Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,300 @@
+
+---
+license: other
+tags:
+- generated_from_trainer
+- google/gemma
+- PyTorch
+- transformers
+- trl
+- peft
+- tensorboard
+model-index:
+- name: gemma-2b-chat-ultra
+  results: []
+datasets:
+- HuggingFaceH4/deita-10k-v0-sft
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+language:
+- en
+base_model: google/gemma-2b
+widget:
+  - example_title: LLM
+    messages:
+      - role: user
+        content: What is a large language model (LLM)?
+pipeline_tag: text-generation
+---
+
+# Model Card for gemma-2b-chat-ultra:
+
+💬🤖
+
+**gemma-2b-chat-ultra** is a language model that is trained to act as AI assistant. It is a finetuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) that was trained using `SFTTrainer` on publicly available dataset
+[HuggingFaceH4/deita-10k-v0-sft](https://huggingface.co/datasets/HuggingFaceH4/deita-10k-v0-sft).
+
+
+## Training Metrics
+
+[The training metrics can be found on **TensorBoard**](https://huggingface.co/Menouar/gemma-2b-chat-ultra/tensorboard).
+
+
+## Training hyperparameters
+
+The following hyperparameters were used during the training:
+
+
+- output_dir: peft-lora-model
+ 
+- overwrite_output_dir: True
+ 
+- do_train: False
+ 
+- do_eval: False
+ 
+- do_predict: False
+ 
+- evaluation_strategy: no
+ 
+- prediction_loss_only: False
+ 
+- per_device_train_batch_size: 2
+ 
+- per_device_eval_batch_size: None
+ 
+- per_gpu_train_batch_size: None
+ 
+- per_gpu_eval_batch_size: None
+ 
+- gradient_accumulation_steps: 4
+ 
+- eval_accumulation_steps: None
+ 
+- eval_delay: 0
+ 
+- learning_rate: 2e-05
+ 
+- weight_decay: 0.0
+ 
+- adam_beta1: 0.9
+ 
+- adam_beta2: 0.999
+ 
+- adam_epsilon: 1e-08
+ 
+- max_grad_norm: 0.3
+ 
+- num_train_epochs: 3
+ 
+- max_steps: -1
+ 
+- lr_scheduler_type: cosine
+ 
+- lr_scheduler_kwargs: {}
+ 
+- warmup_ratio: 0.1
+ 
+- warmup_steps: 0
+ 
+- log_level: passive
+ 
+- log_level_replica: warning
+ 
+- log_on_each_node: True
+ 
+- logging_dir: peft-lora-model/runs/Mar21_07-18-25_a518bf4a6403
+ 
+- logging_strategy: steps
+ 
+- logging_first_step: False
+ 
+- logging_steps: 10
+ 
+- logging_nan_inf_filter: True
+ 
+- save_strategy: epoch
+ 
+- save_steps: 500
+ 
+- save_total_limit: None
+ 
+- save_safetensors: True
+ 
+- save_on_each_node: False
+ 
+- save_only_model: False
+ 
+- no_cuda: False
+ 
+- use_cpu: False
+ 
+- use_mps_device: False
+ 
+- seed: 42
+ 
+- data_seed: None
+ 
+- jit_mode_eval: False
+ 
+- use_ipex: False
+ 
+- bf16: True
+ 
+- fp16: False
+ 
+- fp16_opt_level: O1
+ 
+- half_precision_backend: auto
+ 
+- bf16_full_eval: False
+ 
+- fp16_full_eval: False
+ 
+- tf32: None
+ 
+- local_rank: 0
+ 
+- ddp_backend: None
+ 
+- tpu_num_cores: None
+ 
+- tpu_metrics_debug: False
+ 
+- debug: []
+ 
+- dataloader_drop_last: False
+ 
+- eval_steps: None
+ 
+- dataloader_num_workers: 0
+ 
+- dataloader_prefetch_factor: None
+ 
+- past_index: -1
+ 
+- run_name: peft-lora-model
+ 
+- disable_tqdm: False
+ 
+- remove_unused_columns: True
+ 
+- label_names: None
+ 
+- load_best_model_at_end: False
+ 
+- metric_for_best_model: None
+ 
+- greater_is_better: None
+ 
+- ignore_data_skip: False
+ 
+- fsdp: []
+ 
+- fsdp_min_num_params: 0
+ 
+- fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+ 
+- fsdp_transformer_layer_cls_to_wrap: None
+ 
+- accelerator_config: AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True)
+ 
+- deepspeed: None
+ 
+- label_smoothing_factor: 0.0
+ 
+- optim: adamw_torch_fused
+ 
+- optim_args: None
+ 
+- adafactor: False
+ 
+- group_by_length: False
+ 
+- length_column_name: length
+ 
+- report_to: ['tensorboard']
+ 
+- ddp_find_unused_parameters: None
+ 
+- ddp_bucket_cap_mb: None
+ 
+- ddp_broadcast_buffers: None
+ 
+- dataloader_pin_memory: True
+ 
+- dataloader_persistent_workers: False
+ 
+- skip_memory_metrics: True
+ 
+- use_legacy_prediction_loop: False
+ 
+- push_to_hub: False
+ 
+- resume_from_checkpoint: None
+ 
+- hub_model_id: None
+ 
+- hub_strategy: every_save
+ 
+- hub_token: None
+ 
+- hub_private_repo: False
+ 
+- hub_always_push: False
+ 
+- gradient_checkpointing: True
+ 
+- gradient_checkpointing_kwargs: {'use_reentrant': False}
+ 
+- include_inputs_for_metrics: False
+ 
+- fp16_backend: auto
+ 
+- push_to_hub_model_id: None
+ 
+- push_to_hub_organization: None
+ 
+- push_to_hub_token: None
+ 
+- mp_parameters: 
+ 
+- auto_find_batch_size: False
+ 
+- full_determinism: False
+ 
+- torchdynamo: None
+ 
+- ray_scope: last
+ 
+- ddp_timeout: 1800
+ 
+- torch_compile: False
+ 
+- torch_compile_backend: None
+ 
+- torch_compile_mode: None
+ 
+- dispatch_batches: None
+ 
+- split_batches: None
+ 
+- include_tokens_per_second: False
+ 
+- include_num_input_tokens_seen: False
+ 
+- neftune_noise_alpha: None
+ 
+- distributed_state: Distributed environment: NO
+Num processes: 1
+Process index: 0
+Local process index: 0
+Device: cuda
+
+ 
+- _n_gpu: 1
+ 
+- __cached__setup_devices: cuda:0
+ 
+- deepspeed_plugin: None
+ 

checkpoint-3200/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.8.2

checkpoint-3200/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-3200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399b23dac929168055d7e3fa4e6f6b95bfb605da09fc50e12b2d0bd20c832994
+size 14741912

checkpoint-3200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c5d9ab58c1d16016fa52251550ddfa84fe1f87d365f079462a34e7f7cb231c
+size 29632634

checkpoint-3200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef921b37d77f9afefb1f4f1c9e0dbc734b041337fe0d53bad8a1099e0ad7a0a
+size 14244

checkpoint-3200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f9da520951d2569e78c27fd4edff50d2873e1d7ce537597cb5c78fb46bf2db
+size 1064

checkpoint-3200/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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-3200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-3200/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-3200/trainer_state.json

@@ -0,0 +1,2261 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 9.6875,
+      "learning_rate": 2.0833333333333333e-07,
+      "loss": 1.5494,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.375,
+      "learning_rate": 4.1666666666666667e-07,
+      "loss": 1.6442,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.78125,
+      "learning_rate": 6.25e-07,
+      "loss": 1.5817,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.6262,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 1.6365,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.25e-06,
+      "loss": 1.5901,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.4583333333333335e-06,
+      "loss": 1.5757,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.5234375,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.5956,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.75,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.561,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.59375,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 1.5564,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.546875,
+      "learning_rate": 2.2916666666666666e-06,
+      "loss": 1.6172,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1640625,
+      "learning_rate": 2.5e-06,
+      "loss": 1.6872,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4765625,
+      "learning_rate": 2.7083333333333334e-06,
+      "loss": 1.577,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.916666666666667e-06,
+      "loss": 1.56,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.462890625,
+      "learning_rate": 3.125e-06,
+      "loss": 1.552,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.5752,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.5416666666666673e-06,
+      "loss": 1.6739,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 13.25,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.5538,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8984375,
+      "learning_rate": 3.958333333333333e-06,
+      "loss": 1.6864,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 11.1875,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.5576,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.5328,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.583333333333333e-06,
+      "loss": 1.4953,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.578125,
+      "learning_rate": 4.791666666666668e-06,
+      "loss": 1.5663,
+      "step": 230
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.2265625,
+      "learning_rate": 5e-06,
+      "loss": 1.5063,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.439453125,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 1.4404,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.443359375,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 1.5304,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.44921875,
+      "learning_rate": 5.625e-06,
+      "loss": 1.5536,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.4140625,
+      "learning_rate": 5.833333333333334e-06,
+      "loss": 1.5385,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4609375,
+      "learning_rate": 6.041666666666667e-06,
+      "loss": 1.513,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.50390625,
+      "learning_rate": 6.25e-06,
+      "loss": 1.4549,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6328125,
+      "learning_rate": 6.458333333333334e-06,
+      "loss": 1.4931,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.48046875,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.4201,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.392578125,
+      "learning_rate": 6.875e-06,
+      "loss": 1.5471,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.95703125,
+      "learning_rate": 7.083333333333335e-06,
+      "loss": 1.4287,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.388671875,
+      "learning_rate": 7.291666666666667e-06,
+      "loss": 1.4475,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.33984375,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.477,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.296875,
+      "learning_rate": 7.708333333333334e-06,
+      "loss": 1.4533,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.400390625,
+      "learning_rate": 7.916666666666667e-06,
+      "loss": 1.3663,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.375,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.3953,
+      "step": 390
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.471,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.392578125,
+      "learning_rate": 8.541666666666666e-06,
+      "loss": 1.4374,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.046875,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.4224,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5546875,
+      "learning_rate": 8.958333333333334e-06,
+      "loss": 1.3261,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2578125,
+      "learning_rate": 9.166666666666666e-06,
+      "loss": 1.4033,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.4237,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.435546875,
+      "learning_rate": 9.583333333333335e-06,
+      "loss": 1.4083,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 9.791666666666666e-06,
+      "loss": 1.3245,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.333984375,
+      "learning_rate": 1e-05,
+      "loss": 1.3771,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.0208333333333334e-05,
+      "loss": 1.3789,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 1.4275,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.0625e-05,
+      "loss": 1.3739,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.0833333333333334e-05,
+      "loss": 1.3758,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.1041666666666668e-05,
+      "loss": 1.412,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.125e-05,
+      "loss": 1.4025,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 1.4138,
+      "step": 550
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.259765625,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 1.2598,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.625,
+      "learning_rate": 1.1875e-05,
+      "loss": 1.3543,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2083333333333333e-05,
+      "loss": 1.273,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.2291666666666668e-05,
+      "loss": 1.2361,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.25e-05,
+      "loss": 1.2996,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2708333333333333e-05,
+      "loss": 1.235,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.2916666666666668e-05,
+      "loss": 1.3838,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.3125e-05,
+      "loss": 1.2292,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.2698,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.3541666666666668e-05,
+      "loss": 1.3358,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.375e-05,
+      "loss": 1.237,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.73046875,
+      "learning_rate": 1.3958333333333333e-05,
+      "loss": 1.2976,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.416666666666667e-05,
+      "loss": 1.2324,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.4375e-05,
+      "loss": 1.2436,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.125,
+      "learning_rate": 1.4583333333333333e-05,
+      "loss": 1.2607,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.25,
+      "learning_rate": 1.479166666666667e-05,
+      "loss": 1.2724,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2314,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.375,
+      "learning_rate": 1.5208333333333333e-05,
+      "loss": 1.2632,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.5416666666666668e-05,
+      "loss": 1.3291,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.5625e-05,
+      "loss": 1.2816,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.5833333333333333e-05,
+      "loss": 1.2163,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.604166666666667e-05,
+      "loss": 1.2693,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.41015625,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 1.2114,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.77734375,
+      "learning_rate": 1.6458333333333335e-05,
+      "loss": 1.1689,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2469,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.6875e-05,
+      "loss": 1.2159,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.7083333333333333e-05,
+      "loss": 1.2198,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.729166666666667e-05,
+      "loss": 1.2687,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.2719,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.7708333333333335e-05,
+      "loss": 1.2074,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.7916666666666667e-05,
+      "loss": 1.1637,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.8125e-05,
+      "loss": 1.1775,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.09375,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 1.1949,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.854166666666667e-05,
+      "loss": 1.1488,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.2244,
+      "step": 900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.8958333333333334e-05,
+      "loss": 1.1557,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.916666666666667e-05,
+      "loss": 1.1331,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 1.9375e-05,
+      "loss": 1.235,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.9583333333333333e-05,
+      "loss": 1.1916,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.244140625,
+      "learning_rate": 1.979166666666667e-05,
+      "loss": 1.1931,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.455078125,
+      "learning_rate": 2e-05,
+      "loss": 1.1947,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.9999933893861945e-05,
+      "loss": 1.123,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.9999735576321776e-05,
+      "loss": 1.2481,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.99994050500015e-05,
+      "loss": 1.2567,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.9998942319271076e-05,
+      "loss": 1.1169,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 1.9998347390248377e-05,
+      "loss": 1.1375,
+      "step": 1010
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.999762027079909e-05,
+      "loss": 1.2387,
+      "step": 1020
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.9996760970536635e-05,
+      "loss": 1.239,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9995769500822007e-05,
+      "loss": 1.1548,
+      "step": 1040
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.9994645874763657e-05,
+      "loss": 1.1675,
+      "step": 1050
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.9993390107217302e-05,
+      "loss": 1.1675,
+      "step": 1060
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.71875,
+      "learning_rate": 1.999200221478573e-05,
+      "loss": 1.1909,
+      "step": 1070
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 1.1468,
+      "step": 1080
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9988830130412106e-05,
+      "loss": 1.2334,
+      "step": 1090
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.62109375,
+      "learning_rate": 1.9987045980408907e-05,
+      "loss": 1.2107,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.9985129789397633e-05,
+      "loss": 1.1329,
+      "step": 1110
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.9983081582712684e-05,
+      "loss": 1.2072,
+      "step": 1120
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.9980901387433866e-05,
+      "loss": 1.1971,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.9978589232386036e-05,
+      "loss": 1.2553,
+      "step": 1140
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.9976145148138727e-05,
+      "loss": 1.1773,
+      "step": 1150
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.9973569167005725e-05,
+      "loss": 1.2301,
+      "step": 1160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9970861323044667e-05,
+      "loss": 1.1788,
+      "step": 1170
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.1875,
+      "learning_rate": 1.9968021652056578e-05,
+      "loss": 1.2372,
+      "step": 1180
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.9965050191585388e-05,
+      "loss": 1.1555,
+      "step": 1190
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 1.1395,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.995871206108104e-05,
+      "loss": 1.2342,
+      "step": 1210
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.995534547484574e-05,
+      "loss": 1.1636,
+      "step": 1220
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 1.0984,
+      "step": 1230
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.65234375,
+      "learning_rate": 1.9948217482960334e-05,
+      "loss": 1.186,
+      "step": 1240
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.6328125,
+      "learning_rate": 1.9944456171551024e-05,
+      "loss": 1.2151,
+      "step": 1250
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.9940563382223196e-05,
+      "loss": 1.1904,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.993653916644431e-05,
+      "loss": 1.1485,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 1.1406,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.40625,
+      "learning_rate": 1.9928096670090552e-05,
+      "loss": 1.1583,
+      "step": 1290
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 1.992367850113585e-05,
+      "loss": 1.1775,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.9919129128968938e-05,
+      "loss": 1.173,
+      "step": 1310
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.9914448613738107e-05,
+      "loss": 1.1648,
+      "step": 1320
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.58203125,
+      "learning_rate": 1.9909637017325508e-05,
+      "loss": 1.0632,
+      "step": 1330
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 1.9904694403346362e-05,
+      "loss": 1.1756,
+      "step": 1340
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.989962083714808e-05,
+      "loss": 1.154,
+      "step": 1350
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9894416385809444e-05,
+      "loss": 1.1659,
+      "step": 1360
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 1.9889081118139694e-05,
+      "loss": 1.1852,
+      "step": 1370
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 1.988361510467761e-05,
+      "loss": 1.1686,
+      "step": 1380
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.9878018417690602e-05,
+      "loss": 1.2461,
+      "step": 1390
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.9872291131173743e-05,
+      "loss": 1.1913,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.9866433320848793e-05,
+      "loss": 1.2264,
+      "step": 1410
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.9860445064163193e-05,
+      "loss": 1.151,
+      "step": 1420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1875,
+      "learning_rate": 1.985432644028905e-05,
+      "loss": 1.1306,
+      "step": 1430
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 1.19,
+      "step": 1440
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.9841698416280554e-05,
+      "loss": 1.0554,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.983518918310418e-05,
+      "loss": 1.1399,
+      "step": 1460
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.9828549916653013e-05,
+      "loss": 1.1098,
+      "step": 1470
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.982178070470631e-05,
+      "loss": 1.1319,
+      "step": 1480
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.52734375,
+      "learning_rate": 1.9814881636761355e-05,
+      "loss": 1.2344,
+      "step": 1490
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.578125,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 1.1336,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16796875,
+      "learning_rate": 1.980069429944895e-05,
+      "loss": 1.1052,
+      "step": 1510
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.9793406217655516e-05,
+      "loss": 1.1314,
+      "step": 1520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.9785988655009386e-05,
+      "loss": 1.1783,
+      "step": 1530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.490234375,
+      "learning_rate": 1.977844170957984e-05,
+      "loss": 1.1526,
+      "step": 1540
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.977076548114677e-05,
+      "loss": 1.1069,
+      "step": 1550
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.9762960071199334e-05,
+      "loss": 1.2254,
+      "step": 1560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.640625,
+      "learning_rate": 1.975502558293464e-05,
+      "loss": 1.1648,
+      "step": 1570
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.974696212125635e-05,
+      "loss": 1.1854,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9738769792773338e-05,
+      "loss": 1.2473,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.1984,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.972199897034604e-05,
+      "loss": 1.1372,
+      "step": 1610
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.9713420698132614e-05,
+      "loss": 1.123,
+      "step": 1620
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.9704714002573255e-05,
+      "loss": 1.1167,
+      "step": 1630
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 1.9695878998781162e-05,
+      "loss": 1.1196,
+      "step": 1640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 1.9686915803565934e-05,
+      "loss": 1.1106,
+      "step": 1650
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9677824535432012e-05,
+      "loss": 1.1101,
+      "step": 1660
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.9668605314577124e-05,
+      "loss": 1.1876,
+      "step": 1670
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 1.1827,
+      "step": 1680
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9649783503952196e-05,
+      "loss": 1.1399,
+      "step": 1690
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.9640181163029597e-05,
+      "loss": 1.13,
+      "step": 1700
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.963045136707763e-05,
+      "loss": 1.1582,
+      "step": 1710
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.9620594244736133e-05,
+      "loss": 1.2255,
+      "step": 1720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.9610609926328373e-05,
+      "loss": 1.1538,
+      "step": 1730
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.960049854385929e-05,
+      "loss": 1.1813,
+      "step": 1740
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9590260231013774e-05,
+      "loss": 1.202,
+      "step": 1750
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.957989512315489e-05,
+      "loss": 1.1095,
+      "step": 1760
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 1.1931,
+      "step": 1770
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.9558785072229395e-05,
+      "loss": 1.1645,
+      "step": 1780
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.181640625,
+      "learning_rate": 1.9548040408263575e-05,
+      "loss": 1.1852,
+      "step": 1790
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.953716950748227e-05,
+      "loss": 1.0633,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.952617251361214e-05,
+      "loss": 1.1748,
+      "step": 1810
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.951504957204694e-05,
+      "loss": 1.075,
+      "step": 1820
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.16796875,
+      "learning_rate": 1.9503800829845613e-05,
+      "loss": 1.1498,
+      "step": 1830
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.68359375,
+      "learning_rate": 1.949242643573034e-05,
+      "loss": 1.1333,
+      "step": 1840
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.55078125,
+      "learning_rate": 1.9480926540084578e-05,
+      "loss": 1.1932,
+      "step": 1850
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.946930129495106e-05,
+      "loss": 1.2105,
+      "step": 1860
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.9457550854029797e-05,
+      "loss": 1.0915,
+      "step": 1870
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.944567537267605e-05,
+      "loss": 1.105,
+      "step": 1880
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.27734375,
+      "learning_rate": 1.9433675007898255e-05,
+      "loss": 1.1275,
+      "step": 1890
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 1.9421549918355965e-05,
+      "loss": 1.1369,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9409300264357757e-05,
+      "loss": 1.134,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.0956,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.9384427912460172e-05,
+      "loss": 1.1498,
+      "step": 1930
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.9371805543403826e-05,
+      "loss": 1.1962,
+      "step": 1940
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.935905926757326e-05,
+      "loss": 1.1103,
+      "step": 1950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.9346189253489888e-05,
+      "loss": 1.0858,
+      "step": 1960
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.9333195671311093e-05,
+      "loss": 1.1537,
+      "step": 1970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.932007869282799e-05,
+      "loss": 1.1339,
+      "step": 1980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9306838491463126e-05,
+      "loss": 1.0732,
+      "step": 1990
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.9293475242268224e-05,
+      "loss": 1.1001,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9279989121921846e-05,
+      "loss": 1.1295,
+      "step": 2010
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.9266380308727054e-05,
+      "loss": 1.1069,
+      "step": 2020
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.9252648982609065e-05,
+      "loss": 1.1003,
+      "step": 2030
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 1.098,
+      "step": 2040
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.66796875,
+      "learning_rate": 1.9224819519400825e-05,
+      "loss": 1.1447,
+      "step": 2050
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.91796875,
+      "learning_rate": 1.9210721750250237e-05,
+      "loss": 1.0511,
+      "step": 2060
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.9196502204050925e-05,
+      "loss": 1.1048,
+      "step": 2070
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.9182161068802742e-05,
+      "loss": 1.2156,
+      "step": 2080
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.16015625,
+      "learning_rate": 1.9167698534113105e-05,
+      "loss": 1.0455,
+      "step": 2090
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.9153114791194475e-05,
+      "loss": 1.2662,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.212890625,
+      "learning_rate": 1.9138410032861833e-05,
+      "loss": 1.1073,
+      "step": 2110
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.9123584453530145e-05,
+      "loss": 1.1808,
+      "step": 2120
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.910863824921176e-05,
+      "loss": 1.0918,
+      "step": 2130
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.9093571617513853e-05,
+      "loss": 1.1115,
+      "step": 2140
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.907838475763579e-05,
+      "loss": 1.1847,
+      "step": 2150
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 1.1355,
+      "step": 2160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.9047651158081827e-05,
+      "loss": 1.1227,
+      "step": 2170
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.9032104824741843e-05,
+      "loss": 1.156,
+      "step": 2180
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.901643907588816e-05,
+      "loss": 1.1995,
+      "step": 2190
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.900065411864121e-05,
+      "loss": 1.1294,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 1.898475016169751e-05,
+      "loss": 1.1487,
+      "step": 2210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.248046875,
+      "learning_rate": 1.8968727415326885e-05,
+      "loss": 1.1438,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 1.895258609136972e-05,
+      "loss": 1.1341,
+      "step": 2230
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 1.1479,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.169921875,
+      "learning_rate": 1.8919948565893144e-05,
+      "loss": 1.2063,
+      "step": 2250
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 1.8903452795881893e-05,
+      "loss": 1.1608,
+      "step": 2260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.8886839311294695e-05,
+      "loss": 1.1145,
+      "step": 2270
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 1.0683,
+      "step": 2280
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.19140625,
+      "learning_rate": 1.885326007854855e-05,
+      "loss": 1.1338,
+      "step": 2290
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.883629477434828e-05,
+      "loss": 1.1307,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 1.1751,
+      "step": 2310
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.880201391180111e-05,
+      "loss": 1.1072,
+      "step": 2320
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.8784698806689308e-05,
+      "loss": 1.1771,
+      "step": 2330
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.876726755707508e-05,
+      "loss": 1.1182,
+      "step": 2340
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.8749720393420948e-05,
+      "loss": 1.2228,
+      "step": 2350
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.20703125,
+      "learning_rate": 1.8732057547721962e-05,
+      "loss": 1.1807,
+      "step": 2360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.8714279253502616e-05,
+      "loss": 1.0115,
+      "step": 2370
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.8696385745813793e-05,
+      "loss": 1.0663,
+      "step": 2380
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.8678377261229624e-05,
+      "loss": 1.1894,
+      "step": 2390
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.2207,
+      "step": 2400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.8642016315269345e-05,
+      "loss": 1.092,
+      "step": 2410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.8623664334629576e-05,
+      "loss": 1.1397,
+      "step": 2420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.860519833856079e-05,
+      "loss": 1.1003,
+      "step": 2430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.8586618571206133e-05,
+      "loss": 1.1145,
+      "step": 2440
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.856792527821293e-05,
+      "loss": 1.1072,
+      "step": 2450
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.854911870672947e-05,
+      "loss": 1.2103,
+      "step": 2460
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.173828125,
+      "learning_rate": 1.8530199105401705e-05,
+      "loss": 1.2184,
+      "step": 2470
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 1.8511166724369997e-05,
+      "loss": 1.1892,
+      "step": 2480
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.849202181526579e-05,
+      "loss": 1.1147,
+      "step": 2490
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.177734375,
+      "learning_rate": 1.847276463120828e-05,
+      "loss": 1.1493,
+      "step": 2500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 1.8453395426801083e-05,
+      "loss": 1.1848,
+      "step": 2510
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.843391445812886e-05,
+      "loss": 1.1074,
+      "step": 2520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.24609375,
+      "learning_rate": 1.841432198275393e-05,
+      "loss": 1.1532,
+      "step": 2530
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.197265625,
+      "learning_rate": 1.8394618259712866e-05,
+      "loss": 1.1678,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 1.837480354951308e-05,
+      "loss": 1.1779,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 1.2235,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.833484221700044e-05,
+      "loss": 1.128,
+      "step": 2570
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 1.0884,
+      "step": 2580
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.8294440098560508e-05,
+      "loss": 1.152,
+      "step": 2590
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 1.8274074411415104e-05,
+      "loss": 1.1352,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.8253599330848638e-05,
+      "loss": 1.129,
+      "step": 2610
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.8233015127566805e-05,
+      "loss": 1.1701,
+      "step": 2620
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.8212322073718042e-05,
+      "loss": 1.1856,
+      "step": 2630
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 1.1635,
+      "step": 2640
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.817061051010554e-05,
+      "loss": 1.1203,
+      "step": 2650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.19140625,
+      "learning_rate": 1.8149592551819883e-05,
+      "loss": 1.1662,
+      "step": 2660
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 1.8128466845916156e-05,
+      "loss": 1.1825,
+      "step": 2670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.8107233671702123e-05,
+      "loss": 1.1868,
+      "step": 2680
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.212890625,
+      "learning_rate": 1.808589330990642e-05,
+      "loss": 1.1071,
+      "step": 2690
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 1.806444604267483e-05,
+      "loss": 1.1734,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.8042892153566543e-05,
+      "loss": 1.213,
+      "step": 2710
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.802123192755044e-05,
+      "loss": 1.1722,
+      "step": 2720
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.220703125,
+      "learning_rate": 1.7999465651001297e-05,
+      "loss": 1.0755,
+      "step": 2730
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.7977593611696017e-05,
+      "loss": 1.1852,
+      "step": 2740
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.19921875,
+      "learning_rate": 1.79556160988098e-05,
+      "loss": 1.1037,
+      "step": 2750
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.7933533402912354e-05,
+      "loss": 1.2323,
+      "step": 2760
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.791134581596402e-05,
+      "loss": 1.1885,
+      "step": 2770
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.7889053631311947e-05,
+      "loss": 1.1541,
+      "step": 2780
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 1.786665714368617e-05,
+      "loss": 1.1488,
+      "step": 2790
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.75,
+      "learning_rate": 1.784415664919576e-05,
+      "loss": 1.1424,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.782155244532487e-05,
+      "loss": 1.1235,
+      "step": 2810
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.7798844830928818e-05,
+      "loss": 1.3127,
+      "step": 2820
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.7776034106230156e-05,
+      "loss": 1.1475,
+      "step": 2830
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 1.775312057281466e-05,
+      "loss": 1.1558,
+      "step": 2840
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.171875,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 1.0776,
+      "step": 2850
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.236328125,
+      "learning_rate": 1.770698629296858e-05,
+      "loss": 1.1442,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.498046875,
+      "learning_rate": 1.7683766156489817e-05,
+      "loss": 1.1917,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.2439,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 1.763702142541032e-05,
+      "loss": 1.129,
+      "step": 2890
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.761349744883231e-05,
+      "loss": 1.1861,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.758987281247162e-05,
+      "loss": 1.1001,
+      "step": 2910
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.17578125,
+      "learning_rate": 1.756614782867493e-05,
+      "loss": 1.2019,
+      "step": 2920
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.7542322811115657e-05,
+      "loss": 1.1267,
+      "step": 2930
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.158203125,
+      "learning_rate": 1.7518398074789776e-05,
+      "loss": 1.1625,
+      "step": 2940
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 1.7494373936011674e-05,
+      "loss": 1.1846,
+      "step": 2950
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.7470250712409963e-05,
+      "loss": 1.0803,
+      "step": 2960
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 1.7446028722923266e-05,
+      "loss": 1.1674,
+      "step": 2970
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.240234375,
+      "learning_rate": 1.7421708287796017e-05,
+      "loss": 1.1976,
+      "step": 2980
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.23828125,
+      "learning_rate": 1.7397289728574234e-05,
+      "loss": 1.1307,
+      "step": 2990
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.737277336810124e-05,
+      "loss": 1.1122,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 1.7348159530513424e-05,
+      "loss": 1.1558,
+      "step": 3010
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.7323448541235922e-05,
+      "loss": 1.1335,
+      "step": 3020
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.7298640726978357e-05,
+      "loss": 1.1388,
+      "step": 3030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.7273736415730488e-05,
+      "loss": 1.207,
+      "step": 3040
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.25,
+      "learning_rate": 1.7248735936757882e-05,
+      "loss": 1.113,
+      "step": 3050
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.7223639620597556e-05,
+      "loss": 1.1843,
+      "step": 3060
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.189453125,
+      "learning_rate": 1.719844779905363e-05,
+      "loss": 1.1279,
+      "step": 3070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.18359375,
+      "learning_rate": 1.7173160805192895e-05,
+      "loss": 1.1639,
+      "step": 3080
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 1.7147778973340466e-05,
+      "loss": 1.1434,
+      "step": 3090
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.7122302639075313e-05,
+      "loss": 1.1951,
+      "step": 3100
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.7096732139225853e-05,
+      "loss": 1.1432,
+      "step": 3110
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.1327,
+      "step": 3120
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.314453125,
+      "learning_rate": 1.7045309996308107e-05,
+      "loss": 1.1622,
+      "step": 3130
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 1.7019459033103684e-05,
+      "loss": 1.1804,
+      "step": 3140
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 1.699351526403367e-05,
+      "loss": 1.0703,
+      "step": 3150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.30859375,
+      "learning_rate": 1.6967479032106552e-05,
+      "loss": 1.1724,
+      "step": 3160
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.694135068155327e-05,
+      "loss": 1.1547,
+      "step": 3170
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.6915130557822698e-05,
+      "loss": 1.1062,
+      "step": 3180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.6888819007577054e-05,
+      "loss": 1.1308,
+      "step": 3190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 1.0832,
+      "step": 3200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.386039555779461e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d4a06de6ad4a5ad19246a2d9699177460e0ea627a95ad02a4a8615ba437d95
+size 4920

checkpoint-6400/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.8.2

checkpoint-6400/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-6400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a22354916780dc7e21fa0f8e2826b0abaf61579856273bbfcdb5ed8991a63c2
+size 14741912

checkpoint-6400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08480820954be6038c38a1f15f497dd23e9c44385f5f240fbe0a247d785a74ba
+size 29632634

checkpoint-6400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186b09f4d4e3cfe4186282d9383d5544a391db0e9182ee285b24fe7421d82a61
+size 14244

checkpoint-6400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5c382f52a21ccb343c22d7461807df5c7b4e1cb8a1aad4c371b51e31ac14cb3
+size 1064

checkpoint-6400/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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-6400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-6400/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-6400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d4a06de6ad4a5ad19246a2d9699177460e0ea627a95ad02a4a8615ba437d95
+size 4920

checkpoint-9600/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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 0.8.2

checkpoint-9600/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 6,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-9600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3699447ec3e96f252059905bf4012a1556246207fe8f22412933e1542b509f06
+size 14741912

checkpoint-9600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c58ca16fda597630b51644f67a6f65e88f4211283ff09cdac71d88851478eac
+size 29632634

checkpoint-9600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae69203223709a5d11efcd08eeb5add69710556faca400fb80b96b4c0713167
+size 14244

checkpoint-9600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335ab87ca5673aee005648006732bacac37b65891c2d2a5c9cc63c121983415a
+size 1064

checkpoint-9600/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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-9600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

checkpoint-9600/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-9600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d4a06de6ad4a5ad19246a2d9699177460e0ea627a95ad02a4a8615ba437d95
+size 4920

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a48a252e1ad7221e4d793c4e115e1afd9d96515b6f74f9fed78b7a210b35fe
+size 1948291704

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93061f92a1824e9d7149039c11bf5228befab9f58c85a1bddfbd530ce6e16e42
+size 1981891624

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750cdc431f733ff53d91ff5ae913576dbb9dd6fceec3065fe6c2f934d289b861
+size 1082180264

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/Mar21_07-13-40_a518bf4a6403/events.out.tfevents.1711005287.a518bf4a6403.192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ba56673170366c7fdfab89dcd5ed7000bda34cb0acdfa5f4373e2b4725156e
+size 5049

runs/Mar21_07-18-25_a518bf4a6403/events.out.tfevents.1711005509.a518bf4a6403.2537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae1ab42c5c18b435a864ccdc44ab6b79cc1bb33273efba4872deb387082fad4
+size 207915

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5
+size 17477473

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}