad_norm": 1.7628610134124756,
       "learning_rate": 8e-05,
-      "loss": 1.2183,
+      "loss": 1.8622,
       "step": 5
     },
     {
-      "epoch": 0.5128205128205128,
-      "grad_norm": 1.0445992946624756,
+      "epoch": 0.1702127659574468,
+      "grad_norm": 1.8386660814285278,
       "learning_rate": 0.00018,
-      "loss": 0.673,
+      "loss": 0.9707,
       "step": 10
     },
     {
-      "epoch": 0.7692307692307693,
-      "grad_norm": 0.42482438683509827,
-      "learning_rate": 0.00019578947368421054,
-      "loss": 0.3333,
+      "epoch": 0.2553191489361702,
+      "grad_norm": 1.295538067817688,
+      "learning_rate": 0.00019862068965517243,
+      "loss": 0.5712,
       "step": 15
     },
     {
-      "epoch": 1.0,
-      "grad_norm": 0.400621622800827,
-      "learning_rate": 0.0001905263157894737,
-      "loss": 0.3283,
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.5233324766159058,
+      "learning_rate": 0.00019689655172413795,
+      "loss": 0.4687,
       "step": 20
     },
     {
-      "epoch": 1.2564102564102564,
-      "grad_norm": 0.5521817803382874,
-      "learning_rate": 0.00018526315789473685,
-      "loss": 0.2366,
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.7628127336502075,
+      "learning_rate": 0.00019517241379310345,
+      "loss": 0.5601,
       "step": 25
     },
     {
-      "epoch": 1.5128205128205128,
-      "grad_norm": 0.2746163606643677,
-      "learning_rate": 0.00018,
-      "loss": 0.2179,
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.5182906985282898,
+      "learning_rate": 0.00019344827586206898,
+      "loss": 0.4466,
       "step": 30
     },
     {
-      "epoch": 1.7692307692307692,
-      "grad_norm": 0.2628752589225769,
-      "learning_rate": 0.00017473684210526317,
-      "loss": 0.2274,
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.3616418242454529,
+      "learning_rate": 0.0001917241379310345,
+      "loss": 0.5812,
       "step": 35
     },
     {
-      "epoch": 2.0,
-      "grad_norm": 0.34806522727012634,
-      "learning_rate": 0.00016947368421052633,
-      "loss": 0.1907,
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.48968932032585144,
+      "learning_rate": 0.00019,
+      "loss": 0.3477,
       "step": 40
     },
     {
-      "epoch": 2.2564102564102564,
-      "grad_norm": 0.22281789779663086,
-      "learning_rate": 0.00016421052631578948,
-      "loss": 0.1511,
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.8994768261909485,
+      "learning_rate": 0.00018827586206896554,
+      "loss": 0.3383,
       "step": 45
     },
     {
-      "epoch": 2.5128205128205128,
-      "grad_norm": 0.2427287995815277,
-      "learning_rate": 0.00015894736842105264,
-      "loss": 0.1316,
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.387116402387619,
+      "learning_rate": 0.00018655172413793104,
+      "loss": 0.4003,
       "step": 50
     },
     {
-      "epoch": 2.769230769230769,
-      "grad_norm": 0.31950950622558594,
-      "learning_rate": 0.0001536842105263158,
-      "loss": 0.1253,
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.8058916926383972,
+      "learning_rate": 0.00018482758620689654,
+      "loss": 0.3992,
       "step": 55
     },
     {
-      "epoch": 3.0,
-      "grad_norm": 0.4533534348011017,
-      "learning_rate": 0.00014842105263157895,
-      "loss": 0.1422,
+      "epoch": 1.0170212765957447,
+      "grad_norm": 0.4688344895839691,
+      "learning_rate": 0.00018310344827586207,
+      "loss": 0.3998,
       "step": 60
     },
     {
-      "epoch": 3.2564102564102564,
-      "grad_norm": 0.20593833923339844,
-      "learning_rate": 0.0001431578947368421,
-      "loss": 0.0795,
+      "epoch": 1.102127659574468,
+      "grad_norm": 0.5960966944694519,
+      "learning_rate": 0.0001813793103448276,
+      "loss": 0.2818,
       "step": 65
     },
     {
-      "epoch": 3.5128205128205128,
-      "grad_norm": 0.3185991048812866,
-      "learning_rate": 0.00013789473684210527,
-      "loss": 0.0834,
+      "epoch": 1.1872340425531915,
+      "grad_norm": 0.49853241443634033,
+      "learning_rate": 0.0001796551724137931,
+      "loss": 0.2186,
       "step": 70
     },
     {
-      "epoch": 3.769230769230769,
-      "grad_norm": 0.2598686218261719,
-      "learning_rate": 0.00013263157894736842,
-      "loss": 0.0863,
+      "epoch": 1.2723404255319148,
+      "grad_norm": 0.521017849445343,
+      "learning_rate": 0.00017793103448275862,
+      "loss": 0.322,
       "step": 75
     },
     {
-      "epoch": 4.0,
-      "grad_norm": 0.4340210258960724,
-      "learning_rate": 0.00012736842105263158,
-      "loss": 0.0907,
+      "epoch": 1.3574468085106384,
+      "grad_norm": 0.35342177748680115,
+      "learning_rate": 0.00017620689655172415,
+      "loss": 0.1905,
       "step": 80
     },
     {
-      "epoch": 4.256410256410256,
-      "grad_norm": 0.17483440041542053,
-      "learning_rate": 0.00012210526315789474,
-      "loss": 0.0623,
+      "epoch": 1.4425531914893617,
+      "grad_norm": 0.37390947341918945,
+      "learning_rate": 0.00017448275862068965,
+      "loss": 0.2582,
       "step": 85
     },
     {
-      "epoch": 4.512820512820513,
-      "grad_norm": 0.1727558970451355,
-      "learning_rate": 0.00011684210526315791,
-      "loss": 0.0555,
+      "epoch": 1.527659574468085,
+      "grad_norm": 0.42308491468429565,
+      "learning_rate": 0.00017275862068965518,
+      "loss": 0.2337,
       "step": 90
     },
     {
-      "epoch": 4.769230769230769,
-      "grad_norm": 0.26636630296707153,
-      "learning_rate": 0.00011157894736842105,
-      "loss": 0.0543,
+      "epoch": 1.6127659574468085,
+      "grad_norm": 0.8888659477233887,
+      "learning_rate": 0.0001710344827586207,
+      "loss": 0.2465,
       "step": 95
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 0.30638131499290466,
-      "learning_rate": 0.00010631578947368421,
-      "loss": 0.0525,
+      "epoch": 1.697872340425532,
+      "grad_norm": 0.40344128012657166,
+      "learning_rate": 0.0001693103448275862,
+      "loss": 0.2591,
       "step": 100
     },
     {
-      "epoch": 5.256410256410256,
-      "grad_norm": 0.16161443293094635,
-      "learning_rate": 0.00010105263157894738,
-      "loss": 0.0419,
+      "epoch": 1.7829787234042553,
+      "grad_norm": 0.45671504735946655,
+      "learning_rate": 0.00016758620689655173,
+      "loss": 0.2269,
       "step": 105
     },
     {
-      "epoch": 5.512820512820513,
-      "grad_norm": 0.2057483047246933,
-      "learning_rate": 9.578947368421052e-05,
-      "loss": 0.045,
+      "epoch": 1.8680851063829786,
+      "grad_norm": 0.4616524577140808,
+      "learning_rate": 0.00016586206896551726,
+      "loss": 0.2033,
       "step": 110
     },
     {
-      "epoch": 5.769230769230769,
-      "grad_norm": 0.17914408445358276,
-      "learning_rate": 9.052631578947369e-05,
-      "loss": 0.0398,
+      "epoch": 1.9531914893617022,
+      "grad_norm": 0.4471171200275421,
+      "learning_rate": 0.00016413793103448276,
+      "loss": 0.266,
       "step": 115
     },
     {
-      "epoch": 6.0,
-      "grad_norm": 0.20949575304985046,
-      "learning_rate": 8.526315789473685e-05,
-      "loss": 0.0424,
+      "epoch": 2.0340425531914894,
+      "grad_norm": 0.7043401002883911,
+      "learning_rate": 0.0001624137931034483,
+      "loss": 0.1607,
       "step": 120
     },
     {
-      "epoch": 6.256410256410256,
-      "grad_norm": 0.09992681443691254,
-      "learning_rate": 8e-05,
-      "loss": 0.0364,
+      "epoch": 2.119148936170213,
+      "grad_norm": 0.4361288845539093,
+      "learning_rate": 0.00016068965517241382,
+      "loss": 0.1493,
       "step": 125
     },
     {
-      "epoch": 6.512820512820513,
-      "grad_norm": 0.11780328303575516,
-      "learning_rate": 7.473684210526316e-05,
-      "loss": 0.0329,
+      "epoch": 2.204255319148936,
+      "grad_norm": 0.45557570457458496,
+      "learning_rate": 0.00015896551724137932,
+      "loss": 0.1011,
       "step": 130
     },
     {
-      "epoch": 6.769230769230769,
-      "grad_norm": 0.1347094029188156,
-      "learning_rate": 6.947368421052632e-05,
-      "loss": 0.0355,
+      "epoch": 2.2893617021276595,
+      "grad_norm": 0.3149248957633972,
+      "learning_rate": 0.00015724137931034485,
+      "loss": 0.1112,
       "step": 135
     },
     {
-      "epoch": 7.0,
-      "grad_norm": 0.1570531278848648,
-      "learning_rate": 6.421052631578948e-05,
-      "loss": 0.0368,
+      "epoch": 2.374468085106383,
+      "grad_norm": 0.2783677279949188,
+      "learning_rate": 0.00015551724137931037,
+      "loss": 0.1278,
       "step": 140
     },
     {
-      "epoch": 7.256410256410256,
-      "grad_norm": 0.07153915613889694,
-      "learning_rate": 5.894736842105263e-05,
-      "loss": 0.0315,
+      "epoch": 2.4595744680851066,
+      "grad_norm": 0.46953991055488586,
+      "learning_rate": 0.00015379310344827587,
+      "loss": 0.1157,
       "step": 145
     },
     {
-      "epoch": 7.512820512820513,
-      "grad_norm": 0.13243050873279572,
-      "learning_rate": 5.368421052631579e-05,
-      "loss": 0.032,
+      "epoch": 2.5446808510638297,
+      "grad_norm": 0.5183996558189392,
+      "learning_rate": 0.0001520689655172414,
+      "loss": 0.107,
       "step": 150
     },
     {
-      "epoch": 7.769230769230769,
-      "grad_norm": 0.09201069176197052,
-      "learning_rate": 4.842105263157895e-05,
-      "loss": 0.0307,
+      "epoch": 2.629787234042553,
+      "grad_norm": 0.46928611397743225,
+      "learning_rate": 0.0001503448275862069,
+      "loss": 0.12,
       "step": 155
     },
     {
-      "epoch": 8.0,
-      "grad_norm": 0.13942566514015198,
-      "learning_rate": 4.3157894736842105e-05,
-      "loss": 0.031,
+      "epoch": 2.7148936170212767,
+      "grad_norm": 0.4748971462249756,
+      "learning_rate": 0.00014862068965517243,
+      "loss": 0.1406,
       "step": 160
     },
     {
-      "epoch": 8.256410256410255,
-      "grad_norm": 0.10768593102693558,
-      "learning_rate": 3.789473684210527e-05,
-      "loss": 0.0291,
+      "epoch": 2.8,
+      "grad_norm": 0.7183696627616882,
+      "learning_rate": 0.00014689655172413793,
+      "loss": 0.1533,
       "step": 165
     },
     {
-      "epoch": 8.512820512820513,
-      "grad_norm": 0.14742617309093475,
-      "learning_rate": 3.2631578947368426e-05,
-      "loss": 0.0277,
+      "epoch": 2.8851063829787233,
+      "grad_norm": 0.575391948223114,
+      "learning_rate": 0.00014517241379310346,
+      "loss": 0.1365,
       "step": 170
     },
     {
-      "epoch": 8.76923076923077,
-      "grad_norm": 0.1279958188533783,
-      "learning_rate": 2.7368421052631583e-05,
-      "loss": 0.0293,
+      "epoch": 2.970212765957447,
+      "grad_norm": 0.33236995339393616,
+      "learning_rate": 0.00014344827586206896,
+      "loss": 0.1369,
       "step": 175
     },
     {
-      "epoch": 9.0,
-      "grad_norm": 0.20050744712352753,
-      "learning_rate": 2.2105263157894736e-05,
-      "loss": 0.0275,
+      "epoch": 3.051063829787234,
+      "grad_norm": 0.17017032206058502,
+      "learning_rate": 0.0001417241379310345,
+      "loss": 0.093,
       "step": 180
     },
     {
-      "epoch": 9.256410256410255,
-      "grad_norm": 0.11717718094587326,
-      "learning_rate": 1.6842105263157896e-05,
-      "loss": 0.0244,
+      "epoch": 3.1361702127659576,
+      "grad_norm": 0.8167087435722351,
+      "learning_rate": 0.00014,
+      "loss": 0.1297,
       "step": 185
     },
     {
-      "epoch": 9.512820512820513,
-      "grad_norm": 0.15230141580104828,
-      "learning_rate": 1.1578947368421053e-05,
-      "loss": 0.0269,
+      "epoch": 3.2212765957446807,
+      "grad_norm": 0.4695407748222351,
+      "learning_rate": 0.00013827586206896552,
+      "loss": 0.0794,
       "step": 190
     },
     {
-      "epoch": 9.76923076923077,
-      "grad_norm": 0.1412554681301117,
-      "learning_rate": 6.315789473684211e-06,
-      "loss": 0.0263,
+      "epoch": 3.3063829787234043,
+      "grad_norm": 0.46323472261428833,
+      "learning_rate": 0.00013655172413793104,
+      "loss": 0.0909,
       "step": 195
     },
     {
-      "epoch": 10.0,
-      "grad_norm": 0.18158526718616486,
-      "learning_rate": 1.0526315789473685e-06,
-      "loss": 0.0258,
+      "epoch": 3.391489361702128,
+      "grad_norm": 0.4290667772293091,
+      "learning_rate": 0.00013482758620689654,
+      "loss": 0.0728,
       "step": 200
     },
+    {
+      "epoch": 3.476595744680851,
+      "grad_norm": 0.3602962791919708,
+      "learning_rate": 0.00013310344827586207,
+      "loss": 0.0713,
+      "step": 205
+    },
+    {
+      "epoch": 3.5617021276595744,
+      "grad_norm": 0.3129134476184845,
+      "learning_rate": 0.0001313793103448276,
+      "loss": 0.0878,
+      "step": 210
+    },
+    {
+      "epoch": 3.646808510638298,
+      "grad_norm": 0.4205905795097351,
+      "learning_rate": 0.0001296551724137931,
+      "loss": 0.0815,
+      "step": 215
+    },
+    {
+      "epoch": 3.731914893617021,
+      "grad_norm": 0.47979313135147095,
+      "learning_rate": 0.00012793103448275863,
+      "loss": 0.0696,
+      "step": 220
+    },
+    {
+      "epoch": 3.8170212765957445,
+      "grad_norm": 0.4063044786453247,
+      "learning_rate": 0.00012620689655172415,
+      "loss": 0.0661,
+      "step": 225
+    },
+    {
+      "epoch": 3.902127659574468,
+      "grad_norm": 0.363741934299469,
+      "learning_rate": 0.00012448275862068966,
+      "loss": 0.0972,
+      "step": 230
+    },
+    {
+      "epoch": 3.9872340425531916,
+      "grad_norm": 0.2973483204841614,
+      "learning_rate": 0.00012275862068965518,
+      "loss": 0.0807,
+      "step": 235
+    },
+    {
+      "epoch": 4.068085106382979,
+      "grad_norm": 0.481488436460495,
+      "learning_rate": 0.00012103448275862071,
+      "loss": 0.0678,
+      "step": 240
+    },
+    {
+      "epoch": 4.153191489361702,
+      "grad_norm": 0.18169716000556946,
+      "learning_rate": 0.00011931034482758621,
+      "loss": 0.0555,
+      "step": 245
+    },
+    {
+      "epoch": 4.238297872340426,
+      "grad_norm": 0.3210119307041168,
+      "learning_rate": 0.00011758620689655173,
+      "loss": 0.0506,
+      "step": 250
+    },
+    {
+      "epoch": 4.323404255319149,
+      "grad_norm": 0.3670145273208618,
+      "learning_rate": 0.00011586206896551725,
+      "loss": 0.0685,
+      "step": 255
+    },
+    {
+      "epoch": 4.408510638297872,
+      "grad_norm": 0.2257293462753296,
+      "learning_rate": 0.00011413793103448275,
+      "loss": 0.0592,
+      "step": 260
+    },
+    {
+      "epoch": 4.493617021276596,
+      "grad_norm": 0.16985096037387848,
+      "learning_rate": 0.00011241379310344828,
+      "loss": 0.0745,
+      "step": 265
+    },
+    {
+      "epoch": 4.578723404255319,
+      "grad_norm": 0.31408607959747314,
+      "learning_rate": 0.00011068965517241381,
+      "loss": 0.0866,
+      "step": 270
+    },
+    {
+      "epoch": 4.663829787234042,
+      "grad_norm": 0.2598167657852173,
+      "learning_rate": 0.00010896551724137931,
+      "loss": 0.0494,
+      "step": 275
+    },
+    {
+      "epoch": 4.748936170212766,
+      "grad_norm": 0.4023381471633911,
+      "learning_rate": 0.00010724137931034484,
+      "loss": 0.0632,
+      "step": 280
+    },
+    {
+      "epoch": 4.834042553191489,
+      "grad_norm": 0.24716579914093018,
+      "learning_rate": 0.00010551724137931037,
+      "loss": 0.0499,
+      "step": 285
+    },
+    {
+      "epoch": 4.919148936170213,
+      "grad_norm": 0.39397132396698,
+      "learning_rate": 0.00010379310344827587,
+      "loss": 0.0575,
+      "step": 290
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09666766971349716,
+      "learning_rate": 0.0001020689655172414,
+      "loss": 0.0609,
+      "step": 295
+    },
+    {
+      "epoch": 5.085106382978723,
+      "grad_norm": 0.1626937985420227,
+      "learning_rate": 0.0001003448275862069,
+      "loss": 0.0455,
+      "step": 300
+    },
+    {
+      "epoch": 5.170212765957447,
+      "grad_norm": 0.2916521728038788,
+      "learning_rate": 9.862068965517242e-05,
+      "loss": 0.0437,
+      "step": 305
+    },
+    {
+      "epoch": 5.25531914893617,
+      "grad_norm": 0.3213741183280945,
+      "learning_rate": 9.689655172413794e-05,
+      "loss": 0.0509,
+      "step": 310
+    },
+    {
+      "epoch": 5.340425531914893,
+      "grad_norm": 0.25438761711120605,
+      "learning_rate": 9.517241379310345e-05,
+      "loss": 0.0483,
+      "step": 315
+    },
+    {
+      "epoch": 5.425531914893617,
+      "grad_norm": 0.35173889994621277,
+      "learning_rate": 9.344827586206896e-05,
+      "loss": 0.0394,
+      "step": 320
+    },
+    {
+      "epoch": 5.51063829787234,
+      "grad_norm": 0.2214491218328476,
+      "learning_rate": 9.172413793103448e-05,
+      "loss": 0.0615,
+      "step": 325
+    },
+    {
+      "epoch": 5.595744680851064,
+      "grad_norm": 0.1461336314678192,
+      "learning_rate": 9e-05,
+      "loss": 0.0552,
+      "step": 330
+    },
+    {
+      "epoch": 5.680851063829787,
+      "grad_norm": 0.2651642858982086,
+      "learning_rate": 8.827586206896552e-05,
+      "loss": 0.0417,
+      "step": 335
+    },
+    {
+      "epoch": 5.76595744680851,
+      "grad_norm": 0.3055964708328247,
+      "learning_rate": 8.655172413793103e-05,
+      "loss": 0.0502,
+      "step": 340
+    },
+    {
+      "epoch": 5.851063829787234,
+      "grad_norm": 0.19299010932445526,
+      "learning_rate": 8.482758620689656e-05,
+      "loss": 0.044,
+      "step": 345
+    },
+    {
+      "epoch": 5.9361702127659575,
+      "grad_norm": 0.120607890188694,
+      "learning_rate": 8.310344827586208e-05,
+      "loss": 0.0407,
+      "step": 350
+    },
+    {
+      "epoch": 6.017021276595744,
+      "grad_norm": 0.13520629703998566,
+      "learning_rate": 8.137931034482759e-05,
+      "loss": 0.0512,
+      "step": 355
+    },
+    {
+      "epoch": 6.102127659574468,
+      "grad_norm": 0.20564086735248566,
+      "learning_rate": 7.965517241379312e-05,
+      "loss": 0.0416,
+      "step": 360
+    },
+    {
+      "epoch": 6.187234042553191,
+      "grad_norm": 0.115450419485569,
+      "learning_rate": 7.793103448275862e-05,
+      "loss": 0.0424,
+      "step": 365
+    },
+    {
+      "epoch": 6.272340425531915,
+      "grad_norm": 0.1926778256893158,
+      "learning_rate": 7.620689655172413e-05,
+      "loss": 0.0378,
+      "step": 370
+    },
+    {
+      "epoch": 6.357446808510638,
+      "grad_norm": 0.25700807571411133,
+      "learning_rate": 7.448275862068966e-05,
+      "loss": 0.0453,
+      "step": 375
+    },
+    {
+      "epoch": 6.4425531914893615,
+      "grad_norm": 0.10704706609249115,
+      "learning_rate": 7.275862068965517e-05,
+      "loss": 0.0323,
+      "step": 380
+    },
+    {
+      "epoch": 6.527659574468085,
+      "grad_norm": 0.18126443028450012,
+      "learning_rate": 7.103448275862069e-05,
+      "loss": 0.0393,
+      "step": 385
+    },
+    {
+      "epoch": 6.6127659574468085,
+      "grad_norm": 0.13170169293880463,
+      "learning_rate": 6.931034482758622e-05,
+      "loss": 0.0458,
+      "step": 390
+    },
+    {
+      "epoch": 6.697872340425532,
+      "grad_norm": 0.10165558010339737,
+      "learning_rate": 6.758620689655173e-05,
+      "loss": 0.0359,
+      "step": 395
+    },
+    {
+      "epoch": 6.782978723404256,
+      "grad_norm": 0.20285525918006897,
+      "learning_rate": 6.586206896551724e-05,
+      "loss": 0.0411,
+      "step": 400
+    },
+    {
+      "epoch": 6.868085106382979,
+      "grad_norm": 0.17869718372821808,
+      "learning_rate": 6.413793103448276e-05,
+      "loss": 0.0454,
+      "step": 405
+    },
+    {
+      "epoch": 6.953191489361702,
+      "grad_norm": 0.1431434452533722,
+      "learning_rate": 6.241379310344829e-05,
+      "loss": 0.041,
+      "step": 410
+    },
+    {
+      "epoch": 7.034042553191489,
+      "grad_norm": 0.1481233537197113,
+      "learning_rate": 6.068965517241379e-05,
+      "loss": 0.0505,
+      "step": 415
+    },
+    {
+      "epoch": 7.1191489361702125,
+      "grad_norm": 0.10545721650123596,
+      "learning_rate": 5.896551724137931e-05,
+      "loss": 0.0361,
+      "step": 420
+    },
+    {
+      "epoch": 7.2042553191489365,
+      "grad_norm": 0.13733087480068207,
+      "learning_rate": 5.7241379310344835e-05,
+      "loss": 0.0361,
+      "step": 425
+    },
+    {
+      "epoch": 7.2893617021276595,
+      "grad_norm": 0.09701387584209442,
+      "learning_rate": 5.551724137931035e-05,
+      "loss": 0.0363,
+      "step": 430
+    },
+    {
+      "epoch": 7.374468085106383,
+      "grad_norm": 0.12478837370872498,
+      "learning_rate": 5.379310344827586e-05,
+      "loss": 0.0385,
+      "step": 435
+    },
+    {
+      "epoch": 7.459574468085107,
+      "grad_norm": 0.18108202517032623,
+      "learning_rate": 5.2068965517241384e-05,
+      "loss": 0.0307,
+      "step": 440
+    },
+    {
+      "epoch": 7.54468085106383,
+      "grad_norm": 0.1741178184747696,
+      "learning_rate": 5.03448275862069e-05,
+      "loss": 0.0349,
+      "step": 445
+    },
+    {
+      "epoch": 7.629787234042553,
+      "grad_norm": 0.18830710649490356,
+      "learning_rate": 4.862068965517241e-05,
+      "loss": 0.035,
+      "step": 450
+    },
+    {
+      "epoch": 7.714893617021277,
+      "grad_norm": 0.29267263412475586,
+      "learning_rate": 4.689655172413793e-05,
+      "loss": 0.0396,
+      "step": 455
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.1248115673661232,
+      "learning_rate": 4.5172413793103454e-05,
+      "loss": 0.0417,
+      "step": 460
+    },
+    {
+      "epoch": 7.885106382978723,
+      "grad_norm": 0.12826257944107056,
+      "learning_rate": 4.344827586206897e-05,
+      "loss": 0.0352,
+      "step": 465
+    },
+    {
+      "epoch": 7.970212765957447,
+      "grad_norm": 0.10185350477695465,
+      "learning_rate": 4.172413793103448e-05,
+      "loss": 0.0383,
+      "step": 470
+    },
+    {
+      "epoch": 8.051063829787234,
+      "grad_norm": 0.11523312330245972,
+      "learning_rate": 4e-05,
+      "loss": 0.0372,
+      "step": 475
+    },
+    {
+      "epoch": 8.136170212765958,
+      "grad_norm": 0.07264875620603561,
+      "learning_rate": 3.827586206896552e-05,
+      "loss": 0.0291,
+      "step": 480
+    },
+    {
+      "epoch": 8.221276595744682,
+      "grad_norm": 0.1880428045988083,
+      "learning_rate": 3.655172413793104e-05,
+      "loss": 0.029,
+      "step": 485
+    },
+    {
+      "epoch": 8.306382978723404,
+      "grad_norm": 0.19860832393169403,
+      "learning_rate": 3.482758620689655e-05,
+      "loss": 0.0298,
+      "step": 490
+    },
+    {
+      "epoch": 8.391489361702128,
+      "grad_norm": 0.1690095216035843,
+      "learning_rate": 3.310344827586207e-05,
+      "loss": 0.0371,
+      "step": 495
+    },
+    {
+      "epoch": 8.476595744680852,
+      "grad_norm": 0.171220064163208,
+      "learning_rate": 3.137931034482759e-05,
+      "loss": 0.0294,
+      "step": 500
+    },
+    {
+      "epoch": 8.561702127659574,
+      "grad_norm": 0.12849068641662598,
+      "learning_rate": 2.96551724137931e-05,
+      "loss": 0.0339,
+      "step": 505
+    },
+    {
+      "epoch": 8.646808510638298,
+      "grad_norm": 0.1075233593583107,
+      "learning_rate": 2.7931034482758622e-05,
+      "loss": 0.0346,
+      "step": 510
+    },
+    {
+      "epoch": 8.731914893617022,
+      "grad_norm": 0.14006929099559784,
+      "learning_rate": 2.620689655172414e-05,
+      "loss": 0.03,
+      "step": 515
+    },
+    {
+      "epoch": 8.817021276595744,
+      "grad_norm": 0.1683836579322815,
+      "learning_rate": 2.4482758620689654e-05,
+      "loss": 0.0321,
+      "step": 520
+    },
+    {
+      "epoch": 8.902127659574468,
+      "grad_norm": 0.12975075840950012,
+      "learning_rate": 2.2758620689655175e-05,
+      "loss": 0.0384,
+      "step": 525
+    },
+    {
+      "epoch": 8.987234042553192,
+      "grad_norm": 0.1698654145002365,
+      "learning_rate": 2.1034482758620692e-05,
+      "loss": 0.037,
+      "step": 530
+    },
+    {
+      "epoch": 9.068085106382979,
+      "grad_norm": 0.1573844850063324,
+      "learning_rate": 1.9310344827586207e-05,
+      "loss": 0.0328,
+      "step": 535
+    },
+    {
+      "epoch": 9.153191489361703,
+      "grad_norm": 0.14986495673656464,
+      "learning_rate": 1.7586206896551724e-05,
+      "loss": 0.0313,
+      "step": 540
+    },
+    {
+      "epoch": 9.238297872340425,
+      "grad_norm": 0.13991227746009827,
+      "learning_rate": 1.586206896551724e-05,
+      "loss": 0.0283,
+      "step": 545
+    },
+    {
+      "epoch": 9.323404255319149,
+      "grad_norm": 0.12908954918384552,
+      "learning_rate": 1.4137931034482759e-05,
+      "loss": 0.0283,
+      "step": 550
+    },
+    {
+      "epoch": 9.408510638297873,
+      "grad_norm": 0.1915467232465744,
+      "learning_rate": 1.2413793103448277e-05,
+      "loss": 0.0233,
+      "step": 555
+    },
+    {
+      "epoch": 9.493617021276595,
+      "grad_norm": 0.16341650485992432,
+      "learning_rate": 1.0689655172413794e-05,
+      "loss": 0.0265,
+      "step": 560
+    },
+    {
+      "epoch": 9.578723404255319,
+      "grad_norm": 0.1922847330570221,
+      "learning_rate": 8.96551724137931e-06,
+      "loss": 0.0314,
+      "step": 565
+    },
+    {
+      "epoch": 9.663829787234043,
+      "grad_norm": 0.2411348968744278,
+      "learning_rate": 7.241379310344828e-06,
+      "loss": 0.0334,
+      "step": 570
+    },
+    {
+      "epoch": 9.748936170212765,
+      "grad_norm": 0.20369961857795715,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 0.0336,
+      "step": 575
+    },
+    {
+      "epoch": 9.83404255319149,
+      "grad_norm": 0.19569233059883118,
+      "learning_rate": 3.793103448275862e-06,
+      "loss": 0.0286,
+      "step": 580
+    },
+    {
+      "epoch": 9.919148936170213,
+      "grad_norm": 0.19629313051700592,
+      "learning_rate": 2.0689655172413796e-06,
+      "loss": 0.029,
+      "step": 585
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.18082977831363678,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 0.0283,
+      "step": 590
+    },
     {
       "epoch": 10.0,
-      "step": 200,
-      "total_flos": 1.9472843996476416e+16,
-      "train_loss": 0.12982395909726618,
-      "train_runtime": 551.873,
-      "train_samples_per_second": 2.827,
-      "train_steps_per_second": 0.362
+      "step": 590,
+      "total_flos": 3.2063167604911104e+16,
+      "train_loss": 0.1322159972483829,
+      "train_runtime": 1074.5919,
+      "train_samples_per_second": 4.374,
+      "train_steps_per_second": 0.549
     }
   ],
   "logging_steps": 5,
-  "max_steps": 200,
+  "max_steps": 590,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
@@ -316,7 +862,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9472843996476416e+16,
+  "total_flos": 3.2063167604911104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62784fa807bcc4de86623ba4b16b7f7fa990bea15a4f24e621616bb5fc14022a
+oid sha256:2cb339cf1e256f09d287949096640e324e00ba969d1a72f017e68213fc1d4fa6
 size 5752