End of training

README.md

@@ -0,0 +1,162 @@
+---
+library_name: peft
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 5bb15199-bfd7-4a20-bcce-8ddcac758358
+  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: HuggingFaceM4/tiny-random-LlamaForCausalLM
+bf16: true
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - bb93f37edd760ff3_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/bb93f37edd760ff3_train_data.json
+  type:
+    field_instruction: type
+    field_output: model
+    format: '{instruction}'
+    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: sn56a1/5bb15199-bfd7-4a20-bcce-8ddcac758358
+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/bb93f37edd760ff3_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
+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: 5bb15199-bfd7-4a20-bcce-8ddcac758358
+wandb_project: god
+wandb_run: oufi
+wandb_runid: 5bb15199-bfd7-4a20-bcce-8ddcac758358
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 5bb15199-bfd7-4a20-bcce-8ddcac758358
+
+This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3696
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 10.3661       | 0.0007 | 1    | 10.3732         |
+| 10.3789       | 0.0337 | 50   | 10.3704         |
+| 10.3781       | 0.0674 | 100  | 10.3696         |
+
+
+### 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": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "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": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_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 sha256:432696c6b27fb61888ed107ed68d0e58d338b0a43c243bd97b9571992db011ed
+size 57218

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc362b059434f3dd54fef8792eb41fa186e7c0c0989a459d367fe6f29458af9a
+size 50624

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+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": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "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": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "k_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:bc362b059434f3dd54fef8792eb41fa186e7c0c0989a459d367fe6f29458af9a
+size 50624

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a760681695d399fdc5360274ad37046b442199b04a5c7b15deb05ecc7260bd6
+size 118090

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08431c668410859ce24fa4b1d064ab8633ca8b0a2b5fa41d2a89212310c1182e
+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": "<unk>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,766 @@
+{
+  "best_metric": 10.369635581970215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.06735140596059942,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006735140596059942,
+      "grad_norm": 0.46537747979164124,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 10.3661,
+      "step": 1
+    },
+    {
+      "epoch": 0.0006735140596059942,
+      "eval_loss": 10.37316608428955,
+      "eval_runtime": 5.0121,
+      "eval_samples_per_second": 498.989,
+      "eval_steps_per_second": 124.897,
+      "step": 1
+    },
+    {
+      "epoch": 0.0013470281192119885,
+      "grad_norm": 0.46409550309181213,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 10.3661,
+      "step": 2
+    },
+    {
+      "epoch": 0.0020205421788179827,
+      "grad_norm": 0.4587530195713043,
+      "learning_rate": 1.5e-06,
+      "loss": 10.3661,
+      "step": 3
+    },
+    {
+      "epoch": 0.002694056238423977,
+      "grad_norm": 0.4615240693092346,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 10.3661,
+      "step": 4
+    },
+    {
+      "epoch": 0.003367570298029971,
+      "grad_norm": 0.45824918150901794,
+      "learning_rate": 2.5e-06,
+      "loss": 10.3661,
+      "step": 5
+    },
+    {
+      "epoch": 0.0040410843576359655,
+      "grad_norm": 0.459720253944397,
+      "learning_rate": 3e-06,
+      "loss": 10.366,
+      "step": 6
+    },
+    {
+      "epoch": 0.00471459841724196,
+      "grad_norm": 0.45911216735839844,
+      "learning_rate": 3.5e-06,
+      "loss": 10.366,
+      "step": 7
+    },
+    {
+      "epoch": 0.005388112476847954,
+      "grad_norm": 0.4247434139251709,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 10.3713,
+      "step": 8
+    },
+    {
+      "epoch": 0.006061626536453949,
+      "grad_norm": 0.4762680232524872,
+      "learning_rate": 4.5e-06,
+      "loss": 10.3773,
+      "step": 9
+    },
+    {
+      "epoch": 0.006735140596059942,
+      "grad_norm": 0.4753515422344208,
+      "learning_rate": 5e-06,
+      "loss": 10.3772,
+      "step": 10
+    },
+    {
+      "epoch": 0.007408654655665937,
+      "grad_norm": 0.47528135776519775,
+      "learning_rate": 4.99847706754774e-06,
+      "loss": 10.3771,
+      "step": 11
+    },
+    {
+      "epoch": 0.008082168715271931,
+      "grad_norm": 0.4704223871231079,
+      "learning_rate": 4.993910125649561e-06,
+      "loss": 10.3771,
+      "step": 12
+    },
+    {
+      "epoch": 0.008755682774877925,
+      "grad_norm": 0.46953582763671875,
+      "learning_rate": 4.986304738420684e-06,
+      "loss": 10.377,
+      "step": 13
+    },
+    {
+      "epoch": 0.00942919683448392,
+      "grad_norm": 0.47936081886291504,
+      "learning_rate": 4.975670171853926e-06,
+      "loss": 10.377,
+      "step": 14
+    },
+    {
+      "epoch": 0.010102710894089914,
+      "grad_norm": 0.47104042768478394,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 10.3756,
+      "step": 15
+    },
+    {
+      "epoch": 0.010776224953695908,
+      "grad_norm": 0.7084691524505615,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 10.3593,
+      "step": 16
+    },
+    {
+      "epoch": 0.011449739013301903,
+      "grad_norm": 0.6909227967262268,
+      "learning_rate": 4.925739315689991e-06,
+      "loss": 10.3593,
+      "step": 17
+    },
+    {
+      "epoch": 0.012123253072907897,
+      "grad_norm": 0.6871774792671204,
+      "learning_rate": 4.903154239845798e-06,
+      "loss": 10.3592,
+      "step": 18
+    },
+    {
+      "epoch": 0.012796767132513891,
+      "grad_norm": 0.6961978077888489,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 10.3592,
+      "step": 19
+    },
+    {
+      "epoch": 0.013470281192119885,
+      "grad_norm": 0.6980166435241699,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 10.3591,
+      "step": 20
+    },
+    {
+      "epoch": 0.01414379525172588,
+      "grad_norm": 0.6989056468009949,
+      "learning_rate": 4.817959636416969e-06,
+      "loss": 10.359,
+      "step": 21
+    },
+    {
+      "epoch": 0.014817309311331874,
+      "grad_norm": 0.6959133744239807,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 10.3589,
+      "step": 22
+    },
+    {
+      "epoch": 0.015490823370937868,
+      "grad_norm": 0.7150304913520813,
+      "learning_rate": 4.746985115747918e-06,
+      "loss": 10.372,
+      "step": 23
+    },
+    {
+      "epoch": 0.016164337430543862,
+      "grad_norm": 0.7403161525726318,
+      "learning_rate": 4.707368982147318e-06,
+      "loss": 10.3739,
+      "step": 24
+    },
+    {
+      "epoch": 0.016837851490149856,
+      "grad_norm": 0.749751627445221,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 10.3738,
+      "step": 25
+    },
+    {
+      "epoch": 0.01751136554975585,
+      "grad_norm": 0.7444016933441162,
+      "learning_rate": 4.620120240391065e-06,
+      "loss": 10.3737,
+      "step": 26
+    },
+    {
+      "epoch": 0.018184879609361847,
+      "grad_norm": 0.7366701364517212,
+      "learning_rate": 4.572593931387604e-06,
+      "loss": 10.3737,
+      "step": 27
+    },
+    {
+      "epoch": 0.01885839366896784,
+      "grad_norm": 0.744555652141571,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 10.3736,
+      "step": 28
+    },
+    {
+      "epoch": 0.019531907728573834,
+      "grad_norm": 0.7480055093765259,
+      "learning_rate": 4.470026884016805e-06,
+      "loss": 10.3735,
+      "step": 29
+    },
+    {
+      "epoch": 0.020205421788179828,
+      "grad_norm": 0.7534674406051636,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 10.3734,
+      "step": 30
+    },
+    {
+      "epoch": 0.020878935847785822,
+      "grad_norm": 0.7489609718322754,
+      "learning_rate": 4.357862063693486e-06,
+      "loss": 10.3733,
+      "step": 31
+    },
+    {
+      "epoch": 0.021552449907391816,
+      "grad_norm": 0.7401928305625916,
+      "learning_rate": 4.2983495008466285e-06,
+      "loss": 10.3732,
+      "step": 32
+    },
+    {
+      "epoch": 0.02222596396699781,
+      "grad_norm": 0.7494103908538818,
+      "learning_rate": 4.236645926147493e-06,
+      "loss": 10.3731,
+      "step": 33
+    },
+    {
+      "epoch": 0.022899478026603807,
+      "grad_norm": 0.7467982769012451,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 10.373,
+      "step": 34
+    },
+    {
+      "epoch": 0.0235729920862098,
+      "grad_norm": 0.7477310299873352,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 10.3729,
+      "step": 35
+    },
+    {
+      "epoch": 0.024246506145815794,
+      "grad_norm": 0.7540197968482971,
+      "learning_rate": 4.039153688314146e-06,
+      "loss": 10.3728,
+      "step": 36
+    },
+    {
+      "epoch": 0.02492002020542179,
+      "grad_norm": 0.7551729083061218,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 10.3727,
+      "step": 37
+    },
+    {
+      "epoch": 0.025593534265027782,
+      "grad_norm": 0.7508256435394287,
+      "learning_rate": 3.897982258676867e-06,
+      "loss": 10.3727,
+      "step": 38
+    },
+    {
+      "epoch": 0.026267048324633776,
+      "grad_norm": 0.7513405084609985,
+      "learning_rate": 3.824798160583012e-06,
+      "loss": 10.3725,
+      "step": 39
+    },
+    {
+      "epoch": 0.02694056238423977,
+      "grad_norm": 0.7418174147605896,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 10.3725,
+      "step": 40
+    },
+    {
+      "epoch": 0.027614076443845767,
+      "grad_norm": 0.6083436012268066,
+      "learning_rate": 3.6736789069647273e-06,
+      "loss": 10.3652,
+      "step": 41
+    },
+    {
+      "epoch": 0.02828759050345176,
+      "grad_norm": 0.6467355489730835,
+      "learning_rate": 3.595927866972694e-06,
+      "loss": 10.3789,
+      "step": 42
+    },
+    {
+      "epoch": 0.028961104563057755,
+      "grad_norm": 0.6647388935089111,
+      "learning_rate": 3.516841607689501e-06,
+      "loss": 10.3793,
+      "step": 43
+    },
+    {
+      "epoch": 0.02963461862266375,
+      "grad_norm": 0.6549708843231201,
+      "learning_rate": 3.436516483539781e-06,
+      "loss": 10.3793,
+      "step": 44
+    },
+    {
+      "epoch": 0.030308132682269742,
+      "grad_norm": 0.6744738221168518,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 10.3792,
+      "step": 45
+    },
+    {
+      "epoch": 0.030981646741875736,
+      "grad_norm": 0.6574643850326538,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 10.3792,
+      "step": 46
+    },
+    {
+      "epoch": 0.03165516080148173,
+      "grad_norm": 0.6650392413139343,
+      "learning_rate": 3.189093389542498e-06,
+      "loss": 10.3791,
+      "step": 47
+    },
+    {
+      "epoch": 0.032328674861087724,
+      "grad_norm": 0.6566094160079956,
+      "learning_rate": 3.1048047389991693e-06,
+      "loss": 10.3791,
+      "step": 48
+    },
+    {
+      "epoch": 0.03300218892069372,
+      "grad_norm": 0.6569126844406128,
+      "learning_rate": 3.019779227044398e-06,
+      "loss": 10.379,
+      "step": 49
+    },
+    {
+      "epoch": 0.03367570298029971,
+      "grad_norm": 0.666088879108429,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 10.3789,
+      "step": 50
+    },
+    {
+      "epoch": 0.03367570298029971,
+      "eval_loss": 10.370377540588379,
+      "eval_runtime": 5.0443,
+      "eval_samples_per_second": 495.809,
+      "eval_steps_per_second": 124.101,
+      "step": 50
+    },
+    {
+      "epoch": 0.034349217039905705,
+      "grad_norm": 0.46555596590042114,
+      "learning_rate": 2.847932752400164e-06,
+      "loss": 10.364,
+      "step": 51
+    },
+    {
+      "epoch": 0.0350227310995117,
+      "grad_norm": 0.45745429396629333,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 10.364,
+      "step": 52
+    },
+    {
+      "epoch": 0.0356962451591177,
+      "grad_norm": 0.46381837129592896,
+      "learning_rate": 2.6743911843603134e-06,
+      "loss": 10.364,
+      "step": 53
+    },
+    {
+      "epoch": 0.03636975921872369,
+      "grad_norm": 0.46502989530563354,
+      "learning_rate": 2.587248741756253e-06,
+      "loss": 10.3639,
+      "step": 54
+    },
+    {
+      "epoch": 0.03704327327832969,
+      "grad_norm": 0.4560410678386688,
+      "learning_rate": 2.5e-06,
+      "loss": 10.3639,
+      "step": 55
+    },
+    {
+      "epoch": 0.03771678733793568,
+      "grad_norm": 0.46303921937942505,
+      "learning_rate": 2.4127512582437486e-06,
+      "loss": 10.3639,
+      "step": 56
+    },
+    {
+      "epoch": 0.038390301397541675,
+      "grad_norm": 0.4635196030139923,
+      "learning_rate": 2.325608815639687e-06,
+      "loss": 10.3639,
+      "step": 57
+    },
+    {
+      "epoch": 0.03906381545714767,
+      "grad_norm": 0.45117461681365967,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 10.3732,
+      "step": 58
+    },
+    {
+      "epoch": 0.03973732951675366,
+      "grad_norm": 0.48336178064346313,
+      "learning_rate": 2.1520672475998374e-06,
+      "loss": 10.3749,
+      "step": 59
+    },
+    {
+      "epoch": 0.040410843576359656,
+      "grad_norm": 0.4785865545272827,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 10.3749,
+      "step": 60
+    },
+    {
+      "epoch": 0.04108435763596565,
+      "grad_norm": 0.47746261954307556,
+      "learning_rate": 1.9802207729556023e-06,
+      "loss": 10.3748,
+      "step": 61
+    },
+    {
+      "epoch": 0.041757871695571644,
+      "grad_norm": 0.47557762265205383,
+      "learning_rate": 1.895195261000831e-06,
+      "loss": 10.3748,
+      "step": 62
+    },
+    {
+      "epoch": 0.04243138575517764,
+      "grad_norm": 0.4812166094779968,
+      "learning_rate": 1.8109066104575023e-06,
+      "loss": 10.3748,
+      "step": 63
+    },
+    {
+      "epoch": 0.04310489981478363,
+      "grad_norm": 0.6591014266014099,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 10.3587,
+      "step": 64
+    },
+    {
+      "epoch": 0.043778413874389625,
+      "grad_norm": 0.6979511380195618,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 10.3567,
+      "step": 65
+    },
+    {
+      "epoch": 0.04445192793399562,
+      "grad_norm": 0.6995478272438049,
+      "learning_rate": 1.56348351646022e-06,
+      "loss": 10.3566,
+      "step": 66
+    },
+    {
+      "epoch": 0.04512544199360162,
+      "grad_norm": 0.6948114633560181,
+      "learning_rate": 1.4831583923105e-06,
+      "loss": 10.3567,
+      "step": 67
+    },
+    {
+      "epoch": 0.045798956053207614,
+      "grad_norm": 0.7009080648422241,
+      "learning_rate": 1.4040721330273063e-06,
+      "loss": 10.3566,
+      "step": 68
+    },
+    {
+      "epoch": 0.04647247011281361,
+      "grad_norm": 0.6975271701812744,
+      "learning_rate": 1.3263210930352737e-06,
+      "loss": 10.3566,
+      "step": 69
+    },
+    {
+      "epoch": 0.0471459841724196,
+      "grad_norm": 0.7010521292686462,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 10.3566,
+      "step": 70
+    },
+    {
+      "epoch": 0.047819498232025595,
+      "grad_norm": 0.6726126074790955,
+      "learning_rate": 1.1752018394169882e-06,
+      "loss": 10.3597,
+      "step": 71
+    },
+    {
+      "epoch": 0.04849301229163159,
+      "grad_norm": 0.7577285170555115,
+      "learning_rate": 1.1020177413231334e-06,
+      "loss": 10.3712,
+      "step": 72
+    },
+    {
+      "epoch": 0.04916652635123758,
+      "grad_norm": 0.752513587474823,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 10.3711,
+      "step": 73
+    },
+    {
+      "epoch": 0.04984004041084358,
+      "grad_norm": 0.7591624855995178,
+      "learning_rate": 9.608463116858544e-07,
+      "loss": 10.3711,
+      "step": 74
+    },
+    {
+      "epoch": 0.05051355447044957,
+      "grad_norm": 0.7575279474258423,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 10.3711,
+      "step": 75
+    },
+    {
+      "epoch": 0.051187068530055564,
+      "grad_norm": 0.7515712976455688,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 10.3711,
+      "step": 76
+    },
+    {
+      "epoch": 0.05186058258966156,
+      "grad_norm": 0.7531877160072327,
+      "learning_rate": 7.633540738525066e-07,
+      "loss": 10.3711,
+      "step": 77
+    },
+    {
+      "epoch": 0.05253409664926755,
+      "grad_norm": 0.7591341137886047,
+      "learning_rate": 7.016504991533727e-07,
+      "loss": 10.371,
+      "step": 78
+    },
+    {
+      "epoch": 0.053207610708873546,
+      "grad_norm": 0.7630741000175476,
+      "learning_rate": 6.421379363065142e-07,
+      "loss": 10.371,
+      "step": 79
+    },
+    {
+      "epoch": 0.05388112476847954,
+      "grad_norm": 0.7539241909980774,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 10.371,
+      "step": 80
+    },
+    {
+      "epoch": 0.05455463882808553,
+      "grad_norm": 0.7619889974594116,
+      "learning_rate": 5.299731159831953e-07,
+      "loss": 10.371,
+      "step": 81
+    },
+    {
+      "epoch": 0.055228152887691534,
+      "grad_norm": 0.7507427334785461,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 10.371,
+      "step": 82
+    },
+    {
+      "epoch": 0.05590166694729753,
+      "grad_norm": 0.7484292984008789,
+      "learning_rate": 4.27406068612396e-07,
+      "loss": 10.371,
+      "step": 83
+    },
+    {
+      "epoch": 0.05657518100690352,
+      "grad_norm": 0.7520000338554382,
+      "learning_rate": 3.798797596089351e-07,
+      "loss": 10.371,
+      "step": 84
+    },
+    {
+      "epoch": 0.057248695066509515,
+      "grad_norm": 0.7428855299949646,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 10.371,
+      "step": 85
+    },
+    {
+      "epoch": 0.05792220912611551,
+      "grad_norm": 0.7592101693153381,
+      "learning_rate": 2.9263101785268253e-07,
+      "loss": 10.371,
+      "step": 86
+    },
+    {
+      "epoch": 0.0585957231857215,
+      "grad_norm": 0.7575157284736633,
+      "learning_rate": 2.53014884252083e-07,
+      "loss": 10.3709,
+      "step": 87
+    },
+    {
+      "epoch": 0.0592692372453275,
+      "grad_norm": 0.7541194558143616,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 10.371,
+      "step": 88
+    },
+    {
+      "epoch": 0.05994275130493349,
+      "grad_norm": 0.7604309916496277,
+      "learning_rate": 1.8204036358303173e-07,
+      "loss": 10.3709,
+      "step": 89
+    },
+    {
+      "epoch": 0.060616265364539484,
+      "grad_norm": 0.6117144227027893,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 10.3638,
+      "step": 90
+    },
+    {
+      "epoch": 0.06128977942414548,
+      "grad_norm": 0.6212105751037598,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 10.374,
+      "step": 91
+    },
+    {
+      "epoch": 0.06196329348375147,
+      "grad_norm": 0.6687809824943542,
+      "learning_rate": 9.684576015420277e-08,
+      "loss": 10.378,
+      "step": 92
+    },
+    {
+      "epoch": 0.06263680754335747,
+      "grad_norm": 0.6596706509590149,
+      "learning_rate": 7.426068431000883e-08,
+      "loss": 10.3781,
+      "step": 93
+    },
+    {
+      "epoch": 0.06331032160296346,
+      "grad_norm": 0.6658018827438354,
+      "learning_rate": 5.463099816548578e-08,
+      "loss": 10.3781,
+      "step": 94
+    },
+    {
+      "epoch": 0.06398383566256946,
+      "grad_norm": 0.664378821849823,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 10.378,
+      "step": 95
+    },
+    {
+      "epoch": 0.06465734972217545,
+      "grad_norm": 0.6662086844444275,
+      "learning_rate": 2.4329828146074096e-08,
+      "loss": 10.3781,
+      "step": 96
+    },
+    {
+      "epoch": 0.06533086378178145,
+      "grad_norm": 0.6696534156799316,
+      "learning_rate": 1.3695261579316776e-08,
+      "loss": 10.378,
+      "step": 97
+    },
+    {
+      "epoch": 0.06600437784138743,
+      "grad_norm": 0.6559661626815796,
+      "learning_rate": 6.089874350439507e-09,
+      "loss": 10.3781,
+      "step": 98
+    },
+    {
+      "epoch": 0.06667789190099344,
+      "grad_norm": 0.6552221179008484,
+      "learning_rate": 1.5229324522605949e-09,
+      "loss": 10.3781,
+      "step": 99
+    },
+    {
+      "epoch": 0.06735140596059942,
+      "grad_norm": 0.6548227071762085,
+      "learning_rate": 0.0,
+      "loss": 10.3781,
+      "step": 100
+    },
+    {
+      "epoch": 0.06735140596059942,
+      "eval_loss": 10.369635581970215,
+      "eval_runtime": 5.0309,
+      "eval_samples_per_second": 497.127,
+      "eval_steps_per_second": 124.431,
+      "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": 10460489318400.0,
+  "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:a4122ef1b3bc40a7026779bd682a74723533b58a35f8bb473c041ffdf2237763
+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": "<unk>",
+    "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4122ef1b3bc40a7026779bd682a74723533b58a35f8bb473c041ffdf2237763
+size 6840