Upload folder using huggingface_hub

README.md

@@ -0,0 +1,157 @@
+---
+library_name: peft
+base_model: NousResearch/Yarn-Llama-2-13b-64k
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 62720bd2-5fc2-42cf-9d63-232986b215d6
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: NousResearch/Yarn-Llama-2-13b-64k
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - a65657e24ab10169_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/a65657e24ab10169_train_data.json
+  type:
+    field_input: text
+    field_instruction: title
+    field_output: category
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device: cuda
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: false
+hub_model_id: sn56b2/62720bd2-5fc2-42cf-9d63-232986b215d6
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 8
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 75GiB
+max_steps: 25
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/a65657e24ab10169_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 5
+sequence_len: 1024
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: 62720bd2-5fc2-42cf-9d63-232986b215d6
+wandb_project: god
+wandb_run: 62720bd2-5fc2-42cf-9d63-232986b215d6
+wandb_runid: 62720bd2-5fc2-42cf-9d63-232986b215d6
+warmup_steps: 5
+weight_decay: 0.1
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 62720bd2-5fc2-42cf-9d63-232986b215d6
+
+This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-13b-64k](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5460
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 5
+- training_steps: 25
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 29.9648       | 0.0001 | 1    | 8.5247          |
+| 29.0882       | 0.0002 | 3    | 8.5071          |
+| 26.2052       | 0.0003 | 6    | 8.2005          |
+| 29.4909       | 0.0005 | 9    | 6.9785          |
+| 21.833        | 0.0006 | 12   | 5.5870          |
+| 13.4687       | 0.0008 | 15   | 4.6250          |
+| 19.2738       | 0.0009 | 18   | 3.9614          |
+| 17.1181       | 0.0011 | 21   | 3.6350          |
+| 9.9624        | 0.0012 | 24   | 3.5460          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Yarn-Llama-2-13b-64k",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56360e8fbd4a130220197a69174e6513c595fb6d00c09b7248917fa999a2ab8f
+size 125375434

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891fbe8c868313d618adf2062499c8186267b83564c6e743aa94960c5dc5ae00
+size 125248064

config.json

@@ -0,0 +1,37 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NousResearch/Yarn-Llama-2-13b-64k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "NousResearch/Yarn-Llama-2-13b-64k--configuration_llama.LlamaConfig",
+    "AutoModelForCausalLM": "NousResearch/Yarn-Llama-2-13b-64k--modeling_llama_together_yarn.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 65536,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 16.0,
+    "finetuned": true,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "use_flash_attention": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/Yarn-Llama-2-13b-64k
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Yarn-Llama-2-13b-64k",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891fbe8c868313d618adf2062499c8186267b83564c6e743aa94960c5dc5ae00
+size 125248064

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0180944b694840c99825a4fd955e822af10b07ad66eb33b67ba066a130786126
+size 250819170

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3595217bebe3e5386f8b29e238d4a215ea8ad544e4be916ff8986e8f2877be
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0012675556456928458,
+  "eval_steps": 3,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.070222582771384e-05,
+      "grad_norm": 16.734760284423828,
+      "learning_rate": 2e-05,
+      "loss": 29.9648,
+      "step": 1
+    },
+    {
+      "epoch": 5.070222582771384e-05,
+      "eval_loss": 8.524748802185059,
+      "eval_runtime": 1510.4845,
+      "eval_samples_per_second": 5.498,
+      "eval_steps_per_second": 2.749,
+      "step": 1
+    },
+    {
+      "epoch": 0.00010140445165542768,
+      "grad_norm": 14.790090560913086,
+      "learning_rate": 4e-05,
+      "loss": 33.7103,
+      "step": 2
+    },
+    {
+      "epoch": 0.0001521066774831415,
+      "grad_norm": 14.030793190002441,
+      "learning_rate": 6e-05,
+      "loss": 29.0882,
+      "step": 3
+    },
+    {
+      "epoch": 0.0001521066774831415,
+      "eval_loss": 8.50710391998291,
+      "eval_runtime": 1519.8925,
+      "eval_samples_per_second": 5.464,
+      "eval_steps_per_second": 2.732,
+      "step": 3
+    },
+    {
+      "epoch": 0.00020280890331085536,
+      "grad_norm": 12.610204696655273,
+      "learning_rate": 8e-05,
+      "loss": 28.2266,
+      "step": 4
+    },
+    {
+      "epoch": 0.0002535111291385692,
+      "grad_norm": 16.985925674438477,
+      "learning_rate": 0.0001,
+      "loss": 35.9331,
+      "step": 5
+    },
+    {
+      "epoch": 0.000304213354966283,
+      "grad_norm": 12.154075622558594,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 26.2052,
+      "step": 6
+    },
+    {
+      "epoch": 0.000304213354966283,
+      "eval_loss": 8.200469017028809,
+      "eval_runtime": 1521.6515,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 2.729,
+      "step": 6
+    },
+    {
+      "epoch": 0.00035491558079399685,
+      "grad_norm": 25.15923500061035,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 41.4569,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004056178066217107,
+      "grad_norm": 21.290430068969727,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 26.694,
+      "step": 8
+    },
+    {
+      "epoch": 0.0004563200324494245,
+      "grad_norm": 23.049171447753906,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 29.4909,
+      "step": 9
+    },
+    {
+      "epoch": 0.0004563200324494245,
+      "eval_loss": 6.978517055511475,
+      "eval_runtime": 1521.0316,
+      "eval_samples_per_second": 5.46,
+      "eval_steps_per_second": 2.73,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005070222582771384,
+      "grad_norm": 26.38067054748535,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 34.6105,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005577244841048522,
+      "grad_norm": 24.686254501342773,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 23.0639,
+      "step": 11
+    },
+    {
+      "epoch": 0.000608426709932566,
+      "grad_norm": 22.281373977661133,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 21.833,
+      "step": 12
+    },
+    {
+      "epoch": 0.000608426709932566,
+      "eval_loss": 5.586967945098877,
+      "eval_runtime": 1519.8132,
+      "eval_samples_per_second": 5.464,
+      "eval_steps_per_second": 2.733,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006591289357602798,
+      "grad_norm": 164.1787567138672,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 20.3158,
+      "step": 13
+    },
+    {
+      "epoch": 0.0007098311615879937,
+      "grad_norm": 23.327159881591797,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 21.234,
+      "step": 14
+    },
+    {
+      "epoch": 0.0007605333874157076,
+      "grad_norm": 17.704011917114258,
+      "learning_rate": 5e-05,
+      "loss": 13.4687,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007605333874157076,
+      "eval_loss": 4.6250200271606445,
+      "eval_runtime": 1519.2183,
+      "eval_samples_per_second": 5.467,
+      "eval_steps_per_second": 2.734,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008112356132434214,
+      "grad_norm": 21.224292755126953,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 16.2957,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008619378390711352,
+      "grad_norm": 27.829790115356445,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 23.9581,
+      "step": 17
+    },
+    {
+      "epoch": 0.000912640064898849,
+      "grad_norm": 27.01038360595703,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 19.2738,
+      "step": 18
+    },
+    {
+      "epoch": 0.000912640064898849,
+      "eval_loss": 3.9614384174346924,
+      "eval_runtime": 1519.4201,
+      "eval_samples_per_second": 5.466,
+      "eval_steps_per_second": 2.733,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009633422907265629,
+      "grad_norm": 31.614938735961914,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 16.2201,
+      "step": 19
+    },
+    {
+      "epoch": 0.0010140445165542768,
+      "grad_norm": 30.133304595947266,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 13.2166,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010647467423819906,
+      "grad_norm": 30.905317306518555,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 17.1181,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010647467423819906,
+      "eval_loss": 3.6349897384643555,
+      "eval_runtime": 1521.227,
+      "eval_samples_per_second": 5.459,
+      "eval_steps_per_second": 2.73,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011154489682097045,
+      "grad_norm": 30.500104904174805,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.5841,
+      "step": 22
+    },
+    {
+      "epoch": 0.0011661511940374183,
+      "grad_norm": 33.284156799316406,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 17.699,
+      "step": 23
+    },
+    {
+      "epoch": 0.001216853419865132,
+      "grad_norm": 22.113712310791016,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 9.9624,
+      "step": 24
+    },
+    {
+      "epoch": 0.001216853419865132,
+      "eval_loss": 3.54598331451416,
+      "eval_runtime": 1519.2854,
+      "eval_samples_per_second": 5.466,
+      "eval_steps_per_second": 2.734,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012675556456928458,
+      "grad_norm": 35.23492431640625,
+      "learning_rate": 0.0,
+      "loss": 14.2806,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.390484150386688e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b307449656cfb6c65f3c87d376f66cb8c24810ebdc076bd45eecf9aa7ba214
+size 6712

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b307449656cfb6c65f3c87d376f66cb8c24810ebdc076bd45eecf9aa7ba214
+size 6712