End of training

README.md

@@ -0,0 +1,161 @@
+---
+library_name: peft
+base_model: NousResearch/Yarn-Llama-2-7b-128k
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 3ed5d45e-b05d-4a7e-9627-111a1d0bf345
+  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-2-7b-128k
+bf16: true
+chat_template: llama3
+datasets:
+- data_files:
+  - 511cf02a0f587430_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/511cf02a0f587430_train_data.json
+  type:
+    field_input: fewshot_prompt
+    field_instruction: question
+    field_output: answer
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: sn56m2/3ed5d45e-b05d-4a7e-9627-111a1d0bf345
+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: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 77GiB
+max_steps: 100
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/511cf02a0f587430_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: 25
+save_strategy: steps
+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: 3ed5d45e-b05d-4a7e-9627-111a1d0bf345
+wandb_project: god
+wandb_run: pkal
+wandb_runid: 3ed5d45e-b05d-4a7e-9627-111a1d0bf345
+warmup_steps: 10
+weight_decay: 0.01
+xformers_attention: false
+
+```
+
+</details><br>
+
+# 3ed5d45e-b05d-4a7e-9627-111a1d0bf345
+
+This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-128k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-128k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5047
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- 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: 10
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.7626        | 0.0020 | 1    | 1.3569          |
+| 2.2238        | 0.0176 | 9    | 1.0849          |
+| 1.4718        | 0.0353 | 18   | 0.7200          |
+| 1.1964        | 0.0529 | 27   | 0.6320          |
+| 1.1329        | 0.0705 | 36   | 0.5820          |
+| 1.1189        | 0.0881 | 45   | 0.5556          |
+| 0.9429        | 0.1058 | 54   | 0.5331          |
+| 1.2145        | 0.1234 | 63   | 0.5194          |
+| 1.0349        | 0.1410 | 72   | 0.5107          |
+| 1.1178        | 0.1587 | 81   | 0.5065          |
+| 0.7792        | 0.1763 | 90   | 0.5049          |
+| 1.0804        | 0.1939 | 99   | 0.5047          |
+
+
+### 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-2-7b-128k",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_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 sha256:574dc32501df0b6ba6de6c83ed05d08fee20a484b3985f0b5c7c721a173878fc
+size 160069834

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeccf3fcb866f7fac8d7ee18306a772da2bd946ebd8cb937b446c0baac697248
+size 159967880

config.json

@@ -0,0 +1,37 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NousResearch/Yarn-Llama-2-7b-128k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "NousResearch/Yarn-Llama-2-7b-128k--configuration_llama.LlamaConfig",
+    "AutoModelForCausalLM": "NousResearch/Yarn-Llama-2-7b-128k--modeling_llama_together_yarn.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 131072,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "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-2-7b-128k
+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-2-7b-128k",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_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:aeccf3fcb866f7fac8d7ee18306a772da2bd946ebd8cb937b446c0baac697248
+size 159967880

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:777d9f1d73c18ad2066ed7c7fa3c1127ca6ba3f18ae99235d377573477d9b640
+size 320194002

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d665228d5c674a5322354b2cbabcdb77447213d0273363aa47e9189b164a4bf9
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+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 +1,829 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1958863858961802,
+  "eval_steps": 9,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019588638589618022,
+      "grad_norm": 1.6968050003051758,
+      "learning_rate": 1e-05,
+      "loss": 2.7626,
+      "step": 1
+    },
+    {
+      "epoch": 0.0019588638589618022,
+      "eval_loss": 1.3569356203079224,
+      "eval_runtime": 77.4393,
+      "eval_samples_per_second": 5.553,
+      "eval_steps_per_second": 0.697,
+      "step": 1
+    },
+    {
+      "epoch": 0.0039177277179236044,
+      "grad_norm": 1.5743095874786377,
+      "learning_rate": 2e-05,
+      "loss": 2.5803,
+      "step": 2
+    },
+    {
+      "epoch": 0.005876591576885406,
+      "grad_norm": 1.4882086515426636,
+      "learning_rate": 3e-05,
+      "loss": 2.6338,
+      "step": 3
+    },
+    {
+      "epoch": 0.007835455435847209,
+      "grad_norm": 1.3662413358688354,
+      "learning_rate": 4e-05,
+      "loss": 2.5735,
+      "step": 4
+    },
+    {
+      "epoch": 0.009794319294809012,
+      "grad_norm": 1.5837461948394775,
+      "learning_rate": 5e-05,
+      "loss": 2.6477,
+      "step": 5
+    },
+    {
+      "epoch": 0.011753183153770812,
+      "grad_norm": 1.6326932907104492,
+      "learning_rate": 6e-05,
+      "loss": 2.6416,
+      "step": 6
+    },
+    {
+      "epoch": 0.013712047012732615,
+      "grad_norm": 2.0311954021453857,
+      "learning_rate": 7e-05,
+      "loss": 2.6862,
+      "step": 7
+    },
+    {
+      "epoch": 0.015670910871694418,
+      "grad_norm": 1.5801018476486206,
+      "learning_rate": 8e-05,
+      "loss": 2.3037,
+      "step": 8
+    },
+    {
+      "epoch": 0.01762977473065622,
+      "grad_norm": 1.6803339719772339,
+      "learning_rate": 9e-05,
+      "loss": 2.2238,
+      "step": 9
+    },
+    {
+      "epoch": 0.01762977473065622,
+      "eval_loss": 1.0849395990371704,
+      "eval_runtime": 77.7128,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 9
+    },
+    {
+      "epoch": 0.019588638589618023,
+      "grad_norm": 2.0442919731140137,
+      "learning_rate": 0.0001,
+      "loss": 2.2401,
+      "step": 10
+    },
+    {
+      "epoch": 0.021547502448579822,
+      "grad_norm": 1.5194798707962036,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 2.0831,
+      "step": 11
+    },
+    {
+      "epoch": 0.023506366307541625,
+      "grad_norm": 1.431047797203064,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.9413,
+      "step": 12
+    },
+    {
+      "epoch": 0.025465230166503428,
+      "grad_norm": 1.4518091678619385,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 1.8144,
+      "step": 13
+    },
+    {
+      "epoch": 0.02742409402546523,
+      "grad_norm": 1.4439371824264526,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 1.7324,
+      "step": 14
+    },
+    {
+      "epoch": 0.029382957884427033,
+      "grad_norm": 1.3911993503570557,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.635,
+      "step": 15
+    },
+    {
+      "epoch": 0.031341821743388835,
+      "grad_norm": 1.4029191732406616,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.7204,
+      "step": 16
+    },
+    {
+      "epoch": 0.03330068560235064,
+      "grad_norm": 1.4992731809616089,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 1.6266,
+      "step": 17
+    },
+    {
+      "epoch": 0.03525954946131244,
+      "grad_norm": 1.3220841884613037,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.4718,
+      "step": 18
+    },
+    {
+      "epoch": 0.03525954946131244,
+      "eval_loss": 0.7200331687927246,
+      "eval_runtime": 77.7436,
+      "eval_samples_per_second": 5.531,
+      "eval_steps_per_second": 0.695,
+      "step": 18
+    },
+    {
+      "epoch": 0.03721841332027424,
+      "grad_norm": 1.2800354957580566,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.2747,
+      "step": 19
+    },
+    {
+      "epoch": 0.039177277179236046,
+      "grad_norm": 1.0899313688278198,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 1.2156,
+      "step": 20
+    },
+    {
+      "epoch": 0.04113614103819784,
+      "grad_norm": 1.364983320236206,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 1.2787,
+      "step": 21
+    },
+    {
+      "epoch": 0.043095004897159644,
+      "grad_norm": 1.386749267578125,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.4594,
+      "step": 22
+    },
+    {
+      "epoch": 0.04505386875612145,
+      "grad_norm": 1.2778769731521606,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 1.3377,
+      "step": 23
+    },
+    {
+      "epoch": 0.04701273261508325,
+      "grad_norm": 1.236050009727478,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 1.2467,
+      "step": 24
+    },
+    {
+      "epoch": 0.04897159647404505,
+      "grad_norm": 1.1703822612762451,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.2772,
+      "step": 25
+    },
+    {
+      "epoch": 0.050930460333006855,
+      "grad_norm": 1.2760695219039917,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.2584,
+      "step": 26
+    },
+    {
+      "epoch": 0.05288932419196866,
+      "grad_norm": 1.3161894083023071,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.1964,
+      "step": 27
+    },
+    {
+      "epoch": 0.05288932419196866,
+      "eval_loss": 0.6319804191589355,
+      "eval_runtime": 77.7626,
+      "eval_samples_per_second": 5.53,
+      "eval_steps_per_second": 0.694,
+      "step": 27
+    },
+    {
+      "epoch": 0.05484818805093046,
+      "grad_norm": 1.4488955736160278,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.3106,
+      "step": 28
+    },
+    {
+      "epoch": 0.05680705190989226,
+      "grad_norm": 1.305700421333313,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1911,
+      "step": 29
+    },
+    {
+      "epoch": 0.058765915768854066,
+      "grad_norm": 0.9763986468315125,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.1847,
+      "step": 30
+    },
+    {
+      "epoch": 0.06072477962781587,
+      "grad_norm": 1.1714086532592773,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.2101,
+      "step": 31
+    },
+    {
+      "epoch": 0.06268364348677767,
+      "grad_norm": 1.1862618923187256,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.3224,
+      "step": 32
+    },
+    {
+      "epoch": 0.06464250734573947,
+      "grad_norm": 1.2496484518051147,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.1958,
+      "step": 33
+    },
+    {
+      "epoch": 0.06660137120470128,
+      "grad_norm": 1.2295827865600586,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.141,
+      "step": 34
+    },
+    {
+      "epoch": 0.06856023506366307,
+      "grad_norm": 1.356821060180664,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.3449,
+      "step": 35
+    },
+    {
+      "epoch": 0.07051909892262488,
+      "grad_norm": 0.9776789546012878,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.1329,
+      "step": 36
+    },
+    {
+      "epoch": 0.07051909892262488,
+      "eval_loss": 0.5819911956787109,
+      "eval_runtime": 77.7054,
+      "eval_samples_per_second": 5.534,
+      "eval_steps_per_second": 0.695,
+      "step": 36
+    },
+    {
+      "epoch": 0.07247796278158668,
+      "grad_norm": 1.0513958930969238,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.1187,
+      "step": 37
+    },
+    {
+      "epoch": 0.07443682664054849,
+      "grad_norm": 1.1003583669662476,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.2999,
+      "step": 38
+    },
+    {
+      "epoch": 0.07639569049951028,
+      "grad_norm": 1.393884301185608,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.3398,
+      "step": 39
+    },
+    {
+      "epoch": 0.07835455435847209,
+      "grad_norm": 0.9188857078552246,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.1988,
+      "step": 40
+    },
+    {
+      "epoch": 0.08031341821743389,
+      "grad_norm": 0.9523728489875793,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.2676,
+      "step": 41
+    },
+    {
+      "epoch": 0.08227228207639568,
+      "grad_norm": 0.8900655508041382,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.2159,
+      "step": 42
+    },
+    {
+      "epoch": 0.0842311459353575,
+      "grad_norm": 0.9669986963272095,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.3028,
+      "step": 43
+    },
+    {
+      "epoch": 0.08619000979431929,
+      "grad_norm": 0.9369410872459412,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.0016,
+      "step": 44
+    },
+    {
+      "epoch": 0.0881488736532811,
+      "grad_norm": 0.950991153717041,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.1189,
+      "step": 45
+    },
+    {
+      "epoch": 0.0881488736532811,
+      "eval_loss": 0.5556212663650513,
+      "eval_runtime": 77.7056,
+      "eval_samples_per_second": 5.534,
+      "eval_steps_per_second": 0.695,
+      "step": 45
+    },
+    {
+      "epoch": 0.0901077375122429,
+      "grad_norm": 1.0693860054016113,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.0666,
+      "step": 46
+    },
+    {
+      "epoch": 0.0920666013712047,
+      "grad_norm": 0.9803517460823059,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.0236,
+      "step": 47
+    },
+    {
+      "epoch": 0.0940254652301665,
+      "grad_norm": 1.1268558502197266,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.0705,
+      "step": 48
+    },
+    {
+      "epoch": 0.09598432908912831,
+      "grad_norm": 0.9862860441207886,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.9917,
+      "step": 49
+    },
+    {
+      "epoch": 0.0979431929480901,
+      "grad_norm": 1.0441433191299438,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.1169,
+      "step": 50
+    },
+    {
+      "epoch": 0.09990205680705191,
+      "grad_norm": 1.0051071643829346,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.9685,
+      "step": 51
+    },
+    {
+      "epoch": 0.10186092066601371,
+      "grad_norm": 0.9177164435386658,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.9734,
+      "step": 52
+    },
+    {
+      "epoch": 0.10381978452497552,
+      "grad_norm": 1.0885511636734009,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.1075,
+      "step": 53
+    },
+    {
+      "epoch": 0.10577864838393732,
+      "grad_norm": 0.896792471408844,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.9429,
+      "step": 54
+    },
+    {
+      "epoch": 0.10577864838393732,
+      "eval_loss": 0.5331423282623291,
+      "eval_runtime": 77.7205,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 54
+    },
+    {
+      "epoch": 0.10773751224289912,
+      "grad_norm": 1.3870223760604858,
+      "learning_rate": 5e-05,
+      "loss": 1.0954,
+      "step": 55
+    },
+    {
+      "epoch": 0.10969637610186092,
+      "grad_norm": 1.017014741897583,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.9297,
+      "step": 56
+    },
+    {
+      "epoch": 0.11165523996082272,
+      "grad_norm": 1.0548560619354248,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 1.0921,
+      "step": 57
+    },
+    {
+      "epoch": 0.11361410381978453,
+      "grad_norm": 1.0806331634521484,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.0678,
+      "step": 58
+    },
+    {
+      "epoch": 0.11557296767874632,
+      "grad_norm": 1.070327639579773,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.9668,
+      "step": 59
+    },
+    {
+      "epoch": 0.11753183153770813,
+      "grad_norm": 1.1311798095703125,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.0552,
+      "step": 60
+    },
+    {
+      "epoch": 0.11949069539666993,
+      "grad_norm": 1.0938886404037476,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 1.1016,
+      "step": 61
+    },
+    {
+      "epoch": 0.12144955925563174,
+      "grad_norm": 1.0902200937271118,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.1692,
+      "step": 62
+    },
+    {
+      "epoch": 0.12340842311459353,
+      "grad_norm": 1.2008287906646729,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.2145,
+      "step": 63
+    },
+    {
+      "epoch": 0.12340842311459353,
+      "eval_loss": 0.5193687081336975,
+      "eval_runtime": 77.7036,
+      "eval_samples_per_second": 5.534,
+      "eval_steps_per_second": 0.695,
+      "step": 63
+    },
+    {
+      "epoch": 0.12536728697355534,
+      "grad_norm": 1.1167514324188232,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0153,
+      "step": 64
+    },
+    {
+      "epoch": 0.12732615083251714,
+      "grad_norm": 0.918594241142273,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.9754,
+      "step": 65
+    },
+    {
+      "epoch": 0.12928501469147893,
+      "grad_norm": 1.119093656539917,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.2699,
+      "step": 66
+    },
+    {
+      "epoch": 0.13124387855044076,
+      "grad_norm": 0.9503984451293945,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.8829,
+      "step": 67
+    },
+    {
+      "epoch": 0.13320274240940255,
+      "grad_norm": 1.1151593923568726,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.2008,
+      "step": 68
+    },
+    {
+      "epoch": 0.13516160626836435,
+      "grad_norm": 1.104845643043518,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 1.0592,
+      "step": 69
+    },
+    {
+      "epoch": 0.13712047012732614,
+      "grad_norm": 0.9387127161026001,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0017,
+      "step": 70
+    },
+    {
+      "epoch": 0.13907933398628794,
+      "grad_norm": 0.9120230078697205,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.914,
+      "step": 71
+    },
+    {
+      "epoch": 0.14103819784524976,
+      "grad_norm": 0.9989181160926819,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0349,
+      "step": 72
+    },
+    {
+      "epoch": 0.14103819784524976,
+      "eval_loss": 0.5106868743896484,
+      "eval_runtime": 77.69,
+      "eval_samples_per_second": 5.535,
+      "eval_steps_per_second": 0.695,
+      "step": 72
+    },
+    {
+      "epoch": 0.14299706170421156,
+      "grad_norm": 0.9729260206222534,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.936,
+      "step": 73
+    },
+    {
+      "epoch": 0.14495592556317335,
+      "grad_norm": 0.9475226998329163,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0622,
+      "step": 74
+    },
+    {
+      "epoch": 0.14691478942213515,
+      "grad_norm": 0.7604970335960388,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.9313,
+      "step": 75
+    },
+    {
+      "epoch": 0.14887365328109697,
+      "grad_norm": 0.8500004410743713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9716,
+      "step": 76
+    },
+    {
+      "epoch": 0.15083251714005877,
+      "grad_norm": 0.8731956481933594,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.9631,
+      "step": 77
+    },
+    {
+      "epoch": 0.15279138099902057,
+      "grad_norm": 0.8892145752906799,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.8615,
+      "step": 78
+    },
+    {
+      "epoch": 0.15475024485798236,
+      "grad_norm": 1.024143934249878,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1187,
+      "step": 79
+    },
+    {
+      "epoch": 0.15670910871694418,
+      "grad_norm": 1.179613471031189,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1868,
+      "step": 80
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "grad_norm": 1.2375884056091309,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.1178,
+      "step": 81
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "eval_loss": 0.5064930319786072,
+      "eval_runtime": 77.7099,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 81
+    },
+    {
+      "epoch": 0.16062683643486778,
+      "grad_norm": 1.013840675354004,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0417,
+      "step": 82
+    },
+    {
+      "epoch": 0.16258570029382957,
+      "grad_norm": 1.0417487621307373,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0885,
+      "step": 83
+    },
+    {
+      "epoch": 0.16454456415279137,
+      "grad_norm": 0.8136703968048096,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9909,
+      "step": 84
+    },
+    {
+      "epoch": 0.1665034280117532,
+      "grad_norm": 0.8972939848899841,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8215,
+      "step": 85
+    },
+    {
+      "epoch": 0.168462291870715,
+      "grad_norm": 1.0475735664367676,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0297,
+      "step": 86
+    },
+    {
+      "epoch": 0.17042115572967678,
+      "grad_norm": 1.019552230834961,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.002,
+      "step": 87
+    },
+    {
+      "epoch": 0.17238001958863858,
+      "grad_norm": 1.4625893831253052,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0048,
+      "step": 88
+    },
+    {
+      "epoch": 0.1743388834476004,
+      "grad_norm": 1.1439257860183716,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.2146,
+      "step": 89
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "grad_norm": 0.8621885776519775,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7792,
+      "step": 90
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "eval_loss": 0.5049313306808472,
+      "eval_runtime": 77.7203,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 90
+    },
+    {
+      "epoch": 0.178256611165524,
+      "grad_norm": 1.0577645301818848,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9036,
+      "step": 91
+    },
+    {
+      "epoch": 0.1802154750244858,
+      "grad_norm": 0.9616133570671082,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9035,
+      "step": 92
+    },
+    {
+      "epoch": 0.1821743388834476,
+      "grad_norm": 1.2831529378890991,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0449,
+      "step": 93
+    },
+    {
+      "epoch": 0.1841332027424094,
+      "grad_norm": 0.9351686835289001,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.156,
+      "step": 94
+    },
+    {
+      "epoch": 0.1860920666013712,
+      "grad_norm": 1.0163346529006958,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1315,
+      "step": 95
+    },
+    {
+      "epoch": 0.188050930460333,
+      "grad_norm": 1.0136922597885132,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1075,
+      "step": 96
+    },
+    {
+      "epoch": 0.19000979431929482,
+      "grad_norm": 0.8940609693527222,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.893,
+      "step": 97
+    },
+    {
+      "epoch": 0.19196865817825662,
+      "grad_norm": 1.0098772048950195,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1835,
+      "step": 98
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "grad_norm": 0.994354248046875,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0804,
+      "step": 99
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "eval_loss": 0.5047321915626526,
+      "eval_runtime": 77.66,
+      "eval_samples_per_second": 5.537,
+      "eval_steps_per_second": 0.695,
+      "step": 99
+    },
+    {
+      "epoch": 0.1958863858961802,
+      "grad_norm": 1.6256389617919922,
+      "learning_rate": 0.0,
+      "loss": 1.0082,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.306916403806208e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de861caa453c953acdca6beeba32de807d38903feeb3f80dae6e7b7c5f23889
+size 6776

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 sha256:4de861caa453c953acdca6beeba32de807d38903feeb3f80dae6e7b7c5f23889
+size 6776