End of training

README.md

@@ -0,0 +1,165 @@
+---
+library_name: peft
+base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 21611f4b-7afe-4835-8ed7-462ca5b0d71c
+  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: HuggingFaceH4/tiny-random-LlamaForCausalLM
+bf16: true
+chat_template: llama3
+datasets:
+- data_files:
+  - 36bad80ceaa71752_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/36bad80ceaa71752_train_data.json
+  type:
+    field_instruction: anchor
+    field_output: positive
+    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_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 2
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: sn56a2/21611f4b-7afe-4835-8ed7-462ca5b0d71c
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_memory:
+  0: 77GiB
+max_steps: 100
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/36bad80ceaa71752_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+save_strategy: steps
+sequence_len: 1024
+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: 21611f4b-7afe-4835-8ed7-462ca5b0d71c
+wandb_project: god
+wandb_run: mdps
+wandb_runid: 21611f4b-7afe-4835-8ed7-462ca5b0d71c
+warmup_steps: 10
+weight_decay: 0.01
+xformers_attention: false
+
+```
+
+</details><br>
+
+# 21611f4b-7afe-4835-8ed7-462ca5b0d71c
+
+This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3727
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 10.3771       | 0.0053 | 1    | 10.3778         |
+| 10.3771       | 0.0474 | 9    | 10.3776         |
+| 10.3763       | 0.0947 | 18   | 10.3770         |
+| 10.3753       | 0.1421 | 27   | 10.3764         |
+| 10.3754       | 0.1895 | 36   | 10.3757         |
+| 10.3736       | 0.2368 | 45   | 10.3750         |
+| 10.3734       | 0.2842 | 54   | 10.3743         |
+| 10.3723       | 0.3316 | 63   | 10.3736         |
+| 10.3726       | 0.3789 | 72   | 10.3732         |
+| 10.3723       | 0.4263 | 81   | 10.3729         |
+| 10.3728       | 0.4737 | 90   | 10.3727         |
+| 10.3733       | 0.5211 | 99   | 10.3727         |
+
+
+### 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": "HuggingFaceH4/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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_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:a1eeeab958f14bf69e9fabb6cb3cd7f7286e576db37c385dbaec34f1147209c8
+size 57218

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76e89244544ce381613c20bdfced95c7769a7c525b436a28364961884598565
+size 50624

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "HuggingFaceH4/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: HuggingFaceH4/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": "HuggingFaceH4/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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_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:d76e89244544ce381613c20bdfced95c7769a7c525b436a28364961884598565
+size 50624

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96d6e8fea23edbdcc19b266f90eb386048d32aabe881bab7eb8f9eb95cf0e892
+size 118090

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a3bdea21e6ba079ccbba624ec1dfb599a55306a888996d433b7da6e98cbcc2
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0972cadd551b6d9210f90d9b2e3421a9d27b4b199b21668663b7517dda9ca7
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052d2643f94d39de729385018900f6560552f49ed10facb0a7531f28b31aadc0
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb31cd55af594dd5a265c5dff7191e1e4857df34d419a4bf8db7fd4e3cef497
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.model

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

last-checkpoint/tokenizer_config.json

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

last-checkpoint/trainer_state.json

@@ -0,0 +1,829 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5263157894736842,
+  "eval_steps": 9,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005263157894736842,
+      "grad_norm": 0.01887725666165352,
+      "learning_rate": 1e-05,
+      "loss": 10.3771,
+      "step": 1
+    },
+    {
+      "epoch": 0.005263157894736842,
+      "eval_loss": 10.377787590026855,
+      "eval_runtime": 0.9191,
+      "eval_samples_per_second": 696.364,
+      "eval_steps_per_second": 21.761,
+      "step": 1
+    },
+    {
+      "epoch": 0.010526315789473684,
+      "grad_norm": 0.019658945500850677,
+      "learning_rate": 2e-05,
+      "loss": 10.3771,
+      "step": 2
+    },
+    {
+      "epoch": 0.015789473684210527,
+      "grad_norm": 0.019541945308446884,
+      "learning_rate": 3e-05,
+      "loss": 10.3778,
+      "step": 3
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.01850094273686409,
+      "learning_rate": 4e-05,
+      "loss": 10.3773,
+      "step": 4
+    },
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.020273681730031967,
+      "learning_rate": 5e-05,
+      "loss": 10.3784,
+      "step": 5
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": 0.01795278489589691,
+      "learning_rate": 6e-05,
+      "loss": 10.3766,
+      "step": 6
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 0.019065121188759804,
+      "learning_rate": 7e-05,
+      "loss": 10.3772,
+      "step": 7
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.020125381648540497,
+      "learning_rate": 8e-05,
+      "loss": 10.3777,
+      "step": 8
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 0.019596805796027184,
+      "learning_rate": 9e-05,
+      "loss": 10.3771,
+      "step": 9
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "eval_loss": 10.377553939819336,
+      "eval_runtime": 0.9287,
+      "eval_samples_per_second": 689.13,
+      "eval_steps_per_second": 21.535,
+      "step": 9
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.020519031211733818,
+      "learning_rate": 0.0001,
+      "loss": 10.377,
+      "step": 10
+    },
+    {
+      "epoch": 0.05789473684210526,
+      "grad_norm": 0.022309644147753716,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 10.3767,
+      "step": 11
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 0.018090447410941124,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 10.3771,
+      "step": 12
+    },
+    {
+      "epoch": 0.06842105263157895,
+      "grad_norm": 0.018387112766504288,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 10.3779,
+      "step": 13
+    },
+    {
+      "epoch": 0.07368421052631578,
+      "grad_norm": 0.019601572304964066,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 10.3766,
+      "step": 14
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.019544925540685654,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 10.3759,
+      "step": 15
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.020026741549372673,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 10.3773,
+      "step": 16
+    },
+    {
+      "epoch": 0.08947368421052632,
+      "grad_norm": 0.01871853694319725,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 10.3775,
+      "step": 17
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "grad_norm": 0.019241884350776672,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 10.3763,
+      "step": 18
+    },
+    {
+      "epoch": 0.09473684210526316,
+      "eval_loss": 10.376965522766113,
+      "eval_runtime": 0.9284,
+      "eval_samples_per_second": 689.375,
+      "eval_steps_per_second": 21.543,
+      "step": 18
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.019490916281938553,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 10.3774,
+      "step": 19
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.019260114058852196,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 10.3764,
+      "step": 20
+    },
+    {
+      "epoch": 0.11052631578947368,
+      "grad_norm": 0.020797712728381157,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 10.3756,
+      "step": 21
+    },
+    {
+      "epoch": 0.11578947368421053,
+      "grad_norm": 0.02041136659681797,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 10.3763,
+      "step": 22
+    },
+    {
+      "epoch": 0.12105263157894737,
+      "grad_norm": 0.020149167627096176,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 10.3761,
+      "step": 23
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 0.02349521778523922,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 10.3763,
+      "step": 24
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.019269824028015137,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 10.3761,
+      "step": 25
+    },
+    {
+      "epoch": 0.1368421052631579,
+      "grad_norm": 0.020011985674500465,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 10.3753,
+      "step": 26
+    },
+    {
+      "epoch": 0.14210526315789473,
+      "grad_norm": 0.022693118080496788,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 10.3753,
+      "step": 27
+    },
+    {
+      "epoch": 0.14210526315789473,
+      "eval_loss": 10.376358032226562,
+      "eval_runtime": 0.9357,
+      "eval_samples_per_second": 684.009,
+      "eval_steps_per_second": 21.375,
+      "step": 27
+    },
+    {
+      "epoch": 0.14736842105263157,
+      "grad_norm": 0.02023051679134369,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3745,
+      "step": 28
+    },
+    {
+      "epoch": 0.15263157894736842,
+      "grad_norm": 0.0204804427921772,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 10.3756,
+      "step": 29
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.023711206391453743,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 10.3755,
+      "step": 30
+    },
+    {
+      "epoch": 0.1631578947368421,
+      "grad_norm": 0.022513749077916145,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 10.3755,
+      "step": 31
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.023278402164578438,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 10.3751,
+      "step": 32
+    },
+    {
+      "epoch": 0.1736842105263158,
+      "grad_norm": 0.022470155730843544,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 10.375,
+      "step": 33
+    },
+    {
+      "epoch": 0.17894736842105263,
+      "grad_norm": 0.0218709334731102,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 10.3754,
+      "step": 34
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 0.0222818311303854,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 10.3746,
+      "step": 35
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 0.025049351155757904,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 10.3754,
+      "step": 36
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "eval_loss": 10.375699043273926,
+      "eval_runtime": 0.9263,
+      "eval_samples_per_second": 690.948,
+      "eval_steps_per_second": 21.592,
+      "step": 36
+    },
+    {
+      "epoch": 0.19473684210526315,
+      "grad_norm": 0.02589656598865986,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 10.3752,
+      "step": 37
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.023261601105332375,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 10.3761,
+      "step": 38
+    },
+    {
+      "epoch": 0.20526315789473684,
+      "grad_norm": 0.02525460347533226,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 10.3763,
+      "step": 39
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.024924341589212418,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.3748,
+      "step": 40
+    },
+    {
+      "epoch": 0.21578947368421053,
+      "grad_norm": 0.024391338229179382,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 10.3751,
+      "step": 41
+    },
+    {
+      "epoch": 0.22105263157894736,
+      "grad_norm": 0.025888536125421524,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 10.3742,
+      "step": 42
+    },
+    {
+      "epoch": 0.22631578947368422,
+      "grad_norm": 0.02838965505361557,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 10.374,
+      "step": 43
+    },
+    {
+      "epoch": 0.23157894736842105,
+      "grad_norm": 0.02482176385819912,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 10.3744,
+      "step": 44
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.026742225512862206,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 10.3736,
+      "step": 45
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "eval_loss": 10.374998092651367,
+      "eval_runtime": 0.9248,
+      "eval_samples_per_second": 692.046,
+      "eval_steps_per_second": 21.626,
+      "step": 45
+    },
+    {
+      "epoch": 0.24210526315789474,
+      "grad_norm": 0.02698339708149433,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 10.375,
+      "step": 46
+    },
+    {
+      "epoch": 0.24736842105263157,
+      "grad_norm": 0.029157817363739014,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 10.3752,
+      "step": 47
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.029631920158863068,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 10.3738,
+      "step": 48
+    },
+    {
+      "epoch": 0.2578947368421053,
+      "grad_norm": 0.027307121083140373,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 10.3754,
+      "step": 49
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.030172355473041534,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 10.3744,
+      "step": 50
+    },
+    {
+      "epoch": 0.26842105263157895,
+      "grad_norm": 0.0325302816927433,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 10.375,
+      "step": 51
+    },
+    {
+      "epoch": 0.2736842105263158,
+      "grad_norm": 0.031365640461444855,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3748,
+      "step": 52
+    },
+    {
+      "epoch": 0.2789473684210526,
+      "grad_norm": 0.03049473464488983,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 10.3757,
+      "step": 53
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "grad_norm": 0.03196469694375992,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3734,
+      "step": 54
+    },
+    {
+      "epoch": 0.28421052631578947,
+      "eval_loss": 10.374296188354492,
+      "eval_runtime": 0.9252,
+      "eval_samples_per_second": 691.758,
+      "eval_steps_per_second": 21.617,
+      "step": 54
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.030969073995947838,
+      "learning_rate": 5e-05,
+      "loss": 10.3729,
+      "step": 55
+    },
+    {
+      "epoch": 0.29473684210526313,
+      "grad_norm": 0.03508269786834717,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3744,
+      "step": 56
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.03241340443491936,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 10.3738,
+      "step": 57
+    },
+    {
+      "epoch": 0.30526315789473685,
+      "grad_norm": 0.03365073725581169,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3732,
+      "step": 58
+    },
+    {
+      "epoch": 0.3105263157894737,
+      "grad_norm": 0.03592099994421005,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 10.3742,
+      "step": 59
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.040263496339321136,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3738,
+      "step": 60
+    },
+    {
+      "epoch": 0.32105263157894737,
+      "grad_norm": 0.038791269063949585,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 10.373,
+      "step": 61
+    },
+    {
+      "epoch": 0.3263157894736842,
+      "grad_norm": 0.03754469007253647,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.3735,
+      "step": 62
+    },
+    {
+      "epoch": 0.33157894736842103,
+      "grad_norm": 0.03485563024878502,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 10.3723,
+      "step": 63
+    },
+    {
+      "epoch": 0.33157894736842103,
+      "eval_loss": 10.373647689819336,
+      "eval_runtime": 0.9204,
+      "eval_samples_per_second": 695.37,
+      "eval_steps_per_second": 21.73,
+      "step": 63
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.03888101130723953,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3731,
+      "step": 64
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.0380675308406353,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 10.3738,
+      "step": 65
+    },
+    {
+      "epoch": 0.3473684210526316,
+      "grad_norm": 0.03684001415967941,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3732,
+      "step": 66
+    },
+    {
+      "epoch": 0.3526315789473684,
+      "grad_norm": 0.03874289244413376,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 10.373,
+      "step": 67
+    },
+    {
+      "epoch": 0.35789473684210527,
+      "grad_norm": 0.04221053794026375,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3732,
+      "step": 68
+    },
+    {
+      "epoch": 0.3631578947368421,
+      "grad_norm": 0.03796631097793579,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 10.3732,
+      "step": 69
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.040988244116306305,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3724,
+      "step": 70
+    },
+    {
+      "epoch": 0.3736842105263158,
+      "grad_norm": 0.0414532870054245,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 10.374,
+      "step": 71
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 0.036528851836919785,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3726,
+      "step": 72
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "eval_loss": 10.373167037963867,
+      "eval_runtime": 0.9252,
+      "eval_samples_per_second": 691.742,
+      "eval_steps_per_second": 21.617,
+      "step": 72
+    },
+    {
+      "epoch": 0.38421052631578945,
+      "grad_norm": 0.04054586961865425,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.373,
+      "step": 73
+    },
+    {
+      "epoch": 0.3894736842105263,
+      "grad_norm": 0.041483499109745026,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3723,
+      "step": 74
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.04212287440896034,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3736,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.04082926735281944,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3723,
+      "step": 76
+    },
+    {
+      "epoch": 0.4052631578947368,
+      "grad_norm": 0.036701563745737076,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 10.3723,
+      "step": 77
+    },
+    {
+      "epoch": 0.4105263157894737,
+      "grad_norm": 0.038696736097335815,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.372,
+      "step": 78
+    },
+    {
+      "epoch": 0.41578947368421054,
+      "grad_norm": 0.0416608601808548,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 10.3729,
+      "step": 79
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.03974455967545509,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.4263157894736842,
+      "grad_norm": 0.04495880752801895,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 10.3723,
+      "step": 81
+    },
+    {
+      "epoch": 0.4263157894736842,
+      "eval_loss": 10.37287425994873,
+      "eval_runtime": 0.9258,
+      "eval_samples_per_second": 691.312,
+      "eval_steps_per_second": 21.603,
+      "step": 81
+    },
+    {
+      "epoch": 0.43157894736842106,
+      "grad_norm": 0.040529679507017136,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3725,
+      "step": 82
+    },
+    {
+      "epoch": 0.4368421052631579,
+      "grad_norm": 0.04323343187570572,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 10.3713,
+      "step": 83
+    },
+    {
+      "epoch": 0.4421052631578947,
+      "grad_norm": 0.04294629395008087,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3734,
+      "step": 84
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.038276754319667816,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3725,
+      "step": 85
+    },
+    {
+      "epoch": 0.45263157894736844,
+      "grad_norm": 0.04451122507452965,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3725,
+      "step": 86
+    },
+    {
+      "epoch": 0.45789473684210524,
+      "grad_norm": 0.037747934460639954,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3729,
+      "step": 87
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 0.041622187942266464,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3727,
+      "step": 88
+    },
+    {
+      "epoch": 0.46842105263157896,
+      "grad_norm": 0.04135525971651077,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 10.3719,
+      "step": 89
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.04291734844446182,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3728,
+      "step": 90
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "eval_loss": 10.372746467590332,
+      "eval_runtime": 0.9498,
+      "eval_samples_per_second": 673.837,
+      "eval_steps_per_second": 21.057,
+      "step": 90
+    },
+    {
+      "epoch": 0.4789473684210526,
+      "grad_norm": 0.04497038945555687,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 10.3727,
+      "step": 91
+    },
+    {
+      "epoch": 0.4842105263157895,
+      "grad_norm": 0.04266028478741646,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3728,
+      "step": 92
+    },
+    {
+      "epoch": 0.48947368421052634,
+      "grad_norm": 0.04016754776239395,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 10.3732,
+      "step": 93
+    },
+    {
+      "epoch": 0.49473684210526314,
+      "grad_norm": 0.043641068041324615,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3719,
+      "step": 94
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.04539988562464714,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3733,
+      "step": 95
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.042879585176706314,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3713,
+      "step": 96
+    },
+    {
+      "epoch": 0.5105263157894737,
+      "grad_norm": 0.040448687970638275,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 10.3728,
+      "step": 97
+    },
+    {
+      "epoch": 0.5157894736842106,
+      "grad_norm": 0.04353677108883858,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3718,
+      "step": 98
+    },
+    {
+      "epoch": 0.5210526315789473,
+      "grad_norm": 0.0435049794614315,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 10.3733,
+      "step": 99
+    },
+    {
+      "epoch": 0.5210526315789473,
+      "eval_loss": 10.372721672058105,
+      "eval_runtime": 0.9178,
+      "eval_samples_per_second": 697.282,
+      "eval_steps_per_second": 21.79,
+      "step": 99
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.03980419412255287,
+      "learning_rate": 0.0,
+      "loss": 10.3726,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 35173395333120.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b747b9ca64ce5ec2fa07fee6be2c0d81c985c98cd1b29a256361a2810ba80318
+size 6776

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": 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": "</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:b747b9ca64ce5ec2fa07fee6be2c0d81c985c98cd1b29a256361a2810ba80318
+size 6776