Upload folder using huggingface_hub

README.md

@@ -1,3 +1,131 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model-index:
+- name: model-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: `0.4.0`
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model_type: LlamaForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+
+datasets: 
+  - path: burkelibbey/colors 
+    type:  
+      field_instruction: description  
+      field_output: color 
+
+sequence_len: 4096
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 4
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 4
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# model-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.
+
+## 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
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu118
+- 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",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_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:e7e889a3f7644aa3b914bbe531127edf581cc1bd99b2c07e3d796602006c9d8d
+size 101036698

checkpoint-102/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 0.10.0

checkpoint-102/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",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-102/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382f505f20d31935650d8df0ad4e60e4c9a2713eb79d93837be38c3dbcc235ba
+size 100966336

checkpoint-102/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e01dea5290d76a186ee38e327a7f5f33bbd5a5676a7b20859149048adbb766f
+size 50916644

checkpoint-102/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08548b14479e5541cc6c8235da16935d98d5825ecaa016861c7dcef4b231b38
+size 14244

checkpoint-102/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd0147bd27d92932170ad679293259d413fe6b01771e520a26b92e8e8b343ce
+size 1064

checkpoint-102/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-102/tokenizer.model

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

checkpoint-102/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-102/trainer_state.json

@@ -0,0 +1,735 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9563106796116505,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 6.841878890991211,
+      "learning_rate": 2e-05,
+      "loss": 4.5864,
+      "step": 1
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 6.640402793884277,
+      "learning_rate": 4e-05,
+      "loss": 4.6138,
+      "step": 2
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 6.41209077835083,
+      "learning_rate": 6e-05,
+      "loss": 4.6064,
+      "step": 3
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 6.082383632659912,
+      "learning_rate": 8e-05,
+      "loss": 4.5534,
+      "step": 4
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 4.00201416015625,
+      "learning_rate": 0.0001,
+      "loss": 4.3245,
+      "step": 5
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 3.1707470417022705,
+      "learning_rate": 0.00012,
+      "loss": 4.0971,
+      "step": 6
+    },
+    {
+      "epoch": 0.13592233009708737,
+      "grad_norm": 3.160670518875122,
+      "learning_rate": 0.00014,
+      "loss": 3.789,
+      "step": 7
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.994746208190918,
+      "learning_rate": 0.00016,
+      "loss": 3.3244,
+      "step": 8
+    },
+    {
+      "epoch": 0.17475728155339806,
+      "grad_norm": 2.6664786338806152,
+      "learning_rate": 0.00018,
+      "loss": 2.8561,
+      "step": 9
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 2.029910087585449,
+      "learning_rate": 0.0002,
+      "loss": 2.3926,
+      "step": 10
+    },
+    {
+      "epoch": 0.21359223300970873,
+      "grad_norm": 1.3144137859344482,
+      "learning_rate": 0.00019998688836656323,
+      "loss": 2.0283,
+      "step": 11
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.8263471722602844,
+      "learning_rate": 0.00019994755690455152,
+      "loss": 1.8683,
+      "step": 12
+    },
+    {
+      "epoch": 0.2524271844660194,
+      "grad_norm": 0.7193414568901062,
+      "learning_rate": 0.0001998820159279591,
+      "loss": 1.732,
+      "step": 13
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.8350910544395447,
+      "learning_rate": 0.00019979028262377118,
+      "loss": 1.6208,
+      "step": 14
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.6700139045715332,
+      "learning_rate": 0.00019967238104745696,
+      "loss": 1.493,
+      "step": 15
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.1213518381118774,
+      "learning_rate": 0.0001995283421166614,
+      "loss": 1.4857,
+      "step": 16
+    },
+    {
+      "epoch": 0.3300970873786408,
+      "grad_norm": 0.7505896687507629,
+      "learning_rate": 0.00019935820360309777,
+      "loss": 1.4643,
+      "step": 17
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.6984190940856934,
+      "learning_rate": 0.00019916201012264254,
+      "loss": 1.4227,
+      "step": 18
+    },
+    {
+      "epoch": 0.36893203883495146,
+      "grad_norm": 0.46819525957107544,
+      "learning_rate": 0.00019893981312363562,
+      "loss": 1.3889,
+      "step": 19
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5214670300483704,
+      "learning_rate": 0.00019869167087338907,
+      "loss": 1.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.4077669902912621,
+      "grad_norm": 0.43329402804374695,
+      "learning_rate": 0.00019841764844290744,
+      "loss": 1.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6535053253173828,
+      "learning_rate": 0.0001981178176898239,
+      "loss": 1.3576,
+      "step": 22
+    },
+    {
+      "epoch": 0.44660194174757284,
+      "grad_norm": 0.6363189816474915,
+      "learning_rate": 0.00019779225723955707,
+      "loss": 1.3159,
+      "step": 23
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.42140620946884155,
+      "learning_rate": 0.00019744105246469263,
+      "loss": 1.3072,
+      "step": 24
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.6757440567016602,
+      "learning_rate": 0.00019706429546259593,
+      "loss": 1.3261,
+      "step": 25
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.4116632044315338,
+      "learning_rate": 0.00019666208503126112,
+      "loss": 1.317,
+      "step": 26
+    },
+    {
+      "epoch": 0.5242718446601942,
+      "grad_norm": 0.5359898209571838,
+      "learning_rate": 0.00019623452664340306,
+      "loss": 1.2932,
+      "step": 27
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.4596949517726898,
+      "learning_rate": 0.00019578173241879872,
+      "loss": 1.2601,
+      "step": 28
+    },
+    {
+      "epoch": 0.5631067961165048,
+      "grad_norm": 0.6857442855834961,
+      "learning_rate": 0.0001953038210948861,
+      "loss": 1.2734,
+      "step": 29
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.4453957676887512,
+      "learning_rate": 0.00019480091799562704,
+      "loss": 1.2521,
+      "step": 30
+    },
+    {
+      "epoch": 0.6019417475728155,
+      "grad_norm": 0.6118847131729126,
+      "learning_rate": 0.00019427315499864344,
+      "loss": 1.2252,
+      "step": 31
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4894339442253113,
+      "learning_rate": 0.00019372067050063438,
+      "loss": 1.2369,
+      "step": 32
+    },
+    {
+      "epoch": 0.6407766990291263,
+      "grad_norm": 0.5901785492897034,
+      "learning_rate": 0.00019314360938108425,
+      "loss": 1.2507,
+      "step": 33
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4147897958755493,
+      "learning_rate": 0.00019254212296427044,
+      "loss": 1.2454,
+      "step": 34
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.2836126685142517,
+      "learning_rate": 0.00019191636897958122,
+      "loss": 1.2515,
+      "step": 35
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.4523944556713104,
+      "learning_rate": 0.00019126651152015403,
+      "loss": 1.2217,
+      "step": 36
+    },
+    {
+      "epoch": 0.7184466019417476,
+      "grad_norm": 0.4187013804912567,
+      "learning_rate": 0.0001905927209998447,
+      "loss": 1.2382,
+      "step": 37
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.516381561756134,
+      "learning_rate": 0.00018989517410853955,
+      "loss": 1.2214,
+      "step": 38
+    },
+    {
+      "epoch": 0.7572815533980582,
+      "grad_norm": 0.5928078889846802,
+      "learning_rate": 0.00018917405376582145,
+      "loss": 1.2407,
+      "step": 39
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.4062119722366333,
+      "learning_rate": 0.00018842954907300236,
+      "loss": 1.1958,
+      "step": 40
+    },
+    {
+      "epoch": 0.7961165048543689,
+      "grad_norm": 0.5966278910636902,
+      "learning_rate": 0.0001876618552635348,
+      "loss": 1.2043,
+      "step": 41
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.47196483612060547,
+      "learning_rate": 0.00018687117365181512,
+      "loss": 1.2321,
+      "step": 42
+    },
+    {
+      "epoch": 0.8349514563106796,
+      "grad_norm": 0.6465126872062683,
+      "learning_rate": 0.00018605771158039253,
+      "loss": 1.1996,
+      "step": 43
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.4234643578529358,
+      "learning_rate": 0.00018522168236559695,
+      "loss": 1.198,
+      "step": 44
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3910824656486511,
+      "learning_rate": 0.00018436330524160047,
+      "loss": 1.1895,
+      "step": 45
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.5380635261535645,
+      "learning_rate": 0.00018348280530292713,
+      "loss": 1.1693,
+      "step": 46
+    },
+    {
+      "epoch": 0.912621359223301,
+      "grad_norm": 0.31823453307151794,
+      "learning_rate": 0.00018258041344542566,
+      "loss": 1.159,
+      "step": 47
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.5679419636726379,
+      "learning_rate": 0.0001816563663057211,
+      "loss": 1.1931,
+      "step": 48
+    },
+    {
+      "epoch": 0.9514563106796117,
+      "grad_norm": 0.3980861008167267,
+      "learning_rate": 0.00018071090619916093,
+      "loss": 1.1826,
+      "step": 49
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.3688671588897705,
+      "learning_rate": 0.00017974428105627208,
+      "loss": 1.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.9902912621359223,
+      "grad_norm": 0.4137047827243805,
+      "learning_rate": 0.00017875674435774547,
+      "loss": 1.142,
+      "step": 51
+    },
+    {
+      "epoch": 1.0097087378640777,
+      "grad_norm": 0.3141655921936035,
+      "learning_rate": 0.00017774855506796496,
+      "loss": 1.1614,
+      "step": 52
+    },
+    {
+      "epoch": 1.0048543689320388,
+      "grad_norm": 0.3113202154636383,
+      "learning_rate": 0.00017671997756709863,
+      "loss": 1.1668,
+      "step": 53
+    },
+    {
+      "epoch": 1.0242718446601942,
+      "grad_norm": 0.5369274616241455,
+      "learning_rate": 0.00017567128158176953,
+      "loss": 1.1157,
+      "step": 54
+    },
+    {
+      "epoch": 1.0436893203883495,
+      "grad_norm": 0.550740122795105,
+      "learning_rate": 0.0001746027421143246,
+      "loss": 1.1674,
+      "step": 55
+    },
+    {
+      "epoch": 1.0631067961165048,
+      "grad_norm": 0.4507598578929901,
+      "learning_rate": 0.00017351463937072004,
+      "loss": 1.1484,
+      "step": 56
+    },
+    {
+      "epoch": 1.0825242718446602,
+      "grad_norm": 0.5626426935195923,
+      "learning_rate": 0.00017240725868704218,
+      "loss": 1.1614,
+      "step": 57
+    },
+    {
+      "epoch": 1.1019417475728155,
+      "grad_norm": 0.36562928557395935,
+      "learning_rate": 0.00017128089045468294,
+      "loss": 1.1246,
+      "step": 58
+    },
+    {
+      "epoch": 1.1213592233009708,
+      "grad_norm": 0.6106365323066711,
+      "learning_rate": 0.00017013583004418993,
+      "loss": 1.141,
+      "step": 59
+    },
+    {
+      "epoch": 1.1407766990291262,
+      "grad_norm": 0.3751409947872162,
+      "learning_rate": 0.00016897237772781044,
+      "loss": 1.1565,
+      "step": 60
+    },
+    {
+      "epoch": 1.1601941747572815,
+      "grad_norm": 0.5318562984466553,
+      "learning_rate": 0.00016779083860075033,
+      "loss": 1.1501,
+      "step": 61
+    },
+    {
+      "epoch": 1.1796116504854368,
+      "grad_norm": 0.3675023317337036,
+      "learning_rate": 0.00016659152250116812,
+      "loss": 1.1162,
+      "step": 62
+    },
+    {
+      "epoch": 1.1990291262135921,
+      "grad_norm": 0.38894137740135193,
+      "learning_rate": 0.00016537474392892528,
+      "loss": 1.146,
+      "step": 63
+    },
+    {
+      "epoch": 1.2184466019417475,
+      "grad_norm": 0.3107282817363739,
+      "learning_rate": 0.000164140821963114,
+      "loss": 1.135,
+      "step": 64
+    },
+    {
+      "epoch": 1.237864077669903,
+      "grad_norm": 0.2496870756149292,
+      "learning_rate": 0.00016289008017838445,
+      "loss": 1.133,
+      "step": 65
+    },
+    {
+      "epoch": 1.2572815533980584,
+      "grad_norm": 0.35233214497566223,
+      "learning_rate": 0.00016162284656009274,
+      "loss": 1.1446,
+      "step": 66
+    },
+    {
+      "epoch": 1.2766990291262137,
+      "grad_norm": 0.33078905940055847,
+      "learning_rate": 0.00016033945341829248,
+      "loss": 1.1077,
+      "step": 67
+    },
+    {
+      "epoch": 1.296116504854369,
+      "grad_norm": 0.24236944317817688,
+      "learning_rate": 0.00015904023730059228,
+      "loss": 1.1367,
+      "step": 68
+    },
+    {
+      "epoch": 1.3155339805825244,
+      "grad_norm": 0.3248869776725769,
+      "learning_rate": 0.00015772553890390197,
+      "loss": 1.1405,
+      "step": 69
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 0.3145497739315033,
+      "learning_rate": 0.00015639570298509064,
+      "loss": 1.1134,
+      "step": 70
+    },
+    {
+      "epoch": 1.354368932038835,
+      "grad_norm": 0.3858337700366974,
+      "learning_rate": 0.00015505107827058036,
+      "loss": 1.1293,
+      "step": 71
+    },
+    {
+      "epoch": 1.3737864077669903,
+      "grad_norm": 0.3683490753173828,
+      "learning_rate": 0.0001536920173648984,
+      "loss": 1.1069,
+      "step": 72
+    },
+    {
+      "epoch": 1.3932038834951457,
+      "grad_norm": 0.5532976388931274,
+      "learning_rate": 0.000152318876658213,
+      "loss": 1.1432,
+      "step": 73
+    },
+    {
+      "epoch": 1.412621359223301,
+      "grad_norm": 0.3198872208595276,
+      "learning_rate": 0.00015093201623287631,
+      "loss": 1.1423,
+      "step": 74
+    },
+    {
+      "epoch": 1.4320388349514563,
+      "grad_norm": 0.7470155954360962,
+      "learning_rate": 0.00014953179976899878,
+      "loss": 1.1475,
+      "step": 75
+    },
+    {
+      "epoch": 1.4514563106796117,
+      "grad_norm": 0.4092984199523926,
+      "learning_rate": 0.00014811859444908052,
+      "loss": 1.0955,
+      "step": 76
+    },
+    {
+      "epoch": 1.470873786407767,
+      "grad_norm": 0.6536680459976196,
+      "learning_rate": 0.00014669277086172406,
+      "loss": 1.1359,
+      "step": 77
+    },
+    {
+      "epoch": 1.4902912621359223,
+      "grad_norm": 0.35692015290260315,
+      "learning_rate": 0.00014525470290445392,
+      "loss": 1.1131,
+      "step": 78
+    },
+    {
+      "epoch": 1.5097087378640777,
+      "grad_norm": 0.46786415576934814,
+      "learning_rate": 0.00014380476768566824,
+      "loss": 1.1133,
+      "step": 79
+    },
+    {
+      "epoch": 1.529126213592233,
+      "grad_norm": 0.6847173571586609,
+      "learning_rate": 0.00014234334542574906,
+      "loss": 1.125,
+      "step": 80
+    },
+    {
+      "epoch": 1.5485436893203883,
+      "grad_norm": 0.5090566277503967,
+      "learning_rate": 0.00014087081935735564,
+      "loss": 1.1562,
+      "step": 81
+    },
+    {
+      "epoch": 1.5679611650485437,
+      "grad_norm": 0.7293880581855774,
+      "learning_rate": 0.00013938757562492873,
+      "loss": 1.1348,
+      "step": 82
+    },
+    {
+      "epoch": 1.587378640776699,
+      "grad_norm": 0.3536413908004761,
+      "learning_rate": 0.00013789400318343068,
+      "loss": 1.1134,
+      "step": 83
+    },
+    {
+      "epoch": 1.6067961165048543,
+      "grad_norm": 0.802762508392334,
+      "learning_rate": 0.00013639049369634876,
+      "loss": 1.1256,
+      "step": 84
+    },
+    {
+      "epoch": 1.6262135922330097,
+      "grad_norm": 0.27904102206230164,
+      "learning_rate": 0.00013487744143298822,
+      "loss": 1.1367,
+      "step": 85
+    },
+    {
+      "epoch": 1.645631067961165,
+      "grad_norm": 0.6024283170700073,
+      "learning_rate": 0.00013335524316508208,
+      "loss": 1.1174,
+      "step": 86
+    },
+    {
+      "epoch": 1.6650485436893203,
+      "grad_norm": 0.5118915438652039,
+      "learning_rate": 0.0001318242980627444,
+      "loss": 1.0848,
+      "step": 87
+    },
+    {
+      "epoch": 1.6844660194174756,
+      "grad_norm": 0.3924892544746399,
+      "learning_rate": 0.00013028500758979506,
+      "loss": 1.1114,
+      "step": 88
+    },
+    {
+      "epoch": 1.703883495145631,
+      "grad_norm": 0.4876178801059723,
+      "learning_rate": 0.00012873777539848283,
+      "loss": 1.1303,
+      "step": 89
+    },
+    {
+      "epoch": 1.7233009708737863,
+      "grad_norm": 0.4133356809616089,
+      "learning_rate": 0.0001271830072236343,
+      "loss": 1.0894,
+      "step": 90
+    },
+    {
+      "epoch": 1.7427184466019416,
+      "grad_norm": 0.42908573150634766,
+      "learning_rate": 0.00012562111077625722,
+      "loss": 1.0806,
+      "step": 91
+    },
+    {
+      "epoch": 1.762135922330097,
+      "grad_norm": 0.5923053026199341,
+      "learning_rate": 0.00012405249563662537,
+      "loss": 1.1254,
+      "step": 92
+    },
+    {
+      "epoch": 1.7815533980582523,
+      "grad_norm": 0.34368380904197693,
+      "learning_rate": 0.00012247757314687297,
+      "loss": 1.1251,
+      "step": 93
+    },
+    {
+      "epoch": 1.8009708737864076,
+      "grad_norm": 0.6336709856987,
+      "learning_rate": 0.00012089675630312754,
+      "loss": 1.1042,
+      "step": 94
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 0.32966285943984985,
+      "learning_rate": 0.00011931045964720881,
+      "loss": 1.09,
+      "step": 95
+    },
+    {
+      "epoch": 1.8398058252427183,
+      "grad_norm": 0.42973244190216064,
+      "learning_rate": 0.0001177190991579223,
+      "loss": 1.0896,
+      "step": 96
+    },
+    {
+      "epoch": 1.8592233009708736,
+      "grad_norm": 0.5365500450134277,
+      "learning_rate": 0.00011612309214197599,
+      "loss": 1.1281,
+      "step": 97
+    },
+    {
+      "epoch": 1.8786407766990292,
+      "grad_norm": 0.4330235421657562,
+      "learning_rate": 0.00011452285712454904,
+      "loss": 1.087,
+      "step": 98
+    },
+    {
+      "epoch": 1.8980582524271845,
+      "grad_norm": 0.47839391231536865,
+      "learning_rate": 0.00011291881373954065,
+      "loss": 1.0967,
+      "step": 99
+    },
+    {
+      "epoch": 1.9174757281553398,
+      "grad_norm": 0.27464163303375244,
+      "learning_rate": 0.00011131138261952845,
+      "loss": 1.0981,
+      "step": 100
+    },
+    {
+      "epoch": 1.9368932038834952,
+      "grad_norm": 0.41849982738494873,
+      "learning_rate": 0.00010970098528546481,
+      "loss": 1.1203,
+      "step": 101
+    },
+    {
+      "epoch": 1.9563106796116505,
+      "grad_norm": 0.4630599915981293,
+      "learning_rate": 0.00010808804403614043,
+      "loss": 1.1224,
+      "step": 102
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 51,
+  "total_flos": 2.122607373582336e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-102/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5137d02e04a9e9bac65c98c789ae039033678d1581c7bd7d88ddb181436aa56
+size 5816

checkpoint-153/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 0.10.0

checkpoint-153/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",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-153/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07be8a05be42cce036105a2b492dae703c7a69ba8d214593fed8c7aaedf0fa5
+size 100966336

checkpoint-153/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3300246cdafeb2074b14614dbcf76ef6fa7d4bca7229c5e6bbab13ca482a11
+size 50916644

checkpoint-153/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99db079f9484366e7651458e563afb4133c5ec0c2ec99c01fa732d07831dd752
+size 14244

checkpoint-153/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45550cb7e4860b08baa6921121c8c015f08db1f00c8dfffd452c24d43c24a0fc
+size 1064

checkpoint-153/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-153/tokenizer.model

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

checkpoint-153/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-153/trainer_state.json

@@ -0,0 +1,1092 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9223300970873787,
+  "eval_steps": 500,
+  "global_step": 153,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 6.841878890991211,
+      "learning_rate": 2e-05,
+      "loss": 4.5864,
+      "step": 1
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 6.640402793884277,
+      "learning_rate": 4e-05,
+      "loss": 4.6138,
+      "step": 2
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 6.41209077835083,
+      "learning_rate": 6e-05,
+      "loss": 4.6064,
+      "step": 3
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 6.082383632659912,
+      "learning_rate": 8e-05,
+      "loss": 4.5534,
+      "step": 4
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 4.00201416015625,
+      "learning_rate": 0.0001,
+      "loss": 4.3245,
+      "step": 5
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 3.1707470417022705,
+      "learning_rate": 0.00012,
+      "loss": 4.0971,
+      "step": 6
+    },
+    {
+      "epoch": 0.13592233009708737,
+      "grad_norm": 3.160670518875122,
+      "learning_rate": 0.00014,
+      "loss": 3.789,
+      "step": 7
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.994746208190918,
+      "learning_rate": 0.00016,
+      "loss": 3.3244,
+      "step": 8
+    },
+    {
+      "epoch": 0.17475728155339806,
+      "grad_norm": 2.6664786338806152,
+      "learning_rate": 0.00018,
+      "loss": 2.8561,
+      "step": 9
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 2.029910087585449,
+      "learning_rate": 0.0002,
+      "loss": 2.3926,
+      "step": 10
+    },
+    {
+      "epoch": 0.21359223300970873,
+      "grad_norm": 1.3144137859344482,
+      "learning_rate": 0.00019998688836656323,
+      "loss": 2.0283,
+      "step": 11
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.8263471722602844,
+      "learning_rate": 0.00019994755690455152,
+      "loss": 1.8683,
+      "step": 12
+    },
+    {
+      "epoch": 0.2524271844660194,
+      "grad_norm": 0.7193414568901062,
+      "learning_rate": 0.0001998820159279591,
+      "loss": 1.732,
+      "step": 13
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.8350910544395447,
+      "learning_rate": 0.00019979028262377118,
+      "loss": 1.6208,
+      "step": 14
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.6700139045715332,
+      "learning_rate": 0.00019967238104745696,
+      "loss": 1.493,
+      "step": 15
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.1213518381118774,
+      "learning_rate": 0.0001995283421166614,
+      "loss": 1.4857,
+      "step": 16
+    },
+    {
+      "epoch": 0.3300970873786408,
+      "grad_norm": 0.7505896687507629,
+      "learning_rate": 0.00019935820360309777,
+      "loss": 1.4643,
+      "step": 17
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.6984190940856934,
+      "learning_rate": 0.00019916201012264254,
+      "loss": 1.4227,
+      "step": 18
+    },
+    {
+      "epoch": 0.36893203883495146,
+      "grad_norm": 0.46819525957107544,
+      "learning_rate": 0.00019893981312363562,
+      "loss": 1.3889,
+      "step": 19
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5214670300483704,
+      "learning_rate": 0.00019869167087338907,
+      "loss": 1.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.4077669902912621,
+      "grad_norm": 0.43329402804374695,
+      "learning_rate": 0.00019841764844290744,
+      "loss": 1.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6535053253173828,
+      "learning_rate": 0.0001981178176898239,
+      "loss": 1.3576,
+      "step": 22
+    },
+    {
+      "epoch": 0.44660194174757284,
+      "grad_norm": 0.6363189816474915,
+      "learning_rate": 0.00019779225723955707,
+      "loss": 1.3159,
+      "step": 23
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.42140620946884155,
+      "learning_rate": 0.00019744105246469263,
+      "loss": 1.3072,
+      "step": 24
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.6757440567016602,
+      "learning_rate": 0.00019706429546259593,
+      "loss": 1.3261,
+      "step": 25
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.4116632044315338,
+      "learning_rate": 0.00019666208503126112,
+      "loss": 1.317,
+      "step": 26
+    },
+    {
+      "epoch": 0.5242718446601942,
+      "grad_norm": 0.5359898209571838,
+      "learning_rate": 0.00019623452664340306,
+      "loss": 1.2932,
+      "step": 27
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.4596949517726898,
+      "learning_rate": 0.00019578173241879872,
+      "loss": 1.2601,
+      "step": 28
+    },
+    {
+      "epoch": 0.5631067961165048,
+      "grad_norm": 0.6857442855834961,
+      "learning_rate": 0.0001953038210948861,
+      "loss": 1.2734,
+      "step": 29
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.4453957676887512,
+      "learning_rate": 0.00019480091799562704,
+      "loss": 1.2521,
+      "step": 30
+    },
+    {
+      "epoch": 0.6019417475728155,
+      "grad_norm": 0.6118847131729126,
+      "learning_rate": 0.00019427315499864344,
+      "loss": 1.2252,
+      "step": 31
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4894339442253113,
+      "learning_rate": 0.00019372067050063438,
+      "loss": 1.2369,
+      "step": 32
+    },
+    {
+      "epoch": 0.6407766990291263,
+      "grad_norm": 0.5901785492897034,
+      "learning_rate": 0.00019314360938108425,
+      "loss": 1.2507,
+      "step": 33
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4147897958755493,
+      "learning_rate": 0.00019254212296427044,
+      "loss": 1.2454,
+      "step": 34
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.2836126685142517,
+      "learning_rate": 0.00019191636897958122,
+      "loss": 1.2515,
+      "step": 35
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.4523944556713104,
+      "learning_rate": 0.00019126651152015403,
+      "loss": 1.2217,
+      "step": 36
+    },
+    {
+      "epoch": 0.7184466019417476,
+      "grad_norm": 0.4187013804912567,
+      "learning_rate": 0.0001905927209998447,
+      "loss": 1.2382,
+      "step": 37
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.516381561756134,
+      "learning_rate": 0.00018989517410853955,
+      "loss": 1.2214,
+      "step": 38
+    },
+    {
+      "epoch": 0.7572815533980582,
+      "grad_norm": 0.5928078889846802,
+      "learning_rate": 0.00018917405376582145,
+      "loss": 1.2407,
+      "step": 39
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.4062119722366333,
+      "learning_rate": 0.00018842954907300236,
+      "loss": 1.1958,
+      "step": 40
+    },
+    {
+      "epoch": 0.7961165048543689,
+      "grad_norm": 0.5966278910636902,
+      "learning_rate": 0.0001876618552635348,
+      "loss": 1.2043,
+      "step": 41
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.47196483612060547,
+      "learning_rate": 0.00018687117365181512,
+      "loss": 1.2321,
+      "step": 42
+    },
+    {
+      "epoch": 0.8349514563106796,
+      "grad_norm": 0.6465126872062683,
+      "learning_rate": 0.00018605771158039253,
+      "loss": 1.1996,
+      "step": 43
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.4234643578529358,
+      "learning_rate": 0.00018522168236559695,
+      "loss": 1.198,
+      "step": 44
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3910824656486511,
+      "learning_rate": 0.00018436330524160047,
+      "loss": 1.1895,
+      "step": 45
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.5380635261535645,
+      "learning_rate": 0.00018348280530292713,
+      "loss": 1.1693,
+      "step": 46
+    },
+    {
+      "epoch": 0.912621359223301,
+      "grad_norm": 0.31823453307151794,
+      "learning_rate": 0.00018258041344542566,
+      "loss": 1.159,
+      "step": 47
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.5679419636726379,
+      "learning_rate": 0.0001816563663057211,
+      "loss": 1.1931,
+      "step": 48
+    },
+    {
+      "epoch": 0.9514563106796117,
+      "grad_norm": 0.3980861008167267,
+      "learning_rate": 0.00018071090619916093,
+      "loss": 1.1826,
+      "step": 49
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.3688671588897705,
+      "learning_rate": 0.00017974428105627208,
+      "loss": 1.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.9902912621359223,
+      "grad_norm": 0.4137047827243805,
+      "learning_rate": 0.00017875674435774547,
+      "loss": 1.142,
+      "step": 51
+    },
+    {
+      "epoch": 1.0097087378640777,
+      "grad_norm": 0.3141655921936035,
+      "learning_rate": 0.00017774855506796496,
+      "loss": 1.1614,
+      "step": 52
+    },
+    {
+      "epoch": 1.0048543689320388,
+      "grad_norm": 0.3113202154636383,
+      "learning_rate": 0.00017671997756709863,
+      "loss": 1.1668,
+      "step": 53
+    },
+    {
+      "epoch": 1.0242718446601942,
+      "grad_norm": 0.5369274616241455,
+      "learning_rate": 0.00017567128158176953,
+      "loss": 1.1157,
+      "step": 54
+    },
+    {
+      "epoch": 1.0436893203883495,
+      "grad_norm": 0.550740122795105,
+      "learning_rate": 0.0001746027421143246,
+      "loss": 1.1674,
+      "step": 55
+    },
+    {
+      "epoch": 1.0631067961165048,
+      "grad_norm": 0.4507598578929901,
+      "learning_rate": 0.00017351463937072004,
+      "loss": 1.1484,
+      "step": 56
+    },
+    {
+      "epoch": 1.0825242718446602,
+      "grad_norm": 0.5626426935195923,
+      "learning_rate": 0.00017240725868704218,
+      "loss": 1.1614,
+      "step": 57
+    },
+    {
+      "epoch": 1.1019417475728155,
+      "grad_norm": 0.36562928557395935,
+      "learning_rate": 0.00017128089045468294,
+      "loss": 1.1246,
+      "step": 58
+    },
+    {
+      "epoch": 1.1213592233009708,
+      "grad_norm": 0.6106365323066711,
+      "learning_rate": 0.00017013583004418993,
+      "loss": 1.141,
+      "step": 59
+    },
+    {
+      "epoch": 1.1407766990291262,
+      "grad_norm": 0.3751409947872162,
+      "learning_rate": 0.00016897237772781044,
+      "loss": 1.1565,
+      "step": 60
+    },
+    {
+      "epoch": 1.1601941747572815,
+      "grad_norm": 0.5318562984466553,
+      "learning_rate": 0.00016779083860075033,
+      "loss": 1.1501,
+      "step": 61
+    },
+    {
+      "epoch": 1.1796116504854368,
+      "grad_norm": 0.3675023317337036,
+      "learning_rate": 0.00016659152250116812,
+      "loss": 1.1162,
+      "step": 62
+    },
+    {
+      "epoch": 1.1990291262135921,
+      "grad_norm": 0.38894137740135193,
+      "learning_rate": 0.00016537474392892528,
+      "loss": 1.146,
+      "step": 63
+    },
+    {
+      "epoch": 1.2184466019417475,
+      "grad_norm": 0.3107282817363739,
+      "learning_rate": 0.000164140821963114,
+      "loss": 1.135,
+      "step": 64
+    },
+    {
+      "epoch": 1.237864077669903,
+      "grad_norm": 0.2496870756149292,
+      "learning_rate": 0.00016289008017838445,
+      "loss": 1.133,
+      "step": 65
+    },
+    {
+      "epoch": 1.2572815533980584,
+      "grad_norm": 0.35233214497566223,
+      "learning_rate": 0.00016162284656009274,
+      "loss": 1.1446,
+      "step": 66
+    },
+    {
+      "epoch": 1.2766990291262137,
+      "grad_norm": 0.33078905940055847,
+      "learning_rate": 0.00016033945341829248,
+      "loss": 1.1077,
+      "step": 67
+    },
+    {
+      "epoch": 1.296116504854369,
+      "grad_norm": 0.24236944317817688,
+      "learning_rate": 0.00015904023730059228,
+      "loss": 1.1367,
+      "step": 68
+    },
+    {
+      "epoch": 1.3155339805825244,
+      "grad_norm": 0.3248869776725769,
+      "learning_rate": 0.00015772553890390197,
+      "loss": 1.1405,
+      "step": 69
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 0.3145497739315033,
+      "learning_rate": 0.00015639570298509064,
+      "loss": 1.1134,
+      "step": 70
+    },
+    {
+      "epoch": 1.354368932038835,
+      "grad_norm": 0.3858337700366974,
+      "learning_rate": 0.00015505107827058036,
+      "loss": 1.1293,
+      "step": 71
+    },
+    {
+      "epoch": 1.3737864077669903,
+      "grad_norm": 0.3683490753173828,
+      "learning_rate": 0.0001536920173648984,
+      "loss": 1.1069,
+      "step": 72
+    },
+    {
+      "epoch": 1.3932038834951457,
+      "grad_norm": 0.5532976388931274,
+      "learning_rate": 0.000152318876658213,
+      "loss": 1.1432,
+      "step": 73
+    },
+    {
+      "epoch": 1.412621359223301,
+      "grad_norm": 0.3198872208595276,
+      "learning_rate": 0.00015093201623287631,
+      "loss": 1.1423,
+      "step": 74
+    },
+    {
+      "epoch": 1.4320388349514563,
+      "grad_norm": 0.7470155954360962,
+      "learning_rate": 0.00014953179976899878,
+      "loss": 1.1475,
+      "step": 75
+    },
+    {
+      "epoch": 1.4514563106796117,
+      "grad_norm": 0.4092984199523926,
+      "learning_rate": 0.00014811859444908052,
+      "loss": 1.0955,
+      "step": 76
+    },
+    {
+      "epoch": 1.470873786407767,
+      "grad_norm": 0.6536680459976196,
+      "learning_rate": 0.00014669277086172406,
+      "loss": 1.1359,
+      "step": 77
+    },
+    {
+      "epoch": 1.4902912621359223,
+      "grad_norm": 0.35692015290260315,
+      "learning_rate": 0.00014525470290445392,
+      "loss": 1.1131,
+      "step": 78
+    },
+    {
+      "epoch": 1.5097087378640777,
+      "grad_norm": 0.46786415576934814,
+      "learning_rate": 0.00014380476768566824,
+      "loss": 1.1133,
+      "step": 79
+    },
+    {
+      "epoch": 1.529126213592233,
+      "grad_norm": 0.6847173571586609,
+      "learning_rate": 0.00014234334542574906,
+      "loss": 1.125,
+      "step": 80
+    },
+    {
+      "epoch": 1.5485436893203883,
+      "grad_norm": 0.5090566277503967,
+      "learning_rate": 0.00014087081935735564,
+      "loss": 1.1562,
+      "step": 81
+    },
+    {
+      "epoch": 1.5679611650485437,
+      "grad_norm": 0.7293880581855774,
+      "learning_rate": 0.00013938757562492873,
+      "loss": 1.1348,
+      "step": 82
+    },
+    {
+      "epoch": 1.587378640776699,
+      "grad_norm": 0.3536413908004761,
+      "learning_rate": 0.00013789400318343068,
+      "loss": 1.1134,
+      "step": 83
+    },
+    {
+      "epoch": 1.6067961165048543,
+      "grad_norm": 0.802762508392334,
+      "learning_rate": 0.00013639049369634876,
+      "loss": 1.1256,
+      "step": 84
+    },
+    {
+      "epoch": 1.6262135922330097,
+      "grad_norm": 0.27904102206230164,
+      "learning_rate": 0.00013487744143298822,
+      "loss": 1.1367,
+      "step": 85
+    },
+    {
+      "epoch": 1.645631067961165,
+      "grad_norm": 0.6024283170700073,
+      "learning_rate": 0.00013335524316508208,
+      "loss": 1.1174,
+      "step": 86
+    },
+    {
+      "epoch": 1.6650485436893203,
+      "grad_norm": 0.5118915438652039,
+      "learning_rate": 0.0001318242980627444,
+      "loss": 1.0848,
+      "step": 87
+    },
+    {
+      "epoch": 1.6844660194174756,
+      "grad_norm": 0.3924892544746399,
+      "learning_rate": 0.00013028500758979506,
+      "loss": 1.1114,
+      "step": 88
+    },
+    {
+      "epoch": 1.703883495145631,
+      "grad_norm": 0.4876178801059723,
+      "learning_rate": 0.00012873777539848283,
+      "loss": 1.1303,
+      "step": 89
+    },
+    {
+      "epoch": 1.7233009708737863,
+      "grad_norm": 0.4133356809616089,
+      "learning_rate": 0.0001271830072236343,
+      "loss": 1.0894,
+      "step": 90
+    },
+    {
+      "epoch": 1.7427184466019416,
+      "grad_norm": 0.42908573150634766,
+      "learning_rate": 0.00012562111077625722,
+      "loss": 1.0806,
+      "step": 91
+    },
+    {
+      "epoch": 1.762135922330097,
+      "grad_norm": 0.5923053026199341,
+      "learning_rate": 0.00012405249563662537,
+      "loss": 1.1254,
+      "step": 92
+    },
+    {
+      "epoch": 1.7815533980582523,
+      "grad_norm": 0.34368380904197693,
+      "learning_rate": 0.00012247757314687297,
+      "loss": 1.1251,
+      "step": 93
+    },
+    {
+      "epoch": 1.8009708737864076,
+      "grad_norm": 0.6336709856987,
+      "learning_rate": 0.00012089675630312754,
+      "loss": 1.1042,
+      "step": 94
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 0.32966285943984985,
+      "learning_rate": 0.00011931045964720881,
+      "loss": 1.09,
+      "step": 95
+    },
+    {
+      "epoch": 1.8398058252427183,
+      "grad_norm": 0.42973244190216064,
+      "learning_rate": 0.0001177190991579223,
+      "loss": 1.0896,
+      "step": 96
+    },
+    {
+      "epoch": 1.8592233009708736,
+      "grad_norm": 0.5365500450134277,
+      "learning_rate": 0.00011612309214197599,
+      "loss": 1.1281,
+      "step": 97
+    },
+    {
+      "epoch": 1.8786407766990292,
+      "grad_norm": 0.4330235421657562,
+      "learning_rate": 0.00011452285712454904,
+      "loss": 1.087,
+      "step": 98
+    },
+    {
+      "epoch": 1.8980582524271845,
+      "grad_norm": 0.47839391231536865,
+      "learning_rate": 0.00011291881373954065,
+      "loss": 1.0967,
+      "step": 99
+    },
+    {
+      "epoch": 1.9174757281553398,
+      "grad_norm": 0.27464163303375244,
+      "learning_rate": 0.00011131138261952845,
+      "loss": 1.0981,
+      "step": 100
+    },
+    {
+      "epoch": 1.9368932038834952,
+      "grad_norm": 0.41849982738494873,
+      "learning_rate": 0.00010970098528546481,
+      "loss": 1.1203,
+      "step": 101
+    },
+    {
+      "epoch": 1.9563106796116505,
+      "grad_norm": 0.4630599915981293,
+      "learning_rate": 0.00010808804403614043,
+      "loss": 1.1224,
+      "step": 102
+    },
+    {
+      "epoch": 1.9757281553398058,
+      "grad_norm": 0.34116509556770325,
+      "learning_rate": 0.00010647298183744359,
+      "loss": 1.0871,
+      "step": 103
+    },
+    {
+      "epoch": 1.9951456310679612,
+      "grad_norm": 0.4391232430934906,
+      "learning_rate": 0.00010485622221144484,
+      "loss": 1.1331,
+      "step": 104
+    },
+    {
+      "epoch": 2.0145631067961167,
+      "grad_norm": 0.4344836175441742,
+      "learning_rate": 0.00010323818912533561,
+      "loss": 1.0874,
+      "step": 105
+    },
+    {
+      "epoch": 2.0097087378640777,
+      "grad_norm": 0.42520374059677124,
+      "learning_rate": 0.00010161930688025017,
+      "loss": 1.1068,
+      "step": 106
+    },
+    {
+      "epoch": 2.029126213592233,
+      "grad_norm": 0.3572416305541992,
+      "learning_rate": 0.0001,
+      "loss": 1.1001,
+      "step": 107
+    },
+    {
+      "epoch": 2.0485436893203883,
+      "grad_norm": 0.38590529561042786,
+      "learning_rate": 9.838069311974986e-05,
+      "loss": 1.0833,
+      "step": 108
+    },
+    {
+      "epoch": 2.0679611650485437,
+      "grad_norm": 0.2969411313533783,
+      "learning_rate": 9.676181087466444e-05,
+      "loss": 1.0939,
+      "step": 109
+    },
+    {
+      "epoch": 2.087378640776699,
+      "grad_norm": 0.25997498631477356,
+      "learning_rate": 9.514377778855521e-05,
+      "loss": 1.1063,
+      "step": 110
+    },
+    {
+      "epoch": 2.1067961165048543,
+      "grad_norm": 0.3671320676803589,
+      "learning_rate": 9.352701816255643e-05,
+      "loss": 1.103,
+      "step": 111
+    },
+    {
+      "epoch": 2.1262135922330097,
+      "grad_norm": 0.552992582321167,
+      "learning_rate": 9.19119559638596e-05,
+      "loss": 1.0874,
+      "step": 112
+    },
+    {
+      "epoch": 2.145631067961165,
+      "grad_norm": 0.25193411111831665,
+      "learning_rate": 9.02990147145352e-05,
+      "loss": 1.0946,
+      "step": 113
+    },
+    {
+      "epoch": 2.1650485436893203,
+      "grad_norm": 0.33370667695999146,
+      "learning_rate": 8.868861738047158e-05,
+      "loss": 1.1108,
+      "step": 114
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 0.42085111141204834,
+      "learning_rate": 8.70811862604594e-05,
+      "loss": 1.0883,
+      "step": 115
+    },
+    {
+      "epoch": 2.203883495145631,
+      "grad_norm": 0.40206724405288696,
+      "learning_rate": 8.5477142875451e-05,
+      "loss": 1.1006,
+      "step": 116
+    },
+    {
+      "epoch": 2.2233009708737863,
+      "grad_norm": 0.3052491247653961,
+      "learning_rate": 8.387690785802402e-05,
+      "loss": 1.1155,
+      "step": 117
+    },
+    {
+      "epoch": 2.2427184466019416,
+      "grad_norm": 0.42322033643722534,
+      "learning_rate": 8.228090084207774e-05,
+      "loss": 1.0929,
+      "step": 118
+    },
+    {
+      "epoch": 2.262135922330097,
+      "grad_norm": 0.5083087682723999,
+      "learning_rate": 8.068954035279121e-05,
+      "loss": 1.122,
+      "step": 119
+    },
+    {
+      "epoch": 2.2815533980582523,
+      "grad_norm": 0.2693060636520386,
+      "learning_rate": 7.91032436968725e-05,
+      "loss": 1.0837,
+      "step": 120
+    },
+    {
+      "epoch": 2.3009708737864076,
+      "grad_norm": 0.34834596514701843,
+      "learning_rate": 7.75224268531271e-05,
+      "loss": 1.0768,
+      "step": 121
+    },
+    {
+      "epoch": 2.320388349514563,
+      "grad_norm": 0.3885416090488434,
+      "learning_rate": 7.594750436337467e-05,
+      "loss": 1.0616,
+      "step": 122
+    },
+    {
+      "epoch": 2.3398058252427183,
+      "grad_norm": 0.3093293011188507,
+      "learning_rate": 7.437888922374276e-05,
+      "loss": 1.0799,
+      "step": 123
+    },
+    {
+      "epoch": 2.3592233009708736,
+      "grad_norm": 0.4098259210586548,
+      "learning_rate": 7.281699277636572e-05,
+      "loss": 1.1184,
+      "step": 124
+    },
+    {
+      "epoch": 2.378640776699029,
+      "grad_norm": 0.29187697172164917,
+      "learning_rate": 7.126222460151719e-05,
+      "loss": 1.0883,
+      "step": 125
+    },
+    {
+      "epoch": 2.3980582524271843,
+      "grad_norm": 0.3151191174983978,
+      "learning_rate": 6.971499241020495e-05,
+      "loss": 1.0692,
+      "step": 126
+    },
+    {
+      "epoch": 2.4174757281553396,
+      "grad_norm": 0.3117734491825104,
+      "learning_rate": 6.817570193725564e-05,
+      "loss": 1.0926,
+      "step": 127
+    },
+    {
+      "epoch": 2.436893203883495,
+      "grad_norm": 0.25921401381492615,
+      "learning_rate": 6.664475683491796e-05,
+      "loss": 1.0707,
+      "step": 128
+    },
+    {
+      "epoch": 2.4563106796116507,
+      "grad_norm": 0.31505605578422546,
+      "learning_rate": 6.512255856701177e-05,
+      "loss": 1.0988,
+      "step": 129
+    },
+    {
+      "epoch": 2.475728155339806,
+      "grad_norm": 0.25132912397384644,
+      "learning_rate": 6.360950630365126e-05,
+      "loss": 1.0726,
+      "step": 130
+    },
+    {
+      "epoch": 2.4951456310679614,
+      "grad_norm": 0.2596098780632019,
+      "learning_rate": 6.210599681656933e-05,
+      "loss": 1.1138,
+      "step": 131
+    },
+    {
+      "epoch": 2.5145631067961167,
+      "grad_norm": 0.24262911081314087,
+      "learning_rate": 6.061242437507131e-05,
+      "loss": 1.0759,
+      "step": 132
+    },
+    {
+      "epoch": 2.533980582524272,
+      "grad_norm": 0.29739508032798767,
+      "learning_rate": 5.9129180642644414e-05,
+      "loss": 1.082,
+      "step": 133
+    },
+    {
+      "epoch": 2.5533980582524274,
+      "grad_norm": 0.32182446122169495,
+      "learning_rate": 5.765665457425102e-05,
+      "loss": 1.0698,
+      "step": 134
+    },
+    {
+      "epoch": 2.5728155339805827,
+      "grad_norm": 0.3175111711025238,
+      "learning_rate": 5.6195232314331766e-05,
+      "loss": 1.099,
+      "step": 135
+    },
+    {
+      "epoch": 2.592233009708738,
+      "grad_norm": 0.34597843885421753,
+      "learning_rate": 5.474529709554612e-05,
+      "loss": 1.0971,
+      "step": 136
+    },
+    {
+      "epoch": 2.6116504854368934,
+      "grad_norm": 0.2773433327674866,
+      "learning_rate": 5.3307229138275936e-05,
+      "loss": 1.0747,
+      "step": 137
+    },
+    {
+      "epoch": 2.6310679611650487,
+      "grad_norm": 0.3997284770011902,
+      "learning_rate": 5.1881405550919493e-05,
+      "loss": 1.0579,
+      "step": 138
+    },
+    {
+      "epoch": 2.650485436893204,
+      "grad_norm": 0.3829750716686249,
+      "learning_rate": 5.0468200231001286e-05,
+      "loss": 1.0671,
+      "step": 139
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 0.2364608198404312,
+      "learning_rate": 4.9067983767123736e-05,
+      "loss": 1.0739,
+      "step": 140
+    },
+    {
+      "epoch": 2.6893203883495147,
+      "grad_norm": 0.29015663266181946,
+      "learning_rate": 4.768112334178699e-05,
+      "loss": 1.0626,
+      "step": 141
+    },
+    {
+      "epoch": 2.70873786407767,
+      "grad_norm": 0.39254897832870483,
+      "learning_rate": 4.630798263510162e-05,
+      "loss": 1.0648,
+      "step": 142
+    },
+    {
+      "epoch": 2.7281553398058254,
+      "grad_norm": 0.42674142122268677,
+      "learning_rate": 4.494892172941965e-05,
+      "loss": 1.1137,
+      "step": 143
+    },
+    {
+      "epoch": 2.7475728155339807,
+      "grad_norm": 0.4450013041496277,
+      "learning_rate": 4.360429701490934e-05,
+      "loss": 1.1096,
+      "step": 144
+    },
+    {
+      "epoch": 2.766990291262136,
+      "grad_norm": 0.333667516708374,
+      "learning_rate": 4.227446109609809e-05,
+      "loss": 1.0758,
+      "step": 145
+    },
+    {
+      "epoch": 2.7864077669902914,
+      "grad_norm": 0.4920090436935425,
+      "learning_rate": 4.0959762699407766e-05,
+      "loss": 1.0698,
+      "step": 146
+    },
+    {
+      "epoch": 2.8058252427184467,
+      "grad_norm": 0.31687042117118835,
+      "learning_rate": 3.966054658170754e-05,
+      "loss": 1.0901,
+      "step": 147
+    },
+    {
+      "epoch": 2.825242718446602,
+      "grad_norm": 0.3884165585041046,
+      "learning_rate": 3.8377153439907266e-05,
+      "loss": 1.0753,
+      "step": 148
+    },
+    {
+      "epoch": 2.8446601941747574,
+      "grad_norm": 0.41056135296821594,
+      "learning_rate": 3.710991982161555e-05,
+      "loss": 1.1145,
+      "step": 149
+    },
+    {
+      "epoch": 2.8640776699029127,
+      "grad_norm": 0.32460349798202515,
+      "learning_rate": 3.585917803688603e-05,
+      "loss": 1.0716,
+      "step": 150
+    },
+    {
+      "epoch": 2.883495145631068,
+      "grad_norm": 0.3436354994773865,
+      "learning_rate": 3.4625256071074773e-05,
+      "loss": 1.0995,
+      "step": 151
+    },
+    {
+      "epoch": 2.9029126213592233,
+      "grad_norm": 0.29039478302001953,
+      "learning_rate": 3.340847749883191e-05,
+      "loss": 1.058,
+      "step": 152
+    },
+    {
+      "epoch": 2.9223300970873787,
+      "grad_norm": 0.2641606330871582,
+      "learning_rate": 3.2209161399249674e-05,
+      "loss": 1.0705,
+      "step": 153
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 51,
+  "total_flos": 3.182608847260877e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-153/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5137d02e04a9e9bac65c98c789ae039033678d1581c7bd7d88ddb181436aa56
+size 5816

checkpoint-204/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 0.10.0

checkpoint-204/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",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-204/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1818d92e227b78a4a8293d5066c8c9807353aedab7b4abeaf3002ecd014de713
+size 100966336

checkpoint-204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e82e3dbdec46891523e379c84248451f5dde88a32e8cf0fc92b9753b76571b4
+size 50916644

checkpoint-204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fe480ac13f8022b76fbc5cc6956619acdfb8de57acaa1824e71f8913646416
+size 14244

checkpoint-204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a406cab4a7a12737eda7c59d60db0c008bffa82de17f2878810f2d4cedd3d1ef
+size 1064

checkpoint-204/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-204/tokenizer.model

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

checkpoint-204/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-204/trainer_state.json

@@ -0,0 +1,1449 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.8883495145631066,
+  "eval_steps": 500,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 6.841878890991211,
+      "learning_rate": 2e-05,
+      "loss": 4.5864,
+      "step": 1
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 6.640402793884277,
+      "learning_rate": 4e-05,
+      "loss": 4.6138,
+      "step": 2
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 6.41209077835083,
+      "learning_rate": 6e-05,
+      "loss": 4.6064,
+      "step": 3
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 6.082383632659912,
+      "learning_rate": 8e-05,
+      "loss": 4.5534,
+      "step": 4
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 4.00201416015625,
+      "learning_rate": 0.0001,
+      "loss": 4.3245,
+      "step": 5
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 3.1707470417022705,
+      "learning_rate": 0.00012,
+      "loss": 4.0971,
+      "step": 6
+    },
+    {
+      "epoch": 0.13592233009708737,
+      "grad_norm": 3.160670518875122,
+      "learning_rate": 0.00014,
+      "loss": 3.789,
+      "step": 7
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.994746208190918,
+      "learning_rate": 0.00016,
+      "loss": 3.3244,
+      "step": 8
+    },
+    {
+      "epoch": 0.17475728155339806,
+      "grad_norm": 2.6664786338806152,
+      "learning_rate": 0.00018,
+      "loss": 2.8561,
+      "step": 9
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 2.029910087585449,
+      "learning_rate": 0.0002,
+      "loss": 2.3926,
+      "step": 10
+    },
+    {
+      "epoch": 0.21359223300970873,
+      "grad_norm": 1.3144137859344482,
+      "learning_rate": 0.00019998688836656323,
+      "loss": 2.0283,
+      "step": 11
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.8263471722602844,
+      "learning_rate": 0.00019994755690455152,
+      "loss": 1.8683,
+      "step": 12
+    },
+    {
+      "epoch": 0.2524271844660194,
+      "grad_norm": 0.7193414568901062,
+      "learning_rate": 0.0001998820159279591,
+      "loss": 1.732,
+      "step": 13
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.8350910544395447,
+      "learning_rate": 0.00019979028262377118,
+      "loss": 1.6208,
+      "step": 14
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.6700139045715332,
+      "learning_rate": 0.00019967238104745696,
+      "loss": 1.493,
+      "step": 15
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.1213518381118774,
+      "learning_rate": 0.0001995283421166614,
+      "loss": 1.4857,
+      "step": 16
+    },
+    {
+      "epoch": 0.3300970873786408,
+      "grad_norm": 0.7505896687507629,
+      "learning_rate": 0.00019935820360309777,
+      "loss": 1.4643,
+      "step": 17
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.6984190940856934,
+      "learning_rate": 0.00019916201012264254,
+      "loss": 1.4227,
+      "step": 18
+    },
+    {
+      "epoch": 0.36893203883495146,
+      "grad_norm": 0.46819525957107544,
+      "learning_rate": 0.00019893981312363562,
+      "loss": 1.3889,
+      "step": 19
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5214670300483704,
+      "learning_rate": 0.00019869167087338907,
+      "loss": 1.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.4077669902912621,
+      "grad_norm": 0.43329402804374695,
+      "learning_rate": 0.00019841764844290744,
+      "loss": 1.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6535053253173828,
+      "learning_rate": 0.0001981178176898239,
+      "loss": 1.3576,
+      "step": 22
+    },
+    {
+      "epoch": 0.44660194174757284,
+      "grad_norm": 0.6363189816474915,
+      "learning_rate": 0.00019779225723955707,
+      "loss": 1.3159,
+      "step": 23
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.42140620946884155,
+      "learning_rate": 0.00019744105246469263,
+      "loss": 1.3072,
+      "step": 24
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.6757440567016602,
+      "learning_rate": 0.00019706429546259593,
+      "loss": 1.3261,
+      "step": 25
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.4116632044315338,
+      "learning_rate": 0.00019666208503126112,
+      "loss": 1.317,
+      "step": 26
+    },
+    {
+      "epoch": 0.5242718446601942,
+      "grad_norm": 0.5359898209571838,
+      "learning_rate": 0.00019623452664340306,
+      "loss": 1.2932,
+      "step": 27
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.4596949517726898,
+      "learning_rate": 0.00019578173241879872,
+      "loss": 1.2601,
+      "step": 28
+    },
+    {
+      "epoch": 0.5631067961165048,
+      "grad_norm": 0.6857442855834961,
+      "learning_rate": 0.0001953038210948861,
+      "loss": 1.2734,
+      "step": 29
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.4453957676887512,
+      "learning_rate": 0.00019480091799562704,
+      "loss": 1.2521,
+      "step": 30
+    },
+    {
+      "epoch": 0.6019417475728155,
+      "grad_norm": 0.6118847131729126,
+      "learning_rate": 0.00019427315499864344,
+      "loss": 1.2252,
+      "step": 31
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4894339442253113,
+      "learning_rate": 0.00019372067050063438,
+      "loss": 1.2369,
+      "step": 32
+    },
+    {
+      "epoch": 0.6407766990291263,
+      "grad_norm": 0.5901785492897034,
+      "learning_rate": 0.00019314360938108425,
+      "loss": 1.2507,
+      "step": 33
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4147897958755493,
+      "learning_rate": 0.00019254212296427044,
+      "loss": 1.2454,
+      "step": 34
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.2836126685142517,
+      "learning_rate": 0.00019191636897958122,
+      "loss": 1.2515,
+      "step": 35
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.4523944556713104,
+      "learning_rate": 0.00019126651152015403,
+      "loss": 1.2217,
+      "step": 36
+    },
+    {
+      "epoch": 0.7184466019417476,
+      "grad_norm": 0.4187013804912567,
+      "learning_rate": 0.0001905927209998447,
+      "loss": 1.2382,
+      "step": 37
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.516381561756134,
+      "learning_rate": 0.00018989517410853955,
+      "loss": 1.2214,
+      "step": 38
+    },
+    {
+      "epoch": 0.7572815533980582,
+      "grad_norm": 0.5928078889846802,
+      "learning_rate": 0.00018917405376582145,
+      "loss": 1.2407,
+      "step": 39
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.4062119722366333,
+      "learning_rate": 0.00018842954907300236,
+      "loss": 1.1958,
+      "step": 40
+    },
+    {
+      "epoch": 0.7961165048543689,
+      "grad_norm": 0.5966278910636902,
+      "learning_rate": 0.0001876618552635348,
+      "loss": 1.2043,
+      "step": 41
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.47196483612060547,
+      "learning_rate": 0.00018687117365181512,
+      "loss": 1.2321,
+      "step": 42
+    },
+    {
+      "epoch": 0.8349514563106796,
+      "grad_norm": 0.6465126872062683,
+      "learning_rate": 0.00018605771158039253,
+      "loss": 1.1996,
+      "step": 43
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.4234643578529358,
+      "learning_rate": 0.00018522168236559695,
+      "loss": 1.198,
+      "step": 44
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3910824656486511,
+      "learning_rate": 0.00018436330524160047,
+      "loss": 1.1895,
+      "step": 45
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.5380635261535645,
+      "learning_rate": 0.00018348280530292713,
+      "loss": 1.1693,
+      "step": 46
+    },
+    {
+      "epoch": 0.912621359223301,
+      "grad_norm": 0.31823453307151794,
+      "learning_rate": 0.00018258041344542566,
+      "loss": 1.159,
+      "step": 47
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.5679419636726379,
+      "learning_rate": 0.0001816563663057211,
+      "loss": 1.1931,
+      "step": 48
+    },
+    {
+      "epoch": 0.9514563106796117,
+      "grad_norm": 0.3980861008167267,
+      "learning_rate": 0.00018071090619916093,
+      "loss": 1.1826,
+      "step": 49
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.3688671588897705,
+      "learning_rate": 0.00017974428105627208,
+      "loss": 1.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.9902912621359223,
+      "grad_norm": 0.4137047827243805,
+      "learning_rate": 0.00017875674435774547,
+      "loss": 1.142,
+      "step": 51
+    },
+    {
+      "epoch": 1.0097087378640777,
+      "grad_norm": 0.3141655921936035,
+      "learning_rate": 0.00017774855506796496,
+      "loss": 1.1614,
+      "step": 52
+    },
+    {
+      "epoch": 1.0048543689320388,
+      "grad_norm": 0.3113202154636383,
+      "learning_rate": 0.00017671997756709863,
+      "loss": 1.1668,
+      "step": 53
+    },
+    {
+      "epoch": 1.0242718446601942,
+      "grad_norm": 0.5369274616241455,
+      "learning_rate": 0.00017567128158176953,
+      "loss": 1.1157,
+      "step": 54
+    },
+    {
+      "epoch": 1.0436893203883495,
+      "grad_norm": 0.550740122795105,
+      "learning_rate": 0.0001746027421143246,
+      "loss": 1.1674,
+      "step": 55
+    },
+    {
+      "epoch": 1.0631067961165048,
+      "grad_norm": 0.4507598578929901,
+      "learning_rate": 0.00017351463937072004,
+      "loss": 1.1484,
+      "step": 56
+    },
+    {
+      "epoch": 1.0825242718446602,
+      "grad_norm": 0.5626426935195923,
+      "learning_rate": 0.00017240725868704218,
+      "loss": 1.1614,
+      "step": 57
+    },
+    {
+      "epoch": 1.1019417475728155,
+      "grad_norm": 0.36562928557395935,
+      "learning_rate": 0.00017128089045468294,
+      "loss": 1.1246,
+      "step": 58
+    },
+    {
+      "epoch": 1.1213592233009708,
+      "grad_norm": 0.6106365323066711,
+      "learning_rate": 0.00017013583004418993,
+      "loss": 1.141,
+      "step": 59
+    },
+    {
+      "epoch": 1.1407766990291262,
+      "grad_norm": 0.3751409947872162,
+      "learning_rate": 0.00016897237772781044,
+      "loss": 1.1565,
+      "step": 60
+    },
+    {
+      "epoch": 1.1601941747572815,
+      "grad_norm": 0.5318562984466553,
+      "learning_rate": 0.00016779083860075033,
+      "loss": 1.1501,
+      "step": 61
+    },
+    {
+      "epoch": 1.1796116504854368,
+      "grad_norm": 0.3675023317337036,
+      "learning_rate": 0.00016659152250116812,
+      "loss": 1.1162,
+      "step": 62
+    },
+    {
+      "epoch": 1.1990291262135921,
+      "grad_norm": 0.38894137740135193,
+      "learning_rate": 0.00016537474392892528,
+      "loss": 1.146,
+      "step": 63
+    },
+    {
+      "epoch": 1.2184466019417475,
+      "grad_norm": 0.3107282817363739,
+      "learning_rate": 0.000164140821963114,
+      "loss": 1.135,
+      "step": 64
+    },
+    {
+      "epoch": 1.237864077669903,
+      "grad_norm": 0.2496870756149292,
+      "learning_rate": 0.00016289008017838445,
+      "loss": 1.133,
+      "step": 65
+    },
+    {
+      "epoch": 1.2572815533980584,
+      "grad_norm": 0.35233214497566223,
+      "learning_rate": 0.00016162284656009274,
+      "loss": 1.1446,
+      "step": 66
+    },
+    {
+      "epoch": 1.2766990291262137,
+      "grad_norm": 0.33078905940055847,
+      "learning_rate": 0.00016033945341829248,
+      "loss": 1.1077,
+      "step": 67
+    },
+    {
+      "epoch": 1.296116504854369,
+      "grad_norm": 0.24236944317817688,
+      "learning_rate": 0.00015904023730059228,
+      "loss": 1.1367,
+      "step": 68
+    },
+    {
+      "epoch": 1.3155339805825244,
+      "grad_norm": 0.3248869776725769,
+      "learning_rate": 0.00015772553890390197,
+      "loss": 1.1405,
+      "step": 69
+    },
+    {
+      "epoch": 1.3349514563106797,
+      "grad_norm": 0.3145497739315033,
+      "learning_rate": 0.00015639570298509064,
+      "loss": 1.1134,
+      "step": 70
+    },
+    {
+      "epoch": 1.354368932038835,
+      "grad_norm": 0.3858337700366974,
+      "learning_rate": 0.00015505107827058036,
+      "loss": 1.1293,
+      "step": 71
+    },
+    {
+      "epoch": 1.3737864077669903,
+      "grad_norm": 0.3683490753173828,
+      "learning_rate": 0.0001536920173648984,
+      "loss": 1.1069,
+      "step": 72
+    },
+    {
+      "epoch": 1.3932038834951457,
+      "grad_norm": 0.5532976388931274,
+      "learning_rate": 0.000152318876658213,
+      "loss": 1.1432,
+      "step": 73
+    },
+    {
+      "epoch": 1.412621359223301,
+      "grad_norm": 0.3198872208595276,
+      "learning_rate": 0.00015093201623287631,
+      "loss": 1.1423,
+      "step": 74
+    },
+    {
+      "epoch": 1.4320388349514563,
+      "grad_norm": 0.7470155954360962,
+      "learning_rate": 0.00014953179976899878,
+      "loss": 1.1475,
+      "step": 75
+    },
+    {
+      "epoch": 1.4514563106796117,
+      "grad_norm": 0.4092984199523926,
+      "learning_rate": 0.00014811859444908052,
+      "loss": 1.0955,
+      "step": 76
+    },
+    {
+      "epoch": 1.470873786407767,
+      "grad_norm": 0.6536680459976196,
+      "learning_rate": 0.00014669277086172406,
+      "loss": 1.1359,
+      "step": 77
+    },
+    {
+      "epoch": 1.4902912621359223,
+      "grad_norm": 0.35692015290260315,
+      "learning_rate": 0.00014525470290445392,
+      "loss": 1.1131,
+      "step": 78
+    },
+    {
+      "epoch": 1.5097087378640777,
+      "grad_norm": 0.46786415576934814,
+      "learning_rate": 0.00014380476768566824,
+      "loss": 1.1133,
+      "step": 79
+    },
+    {
+      "epoch": 1.529126213592233,
+      "grad_norm": 0.6847173571586609,
+      "learning_rate": 0.00014234334542574906,
+      "loss": 1.125,
+      "step": 80
+    },
+    {
+      "epoch": 1.5485436893203883,
+      "grad_norm": 0.5090566277503967,
+      "learning_rate": 0.00014087081935735564,
+      "loss": 1.1562,
+      "step": 81
+    },
+    {
+      "epoch": 1.5679611650485437,
+      "grad_norm": 0.7293880581855774,
+      "learning_rate": 0.00013938757562492873,
+      "loss": 1.1348,
+      "step": 82
+    },
+    {
+      "epoch": 1.587378640776699,
+      "grad_norm": 0.3536413908004761,
+      "learning_rate": 0.00013789400318343068,
+      "loss": 1.1134,
+      "step": 83
+    },
+    {
+      "epoch": 1.6067961165048543,
+      "grad_norm": 0.802762508392334,
+      "learning_rate": 0.00013639049369634876,
+      "loss": 1.1256,
+      "step": 84
+    },
+    {
+      "epoch": 1.6262135922330097,
+      "grad_norm": 0.27904102206230164,
+      "learning_rate": 0.00013487744143298822,
+      "loss": 1.1367,
+      "step": 85
+    },
+    {
+      "epoch": 1.645631067961165,
+      "grad_norm": 0.6024283170700073,
+      "learning_rate": 0.00013335524316508208,
+      "loss": 1.1174,
+      "step": 86
+    },
+    {
+      "epoch": 1.6650485436893203,
+      "grad_norm": 0.5118915438652039,
+      "learning_rate": 0.0001318242980627444,
+      "loss": 1.0848,
+      "step": 87
+    },
+    {
+      "epoch": 1.6844660194174756,
+      "grad_norm": 0.3924892544746399,
+      "learning_rate": 0.00013028500758979506,
+      "loss": 1.1114,
+      "step": 88
+    },
+    {
+      "epoch": 1.703883495145631,
+      "grad_norm": 0.4876178801059723,
+      "learning_rate": 0.00012873777539848283,
+      "loss": 1.1303,
+      "step": 89
+    },
+    {
+      "epoch": 1.7233009708737863,
+      "grad_norm": 0.4133356809616089,
+      "learning_rate": 0.0001271830072236343,
+      "loss": 1.0894,
+      "step": 90
+    },
+    {
+      "epoch": 1.7427184466019416,
+      "grad_norm": 0.42908573150634766,
+      "learning_rate": 0.00012562111077625722,
+      "loss": 1.0806,
+      "step": 91
+    },
+    {
+      "epoch": 1.762135922330097,
+      "grad_norm": 0.5923053026199341,
+      "learning_rate": 0.00012405249563662537,
+      "loss": 1.1254,
+      "step": 92
+    },
+    {
+      "epoch": 1.7815533980582523,
+      "grad_norm": 0.34368380904197693,
+      "learning_rate": 0.00012247757314687297,
+      "loss": 1.1251,
+      "step": 93
+    },
+    {
+      "epoch": 1.8009708737864076,
+      "grad_norm": 0.6336709856987,
+      "learning_rate": 0.00012089675630312754,
+      "loss": 1.1042,
+      "step": 94
+    },
+    {
+      "epoch": 1.820388349514563,
+      "grad_norm": 0.32966285943984985,
+      "learning_rate": 0.00011931045964720881,
+      "loss": 1.09,
+      "step": 95
+    },
+    {
+      "epoch": 1.8398058252427183,
+      "grad_norm": 0.42973244190216064,
+      "learning_rate": 0.0001177190991579223,
+      "loss": 1.0896,
+      "step": 96
+    },
+    {
+      "epoch": 1.8592233009708736,
+      "grad_norm": 0.5365500450134277,
+      "learning_rate": 0.00011612309214197599,
+      "loss": 1.1281,
+      "step": 97
+    },
+    {
+      "epoch": 1.8786407766990292,
+      "grad_norm": 0.4330235421657562,
+      "learning_rate": 0.00011452285712454904,
+      "loss": 1.087,
+      "step": 98
+    },
+    {
+      "epoch": 1.8980582524271845,
+      "grad_norm": 0.47839391231536865,
+      "learning_rate": 0.00011291881373954065,
+      "loss": 1.0967,
+      "step": 99
+    },
+    {
+      "epoch": 1.9174757281553398,
+      "grad_norm": 0.27464163303375244,
+      "learning_rate": 0.00011131138261952845,
+      "loss": 1.0981,
+      "step": 100
+    },
+    {
+      "epoch": 1.9368932038834952,
+      "grad_norm": 0.41849982738494873,
+      "learning_rate": 0.00010970098528546481,
+      "loss": 1.1203,
+      "step": 101
+    },
+    {
+      "epoch": 1.9563106796116505,
+      "grad_norm": 0.4630599915981293,
+      "learning_rate": 0.00010808804403614043,
+      "loss": 1.1224,
+      "step": 102
+    },
+    {
+      "epoch": 1.9757281553398058,
+      "grad_norm": 0.34116509556770325,
+      "learning_rate": 0.00010647298183744359,
+      "loss": 1.0871,
+      "step": 103
+    },
+    {
+      "epoch": 1.9951456310679612,
+      "grad_norm": 0.4391232430934906,
+      "learning_rate": 0.00010485622221144484,
+      "loss": 1.1331,
+      "step": 104
+    },
+    {
+      "epoch": 2.0145631067961167,
+      "grad_norm": 0.4344836175441742,
+      "learning_rate": 0.00010323818912533561,
+      "loss": 1.0874,
+      "step": 105
+    },
+    {
+      "epoch": 2.0097087378640777,
+      "grad_norm": 0.42520374059677124,
+      "learning_rate": 0.00010161930688025017,
+      "loss": 1.1068,
+      "step": 106
+    },
+    {
+      "epoch": 2.029126213592233,
+      "grad_norm": 0.3572416305541992,
+      "learning_rate": 0.0001,
+      "loss": 1.1001,
+      "step": 107
+    },
+    {
+      "epoch": 2.0485436893203883,
+      "grad_norm": 0.38590529561042786,
+      "learning_rate": 9.838069311974986e-05,
+      "loss": 1.0833,
+      "step": 108
+    },
+    {
+      "epoch": 2.0679611650485437,
+      "grad_norm": 0.2969411313533783,
+      "learning_rate": 9.676181087466444e-05,
+      "loss": 1.0939,
+      "step": 109
+    },
+    {
+      "epoch": 2.087378640776699,
+      "grad_norm": 0.25997498631477356,
+      "learning_rate": 9.514377778855521e-05,
+      "loss": 1.1063,
+      "step": 110
+    },
+    {
+      "epoch": 2.1067961165048543,
+      "grad_norm": 0.3671320676803589,
+      "learning_rate": 9.352701816255643e-05,
+      "loss": 1.103,
+      "step": 111
+    },
+    {
+      "epoch": 2.1262135922330097,
+      "grad_norm": 0.552992582321167,
+      "learning_rate": 9.19119559638596e-05,
+      "loss": 1.0874,
+      "step": 112
+    },
+    {
+      "epoch": 2.145631067961165,
+      "grad_norm": 0.25193411111831665,
+      "learning_rate": 9.02990147145352e-05,
+      "loss": 1.0946,
+      "step": 113
+    },
+    {
+      "epoch": 2.1650485436893203,
+      "grad_norm": 0.33370667695999146,
+      "learning_rate": 8.868861738047158e-05,
+      "loss": 1.1108,
+      "step": 114
+    },
+    {
+      "epoch": 2.1844660194174756,
+      "grad_norm": 0.42085111141204834,
+      "learning_rate": 8.70811862604594e-05,
+      "loss": 1.0883,
+      "step": 115
+    },
+    {
+      "epoch": 2.203883495145631,
+      "grad_norm": 0.40206724405288696,
+      "learning_rate": 8.5477142875451e-05,
+      "loss": 1.1006,
+      "step": 116
+    },
+    {
+      "epoch": 2.2233009708737863,
+      "grad_norm": 0.3052491247653961,
+      "learning_rate": 8.387690785802402e-05,
+      "loss": 1.1155,
+      "step": 117
+    },
+    {
+      "epoch": 2.2427184466019416,
+      "grad_norm": 0.42322033643722534,
+      "learning_rate": 8.228090084207774e-05,
+      "loss": 1.0929,
+      "step": 118
+    },
+    {
+      "epoch": 2.262135922330097,
+      "grad_norm": 0.5083087682723999,
+      "learning_rate": 8.068954035279121e-05,
+      "loss": 1.122,
+      "step": 119
+    },
+    {
+      "epoch": 2.2815533980582523,
+      "grad_norm": 0.2693060636520386,
+      "learning_rate": 7.91032436968725e-05,
+      "loss": 1.0837,
+      "step": 120
+    },
+    {
+      "epoch": 2.3009708737864076,
+      "grad_norm": 0.34834596514701843,
+      "learning_rate": 7.75224268531271e-05,
+      "loss": 1.0768,
+      "step": 121
+    },
+    {
+      "epoch": 2.320388349514563,
+      "grad_norm": 0.3885416090488434,
+      "learning_rate": 7.594750436337467e-05,
+      "loss": 1.0616,
+      "step": 122
+    },
+    {
+      "epoch": 2.3398058252427183,
+      "grad_norm": 0.3093293011188507,
+      "learning_rate": 7.437888922374276e-05,
+      "loss": 1.0799,
+      "step": 123
+    },
+    {
+      "epoch": 2.3592233009708736,
+      "grad_norm": 0.4098259210586548,
+      "learning_rate": 7.281699277636572e-05,
+      "loss": 1.1184,
+      "step": 124
+    },
+    {
+      "epoch": 2.378640776699029,
+      "grad_norm": 0.29187697172164917,
+      "learning_rate": 7.126222460151719e-05,
+      "loss": 1.0883,
+      "step": 125
+    },
+    {
+      "epoch": 2.3980582524271843,
+      "grad_norm": 0.3151191174983978,
+      "learning_rate": 6.971499241020495e-05,
+      "loss": 1.0692,
+      "step": 126
+    },
+    {
+      "epoch": 2.4174757281553396,
+      "grad_norm": 0.3117734491825104,
+      "learning_rate": 6.817570193725564e-05,
+      "loss": 1.0926,
+      "step": 127
+    },
+    {
+      "epoch": 2.436893203883495,
+      "grad_norm": 0.25921401381492615,
+      "learning_rate": 6.664475683491796e-05,
+      "loss": 1.0707,
+      "step": 128
+    },
+    {
+      "epoch": 2.4563106796116507,
+      "grad_norm": 0.31505605578422546,
+      "learning_rate": 6.512255856701177e-05,
+      "loss": 1.0988,
+      "step": 129
+    },
+    {
+      "epoch": 2.475728155339806,
+      "grad_norm": 0.25132912397384644,
+      "learning_rate": 6.360950630365126e-05,
+      "loss": 1.0726,
+      "step": 130
+    },
+    {
+      "epoch": 2.4951456310679614,
+      "grad_norm": 0.2596098780632019,
+      "learning_rate": 6.210599681656933e-05,
+      "loss": 1.1138,
+      "step": 131
+    },
+    {
+      "epoch": 2.5145631067961167,
+      "grad_norm": 0.24262911081314087,
+      "learning_rate": 6.061242437507131e-05,
+      "loss": 1.0759,
+      "step": 132
+    },
+    {
+      "epoch": 2.533980582524272,
+      "grad_norm": 0.29739508032798767,
+      "learning_rate": 5.9129180642644414e-05,
+      "loss": 1.082,
+      "step": 133
+    },
+    {
+      "epoch": 2.5533980582524274,
+      "grad_norm": 0.32182446122169495,
+      "learning_rate": 5.765665457425102e-05,
+      "loss": 1.0698,
+      "step": 134
+    },
+    {
+      "epoch": 2.5728155339805827,
+      "grad_norm": 0.3175111711025238,
+      "learning_rate": 5.6195232314331766e-05,
+      "loss": 1.099,
+      "step": 135
+    },
+    {
+      "epoch": 2.592233009708738,
+      "grad_norm": 0.34597843885421753,
+      "learning_rate": 5.474529709554612e-05,
+      "loss": 1.0971,
+      "step": 136
+    },
+    {
+      "epoch": 2.6116504854368934,
+      "grad_norm": 0.2773433327674866,
+      "learning_rate": 5.3307229138275936e-05,
+      "loss": 1.0747,
+      "step": 137
+    },
+    {
+      "epoch": 2.6310679611650487,
+      "grad_norm": 0.3997284770011902,
+      "learning_rate": 5.1881405550919493e-05,
+      "loss": 1.0579,
+      "step": 138
+    },
+    {
+      "epoch": 2.650485436893204,
+      "grad_norm": 0.3829750716686249,
+      "learning_rate": 5.0468200231001286e-05,
+      "loss": 1.0671,
+      "step": 139
+    },
+    {
+      "epoch": 2.6699029126213594,
+      "grad_norm": 0.2364608198404312,
+      "learning_rate": 4.9067983767123736e-05,
+      "loss": 1.0739,
+      "step": 140
+    },
+    {
+      "epoch": 2.6893203883495147,
+      "grad_norm": 0.29015663266181946,
+      "learning_rate": 4.768112334178699e-05,
+      "loss": 1.0626,
+      "step": 141
+    },
+    {
+      "epoch": 2.70873786407767,
+      "grad_norm": 0.39254897832870483,
+      "learning_rate": 4.630798263510162e-05,
+      "loss": 1.0648,
+      "step": 142
+    },
+    {
+      "epoch": 2.7281553398058254,
+      "grad_norm": 0.42674142122268677,
+      "learning_rate": 4.494892172941965e-05,
+      "loss": 1.1137,
+      "step": 143
+    },
+    {
+      "epoch": 2.7475728155339807,
+      "grad_norm": 0.4450013041496277,
+      "learning_rate": 4.360429701490934e-05,
+      "loss": 1.1096,
+      "step": 144
+    },
+    {
+      "epoch": 2.766990291262136,
+      "grad_norm": 0.333667516708374,
+      "learning_rate": 4.227446109609809e-05,
+      "loss": 1.0758,
+      "step": 145
+    },
+    {
+      "epoch": 2.7864077669902914,
+      "grad_norm": 0.4920090436935425,
+      "learning_rate": 4.0959762699407766e-05,
+      "loss": 1.0698,
+      "step": 146
+    },
+    {
+      "epoch": 2.8058252427184467,
+      "grad_norm": 0.31687042117118835,
+      "learning_rate": 3.966054658170754e-05,
+      "loss": 1.0901,
+      "step": 147
+    },
+    {
+      "epoch": 2.825242718446602,
+      "grad_norm": 0.3884165585041046,
+      "learning_rate": 3.8377153439907266e-05,
+      "loss": 1.0753,
+      "step": 148
+    },
+    {
+      "epoch": 2.8446601941747574,
+      "grad_norm": 0.41056135296821594,
+      "learning_rate": 3.710991982161555e-05,
+      "loss": 1.1145,
+      "step": 149
+    },
+    {
+      "epoch": 2.8640776699029127,
+      "grad_norm": 0.32460349798202515,
+      "learning_rate": 3.585917803688603e-05,
+      "loss": 1.0716,
+      "step": 150
+    },
+    {
+      "epoch": 2.883495145631068,
+      "grad_norm": 0.3436354994773865,
+      "learning_rate": 3.4625256071074773e-05,
+      "loss": 1.0995,
+      "step": 151
+    },
+    {
+      "epoch": 2.9029126213592233,
+      "grad_norm": 0.29039478302001953,
+      "learning_rate": 3.340847749883191e-05,
+      "loss": 1.058,
+      "step": 152
+    },
+    {
+      "epoch": 2.9223300970873787,
+      "grad_norm": 0.2641606330871582,
+      "learning_rate": 3.2209161399249674e-05,
+      "loss": 1.0705,
+      "step": 153
+    },
+    {
+      "epoch": 2.941747572815534,
+      "grad_norm": 0.3594358265399933,
+      "learning_rate": 3.102762227218957e-05,
+      "loss": 1.0932,
+      "step": 154
+    },
+    {
+      "epoch": 2.9611650485436893,
+      "grad_norm": 0.23593547940254211,
+      "learning_rate": 2.9864169955810084e-05,
+      "loss": 1.0527,
+      "step": 155
+    },
+    {
+      "epoch": 2.9805825242718447,
+      "grad_norm": 0.2442445307970047,
+      "learning_rate": 2.8719109545317103e-05,
+      "loss": 1.0863,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2583329677581787,
+      "learning_rate": 2.759274131295787e-05,
+      "loss": 1.0948,
+      "step": 157
+    },
+    {
+      "epoch": 3.0194174757281553,
+      "grad_norm": 0.3333183228969574,
+      "learning_rate": 2.6485360629279987e-05,
+      "loss": 1.1272,
+      "step": 158
+    },
+    {
+      "epoch": 3.0145631067961167,
+      "grad_norm": 0.34542328119277954,
+      "learning_rate": 2.5397257885675397e-05,
+      "loss": 1.0788,
+      "step": 159
+    },
+    {
+      "epoch": 3.033980582524272,
+      "grad_norm": 0.23096761107444763,
+      "learning_rate": 2.432871841823047e-05,
+      "loss": 1.0871,
+      "step": 160
+    },
+    {
+      "epoch": 3.0533980582524274,
+      "grad_norm": 0.24203942716121674,
+      "learning_rate": 2.3280022432901383e-05,
+      "loss": 1.052,
+      "step": 161
+    },
+    {
+      "epoch": 3.0728155339805827,
+      "grad_norm": 0.21322639286518097,
+      "learning_rate": 2.2251444932035094e-05,
+      "loss": 1.084,
+      "step": 162
+    },
+    {
+      "epoch": 3.092233009708738,
+      "grad_norm": 0.29339829087257385,
+      "learning_rate": 2.1243255642254578e-05,
+      "loss": 1.0899,
+      "step": 163
+    },
+    {
+      "epoch": 3.1116504854368934,
+      "grad_norm": 0.34360697865486145,
+      "learning_rate": 2.025571894372794e-05,
+      "loss": 1.1268,
+      "step": 164
+    },
+    {
+      "epoch": 3.1310679611650487,
+      "grad_norm": 0.30623048543930054,
+      "learning_rate": 1.9289093800839066e-05,
+      "loss": 1.0909,
+      "step": 165
+    },
+    {
+      "epoch": 3.150485436893204,
+      "grad_norm": 0.23241010308265686,
+      "learning_rate": 1.8343633694278895e-05,
+      "loss": 1.0688,
+      "step": 166
+    },
+    {
+      "epoch": 3.1699029126213594,
+      "grad_norm": 0.3101847767829895,
+      "learning_rate": 1.741958655457436e-05,
+      "loss": 1.036,
+      "step": 167
+    },
+    {
+      "epoch": 3.1893203883495147,
+      "grad_norm": 0.31015124917030334,
+      "learning_rate": 1.65171946970729e-05,
+      "loss": 1.0687,
+      "step": 168
+    },
+    {
+      "epoch": 3.20873786407767,
+      "grad_norm": 0.2729584872722626,
+      "learning_rate": 1.563669475839956e-05,
+      "loss": 1.0798,
+      "step": 169
+    },
+    {
+      "epoch": 3.2281553398058254,
+      "grad_norm": 0.31670236587524414,
+      "learning_rate": 1.4778317634403083e-05,
+      "loss": 1.0775,
+      "step": 170
+    },
+    {
+      "epoch": 3.2475728155339807,
+      "grad_norm": 0.319918692111969,
+      "learning_rate": 1.3942288419607475e-05,
+      "loss": 1.0666,
+      "step": 171
+    },
+    {
+      "epoch": 3.266990291262136,
+      "grad_norm": 0.2893763482570648,
+      "learning_rate": 1.3128826348184887e-05,
+      "loss": 1.0665,
+      "step": 172
+    },
+    {
+      "epoch": 3.2864077669902914,
+      "grad_norm": 0.2631440758705139,
+      "learning_rate": 1.233814473646524e-05,
+      "loss": 1.059,
+      "step": 173
+    },
+    {
+      "epoch": 3.3058252427184467,
+      "grad_norm": 0.3630000948905945,
+      "learning_rate": 1.1570450926997655e-05,
+      "loss": 1.0832,
+      "step": 174
+    },
+    {
+      "epoch": 3.325242718446602,
+      "grad_norm": 0.26215022802352905,
+      "learning_rate": 1.0825946234178574e-05,
+      "loss": 1.0813,
+      "step": 175
+    },
+    {
+      "epoch": 3.3446601941747574,
+      "grad_norm": 0.31675612926483154,
+      "learning_rate": 1.010482589146048e-05,
+      "loss": 1.0857,
+      "step": 176
+    },
+    {
+      "epoch": 3.3640776699029127,
+      "grad_norm": 0.287594199180603,
+      "learning_rate": 9.407279000155312e-06,
+      "loss": 1.1148,
+      "step": 177
+    },
+    {
+      "epoch": 3.383495145631068,
+      "grad_norm": 0.24483542144298553,
+      "learning_rate": 8.733488479845997e-06,
+      "loss": 1.0625,
+      "step": 178
+    },
+    {
+      "epoch": 3.4029126213592233,
+      "grad_norm": 0.2373855859041214,
+      "learning_rate": 8.083631020418791e-06,
+      "loss": 1.083,
+      "step": 179
+    },
+    {
+      "epoch": 3.4223300970873787,
+      "grad_norm": 0.2648206055164337,
+      "learning_rate": 7.457877035729588e-06,
+      "loss": 1.0577,
+      "step": 180
+    },
+    {
+      "epoch": 3.441747572815534,
+      "grad_norm": 0.29279831051826477,
+      "learning_rate": 6.856390618915775e-06,
+      "loss": 1.0949,
+      "step": 181
+    },
+    {
+      "epoch": 3.4611650485436893,
+      "grad_norm": 0.27792996168136597,
+      "learning_rate": 6.2793294993656494e-06,
+      "loss": 1.0856,
+      "step": 182
+    },
+    {
+      "epoch": 3.4805825242718447,
+      "grad_norm": 0.2441776841878891,
+      "learning_rate": 5.726845001356573e-06,
+      "loss": 1.0374,
+      "step": 183
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.2667102515697479,
+      "learning_rate": 5.199082004372957e-06,
+      "loss": 1.0732,
+      "step": 184
+    },
+    {
+      "epoch": 3.5194174757281553,
+      "grad_norm": 0.21864843368530273,
+      "learning_rate": 4.6961789051139124e-06,
+      "loss": 1.0823,
+      "step": 185
+    },
+    {
+      "epoch": 3.5388349514563107,
+      "grad_norm": 0.21724966168403625,
+      "learning_rate": 4.2182675812012965e-06,
+      "loss": 1.0892,
+      "step": 186
+    },
+    {
+      "epoch": 3.558252427184466,
+      "grad_norm": 0.2550470530986786,
+      "learning_rate": 3.7654733565969826e-06,
+      "loss": 1.0725,
+      "step": 187
+    },
+    {
+      "epoch": 3.5776699029126213,
+      "grad_norm": 0.23086749017238617,
+      "learning_rate": 3.3379149687388867e-06,
+      "loss": 1.0469,
+      "step": 188
+    },
+    {
+      "epoch": 3.5970873786407767,
+      "grad_norm": 0.20026402175426483,
+      "learning_rate": 2.9357045374040825e-06,
+      "loss": 1.0784,
+      "step": 189
+    },
+    {
+      "epoch": 3.616504854368932,
+      "grad_norm": 0.2986784875392914,
+      "learning_rate": 2.5589475353073988e-06,
+      "loss": 1.0751,
+      "step": 190
+    },
+    {
+      "epoch": 3.6359223300970873,
+      "grad_norm": 0.2252379208803177,
+      "learning_rate": 2.2077427604429433e-06,
+      "loss": 1.0802,
+      "step": 191
+    },
+    {
+      "epoch": 3.6553398058252426,
+      "grad_norm": 0.30462658405303955,
+      "learning_rate": 1.882182310176095e-06,
+      "loss": 1.0753,
+      "step": 192
+    },
+    {
+      "epoch": 3.674757281553398,
+      "grad_norm": 0.3177051842212677,
+      "learning_rate": 1.5823515570925763e-06,
+      "loss": 1.0974,
+      "step": 193
+    },
+    {
+      "epoch": 3.6941747572815533,
+      "grad_norm": 0.26043936610221863,
+      "learning_rate": 1.30832912661093e-06,
+      "loss": 1.0734,
+      "step": 194
+    },
+    {
+      "epoch": 3.7135922330097086,
+      "grad_norm": 0.28095176815986633,
+      "learning_rate": 1.0601868763643996e-06,
+      "loss": 1.029,
+      "step": 195
+    },
+    {
+      "epoch": 3.733009708737864,
+      "grad_norm": 0.25758782029151917,
+      "learning_rate": 8.379898773574924e-07,
+      "loss": 1.0796,
+      "step": 196
+    },
+    {
+      "epoch": 3.7524271844660193,
+      "grad_norm": 0.24343402683734894,
+      "learning_rate": 6.41796396902239e-07,
+      "loss": 1.0581,
+      "step": 197
+    },
+    {
+      "epoch": 3.7718446601941746,
+      "grad_norm": 0.33343780040740967,
+      "learning_rate": 4.7165788333860536e-07,
+      "loss": 1.0505,
+      "step": 198
+    },
+    {
+      "epoch": 3.79126213592233,
+      "grad_norm": 0.2605248987674713,
+      "learning_rate": 3.2761895254306287e-07,
+      "loss": 1.0766,
+      "step": 199
+    },
+    {
+      "epoch": 3.8106796116504853,
+      "grad_norm": 0.212020143866539,
+      "learning_rate": 2.0971737622883515e-07,
+      "loss": 1.0873,
+      "step": 200
+    },
+    {
+      "epoch": 3.8300970873786406,
+      "grad_norm": 0.22274315357208252,
+      "learning_rate": 1.179840720409331e-07,
+      "loss": 1.0891,
+      "step": 201
+    },
+    {
+      "epoch": 3.849514563106796,
+      "grad_norm": 0.22543945908546448,
+      "learning_rate": 5.2443095448506674e-08,
+      "loss": 1.0872,
+      "step": 202
+    },
+    {
+      "epoch": 3.8689320388349513,
+      "grad_norm": 0.23441745340824127,
+      "learning_rate": 1.3111633436779791e-08,
+      "loss": 1.063,
+      "step": 203
+    },
+    {
+      "epoch": 3.8883495145631066,
+      "grad_norm": 0.21964219212532043,
+      "learning_rate": 0.0,
+      "loss": 1.0592,
+      "step": 204
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 51,
+  "total_flos": 4.242610320939418e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-204/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5137d02e04a9e9bac65c98c789ae039033678d1581c7bd7d88ddb181436aa56
+size 5816

checkpoint-51/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 0.10.0

checkpoint-51/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",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-51/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b4b723e0887dfa273147b671f4a009077daa8b46adbecbb5cf38cadd073c9c
+size 100966336

checkpoint-51/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03d5e1aef4faa5c75566c9b333fc1fb6a8892c4f2c7f10dc7f4e05385b7ba044
+size 50916644

checkpoint-51/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab833cfff002e43a167eac31cfae2b8d550a6135c273d9542402c54bb8d1c89
+size 14244

checkpoint-51/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd13ac134c35297ef96960e4179dd2070c464a771be236b3ecea6e530dfbef2
+size 1064

checkpoint-51/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-51/tokenizer.model

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

checkpoint-51/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-51/trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9902912621359223,
+  "eval_steps": 500,
+  "global_step": 51,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 6.841878890991211,
+      "learning_rate": 2e-05,
+      "loss": 4.5864,
+      "step": 1
+    },
+    {
+      "epoch": 0.038834951456310676,
+      "grad_norm": 6.640402793884277,
+      "learning_rate": 4e-05,
+      "loss": 4.6138,
+      "step": 2
+    },
+    {
+      "epoch": 0.05825242718446602,
+      "grad_norm": 6.41209077835083,
+      "learning_rate": 6e-05,
+      "loss": 4.6064,
+      "step": 3
+    },
+    {
+      "epoch": 0.07766990291262135,
+      "grad_norm": 6.082383632659912,
+      "learning_rate": 8e-05,
+      "loss": 4.5534,
+      "step": 4
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 4.00201416015625,
+      "learning_rate": 0.0001,
+      "loss": 4.3245,
+      "step": 5
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 3.1707470417022705,
+      "learning_rate": 0.00012,
+      "loss": 4.0971,
+      "step": 6
+    },
+    {
+      "epoch": 0.13592233009708737,
+      "grad_norm": 3.160670518875122,
+      "learning_rate": 0.00014,
+      "loss": 3.789,
+      "step": 7
+    },
+    {
+      "epoch": 0.1553398058252427,
+      "grad_norm": 2.994746208190918,
+      "learning_rate": 0.00016,
+      "loss": 3.3244,
+      "step": 8
+    },
+    {
+      "epoch": 0.17475728155339806,
+      "grad_norm": 2.6664786338806152,
+      "learning_rate": 0.00018,
+      "loss": 2.8561,
+      "step": 9
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 2.029910087585449,
+      "learning_rate": 0.0002,
+      "loss": 2.3926,
+      "step": 10
+    },
+    {
+      "epoch": 0.21359223300970873,
+      "grad_norm": 1.3144137859344482,
+      "learning_rate": 0.00019998688836656323,
+      "loss": 2.0283,
+      "step": 11
+    },
+    {
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.8263471722602844,
+      "learning_rate": 0.00019994755690455152,
+      "loss": 1.8683,
+      "step": 12
+    },
+    {
+      "epoch": 0.2524271844660194,
+      "grad_norm": 0.7193414568901062,
+      "learning_rate": 0.0001998820159279591,
+      "loss": 1.732,
+      "step": 13
+    },
+    {
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.8350910544395447,
+      "learning_rate": 0.00019979028262377118,
+      "loss": 1.6208,
+      "step": 14
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.6700139045715332,
+      "learning_rate": 0.00019967238104745696,
+      "loss": 1.493,
+      "step": 15
+    },
+    {
+      "epoch": 0.3106796116504854,
+      "grad_norm": 1.1213518381118774,
+      "learning_rate": 0.0001995283421166614,
+      "loss": 1.4857,
+      "step": 16
+    },
+    {
+      "epoch": 0.3300970873786408,
+      "grad_norm": 0.7505896687507629,
+      "learning_rate": 0.00019935820360309777,
+      "loss": 1.4643,
+      "step": 17
+    },
+    {
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.6984190940856934,
+      "learning_rate": 0.00019916201012264254,
+      "loss": 1.4227,
+      "step": 18
+    },
+    {
+      "epoch": 0.36893203883495146,
+      "grad_norm": 0.46819525957107544,
+      "learning_rate": 0.00019893981312363562,
+      "loss": 1.3889,
+      "step": 19
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5214670300483704,
+      "learning_rate": 0.00019869167087338907,
+      "loss": 1.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.4077669902912621,
+      "grad_norm": 0.43329402804374695,
+      "learning_rate": 0.00019841764844290744,
+      "loss": 1.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.6535053253173828,
+      "learning_rate": 0.0001981178176898239,
+      "loss": 1.3576,
+      "step": 22
+    },
+    {
+      "epoch": 0.44660194174757284,
+      "grad_norm": 0.6363189816474915,
+      "learning_rate": 0.00019779225723955707,
+      "loss": 1.3159,
+      "step": 23
+    },
+    {
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.42140620946884155,
+      "learning_rate": 0.00019744105246469263,
+      "loss": 1.3072,
+      "step": 24
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.6757440567016602,
+      "learning_rate": 0.00019706429546259593,
+      "loss": 1.3261,
+      "step": 25
+    },
+    {
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.4116632044315338,
+      "learning_rate": 0.00019666208503126112,
+      "loss": 1.317,
+      "step": 26
+    },
+    {
+      "epoch": 0.5242718446601942,
+      "grad_norm": 0.5359898209571838,
+      "learning_rate": 0.00019623452664340306,
+      "loss": 1.2932,
+      "step": 27
+    },
+    {
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.4596949517726898,
+      "learning_rate": 0.00019578173241879872,
+      "loss": 1.2601,
+      "step": 28
+    },
+    {
+      "epoch": 0.5631067961165048,
+      "grad_norm": 0.6857442855834961,
+      "learning_rate": 0.0001953038210948861,
+      "loss": 1.2734,
+      "step": 29
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.4453957676887512,
+      "learning_rate": 0.00019480091799562704,
+      "loss": 1.2521,
+      "step": 30
+    },
+    {
+      "epoch": 0.6019417475728155,
+      "grad_norm": 0.6118847131729126,
+      "learning_rate": 0.00019427315499864344,
+      "loss": 1.2252,
+      "step": 31
+    },
+    {
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.4894339442253113,
+      "learning_rate": 0.00019372067050063438,
+      "loss": 1.2369,
+      "step": 32
+    },
+    {
+      "epoch": 0.6407766990291263,
+      "grad_norm": 0.5901785492897034,
+      "learning_rate": 0.00019314360938108425,
+      "loss": 1.2507,
+      "step": 33
+    },
+    {
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.4147897958755493,
+      "learning_rate": 0.00019254212296427044,
+      "loss": 1.2454,
+      "step": 34
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.2836126685142517,
+      "learning_rate": 0.00019191636897958122,
+      "loss": 1.2515,
+      "step": 35
+    },
+    {
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.4523944556713104,
+      "learning_rate": 0.00019126651152015403,
+      "loss": 1.2217,
+      "step": 36
+    },
+    {
+      "epoch": 0.7184466019417476,
+      "grad_norm": 0.4187013804912567,
+      "learning_rate": 0.0001905927209998447,
+      "loss": 1.2382,
+      "step": 37
+    },
+    {
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.516381561756134,
+      "learning_rate": 0.00018989517410853955,
+      "loss": 1.2214,
+      "step": 38
+    },
+    {
+      "epoch": 0.7572815533980582,
+      "grad_norm": 0.5928078889846802,
+      "learning_rate": 0.00018917405376582145,
+      "loss": 1.2407,
+      "step": 39
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.4062119722366333,
+      "learning_rate": 0.00018842954907300236,
+      "loss": 1.1958,
+      "step": 40
+    },
+    {
+      "epoch": 0.7961165048543689,
+      "grad_norm": 0.5966278910636902,
+      "learning_rate": 0.0001876618552635348,
+      "loss": 1.2043,
+      "step": 41
+    },
+    {
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.47196483612060547,
+      "learning_rate": 0.00018687117365181512,
+      "loss": 1.2321,
+      "step": 42
+    },
+    {
+      "epoch": 0.8349514563106796,
+      "grad_norm": 0.6465126872062683,
+      "learning_rate": 0.00018605771158039253,
+      "loss": 1.1996,
+      "step": 43
+    },
+    {
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.4234643578529358,
+      "learning_rate": 0.00018522168236559695,
+      "loss": 1.198,
+      "step": 44
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3910824656486511,
+      "learning_rate": 0.00018436330524160047,
+      "loss": 1.1895,
+      "step": 45
+    },
+    {
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.5380635261535645,
+      "learning_rate": 0.00018348280530292713,
+      "loss": 1.1693,
+      "step": 46
+    },
+    {
+      "epoch": 0.912621359223301,
+      "grad_norm": 0.31823453307151794,
+      "learning_rate": 0.00018258041344542566,
+      "loss": 1.159,
+      "step": 47
+    },
+    {
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.5679419636726379,
+      "learning_rate": 0.0001816563663057211,
+      "loss": 1.1931,
+      "step": 48
+    },
+    {
+      "epoch": 0.9514563106796117,
+      "grad_norm": 0.3980861008167267,
+      "learning_rate": 0.00018071090619916093,
+      "loss": 1.1826,
+      "step": 49
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.3688671588897705,
+      "learning_rate": 0.00017974428105627208,
+      "loss": 1.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.9902912621359223,
+      "grad_norm": 0.4137047827243805,
+      "learning_rate": 0.00017875674435774547,
+      "loss": 1.142,
+      "step": 51
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 204,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 51,
+  "total_flos": 1.0626058999037952e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-51/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5137d02e04a9e9bac65c98c789ae039033678d1581c7bd7d88ddb181436aa56
+size 5816

config.json

@@ -0,0 +1,43 @@
+{
+  "_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,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "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