Upload folder using huggingface_hub

README.md

@@ -0,0 +1,165 @@
+---
+library_name: peft
+base_model: NousResearch/CodeLlama-13b-hf-flash
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 7ffaa23e-0e81-4387-9768-13b392d739ba
+  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: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - a82b1571923ea3b6_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/a82b1571923ea3b6_train_data.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 5
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 50
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 8
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn56m1/7ffaa23e-0e81-4387-9768-13b392d739ba
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 5.0e-06
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 32
+lora_dropout: 0.1
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 2.0
+max_memory:
+  0: 70GB
+max_steps: 100
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/a82b1571923ea3b6_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: 50
+saves_per_epoch: null
+sequence_len: 1024
+special_tokens:
+  pad_token: </s>
+strict: false
+tf32: true
+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: 7ffaa23e-0e81-4387-9768-13b392d739ba
+wandb_project: god
+wandb_run: mnjf
+wandb_runid: 7ffaa23e-0e81-4387-9768-13b392d739ba
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 7ffaa23e-0e81-4387-9768-13b392d739ba
+
+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: 1.1556
+
+## 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: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- 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: 10
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 6.0569        | 0.0034 | 1    | 2.1594          |
+| 23.079        | 0.1682 | 50   | 1.5404          |
+| 17.4361       | 0.3364 | 100  | 1.1556          |
+
+
+### 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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_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:ff262dc85ef87023e26d66b34f1e689ef523eabff94c559832ac145647beaf11
+size 250550026

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646b364c7d4b816341c5736f0be61070471dce6b519c3f2c3092aa6ba655e3e3
+size 250422888

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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "gate_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 sha256:646b364c7d4b816341c5736f0be61070471dce6b519c3f2c3092aa6ba655e3e3
+size 250422888

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cdc11e01f89220aeb85e1610ade8369bc7ff68231fb4f58be93cd45eff1b41f
+size 501168482

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f190aed2ed983274d65d9fdfeaf963f11d23fbe04e9143be95ed2df679235a
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
+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 +1,766 @@
+{
+  "best_metric": 1.1555566787719727,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.33641715727502103,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00336417157275021,
+      "grad_norm": 3.9489922523498535,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 6.0569,
+      "step": 1
+    },
+    {
+      "epoch": 0.00336417157275021,
+      "eval_loss": 2.1594057083129883,
+      "eval_runtime": 56.5321,
+      "eval_samples_per_second": 8.862,
+      "eval_steps_per_second": 2.229,
+      "step": 1
+    },
+    {
+      "epoch": 0.00672834314550042,
+      "grad_norm": 4.482152938842773,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 7.2046,
+      "step": 2
+    },
+    {
+      "epoch": 0.010092514718250631,
+      "grad_norm": 5.5263352394104,
+      "learning_rate": 1.5e-06,
+      "loss": 8.4916,
+      "step": 3
+    },
+    {
+      "epoch": 0.01345668629100084,
+      "grad_norm": 5.707150459289551,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 8.8524,
+      "step": 4
+    },
+    {
+      "epoch": 0.01682085786375105,
+      "grad_norm": 6.016858100891113,
+      "learning_rate": 2.5e-06,
+      "loss": 8.9214,
+      "step": 5
+    },
+    {
+      "epoch": 0.020185029436501262,
+      "grad_norm": 6.257847309112549,
+      "learning_rate": 3e-06,
+      "loss": 9.1536,
+      "step": 6
+    },
+    {
+      "epoch": 0.023549201009251473,
+      "grad_norm": 6.696770191192627,
+      "learning_rate": 3.5e-06,
+      "loss": 10.0647,
+      "step": 7
+    },
+    {
+      "epoch": 0.02691337258200168,
+      "grad_norm": 7.250229835510254,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 11.0152,
+      "step": 8
+    },
+    {
+      "epoch": 0.030277544154751892,
+      "grad_norm": 7.7119245529174805,
+      "learning_rate": 4.5e-06,
+      "loss": 11.2444,
+      "step": 9
+    },
+    {
+      "epoch": 0.0336417157275021,
+      "grad_norm": 7.244583606719971,
+      "learning_rate": 5e-06,
+      "loss": 10.8585,
+      "step": 10
+    },
+    {
+      "epoch": 0.03700588730025231,
+      "grad_norm": 7.843494415283203,
+      "learning_rate": 4.99847706754774e-06,
+      "loss": 10.627,
+      "step": 11
+    },
+    {
+      "epoch": 0.040370058873002525,
+      "grad_norm": 8.349863052368164,
+      "learning_rate": 4.993910125649561e-06,
+      "loss": 11.6061,
+      "step": 12
+    },
+    {
+      "epoch": 0.04373423044575273,
+      "grad_norm": 7.974443435668945,
+      "learning_rate": 4.986304738420684e-06,
+      "loss": 10.578,
+      "step": 13
+    },
+    {
+      "epoch": 0.04709840201850295,
+      "grad_norm": 8.698466300964355,
+      "learning_rate": 4.975670171853926e-06,
+      "loss": 11.2472,
+      "step": 14
+    },
+    {
+      "epoch": 0.050462573591253154,
+      "grad_norm": 8.997441291809082,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 11.7005,
+      "step": 15
+    },
+    {
+      "epoch": 0.05382674516400336,
+      "grad_norm": 9.786170959472656,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 12.2871,
+      "step": 16
+    },
+    {
+      "epoch": 0.057190916736753576,
+      "grad_norm": 9.312055587768555,
+      "learning_rate": 4.925739315689991e-06,
+      "loss": 12.1815,
+      "step": 17
+    },
+    {
+      "epoch": 0.060555088309503784,
+      "grad_norm": 9.848001480102539,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 12.2101,
+      "step": 18
+    },
+    {
+      "epoch": 0.063919259882254,
+      "grad_norm": 10.315635681152344,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 12.0979,
+      "step": 19
+    },
+    {
+      "epoch": 0.0672834314550042,
+      "grad_norm": 11.100384712219238,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 12.8286,
+      "step": 20
+    },
+    {
+      "epoch": 0.07064760302775441,
+      "grad_norm": 11.478273391723633,
+      "learning_rate": 4.817959636416969e-06,
+      "loss": 13.5465,
+      "step": 21
+    },
+    {
+      "epoch": 0.07401177460050462,
+      "grad_norm": 11.831793785095215,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 13.9233,
+      "step": 22
+    },
+    {
+      "epoch": 0.07737594617325484,
+      "grad_norm": 12.055624008178711,
+      "learning_rate": 4.746985115747918e-06,
+      "loss": 13.4583,
+      "step": 23
+    },
+    {
+      "epoch": 0.08074011774600505,
+      "grad_norm": 12.33119010925293,
+      "learning_rate": 4.707368982147318e-06,
+      "loss": 13.772,
+      "step": 24
+    },
+    {
+      "epoch": 0.08410428931875526,
+      "grad_norm": 14.89177131652832,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 15.4565,
+      "step": 25
+    },
+    {
+      "epoch": 0.08746846089150546,
+      "grad_norm": 14.688849449157715,
+      "learning_rate": 4.620120240391065e-06,
+      "loss": 15.1635,
+      "step": 26
+    },
+    {
+      "epoch": 0.09083263246425567,
+      "grad_norm": 14.966446876525879,
+      "learning_rate": 4.572593931387604e-06,
+      "loss": 15.1824,
+      "step": 27
+    },
+    {
+      "epoch": 0.0941968040370059,
+      "grad_norm": 15.037090301513672,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 15.248,
+      "step": 28
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 14.603853225708008,
+      "learning_rate": 4.470026884016805e-06,
+      "loss": 16.433,
+      "step": 29
+    },
+    {
+      "epoch": 0.10092514718250631,
+      "grad_norm": 16.51859474182129,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 16.8033,
+      "step": 30
+    },
+    {
+      "epoch": 0.10428931875525652,
+      "grad_norm": 16.52759552001953,
+      "learning_rate": 4.357862063693486e-06,
+      "loss": 16.493,
+      "step": 31
+    },
+    {
+      "epoch": 0.10765349032800672,
+      "grad_norm": 17.3706111907959,
+      "learning_rate": 4.2983495008466285e-06,
+      "loss": 16.9004,
+      "step": 32
+    },
+    {
+      "epoch": 0.11101766190075694,
+      "grad_norm": 17.978242874145508,
+      "learning_rate": 4.236645926147493e-06,
+      "loss": 17.7257,
+      "step": 33
+    },
+    {
+      "epoch": 0.11438183347350715,
+      "grad_norm": 17.74814224243164,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 15.9999,
+      "step": 34
+    },
+    {
+      "epoch": 0.11774600504625736,
+      "grad_norm": 21.516483306884766,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 19.2002,
+      "step": 35
+    },
+    {
+      "epoch": 0.12111017661900757,
+      "grad_norm": 21.676025390625,
+      "learning_rate": 4.039153688314146e-06,
+      "loss": 19.3753,
+      "step": 36
+    },
+    {
+      "epoch": 0.12447434819175777,
+      "grad_norm": 20.633501052856445,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 17.3614,
+      "step": 37
+    },
+    {
+      "epoch": 0.127838519764508,
+      "grad_norm": 23.484853744506836,
+      "learning_rate": 3.897982258676867e-06,
+      "loss": 18.6916,
+      "step": 38
+    },
+    {
+      "epoch": 0.1312026913372582,
+      "grad_norm": 22.21061897277832,
+      "learning_rate": 3.824798160583012e-06,
+      "loss": 18.4351,
+      "step": 39
+    },
+    {
+      "epoch": 0.1345668629100084,
+      "grad_norm": 22.049198150634766,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 18.0943,
+      "step": 40
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 24.594404220581055,
+      "learning_rate": 3.6736789069647273e-06,
+      "loss": 19.8341,
+      "step": 41
+    },
+    {
+      "epoch": 0.14129520605550883,
+      "grad_norm": 23.650936126708984,
+      "learning_rate": 3.595927866972694e-06,
+      "loss": 20.1564,
+      "step": 42
+    },
+    {
+      "epoch": 0.14465937762825903,
+      "grad_norm": 24.20736312866211,
+      "learning_rate": 3.516841607689501e-06,
+      "loss": 19.0633,
+      "step": 43
+    },
+    {
+      "epoch": 0.14802354920100924,
+      "grad_norm": 24.75364112854004,
+      "learning_rate": 3.436516483539781e-06,
+      "loss": 20.2374,
+      "step": 44
+    },
+    {
+      "epoch": 0.15138772077375945,
+      "grad_norm": 25.638423919677734,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 20.1314,
+      "step": 45
+    },
+    {
+      "epoch": 0.15475189234650968,
+      "grad_norm": 24.455801010131836,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 20.3837,
+      "step": 46
+    },
+    {
+      "epoch": 0.1581160639192599,
+      "grad_norm": 28.880544662475586,
+      "learning_rate": 3.189093389542498e-06,
+      "loss": 20.9076,
+      "step": 47
+    },
+    {
+      "epoch": 0.1614802354920101,
+      "grad_norm": 28.061445236206055,
+      "learning_rate": 3.1048047389991693e-06,
+      "loss": 21.1376,
+      "step": 48
+    },
+    {
+      "epoch": 0.1648444070647603,
+      "grad_norm": 30.0025577545166,
+      "learning_rate": 3.019779227044398e-06,
+      "loss": 22.3604,
+      "step": 49
+    },
+    {
+      "epoch": 0.16820857863751051,
+      "grad_norm": 32.991703033447266,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 23.079,
+      "step": 50
+    },
+    {
+      "epoch": 0.16820857863751051,
+      "eval_loss": 1.5404291152954102,
+      "eval_runtime": 57.1121,
+      "eval_samples_per_second": 8.772,
+      "eval_steps_per_second": 2.206,
+      "step": 50
+    },
+    {
+      "epoch": 0.17157275021026072,
+      "grad_norm": 5.8676066398620605,
+      "learning_rate": 2.847932752400164e-06,
+      "loss": 4.9187,
+      "step": 51
+    },
+    {
+      "epoch": 0.17493692178301093,
+      "grad_norm": 6.816829681396484,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 5.2629,
+      "step": 52
+    },
+    {
+      "epoch": 0.17830109335576114,
+      "grad_norm": 7.70700740814209,
+      "learning_rate": 2.6743911843603134e-06,
+      "loss": 6.4171,
+      "step": 53
+    },
+    {
+      "epoch": 0.18166526492851134,
+      "grad_norm": 7.824767589569092,
+      "learning_rate": 2.587248741756253e-06,
+      "loss": 6.0923,
+      "step": 54
+    },
+    {
+      "epoch": 0.18502943650126155,
+      "grad_norm": 8.090392112731934,
+      "learning_rate": 2.5e-06,
+      "loss": 6.6339,
+      "step": 55
+    },
+    {
+      "epoch": 0.1883936080740118,
+      "grad_norm": 8.604589462280273,
+      "learning_rate": 2.4127512582437486e-06,
+      "loss": 6.1605,
+      "step": 56
+    },
+    {
+      "epoch": 0.191757779646762,
+      "grad_norm": 8.222731590270996,
+      "learning_rate": 2.325608815639687e-06,
+      "loss": 6.1605,
+      "step": 57
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 10.205119132995605,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 7.0509,
+      "step": 58
+    },
+    {
+      "epoch": 0.1984861227922624,
+      "grad_norm": 10.104853630065918,
+      "learning_rate": 2.1520672475998374e-06,
+      "loss": 6.9668,
+      "step": 59
+    },
+    {
+      "epoch": 0.20185029436501262,
+      "grad_norm": 10.174232482910156,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 7.273,
+      "step": 60
+    },
+    {
+      "epoch": 0.20521446593776282,
+      "grad_norm": 11.0505952835083,
+      "learning_rate": 1.9802207729556023e-06,
+      "loss": 7.1026,
+      "step": 61
+    },
+    {
+      "epoch": 0.20857863751051303,
+      "grad_norm": 10.55052661895752,
+      "learning_rate": 1.895195261000831e-06,
+      "loss": 7.1445,
+      "step": 62
+    },
+    {
+      "epoch": 0.21194280908326324,
+      "grad_norm": 10.593603134155273,
+      "learning_rate": 1.8109066104575023e-06,
+      "loss": 6.6755,
+      "step": 63
+    },
+    {
+      "epoch": 0.21530698065601345,
+      "grad_norm": 10.96327018737793,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 7.2853,
+      "step": 64
+    },
+    {
+      "epoch": 0.21867115222876365,
+      "grad_norm": 10.896140098571777,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 6.8225,
+      "step": 65
+    },
+    {
+      "epoch": 0.2220353238015139,
+      "grad_norm": 10.829171180725098,
+      "learning_rate": 1.56348351646022e-06,
+      "loss": 7.2135,
+      "step": 66
+    },
+    {
+      "epoch": 0.2253994953742641,
+      "grad_norm": 12.62612247467041,
+      "learning_rate": 1.4831583923105e-06,
+      "loss": 8.1609,
+      "step": 67
+    },
+    {
+      "epoch": 0.2287636669470143,
+      "grad_norm": 12.466354370117188,
+      "learning_rate": 1.4040721330273063e-06,
+      "loss": 7.5541,
+      "step": 68
+    },
+    {
+      "epoch": 0.2321278385197645,
+      "grad_norm": 12.358624458312988,
+      "learning_rate": 1.3263210930352737e-06,
+      "loss": 8.0098,
+      "step": 69
+    },
+    {
+      "epoch": 0.23549201009251472,
+      "grad_norm": 13.029424667358398,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 7.1127,
+      "step": 70
+    },
+    {
+      "epoch": 0.23885618166526493,
+      "grad_norm": 12.36991024017334,
+      "learning_rate": 1.1752018394169882e-06,
+      "loss": 7.7343,
+      "step": 71
+    },
+    {
+      "epoch": 0.24222035323801513,
+      "grad_norm": 14.253127098083496,
+      "learning_rate": 1.1020177413231334e-06,
+      "loss": 8.1448,
+      "step": 72
+    },
+    {
+      "epoch": 0.24558452481076534,
+      "grad_norm": 14.902377128601074,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 8.5399,
+      "step": 73
+    },
+    {
+      "epoch": 0.24894869638351555,
+      "grad_norm": 13.825746536254883,
+      "learning_rate": 9.608463116858544e-07,
+      "loss": 8.2775,
+      "step": 74
+    },
+    {
+      "epoch": 0.2523128679562658,
+      "grad_norm": 14.28534984588623,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 8.3315,
+      "step": 75
+    },
+    {
+      "epoch": 0.255677039529016,
+      "grad_norm": 14.561500549316406,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 8.2985,
+      "step": 76
+    },
+    {
+      "epoch": 0.2590412111017662,
+      "grad_norm": 16.219362258911133,
+      "learning_rate": 7.633540738525066e-07,
+      "loss": 9.6124,
+      "step": 77
+    },
+    {
+      "epoch": 0.2624053826745164,
+      "grad_norm": 16.25676155090332,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 9.5415,
+      "step": 78
+    },
+    {
+      "epoch": 0.2657695542472666,
+      "grad_norm": 15.985312461853027,
+      "learning_rate": 6.421379363065142e-07,
+      "loss": 8.8435,
+      "step": 79
+    },
+    {
+      "epoch": 0.2691337258200168,
+      "grad_norm": 17.515792846679688,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 9.9004,
+      "step": 80
+    },
+    {
+      "epoch": 0.27249789739276703,
+      "grad_norm": 18.003767013549805,
+      "learning_rate": 5.299731159831953e-07,
+      "loss": 9.6217,
+      "step": 81
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 17.7401180267334,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 10.091,
+      "step": 82
+    },
+    {
+      "epoch": 0.27922624053826745,
+      "grad_norm": 18.93708038330078,
+      "learning_rate": 4.27406068612396e-07,
+      "loss": 10.3955,
+      "step": 83
+    },
+    {
+      "epoch": 0.28259041211101765,
+      "grad_norm": 20.82859992980957,
+      "learning_rate": 3.798797596089351e-07,
+      "loss": 10.6501,
+      "step": 84
+    },
+    {
+      "epoch": 0.28595458368376786,
+      "grad_norm": 20.40983009338379,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 11.2433,
+      "step": 85
+    },
+    {
+      "epoch": 0.28931875525651807,
+      "grad_norm": 20.346174240112305,
+      "learning_rate": 2.9263101785268253e-07,
+      "loss": 11.8944,
+      "step": 86
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 21.919641494750977,
+      "learning_rate": 2.53014884252083e-07,
+      "loss": 11.9275,
+      "step": 87
+    },
+    {
+      "epoch": 0.2960470984020185,
+      "grad_norm": 21.59522819519043,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 11.1671,
+      "step": 88
+    },
+    {
+      "epoch": 0.2994112699747687,
+      "grad_norm": 23.782527923583984,
+      "learning_rate": 1.8204036358303173e-07,
+      "loss": 13.3871,
+      "step": 89
+    },
+    {
+      "epoch": 0.3027754415475189,
+      "grad_norm": 22.470487594604492,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 12.2082,
+      "step": 90
+    },
+    {
+      "epoch": 0.30613961312026916,
+      "grad_norm": 22.669078826904297,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 12.4097,
+      "step": 91
+    },
+    {
+      "epoch": 0.30950378469301937,
+      "grad_norm": 23.26660919189453,
+      "learning_rate": 9.684576015420277e-08,
+      "loss": 13.0533,
+      "step": 92
+    },
+    {
+      "epoch": 0.3128679562657696,
+      "grad_norm": 25.632230758666992,
+      "learning_rate": 7.426068431000883e-08,
+      "loss": 14.406,
+      "step": 93
+    },
+    {
+      "epoch": 0.3162321278385198,
+      "grad_norm": 23.212289810180664,
+      "learning_rate": 5.463099816548578e-08,
+      "loss": 12.672,
+      "step": 94
+    },
+    {
+      "epoch": 0.31959629941127,
+      "grad_norm": 26.72962188720703,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 14.1783,
+      "step": 95
+    },
+    {
+      "epoch": 0.3229604709840202,
+      "grad_norm": 26.62249183654785,
+      "learning_rate": 2.4329828146074096e-08,
+      "loss": 14.9785,
+      "step": 96
+    },
+    {
+      "epoch": 0.3263246425567704,
+      "grad_norm": 24.253948211669922,
+      "learning_rate": 1.3695261579316776e-08,
+      "loss": 13.4523,
+      "step": 97
+    },
+    {
+      "epoch": 0.3296888141295206,
+      "grad_norm": 27.36448860168457,
+      "learning_rate": 6.089874350439507e-09,
+      "loss": 15.0062,
+      "step": 98
+    },
+    {
+      "epoch": 0.3330529857022708,
+      "grad_norm": 31.766481399536133,
+      "learning_rate": 1.5229324522605949e-09,
+      "loss": 15.6437,
+      "step": 99
+    },
+    {
+      "epoch": 0.33641715727502103,
+      "grad_norm": 31.894515991210938,
+      "learning_rate": 0.0,
+      "loss": 17.4361,
+      "step": 100
+    },
+    {
+      "epoch": 0.33641715727502103,
+      "eval_loss": 1.1555566787719727,
+      "eval_runtime": 57.1133,
+      "eval_samples_per_second": 8.772,
+      "eval_steps_per_second": 2.206,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.53913198493696e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f133a7685bad8334420366152d30059d7638f53b96101d2261b92d6da951fd
+size 6840

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 sha256:78f133a7685bad8334420366152d30059d7638f53b96101d2261b92d6da951fd
+size 6840