Upload folder using huggingface_hub

README.md

@@ -0,0 +1,160 @@
+---
+library_name: peft
+base_model: NousResearch/CodeLlama-13b-hf-flash
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: a3d592f2-b1ec-4dcb-b6e8-a4e9308fd060
+  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/CodeLlama-13b-hf-flash
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - e282326303ea7f5f_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/e282326303ea7f5f_train_data.json
+  type:
+    field_instruction: prompt
+    field_output: response_a
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+gradient_clipping: 1.0
+group_by_length: true
+hub_model_id: sn56/a3d592f2-b1ec-4dcb-b6e8-a4e9308fd060
+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: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 74GiB
+max_steps: 75
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/e282326303ea7f5f_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+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: 2048
+special_tokens:
+  pad_token: </s>
+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: a3d592f2-b1ec-4dcb-b6e8-a4e9308fd060
+wandb_project: god
+wandb_run: sj9n
+wandb_runid: a3d592f2-b1ec-4dcb-b6e8-a4e9308fd060
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# a3d592f2-b1ec-4dcb-b6e8-a4e9308fd060
+
+This model is a fine-tuned version of [NousResearch/CodeLlama-13b-hf-flash](https://huggingface.co/NousResearch/CodeLlama-13b-hf-flash) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0075
+
+## 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: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 3
+- training_steps: 75
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.8289        | 0.0004 | 1    | 1.1738          |
+| 6.957         | 0.0088 | 25   | 1.0556          |
+| 13.8822       | 0.0176 | 50   | 1.0191          |
+| 8.2613        | 0.0264 | 75   | 1.0075          |
+
+
+### 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/CodeLlama-13b-hf-flash",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_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 sha256:9642cf1527e51045cc34f89a99e95c8281bedd227240f215e93a0841a724e6fe
+size 500897546

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f53abadbe73d719bf92ceebb975e93f99bcaa19acae874c18a0b35430f1b81d
+size 500770656

config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "NousResearch/CodeLlama-13b-hf-flash",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "NousResearch/CodeLlama-13b-hf-flash--configuration_llama.LlamaConfig",
+    "AutoModel": "NousResearch/CodeLlama-13b-hf-flash--modeling_flash_llama.LlamaModel",
+    "AutoModelForCausalLM": "NousResearch/CodeLlama-13b-hf-flash--modeling_flash_llama.LlamaForCausalLM",
+    "AutoModelForSequenceClassification": "NousResearch/CodeLlama-13b-hf-flash--modeling_flash_llama.LlamaForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32016
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NousResearch/CodeLlama-13b-hf-flash
+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/CodeLlama-13b-hf-flash",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_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 sha256:8f53abadbe73d719bf92ceebb975e93f99bcaa19acae874c18a0b35430f1b81d
+size 500770656

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e3262bd01abac8dbd96797ef5d5aac9731cb5120b4cb5395eccc49f4d4370a
+size 1001863522

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31fd9039fdc861dba888e5236e84d999e88f526fb2ab44628def9efc8888394f
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,590 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02635393332454869,
+  "eval_steps": 25,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0003513857776606492,
+      "grad_norm": 0.40566906332969666,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 4.8289,
+      "step": 1
+    },
+    {
+      "epoch": 0.0003513857776606492,
+      "eval_loss": 1.173790454864502,
+      "eval_runtime": 610.791,
+      "eval_samples_per_second": 3.924,
+      "eval_steps_per_second": 1.963,
+      "step": 1
+    },
+    {
+      "epoch": 0.0007027715553212984,
+      "grad_norm": 0.5825751423835754,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 10.7893,
+      "step": 2
+    },
+    {
+      "epoch": 0.0010541573329819476,
+      "grad_norm": 0.4203815460205078,
+      "learning_rate": 0.0001,
+      "loss": 5.0236,
+      "step": 3
+    },
+    {
+      "epoch": 0.0014055431106425968,
+      "grad_norm": 0.5486876964569092,
+      "learning_rate": 9.99524110790929e-05,
+      "loss": 5.2274,
+      "step": 4
+    },
+    {
+      "epoch": 0.001756928888303246,
+      "grad_norm": 0.49067986011505127,
+      "learning_rate": 9.980973490458728e-05,
+      "loss": 8.6525,
+      "step": 5
+    },
+    {
+      "epoch": 0.002108314665963895,
+      "grad_norm": 0.5652139782905579,
+      "learning_rate": 9.957224306869053e-05,
+      "loss": 10.0269,
+      "step": 6
+    },
+    {
+      "epoch": 0.002459700443624544,
+      "grad_norm": 0.6335968375205994,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 6.0283,
+      "step": 7
+    },
+    {
+      "epoch": 0.0028110862212851937,
+      "grad_norm": 0.6399157047271729,
+      "learning_rate": 9.881480035599667e-05,
+      "loss": 5.6921,
+      "step": 8
+    },
+    {
+      "epoch": 0.0031624719989458427,
+      "grad_norm": 0.7017378807067871,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 6.5049,
+      "step": 9
+    },
+    {
+      "epoch": 0.003513857776606492,
+      "grad_norm": 0.6648010015487671,
+      "learning_rate": 9.768584753741134e-05,
+      "loss": 6.5068,
+      "step": 10
+    },
+    {
+      "epoch": 0.003865243554267141,
+      "grad_norm": 0.7622893452644348,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 6.1024,
+      "step": 11
+    },
+    {
+      "epoch": 0.00421662933192779,
+      "grad_norm": 0.8102121353149414,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 6.9054,
+      "step": 12
+    },
+    {
+      "epoch": 0.00456801510958844,
+      "grad_norm": 1.0450242757797241,
+      "learning_rate": 9.53153893518325e-05,
+      "loss": 8.0875,
+      "step": 13
+    },
+    {
+      "epoch": 0.004919400887249088,
+      "grad_norm": 1.1724853515625,
+      "learning_rate": 9.435054165891109e-05,
+      "loss": 6.9638,
+      "step": 14
+    },
+    {
+      "epoch": 0.005270786664909738,
+      "grad_norm": 1.17697012424469,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 6.5686,
+      "step": 15
+    },
+    {
+      "epoch": 0.005622172442570387,
+      "grad_norm": 0.9172914624214172,
+      "learning_rate": 9.21695722906443e-05,
+      "loss": 6.4815,
+      "step": 16
+    },
+    {
+      "epoch": 0.005973558220231036,
+      "grad_norm": 1.8105238676071167,
+      "learning_rate": 9.09576022144496e-05,
+      "loss": 7.5522,
+      "step": 17
+    },
+    {
+      "epoch": 0.0063249439978916855,
+      "grad_norm": 1.1030470132827759,
+      "learning_rate": 8.966766701456177e-05,
+      "loss": 7.9177,
+      "step": 18
+    },
+    {
+      "epoch": 0.006676329775552334,
+      "grad_norm": 1.0749439001083374,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 8.2476,
+      "step": 19
+    },
+    {
+      "epoch": 0.007027715553212984,
+      "grad_norm": 0.988822877407074,
+      "learning_rate": 8.68638668405062e-05,
+      "loss": 8.0408,
+      "step": 20
+    },
+    {
+      "epoch": 0.007379101330873633,
+      "grad_norm": 1.0468634366989136,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 7.7576,
+      "step": 21
+    },
+    {
+      "epoch": 0.007730487108534282,
+      "grad_norm": 1.0833945274353027,
+      "learning_rate": 8.377951038078302e-05,
+      "loss": 7.7106,
+      "step": 22
+    },
+    {
+      "epoch": 0.008081872886194932,
+      "grad_norm": 1.1043288707733154,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 7.796,
+      "step": 23
+    },
+    {
+      "epoch": 0.00843325866385558,
+      "grad_norm": 1.253221869468689,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 7.2421,
+      "step": 24
+    },
+    {
+      "epoch": 0.00878464444151623,
+      "grad_norm": 1.5644135475158691,
+      "learning_rate": 7.86788218175523e-05,
+      "loss": 6.957,
+      "step": 25
+    },
+    {
+      "epoch": 0.00878464444151623,
+      "eval_loss": 1.055617094039917,
+      "eval_runtime": 614.7811,
+      "eval_samples_per_second": 3.899,
+      "eval_steps_per_second": 1.95,
+      "step": 25
+    },
+    {
+      "epoch": 0.00913603021917688,
+      "grad_norm": 1.6291801929473877,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 7.8515,
+      "step": 26
+    },
+    {
+      "epoch": 0.009487415996837528,
+      "grad_norm": 1.4865143299102783,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 6.6876,
+      "step": 27
+    },
+    {
+      "epoch": 0.009838801774498177,
+      "grad_norm": 1.633550763130188,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 9.7649,
+      "step": 28
+    },
+    {
+      "epoch": 0.010190187552158827,
+      "grad_norm": 1.6559158563613892,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 7.7611,
+      "step": 29
+    },
+    {
+      "epoch": 0.010541573329819476,
+      "grad_norm": 1.56125807762146,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 8.1391,
+      "step": 30
+    },
+    {
+      "epoch": 0.010892959107480124,
+      "grad_norm": 1.4842593669891357,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 7.1128,
+      "step": 31
+    },
+    {
+      "epoch": 0.011244344885140775,
+      "grad_norm": 1.9677858352661133,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 8.2545,
+      "step": 32
+    },
+    {
+      "epoch": 0.011595730662801423,
+      "grad_norm": 2.1278786659240723,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 8.5091,
+      "step": 33
+    },
+    {
+      "epoch": 0.011947116440462072,
+      "grad_norm": 1.7648427486419678,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 6.5063,
+      "step": 34
+    },
+    {
+      "epoch": 0.01229850221812272,
+      "grad_norm": 1.6439030170440674,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 8.567,
+      "step": 35
+    },
+    {
+      "epoch": 0.012649887995783371,
+      "grad_norm": 1.884887456893921,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 8.3356,
+      "step": 36
+    },
+    {
+      "epoch": 0.01300127377344402,
+      "grad_norm": 1.6573904752731323,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 7.9903,
+      "step": 37
+    },
+    {
+      "epoch": 0.013352659551104668,
+      "grad_norm": 1.8767001628875732,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 7.5882,
+      "step": 38
+    },
+    {
+      "epoch": 0.013704045328765319,
+      "grad_norm": 2.158738374710083,
+      "learning_rate": 5e-05,
+      "loss": 9.144,
+      "step": 39
+    },
+    {
+      "epoch": 0.014055431106425967,
+      "grad_norm": 2.622767448425293,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 9.0718,
+      "step": 40
+    },
+    {
+      "epoch": 0.014406816884086616,
+      "grad_norm": 2.098249912261963,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 7.5903,
+      "step": 41
+    },
+    {
+      "epoch": 0.014758202661747266,
+      "grad_norm": 2.695885419845581,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 9.2641,
+      "step": 42
+    },
+    {
+      "epoch": 0.015109588439407915,
+      "grad_norm": 2.7287509441375732,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 9.99,
+      "step": 43
+    },
+    {
+      "epoch": 0.015460974217068563,
+      "grad_norm": 2.987199068069458,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 9.1632,
+      "step": 44
+    },
+    {
+      "epoch": 0.015812359994729214,
+      "grad_norm": 3.6520209312438965,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3929,
+      "step": 45
+    },
+    {
+      "epoch": 0.016163745772389864,
+      "grad_norm": 3.4548537731170654,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 10.003,
+      "step": 46
+    },
+    {
+      "epoch": 0.01651513155005051,
+      "grad_norm": 5.150744915008545,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 11.3511,
+      "step": 47
+    },
+    {
+      "epoch": 0.01686651732771116,
+      "grad_norm": 7.644892692565918,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.2625,
+      "step": 48
+    },
+    {
+      "epoch": 0.01721790310537181,
+      "grad_norm": 9.981356620788574,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 11.0407,
+      "step": 49
+    },
+    {
+      "epoch": 0.01756928888303246,
+      "grad_norm": 21.54275131225586,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 13.8822,
+      "step": 50
+    },
+    {
+      "epoch": 0.01756928888303246,
+      "eval_loss": 1.019070029258728,
+      "eval_runtime": 614.5764,
+      "eval_samples_per_second": 3.9,
+      "eval_steps_per_second": 1.951,
+      "step": 50
+    },
+    {
+      "epoch": 0.01792067466069311,
+      "grad_norm": 1.2253239154815674,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.3973,
+      "step": 51
+    },
+    {
+      "epoch": 0.01827206043835376,
+      "grad_norm": 0.9925060868263245,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 5.1567,
+      "step": 52
+    },
+    {
+      "epoch": 0.018623446216014406,
+      "grad_norm": 1.3718881607055664,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 7.931,
+      "step": 53
+    },
+    {
+      "epoch": 0.018974831993675056,
+      "grad_norm": 1.1585586071014404,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.9163,
+      "step": 54
+    },
+    {
+      "epoch": 0.019326217771335707,
+      "grad_norm": 1.292351245880127,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 14.2114,
+      "step": 55
+    },
+    {
+      "epoch": 0.019677603548996354,
+      "grad_norm": 0.7819482088088989,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 5.4162,
+      "step": 56
+    },
+    {
+      "epoch": 0.020028989326657004,
+      "grad_norm": 0.9459342956542969,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.4571,
+      "step": 57
+    },
+    {
+      "epoch": 0.020380375104317654,
+      "grad_norm": 0.8447139859199524,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 4.3193,
+      "step": 58
+    },
+    {
+      "epoch": 0.0207317608819783,
+      "grad_norm": 0.9083331823348999,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 5.212,
+      "step": 59
+    },
+    {
+      "epoch": 0.02108314665963895,
+      "grad_norm": 0.9303866028785706,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 5.864,
+      "step": 60
+    },
+    {
+      "epoch": 0.021434532437299602,
+      "grad_norm": 0.9800831079483032,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 5.7093,
+      "step": 61
+    },
+    {
+      "epoch": 0.02178591821496025,
+      "grad_norm": 1.0370510816574097,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 7.2464,
+      "step": 62
+    },
+    {
+      "epoch": 0.0221373039926209,
+      "grad_norm": 1.0886764526367188,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.793,
+      "step": 63
+    },
+    {
+      "epoch": 0.02248868977028155,
+      "grad_norm": 1.2717602252960205,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 7.8938,
+      "step": 64
+    },
+    {
+      "epoch": 0.022840075547942196,
+      "grad_norm": 1.13100004196167,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 6.6839,
+      "step": 65
+    },
+    {
+      "epoch": 0.023191461325602847,
+      "grad_norm": 1.103505253791809,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.4892,
+      "step": 66
+    },
+    {
+      "epoch": 0.023542847103263497,
+      "grad_norm": 1.0577113628387451,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.9858,
+      "step": 67
+    },
+    {
+      "epoch": 0.023894232880924144,
+      "grad_norm": 1.1837400197982788,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 7.707,
+      "step": 68
+    },
+    {
+      "epoch": 0.024245618658584794,
+      "grad_norm": 1.2462010383605957,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 8.0216,
+      "step": 69
+    },
+    {
+      "epoch": 0.02459700443624544,
+      "grad_norm": 1.1442655324935913,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 7.1856,
+      "step": 70
+    },
+    {
+      "epoch": 0.02494839021390609,
+      "grad_norm": 1.1962558031082153,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 7.0156,
+      "step": 71
+    },
+    {
+      "epoch": 0.025299775991566742,
+      "grad_norm": 1.2656418085098267,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 7.6485,
+      "step": 72
+    },
+    {
+      "epoch": 0.02565116176922739,
+      "grad_norm": 1.0747231245040894,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 6.3779,
+      "step": 73
+    },
+    {
+      "epoch": 0.02600254754688804,
+      "grad_norm": 1.213733196258545,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 8.1561,
+      "step": 74
+    },
+    {
+      "epoch": 0.02635393332454869,
+      "grad_norm": 1.571469783782959,
+      "learning_rate": 0.0,
+      "loss": 8.2613,
+      "step": 75
+    },
+    {
+      "epoch": 0.02635393332454869,
+      "eval_loss": 1.00751793384552,
+      "eval_runtime": 614.6938,
+      "eval_samples_per_second": 3.9,
+      "eval_steps_per_second": 1.951,
+      "step": 75
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 75,
+  "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": 2.2197502476288e+17,
+  "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 sha256:84caf77f4019f10dcb16b83dabd9c89fb5b415e94e82062954eca85730d0b951
+size 6776

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "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 sha256:84caf77f4019f10dcb16b83dabd9c89fb5b415e94e82062954eca85730d0b951
+size 6776