Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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-3195/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,303 @@
+
+---
+license: other
+tags:
+- generated_from_trainer
+- google/gemma
+- PyTorch
+- transformers
+- trl
+- peft
+- tensorboard
+model-index:
+- name: pygemma-2b-ultra-plus-4
+  results: []
+datasets:
+- Vezora/Tested-143k-Python-Alpaca
+language:
+- en
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+base_model: google/gemma-2b
+widget:
+  - example_title: Compute Sum
+    messages:
+      - role: system
+        content: Welcome to PyGemma, your AI-powered Python assistant. I'm here to help you answer common questions about the Python programming language. Let's dive into Python!
+      - role: user
+        content: Create a function to calculate the sum of a sequence of integers.
+pipeline_tag: text-generation
+---
+
+# Model Card for pygemma-2b-ultra-plus-4:
+
+🐍💬🤖
+
+
+**pygemma-2b-ultra-plus-4** is a language model that is trained to act as Python 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
+[Vezora/Tested-143k-Python-Alpaca](https://huggingface.co/datasets/Vezora/Tested-143k-Python-Alpaca).
+
+
+## Training Metrics
+
+[The training metrics can be found on **TensorBoard**](https://huggingface.co/Menouar/pygemma-2b-ultra-plus-4/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: 1
+ 
+- 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/Mar23_06-23-59_676c0e3f20e7
+ 
+- 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-3195/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-3195/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": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-3195/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd625b359455e4352d1153e45020aee005e1e09e265477b2b5fcaad567ce30ff
+size 9838816

checkpoint-3195/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3aed2fb41dd455b9faaf780bea184ec5bce8c6e7142a982b12858012fde70a
+size 19826810

checkpoint-3195/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123889b2557c3007b6c1b9e0840775ae30087abd37920ed417aa2701cdfe28d5
+size 14244

checkpoint-3195/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cacd23a5a5633069cf656f96fd67e94805fd80bec4e2b44b07988996075ab05
+size 1064

checkpoint-3195/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-3195/tokenizer.json

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

checkpoint-3195/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-3195/trainer_state.json

@@ -0,0 +1,2254 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999921758860809,
+  "eval_steps": 500,
+  "global_step": 3195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 8.75,
+      "learning_rate": 6.25e-07,
+      "loss": 1.4854,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.25e-06,
+      "loss": 1.4963,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.4225,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.75,
+      "learning_rate": 2.5e-06,
+      "loss": 1.4683,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.5703125,
+      "learning_rate": 3.125e-06,
+      "loss": 1.4694,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8828125,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.4083,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.5234375,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.3923,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.5390625,
+      "learning_rate": 5e-06,
+      "loss": 1.4969,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.34375,
+      "learning_rate": 5.625e-06,
+      "loss": 1.4255,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.33203125,
+      "learning_rate": 6.25e-06,
+      "loss": 1.3765,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.447265625,
+      "learning_rate": 6.875e-06,
+      "loss": 1.398,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.921875,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.4115,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.0,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.4444,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.3917,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.33203125,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.3245,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1e-05,
+      "loss": 1.3306,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.67578125,
+      "learning_rate": 1.0625e-05,
+      "loss": 1.3055,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.41015625,
+      "learning_rate": 1.125e-05,
+      "loss": 1.3146,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.1875e-05,
+      "loss": 1.2607,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.59375,
+      "learning_rate": 1.25e-05,
+      "loss": 1.2867,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.3125e-05,
+      "loss": 1.2151,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.375e-05,
+      "loss": 1.1951,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.4375e-05,
+      "loss": 1.2246,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2181,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.5625e-05,
+      "loss": 1.1621,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.6250000000000002e-05,
+      "loss": 1.1737,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.6875e-05,
+      "loss": 1.1031,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.515625,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.089,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.8125e-05,
+      "loss": 1.1244,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.490234375,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 1.0991,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.263671875,
+      "learning_rate": 1.9375e-05,
+      "loss": 1.0563,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.27734375,
+      "learning_rate": 2e-05,
+      "loss": 1.0804,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.999940297883134e-05,
+      "loss": 1.0612,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9997611986612203e-05,
+      "loss": 1.0363,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.9994627237194654e-05,
+      "loss": 1.0389,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.279296875,
+      "learning_rate": 1.9990449086970404e-05,
+      "loss": 1.0362,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.998507803482828e-05,
+      "loss": 0.9951,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.205078125,
+      "learning_rate": 1.997851472209465e-05,
+      "loss": 1.003,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.9970759932456836e-05,
+      "loss": 1.0001,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.228515625,
+      "learning_rate": 1.9961814591869558e-05,
+      "loss": 0.9786,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.9951679768444346e-05,
+      "loss": 0.953,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.9940356672322037e-05,
+      "loss": 1.0563,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.992784665552824e-05,
+      "loss": 0.9525,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 1.9914151211811924e-05,
+      "loss": 0.967,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 1.9899271976467058e-05,
+      "loss": 0.9415,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.234375,
+      "learning_rate": 1.9883210726137324e-05,
+      "loss": 0.9645,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.9865969378604023e-05,
+      "loss": 1.0064,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.984754999255704e-05,
+      "loss": 0.9612,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.982795476734905e-05,
+      "loss": 0.9435,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.9807186042732908e-05,
+      "loss": 0.9315,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.9785246298582262e-05,
+      "loss": 0.9232,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.9762138154595448e-05,
+      "loss": 0.9407,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.9737864369982695e-05,
+      "loss": 0.934,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.55078125,
+      "learning_rate": 1.971242784313665e-05,
+      "loss": 0.9394,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.9639,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.965807885013437e-05,
+      "loss": 0.9751,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.259765625,
+      "learning_rate": 1.9629172873477995e-05,
+      "loss": 0.9354,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.2421875,
+      "learning_rate": 1.9599117132813187e-05,
+      "loss": 0.9653,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.208984375,
+      "learning_rate": 1.9567915216922624e-05,
+      "loss": 0.8997,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.9535570851447166e-05,
+      "loss": 0.918,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.9502087898440988e-05,
+      "loss": 0.9498,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.318359375,
+      "learning_rate": 1.9467470355910438e-05,
+      "loss": 0.9661,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.9431722357336657e-05,
+      "loss": 0.9206,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.197265625,
+      "learning_rate": 1.939484817118202e-05,
+      "loss": 0.9338,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 1.9356852200380466e-05,
+      "loss": 0.9092,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.9317738981811776e-05,
+      "loss": 0.9058,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.9277513185759847e-05,
+      "loss": 0.9105,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 1.9236179615355026e-05,
+      "loss": 0.9055,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.9193743206000618e-05,
+      "loss": 0.9213,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.9150209024783564e-05,
+      "loss": 0.8831,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 1.9105582269869413e-05,
+      "loss": 0.9176,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.275390625,
+      "learning_rate": 1.9059868269881637e-05,
+      "loss": 0.925,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 1.9013072483265377e-05,
+      "loss": 0.9372,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.896520049763568e-05,
+      "loss": 0.9168,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.8916258029110305e-05,
+      "loss": 0.9039,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.25390625,
+      "learning_rate": 1.88662509216272e-05,
+      "loss": 0.9119,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 1.8815185146246718e-05,
+      "loss": 0.9186,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.9072,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.87099021073541e-05,
+      "loss": 0.8682,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.236328125,
+      "learning_rate": 1.8655697415082556e-05,
+      "loss": 0.9198,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.8600459195893737e-05,
+      "loss": 0.9109,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.8544194045464888e-05,
+      "loss": 0.9052,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.8486908682093175e-05,
+      "loss": 0.9066,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.842860994589352e-05,
+      "loss": 0.9018,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 1.8369304797981843e-05,
+      "loss": 0.8559,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3203125,
+      "learning_rate": 1.8309000319643892e-05,
+      "loss": 0.9147,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.248046875,
+      "learning_rate": 1.8247703711489684e-05,
+      "loss": 0.8865,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.818542229259376e-05,
+      "loss": 0.9235,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.8122163499621208e-05,
+      "loss": 0.905,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2265625,
+      "learning_rate": 1.8057934885939734e-05,
+      "loss": 0.8682,
+      "step": 900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.7992744120717735e-05,
+      "loss": 0.9197,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.7926598988008584e-05,
+      "loss": 0.8708,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.7859507385821163e-05,
+      "loss": 0.8976,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.7791477325176824e-05,
+      "loss": 0.9113,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.7722516929152828e-05,
+      "loss": 0.9247,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.236328125,
+      "learning_rate": 1.7652634431912417e-05,
+      "loss": 0.9013,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.758183817772163e-05,
+      "loss": 0.8887,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1953125,
+      "learning_rate": 1.7510136619952947e-05,
+      "loss": 0.9126,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.21484375,
+      "learning_rate": 1.743753832007593e-05,
+      "loss": 0.8891,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.7364051946634953e-05,
+      "loss": 0.8732,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.9015,
+      "step": 1010
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.234375,
+      "learning_rate": 1.721445018238956e-05,
+      "loss": 0.8729,
+      "step": 1020
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.713835265466917e-05,
+      "loss": 0.8899,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.706140277741994e-05,
+      "loss": 0.9049,
+      "step": 1040
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.294921875,
+      "learning_rate": 1.6983609738782993e-05,
+      "loss": 0.8922,
+      "step": 1050
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.6904982827576498e-05,
+      "loss": 0.8582,
+      "step": 1060
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.6825531432186545e-05,
+      "loss": 0.9232,
+      "step": 1070
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 1.674526503944611e-05,
+      "loss": 0.9159,
+      "step": 1080
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.6664193233502314e-05,
+      "loss": 0.8846,
+      "step": 1090
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 1.6582325694672032e-05,
+      "loss": 0.9053,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.6499672198285996e-05,
+      "loss": 0.8655,
+      "step": 1110
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.6416242613521612e-05,
+      "loss": 0.868,
+      "step": 1120
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.287109375,
+      "learning_rate": 1.6332046902224518e-05,
+      "loss": 0.865,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.6247095117719106e-05,
+      "loss": 0.8863,
+      "step": 1140
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.265625,
+      "learning_rate": 1.616139740360811e-05,
+      "loss": 0.873,
+      "step": 1150
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.32421875,
+      "learning_rate": 1.607496399256141e-05,
+      "loss": 0.8586,
+      "step": 1160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.232421875,
+      "learning_rate": 1.5987805205094225e-05,
+      "loss": 0.8908,
+      "step": 1170
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.212890625,
+      "learning_rate": 1.5899931448334788e-05,
+      "loss": 0.9169,
+      "step": 1180
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.581135321478169e-05,
+      "loss": 0.9228,
+      "step": 1190
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.263671875,
+      "learning_rate": 1.5722081081051032e-05,
+      "loss": 0.9063,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.5632125706613534e-05,
+      "loss": 0.8776,
+      "step": 1210
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.25,
+      "learning_rate": 1.554149783252175e-05,
+      "loss": 0.8988,
+      "step": 1220
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.5450208280127543e-05,
+      "loss": 0.9082,
+      "step": 1230
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.9217,
+      "step": 1240
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.526568781957371e-05,
+      "loss": 0.8891,
+      "step": 1250
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.125,
+      "learning_rate": 1.5172478943938288e-05,
+      "loss": 0.8866,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.228515625,
+      "learning_rate": 1.5078652452418063e-05,
+      "loss": 0.8937,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.4984219548293361e-05,
+      "loss": 0.8948,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.4889191507252743e-05,
+      "loss": 0.8686,
+      "step": 1290
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2265625,
+      "learning_rate": 1.479357967604663e-05,
+      "loss": 0.8962,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.469739547113246e-05,
+      "loss": 0.9133,
+      "step": 1310
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.4600650377311523e-05,
+      "loss": 0.8863,
+      "step": 1320
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.450335594635761e-05,
+      "loss": 0.8887,
+      "step": 1330
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.44055237956377e-05,
+      "loss": 0.894,
+      "step": 1340
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.55859375,
+      "learning_rate": 1.4307165606724777e-05,
+      "loss": 0.8949,
+      "step": 1350
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.25,
+      "learning_rate": 1.4208293124003028e-05,
+      "loss": 0.8306,
+      "step": 1360
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.4108918153265485e-05,
+      "loss": 0.8799,
+      "step": 1370
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.220703125,
+      "learning_rate": 1.400905256030438e-05,
+      "loss": 0.8666,
+      "step": 1380
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.3908708269494318e-05,
+      "loss": 0.879,
+      "step": 1390
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.69921875,
+      "learning_rate": 1.3807897262368453e-05,
+      "loss": 0.881,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.3706631576187842e-05,
+      "loss": 0.8979,
+      "step": 1410
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.33203125,
+      "learning_rate": 1.3604923302504146e-05,
+      "loss": 0.854,
+      "step": 1420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.3502784585715853e-05,
+      "loss": 0.8637,
+      "step": 1430
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.340022762161817e-05,
+      "loss": 0.9253,
+      "step": 1440
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.244140625,
+      "learning_rate": 1.3297264655946816e-05,
+      "loss": 0.8995,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.23046875,
+      "learning_rate": 1.31939079829158e-05,
+      "loss": 0.8512,
+      "step": 1460
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.8573,
+      "step": 1470
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 1.2986062925208913e-05,
+      "loss": 0.8904,
+      "step": 1480
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.2881599358112888e-05,
+      "loss": 0.9029,
+      "step": 1490
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.2776791715853585e-05,
+      "loss": 0.8792,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.2671652512907213e-05,
+      "loss": 0.8639,
+      "step": 1510
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.2566194303339738e-05,
+      "loss": 0.8806,
+      "step": 1520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.2460429679307863e-05,
+      "loss": 0.9334,
+      "step": 1530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.306640625,
+      "learning_rate": 1.2354371269555478e-05,
+      "loss": 0.8936,
+      "step": 1540
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.2248031737905732e-05,
+      "loss": 0.9028,
+      "step": 1550
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.21875,
+      "learning_rate": 1.2141423781748913e-05,
+      "loss": 0.8395,
+      "step": 1560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.29296875,
+      "learning_rate": 1.2034560130526341e-05,
+      "loss": 0.8692,
+      "step": 1570
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.1927453544210397e-05,
+      "loss": 0.9154,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 1.182011681178095e-05,
+      "loss": 0.8881,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.171256274969829e-05,
+      "loss": 0.882,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.1604804200372786e-05,
+      "loss": 0.8779,
+      "step": 1610
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.30078125,
+      "learning_rate": 1.1496854030631443e-05,
+      "loss": 0.9221,
+      "step": 1620
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.1388725130181566e-05,
+      "loss": 0.8849,
+      "step": 1630
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2421875,
+      "learning_rate": 1.1280430410071652e-05,
+      "loss": 0.8786,
+      "step": 1640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.1171982801149774e-05,
+      "loss": 0.8964,
+      "step": 1650
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2734375,
+      "learning_rate": 1.106339525251958e-05,
+      "loss": 0.8832,
+      "step": 1660
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2265625,
+      "learning_rate": 1.0954680729994103e-05,
+      "loss": 0.8462,
+      "step": 1670
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.08458522145476e-05,
+      "loss": 0.888,
+      "step": 1680
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.073692270076557e-05,
+      "loss": 0.8778,
+      "step": 1690
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.8829,
+      "step": 1700
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.0518812715282001e-05,
+      "loss": 0.908,
+      "step": 1710
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.244140625,
+      "learning_rate": 1.0409658286836144e-05,
+      "loss": 0.8909,
+      "step": 1720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.216796875,
+      "learning_rate": 1.0300454943456457e-05,
+      "loss": 0.8656,
+      "step": 1730
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.0191215724484476e-05,
+      "loss": 0.8787,
+      "step": 1740
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.0081953673545432e-05,
+      "loss": 0.858,
+      "step": 1750
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.255859375,
+      "learning_rate": 9.9726818369908e-06,
+      "loss": 0.8747,
+      "step": 1760
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.59375,
+      "learning_rate": 9.863413262340491e-06,
+      "loss": 0.8954,
+      "step": 1770
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.26953125,
+      "learning_rate": 9.754160996724927e-06,
+      "loss": 0.8983,
+      "step": 1780
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.26953125,
+      "learning_rate": 9.644938085327174e-06,
+      "loss": 0.9041,
+      "step": 1790
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 9.535757569825266e-06,
+      "loss": 0.8551,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.318359375,
+      "learning_rate": 9.426632486834998e-06,
+      "loss": 0.8579,
+      "step": 1810
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.349609375,
+      "learning_rate": 9.317575866353293e-06,
+      "loss": 0.8752,
+      "step": 1820
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.255859375,
+      "learning_rate": 9.20860073020234e-06,
+      "loss": 0.9323,
+      "step": 1830
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.400390625,
+      "learning_rate": 9.099720090474779e-06,
+      "loss": 0.8816,
+      "step": 1840
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.251953125,
+      "learning_rate": 8.990946947979955e-06,
+      "loss": 0.9283,
+      "step": 1850
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.255859375,
+      "learning_rate": 8.882294290691609e-06,
+      "loss": 0.8712,
+      "step": 1860
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 8.773775092197018e-06,
+      "loss": 0.8743,
+      "step": 1870
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 8.665402310147924e-06,
+      "loss": 0.8768,
+      "step": 1880
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.482421875,
+      "learning_rate": 8.557188884713334e-06,
+      "loss": 0.8655,
+      "step": 1890
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.50390625,
+      "learning_rate": 8.44914773703438e-06,
+      "loss": 0.9007,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 8.341291767681523e-06,
+      "loss": 0.8856,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.224609375,
+      "learning_rate": 8.233633855114127e-06,
+      "loss": 0.8677,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2265625,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.906,
+      "step": 1930
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.265625,
+      "learning_rate": 8.018963594394221e-06,
+      "loss": 0.8833,
+      "step": 1940
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.314453125,
+      "learning_rate": 7.911976878779696e-06,
+      "loss": 0.8776,
+      "step": 1950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.805239481965976e-06,
+      "loss": 0.8933,
+      "step": 1960
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 7.698764148850138e-06,
+      "loss": 0.8808,
+      "step": 1970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.234375,
+      "learning_rate": 7.592563593037746e-06,
+      "loss": 0.8555,
+      "step": 1980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.32421875,
+      "learning_rate": 7.486650495324783e-06,
+      "loss": 0.8827,
+      "step": 1990
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.220703125,
+      "learning_rate": 7.3810375021835275e-06,
+      "loss": 0.8878,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.3515625,
+      "learning_rate": 7.275737224252504e-06,
+      "loss": 0.9144,
+      "step": 2010
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2890625,
+      "learning_rate": 7.1707622348307e-06,
+      "loss": 0.9125,
+      "step": 2020
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.0625,
+      "learning_rate": 7.066125068376297e-06,
+      "loss": 0.9072,
+      "step": 2030
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1953125,
+      "learning_rate": 6.961838219009968e-06,
+      "loss": 0.8861,
+      "step": 2040
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.28125,
+      "learning_rate": 6.857914139023058e-06,
+      "loss": 0.8747,
+      "step": 2050
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.234375,
+      "learning_rate": 6.7543652373906966e-06,
+      "loss": 0.8742,
+      "step": 2060
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.37890625,
+      "learning_rate": 6.651203878290139e-06,
+      "loss": 0.9203,
+      "step": 2070
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 6.548442379624425e-06,
+      "loss": 0.9225,
+      "step": 2080
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.22265625,
+      "learning_rate": 6.446093011551551e-06,
+      "loss": 0.8656,
+      "step": 2090
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.27734375,
+      "learning_rate": 6.344167995019395e-06,
+      "loss": 0.8547,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.267578125,
+      "learning_rate": 6.242679500306443e-06,
+      "loss": 0.8825,
+      "step": 2110
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.365234375,
+      "learning_rate": 6.141639645568646e-06,
+      "loss": 0.8829,
+      "step": 2120
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.22265625,
+      "learning_rate": 6.041060495392437e-06,
+      "loss": 0.898,
+      "step": 2130
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.255859375,
+      "learning_rate": 5.940954059354165e-06,
+      "loss": 0.8746,
+      "step": 2140
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 5.841332290586126e-06,
+      "loss": 0.8537,
+      "step": 2150
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.267578125,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.8474,
+      "step": 2160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.69921875,
+      "learning_rate": 5.643590276612909e-06,
+      "loss": 0.8786,
+      "step": 2170
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2265625,
+      "learning_rate": 5.545493642641389e-06,
+      "loss": 0.8978,
+      "step": 2180
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2421875,
+      "learning_rate": 5.447928895588128e-06,
+      "loss": 0.8659,
+      "step": 2190
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2265625,
+      "learning_rate": 5.350907685096983e-06,
+      "loss": 0.8711,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 5.254441595911255e-06,
+      "loss": 0.9029,
+      "step": 2210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.27734375,
+      "learning_rate": 5.1585421464904e-06,
+      "loss": 0.8667,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.208984375,
+      "learning_rate": 5.063220787634686e-06,
+      "loss": 0.8878,
+      "step": 2230
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 4.9684889011179335e-06,
+      "loss": 0.8642,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.25,
+      "learning_rate": 4.874357798328464e-06,
+      "loss": 0.904,
+      "step": 2250
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.20703125,
+      "learning_rate": 4.780838718918467e-06,
+      "loss": 0.8608,
+      "step": 2260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.408203125,
+      "learning_rate": 4.687942829461969e-06,
+      "loss": 0.8818,
+      "step": 2270
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.828125,
+      "learning_rate": 4.595681222121458e-06,
+      "loss": 0.8661,
+      "step": 2280
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.322265625,
+      "learning_rate": 4.504064913323472e-06,
+      "loss": 0.8675,
+      "step": 2290
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.953125,
+      "learning_rate": 4.413104842443149e-06,
+      "loss": 0.8823,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.1640625,
+      "learning_rate": 4.322811870498058e-06,
+      "loss": 0.8793,
+      "step": 2310
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.359375,
+      "learning_rate": 4.2331967788513295e-06,
+      "loss": 0.8819,
+      "step": 2320
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.20703125,
+      "learning_rate": 4.144270267924306e-06,
+      "loss": 0.883,
+      "step": 2330
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.306640625,
+      "learning_rate": 4.05604295591889e-06,
+      "loss": 0.8687,
+      "step": 2340
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 3.968525377549657e-06,
+      "loss": 0.9053,
+      "step": 2350
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.2734375,
+      "learning_rate": 3.881727982785999e-06,
+      "loss": 0.8831,
+      "step": 2360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.267578125,
+      "learning_rate": 3.7956611356043196e-06,
+      "loss": 0.8761,
+      "step": 2370
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.24609375,
+      "learning_rate": 3.7103351127505616e-06,
+      "loss": 0.8585,
+      "step": 2380
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.22265625,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.8917,
+      "step": 2390
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2421875,
+      "learning_rate": 3.5419462035062313e-06,
+      "loss": 0.8664,
+      "step": 2400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.263671875,
+      "learning_rate": 3.4589034234643315e-06,
+      "loss": 0.8929,
+      "step": 2410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.55859375,
+      "learning_rate": 3.376641678046926e-06,
+      "loss": 0.8898,
+      "step": 2420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 3.2951707896546858e-06,
+      "loss": 0.851,
+      "step": 2430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.25390625,
+      "learning_rate": 3.2145004862566185e-06,
+      "loss": 0.9009,
+      "step": 2440
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.134640400228479e-06,
+      "loss": 0.9137,
+      "step": 2450
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.373046875,
+      "learning_rate": 3.055600067202652e-06,
+      "loss": 0.8788,
+      "step": 2460
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.20703125,
+      "learning_rate": 2.9773889249295294e-06,
+      "loss": 0.8805,
+      "step": 2470
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 2.900016312150631e-06,
+      "loss": 0.8907,
+      "step": 2480
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.234375,
+      "learning_rate": 2.8234914674834913e-06,
+      "loss": 0.8522,
+      "step": 2490
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.345703125,
+      "learning_rate": 2.7478235283185504e-06,
+      "loss": 0.8695,
+      "step": 2500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.23828125,
+      "learning_rate": 2.673021529728108e-06,
+      "loss": 0.8858,
+      "step": 2510
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.330078125,
+      "learning_rate": 2.599094403387481e-06,
+      "loss": 0.8689,
+      "step": 2520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.279296875,
+      "learning_rate": 2.5260509765085474e-06,
+      "loss": 0.8793,
+      "step": 2530
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2734375,
+      "learning_rate": 2.453899970785716e-06,
+      "loss": 0.8603,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 2.382650001354543e-06,
+      "loss": 0.8901,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.349609375,
+      "learning_rate": 2.3123095757630344e-06,
+      "loss": 0.8641,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.248046875,
+      "learning_rate": 2.2428870929558012e-06,
+      "loss": 0.8881,
+      "step": 2570
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.23828125,
+      "learning_rate": 2.1743908422712135e-06,
+      "loss": 0.8668,
+      "step": 2580
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.375,
+      "learning_rate": 2.1068290024515925e-06,
+      "loss": 0.8652,
+      "step": 2590
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.341796875,
+      "learning_rate": 2.0402096406666562e-06,
+      "loss": 0.8652,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 1.974540711550248e-06,
+      "loss": 0.8757,
+      "step": 2610
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.9017,
+      "step": 2620
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.255859375,
+      "learning_rate": 1.8460854014937068e-06,
+      "loss": 0.8882,
+      "step": 2630
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.57421875,
+      "learning_rate": 1.783314358661441e-06,
+      "loss": 0.8795,
+      "step": 2640
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2578125,
+      "learning_rate": 1.7215244228820027e-06,
+      "loss": 0.8603,
+      "step": 2650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.474609375,
+      "learning_rate": 1.6607229721353202e-06,
+      "loss": 0.8964,
+      "step": 2660
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.6009172663720352e-06,
+      "loss": 0.9372,
+      "step": 2670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.5421144466466164e-06,
+      "loss": 0.8761,
+      "step": 2680
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.22265625,
+      "learning_rate": 1.4843215342646922e-06,
+      "loss": 0.8741,
+      "step": 2690
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.265625,
+      "learning_rate": 1.4275454299446834e-06,
+      "loss": 0.8693,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2421875,
+      "learning_rate": 1.3717929129938179e-06,
+      "loss": 0.8818,
+      "step": 2710
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.3170706404986645e-06,
+      "loss": 0.898,
+      "step": 2720
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.263385146530234e-06,
+      "loss": 0.8536,
+      "step": 2730
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.26171875,
+      "learning_rate": 1.2107428413637979e-06,
+      "loss": 0.8681,
+      "step": 2740
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.15915001071347e-06,
+      "loss": 0.8945,
+      "step": 2750
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 1.1086128149816544e-06,
+      "loss": 0.8397,
+      "step": 2760
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.0591372885234885e-06,
+      "loss": 0.8802,
+      "step": 2770
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.0107293389262918e-06,
+      "loss": 0.8737,
+      "step": 2780
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.232421875,
+      "learning_rate": 9.63394746304198e-07,
+      "loss": 0.8718,
+      "step": 2790
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.203125,
+      "learning_rate": 9.171391626079629e-07,
+      "loss": 0.846,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.251953125,
+      "learning_rate": 8.719681109501177e-07,
+      "loss": 0.8911,
+      "step": 2810
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.494140625,
+      "learning_rate": 8.278869849454718e-07,
+      "loss": 0.8883,
+      "step": 2820
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 7.849010480670938e-07,
+      "loss": 0.864,
+      "step": 2830
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.28515625,
+      "learning_rate": 7.43015433017844e-07,
+      "loss": 0.9335,
+      "step": 2840
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.244140625,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.8826,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.20703125,
+      "learning_rate": 6.625650417055296e-07,
+      "loss": 0.8849,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.30859375,
+      "learning_rate": 6.240098715597975e-07,
+      "loss": 0.8893,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.59765625,
+      "learning_rate": 5.865742343308345e-07,
+      "loss": 0.8404,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 5.502625999922207e-07,
+      "loss": 0.8526,
+      "step": 2890
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.150793043068269e-07,
+      "loss": 0.9014,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 4.810285483091181e-07,
+      "loss": 0.8988,
+      "step": 2910
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.205078125,
+      "learning_rate": 4.481143978035196e-07,
+      "loss": 0.8694,
+      "step": 2920
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.236328125,
+      "learning_rate": 4.163407828789523e-07,
+      "loss": 0.886,
+      "step": 2930
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.396484375,
+      "learning_rate": 3.857114974395604e-07,
+      "loss": 0.9012,
+      "step": 2940
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.5623019875169916e-07,
+      "loss": 0.9189,
+      "step": 2950
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 3.2790040700725114e-07,
+      "loss": 0.8781,
+      "step": 2960
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 3.0072550490328754e-07,
+      "loss": 0.8869,
+      "step": 2970
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.283203125,
+      "learning_rate": 2.7470873723817405e-07,
+      "loss": 0.8857,
+      "step": 2980
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.23828125,
+      "learning_rate": 2.498532105241158e-07,
+      "loss": 0.8306,
+      "step": 2990
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.23828125,
+      "learning_rate": 2.2616189261623568e-07,
+      "loss": 0.9102,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.578125,
+      "learning_rate": 2.0363761235819402e-07,
+      "loss": 0.8871,
+      "step": 3010
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.8228305924441469e-07,
+      "loss": 0.8874,
+      "step": 3020
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.267578125,
+      "learning_rate": 1.621007830989496e-07,
+      "loss": 0.9135,
+      "step": 3030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.515625,
+      "learning_rate": 1.430931937710156e-07,
+      "loss": 0.8767,
+      "step": 3040
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 1.2526256084725351e-07,
+      "loss": 0.8801,
+      "step": 3050
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.0861101338072499e-07,
+      "loss": 0.8397,
+      "step": 3060
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.25390625,
+      "learning_rate": 9.314053963669245e-08,
+      "loss": 0.8851,
+      "step": 3070
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.875,
+      "step": 3080
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.575006103060388e-08,
+      "loss": 0.8589,
+      "step": 3090
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.28515625,
+      "learning_rate": 5.3833326707656284e-08,
+      "loss": 0.8344,
+      "step": 3100
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.50390625,
+      "learning_rate": 4.310420679490945e-08,
+      "loss": 0.8784,
+      "step": 3110
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 3.356398239470427e-08,
+      "loss": 0.8732,
+      "step": 3120
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.220703125,
+      "learning_rate": 2.5213792650227165e-08,
+      "loss": 0.8971,
+      "step": 3130
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.46484375,
+      "learning_rate": 1.8054634609484534e-08,
+      "loss": 0.8758,
+      "step": 3140
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.23828125,
+      "learning_rate": 1.20873631062568e-08,
+      "loss": 0.9064,
+      "step": 3150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 7.312690658024535e-09,
+      "loss": 0.863,
+      "step": 3160
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.24609375,
+      "learning_rate": 3.731187380893176e-09,
+      "loss": 0.8839,
+      "step": 3170
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.343280921518586e-09,
+      "loss": 0.8454,
+      "step": 3180
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2060546875,
+      "learning_rate": 1.4925640603902226e-10,
+      "loss": 0.8938,
+      "step": 3190
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3195,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 9.360190605990298e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3195/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1e05b8e300b18fc94d29705ee77bdedbf07abf9ebcbd16ed1d7f0c7ba97de5
+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:a885db92be88a2020a3bd239868df652341fde5483d4efd3266384ced6f6b722
+size 1948291704

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e16ade0685a75be0969bb55645e18ab885b22786f54c74662ac11d3c5b6e556
+size 1981891624

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1ce63a91c8bec7f58436be451975fd812ed75664f9a1ebe11741315f119035
+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/Mar23_06-21-09_676c0e3f20e7/events.out.tfevents.1711174939.676c0e3f20e7.1229.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596615eb9391963cdd77f7c5ddc803ebb2b9cf822f3aacccf6ab78eb5ae7a132
+size 4184

runs/Mar23_06-23-59_676c0e3f20e7/events.out.tfevents.1711175043.676c0e3f20e7.3429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70c8043f04c5e378a91b3e9431cba02c7dda613e7605553d29e84a7f00943bd
+size 72664

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
+}