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-3749/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
+  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: "fdfsdfsdf"
+      - 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:
+
+🐍💬🤖
+
+
+**pygemma-2b-ultra** 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/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/Mar22_07-15-06_2013f91d074a
+ 
+- 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-3749/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-3749/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": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-3749/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dff5f5739a22609780f6256bdec4c7a30fa5e53cff194b27f38d214ca48460
+size 627607208

checkpoint-3749/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6ad0ae7d8dd82e7b06383e1498aa397946ec4c79063f1e24eb453f807f3131
+size 1255362234

checkpoint-3749/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f356f9214bda56da16f0591c90def82a5e9a821de831bf8bd2cf977581605a46
+size 14244

checkpoint-3749/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf79e87b7bc60d4db7206dfaed011f213a4b9fad391b75707212de5af9b0e65
+size 1064

checkpoint-3749/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-3749/tokenizer.json

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

checkpoint-3749/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-3749/trainer_state.json

@@ -0,0 +1,2639 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9997999866657777,
+  "eval_steps": 500,
+  "global_step": 3749,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.333333333333335e-07,
+      "loss": 2.017,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.734375,
+      "learning_rate": 1.066666666666667e-06,
+      "loss": 2.3713,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.234375,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 2.1764,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.90234375,
+      "learning_rate": 2.133333333333334e-06,
+      "loss": 2.1757,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.4453125,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.1736,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.125,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 2.1865,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.7333333333333337e-06,
+      "loss": 2.0263,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.015625,
+      "learning_rate": 4.266666666666668e-06,
+      "loss": 1.9312,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.8754,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.70703125,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.7123,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.90625,
+      "learning_rate": 5.8666666666666675e-06,
+      "loss": 1.8266,
+      "step": 110
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.97265625,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.6079,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7578125,
+      "learning_rate": 6.9333333333333344e-06,
+      "loss": 1.5006,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.3359375,
+      "learning_rate": 7.4666666666666675e-06,
+      "loss": 1.4158,
+      "step": 140
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.068359375,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3677,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.384765625,
+      "learning_rate": 8.533333333333335e-06,
+      "loss": 1.374,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.296875,
+      "learning_rate": 9.066666666666667e-06,
+      "loss": 1.3052,
+      "step": 170
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.275,
+      "step": 180
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 1.0133333333333335e-05,
+      "loss": 1.2574,
+      "step": 190
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.09765625,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 1.2239,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2109375,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 1.1565,
+      "step": 210
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.1733333333333335e-05,
+      "loss": 1.1758,
+      "step": 220
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.138671875,
+      "learning_rate": 1.2266666666666667e-05,
+      "loss": 1.1843,
+      "step": 230
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.22265625,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 1.1936,
+      "step": 240
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1426,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 1.3866666666666669e-05,
+      "loss": 1.114,
+      "step": 260
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 1.1195,
+      "step": 270
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.043701171875,
+      "learning_rate": 1.4933333333333335e-05,
+      "loss": 1.1256,
+      "step": 280
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.041015625,
+      "learning_rate": 1.546666666666667e-05,
+      "loss": 1.102,
+      "step": 290
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.0762,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.0419921875,
+      "learning_rate": 1.6533333333333333e-05,
+      "loss": 1.0761,
+      "step": 310
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.09765625,
+      "learning_rate": 1.706666666666667e-05,
+      "loss": 1.0501,
+      "step": 320
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.041015625,
+      "learning_rate": 1.76e-05,
+      "loss": 1.0105,
+      "step": 330
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 1.8133333333333335e-05,
+      "loss": 1.0232,
+      "step": 340
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.989,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.034423828125,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.9894,
+      "step": 360
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 1.9733333333333336e-05,
+      "loss": 0.9824,
+      "step": 370
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0439453125,
+      "learning_rate": 1.999989162756852e-05,
+      "loss": 0.9569,
+      "step": 380
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.034912109375,
+      "learning_rate": 1.999902466221011e-05,
+      "loss": 0.928,
+      "step": 390
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 1.9997290806656996e-05,
+      "loss": 0.9349,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 1.9994690211230084e-05,
+      "loss": 0.9489,
+      "step": 410
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 1.999122310139442e-05,
+      "loss": 0.916,
+      "step": 420
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.034912109375,
+      "learning_rate": 1.9986889777739686e-05,
+      "loss": 0.9541,
+      "step": 430
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 1.9981690615954097e-05,
+      "loss": 0.9155,
+      "step": 440
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 1.9975626066791855e-05,
+      "loss": 0.9015,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 1.996869665603406e-05,
+      "loss": 0.9115,
+      "step": 460
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 1.996090298444313e-05,
+      "loss": 0.896,
+      "step": 470
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 1.9952245727710723e-05,
+      "loss": 0.8855,
+      "step": 480
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.193359375,
+      "learning_rate": 1.9942725636399136e-05,
+      "loss": 0.9084,
+      "step": 490
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 1.9932343535876255e-05,
+      "loss": 0.8899,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.9921100326243977e-05,
+      "loss": 0.8952,
+      "step": 510
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.038330078125,
+      "learning_rate": 1.9908996982260196e-05,
+      "loss": 0.8857,
+      "step": 520
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 1.9896034553254284e-05,
+      "loss": 0.8677,
+      "step": 530
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 1.988221416303611e-05,
+      "loss": 0.8637,
+      "step": 540
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.041748046875,
+      "learning_rate": 1.986753700979861e-05,
+      "loss": 0.8384,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 1.985200436601392e-05,
+      "loss": 0.9015,
+      "step": 560
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 1.9835617578323038e-05,
+      "loss": 0.8564,
+      "step": 570
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 1.9818378067419092e-05,
+      "loss": 0.8183,
+      "step": 580
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 1.9800287327924152e-05,
+      "loss": 0.8358,
+      "step": 590
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.9781346928259662e-05,
+      "loss": 0.8564,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 1.9761558510510453e-05,
+      "loss": 0.8295,
+      "step": 610
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 1.974092379028239e-05,
+      "loss": 0.8403,
+      "step": 620
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.064453125,
+      "learning_rate": 1.9719444556553616e-05,
+      "loss": 0.8582,
+      "step": 630
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 1.969712267151948e-05,
+      "loss": 0.8328,
+      "step": 640
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 1.9673960070431043e-05,
+      "loss": 0.8571,
+      "step": 650
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 1.9649958761427364e-05,
+      "loss": 0.824,
+      "step": 660
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 1.9625120825361326e-05,
+      "loss": 0.8418,
+      "step": 670
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 1.9599448415619283e-05,
+      "loss": 0.8267,
+      "step": 680
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 1.957294375793435e-05,
+      "loss": 0.8677,
+      "step": 690
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.031005859375,
+      "learning_rate": 1.954560915019343e-05,
+      "loss": 0.827,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 1.951744696223801e-05,
+      "loss": 0.8303,
+      "step": 710
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.024169921875,
+      "learning_rate": 1.9488459635658687e-05,
+      "loss": 0.8455,
+      "step": 720
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.041259765625,
+      "learning_rate": 1.945864968358349e-05,
+      "loss": 0.8297,
+      "step": 730
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 1.9428019690460008e-05,
+      "loss": 0.8516,
+      "step": 740
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 1.939657231183132e-05,
+      "loss": 0.8538,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.037109375,
+      "learning_rate": 1.9364310274105758e-05,
+      "loss": 0.8045,
+      "step": 760
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.034423828125,
+      "learning_rate": 1.933123637432054e-05,
+      "loss": 0.8436,
+      "step": 770
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 1.929735347989929e-05,
+      "loss": 0.8123,
+      "step": 780
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.92626645284034e-05,
+      "loss": 0.8184,
+      "step": 790
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.047119140625,
+      "learning_rate": 1.92271725272774e-05,
+      "loss": 0.8222,
+      "step": 800
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 1.919088055358818e-05,
+      "loss": 0.8434,
+      "step": 810
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.224609375,
+      "learning_rate": 1.9153791753758236e-05,
+      "loss": 0.8413,
+      "step": 820
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 1.911590934329288e-05,
+      "loss": 0.8323,
+      "step": 830
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 1.9077236606501465e-05,
+      "loss": 0.7935,
+      "step": 840
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.022705078125,
+      "learning_rate": 1.903777689621263e-05,
+      "loss": 0.8186,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 1.899753363348364e-05,
+      "loss": 0.8094,
+      "step": 860
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 1.895651030730378e-05,
+      "loss": 0.8265,
+      "step": 870
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 1.891471047429186e-05,
+      "loss": 0.9105,
+      "step": 880
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 1.8872137758387873e-05,
+      "loss": 0.8028,
+      "step": 890
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 1.8828795850538804e-05,
+      "loss": 0.8322,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.8784688508378655e-05,
+      "loss": 0.798,
+      "step": 910
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 1.8739819555902626e-05,
+      "loss": 0.8202,
+      "step": 920
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 1.8694192883135632e-05,
+      "loss": 0.8819,
+      "step": 930
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 1.8647812445795003e-05,
+      "loss": 0.8273,
+      "step": 940
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 1.8600682264947566e-05,
+      "loss": 0.8294,
+      "step": 950
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 1.8552806426661022e-05,
+      "loss": 0.8222,
+      "step": 960
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.185546875,
+      "learning_rate": 1.8504189081649678e-05,
+      "loss": 0.8109,
+      "step": 970
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 1.8454834444914607e-05,
+      "loss": 0.7972,
+      "step": 980
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 1.8404746795378218e-05,
+      "loss": 0.8107,
+      "step": 990
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.087890625,
+      "learning_rate": 1.8353930475513268e-05,
+      "loss": 0.8208,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 1.8302389890966404e-05,
+      "loss": 0.7933,
+      "step": 1010
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 1.8250129510176183e-05,
+      "loss": 0.814,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 1.8197153863985686e-05,
+      "loss": 0.8251,
+      "step": 1030
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 1.8143467545249694e-05,
+      "loss": 0.7962,
+      "step": 1040
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 1.8089075208436507e-05,
+      "loss": 0.8164,
+      "step": 1050
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.0223388671875,
+      "learning_rate": 1.8033981569224404e-05,
+      "loss": 0.8081,
+      "step": 1060
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 1.797819140409282e-05,
+      "loss": 0.8211,
+      "step": 1070
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 1.7921709549908222e-05,
+      "loss": 0.8526,
+      "step": 1080
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 1.7864540903504777e-05,
+      "loss": 0.8195,
+      "step": 1090
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0230712890625,
+      "learning_rate": 1.7806690421259794e-05,
+      "loss": 0.7951,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 1.774816311866404e-05,
+      "loss": 0.8389,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 1.768896406988689e-05,
+      "loss": 0.8031,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 1.7629098407336415e-05,
+      "loss": 0.8188,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 1.756857132121443e-05,
+      "loss": 0.8232,
+      "step": 1140
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.043701171875,
+      "learning_rate": 1.7507388059066492e-05,
+      "loss": 0.8126,
+      "step": 1150
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.06982421875,
+      "learning_rate": 1.7445553925326963e-05,
+      "loss": 0.7775,
+      "step": 1160
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 1.7383074280859132e-05,
+      "loss": 0.8205,
+      "step": 1170
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.7319954542490448e-05,
+      "loss": 0.8158,
+      "step": 1180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.041259765625,
+      "learning_rate": 1.725620018254286e-05,
+      "loss": 0.8146,
+      "step": 1190
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.271484375,
+      "learning_rate": 1.7191816728358435e-05,
+      "loss": 0.8259,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 1.71268097618201e-05,
+      "loss": 0.8213,
+      "step": 1210
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 1.706118491886774e-05,
+      "loss": 0.7947,
+      "step": 1220
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 1.6994947889009563e-05,
+      "loss": 0.8364,
+      "step": 1230
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 1.692810441482884e-05,
+      "loss": 0.8268,
+      "step": 1240
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.6860660291486023e-05,
+      "loss": 0.7868,
+      "step": 1250
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 1.6792621366216338e-05,
+      "loss": 0.8402,
+      "step": 1260
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.036865234375,
+      "learning_rate": 1.6723993537822837e-05,
+      "loss": 0.81,
+      "step": 1270
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 1.6654782756164983e-05,
+      "loss": 0.8151,
+      "step": 1280
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 1.6584995021642814e-05,
+      "loss": 0.7716,
+      "step": 1290
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 1.651463638467673e-05,
+      "loss": 0.8236,
+      "step": 1300
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.031005859375,
+      "learning_rate": 1.6443712945182933e-05,
+      "loss": 0.7794,
+      "step": 1310
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.03955078125,
+      "learning_rate": 1.637223085204457e-05,
+      "loss": 0.8222,
+      "step": 1320
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 1.630019630257865e-05,
+      "loss": 0.8134,
+      "step": 1330
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 1.6227615541998756e-05,
+      "loss": 0.8209,
+      "step": 1340
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 1.6154494862873588e-05,
+      "loss": 0.79,
+      "step": 1350
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.6080840604581435e-05,
+      "loss": 0.812,
+      "step": 1360
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 1.600665915276054e-05,
+      "loss": 0.8119,
+      "step": 1370
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 1.5931956938755494e-05,
+      "loss": 0.8073,
+      "step": 1380
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0220947265625,
+      "learning_rate": 1.585674043905966e-05,
+      "loss": 0.8205,
+      "step": 1390
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 1.5781016174753675e-05,
+      "loss": 0.8222,
+      "step": 1400
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 1.5704790710940074e-05,
+      "loss": 0.8307,
+      "step": 1410
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 1.5628070656174135e-05,
+      "loss": 0.8038,
+      "step": 1420
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 1.5550862661890918e-05,
+      "loss": 0.7824,
+      "step": 1430
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 1.547317342182861e-05,
+      "loss": 0.7891,
+      "step": 1440
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.5395009671448186e-05,
+      "loss": 0.8051,
+      "step": 1450
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 1.5316378187349476e-05,
+      "loss": 0.7899,
+      "step": 1460
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.02734375,
+      "learning_rate": 1.5237285786683638e-05,
+      "loss": 0.827,
+      "step": 1470
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.034912109375,
+      "learning_rate": 1.515773932656213e-05,
+      "loss": 0.8107,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0213623046875,
+      "learning_rate": 1.5077745703462228e-05,
+      "loss": 0.7785,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 1.4997311852629097e-05,
+      "loss": 0.8053,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.029296875,
+      "learning_rate": 1.4916444747474542e-05,
+      "loss": 0.8034,
+      "step": 1510
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 1.4835151398972424e-05,
+      "loss": 0.8117,
+      "step": 1520
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.0303955078125,
+      "learning_rate": 1.475343885505083e-05,
+      "loss": 0.7811,
+      "step": 1530
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.166015625,
+      "learning_rate": 1.4671314199981019e-05,
+      "loss": 0.8069,
+      "step": 1540
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 1.4588784553763262e-05,
+      "loss": 0.8312,
+      "step": 1550
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 1.4505857071509523e-05,
+      "loss": 0.8132,
+      "step": 1560
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 1.4422538942823158e-05,
+      "loss": 0.812,
+      "step": 1570
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.822,
+      "step": 1580
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 1.425475967328001e-05,
+      "loss": 0.8269,
+      "step": 1590
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.046630859375,
+      "learning_rate": 1.4170313078462318e-05,
+      "loss": 0.8027,
+      "step": 1600
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.115234375,
+      "learning_rate": 1.4085504928029086e-05,
+      "loss": 0.8123,
+      "step": 1610
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 1.4000342574632846e-05,
+      "loss": 0.8028,
+      "step": 1620
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 1.3914833401634642e-05,
+      "loss": 0.7812,
+      "step": 1630
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.036865234375,
+      "learning_rate": 1.3828984822463895e-05,
+      "loss": 0.8294,
+      "step": 1640
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 1.3742804279975686e-05,
+      "loss": 0.8118,
+      "step": 1650
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 1.3656299245805476e-05,
+      "loss": 0.8086,
+      "step": 1660
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.03955078125,
+      "learning_rate": 1.3569477219721336e-05,
+      "loss": 0.8155,
+      "step": 1670
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 1.3482345728973742e-05,
+      "loss": 0.8394,
+      "step": 1680
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 1.3394912327642966e-05,
+      "loss": 0.8172,
+      "step": 1690
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 1.330718459598417e-05,
+      "loss": 0.7993,
+      "step": 1700
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 1.3219170139770213e-05,
+      "loss": 0.7824,
+      "step": 1710
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 1.3130876589632243e-05,
+      "loss": 0.7982,
+      "step": 1720
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.037109375,
+      "learning_rate": 1.3042311600398157e-05,
+      "loss": 0.8093,
+      "step": 1730
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 1.2953482850428927e-05,
+      "loss": 0.7864,
+      "step": 1740
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 1.2864398040952921e-05,
+      "loss": 0.778,
+      "step": 1750
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 1.2775064895398217e-05,
+      "loss": 0.7869,
+      "step": 1760
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 1.2685491158723003e-05,
+      "loss": 0.8012,
+      "step": 1770
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 1.2595684596744112e-05,
+      "loss": 0.8385,
+      "step": 1780
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.045166015625,
+      "learning_rate": 1.250565299546374e-05,
+      "loss": 0.8062,
+      "step": 1790
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 1.2415404160394429e-05,
+      "loss": 0.8076,
+      "step": 1800
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.2324945915882334e-05,
+      "loss": 0.7864,
+      "step": 1810
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.03125,
+      "learning_rate": 1.2234286104428884e-05,
+      "loss": 0.833,
+      "step": 1820
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 1.2143432586010851e-05,
+      "loss": 0.7848,
+      "step": 1830
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.037109375,
+      "learning_rate": 1.2052393237398916e-05,
+      "loss": 0.7838,
+      "step": 1840
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 1.1961175951474766e-05,
+      "loss": 0.808,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.1869788636546801e-05,
+      "loss": 0.8076,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 1.1778239215664512e-05,
+      "loss": 0.8196,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 1.1686535625931566e-05,
+      "loss": 0.7873,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.046630859375,
+      "learning_rate": 1.1594685817817673e-05,
+      "loss": 0.8126,
+      "step": 1890
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 1.1502697754469315e-05,
+      "loss": 0.8462,
+      "step": 1900
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.029296875,
+      "learning_rate": 1.141057941101935e-05,
+      "loss": 0.8273,
+      "step": 1910
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 1.1318338773895596e-05,
+      "loss": 0.8222,
+      "step": 1920
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 1.1225983840128418e-05,
+      "loss": 0.7724,
+      "step": 1930
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.0400390625,
+      "learning_rate": 1.1133522616657417e-05,
+      "loss": 0.8072,
+      "step": 1940
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 1.104096311963724e-05,
+      "loss": 0.8306,
+      "step": 1950
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 1.0948313373742606e-05,
+      "loss": 0.7973,
+      "step": 1960
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 1.0855581411472576e-05,
+      "loss": 0.8385,
+      "step": 1970
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 1.076277527245417e-05,
+      "loss": 0.8238,
+      "step": 1980
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 1.0669903002745343e-05,
+      "loss": 0.8102,
+      "step": 1990
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 1.0576972654137411e-05,
+      "loss": 0.8189,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 1.0483992283456992e-05,
+      "loss": 0.7938,
+      "step": 2010
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 1.0390969951867482e-05,
+      "loss": 0.8171,
+      "step": 2020
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 1.0297913724170187e-05,
+      "loss": 0.8082,
+      "step": 2030
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.0204831668105117e-05,
+      "loss": 0.7972,
+      "step": 2040
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 1.011173185365154e-05,
+      "loss": 0.7743,
+      "step": 2050
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.03515625,
+      "learning_rate": 1.0018622352328331e-05,
+      "loss": 0.8095,
+      "step": 2060
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.03564453125,
+      "learning_rate": 9.92551123649419e-06,
+      "loss": 0.796,
+      "step": 2070
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 9.832406578647789e-06,
+      "loss": 0.7923,
+      "step": 2080
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0230712890625,
+      "learning_rate": 9.739316450727914e-06,
+      "loss": 0.8106,
+      "step": 2090
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 9.646248923413639e-06,
+      "loss": 0.7871,
+      "step": 2100
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 9.553212065424625e-06,
+      "loss": 0.798,
+      "step": 2110
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 9.460213942821578e-06,
+      "loss": 0.795,
+      "step": 2120
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 9.367262618306947e-06,
+      "loss": 0.8001,
+      "step": 2130
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 9.274366150525902e-06,
+      "loss": 0.766,
+      "step": 2140
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.02587890625,
+      "learning_rate": 9.181532593367675e-06,
+      "loss": 0.7999,
+      "step": 2150
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.0224609375,
+      "learning_rate": 9.0887699952673e-06,
+      "loss": 0.813,
+      "step": 2160
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.035400390625,
+      "learning_rate": 8.996086398507848e-06,
+      "loss": 0.8108,
+      "step": 2170
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 8.903489838523167e-06,
+      "loss": 0.841,
+      "step": 2180
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 8.81098834320124e-06,
+      "loss": 0.8204,
+      "step": 2190
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.03759765625,
+      "learning_rate": 8.71858993218818e-06,
+      "loss": 0.7937,
+      "step": 2200
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 8.626302616192955e-06,
+      "loss": 0.799,
+      "step": 2210
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 8.534134396292875e-06,
+      "loss": 0.8033,
+      "step": 2220
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 8.442093263239913e-06,
+      "loss": 0.8089,
+      "step": 2230
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0228271484375,
+      "learning_rate": 8.350187196767942e-06,
+      "loss": 0.792,
+      "step": 2240
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.047607421875,
+      "learning_rate": 8.258424164900899e-06,
+      "loss": 0.8242,
+      "step": 2250
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0250244140625,
+      "learning_rate": 8.166812123261982e-06,
+      "loss": 0.8058,
+      "step": 2260
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 8.075359014383914e-06,
+      "loss": 0.8084,
+      "step": 2270
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0228271484375,
+      "learning_rate": 7.984072767020359e-06,
+      "loss": 0.7894,
+      "step": 2280
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0419921875,
+      "learning_rate": 7.892961295458496e-06,
+      "loss": 0.7993,
+      "step": 2290
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 7.802032498832895e-06,
+      "loss": 0.8036,
+      "step": 2300
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 7.71129426044066e-06,
+      "loss": 0.7973,
+      "step": 2310
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 7.620754447057985e-06,
+      "loss": 0.7964,
+      "step": 2320
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 7.530420908258111e-06,
+      "loss": 0.777,
+      "step": 2330
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.029541015625,
+      "learning_rate": 7.4403014757308e-06,
+      "loss": 0.8116,
+      "step": 2340
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 7.350403962603335e-06,
+      "loss": 0.8267,
+      "step": 2350
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 7.260736162763149e-06,
+      "loss": 0.8153,
+      "step": 2360
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 7.171305850182113e-06,
+      "loss": 0.8026,
+      "step": 2370
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.03466796875,
+      "learning_rate": 7.082120778242554e-06,
+      "loss": 0.8198,
+      "step": 2380
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.034423828125,
+      "learning_rate": 6.993188679065048e-06,
+      "loss": 0.7804,
+      "step": 2390
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 6.904517262838082e-06,
+      "loss": 0.8251,
+      "step": 2400
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.047607421875,
+      "learning_rate": 6.8161142171495785e-06,
+      "loss": 0.849,
+      "step": 2410
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 6.72798720632042e-06,
+      "loss": 0.7912,
+      "step": 2420
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 6.640143870739956e-06,
+      "loss": 0.7864,
+      "step": 2430
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 6.552591826203616e-06,
+      "loss": 0.7713,
+      "step": 2440
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 6.4653386632526275e-06,
+      "loss": 0.7925,
+      "step": 2450
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.045166015625,
+      "learning_rate": 6.378391946515937e-06,
+      "loss": 0.8402,
+      "step": 2460
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.023681640625,
+      "learning_rate": 6.291759214054383e-06,
+      "loss": 0.8032,
+      "step": 2470
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 6.205447976707154e-06,
+      "loss": 0.7891,
+      "step": 2480
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 6.119465717440629e-06,
+      "loss": 0.819,
+      "step": 2490
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 6.033819890699616e-06,
+      "loss": 0.8318,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 5.94851792176107e-06,
+      "loss": 0.8241,
+      "step": 2510
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 5.863567206090348e-06,
+      "loss": 0.7844,
+      "step": 2520
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 5.778975108700031e-06,
+      "loss": 0.8273,
+      "step": 2530
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.03759765625,
+      "learning_rate": 5.694748963511396e-06,
+      "loss": 0.8117,
+      "step": 2540
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 5.610896072718603e-06,
+      "loss": 0.8067,
+      "step": 2550
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.0213623046875,
+      "learning_rate": 5.527423706155586e-06,
+      "loss": 0.7988,
+      "step": 2560
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.0230712890625,
+      "learning_rate": 5.4443391006657896e-06,
+      "loss": 0.8286,
+      "step": 2570
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 5.361649459474756e-06,
+      "loss": 0.8054,
+      "step": 2580
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 5.279361951565618e-06,
+      "loss": 0.7801,
+      "step": 2590
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 5.197483711057569e-06,
+      "loss": 0.8107,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 5.116021836587353e-06,
+      "loss": 0.8273,
+      "step": 2610
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 5.0349833906938235e-06,
+      "loss": 0.7919,
+      "step": 2620
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 4.954375399205655e-06,
+      "loss": 0.8371,
+      "step": 2630
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 4.8742048506322045e-06,
+      "loss": 0.7882,
+      "step": 2640
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 4.794478695557631e-06,
+      "loss": 0.8149,
+      "step": 2650
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 4.715203846038312e-06,
+      "loss": 0.8254,
+      "step": 2660
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 4.636387175003558e-06,
+      "loss": 0.8249,
+      "step": 2670
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 4.558035515659768e-06,
+      "loss": 0.8004,
+      "step": 2680
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0230712890625,
+      "learning_rate": 4.480155660898001e-06,
+      "loss": 0.7959,
+      "step": 2690
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 4.402754362705051e-06,
+      "loss": 0.786,
+      "step": 2700
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.033203125,
+      "learning_rate": 4.325838331578061e-06,
+      "loss": 0.7948,
+      "step": 2710
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 4.249414235942755e-06,
+      "loss": 0.7959,
+      "step": 2720
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.045654296875,
+      "learning_rate": 4.173488701575274e-06,
+      "loss": 0.775,
+      "step": 2730
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 4.098068311027772e-06,
+      "loss": 0.7992,
+      "step": 2740
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 4.023159603057698e-06,
+      "loss": 0.8045,
+      "step": 2750
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 3.948769072060927e-06,
+      "loss": 0.7903,
+      "step": 2760
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0458984375,
+      "learning_rate": 3.874903167508688e-06,
+      "loss": 0.7974,
+      "step": 2770
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 3.801568293388421e-06,
+      "loss": 0.7766,
+      "step": 2780
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.0400390625,
+      "learning_rate": 3.728770807648574e-06,
+      "loss": 0.8202,
+      "step": 2790
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.0250244140625,
+      "learning_rate": 3.6565170216473744e-06,
+      "loss": 0.8047,
+      "step": 2800
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 3.584813199605658e-06,
+      "loss": 0.8324,
+      "step": 2810
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 3.513665558063771e-06,
+      "loss": 0.8203,
+      "step": 2820
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.034912109375,
+      "learning_rate": 3.4430802653426176e-06,
+      "loss": 0.7997,
+      "step": 2830
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 3.373063441008877e-06,
+      "loss": 0.7783,
+      "step": 2840
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 3.303621155344453e-06,
+      "loss": 0.8088,
+      "step": 2850
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.0250244140625,
+      "learning_rate": 3.234759428820198e-06,
+      "loss": 0.8231,
+      "step": 2860
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.0235595703125,
+      "learning_rate": 3.1664842315739586e-06,
+      "loss": 0.8005,
+      "step": 2870
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 3.098801482892966e-06,
+      "loss": 0.7926,
+      "step": 2880
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 3.031717050700659e-06,
+      "loss": 0.7926,
+      "step": 2890
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.045166015625,
+      "learning_rate": 2.9652367510479476e-06,
+      "loss": 0.8127,
+      "step": 2900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 2.899366347608974e-06,
+      "loss": 0.8046,
+      "step": 2910
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.036865234375,
+      "learning_rate": 2.834111551181423e-06,
+      "loss": 0.7647,
+      "step": 2920
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 2.7694780191914005e-06,
+      "loss": 0.7985,
+      "step": 2930
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 2.7054713552029577e-06,
+      "loss": 0.841,
+      "step": 2940
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.041748046875,
+      "learning_rate": 2.6420971084322745e-06,
+      "loss": 0.7775,
+      "step": 2950
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 2.5793607732665402e-06,
+      "loss": 0.7954,
+      "step": 2960
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.03125,
+      "learning_rate": 2.5172677887876416e-06,
+      "loss": 0.7875,
+      "step": 2970
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 2.455823538300569e-06,
+      "loss": 0.8065,
+      "step": 2980
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0224609375,
+      "learning_rate": 2.3950333488667178e-06,
+      "loss": 0.8201,
+      "step": 2990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 2.3349024908420403e-06,
+      "loss": 0.813,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 2.2754361774201217e-06,
+      "loss": 0.8076,
+      "step": 3010
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 2.2166395641802076e-06,
+      "loss": 0.8135,
+      "step": 3020
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 2.1585177486402275e-06,
+      "loss": 0.8095,
+      "step": 3030
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 2.101075769814855e-06,
+      "loss": 0.7985,
+      "step": 3040
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 2.0443186077786358e-06,
+      "loss": 0.7976,
+      "step": 3050
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 1.9882511832342297e-06,
+      "loss": 0.7868,
+      "step": 3060
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 1.9328783570857954e-06,
+      "loss": 0.8072,
+      "step": 3070
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.04296875,
+      "learning_rate": 1.8782049300175698e-06,
+      "loss": 0.7931,
+      "step": 3080
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 1.8242356420776485e-06,
+      "loss": 0.8185,
+      "step": 3090
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 1.7709751722670466e-06,
+      "loss": 0.8391,
+      "step": 3100
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 1.718428138134034e-06,
+      "loss": 0.8502,
+      "step": 3110
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 1.666599095373811e-06,
+      "loss": 0.8185,
+      "step": 3120
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.025390625,
+      "learning_rate": 1.6154925374335362e-06,
+      "loss": 0.806,
+      "step": 3130
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 1.5651128951227613e-06,
+      "loss": 0.783,
+      "step": 3140
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 1.5154645362292853e-06,
+      "loss": 0.8159,
+      "step": 3150
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.025390625,
+      "learning_rate": 1.4665517651404814e-06,
+      "loss": 0.7793,
+      "step": 3160
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0220947265625,
+      "learning_rate": 1.4183788224701201e-06,
+      "loss": 0.7754,
+      "step": 3170
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 1.370949884690711e-06,
+      "loss": 0.847,
+      "step": 3180
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.035888671875,
+      "learning_rate": 1.3242690637714228e-06,
+      "loss": 0.8014,
+      "step": 3190
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.2783404068215776e-06,
+      "loss": 0.8235,
+      "step": 3200
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 1.2331678957397819e-06,
+      "loss": 0.7997,
+      "step": 3210
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.033203125,
+      "learning_rate": 1.1887554468687046e-06,
+      "loss": 0.8159,
+      "step": 3220
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 1.145106910655538e-06,
+      "loss": 0.8392,
+      "step": 3230
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 1.1022260713181786e-06,
+      "loss": 0.8266,
+      "step": 3240
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.03662109375,
+      "learning_rate": 1.0601166465171387e-06,
+      "loss": 0.8209,
+      "step": 3250
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 1.0187822870332398e-06,
+      "loss": 0.8021,
+      "step": 3260
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 9.782265764510968e-07,
+      "loss": 0.7938,
+      "step": 3270
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 9.384530308484275e-07,
+      "loss": 0.8007,
+      "step": 3280
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 8.99465098491229e-07,
+      "loss": 0.8097,
+      "step": 3290
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 8.612661595348038e-07,
+      "loss": 0.8029,
+      "step": 3300
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0234375,
+      "learning_rate": 8.238595257307225e-07,
+      "loss": 0.8079,
+      "step": 3310
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.03125,
+      "learning_rate": 7.872484401397018e-07,
+      "loss": 0.8074,
+      "step": 3320
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 7.514360768504314e-07,
+      "loss": 0.7961,
+      "step": 3330
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.03125,
+      "learning_rate": 7.164255407043986e-07,
+      "loss": 0.7701,
+      "step": 3340
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 6.822198670266989e-07,
+      "loss": 0.8165,
+      "step": 3350
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 6.488220213628837e-07,
+      "loss": 0.8097,
+      "step": 3360
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 6.16234899221858e-07,
+      "loss": 0.8073,
+      "step": 3370
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0234375,
+      "learning_rate": 5.844613258248411e-07,
+      "loss": 0.7865,
+      "step": 3380
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.130859375,
+      "learning_rate": 5.535040558604299e-07,
+      "loss": 0.8182,
+      "step": 3390
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 5.233657732457775e-07,
+      "loss": 0.78,
+      "step": 3400
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 4.940490908938977e-07,
+      "loss": 0.7961,
+      "step": 3410
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0478515625,
+      "learning_rate": 4.6555655048713953e-07,
+      "loss": 0.7946,
+      "step": 3420
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 4.3789062225682356e-07,
+      "loss": 0.8022,
+      "step": 3430
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 4.1105370476908104e-07,
+      "loss": 0.8201,
+      "step": 3440
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.042236328125,
+      "learning_rate": 3.8504812471690687e-07,
+      "loss": 0.8014,
+      "step": 3450
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 3.598761367184367e-07,
+      "loss": 0.7995,
+      "step": 3460
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 3.3553992312148177e-07,
+      "loss": 0.8139,
+      "step": 3470
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 3.1204159381432174e-07,
+      "loss": 0.8127,
+      "step": 3480
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 2.8938318604278314e-07,
+      "loss": 0.8009,
+      "step": 3490
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 2.675666642336172e-07,
+      "loss": 0.8319,
+      "step": 3500
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 2.4659391982418626e-07,
+      "loss": 0.8413,
+      "step": 3510
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.264667710984836e-07,
+      "loss": 0.8194,
+      "step": 3520
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 2.0718696302949092e-07,
+      "loss": 0.8128,
+      "step": 3530
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 1.8875616712789257e-07,
+      "loss": 0.8008,
+      "step": 3540
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 1.7117598129716362e-07,
+      "loss": 0.7753,
+      "step": 3550
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 1.544479296950341e-07,
+      "loss": 0.802,
+      "step": 3560
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 1.385734626013435e-07,
+      "loss": 0.7936,
+      "step": 3570
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 1.2355395629231493e-07,
+      "loss": 0.7956,
+      "step": 3580
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 1.0939071292122572e-07,
+      "loss": 0.7769,
+      "step": 3590
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 9.608496040551918e-08,
+      "loss": 0.7957,
+      "step": 3600
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 8.363785232034849e-08,
+      "loss": 0.814,
+      "step": 3610
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 7.205046779856007e-08,
+      "loss": 0.8155,
+      "step": 3620
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 6.132381143713728e-08,
+      "loss": 0.8364,
+      "step": 3630
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 5.1458813210106815e-08,
+      "loss": 0.8173,
+      "step": 3640
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 4.245632838791092e-08,
+      "loss": 0.8085,
+      "step": 3650
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0225830078125,
+      "learning_rate": 3.431713746325449e-08,
+      "loss": 0.8195,
+      "step": 3660
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0751953125,
+      "learning_rate": 2.7041946083442573e-08,
+      "loss": 0.8029,
+      "step": 3670
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 2.0631384989202585e-08,
+      "loss": 0.8359,
+      "step": 3680
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 1.5086009959995875e-08,
+      "loss": 0.8233,
+      "step": 3690
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.0228271484375,
+      "learning_rate": 1.0406301765837346e-08,
+      "loss": 0.7743,
+      "step": 3700
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 6.592666125614377e-09,
+      "loss": 0.7764,
+      "step": 3710
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 3.645433671908283e-09,
+      "loss": 0.798,
+      "step": 3720
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 1.5648599223316852e-09,
+      "loss": 0.8119,
+      "step": 3730
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 3.5112525737734935e-10,
+      "loss": 0.8295,
+      "step": 3740
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3749,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.2690756062895145e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3749/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5356fbb048ee7ff25112c3ec47aefcc7e7a98ee5b1b422e51abe8c4254ba97
+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 sha256:3c5e29e54daf146219e8057d80955d57d314ef6939096eda6657f8e96a0f3c44
+size 1948291704

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a4c35804b3838a8b79f4edfa9eb4cf51f12ad42b1354318096a57ce47af3e6
+size 1981891624

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8613bc9974e1f723a9c8cb9cafde49f435638d1060dc5237b1c55194cb65056
+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/Mar22_07-15-06_2013f91d074a/events.out.tfevents.1711091786.2013f91d074a.192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a22e3396072b9c08829fa0653cf7d46f2644ccc6b4001c85eecd2448499a39
+size 84269

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
+}