Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: mit
----
+---
+base_model: AI-MO/NuminaMath-7B-TIR
+library_name: transformers
+model_name: outputs
+tags:
+- generated_from_trainer
+- sft
+- unsloth
+- trl
+licence: license
+---
+
+# Model Card for outputs
+
+This model is a fine-tuned version of [AI-MO/NuminaMath-7B-TIR](https://huggingface.co/AI-MO/NuminaMath-7B-TIR).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Chattso-GPT/outputs", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yasuhito-yanagisawa/my-llm-finetuning/runs/j98wwc29) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.21.0
+- Transformers: 4.55.0
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "AI-MO/NuminaMath-7B-TIR",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676f773377dabafa7edbe288d07e9efa58ee09b94f77c71f5e7fa5cb24e9d6ae
+size 299883760

chat_template.jinja

@@ -0,0 +1,3 @@
+{% for message in messages %}{% if (message['role'] == 'system')%}{{ '' }}{% elif (message['role'] == 'user')%}{{ '### Problem: ' + message['content'] + '
+' }}{% elif (message['role'] == 'assistant')%}{{ '### Solution: ' + message['content'] + '
+' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ '### Solution: ' }}{% endif %}{% endfor %}

checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: AI-MO/NuminaMath-7B-TIR
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:AI-MO/NuminaMath-7B-TIR
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.17.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "AI-MO/NuminaMath-7B-TIR",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676f773377dabafa7edbe288d07e9efa58ee09b94f77c71f5e7fa5cb24e9d6ae
+size 299883760

checkpoint-100/chat_template.jinja

@@ -0,0 +1,3 @@
+{% for message in messages %}{% if (message['role'] == 'system')%}{{ '' }}{% elif (message['role'] == 'user')%}{{ '### Problem: ' + message['content'] + '
+' }}{% elif (message['role'] == 'assistant')%}{{ '### Solution: ' + message['content'] + '
+' }}{% endif %}{% if loop.last and message['role'] == 'user' and add_generation_prompt %}{{ '### Solution: ' }}{% endif %}{% endfor %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4694c0fe9cad1d8fb6e27115e4c0d01b9e1618c14ffbe62424004259b9f29e66
+size 600009423

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b439e90b564a7442d5bed705075ca5e89bbd9ac789efd1c03962b19e85aa86a
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88a70f83ca592a7838eb4a3d66823c7f6c02bdad677beb6fe30c7ece2333715
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|PAD_TOKEN|>"
+}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.028070175438596492,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002807017543859649,
+      "grad_norm": 0.7608377933502197,
+      "learning_rate": 0.0,
+      "loss": 1.7214,
+      "step": 1
+    },
+    {
+      "epoch": 0.0005614035087719298,
+      "grad_norm": 0.8957514762878418,
+      "learning_rate": 4e-05,
+      "loss": 1.9895,
+      "step": 2
+    },
+    {
+      "epoch": 0.0008421052631578948,
+      "grad_norm": 1.089669942855835,
+      "learning_rate": 8e-05,
+      "loss": 2.072,
+      "step": 3
+    },
+    {
+      "epoch": 0.0011228070175438596,
+      "grad_norm": 1.0289334058761597,
+      "learning_rate": 0.00012,
+      "loss": 1.8603,
+      "step": 4
+    },
+    {
+      "epoch": 0.0014035087719298245,
+      "grad_norm": 0.767257809638977,
+      "learning_rate": 0.00016,
+      "loss": 1.4284,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016842105263157896,
+      "grad_norm": 0.5978246331214905,
+      "learning_rate": 0.0002,
+      "loss": 1.2488,
+      "step": 6
+    },
+    {
+      "epoch": 0.0019649122807017545,
+      "grad_norm": 0.4895220100879669,
+      "learning_rate": 0.00019789473684210526,
+      "loss": 0.8206,
+      "step": 7
+    },
+    {
+      "epoch": 0.002245614035087719,
+      "grad_norm": 0.4384584426879883,
+      "learning_rate": 0.00019578947368421054,
+      "loss": 0.7915,
+      "step": 8
+    },
+    {
+      "epoch": 0.0025263157894736842,
+      "grad_norm": 0.44429001212120056,
+      "learning_rate": 0.0001936842105263158,
+      "loss": 0.9091,
+      "step": 9
+    },
+    {
+      "epoch": 0.002807017543859649,
+      "grad_norm": 0.3982425332069397,
+      "learning_rate": 0.00019157894736842104,
+      "loss": 1.0326,
+      "step": 10
+    },
+    {
+      "epoch": 0.003087719298245614,
+      "grad_norm": 0.386045902967453,
+      "learning_rate": 0.00018947368421052632,
+      "loss": 0.8021,
+      "step": 11
+    },
+    {
+      "epoch": 0.003368421052631579,
+      "grad_norm": 0.22769981622695923,
+      "learning_rate": 0.0001873684210526316,
+      "loss": 0.7192,
+      "step": 12
+    },
+    {
+      "epoch": 0.003649122807017544,
+      "grad_norm": 0.2643820643424988,
+      "learning_rate": 0.00018526315789473685,
+      "loss": 0.8537,
+      "step": 13
+    },
+    {
+      "epoch": 0.003929824561403509,
+      "grad_norm": 0.29013004899024963,
+      "learning_rate": 0.0001831578947368421,
+      "loss": 0.7323,
+      "step": 14
+    },
+    {
+      "epoch": 0.004210526315789474,
+      "grad_norm": 0.28618916869163513,
+      "learning_rate": 0.00018105263157894739,
+      "loss": 0.8345,
+      "step": 15
+    },
+    {
+      "epoch": 0.004491228070175438,
+      "grad_norm": 0.2927887439727783,
+      "learning_rate": 0.00017894736842105264,
+      "loss": 0.6711,
+      "step": 16
+    },
+    {
+      "epoch": 0.004771929824561404,
+      "grad_norm": 0.3290823996067047,
+      "learning_rate": 0.0001768421052631579,
+      "loss": 0.9138,
+      "step": 17
+    },
+    {
+      "epoch": 0.0050526315789473685,
+      "grad_norm": 0.4104742109775543,
+      "learning_rate": 0.00017473684210526317,
+      "loss": 0.7287,
+      "step": 18
+    },
+    {
+      "epoch": 0.005333333333333333,
+      "grad_norm": 0.3225669860839844,
+      "learning_rate": 0.00017263157894736842,
+      "loss": 0.7856,
+      "step": 19
+    },
+    {
+      "epoch": 0.005614035087719298,
+      "grad_norm": 0.2503960430622101,
+      "learning_rate": 0.0001705263157894737,
+      "loss": 0.7148,
+      "step": 20
+    },
+    {
+      "epoch": 0.005894736842105263,
+      "grad_norm": 0.3453228771686554,
+      "learning_rate": 0.00016842105263157895,
+      "loss": 0.7775,
+      "step": 21
+    },
+    {
+      "epoch": 0.006175438596491228,
+      "grad_norm": 0.26591363549232483,
+      "learning_rate": 0.00016631578947368423,
+      "loss": 0.6831,
+      "step": 22
+    },
+    {
+      "epoch": 0.006456140350877193,
+      "grad_norm": 0.41043636202812195,
+      "learning_rate": 0.00016421052631578948,
+      "loss": 0.57,
+      "step": 23
+    },
+    {
+      "epoch": 0.006736842105263158,
+      "grad_norm": 0.21183069050312042,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 0.7367,
+      "step": 24
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 0.22407041490077972,
+      "learning_rate": 0.00016,
+      "loss": 0.5179,
+      "step": 25
+    },
+    {
+      "epoch": 0.007298245614035088,
+      "grad_norm": 0.2489241659641266,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.5823,
+      "step": 26
+    },
+    {
+      "epoch": 0.007578947368421052,
+      "grad_norm": 0.2461841106414795,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 0.6216,
+      "step": 27
+    },
+    {
+      "epoch": 0.007859649122807018,
+      "grad_norm": 0.22744964063167572,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 0.4537,
+      "step": 28
+    },
+    {
+      "epoch": 0.008140350877192983,
+      "grad_norm": 0.27331238985061646,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 0.5216,
+      "step": 29
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 0.21308669447898865,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 0.6252,
+      "step": 30
+    },
+    {
+      "epoch": 0.008701754385964912,
+      "grad_norm": 0.26308220624923706,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 0.7632,
+      "step": 31
+    },
+    {
+      "epoch": 0.008982456140350877,
+      "grad_norm": 0.23341232538223267,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.7243,
+      "step": 32
+    },
+    {
+      "epoch": 0.009263157894736843,
+      "grad_norm": 0.328726589679718,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 0.7539,
+      "step": 33
+    },
+    {
+      "epoch": 0.009543859649122808,
+      "grad_norm": 0.2569667398929596,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 0.7572,
+      "step": 34
+    },
+    {
+      "epoch": 0.009824561403508772,
+      "grad_norm": 0.23884397745132446,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 0.6237,
+      "step": 35
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "grad_norm": 0.19555659592151642,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 0.6168,
+      "step": 36
+    },
+    {
+      "epoch": 0.010385964912280702,
+      "grad_norm": 0.18646731972694397,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 0.5538,
+      "step": 37
+    },
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 0.22244583070278168,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 0.695,
+      "step": 38
+    },
+    {
+      "epoch": 0.010947368421052631,
+      "grad_norm": 0.1918996125459671,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 0.4743,
+      "step": 39
+    },
+    {
+      "epoch": 0.011228070175438596,
+      "grad_norm": 0.2257566899061203,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 0.6041,
+      "step": 40
+    },
+    {
+      "epoch": 0.011508771929824562,
+      "grad_norm": 0.23808154463768005,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.6772,
+      "step": 41
+    },
+    {
+      "epoch": 0.011789473684210527,
+      "grad_norm": 0.16062161326408386,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.4744,
+      "step": 42
+    },
+    {
+      "epoch": 0.012070175438596491,
+      "grad_norm": 0.27486950159072876,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 0.6789,
+      "step": 43
+    },
+    {
+      "epoch": 0.012350877192982456,
+      "grad_norm": 0.22151979804039001,
+      "learning_rate": 0.00012,
+      "loss": 0.5758,
+      "step": 44
+    },
+    {
+      "epoch": 0.01263157894736842,
+      "grad_norm": 0.25173574686050415,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 0.5524,
+      "step": 45
+    },
+    {
+      "epoch": 0.012912280701754385,
+      "grad_norm": 0.18759620189666748,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 0.5261,
+      "step": 46
+    },
+    {
+      "epoch": 0.01319298245614035,
+      "grad_norm": 0.1941239982843399,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 0.7774,
+      "step": 47
+    },
+    {
+      "epoch": 0.013473684210526317,
+      "grad_norm": 0.21030020713806152,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 0.61,
+      "step": 48
+    },
+    {
+      "epoch": 0.013754385964912281,
+      "grad_norm": 0.20546339452266693,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 0.605,
+      "step": 49
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 0.1955367475748062,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 0.4951,
+      "step": 50
+    },
+    {
+      "epoch": 0.01431578947368421,
+      "grad_norm": 0.2012670934200287,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.5174,
+      "step": 51
+    },
+    {
+      "epoch": 0.014596491228070175,
+      "grad_norm": 0.21794946491718292,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.6387,
+      "step": 52
+    },
+    {
+      "epoch": 0.01487719298245614,
+      "grad_norm": 0.1851382851600647,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 0.4906,
+      "step": 53
+    },
+    {
+      "epoch": 0.015157894736842105,
+      "grad_norm": 0.19877484440803528,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 0.5981,
+      "step": 54
+    },
+    {
+      "epoch": 0.015438596491228071,
+      "grad_norm": 0.28672927618026733,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 0.7185,
+      "step": 55
+    },
+    {
+      "epoch": 0.015719298245614036,
+      "grad_norm": 0.24410443007946014,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.4882,
+      "step": 56
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 0.2676307260990143,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 0.628,
+      "step": 57
+    },
+    {
+      "epoch": 0.016280701754385965,
+      "grad_norm": 0.2523461878299713,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 0.478,
+      "step": 58
+    },
+    {
+      "epoch": 0.01656140350877193,
+      "grad_norm": 0.2071600705385208,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 0.5096,
+      "step": 59
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.20321086049079895,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 0.5864,
+      "step": 60
+    },
+    {
+      "epoch": 0.01712280701754386,
+      "grad_norm": 0.20558391511440277,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 0.6181,
+      "step": 61
+    },
+    {
+      "epoch": 0.017403508771929824,
+      "grad_norm": 0.22859832644462585,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.8814,
+      "step": 62
+    },
+    {
+      "epoch": 0.01768421052631579,
+      "grad_norm": 0.20681747794151306,
+      "learning_rate": 8e-05,
+      "loss": 0.7479,
+      "step": 63
+    },
+    {
+      "epoch": 0.017964912280701753,
+      "grad_norm": 0.26385411620140076,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.5815,
+      "step": 64
+    },
+    {
+      "epoch": 0.018245614035087718,
+      "grad_norm": 0.21943461894989014,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.657,
+      "step": 65
+    },
+    {
+      "epoch": 0.018526315789473686,
+      "grad_norm": 0.24849221110343933,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.5341,
+      "step": 66
+    },
+    {
+      "epoch": 0.01880701754385965,
+      "grad_norm": 0.2595747411251068,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 0.5888,
+      "step": 67
+    },
+    {
+      "epoch": 0.019087719298245615,
+      "grad_norm": 0.23266763985157013,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 0.4899,
+      "step": 68
+    },
+    {
+      "epoch": 0.01936842105263158,
+      "grad_norm": 0.2767358720302582,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 0.6119,
+      "step": 69
+    },
+    {
+      "epoch": 0.019649122807017545,
+      "grad_norm": 0.23197737336158752,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 0.6986,
+      "step": 70
+    },
+    {
+      "epoch": 0.01992982456140351,
+      "grad_norm": 0.218978613615036,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.582,
+      "step": 71
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 0.2475346177816391,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.615,
+      "step": 72
+    },
+    {
+      "epoch": 0.02049122807017544,
+      "grad_norm": 0.21986079216003418,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 0.6171,
+      "step": 73
+    },
+    {
+      "epoch": 0.020771929824561403,
+      "grad_norm": 0.2430456131696701,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 0.6572,
+      "step": 74
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.20442380011081696,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 0.5898,
+      "step": 75
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 0.2875303328037262,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 0.7135,
+      "step": 76
+    },
+    {
+      "epoch": 0.021614035087719297,
+      "grad_norm": 0.26638996601104736,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 0.564,
+      "step": 77
+    },
+    {
+      "epoch": 0.021894736842105262,
+      "grad_norm": 0.23086141049861908,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 0.5978,
+      "step": 78
+    },
+    {
+      "epoch": 0.022175438596491227,
+      "grad_norm": 0.24883733689785004,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 0.7299,
+      "step": 79
+    },
+    {
+      "epoch": 0.02245614035087719,
+      "grad_norm": 0.1697564423084259,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 0.4933,
+      "step": 80
+    },
+    {
+      "epoch": 0.02273684210526316,
+      "grad_norm": 0.20351547002792358,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.5148,
+      "step": 81
+    },
+    {
+      "epoch": 0.023017543859649124,
+      "grad_norm": 0.1920584887266159,
+      "learning_rate": 4e-05,
+      "loss": 0.4831,
+      "step": 82
+    },
+    {
+      "epoch": 0.02329824561403509,
+      "grad_norm": 0.1843676120042801,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 0.5108,
+      "step": 83
+    },
+    {
+      "epoch": 0.023578947368421053,
+      "grad_norm": 0.2634964883327484,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 0.6499,
+      "step": 84
+    },
+    {
+      "epoch": 0.023859649122807018,
+      "grad_norm": 0.19457034766674042,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 0.4723,
+      "step": 85
+    },
+    {
+      "epoch": 0.024140350877192983,
+      "grad_norm": 0.2747279405593872,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.5834,
+      "step": 86
+    },
+    {
+      "epoch": 0.024421052631578948,
+      "grad_norm": 0.24927914142608643,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 0.7072,
+      "step": 87
+    },
+    {
+      "epoch": 0.024701754385964912,
+      "grad_norm": 0.1812397688627243,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 0.4519,
+      "step": 88
+    },
+    {
+      "epoch": 0.024982456140350877,
+      "grad_norm": 0.1891927719116211,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 0.4875,
+      "step": 89
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 0.1999116688966751,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 0.6227,
+      "step": 90
+    },
+    {
+      "epoch": 0.025543859649122806,
+      "grad_norm": 0.1899036467075348,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.6303,
+      "step": 91
+    },
+    {
+      "epoch": 0.02582456140350877,
+      "grad_norm": 0.20942147076129913,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 0.6452,
+      "step": 92
+    },
+    {
+      "epoch": 0.026105263157894736,
+      "grad_norm": 0.19382309913635254,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.5471,
+      "step": 93
+    },
+    {
+      "epoch": 0.0263859649122807,
+      "grad_norm": 0.24067223072052002,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 0.6691,
+      "step": 94
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 0.15286678075790405,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 0.4751,
+      "step": 95
+    },
+    {
+      "epoch": 0.026947368421052633,
+      "grad_norm": 0.3723171055316925,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.554,
+      "step": 96
+    },
+    {
+      "epoch": 0.027228070175438598,
+      "grad_norm": 0.22701109945774078,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.6832,
+      "step": 97
+    },
+    {
+      "epoch": 0.027508771929824562,
+      "grad_norm": 0.2766507565975189,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 0.6373,
+      "step": 98
+    },
+    {
+      "epoch": 0.027789473684210527,
+      "grad_norm": 0.24072766304016113,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.4333,
+      "step": 99
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 0.2390160858631134,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.6499,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7364055070973952.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e523a4ec0f93a8547b1b2df96f5c7bf966ab09f19986f4e935f3b88f26640a60
+size 6097

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|PAD_TOKEN|>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e523a4ec0f93a8547b1b2df96f5c7bf966ab09f19986f4e935f3b88f26640a60
+size 6097