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-chat
+model-index:
+- name: prem-1B-chat-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-chat
+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-chat-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-chat-32k
+
+This model is a fine-tuned version of [premai-io/prem-1B-chat](https://huggingface.co/premai-io/prem-1B-chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 6.9843
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5389        | 1.0   | 1    | 6.3469          |
+| 0.5389        | 2.0   | 2    | 6.2533          |
+| 0.5017        | 3.0   | 3    | 6.2101          |
+| 0.4689        | 4.0   | 4    | 6.3163          |
+| 0.3604        | 5.0   | 5    | 6.4144          |
+| 0.3107        | 6.0   | 6    | 6.4127          |
+| 0.2698        | 7.0   | 7    | 6.8089          |
+| 0.317         | 8.0   | 8    | 7.3388          |
+| 0.2228        | 9.0   | 9    | 6.5063          |
+| 0.1798        | 10.0  | 10   | 5.7073          |
+| 0.1436        | 11.0  | 11   | 5.1185          |
+| 0.1183        | 12.0  | 12   | 4.8994          |
+| 0.1002        | 13.0  | 13   | 4.8033          |
+| 0.0865        | 14.0  | 14   | 5.1707          |
+| 0.0758        | 15.0  | 15   | 5.7089          |
+| 0.0663        | 16.0  | 16   | 6.4052          |
+| 0.0601        | 17.0  | 17   | 6.7814          |
+| 0.0545        | 18.0  | 18   | 6.9586          |
+| 0.0505        | 19.0  | 19   | 6.9766          |
+| 0.0482        | 20.0  | 20   | 6.9843          |
+
+
+### 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-chat",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_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 sha256:7135deeefcca08872107b434a02562c5a9dac3b13a56ab57cc75e3239902610d
+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-chat
+---
+
+# 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-chat",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_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 sha256:429d4b9833ee74a769817e87156246f93d59b8e5f2c0005a7f4c54ce9185c2cc
+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 sha256:45948a18bf668fc96e5d74900efffa3532580dcf43bd2301cbd37767e647066a
+size 840750906

checkpoint-17/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0144d29b3aa536686955d800d4c2fbc02cd28bc58406f12c908e953d505b0599
+size 15984

checkpoint-17/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162eb503eadc6662930cd402ef3d374c715efd7d125618a790791d9797810b1b
+size 15984

checkpoint-17/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2394e747bb813a6d1bfbc44e9237ccfe9b853a8df8698425d0a7e9cb1d91323
+size 15984

checkpoint-17/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277646b3bc33d5d1436d12e505b95d751d7b570c4624fe8241f71b5332676ab9
+size 15984

checkpoint-17/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21da2fcbd3a47a9a85ba950b2038f33ab518c5b704739283c172c008d5f793d2
+size 15984

checkpoint-17/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69e26c10f0af352c47ed82a0d65bf10a83a49b05d570aab97a8d2c1d0d4af1e
+size 15984

checkpoint-17/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcfbf51cc278c927c0804927b31a315a90d582074859f6fe8cb4f48f4dbc012
+size 15984

checkpoint-17/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4075bb6912e855f8af330ecf75a6fe95857bd8d2b990ccb2e23ede0e9f0192f
+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": 30.875,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.5389,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.346914291381836,
+      "eval_runtime": 0.1184,
+      "eval_samples_per_second": 8.443,
+      "eval_steps_per_second": 8.443,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 30.75,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.5389,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.253310680389404,
+      "eval_runtime": 0.1196,
+      "eval_samples_per_second": 8.359,
+      "eval_steps_per_second": 8.359,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.875,
+      "learning_rate": 3e-06,
+      "loss": 0.5017,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.210088729858398,
+      "eval_runtime": 0.1203,
+      "eval_samples_per_second": 8.313,
+      "eval_steps_per_second": 8.313,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.40625,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4689,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.316311359405518,
+      "eval_runtime": 0.1184,
+      "eval_samples_per_second": 8.446,
+      "eval_steps_per_second": 8.446,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.578125,
+      "learning_rate": 5e-06,
+      "loss": 0.3604,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 6.414371967315674,
+      "eval_runtime": 0.1193,
+      "eval_samples_per_second": 8.381,
+      "eval_steps_per_second": 8.381,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.9375,
+      "learning_rate": 6e-06,
+      "loss": 0.3107,
+      "step": 6
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 6.412661075592041,
+      "eval_runtime": 0.1183,
+      "eval_samples_per_second": 8.452,
+      "eval_steps_per_second": 8.452,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 23.625,
+      "learning_rate": 7e-06,
+      "loss": 0.2698,
+      "step": 7
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 6.808929443359375,
+      "eval_runtime": 0.1187,
+      "eval_samples_per_second": 8.426,
+      "eval_steps_per_second": 8.426,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 30464.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.317,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 7.338753700256348,
+      "eval_runtime": 0.117,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 8.546,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 24.75,
+      "learning_rate": 9e-06,
+      "loss": 0.2228,
+      "step": 9
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 6.506290435791016,
+      "eval_runtime": 0.1168,
+      "eval_samples_per_second": 8.564,
+      "eval_steps_per_second": 8.564,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 12.0625,
+      "learning_rate": 1e-05,
+      "loss": 0.1798,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.707322597503662,
+      "eval_runtime": 0.1186,
+      "eval_samples_per_second": 8.429,
+      "eval_steps_per_second": 8.429,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.1436,
+      "step": 11
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 5.118520259857178,
+      "eval_runtime": 0.1191,
+      "eval_samples_per_second": 8.398,
+      "eval_steps_per_second": 8.398,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.6875,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.1183,
+      "step": 12
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 4.899399280548096,
+      "eval_runtime": 0.1192,
+      "eval_samples_per_second": 8.386,
+      "eval_steps_per_second": 8.386,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 4.34375,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.1002,
+      "step": 13
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 4.803285598754883,
+      "eval_runtime": 0.1193,
+      "eval_samples_per_second": 8.381,
+      "eval_steps_per_second": 8.381,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 3.484375,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.0865,
+      "step": 14
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 5.1707048416137695,
+      "eval_runtime": 0.1192,
+      "eval_samples_per_second": 8.389,
+      "eval_steps_per_second": 8.389,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.8125,
+      "learning_rate": 5e-06,
+      "loss": 0.0758,
+      "step": 15
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 5.70893669128418,
+      "eval_runtime": 0.1195,
+      "eval_samples_per_second": 8.367,
+      "eval_steps_per_second": 8.367,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.9375,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.0663,
+      "step": 16
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 6.405214786529541,
+      "eval_runtime": 0.117,
+      "eval_samples_per_second": 8.55,
+      "eval_steps_per_second": 8.55,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 2.859375,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.0601,
+      "step": 17
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 6.781367778778076,
+      "eval_runtime": 0.1172,
+      "eval_samples_per_second": 8.534,
+      "eval_steps_per_second": 8.534,
+      "step": 17
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 1,
+  "total_flos": 7722232348409856.0,
+  "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:d508e6d4d2b8eb66889892d260b92e88e08dc1b5ab24946a4250fb9740872226
+size 5816

checkpoint-18/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: premai-io/prem-1B-chat
+---
+
+# 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-chat",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_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 sha256:0dd3fedf3c4a75ca75514373145f9ebbada3bd2546ca417aaa84b6a058813d81
+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:a1d186515dc518c0dd7a70ed54ef07a141af9040208fa9d8f79795481811ce70
+size 840750906

checkpoint-18/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2fe07fc141185b9f19e2414387272d79d77494f1031aaf4aa846bf50ea73cd
+size 15984

checkpoint-18/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5909b51ce9c7cbb719e845e2e066d76cc02181ce1d72d30195ec11b21dad91fa
+size 15984

checkpoint-18/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00d99c6ac024ad42acd58b882ea646cdaf06a6fa906050e1b3a05e251f3ab10
+size 15984

checkpoint-18/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24714565707343103d95ee3b074ef5a488b0e0ecaf52bb5e750eee64c7f249f1
+size 15984

checkpoint-18/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf7cab6312bd07df65a5098300686d46b37d885f02dc6313fc60779cb93c31c
+size 15984

checkpoint-18/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e857341ff914bc44ce9ce0f261413755671028ae9b654baef3d55cc04d10780
+size 15984

checkpoint-18/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3237eaa8548970a8f4f917c067c18f4f15ab27a832a6f75a5ce324428c0803f9
+size 15984

checkpoint-18/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b7ccdc2c03793778b99097e87aa605fbed3a37fbe7489b7f57c097361a0a35
+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": 30.875,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.5389,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.346914291381836,
+      "eval_runtime": 0.1184,
+      "eval_samples_per_second": 8.443,
+      "eval_steps_per_second": 8.443,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 30.75,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.5389,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.253310680389404,
+      "eval_runtime": 0.1196,
+      "eval_samples_per_second": 8.359,
+      "eval_steps_per_second": 8.359,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 14.875,
+      "learning_rate": 3e-06,
+      "loss": 0.5017,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.210088729858398,
+      "eval_runtime": 0.1203,
+      "eval_samples_per_second": 8.313,
+      "eval_steps_per_second": 8.313,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.40625,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4689,
+      "step": 4
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.316311359405518,
+      "eval_runtime": 0.1184,
+      "eval_samples_per_second": 8.446,
+      "eval_steps_per_second": 8.446,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.578125,
+      "learning_rate": 5e-06,
+      "loss": 0.3604,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 6.414371967315674,
+      "eval_runtime": 0.1193,
+      "eval_samples_per_second": 8.381,
+      "eval_steps_per_second": 8.381,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.9375,
+      "learning_rate": 6e-06,
+      "loss": 0.3107,
+      "step": 6
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 6.412661075592041,
+      "eval_runtime": 0.1183,
+      "eval_samples_per_second": 8.452,
+      "eval_steps_per_second": 8.452,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 23.625,
+      "learning_rate": 7e-06,
+      "loss": 0.2698,
+      "step": 7
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 6.808929443359375,
+      "eval_runtime": 0.1187,
+      "eval_samples_per_second": 8.426,
+      "eval_steps_per_second": 8.426,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 30464.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.317,
+      "step": 8
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 7.338753700256348,
+      "eval_runtime": 0.117,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 8.546,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 24.75,
+      "learning_rate": 9e-06,
+      "loss": 0.2228,
+      "step": 9
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 6.506290435791016,
+      "eval_runtime": 0.1168,
+      "eval_samples_per_second": 8.564,
+      "eval_steps_per_second": 8.564,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 12.0625,
+      "learning_rate": 1e-05,
+      "loss": 0.1798,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 5.707322597503662,
+      "eval_runtime": 0.1186,
+      "eval_samples_per_second": 8.429,
+      "eval_steps_per_second": 8.429,
+      "step": 10
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.1436,
+      "step": 11
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 5.118520259857178,
+      "eval_runtime": 0.1191,
+      "eval_samples_per_second": 8.398,
+      "eval_steps_per_second": 8.398,
+      "step": 11
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 4.6875,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.1183,
+      "step": 12
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 4.899399280548096,
+      "eval_runtime": 0.1192,
+      "eval_samples_per_second": 8.386,
+      "eval_steps_per_second": 8.386,
+      "step": 12
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 4.34375,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.1002,
+      "step": 13
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 4.803285598754883,
+      "eval_runtime": 0.1193,
+      "eval_samples_per_second": 8.381,
+      "eval_steps_per_second": 8.381,
+      "step": 13
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 3.484375,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.0865,
+      "step": 14
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 5.1707048416137695,
+      "eval_runtime": 0.1192,
+      "eval_samples_per_second": 8.389,
+      "eval_steps_per_second": 8.389,
+      "step": 14
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 2.8125,
+      "learning_rate": 5e-06,
+      "loss": 0.0758,
+      "step": 15
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 5.70893669128418,
+      "eval_runtime": 0.1195,
+      "eval_samples_per_second": 8.367,
+      "eval_steps_per_second": 8.367,
+      "step": 15
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 1.9375,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.0663,
+      "step": 16
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 6.405214786529541,
+      "eval_runtime": 0.117,
+      "eval_samples_per_second": 8.55,
+      "eval_steps_per_second": 8.55,
+      "step": 16
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 2.859375,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.0601,
+      "step": 17
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 6.781367778778076,
+      "eval_runtime": 0.1172,
+      "eval_samples_per_second": 8.534,
+      "eval_steps_per_second": 8.534,
+      "step": 17
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 3.28125,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0545,
+      "step": 18
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 6.95858097076416,
+      "eval_runtime": 0.1189,
+      "eval_samples_per_second": 8.409,
+      "eval_steps_per_second": 8.409,
+      "step": 18
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 1,
+  "total_flos": 8176481310081024.0,
+  "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:d508e6d4d2b8eb66889892d260b92e88e08dc1b5ab24946a4250fb9740872226
+size 5816

checkpoint-19/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: premai-io/prem-1B-chat
+---
+
+# 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-chat",
+  "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": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_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:a070d0625f20f4bce7706416868adbb3fdd97b561ceb246f9c6d8a67ee449da3
+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:f73ad8ddc1a456af11694ddd13aa1d0fa5c10ea56c3d54664739c218af600d96
+size 840750906

checkpoint-19/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575a77d052e2350b0caeb1f6840005b8912c87ad8abbb4cf32b32f9e9efe4a1f
+size 15984