Upload folder using huggingface_hub

README.md

@@ -0,0 +1,183 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: premai-io/prem-1B
+model-index:
+- name: prem-1B-32k
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: premai-io/prem-1B
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: argilla/distilabel-capybara-dpo-7k-binarized
+    type: orpo.chat_template
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.001
+output_dir: ./prem-1B-32k
+save_safetensors: true
+sequence_len: 8192
+sample_packing: false
+pad_to_sequence_len: false
+use_pose: true
+pose_max_context_len: 262144
+min_sample_len: 6144
+pose_num_chunks: 16
+curriculum_sampling: true
+
+overrides_of_model_config:
+  rope_theta: 500000.0
+  max_position_embeddings: 262144
+
+  # peft_use_dora: true
+adapter: lora
+peft_use_rslora: true
+lora_model_dir:
+lora_r: 1024
+lora_alpha: 1024
+lora_dropout: 0.1
+lora_target_modules:
+  - q_proj
+  - k_proj
+  - v_proj
+  - o_proj
+lora_modules_to_save:
+  - embed_tokens
+  - lm_head
+
+wandb_project:
+wandb_entity: 
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 20
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+max_grad_norm: 1.0
+adam_beta2: 0.95
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+sdp_attention:
+s2_attention:
+
+warmup_steps: 10
+evals_per_epoch: 8
+saves_per_epoch: 8
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|end_of_text|>
+
+
+
+```
+
+</details><br>
+
+# prem-1B-32k
+
+This model is a fine-tuned version of [premai-io/prem-1B](https://huggingface.co/premai-io/prem-1B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0059
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7672        | 1.0   | 1    | 3.0074          |
+| 0.7672        | 2.0   | 2    | 2.6057          |
+| 0.7422        | 3.0   | 3    | 2.2898          |
+| 0.7211        | 4.0   | 4    | 2.1453          |
+| 0.6591        | 5.0   | 5    | 1.6360          |
+| 0.4514        | 6.0   | 6    | 0.7589          |
+| 0.24          | 7.0   | 7    | 0.6621          |
+| 0.1584        | 8.0   | 8    | 0.8121          |
+| 0.1235        | 9.0   | 9    | 0.7538          |
+| 0.0998        | 10.0  | 10   | 0.7743          |
+| 0.0869        | 11.0  | 11   | 0.7771          |
+| 0.1692        | 12.0  | 12   | 0.8293          |
+| 0.0702        | 13.0  | 13   | 0.8939          |
+| 0.063         | 14.0  | 14   | 0.9582          |
+| 0.0567        | 15.0  | 15   | 0.9825          |
+| 0.052         | 16.0  | 16   | 0.9960          |
+| 0.0488        | 17.0  | 17   | 0.9883          |
+| 0.0457        | 18.0  | 18   | 1.0004          |
+| 0.0436        | 19.0  | 19   | 1.0056          |
+| 0.0427        | 20.0  | 20   | 1.0059          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "premai-io/prem-1B",
+  "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": 1024,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 1024,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a4fae6e643b0783a9b071a59c272f69d5ae23ecd7f4e6dbb67dcba7e5a1fe5
+size 1363297208

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|end_of_text|>": 32004,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

checkpoint-17/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: premai-io/prem-1B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-17/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "premai-io/prem-1B",
+  "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": 1024,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 1024,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-17/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e7eb9f4af7c7b74962bff3d761f61913bc3f331702e6951b4f7fba5a6ad6f9
+size 1363297208

checkpoint-17/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|end_of_text|>": 32004,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

checkpoint-17/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3851fde7907acf7362daac33c83e18a29cfd97e8d1c280297392830013fb8e8c
+size 840750906

checkpoint-17/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba234ca195f826fa5ba834af4c9429f87043762495c017cece37d8374766f43
+size 15984

checkpoint-17/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecc0b6f5f63d576fab29439bbd01eb08f8fd5f6ef89b12dff17663853be372b
+size 15984

checkpoint-17/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba2f8f1bbc48d1716cafb36b8cbfc5a96399f041a3c0a6e767e073df6370fb19
+size 15984

checkpoint-17/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa28eda891f53d354254b40327f8c9d9eea057a86dd116ecfbf780837aaad93
+size 15984

checkpoint-17/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76725b4eb620d489395fcb1e91472687abc9dd281316dcfd1e6a80e84883a8ab
+size 15984

checkpoint-17/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f067fae64dab66de42be701839e0136598b609c41bbf43417cae9bde8c47ed
+size 15984

checkpoint-17/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c184ae9a08d2d24fd0d25b6b323dbfd1a8513317e7cce0b06c636c33ace69e29
+size 15984

checkpoint-17/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f007df36bbb4e4328af9a38cb0deb66a85bda8cbb4325fd2de5fea0d2bae1f9
+size 15984

checkpoint-17/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518cef45dd81f607851d009435a1218b0af33b1e066e2a5044e24b54f1a3c316
+size 1064

checkpoint-17/special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-17/tokenizer.model

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

checkpoint-17/tokenizer_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-17/trainer_state.json

@@ -0,0 +1,276 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 17.0,
+  "eval_steps": 1,
+  "global_step": 17,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.5,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7672,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0074498653411865,
+      "eval_runtime": 0.1009,
+      "eval_samples_per_second": 9.911,
+      "eval_steps_per_second": 9.911,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.5625,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.7672,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.6057260036468506,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.839,
+      "eval_steps_per_second": 9.839,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.84375,
+      "learning_rate": 3e-06,
+      "loss": 0.7422,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.2898356914520264,
+      "eval_runtime": 0.1036,
+      "eval_samples_per_second": 9.649,
+      "eval_steps_per_second": 9.649,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.7211,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.14534854888916,
+      "eval_runtime": 0.1037,
+      "eval_samples_per_second": 9.647,
+      "eval_steps_per_second": 9.647,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 72.0,
+      "learning_rate": 5e-06,
+      "loss": 0.6591,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.636004090309143,
+      "eval_runtime": 0.1032,
+      "eval_samples_per_second": 9.688,
+      "eval_steps_per_second": 9.688,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 53.25,
+      "learning_rate": 6e-06,
+      "loss": 0.4514,
+      "step": 6
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.7588775753974915,
+      "eval_runtime": 0.1037,
+      "eval_samples_per_second": 9.646,
+      "eval_steps_per_second": 9.646,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 26.625,
+      "learning_rate": 7e-06,
+      "loss": 0.24,
+      "step": 7
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.6620572805404663,
+      "eval_runtime": 0.1031,
+      "eval_samples_per_second": 9.703,
+      "eval_steps_per_second": 9.703,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 23.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1584,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8120734691619873,
+      "eval_runtime": 0.1013,
+      "eval_samples_per_second": 9.872,
+      "eval_steps_per_second": 9.872,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 21.25,
+      "learning_rate": 9e-06,
+      "loss": 0.1235,
+      "step": 9
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.7537858486175537,
+      "eval_runtime": 0.102,
+      "eval_samples_per_second": 9.8,
+      "eval_steps_per_second": 9.8,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 9.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0998,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7743023037910461,
+      "eval_runtime": 0.103,
+      "eval_samples_per_second": 9.708,
+      "eval_steps_per_second": 9.708,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 7.3125,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.0869,
+      "step": 11
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.7770701050758362,
+      "eval_runtime": 0.1025,
+      "eval_samples_per_second": 9.756,
+      "eval_steps_per_second": 9.756,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.625,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.1692,
+      "step": 12
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.8292599320411682,
+      "eval_runtime": 0.1014,
+      "eval_samples_per_second": 9.862,
+      "eval_steps_per_second": 9.862,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 2.28125,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.0702,
+      "step": 13
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.8938868045806885,
+      "eval_runtime": 0.1028,
+      "eval_samples_per_second": 9.729,
+      "eval_steps_per_second": 9.729,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.984375,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.063,
+      "step": 14
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.9581525325775146,
+      "eval_runtime": 0.1015,
+      "eval_samples_per_second": 9.856,
+      "eval_steps_per_second": 9.856,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5e-06,
+      "loss": 0.0567,
+      "step": 15
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.9825366139411926,
+      "eval_runtime": 0.1012,
+      "eval_samples_per_second": 9.886,
+      "eval_steps_per_second": 9.886,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.640625,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.052,
+      "step": 16
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.9959811568260193,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.843,
+      "eval_steps_per_second": 9.843,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.0488,
+      "step": 17
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.9883414506912231,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.844,
+      "eval_steps_per_second": 9.844,
+      "step": 17
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 1,
+  "total_flos": 8411070007869440.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-17/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42851d2f3d29130f0388bf1708f72e0e5be2ff98c3f953c50d68b6a6b7839d34
+size 5816

checkpoint-18/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: premai-io/prem-1B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-18/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "premai-io/prem-1B",
+  "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": 1024,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 1024,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cadbbfe91a496beef8af8f5e4f4a5a3ba62f38cd35508dc1fc23e30744b7372
+size 1363297208

checkpoint-18/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|end_of_text|>": 32004,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707118e7d3726d6b6ba25fbffeaf3f4dc0e30755db1b83e28dc7b85685b05b8c
+size 840750906

checkpoint-18/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93947f8643d5a05954703728371b4855d29ab0863b745691f0c7e527a1910e36
+size 15984

checkpoint-18/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc44eb6ad4fd0f3f2cf50306ec5b394f1eceac68de422b79a12bf534cc53567
+size 15984

checkpoint-18/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638ee349dc227ba9b558541defcd336579b77675ca0a579442e390f7d24afdf8
+size 15984

checkpoint-18/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebbaa3d1c3233f92a7cbaec88819f4a1ffd23a6495f8718491dabc42517791d
+size 15984

checkpoint-18/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2cf9fa5a5ee589c853505844354382bb49b0af7638a6c8f344a33d52e23abb7
+size 15984

checkpoint-18/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d20ace4e92813f34ee251fd03c61aa4e9141930c088e08436ca1bd5534de6e
+size 15984

checkpoint-18/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2558384f7890a852b9c680ba434e6b4269771b8d10b576daf7baaeab4e4999cd
+size 15984

checkpoint-18/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825852be9fdd5aa956bf6336fae47c80511d0231cdabedca3160bde0095ccb24
+size 15984

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ef15f031037bd60728c1910535c3dfb92b0e61b4f5e777814e95a9d1502d77
+size 1064

checkpoint-18/special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-18/tokenizer.model

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

checkpoint-18/tokenizer_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_header_id|>",
+    "<|end_header_id|>",
+    "<|eot_id|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-18/trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 18.0,
+  "eval_steps": 1,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.5,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7672,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0074498653411865,
+      "eval_runtime": 0.1009,
+      "eval_samples_per_second": 9.911,
+      "eval_steps_per_second": 9.911,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.5625,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.7672,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.6057260036468506,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.839,
+      "eval_steps_per_second": 9.839,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.84375,
+      "learning_rate": 3e-06,
+      "loss": 0.7422,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.2898356914520264,
+      "eval_runtime": 0.1036,
+      "eval_samples_per_second": 9.649,
+      "eval_steps_per_second": 9.649,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 10.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.7211,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.14534854888916,
+      "eval_runtime": 0.1037,
+      "eval_samples_per_second": 9.647,
+      "eval_steps_per_second": 9.647,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 72.0,
+      "learning_rate": 5e-06,
+      "loss": 0.6591,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.636004090309143,
+      "eval_runtime": 0.1032,
+      "eval_samples_per_second": 9.688,
+      "eval_steps_per_second": 9.688,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 53.25,
+      "learning_rate": 6e-06,
+      "loss": 0.4514,
+      "step": 6
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.7588775753974915,
+      "eval_runtime": 0.1037,
+      "eval_samples_per_second": 9.646,
+      "eval_steps_per_second": 9.646,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 26.625,
+      "learning_rate": 7e-06,
+      "loss": 0.24,
+      "step": 7
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.6620572805404663,
+      "eval_runtime": 0.1031,
+      "eval_samples_per_second": 9.703,
+      "eval_steps_per_second": 9.703,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 23.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1584,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8120734691619873,
+      "eval_runtime": 0.1013,
+      "eval_samples_per_second": 9.872,
+      "eval_steps_per_second": 9.872,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 21.25,
+      "learning_rate": 9e-06,
+      "loss": 0.1235,
+      "step": 9
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.7537858486175537,
+      "eval_runtime": 0.102,
+      "eval_samples_per_second": 9.8,
+      "eval_steps_per_second": 9.8,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 9.75,
+      "learning_rate": 1e-05,
+      "loss": 0.0998,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.7743023037910461,
+      "eval_runtime": 0.103,
+      "eval_samples_per_second": 9.708,
+      "eval_steps_per_second": 9.708,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 7.3125,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.0869,
+      "step": 11
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.7770701050758362,
+      "eval_runtime": 0.1025,
+      "eval_samples_per_second": 9.756,
+      "eval_steps_per_second": 9.756,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.625,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.1692,
+      "step": 12
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.8292599320411682,
+      "eval_runtime": 0.1014,
+      "eval_samples_per_second": 9.862,
+      "eval_steps_per_second": 9.862,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 2.28125,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.0702,
+      "step": 13
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.8938868045806885,
+      "eval_runtime": 0.1028,
+      "eval_samples_per_second": 9.729,
+      "eval_steps_per_second": 9.729,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.984375,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.063,
+      "step": 14
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.9581525325775146,
+      "eval_runtime": 0.1015,
+      "eval_samples_per_second": 9.856,
+      "eval_steps_per_second": 9.856,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5e-06,
+      "loss": 0.0567,
+      "step": 15
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.9825366139411926,
+      "eval_runtime": 0.1012,
+      "eval_samples_per_second": 9.886,
+      "eval_steps_per_second": 9.886,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.640625,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.052,
+      "step": 16
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.9959811568260193,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.843,
+      "eval_steps_per_second": 9.843,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.0488,
+      "step": 17
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.9883414506912231,
+      "eval_runtime": 0.1016,
+      "eval_samples_per_second": 9.844,
+      "eval_steps_per_second": 9.844,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0457,
+      "step": 18
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.0003694295883179,
+      "eval_runtime": 0.1045,
+      "eval_samples_per_second": 9.568,
+      "eval_steps_per_second": 9.568,
+      "step": 18
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 1,
+  "total_flos": 8905838831861760.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42851d2f3d29130f0388bf1708f72e0e5be2ff98c3f953c50d68b6a6b7839d34
+size 5816

checkpoint-19/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: premai-io/prem-1B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

checkpoint-19/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "premai-io/prem-1B",
+  "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": 1024,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 1024,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-19/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78e676c7a92e7c0b5d86c901f83c668195628c5862c94a42269ce23a773fa27
+size 1363297208

checkpoint-19/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|end_header_id|>": 32001,
+  "<|end_of_text|>": 32004,
+  "<|eot_id|>": 32002,
+  "<|start_header_id|>": 32000,
+  "[PAD]": 32003
+}

checkpoint-19/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2717f9274d707ff202402b697ecffa620019a337b4a9ab52ea210f18ee2d197
+size 840750906

checkpoint-19/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6eb9dc120f77e5ca03527fc2bcc53fd7063acc021a2e640485b622708f593a
+size 15984