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-3189/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,301 @@
+
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- google/gemma
+- PyTorch
+- transformers
+- trl
+- peft
+- tensorboard
+model-index:
+- name: pygemma-2b-it
+  results: []
+datasets:
+- Vezora/Tested-143k-Python-Alpaca
+language:
+- en
+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-it:
+
+🐍💬🤖
+
+
+**pygemma-2b-it** is a language model that is trained to act as Python assistant. It is a finetuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) 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-it/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/Mar27_16-25-16_393edc92728c
+ 
+- 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-3189/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-2b-it
+---
+
+# 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-3189/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-3189/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9dff0bf83a8edff7cd20a1aefc13b5c88269824e89faf44b978a9f52d269e3
+size 14741912

checkpoint-3189/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8428fddbaa60a70bcaa2f37ccb1259242f389e743d2d28147c5ce4c72072010
+size 29632634

checkpoint-3189/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0c9ad8ed7f26da07b2ebdefd5b26221bb755988b49b34d6e3873456f009d84
+size 14244

checkpoint-3189/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3052206627118932eac0246dd2f0072d1c016df2fe5429652766e4eb44c70e
+size 1064

checkpoint-3189/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-3189/tokenizer.json

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

checkpoint-3189/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-3189/trainer_state.json

@@ -0,0 +1,2247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998432356168678,
+  "eval_steps": 500,
+  "global_step": 3189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.1328125,
+      "learning_rate": 6.269592476489028e-07,
+      "loss": 2.1857,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.15625,
+      "learning_rate": 1.2539184952978056e-06,
+      "loss": 2.2401,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.171875,
+      "learning_rate": 1.8808777429467086e-06,
+      "loss": 2.2405,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.1796875,
+      "learning_rate": 2.507836990595611e-06,
+      "loss": 2.2319,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.1347962382445144e-06,
+      "loss": 2.1898,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1171875,
+      "learning_rate": 3.7617554858934172e-06,
+      "loss": 2.2211,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4.3887147335423205e-06,
+      "loss": 2.1384,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.1640625,
+      "learning_rate": 5.015673981191222e-06,
+      "loss": 2.1226,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.1171875,
+      "learning_rate": 5.642633228840125e-06,
+      "loss": 2.0606,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.140625,
+      "learning_rate": 6.269592476489029e-06,
+      "loss": 2.0945,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 2.0137,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.21875,
+      "learning_rate": 7.5235109717868345e-06,
+      "loss": 1.9084,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.150470219435737e-06,
+      "loss": 1.8718,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.09375,
+      "learning_rate": 8.777429467084641e-06,
+      "loss": 1.7715,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.404388714733543e-06,
+      "loss": 1.6878,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.0031347962382445e-05,
+      "loss": 1.5875,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.76953125,
+      "learning_rate": 1.0658307210031348e-05,
+      "loss": 1.5414,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.64453125,
+      "learning_rate": 1.128526645768025e-05,
+      "loss": 1.4793,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.74609375,
+      "learning_rate": 1.1912225705329154e-05,
+      "loss": 1.4169,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.7578125,
+      "learning_rate": 1.2539184952978058e-05,
+      "loss": 1.3904,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.316614420062696e-05,
+      "loss": 1.3295,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.3793103448275863e-05,
+      "loss": 1.3289,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.97265625,
+      "learning_rate": 1.4420062695924765e-05,
+      "loss": 1.257,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.9296875,
+      "learning_rate": 1.5047021943573669e-05,
+      "loss": 1.2668,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.567398119122257e-05,
+      "loss": 1.2188,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.375,
+      "learning_rate": 1.6300940438871475e-05,
+      "loss": 1.2408,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.6927899686520378e-05,
+      "loss": 1.1614,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.7554858934169282e-05,
+      "loss": 1.1643,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 1.1071,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.8808777429467086e-05,
+      "loss": 1.1014,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.943573667711599e-05,
+      "loss": 1.1347,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.999999400890905e-05,
+      "loss": 1.0571,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.9999275086680688e-05,
+      "loss": 1.0499,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.326171875,
+      "learning_rate": 1.9997358044965833e-05,
+      "loss": 1.0195,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.291015625,
+      "learning_rate": 1.9994243113465627e-05,
+      "loss": 0.9811,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.328125,
+      "learning_rate": 1.9989930665413148e-05,
+      "loss": 0.9659,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3046875,
+      "learning_rate": 1.9984421217528654e-05,
+      "loss": 1.0054,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.997771542995769e-05,
+      "loss": 1.0214,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9969814106191973e-05,
+      "loss": 0.9312,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.996071819297314e-05,
+      "loss": 0.9643,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.9950428780179274e-05,
+      "loss": 0.9579,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.9938947100694354e-05,
+      "loss": 0.9325,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.330078125,
+      "learning_rate": 1.99262745302605e-05,
+      "loss": 0.983,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.337890625,
+      "learning_rate": 1.991241258731314e-05,
+      "loss": 0.9483,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.9897362932799078e-05,
+      "loss": 0.9132,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.988112736997747e-05,
+      "loss": 0.9624,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.33984375,
+      "learning_rate": 1.9863707844203756e-05,
+      "loss": 0.9126,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.408203125,
+      "learning_rate": 1.9845106442696563e-05,
+      "loss": 0.905,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.982532539428763e-05,
+      "loss": 0.9313,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.980436706915473e-05,
+      "loss": 0.9669,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.978223397853768e-05,
+      "loss": 0.9132,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.9758928774437444e-05,
+      "loss": 0.9013,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9734454249298367e-05,
+      "loss": 0.9473,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.9708813335673582e-05,
+      "loss": 0.9341,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.9682009105873633e-05,
+      "loss": 0.9394,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.9654044771598343e-05,
+      "loss": 0.9168,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.9624923683551992e-05,
+      "loss": 0.894,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.9594649331041826e-05,
+      "loss": 0.9145,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.9563225341559982e-05,
+      "loss": 0.9234,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.9530655480348823e-05,
+      "loss": 0.9097,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.9496943649949777e-05,
+      "loss": 0.8847,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.9462093889735766e-05,
+      "loss": 0.8769,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.9426110375427175e-05,
+      "loss": 0.9179,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.9388997418591518e-05,
+      "loss": 0.9184,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.9350759466126838e-05,
+      "loss": 0.8625,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.9311401099728865e-05,
+      "loss": 0.9069,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.927092703534204e-05,
+      "loss": 0.9142,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.922934212259444e-05,
+      "loss": 0.8774,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.38671875,
+      "learning_rate": 1.9186651344216703e-05,
+      "loss": 0.8555,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.373046875,
+      "learning_rate": 1.9142859815444982e-05,
+      "loss": 0.9122,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.909797278340805e-05,
+      "loss": 0.9002,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.905199562649857e-05,
+      "loss": 0.913,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.900493385372866e-05,
+      "loss": 0.8859,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.41015625,
+      "learning_rate": 1.8956793104069797e-05,
+      "loss": 0.8955,
+      "step": 740
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.447265625,
+      "learning_rate": 1.8907579145777156e-05,
+      "loss": 0.8676,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.8857297875698455e-05,
+      "loss": 0.8559,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.880595531856738e-05,
+      "loss": 0.8908,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.875355762628171e-05,
+      "loss": 0.871,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.49609375,
+      "learning_rate": 1.8700111077166186e-05,
+      "loss": 0.8959,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.498046875,
+      "learning_rate": 1.8645622075220246e-05,
+      "loss": 0.8651,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.859009714935067e-05,
+      "loss": 0.8543,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.8533542952589322e-05,
+      "loss": 0.8772,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.8475966261295947e-05,
+      "loss": 0.8792,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.841737397434623e-05,
+      "loss": 0.8888,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.8357773112305183e-05,
+      "loss": 0.8525,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.56640625,
+      "learning_rate": 1.829717081658591e-05,
+      "loss": 0.8562,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.823557434859395e-05,
+      "loss": 0.8433,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.8172991088857187e-05,
+      "loss": 0.873,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.8109428536141515e-05,
+      "loss": 0.8523,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.8044894306552338e-05,
+      "loss": 0.8178,
+      "step": 900
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.408203125,
+      "learning_rate": 1.7979396132621997e-05,
+      "loss": 0.8542,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.791294186238327e-05,
+      "loss": 0.8755,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.7845539458428973e-05,
+      "loss": 0.8354,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.7777196996957934e-05,
+      "loss": 0.9218,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.770792266680725e-05,
+      "loss": 0.8447,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.7637724768471127e-05,
+      "loss": 0.8294,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.388671875,
+      "learning_rate": 1.7566611713106287e-05,
+      "loss": 0.86,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.5078125,
+      "learning_rate": 1.7494592021524156e-05,
+      "loss": 0.878,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.7421674323169885e-05,
+      "loss": 0.8435,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.404296875,
+      "learning_rate": 1.7347867355088358e-05,
+      "loss": 0.8335,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.7273179960877335e-05,
+      "loss": 0.8757,
+      "step": 1010
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.7197621089627785e-05,
+      "loss": 0.818,
+      "step": 1020
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.712119979485161e-05,
+      "loss": 0.883,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.7043925233396855e-05,
+      "loss": 0.8833,
+      "step": 1040
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.6965806664350505e-05,
+      "loss": 0.8822,
+      "step": 1050
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.6886853447929082e-05,
+      "loss": 0.8766,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.478515625,
+      "learning_rate": 1.6807075044357074e-05,
+      "loss": 0.8363,
+      "step": 1070
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.6726481012733437e-05,
+      "loss": 0.8681,
+      "step": 1080
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.6645081009886178e-05,
+      "loss": 0.8692,
+      "step": 1090
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.384765625,
+      "learning_rate": 1.6562884789215298e-05,
+      "loss": 0.8569,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.431640625,
+      "learning_rate": 1.6479902199524116e-05,
+      "loss": 0.885,
+      "step": 1110
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.6396143183839192e-05,
+      "loss": 0.8938,
+      "step": 1120
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.6311617778218945e-05,
+      "loss": 0.8443,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.4765625,
+      "learning_rate": 1.622633611055111e-05,
+      "loss": 0.8257,
+      "step": 1140
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.614030839933923e-05,
+      "loss": 0.874,
+      "step": 1150
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.6053544952478258e-05,
+      "loss": 0.87,
+      "step": 1160
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.5966056166019453e-05,
+      "loss": 0.8557,
+      "step": 1170
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.439453125,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.8833,
+      "step": 1180
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.5788944591810588e-05,
+      "loss": 0.8315,
+      "step": 1190
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.46484375,
+      "learning_rate": 1.5699343025681746e-05,
+      "loss": 0.8635,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.560905856065472e-05,
+      "loss": 0.8579,
+      "step": 1210
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.45703125,
+      "learning_rate": 1.5518102014671405e-05,
+      "loss": 0.8502,
+      "step": 1220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.5426484286202863e-05,
+      "loss": 0.8804,
+      "step": 1230
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.390625,
+      "learning_rate": 1.5334216352943464e-05,
+      "loss": 0.8496,
+      "step": 1240
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.5241309270495524e-05,
+      "loss": 0.8425,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.5147774171044619e-05,
+      "loss": 0.8578,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.447265625,
+      "learning_rate": 1.5053622262025718e-05,
+      "loss": 0.8598,
+      "step": 1270
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.495886482478032e-05,
+      "loss": 0.8864,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.4863513213204681e-05,
+      "loss": 0.8334,
+      "step": 1290
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.476757885238942e-05,
+      "loss": 0.8612,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.4671073237250519e-05,
+      "loss": 0.8449,
+      "step": 1310
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.515625,
+      "learning_rate": 1.4574007931152037e-05,
+      "loss": 0.8501,
+      "step": 1320
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.412109375,
+      "learning_rate": 1.4476394564520542e-05,
+      "loss": 0.8367,
+      "step": 1330
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.4378244833451576e-05,
+      "loss": 0.8656,
+      "step": 1340
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.4279570498308198e-05,
+      "loss": 0.8767,
+      "step": 1350
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.46875,
+      "learning_rate": 1.4180383382311867e-05,
+      "loss": 0.8521,
+      "step": 1360
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.4080695370125761e-05,
+      "loss": 0.8959,
+      "step": 1370
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.48828125,
+      "learning_rate": 1.3980518406430767e-05,
+      "loss": 0.849,
+      "step": 1380
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.3879864494494252e-05,
+      "loss": 0.8495,
+      "step": 1390
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5234375,
+      "learning_rate": 1.3778745694731816e-05,
+      "loss": 0.826,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.3677174123262216e-05,
+      "loss": 0.8623,
+      "step": 1410
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.3575161950455604e-05,
+      "loss": 0.8474,
+      "step": 1420
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.3472721399475266e-05,
+      "loss": 0.8403,
+      "step": 1430
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.3369864744813025e-05,
+      "loss": 0.8379,
+      "step": 1440
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.3266604310818525e-05,
+      "loss": 0.8801,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.470703125,
+      "learning_rate": 1.3162952470222488e-05,
+      "loss": 0.8501,
+      "step": 1460
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.48046875,
+      "learning_rate": 1.3058921642654235e-05,
+      "loss": 0.8755,
+      "step": 1470
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.2954524293153546e-05,
+      "loss": 0.8114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.2849772930677087e-05,
+      "loss": 0.8221,
+      "step": 1490
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4609375,
+      "learning_rate": 1.274468010659959e-05,
+      "loss": 0.8379,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.2639258413209922e-05,
+      "loss": 0.8338,
+      "step": 1510
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.2533520482202293e-05,
+      "loss": 0.8463,
+      "step": 1520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.482421875,
+      "learning_rate": 1.2427478983162694e-05,
+      "loss": 0.8561,
+      "step": 1530
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.2321146622050838e-05,
+      "loss": 0.8377,
+      "step": 1540
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.41015625,
+      "learning_rate": 1.2214536139677712e-05,
+      "loss": 0.8703,
+      "step": 1550
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.44140625,
+      "learning_rate": 1.2107660310178966e-05,
+      "loss": 0.8378,
+      "step": 1560
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.47265625,
+      "learning_rate": 1.2000531939484321e-05,
+      "loss": 0.8509,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.1893163863783131e-05,
+      "loss": 0.8289,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.1785568947986368e-05,
+      "loss": 0.8373,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.44140625,
+      "learning_rate": 1.1677760084185123e-05,
+      "loss": 0.8202,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4375,
+      "learning_rate": 1.1569750190105871e-05,
+      "loss": 0.8372,
+      "step": 1610
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5234375,
+      "learning_rate": 1.1461552207562665e-05,
+      "loss": 0.8803,
+      "step": 1620
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.466796875,
+      "learning_rate": 1.1353179100906438e-05,
+      "loss": 0.8625,
+      "step": 1630
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.1244643855471603e-05,
+      "loss": 0.8754,
+      "step": 1640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.1135959476020144e-05,
+      "loss": 0.8621,
+      "step": 1650
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.1027138985183381e-05,
+      "loss": 0.8583,
+      "step": 1660
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.486328125,
+      "learning_rate": 1.0918195421901583e-05,
+      "loss": 0.8384,
+      "step": 1670
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.080914183986164e-05,
+      "loss": 0.8043,
+      "step": 1680
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.435546875,
+      "learning_rate": 1.0699991305932955e-05,
+      "loss": 0.8519,
+      "step": 1690
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.0590756898601775e-05,
+      "loss": 0.8593,
+      "step": 1700
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.43359375,
+      "learning_rate": 1.0481451706404104e-05,
+      "loss": 0.8366,
+      "step": 1710
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.4296875,
+      "learning_rate": 1.0372088826357443e-05,
+      "loss": 0.8655,
+      "step": 1720
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.5703125,
+      "learning_rate": 1.0262681362391473e-05,
+      "loss": 0.8525,
+      "step": 1730
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.0153242423777964e-05,
+      "loss": 0.8553,
+      "step": 1740
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5234375,
+      "learning_rate": 1.004378512355999e-05,
+      "loss": 0.8411,
+      "step": 1750
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.447265625,
+      "learning_rate": 9.934322576980721e-06,
+      "loss": 0.8177,
+      "step": 1760
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5078125,
+      "learning_rate": 9.824867899911962e-06,
+      "loss": 0.8661,
+      "step": 1770
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.47265625,
+      "learning_rate": 9.715434207282574e-06,
+      "loss": 0.835,
+      "step": 1780
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.408203125,
+      "learning_rate": 9.606034611507058e-06,
+      "loss": 0.8702,
+      "step": 1790
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.4453125,
+      "learning_rate": 9.496682220914403e-06,
+      "loss": 0.8272,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.416015625,
+      "learning_rate": 9.387390138177447e-06,
+      "loss": 0.8434,
+      "step": 1810
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.478515625,
+      "learning_rate": 9.278171458742903e-06,
+      "loss": 0.8639,
+      "step": 1820
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.419921875,
+      "learning_rate": 9.16903926926225e-06,
+      "loss": 0.8371,
+      "step": 1830
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.3984375,
+      "learning_rate": 9.060006646023683e-06,
+      "loss": 0.8489,
+      "step": 1840
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.412109375,
+      "learning_rate": 8.951086653385323e-06,
+      "loss": 0.848,
+      "step": 1850
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.4375,
+      "learning_rate": 8.842292342209801e-06,
+      "loss": 0.8177,
+      "step": 1860
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.458984375,
+      "learning_rate": 8.733636748300524e-06,
+      "loss": 0.837,
+      "step": 1870
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.474609375,
+      "learning_rate": 8.625132890839706e-06,
+      "loss": 0.8526,
+      "step": 1880
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.453125,
+      "learning_rate": 8.516793770828412e-06,
+      "loss": 0.871,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.48046875,
+      "learning_rate": 8.40863236952875e-06,
+      "loss": 0.8217,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.427734375,
+      "learning_rate": 8.30066164690847e-06,
+      "loss": 0.8344,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.46484375,
+      "learning_rate": 8.192894540088061e-06,
+      "loss": 0.8646,
+      "step": 1920
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.439453125,
+      "learning_rate": 8.085343961790666e-06,
+      "loss": 0.8456,
+      "step": 1930
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.447265625,
+      "learning_rate": 7.978022798794825e-06,
+      "loss": 0.8373,
+      "step": 1940
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.435546875,
+      "learning_rate": 7.870943910390392e-06,
+      "loss": 0.8718,
+      "step": 1950
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.447265625,
+      "learning_rate": 7.764120126837731e-06,
+      "loss": 0.8596,
+      "step": 1960
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.466796875,
+      "learning_rate": 7.657564247830381e-06,
+      "loss": 0.8568,
+      "step": 1970
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.439453125,
+      "learning_rate": 7.551289040961381e-06,
+      "loss": 0.832,
+      "step": 1980
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.4375,
+      "learning_rate": 7.445307240193462e-06,
+      "loss": 0.8485,
+      "step": 1990
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.43359375,
+      "learning_rate": 7.33963154433325e-06,
+      "loss": 0.8321,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.462890625,
+      "learning_rate": 7.234274615509686e-06,
+      "loss": 0.8492,
+      "step": 2010
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.4609375,
+      "learning_rate": 7.129249077656844e-06,
+      "loss": 0.8391,
+      "step": 2020
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.455078125,
+      "learning_rate": 7.02456751500131e-06,
+      "loss": 0.8256,
+      "step": 2030
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.455078125,
+      "learning_rate": 6.920242470554366e-06,
+      "loss": 0.8354,
+      "step": 2040
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.41015625,
+      "learning_rate": 6.816286444609037e-06,
+      "loss": 0.8848,
+      "step": 2050
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.412109375,
+      "learning_rate": 6.712711893242325e-06,
+      "loss": 0.8308,
+      "step": 2060
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.421875,
+      "learning_rate": 6.6095312268226955e-06,
+      "loss": 0.8383,
+      "step": 2070
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.44921875,
+      "learning_rate": 6.5067568085230896e-06,
+      "loss": 0.8878,
+      "step": 2080
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4609375,
+      "learning_rate": 6.404400952839522e-06,
+      "loss": 0.8623,
+      "step": 2090
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.45703125,
+      "learning_rate": 6.302475924115581e-06,
+      "loss": 0.872,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.44921875,
+      "learning_rate": 6.2009939350728865e-06,
+      "loss": 0.8555,
+      "step": 2110
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.458984375,
+      "learning_rate": 6.09996714534777e-06,
+      "loss": 0.8631,
+      "step": 2120
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.478515625,
+      "learning_rate": 5.999407660034289e-06,
+      "loss": 0.8645,
+      "step": 2130
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.4375,
+      "learning_rate": 5.899327528233787e-06,
+      "loss": 0.8597,
+      "step": 2140
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.478515625,
+      "learning_rate": 5.7997387416111685e-06,
+      "loss": 0.8945,
+      "step": 2150
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.412109375,
+      "learning_rate": 5.700653232958047e-06,
+      "loss": 0.8599,
+      "step": 2160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4375,
+      "learning_rate": 5.602082874762952e-06,
+      "loss": 0.8354,
+      "step": 2170
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.48828125,
+      "learning_rate": 5.50403947778875e-06,
+      "loss": 0.8688,
+      "step": 2180
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.470703125,
+      "learning_rate": 5.40653478965749e-06,
+      "loss": 0.8757,
+      "step": 2190
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.5,
+      "learning_rate": 5.309580493442784e-06,
+      "loss": 0.8201,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.453125,
+      "learning_rate": 5.213188206269926e-06,
+      "loss": 0.8627,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.427734375,
+      "learning_rate": 5.1173694779239415e-06,
+      "loss": 0.8582,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.408203125,
+      "learning_rate": 5.0221357894656605e-06,
+      "loss": 0.8264,
+      "step": 2230
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.4765625,
+      "learning_rate": 4.927498551856077e-06,
+      "loss": 0.8992,
+      "step": 2240
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.470703125,
+      "learning_rate": 4.83346910458906e-06,
+      "loss": 0.8369,
+      "step": 2250
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.41015625,
+      "learning_rate": 4.740058714332647e-06,
+      "loss": 0.8433,
+      "step": 2260
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.423828125,
+      "learning_rate": 4.64727857357908e-06,
+      "loss": 0.8378,
+      "step": 2270
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.458984375,
+      "learning_rate": 4.555139799303706e-06,
+      "loss": 0.8623,
+      "step": 2280
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4375,
+      "learning_rate": 4.463653431632926e-06,
+      "loss": 0.8542,
+      "step": 2290
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.372830432521377e-06,
+      "loss": 0.8069,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.44140625,
+      "learning_rate": 4.282681684438439e-06,
+      "loss": 0.841,
+      "step": 2310
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.439453125,
+      "learning_rate": 4.193217989064332e-06,
+      "loss": 0.862,
+      "step": 2320
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4296875,
+      "learning_rate": 4.104450065995799e-06,
+      "loss": 0.8575,
+      "step": 2330
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.478515625,
+      "learning_rate": 4.0163885514617175e-06,
+      "loss": 0.8578,
+      "step": 2340
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.435546875,
+      "learning_rate": 3.929043997048647e-06,
+      "loss": 0.8467,
+      "step": 2350
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.44140625,
+      "learning_rate": 3.8424268684365204e-06,
+      "loss": 0.8407,
+      "step": 2360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.466796875,
+      "learning_rate": 3.756547544144664e-06,
+      "loss": 0.851,
+      "step": 2370
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4140625,
+      "learning_rate": 3.671416314288204e-06,
+      "loss": 0.8157,
+      "step": 2380
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.453125,
+      "learning_rate": 3.587043379345134e-06,
+      "loss": 0.8471,
+      "step": 2390
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.455078125,
+      "learning_rate": 3.503438848934063e-06,
+      "loss": 0.8575,
+      "step": 2400
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.46875,
+      "learning_rate": 3.4206127406028744e-06,
+      "loss": 0.8357,
+      "step": 2410
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.447265625,
+      "learning_rate": 3.338574978628436e-06,
+      "loss": 0.8485,
+      "step": 2420
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.478515625,
+      "learning_rate": 3.257335392827451e-06,
+      "loss": 0.8503,
+      "step": 2430
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4453125,
+      "learning_rate": 3.1769037173786376e-06,
+      "loss": 0.848,
+      "step": 2440
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.5390625,
+      "learning_rate": 3.0972895896564004e-06,
+      "loss": 0.847,
+      "step": 2450
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.4140625,
+      "learning_rate": 3.0185025490760346e-06,
+      "loss": 0.8655,
+      "step": 2460
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.44140625,
+      "learning_rate": 2.9405520359507543e-06,
+      "loss": 0.8491,
+      "step": 2470
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.408203125,
+      "learning_rate": 2.8634473903605008e-06,
+      "loss": 0.8385,
+      "step": 2480
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.453125,
+      "learning_rate": 2.787197851032848e-06,
+      "loss": 0.8366,
+      "step": 2490
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.41796875,
+      "learning_rate": 2.7118125542359775e-06,
+      "loss": 0.8262,
+      "step": 2500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.43359375,
+      "learning_rate": 2.6373005326839973e-06,
+      "loss": 0.855,
+      "step": 2510
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.44921875,
+      "learning_rate": 2.563670714454617e-06,
+      "loss": 0.808,
+      "step": 2520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.474609375,
+      "learning_rate": 2.4909319219193774e-06,
+      "loss": 0.8427,
+      "step": 2530
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.455078125,
+      "learning_rate": 2.4190928706865634e-06,
+      "loss": 0.8568,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.419921875,
+      "learning_rate": 2.3481621685568867e-06,
+      "loss": 0.8825,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.494140625,
+      "learning_rate": 2.2781483144920833e-06,
+      "loss": 0.8631,
+      "step": 2560
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.453125,
+      "learning_rate": 2.209059697596585e-06,
+      "loss": 0.8518,
+      "step": 2570
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.43359375,
+      "learning_rate": 2.1409045961123067e-06,
+      "loss": 0.8221,
+      "step": 2580
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.435546875,
+      "learning_rate": 2.073691176426761e-06,
+      "loss": 0.8804,
+      "step": 2590
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.0074274920945537e-06,
+      "loss": 0.8412,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.9421214828723857e-06,
+      "loss": 0.848,
+      "step": 2610
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.8777809737677299e-06,
+      "loss": 0.8372,
+      "step": 2620
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.453125,
+      "learning_rate": 1.8144136741012209e-06,
+      "loss": 0.8216,
+      "step": 2630
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.7520271765829112e-06,
+      "loss": 0.8504,
+      "step": 2640
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.690628956402528e-06,
+      "loss": 0.8346,
+      "step": 2650
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.408203125,
+      "learning_rate": 1.6302263703337774e-06,
+      "loss": 0.8484,
+      "step": 2660
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.5708266558528562e-06,
+      "loss": 0.8687,
+      "step": 2670
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.512436930271244e-06,
+      "loss": 0.8391,
+      "step": 2680
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.4550641898829165e-06,
+      "loss": 0.8207,
+      "step": 2690
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.421875,
+      "learning_rate": 1.3987153091260398e-06,
+      "loss": 0.8343,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.44921875,
+      "learning_rate": 1.3433970397592599e-06,
+      "loss": 0.8498,
+      "step": 2710
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.458984375,
+      "learning_rate": 1.2891160100527222e-06,
+      "loss": 0.8372,
+      "step": 2720
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.2358787239938497e-06,
+      "loss": 0.8286,
+      "step": 2730
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.455078125,
+      "learning_rate": 1.1836915605080445e-06,
+      "loss": 0.8899,
+      "step": 2740
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.50390625,
+      "learning_rate": 1.1325607726943567e-06,
+      "loss": 0.8343,
+      "step": 2750
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.41796875,
+      "learning_rate": 1.0824924870762243e-06,
+      "loss": 0.8134,
+      "step": 2760
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.4453125,
+      "learning_rate": 1.033492702867407e-06,
+      "loss": 0.8391,
+      "step": 2770
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.45703125,
+      "learning_rate": 9.855672912531455e-07,
+      "loss": 0.8719,
+      "step": 2780
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.439453125,
+      "learning_rate": 9.387219946866699e-07,
+      "loss": 0.8157,
+      "step": 2790
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.42578125,
+      "learning_rate": 8.929624262011472e-07,
+      "loss": 0.8486,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.46484375,
+      "learning_rate": 8.482940687371067e-07,
+      "loss": 0.8514,
+      "step": 2810
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.43359375,
+      "learning_rate": 8.047222744854943e-07,
+      "loss": 0.8384,
+      "step": 2820
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.50390625,
+      "learning_rate": 7.622522642463425e-07,
+      "loss": 0.848,
+      "step": 2830
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.462890625,
+      "learning_rate": 7.208891268032336e-07,
+      "loss": 0.8472,
+      "step": 2840
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.4296875,
+      "learning_rate": 6.80637818313541e-07,
+      "loss": 0.8309,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46484375,
+      "learning_rate": 6.415031617145951e-07,
+      "loss": 0.8309,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.453125,
+      "learning_rate": 6.034898461457861e-07,
+      "loss": 0.8478,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.470703125,
+      "learning_rate": 5.666024263867042e-07,
+      "loss": 0.8276,
+      "step": 2880
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.308453223113962e-07,
+      "loss": 0.8676,
+      "step": 2890
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.44140625,
+      "learning_rate": 4.962228183587669e-07,
+      "loss": 0.8098,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.416015625,
+      "learning_rate": 4.6273906301920744e-07,
+      "loss": 0.8382,
+      "step": 2910
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4765625,
+      "learning_rate": 4.303980683375353e-07,
+      "loss": 0.8405,
+      "step": 2920
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.431640625,
+      "learning_rate": 3.992037094322532e-07,
+      "loss": 0.8273,
+      "step": 2930
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.984375,
+      "learning_rate": 3.691597240312439e-07,
+      "loss": 0.8326,
+      "step": 2940
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.439453125,
+      "learning_rate": 3.4026971202390404e-07,
+      "loss": 0.8732,
+      "step": 2950
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.470703125,
+      "learning_rate": 3.1253713502980566e-07,
+      "loss": 0.8436,
+      "step": 2960
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.404296875,
+      "learning_rate": 2.8596531598392264e-07,
+      "loss": 0.8522,
+      "step": 2970
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.44140625,
+      "learning_rate": 2.605574387384779e-07,
+      "loss": 0.8684,
+      "step": 2980
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.42578125,
+      "learning_rate": 2.363165476814455e-07,
+      "loss": 0.8315,
+      "step": 2990
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.416015625,
+      "learning_rate": 2.132455473717765e-07,
+      "loss": 0.8442,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.913472021913665e-07,
+      "loss": 0.8329,
+      "step": 3010
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.7062413601383498e-07,
+      "loss": 0.8163,
+      "step": 3020
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.5107883189012018e-07,
+      "loss": 0.8183,
+      "step": 3030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.416015625,
+      "learning_rate": 1.3271363175096696e-07,
+      "loss": 0.8535,
+      "step": 3040
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.482421875,
+      "learning_rate": 1.1553073612631138e-07,
+      "loss": 0.8443,
+      "step": 3050
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.443359375,
+      "learning_rate": 9.953220388160934e-08,
+      "loss": 0.8592,
+      "step": 3060
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.451171875,
+      "learning_rate": 8.471995197114836e-08,
+      "loss": 0.866,
+      "step": 3070
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.41796875,
+      "learning_rate": 7.109575520835244e-08,
+      "loss": 0.8496,
+      "step": 3080
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.43359375,
+      "learning_rate": 5.866124605312329e-08,
+      "loss": 0.8474,
+      "step": 3090
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.466796875,
+      "learning_rate": 4.7417914416239e-08,
+      "loss": 0.8686,
+      "step": 3100
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.46875,
+      "learning_rate": 3.7367107480832385e-08,
+      "loss": 0.8247,
+      "step": 3110
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.427734375,
+      "learning_rate": 2.8510029540967933e-08,
+      "loss": 0.8272,
+      "step": 3120
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.45703125,
+      "learning_rate": 2.084774185734495e-08,
+      "loss": 0.854,
+      "step": 3130
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.423828125,
+      "learning_rate": 1.4381162530135995e-08,
+      "loss": 0.8252,
+      "step": 3140
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.470703125,
+      "learning_rate": 9.111066388981515e-09,
+      "loss": 0.8625,
+      "step": 3150
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.45703125,
+      "learning_rate": 5.0380849001430145e-09,
+      "loss": 0.867,
+      "step": 3160
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.443359375,
+      "learning_rate": 2.1627060908491204e-09,
+      "loss": 0.8625,
+      "step": 3170
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.419921875,
+      "learning_rate": 4.85274490813481e-10,
+      "loss": 0.8536,
+      "step": 3180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 9.354140440917443e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3189/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a50bb29af61128838551564313ec7ef05270e9d44a714e155b92224762eba7
+size 4920

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-2b-it",
+  "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:cc2cea5a61c9ae74f27f1809b3bde24fe9a76c2abcfec204445868b6b21ff827
+size 1948291704

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5697814e1f6135c2b8b36a9bbecf186bd02c3932915464a6ee51ff2c4045f770
+size 1981891624

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b24640163e7e0667f65d62a2d013576af0c990ee24000b878cf6640f75fa35
+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/Mar27_16-25-16_393edc92728c/events.out.tfevents.1711556787.393edc92728c.586.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2110e5e457105af639fd86b32c8b57883f96aa3d4c30ed6964fa7801cdb0d3a
+size 72456

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
+}