Subiendo mi modelo entrenado finetuneado desde Trisert/tinyllama-alpaca

README.md

@@ -0,0 +1,143 @@
+---
+base_model: Trisert/tinyllama-alpaca
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/qlora-out-context
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: qlora
+base_model: Trisert/tinyllama-alpaca
+bf16: false
+dataset_prepared_path: null
+datasets:
+- ds_tipe: json
+  path: /content/pubmed_continual_pretraning_dataset.jsonl
+  type: completion
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_sample_packing: false
+evals_per_epoch: 4
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: false
+learning_rate: 0.0002
+load_in_4bit: true
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lora_target_modules: null
+lr_scheduler: cosine
+micro_batch_size: 8
+model_type: AutoModelForCausalLM
+num_epochs: 4
+optimizer: paged_adamw_32bit
+output_dir: ./outputs/qlora-out-context
+pad_to_sequence_len: false
+resume_from_checkpoint: null
+sample_packing: false
+saves_per_epoch: 1
+sequence_len: 4096
+special_tokens: null
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+val_set_size: 0.05
+wandb_entity: null
+wandb_log_model: null
+wandb_name: null
+wandb_project: null
+wandb_watch: null
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# outputs/qlora-out-context
+
+This model is a fine-tuned version of [Trisert/tinyllama-alpaca](https://huggingface.co/Trisert/tinyllama-alpaca) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8030
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.6905        | 0.0336 | 1    | 2.7292          |
+| 2.4725        | 0.2689 | 8    | 2.3972          |
+| 1.9891        | 0.5378 | 16   | 2.0718          |
+| 1.8345        | 0.8067 | 24   | 1.9329          |
+| 1.8088        | 1.0756 | 32   | 1.8730          |
+| 1.8183        | 1.3445 | 40   | 1.8430          |
+| 1.8004        | 1.6134 | 48   | 1.8263          |
+| 1.7674        | 1.8824 | 56   | 1.8167          |
+| 1.7164        | 2.1513 | 64   | 1.8104          |
+| 1.6525        | 2.4202 | 72   | 1.8069          |
+| 1.7917        | 2.6891 | 80   | 1.8053          |
+| 1.8022        | 2.9580 | 88   | 1.8037          |
+| 1.6917        | 3.2269 | 96   | 1.8032          |
+| 1.765         | 3.4958 | 104  | 1.8030          |
+| 1.6784        | 3.7647 | 112  | 1.8030          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trisert/tinyllama-alpaca",
+  "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",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd33854a7792bab0b4afc066474a60d920a982671c53bec0bd2053bf3fe1c521
+size 50573978

checkpoint-116/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Trisert/tinyllama-alpaca
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-116/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trisert/tinyllama-alpaca",
+  "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",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-116/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f568e6576f16b81e9bec90a3a92ea01031a33d0cb6a8fdcd3d6f304273a572
+size 50503848

checkpoint-116/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47e5ffbf73b628bed73b14ff5069203be95b4eadc1d2e2abc2a5ca79b8e4707
+size 202035450

checkpoint-116/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbf3bea1d4f693a677a0bf33551e5e3063cbd96faf6ce6d46f9d3b4ff62532d
+size 14244

checkpoint-116/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68424c30349bda77a4657d1902f52c5a348248ab657a58e4aee2ebfc370c25ab
+size 1064

checkpoint-116/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-116/tokenizer.model

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

checkpoint-116/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-116/trainer_state.json

@@ -0,0 +1,965 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.899159663865546,
+  "eval_steps": 8,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2e-05,
+      "loss": 2.6905,
+      "step": 1
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "eval_loss": 2.729154109954834,
+      "eval_runtime": 20.6566,
+      "eval_samples_per_second": 2.421,
+      "eval_steps_per_second": 0.339,
+      "step": 1
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4e-05,
+      "loss": 2.687,
+      "step": 2
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6e-05,
+      "loss": 2.8062,
+      "step": 3
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.03125,
+      "learning_rate": 8e-05,
+      "loss": 2.6619,
+      "step": 4
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5939,
+      "step": 5
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00012,
+      "loss": 2.6307,
+      "step": 6
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.00014,
+      "loss": 2.5751,
+      "step": 7
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00016,
+      "loss": 2.4725,
+      "step": 8
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "eval_loss": 2.3971643447875977,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00018,
+      "loss": 2.2905,
+      "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0002,
+      "loss": 2.3883,
+      "step": 10
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00019995608365087946,
+      "loss": 2.3071,
+      "step": 11
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.00019982437317643217,
+      "loss": 2.0817,
+      "step": 12
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001996049842615217,
+      "loss": 2.0883,
+      "step": 13
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019929810960135172,
+      "loss": 2.1018,
+      "step": 14
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001989040187322164,
+      "loss": 2.1015,
+      "step": 15
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019842305779475968,
+      "loss": 1.9891,
+      "step": 16
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "eval_loss": 2.071833610534668,
+      "eval_runtime": 20.5312,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 16
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001978556492299504,
+      "loss": 2.1245,
+      "step": 17
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.0001972022914080411,
+      "loss": 1.9485,
+      "step": 18
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.00019646355819083589,
+      "loss": 2.0621,
+      "step": 19
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00019564009842765225,
+      "loss": 1.9076,
+      "step": 20
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.00019473263538541914,
+      "loss": 1.8968,
+      "step": 21
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.0001937419661134121,
+      "loss": 1.8977,
+      "step": 22
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019266896074318334,
+      "loss": 1.9926,
+      "step": 23
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019151456172430183,
+      "loss": 1.8345,
+      "step": 24
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "eval_loss": 1.932895302772522,
+      "eval_runtime": 20.5148,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 24
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019027978299657436,
+      "loss": 1.8168,
+      "step": 25
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00018896570909947475,
+      "loss": 1.8794,
+      "step": 26
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001875734942195637,
+      "loss": 1.9604,
+      "step": 27
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00018610436117673555,
+      "loss": 1.824,
+      "step": 28
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001845596003501826,
+      "loss": 1.9186,
+      "step": 29
+    },
+    {
+      "epoch": 1.0084033613445378,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001829405685450202,
+      "loss": 1.9281,
+      "step": 30
+    },
+    {
+      "epoch": 1.0420168067226891,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018124868780056814,
+      "loss": 1.833,
+      "step": 31
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.00017948544414133534,
+      "loss": 1.8088,
+      "step": 32
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "eval_loss": 1.8729643821716309,
+      "eval_runtime": 20.5377,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 32
+    },
+    {
+      "epoch": 1.1092436974789917,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00017765238627180424,
+      "loss": 1.8401,
+      "step": 33
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 0.00017575112421616202,
+      "loss": 1.7736,
+      "step": 34
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.00017378332790417273,
+      "loss": 1.7875,
+      "step": 35
+    },
+    {
+      "epoch": 1.2100840336134453,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00017175072570443312,
+      "loss": 1.7743,
+      "step": 36
+    },
+    {
+      "epoch": 1.2436974789915967,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 0.00016965510290629972,
+      "loss": 1.8167,
+      "step": 37
+    },
+    {
+      "epoch": 1.2773109243697478,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 0.00016749830015182107,
+      "loss": 1.8317,
+      "step": 38
+    },
+    {
+      "epoch": 1.3109243697478992,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00016528221181905217,
+      "loss": 1.7498,
+      "step": 39
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 0.197265625,
+      "learning_rate": 0.00016300878435817113,
+      "loss": 1.8183,
+      "step": 40
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "eval_loss": 1.8429957628250122,
+      "eval_runtime": 20.5619,
+      "eval_samples_per_second": 2.432,
+      "eval_steps_per_second": 0.34,
+      "step": 40
+    },
+    {
+      "epoch": 1.3781512605042017,
+      "grad_norm": 0.193359375,
+      "learning_rate": 0.00016068001458185936,
+      "loss": 1.7504,
+      "step": 41
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001582979479114472,
+      "loss": 1.7476,
+      "step": 42
+    },
+    {
+      "epoch": 1.4453781512605042,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00015586467658036524,
+      "loss": 1.8082,
+      "step": 43
+    },
+    {
+      "epoch": 1.4789915966386555,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001533823377964791,
+      "loss": 1.6987,
+      "step": 44
+    },
+    {
+      "epoch": 1.5126050420168067,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 0.00015085311186492206,
+      "loss": 1.7417,
+      "step": 45
+    },
+    {
+      "epoch": 1.5462184873949578,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.00014827922027307451,
+      "loss": 1.779,
+      "step": 46
+    },
+    {
+      "epoch": 1.5798319327731094,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.0001456629237393713,
+      "loss": 1.7552,
+      "step": 47
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00014300652022765207,
+      "loss": 1.8004,
+      "step": 48
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "eval_loss": 1.8263332843780518,
+      "eval_runtime": 20.4305,
+      "eval_samples_per_second": 2.447,
+      "eval_steps_per_second": 0.343,
+      "step": 48
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014031234292879725,
+      "loss": 1.7857,
+      "step": 49
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.00013758275821142382,
+      "loss": 1.7193,
+      "step": 50
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 0.0001348201635434399,
+      "loss": 1.7734,
+      "step": 51
+    },
+    {
+      "epoch": 1.7478991596638656,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013202698538628376,
+      "loss": 1.7644,
+      "step": 52
+    },
+    {
+      "epoch": 1.7815126050420167,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00012920567706369758,
+      "loss": 1.8631,
+      "step": 53
+    },
+    {
+      "epoch": 1.815126050420168,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 0.00012635871660690676,
+      "loss": 1.7735,
+      "step": 54
+    },
+    {
+      "epoch": 1.8487394957983194,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00012348860457809838,
+      "loss": 1.7956,
+      "step": 55
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 0.00012059786187410984,
+      "loss": 1.7674,
+      "step": 56
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "eval_loss": 1.8166663646697998,
+      "eval_runtime": 20.5178,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 56
+    },
+    {
+      "epoch": 1.9159663865546217,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.0001176890275122573,
+      "loss": 1.7228,
+      "step": 57
+    },
+    {
+      "epoch": 1.949579831932773,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00011476465640024814,
+      "loss": 1.7496,
+      "step": 58
+    },
+    {
+      "epoch": 1.9831932773109244,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.00011182731709213659,
+      "loss": 1.6776,
+      "step": 59
+    },
+    {
+      "epoch": 2.0168067226890756,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00010887958953229349,
+      "loss": 1.7346,
+      "step": 60
+    },
+    {
+      "epoch": 2.0504201680672267,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00010592406278937144,
+      "loss": 1.8371,
+      "step": 61
+    },
+    {
+      "epoch": 2.0840336134453783,
+      "grad_norm": 0.158203125,
+      "learning_rate": 0.00010296333278225599,
+      "loss": 1.7113,
+      "step": 62
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.0001,
+      "loss": 1.7299,
+      "step": 63
+    },
+    {
+      "epoch": 2.1512605042016806,
+      "grad_norm": 0.154296875,
+      "learning_rate": 9.703666721774402e-05,
+      "loss": 1.7164,
+      "step": 64
+    },
+    {
+      "epoch": 2.1512605042016806,
+      "eval_loss": 1.810401439666748,
+      "eval_runtime": 20.5114,
+      "eval_samples_per_second": 2.438,
+      "eval_steps_per_second": 0.341,
+      "step": 64
+    },
+    {
+      "epoch": 2.184873949579832,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 9.407593721062859e-05,
+      "loss": 1.746,
+      "step": 65
+    },
+    {
+      "epoch": 2.2184873949579833,
+      "grad_norm": 0.169921875,
+      "learning_rate": 9.112041046770653e-05,
+      "loss": 1.7507,
+      "step": 66
+    },
+    {
+      "epoch": 2.2521008403361344,
+      "grad_norm": 0.158203125,
+      "learning_rate": 8.817268290786343e-05,
+      "loss": 1.6836,
+      "step": 67
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.154296875,
+      "learning_rate": 8.523534359975189e-05,
+      "loss": 1.7432,
+      "step": 68
+    },
+    {
+      "epoch": 2.3193277310924367,
+      "grad_norm": 0.16796875,
+      "learning_rate": 8.231097248774274e-05,
+      "loss": 1.7734,
+      "step": 69
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 7.940213812589018e-05,
+      "loss": 1.6683,
+      "step": 70
+    },
+    {
+      "epoch": 2.3865546218487395,
+      "grad_norm": 0.154296875,
+      "learning_rate": 7.651139542190164e-05,
+      "loss": 1.6743,
+      "step": 71
+    },
+    {
+      "epoch": 2.4201680672268906,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 7.364128339309326e-05,
+      "loss": 1.6525,
+      "step": 72
+    },
+    {
+      "epoch": 2.4201680672268906,
+      "eval_loss": 1.806851863861084,
+      "eval_runtime": 20.4653,
+      "eval_samples_per_second": 2.443,
+      "eval_steps_per_second": 0.342,
+      "step": 72
+    },
+    {
+      "epoch": 2.453781512605042,
+      "grad_norm": 0.16015625,
+      "learning_rate": 7.079432293630244e-05,
+      "loss": 1.708,
+      "step": 73
+    },
+    {
+      "epoch": 2.4873949579831933,
+      "grad_norm": 0.16015625,
+      "learning_rate": 6.797301461371625e-05,
+      "loss": 1.6694,
+      "step": 74
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 0.162109375,
+      "learning_rate": 6.517983645656014e-05,
+      "loss": 1.5762,
+      "step": 75
+    },
+    {
+      "epoch": 2.5546218487394956,
+      "grad_norm": 0.1640625,
+      "learning_rate": 6.24172417885762e-05,
+      "loss": 1.7879,
+      "step": 76
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 5.96876570712028e-05,
+      "loss": 1.6566,
+      "step": 77
+    },
+    {
+      "epoch": 2.6218487394957983,
+      "grad_norm": 0.16015625,
+      "learning_rate": 5.699347977234799e-05,
+      "loss": 1.686,
+      "step": 78
+    },
+    {
+      "epoch": 2.6554621848739495,
+      "grad_norm": 0.158203125,
+      "learning_rate": 5.43370762606287e-05,
+      "loss": 1.7537,
+      "step": 79
+    },
+    {
+      "epoch": 2.689075630252101,
+      "grad_norm": 0.162109375,
+      "learning_rate": 5.172077972692553e-05,
+      "loss": 1.7917,
+      "step": 80
+    },
+    {
+      "epoch": 2.689075630252101,
+      "eval_loss": 1.805298924446106,
+      "eval_runtime": 20.4745,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 80
+    },
+    {
+      "epoch": 2.722689075630252,
+      "grad_norm": 0.166015625,
+      "learning_rate": 4.914688813507797e-05,
+      "loss": 1.7791,
+      "step": 81
+    },
+    {
+      "epoch": 2.7563025210084033,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 4.661766220352097e-05,
+      "loss": 1.7805,
+      "step": 82
+    },
+    {
+      "epoch": 2.7899159663865545,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 4.4135323419634766e-05,
+      "loss": 1.6505,
+      "step": 83
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.15625,
+      "learning_rate": 4.170205208855281e-05,
+      "loss": 1.6896,
+      "step": 84
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 3.931998541814069e-05,
+      "loss": 1.6374,
+      "step": 85
+    },
+    {
+      "epoch": 2.8907563025210083,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 3.69912156418289e-05,
+      "loss": 1.7444,
+      "step": 86
+    },
+    {
+      "epoch": 2.92436974789916,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 3.471778818094785e-05,
+      "loss": 1.7065,
+      "step": 87
+    },
+    {
+      "epoch": 2.957983193277311,
+      "grad_norm": 0.16796875,
+      "learning_rate": 3.250169984817897e-05,
+      "loss": 1.8022,
+      "step": 88
+    },
+    {
+      "epoch": 2.957983193277311,
+      "eval_loss": 1.8037484884262085,
+      "eval_runtime": 20.1207,
+      "eval_samples_per_second": 2.485,
+      "eval_steps_per_second": 0.348,
+      "step": 88
+    },
+    {
+      "epoch": 2.991596638655462,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 3.034489709370033e-05,
+      "loss": 1.7397,
+      "step": 89
+    },
+    {
+      "epoch": 3.0252100840336134,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 2.8249274295566864e-05,
+      "loss": 1.6042,
+      "step": 90
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.166015625,
+      "learning_rate": 2.6216672095827266e-05,
+      "loss": 1.6899,
+      "step": 91
+    },
+    {
+      "epoch": 3.092436974789916,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 2.4248875783837987e-05,
+      "loss": 1.7153,
+      "step": 92
+    },
+    {
+      "epoch": 3.1260504201680672,
+      "grad_norm": 0.162109375,
+      "learning_rate": 2.234761372819577e-05,
+      "loss": 1.7026,
+      "step": 93
+    },
+    {
+      "epoch": 3.1596638655462184,
+      "grad_norm": 0.15234375,
+      "learning_rate": 2.0514555858664663e-05,
+      "loss": 1.7049,
+      "step": 94
+    },
+    {
+      "epoch": 3.19327731092437,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.875131219943187e-05,
+      "loss": 1.6494,
+      "step": 95
+    },
+    {
+      "epoch": 3.226890756302521,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 1.7059431454979824e-05,
+      "loss": 1.6917,
+      "step": 96
+    },
+    {
+      "epoch": 3.226890756302521,
+      "eval_loss": 1.803171992301941,
+      "eval_runtime": 20.6532,
+      "eval_samples_per_second": 2.421,
+      "eval_steps_per_second": 0.339,
+      "step": 96
+    },
+    {
+      "epoch": 3.2605042016806722,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 1.5440399649817385e-05,
+      "loss": 1.7578,
+      "step": 97
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 1.3895638823264446e-05,
+      "loss": 1.7519,
+      "step": 98
+    },
+    {
+      "epoch": 3.327731092436975,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 1.2426505780436326e-05,
+      "loss": 1.7038,
+      "step": 99
+    },
+    {
+      "epoch": 3.361344537815126,
+      "grad_norm": 0.15234375,
+      "learning_rate": 1.103429090052528e-05,
+      "loss": 1.8117,
+      "step": 100
+    },
+    {
+      "epoch": 3.3949579831932772,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 9.720217003425647e-06,
+      "loss": 1.6114,
+      "step": 101
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.166015625,
+      "learning_rate": 8.485438275698154e-06,
+      "loss": 1.6631,
+      "step": 102
+    },
+    {
+      "epoch": 3.46218487394958,
+      "grad_norm": 0.158203125,
+      "learning_rate": 7.331039256816663e-06,
+      "loss": 1.6935,
+      "step": 103
+    },
+    {
+      "epoch": 3.495798319327731,
+      "grad_norm": 0.16796875,
+      "learning_rate": 6.258033886587911e-06,
+      "loss": 1.765,
+      "step": 104
+    },
+    {
+      "epoch": 3.495798319327731,
+      "eval_loss": 1.8030322790145874,
+      "eval_runtime": 20.1805,
+      "eval_samples_per_second": 2.478,
+      "eval_steps_per_second": 0.347,
+      "step": 104
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.158203125,
+      "learning_rate": 5.267364614580861e-06,
+      "loss": 1.7894,
+      "step": 105
+    },
+    {
+      "epoch": 3.5630252100840334,
+      "grad_norm": 0.162109375,
+      "learning_rate": 4.359901572347758e-06,
+      "loss": 1.7038,
+      "step": 106
+    },
+    {
+      "epoch": 3.596638655462185,
+      "grad_norm": 0.166015625,
+      "learning_rate": 3.5364418091641373e-06,
+      "loss": 1.7574,
+      "step": 107
+    },
+    {
+      "epoch": 3.630252100840336,
+      "grad_norm": 0.154296875,
+      "learning_rate": 2.7977085919589254e-06,
+      "loss": 1.6358,
+      "step": 108
+    },
+    {
+      "epoch": 3.6638655462184873,
+      "grad_norm": 0.15625,
+      "learning_rate": 2.144350770049597e-06,
+      "loss": 1.67,
+      "step": 109
+    },
+    {
+      "epoch": 3.697478991596639,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.576942205240317e-06,
+      "loss": 1.6081,
+      "step": 110
+    },
+    {
+      "epoch": 3.73109243697479,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.0959812677835968e-06,
+      "loss": 1.631,
+      "step": 111
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.1513671875,
+      "learning_rate": 7.018903986483083e-07,
+      "loss": 1.6784,
+      "step": 112
+    },
+    {
+      "epoch": 3.764705882352941,
+      "eval_loss": 1.803009033203125,
+      "eval_runtime": 20.0933,
+      "eval_samples_per_second": 2.488,
+      "eval_steps_per_second": 0.348,
+      "step": 112
+    },
+    {
+      "epoch": 3.7983193277310923,
+      "grad_norm": 0.16796875,
+      "learning_rate": 3.950157384783104e-07,
+      "loss": 1.6616,
+      "step": 113
+    },
+    {
+      "epoch": 3.831932773109244,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.7562682356786487e-07,
+      "loss": 1.7144,
+      "step": 114
+    },
+    {
+      "epoch": 3.865546218487395,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 4.391634912056519e-08,
+      "loss": 1.7248,
+      "step": 115
+    },
+    {
+      "epoch": 3.899159663865546,
+      "grad_norm": 0.162109375,
+      "learning_rate": 0.0,
+      "loss": 1.6563,
+      "step": 116
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 29,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3243100413820928e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-116/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37543517ebd16440b890dba9516abd772f75dbc4134102c3add23bd758d5df84
+size 6008

checkpoint-29/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Trisert/tinyllama-alpaca
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-29/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trisert/tinyllama-alpaca",
+  "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",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-29/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5495732593cdb0e01d67d0ff2a86f90be82d48db42670757f77ef06d98be5ff7
+size 50503848

checkpoint-29/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8846d0473e7a0d404f6622803fdcc9a3c5d15e01c00a84226a3c75f9ee3d189b
+size 202035450

checkpoint-29/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dff5ca7ee6d9737c0fb532125f4108aa3bd942be0c6c415c0eee299436cfee
+size 14244

checkpoint-29/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e0ea69a0f2d46a8611802e20de4ba9ab4c81307121d85f58745fed7e6bfae6
+size 1064

checkpoint-29/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-29/tokenizer.model

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

checkpoint-29/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-29/trainer_state.json

@@ -0,0 +1,268 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9747899159663865,
+  "eval_steps": 8,
+  "global_step": 29,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2e-05,
+      "loss": 2.6905,
+      "step": 1
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "eval_loss": 2.729154109954834,
+      "eval_runtime": 20.6566,
+      "eval_samples_per_second": 2.421,
+      "eval_steps_per_second": 0.339,
+      "step": 1
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4e-05,
+      "loss": 2.687,
+      "step": 2
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6e-05,
+      "loss": 2.8062,
+      "step": 3
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.03125,
+      "learning_rate": 8e-05,
+      "loss": 2.6619,
+      "step": 4
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5939,
+      "step": 5
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00012,
+      "loss": 2.6307,
+      "step": 6
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.00014,
+      "loss": 2.5751,
+      "step": 7
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00016,
+      "loss": 2.4725,
+      "step": 8
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "eval_loss": 2.3971643447875977,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00018,
+      "loss": 2.2905,
+      "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0002,
+      "loss": 2.3883,
+      "step": 10
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00019995608365087946,
+      "loss": 2.3071,
+      "step": 11
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.00019982437317643217,
+      "loss": 2.0817,
+      "step": 12
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001996049842615217,
+      "loss": 2.0883,
+      "step": 13
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019929810960135172,
+      "loss": 2.1018,
+      "step": 14
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001989040187322164,
+      "loss": 2.1015,
+      "step": 15
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019842305779475968,
+      "loss": 1.9891,
+      "step": 16
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "eval_loss": 2.071833610534668,
+      "eval_runtime": 20.5312,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 16
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001978556492299504,
+      "loss": 2.1245,
+      "step": 17
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.0001972022914080411,
+      "loss": 1.9485,
+      "step": 18
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.00019646355819083589,
+      "loss": 2.0621,
+      "step": 19
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00019564009842765225,
+      "loss": 1.9076,
+      "step": 20
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.00019473263538541914,
+      "loss": 1.8968,
+      "step": 21
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.0001937419661134121,
+      "loss": 1.8977,
+      "step": 22
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019266896074318334,
+      "loss": 1.9926,
+      "step": 23
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019151456172430183,
+      "loss": 1.8345,
+      "step": 24
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "eval_loss": 1.932895302772522,
+      "eval_runtime": 20.5148,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 24
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019027978299657436,
+      "loss": 1.8168,
+      "step": 25
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00018896570909947475,
+      "loss": 1.8794,
+      "step": 26
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001875734942195637,
+      "loss": 1.9604,
+      "step": 27
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00018610436117673555,
+      "loss": 1.824,
+      "step": 28
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001845596003501826,
+      "loss": 1.9186,
+      "step": 29
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 29,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3366220896141312.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-29/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37543517ebd16440b890dba9516abd772f75dbc4134102c3add23bd758d5df84
+size 6008

checkpoint-58/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Trisert/tinyllama-alpaca
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-58/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trisert/tinyllama-alpaca",
+  "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",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-58/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73751eecad8ff01e71f3de65328cf78fd56da01cb86dff74367031e97f45cece
+size 50503848

checkpoint-58/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0398c6a4cc7e82e3fb274ef0db75713d69e227ac26899c19b5735f61e975337a
+size 202035450

checkpoint-58/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2714773be96a258d965b3d5be5d9e51b91e01c435077d016f8a6cad6f5455b
+size 14244

checkpoint-58/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffd843f86241f649ae5523a8aa7c9d13157ef6bc9ba4fe819ec88f7f7923587
+size 1064

checkpoint-58/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-58/tokenizer.model

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

checkpoint-58/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-58/trainer_state.json

@@ -0,0 +1,503 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.949579831932773,
+  "eval_steps": 8,
+  "global_step": 58,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2e-05,
+      "loss": 2.6905,
+      "step": 1
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "eval_loss": 2.729154109954834,
+      "eval_runtime": 20.6566,
+      "eval_samples_per_second": 2.421,
+      "eval_steps_per_second": 0.339,
+      "step": 1
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4e-05,
+      "loss": 2.687,
+      "step": 2
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6e-05,
+      "loss": 2.8062,
+      "step": 3
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.03125,
+      "learning_rate": 8e-05,
+      "loss": 2.6619,
+      "step": 4
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5939,
+      "step": 5
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00012,
+      "loss": 2.6307,
+      "step": 6
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.00014,
+      "loss": 2.5751,
+      "step": 7
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00016,
+      "loss": 2.4725,
+      "step": 8
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "eval_loss": 2.3971643447875977,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00018,
+      "loss": 2.2905,
+      "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0002,
+      "loss": 2.3883,
+      "step": 10
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00019995608365087946,
+      "loss": 2.3071,
+      "step": 11
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.00019982437317643217,
+      "loss": 2.0817,
+      "step": 12
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001996049842615217,
+      "loss": 2.0883,
+      "step": 13
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019929810960135172,
+      "loss": 2.1018,
+      "step": 14
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001989040187322164,
+      "loss": 2.1015,
+      "step": 15
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019842305779475968,
+      "loss": 1.9891,
+      "step": 16
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "eval_loss": 2.071833610534668,
+      "eval_runtime": 20.5312,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 16
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001978556492299504,
+      "loss": 2.1245,
+      "step": 17
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.0001972022914080411,
+      "loss": 1.9485,
+      "step": 18
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.00019646355819083589,
+      "loss": 2.0621,
+      "step": 19
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00019564009842765225,
+      "loss": 1.9076,
+      "step": 20
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.00019473263538541914,
+      "loss": 1.8968,
+      "step": 21
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.0001937419661134121,
+      "loss": 1.8977,
+      "step": 22
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019266896074318334,
+      "loss": 1.9926,
+      "step": 23
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019151456172430183,
+      "loss": 1.8345,
+      "step": 24
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "eval_loss": 1.932895302772522,
+      "eval_runtime": 20.5148,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 24
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019027978299657436,
+      "loss": 1.8168,
+      "step": 25
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00018896570909947475,
+      "loss": 1.8794,
+      "step": 26
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001875734942195637,
+      "loss": 1.9604,
+      "step": 27
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00018610436117673555,
+      "loss": 1.824,
+      "step": 28
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001845596003501826,
+      "loss": 1.9186,
+      "step": 29
+    },
+    {
+      "epoch": 1.0084033613445378,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001829405685450202,
+      "loss": 1.9281,
+      "step": 30
+    },
+    {
+      "epoch": 1.0420168067226891,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018124868780056814,
+      "loss": 1.833,
+      "step": 31
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.00017948544414133534,
+      "loss": 1.8088,
+      "step": 32
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "eval_loss": 1.8729643821716309,
+      "eval_runtime": 20.5377,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 32
+    },
+    {
+      "epoch": 1.1092436974789917,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00017765238627180424,
+      "loss": 1.8401,
+      "step": 33
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 0.00017575112421616202,
+      "loss": 1.7736,
+      "step": 34
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.00017378332790417273,
+      "loss": 1.7875,
+      "step": 35
+    },
+    {
+      "epoch": 1.2100840336134453,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00017175072570443312,
+      "loss": 1.7743,
+      "step": 36
+    },
+    {
+      "epoch": 1.2436974789915967,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 0.00016965510290629972,
+      "loss": 1.8167,
+      "step": 37
+    },
+    {
+      "epoch": 1.2773109243697478,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 0.00016749830015182107,
+      "loss": 1.8317,
+      "step": 38
+    },
+    {
+      "epoch": 1.3109243697478992,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00016528221181905217,
+      "loss": 1.7498,
+      "step": 39
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 0.197265625,
+      "learning_rate": 0.00016300878435817113,
+      "loss": 1.8183,
+      "step": 40
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "eval_loss": 1.8429957628250122,
+      "eval_runtime": 20.5619,
+      "eval_samples_per_second": 2.432,
+      "eval_steps_per_second": 0.34,
+      "step": 40
+    },
+    {
+      "epoch": 1.3781512605042017,
+      "grad_norm": 0.193359375,
+      "learning_rate": 0.00016068001458185936,
+      "loss": 1.7504,
+      "step": 41
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001582979479114472,
+      "loss": 1.7476,
+      "step": 42
+    },
+    {
+      "epoch": 1.4453781512605042,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00015586467658036524,
+      "loss": 1.8082,
+      "step": 43
+    },
+    {
+      "epoch": 1.4789915966386555,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001533823377964791,
+      "loss": 1.6987,
+      "step": 44
+    },
+    {
+      "epoch": 1.5126050420168067,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 0.00015085311186492206,
+      "loss": 1.7417,
+      "step": 45
+    },
+    {
+      "epoch": 1.5462184873949578,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.00014827922027307451,
+      "loss": 1.779,
+      "step": 46
+    },
+    {
+      "epoch": 1.5798319327731094,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.0001456629237393713,
+      "loss": 1.7552,
+      "step": 47
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00014300652022765207,
+      "loss": 1.8004,
+      "step": 48
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "eval_loss": 1.8263332843780518,
+      "eval_runtime": 20.4305,
+      "eval_samples_per_second": 2.447,
+      "eval_steps_per_second": 0.343,
+      "step": 48
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014031234292879725,
+      "loss": 1.7857,
+      "step": 49
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.00013758275821142382,
+      "loss": 1.7193,
+      "step": 50
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 0.0001348201635434399,
+      "loss": 1.7734,
+      "step": 51
+    },
+    {
+      "epoch": 1.7478991596638656,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013202698538628376,
+      "loss": 1.7644,
+      "step": 52
+    },
+    {
+      "epoch": 1.7815126050420167,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00012920567706369758,
+      "loss": 1.8631,
+      "step": 53
+    },
+    {
+      "epoch": 1.815126050420168,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 0.00012635871660690676,
+      "loss": 1.7735,
+      "step": 54
+    },
+    {
+      "epoch": 1.8487394957983194,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00012348860457809838,
+      "loss": 1.7956,
+      "step": 55
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 0.00012059786187410984,
+      "loss": 1.7674,
+      "step": 56
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "eval_loss": 1.8166663646697998,
+      "eval_runtime": 20.5178,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 56
+    },
+    {
+      "epoch": 1.9159663865546217,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.0001176890275122573,
+      "loss": 1.7228,
+      "step": 57
+    },
+    {
+      "epoch": 1.949579831932773,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00011476465640024814,
+      "loss": 1.7496,
+      "step": 58
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 29,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6643321582387200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-58/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37543517ebd16440b890dba9516abd772f75dbc4134102c3add23bd758d5df84
+size 6008

checkpoint-87/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Trisert/tinyllama-alpaca
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-87/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Trisert/tinyllama-alpaca",
+  "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",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-87/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d733f241e248ce3212756ab5441a8acce96188bf122d016882fc5af309a002d
+size 50503848

checkpoint-87/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f1922bd159fd75b2e6aa9d8d2ee9e550c0f9e90edc4cdfc412550e11ae1498
+size 202035450

checkpoint-87/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abee6b45a92cc12ab71fa5ef10750e86110e096fada3acf2955d86fe41f121d3
+size 14244

checkpoint-87/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dfdc4ac2eb14a7a5283672324c02dd21283974614857cbf29d0d55e24e2b3f
+size 1064

checkpoint-87/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-87/tokenizer.model

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

checkpoint-87/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-87/trainer_state.json

@@ -0,0 +1,730 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.92436974789916,
+  "eval_steps": 8,
+  "global_step": 87,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2e-05,
+      "loss": 2.6905,
+      "step": 1
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "eval_loss": 2.729154109954834,
+      "eval_runtime": 20.6566,
+      "eval_samples_per_second": 2.421,
+      "eval_steps_per_second": 0.339,
+      "step": 1
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0390625,
+      "learning_rate": 4e-05,
+      "loss": 2.687,
+      "step": 2
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6e-05,
+      "loss": 2.8062,
+      "step": 3
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 1.03125,
+      "learning_rate": 8e-05,
+      "loss": 2.6619,
+      "step": 4
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5939,
+      "step": 5
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00012,
+      "loss": 2.6307,
+      "step": 6
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.86328125,
+      "learning_rate": 0.00014,
+      "loss": 2.5751,
+      "step": 7
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.82421875,
+      "learning_rate": 0.00016,
+      "loss": 2.4725,
+      "step": 8
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "eval_loss": 2.3971643447875977,
+      "eval_runtime": 20.4746,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 8
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.00018,
+      "loss": 2.2905,
+      "step": 9
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.0002,
+      "loss": 2.3883,
+      "step": 10
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00019995608365087946,
+      "loss": 2.3071,
+      "step": 11
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.00019982437317643217,
+      "loss": 2.0817,
+      "step": 12
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.0001996049842615217,
+      "loss": 2.0883,
+      "step": 13
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00019929810960135172,
+      "loss": 2.1018,
+      "step": 14
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.0001989040187322164,
+      "loss": 2.1015,
+      "step": 15
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019842305779475968,
+      "loss": 1.9891,
+      "step": 16
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "eval_loss": 2.071833610534668,
+      "eval_runtime": 20.5312,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 16
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001978556492299504,
+      "loss": 2.1245,
+      "step": 17
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 0.46875,
+      "learning_rate": 0.0001972022914080411,
+      "loss": 1.9485,
+      "step": 18
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 0.4140625,
+      "learning_rate": 0.00019646355819083589,
+      "loss": 2.0621,
+      "step": 19
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.00019564009842765225,
+      "loss": 1.9076,
+      "step": 20
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.4375,
+      "learning_rate": 0.00019473263538541914,
+      "loss": 1.8968,
+      "step": 21
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.0001937419661134121,
+      "loss": 1.8977,
+      "step": 22
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019266896074318334,
+      "loss": 1.9926,
+      "step": 23
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 0.27734375,
+      "learning_rate": 0.00019151456172430183,
+      "loss": 1.8345,
+      "step": 24
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "eval_loss": 1.932895302772522,
+      "eval_runtime": 20.5148,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 24
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.291015625,
+      "learning_rate": 0.00019027978299657436,
+      "loss": 1.8168,
+      "step": 25
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00018896570909947475,
+      "loss": 1.8794,
+      "step": 26
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001875734942195637,
+      "loss": 1.9604,
+      "step": 27
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00018610436117673555,
+      "loss": 1.824,
+      "step": 28
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.0001845596003501826,
+      "loss": 1.9186,
+      "step": 29
+    },
+    {
+      "epoch": 1.0084033613445378,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001829405685450202,
+      "loss": 1.9281,
+      "step": 30
+    },
+    {
+      "epoch": 1.0420168067226891,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018124868780056814,
+      "loss": 1.833,
+      "step": 31
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.00017948544414133534,
+      "loss": 1.8088,
+      "step": 32
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "eval_loss": 1.8729643821716309,
+      "eval_runtime": 20.5377,
+      "eval_samples_per_second": 2.435,
+      "eval_steps_per_second": 0.341,
+      "step": 32
+    },
+    {
+      "epoch": 1.1092436974789917,
+      "grad_norm": 0.29296875,
+      "learning_rate": 0.00017765238627180424,
+      "loss": 1.8401,
+      "step": 33
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.2451171875,
+      "learning_rate": 0.00017575112421616202,
+      "loss": 1.7736,
+      "step": 34
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.00017378332790417273,
+      "loss": 1.7875,
+      "step": 35
+    },
+    {
+      "epoch": 1.2100840336134453,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00017175072570443312,
+      "loss": 1.7743,
+      "step": 36
+    },
+    {
+      "epoch": 1.2436974789915967,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 0.00016965510290629972,
+      "loss": 1.8167,
+      "step": 37
+    },
+    {
+      "epoch": 1.2773109243697478,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 0.00016749830015182107,
+      "loss": 1.8317,
+      "step": 38
+    },
+    {
+      "epoch": 1.3109243697478992,
+      "grad_norm": 0.1796875,
+      "learning_rate": 0.00016528221181905217,
+      "loss": 1.7498,
+      "step": 39
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 0.197265625,
+      "learning_rate": 0.00016300878435817113,
+      "loss": 1.8183,
+      "step": 40
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "eval_loss": 1.8429957628250122,
+      "eval_runtime": 20.5619,
+      "eval_samples_per_second": 2.432,
+      "eval_steps_per_second": 0.34,
+      "step": 40
+    },
+    {
+      "epoch": 1.3781512605042017,
+      "grad_norm": 0.193359375,
+      "learning_rate": 0.00016068001458185936,
+      "loss": 1.7504,
+      "step": 41
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.0001582979479114472,
+      "loss": 1.7476,
+      "step": 42
+    },
+    {
+      "epoch": 1.4453781512605042,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00015586467658036524,
+      "loss": 1.8082,
+      "step": 43
+    },
+    {
+      "epoch": 1.4789915966386555,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001533823377964791,
+      "loss": 1.6987,
+      "step": 44
+    },
+    {
+      "epoch": 1.5126050420168067,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 0.00015085311186492206,
+      "loss": 1.7417,
+      "step": 45
+    },
+    {
+      "epoch": 1.5462184873949578,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.00014827922027307451,
+      "loss": 1.779,
+      "step": 46
+    },
+    {
+      "epoch": 1.5798319327731094,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 0.0001456629237393713,
+      "loss": 1.7552,
+      "step": 47
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "grad_norm": 0.1767578125,
+      "learning_rate": 0.00014300652022765207,
+      "loss": 1.8004,
+      "step": 48
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "eval_loss": 1.8263332843780518,
+      "eval_runtime": 20.4305,
+      "eval_samples_per_second": 2.447,
+      "eval_steps_per_second": 0.343,
+      "step": 48
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.19140625,
+      "learning_rate": 0.00014031234292879725,
+      "loss": 1.7857,
+      "step": 49
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 0.181640625,
+      "learning_rate": 0.00013758275821142382,
+      "loss": 1.7193,
+      "step": 50
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 0.0001348201635434399,
+      "loss": 1.7734,
+      "step": 51
+    },
+    {
+      "epoch": 1.7478991596638656,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00013202698538628376,
+      "loss": 1.7644,
+      "step": 52
+    },
+    {
+      "epoch": 1.7815126050420167,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00012920567706369758,
+      "loss": 1.8631,
+      "step": 53
+    },
+    {
+      "epoch": 1.815126050420168,
+      "grad_norm": 0.1845703125,
+      "learning_rate": 0.00012635871660690676,
+      "loss": 1.7735,
+      "step": 54
+    },
+    {
+      "epoch": 1.8487394957983194,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00012348860457809838,
+      "loss": 1.7956,
+      "step": 55
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 0.00012059786187410984,
+      "loss": 1.7674,
+      "step": 56
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "eval_loss": 1.8166663646697998,
+      "eval_runtime": 20.5178,
+      "eval_samples_per_second": 2.437,
+      "eval_steps_per_second": 0.341,
+      "step": 56
+    },
+    {
+      "epoch": 1.9159663865546217,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.0001176890275122573,
+      "loss": 1.7228,
+      "step": 57
+    },
+    {
+      "epoch": 1.949579831932773,
+      "grad_norm": 0.169921875,
+      "learning_rate": 0.00011476465640024814,
+      "loss": 1.7496,
+      "step": 58
+    },
+    {
+      "epoch": 1.9831932773109244,
+      "grad_norm": 0.173828125,
+      "learning_rate": 0.00011182731709213659,
+      "loss": 1.6776,
+      "step": 59
+    },
+    {
+      "epoch": 2.0168067226890756,
+      "grad_norm": 0.171875,
+      "learning_rate": 0.00010887958953229349,
+      "loss": 1.7346,
+      "step": 60
+    },
+    {
+      "epoch": 2.0504201680672267,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.00010592406278937144,
+      "loss": 1.8371,
+      "step": 61
+    },
+    {
+      "epoch": 2.0840336134453783,
+      "grad_norm": 0.158203125,
+      "learning_rate": 0.00010296333278225599,
+      "loss": 1.7113,
+      "step": 62
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.14453125,
+      "learning_rate": 0.0001,
+      "loss": 1.7299,
+      "step": 63
+    },
+    {
+      "epoch": 2.1512605042016806,
+      "grad_norm": 0.154296875,
+      "learning_rate": 9.703666721774402e-05,
+      "loss": 1.7164,
+      "step": 64
+    },
+    {
+      "epoch": 2.1512605042016806,
+      "eval_loss": 1.810401439666748,
+      "eval_runtime": 20.5114,
+      "eval_samples_per_second": 2.438,
+      "eval_steps_per_second": 0.341,
+      "step": 64
+    },
+    {
+      "epoch": 2.184873949579832,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 9.407593721062859e-05,
+      "loss": 1.746,
+      "step": 65
+    },
+    {
+      "epoch": 2.2184873949579833,
+      "grad_norm": 0.169921875,
+      "learning_rate": 9.112041046770653e-05,
+      "loss": 1.7507,
+      "step": 66
+    },
+    {
+      "epoch": 2.2521008403361344,
+      "grad_norm": 0.158203125,
+      "learning_rate": 8.817268290786343e-05,
+      "loss": 1.6836,
+      "step": 67
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.154296875,
+      "learning_rate": 8.523534359975189e-05,
+      "loss": 1.7432,
+      "step": 68
+    },
+    {
+      "epoch": 2.3193277310924367,
+      "grad_norm": 0.16796875,
+      "learning_rate": 8.231097248774274e-05,
+      "loss": 1.7734,
+      "step": 69
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 7.940213812589018e-05,
+      "loss": 1.6683,
+      "step": 70
+    },
+    {
+      "epoch": 2.3865546218487395,
+      "grad_norm": 0.154296875,
+      "learning_rate": 7.651139542190164e-05,
+      "loss": 1.6743,
+      "step": 71
+    },
+    {
+      "epoch": 2.4201680672268906,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 7.364128339309326e-05,
+      "loss": 1.6525,
+      "step": 72
+    },
+    {
+      "epoch": 2.4201680672268906,
+      "eval_loss": 1.806851863861084,
+      "eval_runtime": 20.4653,
+      "eval_samples_per_second": 2.443,
+      "eval_steps_per_second": 0.342,
+      "step": 72
+    },
+    {
+      "epoch": 2.453781512605042,
+      "grad_norm": 0.16015625,
+      "learning_rate": 7.079432293630244e-05,
+      "loss": 1.708,
+      "step": 73
+    },
+    {
+      "epoch": 2.4873949579831933,
+      "grad_norm": 0.16015625,
+      "learning_rate": 6.797301461371625e-05,
+      "loss": 1.6694,
+      "step": 74
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 0.162109375,
+      "learning_rate": 6.517983645656014e-05,
+      "loss": 1.5762,
+      "step": 75
+    },
+    {
+      "epoch": 2.5546218487394956,
+      "grad_norm": 0.1640625,
+      "learning_rate": 6.24172417885762e-05,
+      "loss": 1.7879,
+      "step": 76
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 5.96876570712028e-05,
+      "loss": 1.6566,
+      "step": 77
+    },
+    {
+      "epoch": 2.6218487394957983,
+      "grad_norm": 0.16015625,
+      "learning_rate": 5.699347977234799e-05,
+      "loss": 1.686,
+      "step": 78
+    },
+    {
+      "epoch": 2.6554621848739495,
+      "grad_norm": 0.158203125,
+      "learning_rate": 5.43370762606287e-05,
+      "loss": 1.7537,
+      "step": 79
+    },
+    {
+      "epoch": 2.689075630252101,
+      "grad_norm": 0.162109375,
+      "learning_rate": 5.172077972692553e-05,
+      "loss": 1.7917,
+      "step": 80
+    },
+    {
+      "epoch": 2.689075630252101,
+      "eval_loss": 1.805298924446106,
+      "eval_runtime": 20.4745,
+      "eval_samples_per_second": 2.442,
+      "eval_steps_per_second": 0.342,
+      "step": 80
+    },
+    {
+      "epoch": 2.722689075630252,
+      "grad_norm": 0.166015625,
+      "learning_rate": 4.914688813507797e-05,
+      "loss": 1.7791,
+      "step": 81
+    },
+    {
+      "epoch": 2.7563025210084033,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 4.661766220352097e-05,
+      "loss": 1.7805,
+      "step": 82
+    },
+    {
+      "epoch": 2.7899159663865545,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 4.4135323419634766e-05,
+      "loss": 1.6505,
+      "step": 83
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.15625,
+      "learning_rate": 4.170205208855281e-05,
+      "loss": 1.6896,
+      "step": 84
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 3.931998541814069e-05,
+      "loss": 1.6374,
+      "step": 85
+    },
+    {
+      "epoch": 2.8907563025210083,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 3.69912156418289e-05,
+      "loss": 1.7444,
+      "step": 86
+    },
+    {
+      "epoch": 2.92436974789916,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 3.471778818094785e-05,
+      "loss": 1.7065,
+      "step": 87
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 29,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9933851341357056.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}