Subiendo mi modelo entrenado

README.md

@@ -0,0 +1,143 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model-index:
+- name: outputs/qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: qlora
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+bf16: false
+dataset_prepared_path: null
+datasets:
+- path: mhenrichsen/alpaca_2k_test
+  type: alpaca
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_sample_packing: false
+evals_per_epoch: 4
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: false
+learning_rate: 0.0002
+load_in_4bit: true
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lora_target_modules: null
+lr_scheduler: cosine
+micro_batch_size: 2
+model_type: LlamaForCausalLM
+num_epochs: 4
+optimizer: paged_adamw_32bit
+output_dir: ./outputs/qlora-out
+pad_to_sequence_len: false
+resume_from_checkpoint: null
+sample_packing: false
+saves_per_epoch: 1
+sequence_len: 4096
+special_tokens: null
+strict: false
+tf32: null
+tokenizer_type: LlamaTokenizer
+train_on_inputs: false
+val_set_size: 0.05
+wandb_entity: null
+wandb_log_model: null
+wandb_name: null
+wandb_project: null
+wandb_watch: null
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# outputs/qlora-out
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2295
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.5605        | 0.0042 | 1    | 1.5265          |
+| 1.1485        | 0.2526 | 60   | 1.2386          |
+| 1.1249        | 0.5053 | 120  | 1.2167          |
+| 1.3675        | 0.7579 | 180  | 1.2130          |
+| 1.3449        | 1.0105 | 240  | 1.1995          |
+| 1.1825        | 1.2632 | 300  | 1.2074          |
+| 0.9782        | 1.5158 | 360  | 1.2060          |
+| 1.2063        | 1.7684 | 420  | 1.1994          |
+| 0.9614        | 2.0211 | 480  | 1.1929          |
+| 1.0084        | 2.2737 | 540  | 1.2140          |
+| 1.1655        | 2.5263 | 600  | 1.2174          |
+| 1.1503        | 2.7789 | 660  | 1.2198          |
+| 0.9577        | 3.0316 | 720  | 1.2164          |
+| 0.9943        | 3.2842 | 780  | 1.2286          |
+| 1.0043        | 3.5368 | 840  | 1.2289          |
+| 1.128         | 3.7895 | 900  | 1.2295          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe890ad8ee220f505bc4a0ebd66cf525a3d15a760985d3af21a1e0e8212e40b4
+size 50573978

checkpoint-237/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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 0.11.1

checkpoint-237/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-237/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0117ce11d9f2e5d6bd5f133ad30669999be08dbaa426121bbd98337975bf835
+size 50503848

checkpoint-237/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8acf16b4e1bd9dc6c260276356388e91496c718a307a28cecd8e4a79af1e2f
+size 202035450

checkpoint-237/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1746df72a4bad5eddb1e3c7cb25ea26a49bf4140a3ca0312fff3900f3c96776
+size 14244

checkpoint-237/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d93959d5a6796fe7eb3f081e11fa0927ee021d92c2af05266234d62643f7e6c
+size 1064

checkpoint-237/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-237/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-237/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-237/trainer_state.json

@@ -0,0 +1,1724 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9978947368421053,
+  "eval_steps": 60,
+  "global_step": 237,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004210526315789474,
+      "grad_norm": 0.310546875,
+      "learning_rate": 2e-05,
+      "loss": 1.5605,
+      "step": 1
+    },
+    {
+      "epoch": 0.004210526315789474,
+      "eval_loss": 1.5264556407928467,
+      "eval_runtime": 26.3082,
+      "eval_samples_per_second": 3.801,
+      "eval_steps_per_second": 1.901,
+      "step": 1
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 0.306640625,
+      "learning_rate": 4e-05,
+      "loss": 1.4702,
+      "step": 2
+    },
+    {
+      "epoch": 0.01263157894736842,
+      "grad_norm": 0.2578125,
+      "learning_rate": 6e-05,
+      "loss": 1.4576,
+      "step": 3
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.65234375,
+      "learning_rate": 8e-05,
+      "loss": 1.5868,
+      "step": 4
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001,
+      "loss": 1.5916,
+      "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00012,
+      "loss": 1.7851,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 0.3359375,
+      "learning_rate": 0.00014,
+      "loss": 1.5319,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00016,
+      "loss": 1.8462,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00018,
+      "loss": 1.4219,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.0002,
+      "loss": 1.6555,
+      "step": 10
+    },
+    {
+      "epoch": 0.04631578947368421,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.0001999994391281196,
+      "loss": 1.1527,
+      "step": 11
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019999775651876987,
+      "loss": 1.4265,
+      "step": 12
+    },
+    {
+      "epoch": 0.05473684210526316,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00019999495219082545,
+      "loss": 1.5505,
+      "step": 13
+    },
+    {
+      "epoch": 0.05894736842105263,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00019999102617574365,
+      "loss": 1.0313,
+      "step": 14
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001999859785175643,
+      "loss": 1.439,
+      "step": 15
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019997980927290927,
+      "loss": 1.3511,
+      "step": 16
+    },
+    {
+      "epoch": 0.07157894736842105,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.0001999725185109816,
+      "loss": 1.2886,
+      "step": 17
+    },
+    {
+      "epoch": 0.07578947368421053,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00019996410631356498,
+      "loss": 1.3057,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00019995457277502271,
+      "loss": 1.7375,
+      "step": 19
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019994391800229666,
+      "loss": 1.3436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08842105263157894,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019993214211490608,
+      "loss": 1.14,
+      "step": 21
+    },
+    {
+      "epoch": 0.09263157894736843,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00019991924524494627,
+      "loss": 1.1322,
+      "step": 22
+    },
+    {
+      "epoch": 0.0968421052631579,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.00019990522753708705,
+      "loss": 1.4512,
+      "step": 23
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 1.3419,
+      "step": 24
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00019987383024921255,
+      "loss": 1.382,
+      "step": 25
+    },
+    {
+      "epoch": 0.10947368421052632,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001998564510213944,
+      "loss": 1.582,
+      "step": 26
+    },
+    {
+      "epoch": 0.11368421052631579,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00019983795166006715,
+      "loss": 1.188,
+      "step": 27
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00019981833237274618,
+      "loss": 1.4246,
+      "step": 28
+    },
+    {
+      "epoch": 0.12210526315789473,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00019979759337950968,
+      "loss": 1.2828,
+      "step": 29
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00019977573491299598,
+      "loss": 1.6199,
+      "step": 30
+    },
+    {
+      "epoch": 0.13052631578947368,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.00019975275721840103,
+      "loss": 1.2398,
+      "step": 31
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019972866055347572,
+      "loss": 1.4295,
+      "step": 32
+    },
+    {
+      "epoch": 0.13894736842105262,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001997034451885229,
+      "loss": 1.2814,
+      "step": 33
+    },
+    {
+      "epoch": 0.1431578947368421,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001996771114063943,
+      "loss": 1.532,
+      "step": 34
+    },
+    {
+      "epoch": 0.14736842105263157,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00019964965950248757,
+      "loss": 1.3516,
+      "step": 35
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.44921875,
+      "learning_rate": 0.00019962108978474263,
+      "loss": 1.1487,
+      "step": 36
+    },
+    {
+      "epoch": 0.15578947368421053,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.0001995914025736386,
+      "loss": 1.3543,
+      "step": 37
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.00019956059820218982,
+      "loss": 1.2986,
+      "step": 38
+    },
+    {
+      "epoch": 0.16421052631578947,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00019952867701594247,
+      "loss": 1.0167,
+      "step": 39
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.00019949563937297045,
+      "loss": 1.2287,
+      "step": 40
+    },
+    {
+      "epoch": 0.1726315789473684,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019946148564387145,
+      "loss": 1.0063,
+      "step": 41
+    },
+    {
+      "epoch": 0.17684210526315788,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019942621621176282,
+      "loss": 1.2712,
+      "step": 42
+    },
+    {
+      "epoch": 0.18105263157894738,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019938983147227716,
+      "loss": 1.2106,
+      "step": 43
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0001993523318335581,
+      "loss": 1.4887,
+      "step": 44
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00019931371771625544,
+      "loss": 1.2747,
+      "step": 45
+    },
+    {
+      "epoch": 0.1936842105263158,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 0.00019927398955352061,
+      "loss": 1.1946,
+      "step": 46
+    },
+    {
+      "epoch": 0.19789473684210526,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00019923314779100184,
+      "loss": 1.2467,
+      "step": 47
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00019919119288683908,
+      "loss": 1.5067,
+      "step": 48
+    },
+    {
+      "epoch": 0.2063157894736842,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00019914812531165877,
+      "loss": 1.4291,
+      "step": 49
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019910394554856876,
+      "loss": 1.0136,
+      "step": 50
+    },
+    {
+      "epoch": 0.21473684210526317,
+      "grad_norm": 1.328125,
+      "learning_rate": 0.00019905865409315288,
+      "loss": 1.2874,
+      "step": 51
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.0001990122514534651,
+      "loss": 0.9588,
+      "step": 52
+    },
+    {
+      "epoch": 0.2231578947368421,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001989647381500242,
+      "loss": 1.3036,
+      "step": 53
+    },
+    {
+      "epoch": 0.22736842105263158,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019891611471580764,
+      "loss": 1.514,
+      "step": 54
+    },
+    {
+      "epoch": 0.23157894736842105,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.0001988663816962458,
+      "loss": 1.2444,
+      "step": 55
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00019881553964921572,
+      "loss": 1.2261,
+      "step": 56
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019876358914503492,
+      "loss": 1.2489,
+      "step": 57
+    },
+    {
+      "epoch": 0.24421052631578946,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.00019871053076645488,
+      "loss": 1.2134,
+      "step": 58
+    },
+    {
+      "epoch": 0.24842105263157896,
+      "grad_norm": 0.259765625,
+      "learning_rate": 0.00019865636510865467,
+      "loss": 1.1999,
+      "step": 59
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.2421875,
+      "learning_rate": 0.00019860109277923418,
+      "loss": 1.1485,
+      "step": 60
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "eval_loss": 1.2386109828948975,
+      "eval_runtime": 25.8708,
+      "eval_samples_per_second": 3.865,
+      "eval_steps_per_second": 1.933,
+      "step": 60
+    },
+    {
+      "epoch": 0.25684210526315787,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019854471439820733,
+      "loss": 1.2963,
+      "step": 61
+    },
+    {
+      "epoch": 0.26105263157894737,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019848723059799506,
+      "loss": 1.097,
+      "step": 62
+    },
+    {
+      "epoch": 0.26526315789473687,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00019842864202341835,
+      "loss": 1.1463,
+      "step": 63
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019836894933169088,
+      "loss": 1.1921,
+      "step": 64
+    },
+    {
+      "epoch": 0.2736842105263158,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00019830815319241168,
+      "loss": 1.1835,
+      "step": 65
+    },
+    {
+      "epoch": 0.27789473684210525,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.0001982462542875576,
+      "loss": 1.1998,
+      "step": 66
+    },
+    {
+      "epoch": 0.28210526315789475,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.00019818325331147585,
+      "loss": 1.1047,
+      "step": 67
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.00019811915097087587,
+      "loss": 1.2452,
+      "step": 68
+    },
+    {
+      "epoch": 0.2905263157894737,
+      "grad_norm": 0.259765625,
+      "learning_rate": 0.00019805394798482167,
+      "loss": 1.1633,
+      "step": 69
+    },
+    {
+      "epoch": 0.29473684210526313,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.00019798764508472373,
+      "loss": 1.0081,
+      "step": 70
+    },
+    {
+      "epoch": 0.29894736842105263,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00019792024301433064,
+      "loss": 0.9194,
+      "step": 71
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00019785174252972092,
+      "loss": 0.8091,
+      "step": 72
+    },
+    {
+      "epoch": 0.30736842105263157,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00019778214439929452,
+      "loss": 1.1248,
+      "step": 73
+    },
+    {
+      "epoch": 0.31157894736842107,
+      "grad_norm": 0.23046875,
+      "learning_rate": 0.0001977114494037641,
+      "loss": 1.1204,
+      "step": 74
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001976396583361464,
+      "loss": 1.1662,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00019756677200175315,
+      "loss": 1.1222,
+      "step": 76
+    },
+    {
+      "epoch": 0.32421052631578945,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.0329,
+      "step": 77
+    },
+    {
+      "epoch": 0.32842105263157895,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 0.0001974177168153088,
+      "loss": 1.1199,
+      "step": 78
+    },
+    {
+      "epoch": 0.33263157894736844,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.00019734154963527495,
+      "loss": 1.4391,
+      "step": 79
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.0001972642905324813,
+      "loss": 1.3924,
+      "step": 80
+    },
+    {
+      "epoch": 0.3410526315789474,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.00019718594037357713,
+      "loss": 1.1518,
+      "step": 81
+    },
+    {
+      "epoch": 0.3452631578947368,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.0001971065000374504,
+      "loss": 1.2606,
+      "step": 82
+    },
+    {
+      "epoch": 0.3494736842105263,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001970259704152181,
+      "loss": 1.2293,
+      "step": 83
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0001969443524102163,
+      "loss": 0.9564,
+      "step": 84
+    },
+    {
+      "epoch": 0.35789473684210527,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00019686164693798986,
+      "loss": 1.2023,
+      "step": 85
+    },
+    {
+      "epoch": 0.36210526315789476,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.0001967778549262822,
+      "loss": 0.9322,
+      "step": 86
+    },
+    {
+      "epoch": 0.3663157894736842,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00019669297731502507,
+      "loss": 1.2589,
+      "step": 87
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019660701505632772,
+      "loss": 1.3188,
+      "step": 88
+    },
+    {
+      "epoch": 0.37473684210526315,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019651996911446647,
+      "loss": 1.0415,
+      "step": 89
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.427734375,
+      "learning_rate": 0.0001964318404658737,
+      "loss": 1.467,
+      "step": 90
+    },
+    {
+      "epoch": 0.3831578947368421,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00019634263009912705,
+      "loss": 1.5527,
+      "step": 91
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019625233901493822,
+      "loss": 1.2043,
+      "step": 92
+    },
+    {
+      "epoch": 0.391578947368421,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00019616096822614186,
+      "loss": 0.9677,
+      "step": 93
+    },
+    {
+      "epoch": 0.3957894736842105,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.000196068518757684,
+      "loss": 1.1942,
+      "step": 94
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00019597499164661093,
+      "loss": 1.3481,
+      "step": 95
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019588038794205703,
+      "loss": 1.2776,
+      "step": 96
+    },
+    {
+      "epoch": 0.40842105263157896,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00019578470870523359,
+      "loss": 1.4808,
+      "step": 97
+    },
+    {
+      "epoch": 0.4126315789473684,
+      "grad_norm": 0.28125,
+      "learning_rate": 0.00019568795500941635,
+      "loss": 1.3385,
+      "step": 98
+    },
+    {
+      "epoch": 0.4168421052631579,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019559012793993392,
+      "loss": 1.5787,
+      "step": 99
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019549122859415538,
+      "loss": 1.2151,
+      "step": 100
+    },
+    {
+      "epoch": 0.42526315789473684,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.0001953912580814779,
+      "loss": 1.0332,
+      "step": 101
+    },
+    {
+      "epoch": 0.42947368421052634,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00019529021752331453,
+      "loss": 1.2677,
+      "step": 102
+    },
+    {
+      "epoch": 0.4336842105263158,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001951881080530814,
+      "loss": 1.0672,
+      "step": 103
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00019508493081618513,
+      "loss": 1.1736,
+      "step": 104
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019498068697000994,
+      "loss": 1.1174,
+      "step": 105
+    },
+    {
+      "epoch": 0.4463157894736842,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00019487537768390464,
+      "loss": 1.0712,
+      "step": 106
+    },
+    {
+      "epoch": 0.45052631578947366,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001947690041391696,
+      "loss": 1.4496,
+      "step": 107
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00019466156752904343,
+      "loss": 1.2413,
+      "step": 108
+    },
+    {
+      "epoch": 0.4589473684210526,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001945530690586896,
+      "loss": 1.0208,
+      "step": 109
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.0001944435099451829,
+      "loss": 1.3997,
+      "step": 110
+    },
+    {
+      "epoch": 0.4673684210526316,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00019433289141749586,
+      "loss": 1.2914,
+      "step": 111
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.63671875,
+      "learning_rate": 0.00019422121471648497,
+      "loss": 0.8134,
+      "step": 112
+    },
+    {
+      "epoch": 0.47578947368421054,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019410848109487658,
+      "loss": 1.1282,
+      "step": 113
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001939946918172531,
+      "loss": 1.3254,
+      "step": 114
+    },
+    {
+      "epoch": 0.4842105263157895,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019387984816003867,
+      "loss": 1.6428,
+      "step": 115
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019376395141148476,
+      "loss": 1.0688,
+      "step": 116
+    },
+    {
+      "epoch": 0.4926315789473684,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00019364700287165604,
+      "loss": 1.0969,
+      "step": 117
+    },
+    {
+      "epoch": 0.4968421052631579,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.00019352900385241536,
+      "loss": 1.5249,
+      "step": 118
+    },
+    {
+      "epoch": 0.5010526315789474,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 0.00019340995567740938,
+      "loss": 1.2095,
+      "step": 119
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.0001932898596820536,
+      "loss": 1.1249,
+      "step": 120
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 1.2166697978973389,
+      "eval_runtime": 25.8713,
+      "eval_samples_per_second": 3.865,
+      "eval_steps_per_second": 1.933,
+      "step": 120
+    },
+    {
+      "epoch": 0.5094736842105263,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00019316871721351733,
+      "loss": 1.5017,
+      "step": 121
+    },
+    {
+      "epoch": 0.5136842105263157,
+      "grad_norm": 0.7421875,
+      "learning_rate": 0.0001930465296307087,
+      "loss": 1.0994,
+      "step": 122
+    },
+    {
+      "epoch": 0.5178947368421053,
+      "grad_norm": 0.21875,
+      "learning_rate": 0.0001929232983042592,
+      "loss": 1.0339,
+      "step": 123
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00019279902461650866,
+      "loss": 1.1317,
+      "step": 124
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00019267370996148934,
+      "loss": 0.9421,
+      "step": 125
+    },
+    {
+      "epoch": 0.5305263157894737,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00019254735574491058,
+      "loss": 1.3029,
+      "step": 126
+    },
+    {
+      "epoch": 0.5347368421052632,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.00019241996338414296,
+      "loss": 1.3548,
+      "step": 127
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.00019229153430820232,
+      "loss": 1.0865,
+      "step": 128
+    },
+    {
+      "epoch": 0.5431578947368421,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00019216206995773373,
+      "loss": 0.8151,
+      "step": 129
+    },
+    {
+      "epoch": 0.5473684210526316,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0001920315717849956,
+      "loss": 1.3576,
+      "step": 130
+    },
+    {
+      "epoch": 0.5515789473684211,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00019190004125384293,
+      "loss": 1.2439,
+      "step": 131
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001917674798397113,
+      "loss": 0.9743,
+      "step": 132
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0001916338890296001,
+      "loss": 1.3315,
+      "step": 133
+    },
+    {
+      "epoch": 0.5642105263157895,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019149927032205587,
+      "loss": 1.3268,
+      "step": 134
+    },
+    {
+      "epoch": 0.5684210526315789,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00019136362522715562,
+      "loss": 1.4751,
+      "step": 135
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019122695526648968,
+      "loss": 1.1219,
+      "step": 136
+    },
+    {
+      "epoch": 0.5768421052631579,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019108926197314486,
+      "loss": 1.4059,
+      "step": 137
+    },
+    {
+      "epoch": 0.5810526315789474,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019095054689168705,
+      "loss": 1.3282,
+      "step": 138
+    },
+    {
+      "epoch": 0.5852631578947368,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.00019081081157814404,
+      "loss": 1.6334,
+      "step": 139
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00019067005759998797,
+      "loss": 1.159,
+      "step": 140
+    },
+    {
+      "epoch": 0.5936842105263158,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019052828653611786,
+      "loss": 1.3261,
+      "step": 141
+    },
+    {
+      "epoch": 0.5978947368421053,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001903854999768417,
+      "loss": 1.2041,
+      "step": 142
+    },
+    {
+      "epoch": 0.6021052631578947,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019024169952385885,
+      "loss": 1.1998,
+      "step": 143
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.6427,
+      "step": 144
+    },
+    {
+      "epoch": 0.6105263157894737,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.00018995106340041873,
+      "loss": 1.1968,
+      "step": 145
+    },
+    {
+      "epoch": 0.6147368421052631,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00018980423099015402,
+      "loss": 0.8641,
+      "step": 146
+    },
+    {
+      "epoch": 0.6189473684210526,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00018965639120653121,
+      "loss": 1.4518,
+      "step": 147
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00018950754570793384,
+      "loss": 1.3077,
+      "step": 148
+    },
+    {
+      "epoch": 0.6273684210526316,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00018935769616402703,
+      "loss": 1.2077,
+      "step": 149
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.224609375,
+      "learning_rate": 0.00018920684425573865,
+      "loss": 1.0868,
+      "step": 150
+    },
+    {
+      "epoch": 0.6357894736842106,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00018905499167524062,
+      "loss": 1.2018,
+      "step": 151
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00018890214012592975,
+      "loss": 1.1675,
+      "step": 152
+    },
+    {
+      "epoch": 0.6442105263157895,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 0.00018874829132240874,
+      "loss": 1.2348,
+      "step": 153
+    },
+    {
+      "epoch": 0.6484210526315789,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.000188593446990467,
+      "loss": 1.3202,
+      "step": 154
+    },
+    {
+      "epoch": 0.6526315789473685,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0001884376088670611,
+      "loss": 1.0171,
+      "step": 155
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.00018828077870029552,
+      "loss": 1.219,
+      "step": 156
+    },
+    {
+      "epoch": 0.6610526315789473,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00018812295824940285,
+      "loss": 0.8956,
+      "step": 157
+    },
+    {
+      "epoch": 0.6652631578947369,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.00018796414928472417,
+      "loss": 0.9322,
+      "step": 158
+    },
+    {
+      "epoch": 0.6694736842105263,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.0001878043535876891,
+      "loss": 1.2062,
+      "step": 159
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001876435729507959,
+      "loss": 1.3113,
+      "step": 160
+    },
+    {
+      "epoch": 0.6778947368421052,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00018748180917759136,
+      "loss": 1.1539,
+      "step": 161
+    },
+    {
+      "epoch": 0.6821052631578948,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.0001873190640826505,
+      "loss": 1.3287,
+      "step": 162
+    },
+    {
+      "epoch": 0.6863157894736842,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00018715533949155625,
+      "loss": 1.0616,
+      "step": 163
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 1.0171,
+      "step": 164
+    },
+    {
+      "epoch": 0.6947368421052632,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00018682495917815608,
+      "loss": 1.1113,
+      "step": 165
+    },
+    {
+      "epoch": 0.6989473684210527,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00018665830716187065,
+      "loss": 0.8351,
+      "step": 166
+    },
+    {
+      "epoch": 0.7031578947368421,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001864906830614314,
+      "loss": 1.2181,
+      "step": 167
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001863220887571512,
+      "loss": 1.1843,
+      "step": 168
+    },
+    {
+      "epoch": 0.7115789473684211,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018615252614022617,
+      "loss": 1.3809,
+      "step": 169
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.0001859819971127143,
+      "loss": 1.4288,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00018581050358751445,
+      "loss": 1.1449,
+      "step": 171
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.00018563804748834438,
+      "loss": 1.0703,
+      "step": 172
+    },
+    {
+      "epoch": 0.728421052631579,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00018546463074971977,
+      "loss": 1.2093,
+      "step": 173
+    },
+    {
+      "epoch": 0.7326315789473684,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.000185290255316932,
+      "loss": 0.7346,
+      "step": 174
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00018511492314602656,
+      "loss": 1.2782,
+      "step": 175
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00018493863620378122,
+      "loss": 1.0844,
+      "step": 176
+    },
+    {
+      "epoch": 0.7452631578947368,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 0.00018476139646768372,
+      "loss": 1.1771,
+      "step": 177
+    },
+    {
+      "epoch": 0.7494736842105263,
+      "grad_norm": 0.228515625,
+      "learning_rate": 0.00018458320592590975,
+      "loss": 1.2,
+      "step": 178
+    },
+    {
+      "epoch": 0.7536842105263157,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00018440406657730058,
+      "loss": 1.2248,
+      "step": 179
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00018422398043134067,
+      "loss": 1.3675,
+      "step": 180
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "eval_loss": 1.2129631042480469,
+      "eval_runtime": 25.9253,
+      "eval_samples_per_second": 3.857,
+      "eval_steps_per_second": 1.929,
+      "step": 180
+    },
+    {
+      "epoch": 0.7621052631578947,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001840429495081352,
+      "loss": 1.2456,
+      "step": 181
+    },
+    {
+      "epoch": 0.7663157894736842,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00018386097583838714,
+      "loss": 1.2617,
+      "step": 182
+    },
+    {
+      "epoch": 0.7705263157894737,
+      "grad_norm": 0.283203125,
+      "learning_rate": 0.00018367806146337483,
+      "loss": 1.2708,
+      "step": 183
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.00018349420843492888,
+      "loss": 1.3771,
+      "step": 184
+    },
+    {
+      "epoch": 0.7789473684210526,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00018330941881540915,
+      "loss": 1.3123,
+      "step": 185
+    },
+    {
+      "epoch": 0.783157894736842,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00018312369467768166,
+      "loss": 1.1952,
+      "step": 186
+    },
+    {
+      "epoch": 0.7873684210526316,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.00018293703810509537,
+      "loss": 1.426,
+      "step": 187
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.0001827494511914587,
+      "loss": 1.3205,
+      "step": 188
+    },
+    {
+      "epoch": 0.7957894736842105,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00018256093604101617,
+      "loss": 1.2221,
+      "step": 189
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0001823714947684247,
+      "loss": 1.4212,
+      "step": 190
+    },
+    {
+      "epoch": 0.8042105263157895,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00018218112949872995,
+      "loss": 1.2183,
+      "step": 191
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00018198984236734246,
+      "loss": 0.9922,
+      "step": 192
+    },
+    {
+      "epoch": 0.8126315789473684,
+      "grad_norm": 0.373046875,
+      "learning_rate": 0.0001817976355200137,
+      "loss": 1.334,
+      "step": 193
+    },
+    {
+      "epoch": 0.8168421052631579,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.000181604511112812,
+      "loss": 1.1052,
+      "step": 194
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.0001814104713120983,
+      "loss": 0.8112,
+      "step": 195
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.000181215518294502,
+      "loss": 1.2507,
+      "step": 196
+    },
+    {
+      "epoch": 0.8294736842105264,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.0001810196542468964,
+      "loss": 1.1228,
+      "step": 197
+    },
+    {
+      "epoch": 0.8336842105263158,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00018082288136637422,
+      "loss": 1.3562,
+      "step": 198
+    },
+    {
+      "epoch": 0.8378947368421052,
+      "grad_norm": 0.302734375,
+      "learning_rate": 0.000180625201860223,
+      "loss": 0.7766,
+      "step": 199
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00018042661794590023,
+      "loss": 1.2885,
+      "step": 200
+    },
+    {
+      "epoch": 0.8463157894736842,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.0001802271318510086,
+      "loss": 1.271,
+      "step": 201
+    },
+    {
+      "epoch": 0.8505263157894737,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00018002674581327094,
+      "loss": 1.3777,
+      "step": 202
+    },
+    {
+      "epoch": 0.8547368421052631,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00017982546208050515,
+      "loss": 1.32,
+      "step": 203
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00017962328291059888,
+      "loss": 1.1265,
+      "step": 204
+    },
+    {
+      "epoch": 0.8631578947368421,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00017942021057148436,
+      "loss": 1.523,
+      "step": 205
+    },
+    {
+      "epoch": 0.8673684210526316,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00017921624734111292,
+      "loss": 1.0251,
+      "step": 206
+    },
+    {
+      "epoch": 0.871578947368421,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001790113955074294,
+      "loss": 1.2665,
+      "step": 207
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.6875,
+      "learning_rate": 0.0001788056573683464,
+      "loss": 1.2244,
+      "step": 208
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 0.0001785990352317187,
+      "loss": 1.1621,
+      "step": 209
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00017839153141531718,
+      "loss": 1.3182,
+      "step": 210
+    },
+    {
+      "epoch": 0.888421052631579,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.000178183148246803,
+      "loss": 1.4508,
+      "step": 211
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00017797388806370132,
+      "loss": 1.1155,
+      "step": 212
+    },
+    {
+      "epoch": 0.8968421052631579,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.00017776375321337521,
+      "loss": 0.9191,
+      "step": 213
+    },
+    {
+      "epoch": 0.9010526315789473,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 0.00017755274605299923,
+      "loss": 1.1577,
+      "step": 214
+    },
+    {
+      "epoch": 0.9052631578947369,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017734086894953305,
+      "loss": 1.372,
+      "step": 215
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.353515625,
+      "learning_rate": 0.00017712812427969485,
+      "loss": 1.1932,
+      "step": 216
+    },
+    {
+      "epoch": 0.9136842105263158,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.0001769145144299347,
+      "loss": 1.3167,
+      "step": 217
+    },
+    {
+      "epoch": 0.9178947368421052,
+      "grad_norm": 0.255859375,
+      "learning_rate": 0.00017670004179640774,
+      "loss": 1.2357,
+      "step": 218
+    },
+    {
+      "epoch": 0.9221052631578948,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00017648470878494737,
+      "loss": 0.9556,
+      "step": 219
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0001762685178110382,
+      "loss": 1.2047,
+      "step": 220
+    },
+    {
+      "epoch": 0.9305263157894736,
+      "grad_norm": 0.271484375,
+      "learning_rate": 0.00017605147129978903,
+      "loss": 1.1935,
+      "step": 221
+    },
+    {
+      "epoch": 0.9347368421052632,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.0001758335716859055,
+      "loss": 1.3426,
+      "step": 222
+    },
+    {
+      "epoch": 0.9389473684210526,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.000175614821413663,
+      "loss": 1.5181,
+      "step": 223
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00017539522293687898,
+      "loss": 1.0962,
+      "step": 224
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00017517477871888568,
+      "loss": 1.3922,
+      "step": 225
+    },
+    {
+      "epoch": 0.9515789473684211,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00017495349123250242,
+      "loss": 1.2535,
+      "step": 226
+    },
+    {
+      "epoch": 0.9557894736842105,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00017473136296000772,
+      "loss": 1.1987,
+      "step": 227
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017450839639311162,
+      "loss": 1.4301,
+      "step": 228
+    },
+    {
+      "epoch": 0.9642105263157895,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00017428459403292767,
+      "loss": 1.3164,
+      "step": 229
+    },
+    {
+      "epoch": 0.968421052631579,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.00017405995838994494,
+      "loss": 1.1554,
+      "step": 230
+    },
+    {
+      "epoch": 0.9726315789473684,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00017383449198399964,
+      "loss": 1.3036,
+      "step": 231
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00017360819734424715,
+      "loss": 1.2797,
+      "step": 232
+    },
+    {
+      "epoch": 0.9810526315789474,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017338107700913354,
+      "loss": 1.1202,
+      "step": 233
+    },
+    {
+      "epoch": 0.9852631578947368,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001731531335263669,
+      "loss": 0.8187,
+      "step": 234
+    },
+    {
+      "epoch": 0.9894736842105263,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001729243694528891,
+      "loss": 1.1702,
+      "step": 235
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00017269478735484683,
+      "loss": 1.1406,
+      "step": 236
+    },
+    {
+      "epoch": 0.9978947368421053,
+      "grad_norm": 0.3359375,
+      "learning_rate": 0.00017246438980756293,
+      "loss": 0.9633,
+      "step": 237
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 948,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 237,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3952216796823552.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-237/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee017c711219d88132625f3e50d1a67d1c6236a55d3f5a2ad9f499310d968cef
+size 5944

checkpoint-474/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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 0.11.1

checkpoint-474/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-474/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f694edaccdd42023f0a1cee653f7f3e9fd1123a26113cdf9fd49fe00ce746e
+size 50503848

checkpoint-474/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a1e2576fd196bd384fbd66e8d7d237c7f8d9aef44cbdeac73b0d7051b70f35
+size 202035770

checkpoint-474/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8ea66452a468b349a3bdfd131d03d7a70b38ad4ea6f8a3c4d500229279eb91
+size 14244

checkpoint-474/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42714fb01454b0350f3ff250f6bc8bc2da6df691649aefca623325cce43ab6b3
+size 1064

checkpoint-474/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-474/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-474/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-474/trainer_state.json

@@ -0,0 +1,3415 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9957894736842106,
+  "eval_steps": 60,
+  "global_step": 474,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004210526315789474,
+      "grad_norm": 0.310546875,
+      "learning_rate": 2e-05,
+      "loss": 1.5605,
+      "step": 1
+    },
+    {
+      "epoch": 0.004210526315789474,
+      "eval_loss": 1.5264556407928467,
+      "eval_runtime": 26.3082,
+      "eval_samples_per_second": 3.801,
+      "eval_steps_per_second": 1.901,
+      "step": 1
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 0.306640625,
+      "learning_rate": 4e-05,
+      "loss": 1.4702,
+      "step": 2
+    },
+    {
+      "epoch": 0.01263157894736842,
+      "grad_norm": 0.2578125,
+      "learning_rate": 6e-05,
+      "loss": 1.4576,
+      "step": 3
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.65234375,
+      "learning_rate": 8e-05,
+      "loss": 1.5868,
+      "step": 4
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001,
+      "loss": 1.5916,
+      "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00012,
+      "loss": 1.7851,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 0.3359375,
+      "learning_rate": 0.00014,
+      "loss": 1.5319,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00016,
+      "loss": 1.8462,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00018,
+      "loss": 1.4219,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.0002,
+      "loss": 1.6555,
+      "step": 10
+    },
+    {
+      "epoch": 0.04631578947368421,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.0001999994391281196,
+      "loss": 1.1527,
+      "step": 11
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019999775651876987,
+      "loss": 1.4265,
+      "step": 12
+    },
+    {
+      "epoch": 0.05473684210526316,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00019999495219082545,
+      "loss": 1.5505,
+      "step": 13
+    },
+    {
+      "epoch": 0.05894736842105263,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00019999102617574365,
+      "loss": 1.0313,
+      "step": 14
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001999859785175643,
+      "loss": 1.439,
+      "step": 15
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019997980927290927,
+      "loss": 1.3511,
+      "step": 16
+    },
+    {
+      "epoch": 0.07157894736842105,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.0001999725185109816,
+      "loss": 1.2886,
+      "step": 17
+    },
+    {
+      "epoch": 0.07578947368421053,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00019996410631356498,
+      "loss": 1.3057,
+      "step": 18
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00019995457277502271,
+      "loss": 1.7375,
+      "step": 19
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019994391800229666,
+      "loss": 1.3436,
+      "step": 20
+    },
+    {
+      "epoch": 0.08842105263157894,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019993214211490608,
+      "loss": 1.14,
+      "step": 21
+    },
+    {
+      "epoch": 0.09263157894736843,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00019991924524494627,
+      "loss": 1.1322,
+      "step": 22
+    },
+    {
+      "epoch": 0.0968421052631579,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.00019990522753708705,
+      "loss": 1.4512,
+      "step": 23
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 0.00019989008914857116,
+      "loss": 1.3419,
+      "step": 24
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00019987383024921255,
+      "loss": 1.382,
+      "step": 25
+    },
+    {
+      "epoch": 0.10947368421052632,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001998564510213944,
+      "loss": 1.582,
+      "step": 26
+    },
+    {
+      "epoch": 0.11368421052631579,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00019983795166006715,
+      "loss": 1.188,
+      "step": 27
+    },
+    {
+      "epoch": 0.11789473684210526,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00019981833237274618,
+      "loss": 1.4246,
+      "step": 28
+    },
+    {
+      "epoch": 0.12210526315789473,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00019979759337950968,
+      "loss": 1.2828,
+      "step": 29
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00019977573491299598,
+      "loss": 1.6199,
+      "step": 30
+    },
+    {
+      "epoch": 0.13052631578947368,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.00019975275721840103,
+      "loss": 1.2398,
+      "step": 31
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019972866055347572,
+      "loss": 1.4295,
+      "step": 32
+    },
+    {
+      "epoch": 0.13894736842105262,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001997034451885229,
+      "loss": 1.2814,
+      "step": 33
+    },
+    {
+      "epoch": 0.1431578947368421,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001996771114063943,
+      "loss": 1.532,
+      "step": 34
+    },
+    {
+      "epoch": 0.14736842105263157,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00019964965950248757,
+      "loss": 1.3516,
+      "step": 35
+    },
+    {
+      "epoch": 0.15157894736842106,
+      "grad_norm": 0.44921875,
+      "learning_rate": 0.00019962108978474263,
+      "loss": 1.1487,
+      "step": 36
+    },
+    {
+      "epoch": 0.15578947368421053,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.0001995914025736386,
+      "loss": 1.3543,
+      "step": 37
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.00019956059820218982,
+      "loss": 1.2986,
+      "step": 38
+    },
+    {
+      "epoch": 0.16421052631578947,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00019952867701594247,
+      "loss": 1.0167,
+      "step": 39
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.00019949563937297045,
+      "loss": 1.2287,
+      "step": 40
+    },
+    {
+      "epoch": 0.1726315789473684,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019946148564387145,
+      "loss": 1.0063,
+      "step": 41
+    },
+    {
+      "epoch": 0.17684210526315788,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019942621621176282,
+      "loss": 1.2712,
+      "step": 42
+    },
+    {
+      "epoch": 0.18105263157894738,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019938983147227716,
+      "loss": 1.2106,
+      "step": 43
+    },
+    {
+      "epoch": 0.18526315789473685,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0001993523318335581,
+      "loss": 1.4887,
+      "step": 44
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00019931371771625544,
+      "loss": 1.2747,
+      "step": 45
+    },
+    {
+      "epoch": 0.1936842105263158,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 0.00019927398955352061,
+      "loss": 1.1946,
+      "step": 46
+    },
+    {
+      "epoch": 0.19789473684210526,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00019923314779100184,
+      "loss": 1.2467,
+      "step": 47
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00019919119288683908,
+      "loss": 1.5067,
+      "step": 48
+    },
+    {
+      "epoch": 0.2063157894736842,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00019914812531165877,
+      "loss": 1.4291,
+      "step": 49
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019910394554856876,
+      "loss": 1.0136,
+      "step": 50
+    },
+    {
+      "epoch": 0.21473684210526317,
+      "grad_norm": 1.328125,
+      "learning_rate": 0.00019905865409315288,
+      "loss": 1.2874,
+      "step": 51
+    },
+    {
+      "epoch": 0.21894736842105264,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.0001990122514534651,
+      "loss": 0.9588,
+      "step": 52
+    },
+    {
+      "epoch": 0.2231578947368421,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001989647381500242,
+      "loss": 1.3036,
+      "step": 53
+    },
+    {
+      "epoch": 0.22736842105263158,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019891611471580764,
+      "loss": 1.514,
+      "step": 54
+    },
+    {
+      "epoch": 0.23157894736842105,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.0001988663816962458,
+      "loss": 1.2444,
+      "step": 55
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00019881553964921572,
+      "loss": 1.2261,
+      "step": 56
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019876358914503492,
+      "loss": 1.2489,
+      "step": 57
+    },
+    {
+      "epoch": 0.24421052631578946,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.00019871053076645488,
+      "loss": 1.2134,
+      "step": 58
+    },
+    {
+      "epoch": 0.24842105263157896,
+      "grad_norm": 0.259765625,
+      "learning_rate": 0.00019865636510865467,
+      "loss": 1.1999,
+      "step": 59
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.2421875,
+      "learning_rate": 0.00019860109277923418,
+      "loss": 1.1485,
+      "step": 60
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "eval_loss": 1.2386109828948975,
+      "eval_runtime": 25.8708,
+      "eval_samples_per_second": 3.865,
+      "eval_steps_per_second": 1.933,
+      "step": 60
+    },
+    {
+      "epoch": 0.25684210526315787,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019854471439820733,
+      "loss": 1.2963,
+      "step": 61
+    },
+    {
+      "epoch": 0.26105263157894737,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00019848723059799506,
+      "loss": 1.097,
+      "step": 62
+    },
+    {
+      "epoch": 0.26526315789473687,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00019842864202341835,
+      "loss": 1.1463,
+      "step": 63
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00019836894933169088,
+      "loss": 1.1921,
+      "step": 64
+    },
+    {
+      "epoch": 0.2736842105263158,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00019830815319241168,
+      "loss": 1.1835,
+      "step": 65
+    },
+    {
+      "epoch": 0.27789473684210525,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.0001982462542875576,
+      "loss": 1.1998,
+      "step": 66
+    },
+    {
+      "epoch": 0.28210526315789475,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.00019818325331147585,
+      "loss": 1.1047,
+      "step": 67
+    },
+    {
+      "epoch": 0.2863157894736842,
+      "grad_norm": 0.244140625,
+      "learning_rate": 0.00019811915097087587,
+      "loss": 1.2452,
+      "step": 68
+    },
+    {
+      "epoch": 0.2905263157894737,
+      "grad_norm": 0.259765625,
+      "learning_rate": 0.00019805394798482167,
+      "loss": 1.1633,
+      "step": 69
+    },
+    {
+      "epoch": 0.29473684210526313,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.00019798764508472373,
+      "loss": 1.0081,
+      "step": 70
+    },
+    {
+      "epoch": 0.29894736842105263,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00019792024301433064,
+      "loss": 0.9194,
+      "step": 71
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00019785174252972092,
+      "loss": 0.8091,
+      "step": 72
+    },
+    {
+      "epoch": 0.30736842105263157,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00019778214439929452,
+      "loss": 1.1248,
+      "step": 73
+    },
+    {
+      "epoch": 0.31157894736842107,
+      "grad_norm": 0.23046875,
+      "learning_rate": 0.0001977114494037641,
+      "loss": 1.1204,
+      "step": 74
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001976396583361464,
+      "loss": 1.1662,
+      "step": 75
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00019756677200175315,
+      "loss": 1.1222,
+      "step": 76
+    },
+    {
+      "epoch": 0.32421052631578945,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 1.0329,
+      "step": 77
+    },
+    {
+      "epoch": 0.32842105263157895,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 0.0001974177168153088,
+      "loss": 1.1199,
+      "step": 78
+    },
+    {
+      "epoch": 0.33263157894736844,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.00019734154963527495,
+      "loss": 1.4391,
+      "step": 79
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.0001972642905324813,
+      "loss": 1.3924,
+      "step": 80
+    },
+    {
+      "epoch": 0.3410526315789474,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.00019718594037357713,
+      "loss": 1.1518,
+      "step": 81
+    },
+    {
+      "epoch": 0.3452631578947368,
+      "grad_norm": 0.953125,
+      "learning_rate": 0.0001971065000374504,
+      "loss": 1.2606,
+      "step": 82
+    },
+    {
+      "epoch": 0.3494736842105263,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001970259704152181,
+      "loss": 1.2293,
+      "step": 83
+    },
+    {
+      "epoch": 0.35368421052631577,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0001969443524102163,
+      "loss": 0.9564,
+      "step": 84
+    },
+    {
+      "epoch": 0.35789473684210527,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00019686164693798986,
+      "loss": 1.2023,
+      "step": 85
+    },
+    {
+      "epoch": 0.36210526315789476,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.0001967778549262822,
+      "loss": 0.9322,
+      "step": 86
+    },
+    {
+      "epoch": 0.3663157894736842,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00019669297731502507,
+      "loss": 1.2589,
+      "step": 87
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019660701505632772,
+      "loss": 1.3188,
+      "step": 88
+    },
+    {
+      "epoch": 0.37473684210526315,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019651996911446647,
+      "loss": 1.0415,
+      "step": 89
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.427734375,
+      "learning_rate": 0.0001964318404658737,
+      "loss": 1.467,
+      "step": 90
+    },
+    {
+      "epoch": 0.3831578947368421,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00019634263009912705,
+      "loss": 1.5527,
+      "step": 91
+    },
+    {
+      "epoch": 0.3873684210526316,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019625233901493822,
+      "loss": 1.2043,
+      "step": 92
+    },
+    {
+      "epoch": 0.391578947368421,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00019616096822614186,
+      "loss": 0.9677,
+      "step": 93
+    },
+    {
+      "epoch": 0.3957894736842105,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.000196068518757684,
+      "loss": 1.1942,
+      "step": 94
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00019597499164661093,
+      "loss": 1.3481,
+      "step": 95
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019588038794205703,
+      "loss": 1.2776,
+      "step": 96
+    },
+    {
+      "epoch": 0.40842105263157896,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00019578470870523359,
+      "loss": 1.4808,
+      "step": 97
+    },
+    {
+      "epoch": 0.4126315789473684,
+      "grad_norm": 0.28125,
+      "learning_rate": 0.00019568795500941635,
+      "loss": 1.3385,
+      "step": 98
+    },
+    {
+      "epoch": 0.4168421052631579,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019559012793993392,
+      "loss": 1.5787,
+      "step": 99
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019549122859415538,
+      "loss": 1.2151,
+      "step": 100
+    },
+    {
+      "epoch": 0.42526315789473684,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.0001953912580814779,
+      "loss": 1.0332,
+      "step": 101
+    },
+    {
+      "epoch": 0.42947368421052634,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00019529021752331453,
+      "loss": 1.2677,
+      "step": 102
+    },
+    {
+      "epoch": 0.4336842105263158,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001951881080530814,
+      "loss": 1.0672,
+      "step": 103
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00019508493081618513,
+      "loss": 1.1736,
+      "step": 104
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00019498068697000994,
+      "loss": 1.1174,
+      "step": 105
+    },
+    {
+      "epoch": 0.4463157894736842,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00019487537768390464,
+      "loss": 1.0712,
+      "step": 106
+    },
+    {
+      "epoch": 0.45052631578947366,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001947690041391696,
+      "loss": 1.4496,
+      "step": 107
+    },
+    {
+      "epoch": 0.45473684210526316,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00019466156752904343,
+      "loss": 1.2413,
+      "step": 108
+    },
+    {
+      "epoch": 0.4589473684210526,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001945530690586896,
+      "loss": 1.0208,
+      "step": 109
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.0001944435099451829,
+      "loss": 1.3997,
+      "step": 110
+    },
+    {
+      "epoch": 0.4673684210526316,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00019433289141749586,
+      "loss": 1.2914,
+      "step": 111
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 0.63671875,
+      "learning_rate": 0.00019422121471648497,
+      "loss": 0.8134,
+      "step": 112
+    },
+    {
+      "epoch": 0.47578947368421054,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019410848109487658,
+      "loss": 1.1282,
+      "step": 113
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001939946918172531,
+      "loss": 1.3254,
+      "step": 114
+    },
+    {
+      "epoch": 0.4842105263157895,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00019387984816003867,
+      "loss": 1.6428,
+      "step": 115
+    },
+    {
+      "epoch": 0.4884210526315789,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019376395141148476,
+      "loss": 1.0688,
+      "step": 116
+    },
+    {
+      "epoch": 0.4926315789473684,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00019364700287165604,
+      "loss": 1.0969,
+      "step": 117
+    },
+    {
+      "epoch": 0.4968421052631579,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.00019352900385241536,
+      "loss": 1.5249,
+      "step": 118
+    },
+    {
+      "epoch": 0.5010526315789474,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 0.00019340995567740938,
+      "loss": 1.2095,
+      "step": 119
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.0001932898596820536,
+      "loss": 1.1249,
+      "step": 120
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_loss": 1.2166697978973389,
+      "eval_runtime": 25.8713,
+      "eval_samples_per_second": 3.865,
+      "eval_steps_per_second": 1.933,
+      "step": 120
+    },
+    {
+      "epoch": 0.5094736842105263,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00019316871721351733,
+      "loss": 1.5017,
+      "step": 121
+    },
+    {
+      "epoch": 0.5136842105263157,
+      "grad_norm": 0.7421875,
+      "learning_rate": 0.0001930465296307087,
+      "loss": 1.0994,
+      "step": 122
+    },
+    {
+      "epoch": 0.5178947368421053,
+      "grad_norm": 0.21875,
+      "learning_rate": 0.0001929232983042592,
+      "loss": 1.0339,
+      "step": 123
+    },
+    {
+      "epoch": 0.5221052631578947,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00019279902461650866,
+      "loss": 1.1317,
+      "step": 124
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00019267370996148934,
+      "loss": 0.9421,
+      "step": 125
+    },
+    {
+      "epoch": 0.5305263157894737,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00019254735574491058,
+      "loss": 1.3029,
+      "step": 126
+    },
+    {
+      "epoch": 0.5347368421052632,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.00019241996338414296,
+      "loss": 1.3548,
+      "step": 127
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 0.84765625,
+      "learning_rate": 0.00019229153430820232,
+      "loss": 1.0865,
+      "step": 128
+    },
+    {
+      "epoch": 0.5431578947368421,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00019216206995773373,
+      "loss": 0.8151,
+      "step": 129
+    },
+    {
+      "epoch": 0.5473684210526316,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0001920315717849956,
+      "loss": 1.3576,
+      "step": 130
+    },
+    {
+      "epoch": 0.5515789473684211,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00019190004125384293,
+      "loss": 1.2439,
+      "step": 131
+    },
+    {
+      "epoch": 0.5557894736842105,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001917674798397113,
+      "loss": 0.9743,
+      "step": 132
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.1015625,
+      "learning_rate": 0.0001916338890296001,
+      "loss": 1.3315,
+      "step": 133
+    },
+    {
+      "epoch": 0.5642105263157895,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00019149927032205587,
+      "loss": 1.3268,
+      "step": 134
+    },
+    {
+      "epoch": 0.5684210526315789,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00019136362522715562,
+      "loss": 1.4751,
+      "step": 135
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019122695526648968,
+      "loss": 1.1219,
+      "step": 136
+    },
+    {
+      "epoch": 0.5768421052631579,
+      "grad_norm": 1.0703125,
+      "learning_rate": 0.00019108926197314486,
+      "loss": 1.4059,
+      "step": 137
+    },
+    {
+      "epoch": 0.5810526315789474,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019095054689168705,
+      "loss": 1.3282,
+      "step": 138
+    },
+    {
+      "epoch": 0.5852631578947368,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.00019081081157814404,
+      "loss": 1.6334,
+      "step": 139
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00019067005759998797,
+      "loss": 1.159,
+      "step": 140
+    },
+    {
+      "epoch": 0.5936842105263158,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019052828653611786,
+      "loss": 1.3261,
+      "step": 141
+    },
+    {
+      "epoch": 0.5978947368421053,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001903854999768417,
+      "loss": 1.2041,
+      "step": 142
+    },
+    {
+      "epoch": 0.6021052631578947,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019024169952385885,
+      "loss": 1.1998,
+      "step": 143
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.6427,
+      "step": 144
+    },
+    {
+      "epoch": 0.6105263157894737,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.00018995106340041873,
+      "loss": 1.1968,
+      "step": 145
+    },
+    {
+      "epoch": 0.6147368421052631,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00018980423099015402,
+      "loss": 0.8641,
+      "step": 146
+    },
+    {
+      "epoch": 0.6189473684210526,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00018965639120653121,
+      "loss": 1.4518,
+      "step": 147
+    },
+    {
+      "epoch": 0.6231578947368421,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00018950754570793384,
+      "loss": 1.3077,
+      "step": 148
+    },
+    {
+      "epoch": 0.6273684210526316,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.00018935769616402703,
+      "loss": 1.2077,
+      "step": 149
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.224609375,
+      "learning_rate": 0.00018920684425573865,
+      "loss": 1.0868,
+      "step": 150
+    },
+    {
+      "epoch": 0.6357894736842106,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00018905499167524062,
+      "loss": 1.2018,
+      "step": 151
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00018890214012592975,
+      "loss": 1.1675,
+      "step": 152
+    },
+    {
+      "epoch": 0.6442105263157895,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 0.00018874829132240874,
+      "loss": 1.2348,
+      "step": 153
+    },
+    {
+      "epoch": 0.6484210526315789,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.000188593446990467,
+      "loss": 1.3202,
+      "step": 154
+    },
+    {
+      "epoch": 0.6526315789473685,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.0001884376088670611,
+      "loss": 1.0171,
+      "step": 155
+    },
+    {
+      "epoch": 0.6568421052631579,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.00018828077870029552,
+      "loss": 1.219,
+      "step": 156
+    },
+    {
+      "epoch": 0.6610526315789473,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00018812295824940285,
+      "loss": 0.8956,
+      "step": 157
+    },
+    {
+      "epoch": 0.6652631578947369,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.00018796414928472417,
+      "loss": 0.9322,
+      "step": 158
+    },
+    {
+      "epoch": 0.6694736842105263,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.0001878043535876891,
+      "loss": 1.2062,
+      "step": 159
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001876435729507959,
+      "loss": 1.3113,
+      "step": 160
+    },
+    {
+      "epoch": 0.6778947368421052,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00018748180917759136,
+      "loss": 1.1539,
+      "step": 161
+    },
+    {
+      "epoch": 0.6821052631578948,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.0001873190640826505,
+      "loss": 1.3287,
+      "step": 162
+    },
+    {
+      "epoch": 0.6863157894736842,
+      "grad_norm": 0.298828125,
+      "learning_rate": 0.00018715533949155625,
+      "loss": 1.0616,
+      "step": 163
+    },
+    {
+      "epoch": 0.6905263157894737,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018699063724087904,
+      "loss": 1.0171,
+      "step": 164
+    },
+    {
+      "epoch": 0.6947368421052632,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00018682495917815608,
+      "loss": 1.1113,
+      "step": 165
+    },
+    {
+      "epoch": 0.6989473684210527,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00018665830716187065,
+      "loss": 0.8351,
+      "step": 166
+    },
+    {
+      "epoch": 0.7031578947368421,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001864906830614314,
+      "loss": 1.2181,
+      "step": 167
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001863220887571512,
+      "loss": 1.1843,
+      "step": 168
+    },
+    {
+      "epoch": 0.7115789473684211,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018615252614022617,
+      "loss": 1.3809,
+      "step": 169
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.0001859819971127143,
+      "loss": 1.4288,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00018581050358751445,
+      "loss": 1.1449,
+      "step": 171
+    },
+    {
+      "epoch": 0.7242105263157895,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.00018563804748834438,
+      "loss": 1.0703,
+      "step": 172
+    },
+    {
+      "epoch": 0.728421052631579,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00018546463074971977,
+      "loss": 1.2093,
+      "step": 173
+    },
+    {
+      "epoch": 0.7326315789473684,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.000185290255316932,
+      "loss": 0.7346,
+      "step": 174
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00018511492314602656,
+      "loss": 1.2782,
+      "step": 175
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00018493863620378122,
+      "loss": 1.0844,
+      "step": 176
+    },
+    {
+      "epoch": 0.7452631578947368,
+      "grad_norm": 0.2470703125,
+      "learning_rate": 0.00018476139646768372,
+      "loss": 1.1771,
+      "step": 177
+    },
+    {
+      "epoch": 0.7494736842105263,
+      "grad_norm": 0.228515625,
+      "learning_rate": 0.00018458320592590975,
+      "loss": 1.2,
+      "step": 178
+    },
+    {
+      "epoch": 0.7536842105263157,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00018440406657730058,
+      "loss": 1.2248,
+      "step": 179
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00018422398043134067,
+      "loss": 1.3675,
+      "step": 180
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "eval_loss": 1.2129631042480469,
+      "eval_runtime": 25.9253,
+      "eval_samples_per_second": 3.857,
+      "eval_steps_per_second": 1.929,
+      "step": 180
+    },
+    {
+      "epoch": 0.7621052631578947,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001840429495081352,
+      "loss": 1.2456,
+      "step": 181
+    },
+    {
+      "epoch": 0.7663157894736842,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00018386097583838714,
+      "loss": 1.2617,
+      "step": 182
+    },
+    {
+      "epoch": 0.7705263157894737,
+      "grad_norm": 0.283203125,
+      "learning_rate": 0.00018367806146337483,
+      "loss": 1.2708,
+      "step": 183
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.00018349420843492888,
+      "loss": 1.3771,
+      "step": 184
+    },
+    {
+      "epoch": 0.7789473684210526,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00018330941881540915,
+      "loss": 1.3123,
+      "step": 185
+    },
+    {
+      "epoch": 0.783157894736842,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.00018312369467768166,
+      "loss": 1.1952,
+      "step": 186
+    },
+    {
+      "epoch": 0.7873684210526316,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.00018293703810509537,
+      "loss": 1.426,
+      "step": 187
+    },
+    {
+      "epoch": 0.791578947368421,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.0001827494511914587,
+      "loss": 1.3205,
+      "step": 188
+    },
+    {
+      "epoch": 0.7957894736842105,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00018256093604101617,
+      "loss": 1.2221,
+      "step": 189
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0001823714947684247,
+      "loss": 1.4212,
+      "step": 190
+    },
+    {
+      "epoch": 0.8042105263157895,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00018218112949872995,
+      "loss": 1.2183,
+      "step": 191
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00018198984236734246,
+      "loss": 0.9922,
+      "step": 192
+    },
+    {
+      "epoch": 0.8126315789473684,
+      "grad_norm": 0.373046875,
+      "learning_rate": 0.0001817976355200137,
+      "loss": 1.334,
+      "step": 193
+    },
+    {
+      "epoch": 0.8168421052631579,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.000181604511112812,
+      "loss": 1.1052,
+      "step": 194
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.0001814104713120983,
+      "loss": 0.8112,
+      "step": 195
+    },
+    {
+      "epoch": 0.8252631578947368,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.000181215518294502,
+      "loss": 1.2507,
+      "step": 196
+    },
+    {
+      "epoch": 0.8294736842105264,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.0001810196542468964,
+      "loss": 1.1228,
+      "step": 197
+    },
+    {
+      "epoch": 0.8336842105263158,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00018082288136637422,
+      "loss": 1.3562,
+      "step": 198
+    },
+    {
+      "epoch": 0.8378947368421052,
+      "grad_norm": 0.302734375,
+      "learning_rate": 0.000180625201860223,
+      "loss": 0.7766,
+      "step": 199
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00018042661794590023,
+      "loss": 1.2885,
+      "step": 200
+    },
+    {
+      "epoch": 0.8463157894736842,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.0001802271318510086,
+      "loss": 1.271,
+      "step": 201
+    },
+    {
+      "epoch": 0.8505263157894737,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00018002674581327094,
+      "loss": 1.3777,
+      "step": 202
+    },
+    {
+      "epoch": 0.8547368421052631,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00017982546208050515,
+      "loss": 1.32,
+      "step": 203
+    },
+    {
+      "epoch": 0.8589473684210527,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00017962328291059888,
+      "loss": 1.1265,
+      "step": 204
+    },
+    {
+      "epoch": 0.8631578947368421,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00017942021057148436,
+      "loss": 1.523,
+      "step": 205
+    },
+    {
+      "epoch": 0.8673684210526316,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00017921624734111292,
+      "loss": 1.0251,
+      "step": 206
+    },
+    {
+      "epoch": 0.871578947368421,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001790113955074294,
+      "loss": 1.2665,
+      "step": 207
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 0.6875,
+      "learning_rate": 0.0001788056573683464,
+      "loss": 1.2244,
+      "step": 208
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2177734375,
+      "learning_rate": 0.0001785990352317187,
+      "loss": 1.1621,
+      "step": 209
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00017839153141531718,
+      "loss": 1.3182,
+      "step": 210
+    },
+    {
+      "epoch": 0.888421052631579,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.000178183148246803,
+      "loss": 1.4508,
+      "step": 211
+    },
+    {
+      "epoch": 0.8926315789473684,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00017797388806370132,
+      "loss": 1.1155,
+      "step": 212
+    },
+    {
+      "epoch": 0.8968421052631579,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.00017776375321337521,
+      "loss": 0.9191,
+      "step": 213
+    },
+    {
+      "epoch": 0.9010526315789473,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 0.00017755274605299923,
+      "loss": 1.1577,
+      "step": 214
+    },
+    {
+      "epoch": 0.9052631578947369,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017734086894953305,
+      "loss": 1.372,
+      "step": 215
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 0.353515625,
+      "learning_rate": 0.00017712812427969485,
+      "loss": 1.1932,
+      "step": 216
+    },
+    {
+      "epoch": 0.9136842105263158,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.0001769145144299347,
+      "loss": 1.3167,
+      "step": 217
+    },
+    {
+      "epoch": 0.9178947368421052,
+      "grad_norm": 0.255859375,
+      "learning_rate": 0.00017670004179640774,
+      "loss": 1.2357,
+      "step": 218
+    },
+    {
+      "epoch": 0.9221052631578948,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.00017648470878494737,
+      "loss": 0.9556,
+      "step": 219
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.0001762685178110382,
+      "loss": 1.2047,
+      "step": 220
+    },
+    {
+      "epoch": 0.9305263157894736,
+      "grad_norm": 0.271484375,
+      "learning_rate": 0.00017605147129978903,
+      "loss": 1.1935,
+      "step": 221
+    },
+    {
+      "epoch": 0.9347368421052632,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.0001758335716859055,
+      "loss": 1.3426,
+      "step": 222
+    },
+    {
+      "epoch": 0.9389473684210526,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.000175614821413663,
+      "loss": 1.5181,
+      "step": 223
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00017539522293687898,
+      "loss": 1.0962,
+      "step": 224
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00017517477871888568,
+      "loss": 1.3922,
+      "step": 225
+    },
+    {
+      "epoch": 0.9515789473684211,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00017495349123250242,
+      "loss": 1.2535,
+      "step": 226
+    },
+    {
+      "epoch": 0.9557894736842105,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00017473136296000772,
+      "loss": 1.1987,
+      "step": 227
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017450839639311162,
+      "loss": 1.4301,
+      "step": 228
+    },
+    {
+      "epoch": 0.9642105263157895,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00017428459403292767,
+      "loss": 1.3164,
+      "step": 229
+    },
+    {
+      "epoch": 0.968421052631579,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.00017405995838994494,
+      "loss": 1.1554,
+      "step": 230
+    },
+    {
+      "epoch": 0.9726315789473684,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00017383449198399964,
+      "loss": 1.3036,
+      "step": 231
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00017360819734424715,
+      "loss": 1.2797,
+      "step": 232
+    },
+    {
+      "epoch": 0.9810526315789474,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017338107700913354,
+      "loss": 1.1202,
+      "step": 233
+    },
+    {
+      "epoch": 0.9852631578947368,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001731531335263669,
+      "loss": 0.8187,
+      "step": 234
+    },
+    {
+      "epoch": 0.9894736842105263,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001729243694528891,
+      "loss": 1.1702,
+      "step": 235
+    },
+    {
+      "epoch": 0.9936842105263158,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00017269478735484683,
+      "loss": 1.1406,
+      "step": 236
+    },
+    {
+      "epoch": 0.9978947368421053,
+      "grad_norm": 0.3359375,
+      "learning_rate": 0.00017246438980756293,
+      "loss": 0.9633,
+      "step": 237
+    },
+    {
+      "epoch": 1.0021052631578948,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00017223317939550753,
+      "loss": 1.2181,
+      "step": 238
+    },
+    {
+      "epoch": 1.0063157894736843,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 0.00017200115871226904,
+      "loss": 1.2035,
+      "step": 239
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00017176833036052495,
+      "loss": 1.3449,
+      "step": 240
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "eval_loss": 1.1994891166687012,
+      "eval_runtime": 25.9787,
+      "eval_samples_per_second": 3.849,
+      "eval_steps_per_second": 1.925,
+      "step": 240
+    },
+    {
+      "epoch": 1.0147368421052632,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00017153469695201277,
+      "loss": 1.0695,
+      "step": 241
+    },
+    {
+      "epoch": 1.0189473684210526,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.0001713002611075007,
+      "loss": 0.8898,
+      "step": 242
+    },
+    {
+      "epoch": 1.023157894736842,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.0001710650254567582,
+      "loss": 1.087,
+      "step": 243
+    },
+    {
+      "epoch": 1.0273684210526315,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.0001708289926385265,
+      "loss": 1.1739,
+      "step": 244
+    },
+    {
+      "epoch": 1.0315789473684212,
+      "grad_norm": 0.3515625,
+      "learning_rate": 0.000170592165300489,
+      "loss": 1.0413,
+      "step": 245
+    },
+    {
+      "epoch": 1.0357894736842106,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001703545460992416,
+      "loss": 1.0745,
+      "step": 246
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.25,
+      "learning_rate": 0.00017011613770026292,
+      "loss": 1.2494,
+      "step": 247
+    },
+    {
+      "epoch": 1.0442105263157895,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.00016987694277788417,
+      "loss": 0.7568,
+      "step": 248
+    },
+    {
+      "epoch": 1.048421052631579,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001696369640152596,
+      "loss": 1.2675,
+      "step": 249
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001693962041043359,
+      "loss": 1.0456,
+      "step": 250
+    },
+    {
+      "epoch": 1.0568421052631578,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.00016915466574582246,
+      "loss": 1.1145,
+      "step": 251
+    },
+    {
+      "epoch": 1.0610526315789475,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00016891235164916065,
+      "loss": 1.1659,
+      "step": 252
+    },
+    {
+      "epoch": 1.065263157894737,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.0001686692645324938,
+      "loss": 0.9993,
+      "step": 253
+    },
+    {
+      "epoch": 1.0694736842105264,
+      "grad_norm": 0.78125,
+      "learning_rate": 0.00016842540712263637,
+      "loss": 1.2847,
+      "step": 254
+    },
+    {
+      "epoch": 1.0736842105263158,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.0001681807821550438,
+      "loss": 1.1483,
+      "step": 255
+    },
+    {
+      "epoch": 1.0778947368421052,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00016793539237378128,
+      "loss": 0.7895,
+      "step": 256
+    },
+    {
+      "epoch": 1.0821052631578947,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00016768924053149338,
+      "loss": 1.2321,
+      "step": 257
+    },
+    {
+      "epoch": 1.0863157894736841,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00016744232938937308,
+      "loss": 1.0098,
+      "step": 258
+    },
+    {
+      "epoch": 1.0905263157894738,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00016719466171713073,
+      "loss": 1.3362,
+      "step": 259
+    },
+    {
+      "epoch": 1.0947368421052632,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.0001669462402929629,
+      "loss": 1.2487,
+      "step": 260
+    },
+    {
+      "epoch": 1.0989473684210527,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00016669706790352148,
+      "loss": 1.1732,
+      "step": 261
+    },
+    {
+      "epoch": 1.1031578947368421,
+      "grad_norm": 0.28125,
+      "learning_rate": 0.00016644714734388217,
+      "loss": 1.1493,
+      "step": 262
+    },
+    {
+      "epoch": 1.1073684210526316,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001661964814175133,
+      "loss": 1.0521,
+      "step": 263
+    },
+    {
+      "epoch": 1.111578947368421,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00016594507293624425,
+      "loss": 1.07,
+      "step": 264
+    },
+    {
+      "epoch": 1.1157894736842104,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00016569292472023392,
+      "loss": 1.1393,
+      "step": 265
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00016544003959793925,
+      "loss": 1.2059,
+      "step": 266
+    },
+    {
+      "epoch": 1.1242105263157895,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001651864204060833,
+      "loss": 0.9832,
+      "step": 267
+    },
+    {
+      "epoch": 1.128421052631579,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00016493206998962354,
+      "loss": 0.9154,
+      "step": 268
+    },
+    {
+      "epoch": 1.1326315789473684,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.00016467699120171987,
+      "loss": 1.0839,
+      "step": 269
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.0001644211869037027,
+      "loss": 1.1298,
+      "step": 270
+    },
+    {
+      "epoch": 1.1410526315789473,
+      "grad_norm": 0.341796875,
+      "learning_rate": 0.00016416465996504077,
+      "loss": 1.131,
+      "step": 271
+    },
+    {
+      "epoch": 1.1452631578947368,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00016390741326330907,
+      "loss": 1.0148,
+      "step": 272
+    },
+    {
+      "epoch": 1.1494736842105264,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00016364944968415632,
+      "loss": 0.788,
+      "step": 273
+    },
+    {
+      "epoch": 1.1536842105263159,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00016339077212127294,
+      "loss": 0.9585,
+      "step": 274
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00016313138347635837,
+      "loss": 0.9937,
+      "step": 275
+    },
+    {
+      "epoch": 1.1621052631578948,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.0001628712866590885,
+      "loss": 1.069,
+      "step": 276
+    },
+    {
+      "epoch": 1.1663157894736842,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.00016261048458708318,
+      "loss": 1.2734,
+      "step": 277
+    },
+    {
+      "epoch": 1.1705263157894736,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.1955,
+      "step": 278
+    },
+    {
+      "epoch": 1.174736842105263,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00016208677638886835,
+      "loss": 0.9949,
+      "step": 279
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00016182387613732291,
+      "loss": 1.1192,
+      "step": 280
+    },
+    {
+      "epoch": 1.1831578947368422,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.00016156028238030422,
+      "loss": 1.165,
+      "step": 281
+    },
+    {
+      "epoch": 1.1873684210526316,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00016129599807465875,
+      "loss": 0.9109,
+      "step": 282
+    },
+    {
+      "epoch": 1.191578947368421,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00016103102618497922,
+      "loss": 0.9441,
+      "step": 283
+    },
+    {
+      "epoch": 1.1957894736842105,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.0001607653696835713,
+      "loss": 1.3679,
+      "step": 284
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.0001604990315504202,
+      "loss": 0.8203,
+      "step": 285
+    },
+    {
+      "epoch": 1.2042105263157894,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00016023201477315731,
+      "loss": 1.052,
+      "step": 286
+    },
+    {
+      "epoch": 1.208421052631579,
+      "grad_norm": 0.72265625,
+      "learning_rate": 0.00015996432234702666,
+      "loss": 1.281,
+      "step": 287
+    },
+    {
+      "epoch": 1.2126315789473685,
+      "grad_norm": 0.44921875,
+      "learning_rate": 0.0001596959572748514,
+      "loss": 1.1851,
+      "step": 288
+    },
+    {
+      "epoch": 1.216842105263158,
+      "grad_norm": 1.3515625,
+      "learning_rate": 0.0001594269225669999,
+      "loss": 1.1378,
+      "step": 289
+    },
+    {
+      "epoch": 1.2210526315789474,
+      "grad_norm": 0.337890625,
+      "learning_rate": 0.00015915722124135227,
+      "loss": 0.7495,
+      "step": 290
+    },
+    {
+      "epoch": 1.2252631578947368,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00015888685632326627,
+      "loss": 1.0089,
+      "step": 291
+    },
+    {
+      "epoch": 1.2294736842105263,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00015861583084554349,
+      "loss": 0.7145,
+      "step": 292
+    },
+    {
+      "epoch": 1.2336842105263157,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.00015834414784839532,
+      "loss": 1.1728,
+      "step": 293
+    },
+    {
+      "epoch": 1.2378947368421054,
+      "grad_norm": 1.5703125,
+      "learning_rate": 0.0001580718103794089,
+      "loss": 1.351,
+      "step": 294
+    },
+    {
+      "epoch": 1.2421052631578948,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001577988214935127,
+      "loss": 1.0116,
+      "step": 295
+    },
+    {
+      "epoch": 1.2463157894736843,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00015752518425294257,
+      "loss": 1.1591,
+      "step": 296
+    },
+    {
+      "epoch": 1.2505263157894737,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.0001572509017272072,
+      "loss": 1.0848,
+      "step": 297
+    },
+    {
+      "epoch": 1.2547368421052632,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00015697597699305366,
+      "loss": 1.0024,
+      "step": 298
+    },
+    {
+      "epoch": 1.2589473684210526,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00015670041313443304,
+      "loss": 1.072,
+      "step": 299
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.00015642421324246568,
+      "loss": 1.1825,
+      "step": 300
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 1.207429051399231,
+      "eval_runtime": 25.9189,
+      "eval_samples_per_second": 3.858,
+      "eval_steps_per_second": 1.929,
+      "step": 300
+    },
+    {
+      "epoch": 1.2673684210526317,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.00015614738041540668,
+      "loss": 0.8984,
+      "step": 301
+    },
+    {
+      "epoch": 1.271578947368421,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00015586991775861102,
+      "loss": 0.9569,
+      "step": 302
+    },
+    {
+      "epoch": 1.2757894736842106,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.00015559182838449873,
+      "loss": 1.177,
+      "step": 303
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.416015625,
+      "learning_rate": 0.00015531311541251995,
+      "loss": 0.9957,
+      "step": 304
+    },
+    {
+      "epoch": 1.2842105263157895,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00015503378196912013,
+      "loss": 0.8083,
+      "step": 305
+    },
+    {
+      "epoch": 1.288421052631579,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.00015475383118770472,
+      "loss": 1.0463,
+      "step": 306
+    },
+    {
+      "epoch": 1.2926315789473684,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00015447326620860415,
+      "loss": 1.0709,
+      "step": 307
+    },
+    {
+      "epoch": 1.296842105263158,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00015419209017903852,
+      "loss": 1.2547,
+      "step": 308
+    },
+    {
+      "epoch": 1.3010526315789472,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.00015391030625308249,
+      "loss": 0.8027,
+      "step": 309
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001536279175916296,
+      "loss": 1.0735,
+      "step": 310
+    },
+    {
+      "epoch": 1.3094736842105263,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00015334492736235705,
+      "loss": 1.0046,
+      "step": 311
+    },
+    {
+      "epoch": 1.3136842105263158,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.0001530613387396901,
+      "loss": 1.1327,
+      "step": 312
+    },
+    {
+      "epoch": 1.3178947368421052,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00015277715490476641,
+      "loss": 0.9917,
+      "step": 313
+    },
+    {
+      "epoch": 1.3221052631578947,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.0001524923790454004,
+      "loss": 1.2532,
+      "step": 314
+    },
+    {
+      "epoch": 1.3263157894736843,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001522070143560476,
+      "loss": 0.9906,
+      "step": 315
+    },
+    {
+      "epoch": 1.3305263157894736,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00015192106403776848,
+      "loss": 1.0958,
+      "step": 316
+    },
+    {
+      "epoch": 1.3347368421052632,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.000151634531298193,
+      "loss": 1.1674,
+      "step": 317
+    },
+    {
+      "epoch": 1.3389473684210527,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.0001513474193514842,
+      "loss": 0.9189,
+      "step": 318
+    },
+    {
+      "epoch": 1.343157894736842,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001510597314183025,
+      "loss": 1.2956,
+      "step": 319
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00015077147072576933,
+      "loss": 1.3053,
+      "step": 320
+    },
+    {
+      "epoch": 1.351578947368421,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.00015048264050743096,
+      "loss": 1.26,
+      "step": 321
+    },
+    {
+      "epoch": 1.3557894736842107,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.00015019324400322243,
+      "loss": 1.1314,
+      "step": 322
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00014990328445943092,
+      "loss": 1.1536,
+      "step": 323
+    },
+    {
+      "epoch": 1.3642105263157895,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00014961276512865954,
+      "loss": 0.8678,
+      "step": 324
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00014932168926979074,
+      "loss": 1.0508,
+      "step": 325
+    },
+    {
+      "epoch": 1.3726315789473684,
+      "grad_norm": 0.333984375,
+      "learning_rate": 0.00014903006014794983,
+      "loss": 0.9275,
+      "step": 326
+    },
+    {
+      "epoch": 1.3768421052631579,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00014873788103446825,
+      "loss": 1.0225,
+      "step": 327
+    },
+    {
+      "epoch": 1.3810526315789473,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00014844515520684703,
+      "loss": 0.9955,
+      "step": 328
+    },
+    {
+      "epoch": 1.385263157894737,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.00014815188594871983,
+      "loss": 1.2857,
+      "step": 329
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00014785807654981627,
+      "loss": 1.0598,
+      "step": 330
+    },
+    {
+      "epoch": 1.3936842105263159,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00014756373030592497,
+      "loss": 1.1031,
+      "step": 331
+    },
+    {
+      "epoch": 1.3978947368421053,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00014726885051885653,
+      "loss": 1.3287,
+      "step": 332
+    },
+    {
+      "epoch": 1.4021052631578947,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00014697344049640658,
+      "loss": 1.1952,
+      "step": 333
+    },
+    {
+      "epoch": 1.4063157894736842,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001466775035523186,
+      "loss": 1.083,
+      "step": 334
+    },
+    {
+      "epoch": 1.4105263157894736,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00014638104300624685,
+      "loss": 0.8393,
+      "step": 335
+    },
+    {
+      "epoch": 1.4147368421052633,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00014608406218371894,
+      "loss": 1.3947,
+      "step": 336
+    },
+    {
+      "epoch": 1.4189473684210525,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.0001457865644160987,
+      "loss": 1.028,
+      "step": 337
+    },
+    {
+      "epoch": 1.4231578947368422,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00014548855304054886,
+      "loss": 1.1156,
+      "step": 338
+    },
+    {
+      "epoch": 1.4273684210526316,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00014519003139999337,
+      "loss": 1.1537,
+      "step": 339
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00014489100284308017,
+      "loss": 1.207,
+      "step": 340
+    },
+    {
+      "epoch": 1.4357894736842105,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00014459147072414335,
+      "loss": 1.125,
+      "step": 341
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00014429143840316585,
+      "loss": 1.0774,
+      "step": 342
+    },
+    {
+      "epoch": 1.4442105263157896,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.0001439909092457415,
+      "loss": 1.3349,
+      "step": 343
+    },
+    {
+      "epoch": 1.4484210526315788,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00014368988662303732,
+      "loss": 0.6138,
+      "step": 344
+    },
+    {
+      "epoch": 1.4526315789473685,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 1.1961,
+      "step": 345
+    },
+    {
+      "epoch": 1.456842105263158,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00014308637449409706,
+      "loss": 1.067,
+      "step": 346
+    },
+    {
+      "epoch": 1.4610526315789474,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.0001427838917577206,
+      "loss": 1.0033,
+      "step": 347
+    },
+    {
+      "epoch": 1.4652631578947368,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00014248092909570774,
+      "loss": 1.011,
+      "step": 348
+    },
+    {
+      "epoch": 1.4694736842105263,
+      "grad_norm": 0.75,
+      "learning_rate": 0.00014217748990652318,
+      "loss": 1.3504,
+      "step": 349
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00014187357759397714,
+      "loss": 1.0421,
+      "step": 350
+    },
+    {
+      "epoch": 1.4778947368421052,
+      "grad_norm": 0.73828125,
+      "learning_rate": 0.00014156919556718698,
+      "loss": 1.1829,
+      "step": 351
+    },
+    {
+      "epoch": 1.4821052631578948,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00014126434724053913,
+      "loss": 1.1985,
+      "step": 352
+    },
+    {
+      "epoch": 1.4863157894736843,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00014095903603365066,
+      "loss": 1.1609,
+      "step": 353
+    },
+    {
+      "epoch": 1.4905263157894737,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00014065326537133094,
+      "loss": 1.2552,
+      "step": 354
+    },
+    {
+      "epoch": 1.4947368421052631,
+      "grad_norm": 1.2265625,
+      "learning_rate": 0.0001403470386835434,
+      "loss": 0.9655,
+      "step": 355
+    },
+    {
+      "epoch": 1.4989473684210526,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.0001400403594053667,
+      "loss": 0.9709,
+      "step": 356
+    },
+    {
+      "epoch": 1.5031578947368422,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00013973323097695657,
+      "loss": 1.048,
+      "step": 357
+    },
+    {
+      "epoch": 1.5073684210526315,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00013942565684350698,
+      "loss": 1.0853,
+      "step": 358
+    },
+    {
+      "epoch": 1.5115789473684211,
+      "grad_norm": 0.9140625,
+      "learning_rate": 0.00013911764045521159,
+      "loss": 1.1191,
+      "step": 359
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.00013880918526722497,
+      "loss": 0.9782,
+      "step": 360
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "eval_loss": 1.2060081958770752,
+      "eval_runtime": 25.9425,
+      "eval_samples_per_second": 3.855,
+      "eval_steps_per_second": 1.927,
+      "step": 360
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.361328125,
+      "learning_rate": 0.00013850029473962402,
+      "loss": 0.9822,
+      "step": 361
+    },
+    {
+      "epoch": 1.5242105263157895,
+      "grad_norm": 0.44921875,
+      "learning_rate": 0.00013819097233736888,
+      "loss": 0.957,
+      "step": 362
+    },
+    {
+      "epoch": 1.528421052631579,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.0001378812215302644,
+      "loss": 0.9774,
+      "step": 363
+    },
+    {
+      "epoch": 1.5326315789473686,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00013757104579292082,
+      "loss": 1.2854,
+      "step": 364
+    },
+    {
+      "epoch": 1.5368421052631578,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00013726044860471522,
+      "loss": 0.9209,
+      "step": 365
+    },
+    {
+      "epoch": 1.5410526315789475,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.00013694943344975212,
+      "loss": 0.9489,
+      "step": 366
+    },
+    {
+      "epoch": 1.545263157894737,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00013663800381682464,
+      "loss": 1.2956,
+      "step": 367
+    },
+    {
+      "epoch": 1.5494736842105263,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00013632616319937522,
+      "loss": 1.0642,
+      "step": 368
+    },
+    {
+      "epoch": 1.5536842105263158,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.0001360139150954566,
+      "loss": 1.034,
+      "step": 369
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.00013570126300769232,
+      "loss": 0.8314,
+      "step": 370
+    },
+    {
+      "epoch": 1.5621052631578949,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00013538821044323772,
+      "loss": 1.1934,
+      "step": 371
+    },
+    {
+      "epoch": 1.566315789473684,
+      "grad_norm": 0.353515625,
+      "learning_rate": 0.0001350747609137404,
+      "loss": 1.2661,
+      "step": 372
+    },
+    {
+      "epoch": 1.5705263157894738,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00013476091793530092,
+      "loss": 0.9746,
+      "step": 373
+    },
+    {
+      "epoch": 1.5747368421052632,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.0001344466850284333,
+      "loss": 1.0562,
+      "step": 374
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00013413206571802558,
+      "loss": 0.8612,
+      "step": 375
+    },
+    {
+      "epoch": 1.583157894736842,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00013381706353330014,
+      "loss": 0.7912,
+      "step": 376
+    },
+    {
+      "epoch": 1.5873684210526315,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00013350168200777448,
+      "loss": 1.0244,
+      "step": 377
+    },
+    {
+      "epoch": 1.5915789473684212,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.0001331859246792211,
+      "loss": 1.1267,
+      "step": 378
+    },
+    {
+      "epoch": 1.5957894736842104,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00013286979508962815,
+      "loss": 1.0055,
+      "step": 379
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.0001325532967851596,
+      "loss": 1.2348,
+      "step": 380
+    },
+    {
+      "epoch": 1.6042105263157893,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00013223643331611537,
+      "loss": 0.991,
+      "step": 381
+    },
+    {
+      "epoch": 1.608421052631579,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00013191920823689177,
+      "loss": 1.0261,
+      "step": 382
+    },
+    {
+      "epoch": 1.6126315789473684,
+      "grad_norm": 0.90234375,
+      "learning_rate": 0.00013160162510594123,
+      "loss": 1.0752,
+      "step": 383
+    },
+    {
+      "epoch": 1.6168421052631579,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00013128368748573273,
+      "loss": 1.1808,
+      "step": 384
+    },
+    {
+      "epoch": 1.6210526315789475,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001309653989427117,
+      "loss": 0.8969,
+      "step": 385
+    },
+    {
+      "epoch": 1.6252631578947367,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00013064676304726,
+      "loss": 1.1139,
+      "step": 386
+    },
+    {
+      "epoch": 1.6294736842105264,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.00013032778337365592,
+      "loss": 1.2781,
+      "step": 387
+    },
+    {
+      "epoch": 1.6336842105263156,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.0001300084635000341,
+      "loss": 1.1434,
+      "step": 388
+    },
+    {
+      "epoch": 1.6378947368421053,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00012968880700834517,
+      "loss": 0.7428,
+      "step": 389
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.000129368817484316,
+      "loss": 1.256,
+      "step": 390
+    },
+    {
+      "epoch": 1.6463157894736842,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.00012904849851740906,
+      "loss": 1.1516,
+      "step": 391
+    },
+    {
+      "epoch": 1.6505263157894738,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.0001287278537007824,
+      "loss": 1.1683,
+      "step": 392
+    },
+    {
+      "epoch": 1.654736842105263,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.0001284068866312492,
+      "loss": 0.9682,
+      "step": 393
+    },
+    {
+      "epoch": 1.6589473684210527,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.00012808560090923758,
+      "loss": 1.2109,
+      "step": 394
+    },
+    {
+      "epoch": 1.663157894736842,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00012776400013875006,
+      "loss": 1.1139,
+      "step": 395
+    },
+    {
+      "epoch": 1.6673684210526316,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00012744208792732324,
+      "loss": 1.0977,
+      "step": 396
+    },
+    {
+      "epoch": 1.671578947368421,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.00012711986788598725,
+      "loss": 1.1872,
+      "step": 397
+    },
+    {
+      "epoch": 1.6757894736842105,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00012679734362922528,
+      "loss": 1.0773,
+      "step": 398
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.00012647451877493307,
+      "loss": 0.6203,
+      "step": 399
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00012615139694437835,
+      "loss": 1.1557,
+      "step": 400
+    },
+    {
+      "epoch": 1.688421052631579,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.00012582798176215997,
+      "loss": 1.1022,
+      "step": 401
+    },
+    {
+      "epoch": 1.6926315789473683,
+      "grad_norm": 0.4609375,
+      "learning_rate": 0.00012550427685616765,
+      "loss": 1.193,
+      "step": 402
+    },
+    {
+      "epoch": 1.696842105263158,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00012518028585754094,
+      "loss": 0.8758,
+      "step": 403
+    },
+    {
+      "epoch": 1.7010526315789474,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00012485601240062869,
+      "loss": 0.9792,
+      "step": 404
+    },
+    {
+      "epoch": 1.7052631578947368,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00012453146012294812,
+      "loss": 1.1347,
+      "step": 405
+    },
+    {
+      "epoch": 1.7094736842105265,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00012420663266514417,
+      "loss": 1.1692,
+      "step": 406
+    },
+    {
+      "epoch": 1.7136842105263157,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00012388153367094858,
+      "loss": 0.9904,
+      "step": 407
+    },
+    {
+      "epoch": 1.7178947368421054,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.0001235561667871391,
+      "loss": 0.8854,
+      "step": 408
+    },
+    {
+      "epoch": 1.7221052631578946,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00012323053566349834,
+      "loss": 1.3143,
+      "step": 409
+    },
+    {
+      "epoch": 1.7263157894736842,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.0001229046439527732,
+      "loss": 1.0957,
+      "step": 410
+    },
+    {
+      "epoch": 1.7305263157894737,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00012257849531063352,
+      "loss": 1.0458,
+      "step": 411
+    },
+    {
+      "epoch": 1.7347368421052631,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 1.3262,
+      "step": 412
+    },
+    {
+      "epoch": 1.7389473684210528,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00012192544186916006,
+      "loss": 1.1506,
+      "step": 413
+    },
+    {
+      "epoch": 1.743157894736842,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00012159854439541245,
+      "loss": 1.035,
+      "step": 414
+    },
+    {
+      "epoch": 1.7473684210526317,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00012127140464134066,
+      "loss": 1.3485,
+      "step": 415
+    },
+    {
+      "epoch": 1.751578947368421,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00012094402627661447,
+      "loss": 1.1842,
+      "step": 416
+    },
+    {
+      "epoch": 1.7557894736842106,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.00012061641297358022,
+      "loss": 1.4594,
+      "step": 417
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.00012028856840721974,
+      "loss": 1.1014,
+      "step": 418
+    },
+    {
+      "epoch": 1.7642105263157895,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.00011996049625510901,
+      "loss": 0.7333,
+      "step": 419
+    },
+    {
+      "epoch": 1.768421052631579,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00011963220019737691,
+      "loss": 1.2063,
+      "step": 420
+    },
+    {
+      "epoch": 1.768421052631579,
+      "eval_loss": 1.199410080909729,
+      "eval_runtime": 25.8809,
+      "eval_samples_per_second": 3.864,
+      "eval_steps_per_second": 1.932,
+      "step": 420
+    },
+    {
+      "epoch": 1.7726315789473683,
+      "grad_norm": 0.73046875,
+      "learning_rate": 0.00011930368391666398,
+      "loss": 1.2112,
+      "step": 421
+    },
+    {
+      "epoch": 1.776842105263158,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.00011897495109808107,
+      "loss": 1.0342,
+      "step": 422
+    },
+    {
+      "epoch": 1.7810526315789472,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00011864600542916813,
+      "loss": 1.2239,
+      "step": 423
+    },
+    {
+      "epoch": 1.7852631578947369,
+      "grad_norm": 0.361328125,
+      "learning_rate": 0.00011831685059985262,
+      "loss": 0.9817,
+      "step": 424
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.30859375,
+      "learning_rate": 0.00011798749030240834,
+      "loss": 1.3617,
+      "step": 425
+    },
+    {
+      "epoch": 1.7936842105263158,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00011765792823141384,
+      "loss": 1.2746,
+      "step": 426
+    },
+    {
+      "epoch": 1.7978947368421052,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00011732816808371115,
+      "loss": 1.471,
+      "step": 427
+    },
+    {
+      "epoch": 1.8021052631578947,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00011699821355836409,
+      "loss": 1.1071,
+      "step": 428
+    },
+    {
+      "epoch": 1.8063157894736843,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00011666806835661699,
+      "loss": 1.0702,
+      "step": 429
+    },
+    {
+      "epoch": 1.8105263157894735,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00011633773618185302,
+      "loss": 1.2166,
+      "step": 430
+    },
+    {
+      "epoch": 1.8147368421052632,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.00011600722073955282,
+      "loss": 1.1926,
+      "step": 431
+    },
+    {
+      "epoch": 1.8189473684210526,
+      "grad_norm": 0.35546875,
+      "learning_rate": 0.00011567652573725262,
+      "loss": 1.0472,
+      "step": 432
+    },
+    {
+      "epoch": 1.823157894736842,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00011534565488450311,
+      "loss": 0.9258,
+      "step": 433
+    },
+    {
+      "epoch": 1.8273684210526315,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00011501461189282733,
+      "loss": 1.6986,
+      "step": 434
+    },
+    {
+      "epoch": 1.831578947368421,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00011468340047567947,
+      "loss": 1.1726,
+      "step": 435
+    },
+    {
+      "epoch": 1.8357894736842106,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00011435202434840287,
+      "loss": 1.2373,
+      "step": 436
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0001140204872281886,
+      "loss": 0.7262,
+      "step": 437
+    },
+    {
+      "epoch": 1.8442105263157895,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001136887928340336,
+      "loss": 1.0527,
+      "step": 438
+    },
+    {
+      "epoch": 1.848421052631579,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00011335694488669904,
+      "loss": 0.89,
+      "step": 439
+    },
+    {
+      "epoch": 1.8526315789473684,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00011302494710866857,
+      "loss": 1.109,
+      "step": 440
+    },
+    {
+      "epoch": 1.8568421052631578,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.00011269280322410658,
+      "loss": 1.0818,
+      "step": 441
+    },
+    {
+      "epoch": 1.8610526315789473,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.00011236051695881633,
+      "loss": 1.2366,
+      "step": 442
+    },
+    {
+      "epoch": 1.865263157894737,
+      "grad_norm": 0.427734375,
+      "learning_rate": 0.0001120280920401983,
+      "loss": 1.1401,
+      "step": 443
+    },
+    {
+      "epoch": 1.8694736842105262,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00011169553219720828,
+      "loss": 1.0061,
+      "step": 444
+    },
+    {
+      "epoch": 1.8736842105263158,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0001113628411603155,
+      "loss": 1.2742,
+      "step": 445
+    },
+    {
+      "epoch": 1.8778947368421053,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00011103002266146096,
+      "loss": 1.296,
+      "step": 446
+    },
+    {
+      "epoch": 1.8821052631578947,
+      "grad_norm": 0.7578125,
+      "learning_rate": 0.0001106970804340154,
+      "loss": 0.9062,
+      "step": 447
+    },
+    {
+      "epoch": 1.8863157894736842,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.0001103640182127375,
+      "loss": 0.85,
+      "step": 448
+    },
+    {
+      "epoch": 1.8905263157894736,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.00011003083973373187,
+      "loss": 1.0045,
+      "step": 449
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.00010969754873440743,
+      "loss": 0.8616,
+      "step": 450
+    },
+    {
+      "epoch": 1.8989473684210525,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001093641489534351,
+      "loss": 0.9867,
+      "step": 451
+    },
+    {
+      "epoch": 1.9031578947368422,
+      "grad_norm": 0.462890625,
+      "learning_rate": 0.00010903064413070612,
+      "loss": 1.1836,
+      "step": 452
+    },
+    {
+      "epoch": 1.9073684210526316,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00010869703800729,
+      "loss": 0.9996,
+      "step": 453
+    },
+    {
+      "epoch": 1.911578947368421,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00010836333432539272,
+      "loss": 1.4083,
+      "step": 454
+    },
+    {
+      "epoch": 1.9157894736842105,
+      "grad_norm": 0.474609375,
+      "learning_rate": 0.0001080295368283144,
+      "loss": 0.9889,
+      "step": 455
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00010769564926040769,
+      "loss": 0.8322,
+      "step": 456
+    },
+    {
+      "epoch": 1.9242105263157896,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.00010736167536703556,
+      "loss": 0.8793,
+      "step": 457
+    },
+    {
+      "epoch": 1.9284210526315788,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.0001070276188945293,
+      "loss": 1.1383,
+      "step": 458
+    },
+    {
+      "epoch": 1.9326315789473685,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00010669348359014657,
+      "loss": 1.2608,
+      "step": 459
+    },
+    {
+      "epoch": 1.936842105263158,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00010635927320202928,
+      "loss": 1.1444,
+      "step": 460
+    },
+    {
+      "epoch": 1.9410526315789474,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00010602499147916159,
+      "loss": 1.1779,
+      "step": 461
+    },
+    {
+      "epoch": 1.9452631578947368,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00010569064217132791,
+      "loss": 1.2066,
+      "step": 462
+    },
+    {
+      "epoch": 1.9494736842105262,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00010535622902907072,
+      "loss": 1.3065,
+      "step": 463
+    },
+    {
+      "epoch": 1.953684210526316,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00010502175580364857,
+      "loss": 0.9167,
+      "step": 464
+    },
+    {
+      "epoch": 1.9578947368421051,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.00010468722624699401,
+      "loss": 1.059,
+      "step": 465
+    },
+    {
+      "epoch": 1.9621052631578948,
+      "grad_norm": 0.93359375,
+      "learning_rate": 0.00010435264411167148,
+      "loss": 0.8437,
+      "step": 466
+    },
+    {
+      "epoch": 1.9663157894736842,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00010401801315083519,
+      "loss": 1.1105,
+      "step": 467
+    },
+    {
+      "epoch": 1.9705263157894737,
+      "grad_norm": 0.81640625,
+      "learning_rate": 0.0001036833371181871,
+      "loss": 1.5699,
+      "step": 468
+    },
+    {
+      "epoch": 1.9747368421052631,
+      "grad_norm": 0.359375,
+      "learning_rate": 0.00010334861976793465,
+      "loss": 1.0942,
+      "step": 469
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.00010301386485474889,
+      "loss": 0.923,
+      "step": 470
+    },
+    {
+      "epoch": 1.9831578947368422,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00010267907613372217,
+      "loss": 1.123,
+      "step": 471
+    },
+    {
+      "epoch": 1.9873684210526315,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00010234425736032607,
+      "loss": 1.1807,
+      "step": 472
+    },
+    {
+      "epoch": 1.9915789473684211,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00010200941229036926,
+      "loss": 1.2465,
+      "step": 473
+    },
+    {
+      "epoch": 1.9957894736842106,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00010167454467995549,
+      "loss": 0.9394,
+      "step": 474
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 948,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 237,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7894666995302400.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-474/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee017c711219d88132625f3e50d1a67d1c6236a55d3f5a2ad9f499310d968cef
+size 5944

checkpoint-711/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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 0.11.1

checkpoint-711/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-711/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d357a366841f558231ed2389af28f3fe28086fe66e31a267d4f56d9156a9362b
+size 50503848

checkpoint-711/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c973fd01cf5316029454305401c3a156d9fab6260ae3b9a4e66c840802f9f0
+size 202035770

checkpoint-711/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d2e6162181dcdcfe51f923b36befadfc1a6aba4ef5f93190a0edf99f4ab509
+size 14244

checkpoint-711/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da888c03aef9f24d8da0ae60bea1fbcb9a9e606b82616e3a258fa56bd3b1d022
+size 1064

checkpoint-711/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-711/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-711/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-711/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee017c711219d88132625f3e50d1a67d1c6236a55d3f5a2ad9f499310d968cef
+size 5944

checkpoint-948/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+---
+
+# 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 0.11.1

checkpoint-948/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-948/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe388d987f9b4a7486827806ff2dbb1a347a4d34f04b03169d6bf3098290369
+size 50503848

checkpoint-948/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7ccbc0992f3b6ba1f71ee713f8f3fb4b6aba77cdd6bd7bf05522d87c22d4ea
+size 202035770

checkpoint-948/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da40348f8e17b04ef2d2acf88108eb73604897a344bb8f7a0555a7c1e686a3c
+size 14244

checkpoint-948/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c026f009280473e2b93182b16ddf0967c143d42c2c00e0cf6d8a798838077f81
+size 1064

checkpoint-948/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-948/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-948/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-948/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee017c711219d88132625f3e50d1a67d1c6236a55d3f5a2ad9f499310d968cef
+size 5944

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723