Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+model_name: smollm2-finetuned
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for smollm2-finetuned
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
+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="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.27.2
+- Transformers: 5.0.0
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.22.2
+
+## 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 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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:b7a03684361a52556cf07895b28c7947686a09bdf257bb8ed933abb1ed5d2da6
+size 3702168

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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 sha256:8e84c28e4d9f54eace402f4c377aee733a1b5eabe29a3c34ce221d279b3e7b25
+size 3702168

checkpoint-100/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cc948a5a2e6d49f026380dda34e50af855ded272f06729f493e60156a1a817
+size 7474123

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c62f0aba29fa1e62bbda53ac099211f24c2a078b6c8b92de2c1278645181758
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31dcc952e23cde9c32791f5eef02f3ae04c11b4696574b49b612390af96bc354
+size 1465

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.771084337349397,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.4292277455329896,
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.6307664513587952,
+      "learning_rate": 1.8e-05,
+      "loss": 3.0442886352539062,
+      "mean_token_accuracy": 0.46766130477190015,
+      "num_tokens": 17923.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.444719433784485,
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.6848517656326294,
+      "learning_rate": 3.8e-05,
+      "loss": 3.031746673583984,
+      "mean_token_accuracy": 0.4698774144053459,
+      "num_tokens": 35250.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.457280391301864,
+      "epoch": 1.4337349397590362,
+      "grad_norm": 0.6216166019439697,
+      "learning_rate": 5.8e-05,
+      "loss": 2.976375770568848,
+      "mean_token_accuracy": 0.4719637380196498,
+      "num_tokens": 52238.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.488101828098297,
+      "epoch": 1.9156626506024095,
+      "grad_norm": 0.6543117761611938,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.8618513107299806,
+      "mean_token_accuracy": 0.476394709199667,
+      "num_tokens": 69902.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.5051046029115334,
+      "epoch": 2.3855421686746987,
+      "grad_norm": 0.609826922416687,
+      "learning_rate": 9.8e-05,
+      "loss": 2.6897743225097654,
+      "mean_token_accuracy": 0.5106202998222449,
+      "num_tokens": 87116.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.5005000472068786,
+      "epoch": 2.8674698795180724,
+      "grad_norm": 0.553192138671875,
+      "learning_rate": 0.000118,
+      "loss": 2.5065143585205076,
+      "mean_token_accuracy": 0.5546621397137642,
+      "num_tokens": 104703.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.387304954039745,
+      "epoch": 3.337349397590361,
+      "grad_norm": 0.6644495129585266,
+      "learning_rate": 0.000138,
+      "loss": 2.2520526885986327,
+      "mean_token_accuracy": 0.5785491466522217,
+      "num_tokens": 121631.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.0719014376401903,
+      "epoch": 3.819277108433735,
+      "grad_norm": 0.6696016192436218,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.9487775802612304,
+      "mean_token_accuracy": 0.6266681879758835,
+      "num_tokens": 139418.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.6902621189753215,
+      "epoch": 4.289156626506024,
+      "grad_norm": 0.6979990601539612,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.5796000480651855,
+      "mean_token_accuracy": 0.702749891158862,
+      "num_tokens": 156093.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.3935824990272523,
+      "epoch": 4.771084337349397,
+      "grad_norm": 0.42392370104789734,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.3410226821899414,
+      "mean_token_accuracy": 0.754179036617279,
+      "num_tokens": 173750.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 126,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 137273474760192.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4899ce28097fd14703f16d4135e24d5ad668ab9d6882e7e175ee799b2e1629
+size 5585

checkpoint-12/README.md

@@ -0,0 +1,209 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-12/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-12/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625bffa70a415fc68d5e398d58def7cac587d0c564943a741043bd8181fbea6d
+size 3702168

checkpoint-12/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-12/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bfcc1d6d4e016579134438b29a9b1cd9e752b1920619a378899e14c30f2b55
+size 7474123

checkpoint-12/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3139bcaded26a815ab4498e51b4e2ec80a2dbb2722d5a6a7d2445240e193eb3
+size 14645

checkpoint-12/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f44cc78bf045fd4d7001e2d8ece9d216309b28a1165fd9f8b80fe80dc915dd9
+size 1465

checkpoint-12/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-12/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.414093440771103,
+      "epoch": 5.0,
+      "grad_norm": 0.727672278881073,
+      "learning_rate": 1.8e-05,
+      "loss": 2.9958248138427734,
+      "mean_token_accuracy": 0.4657438211143017,
+      "num_tokens": 15425.0,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 12,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 14294767472640.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4899ce28097fd14703f16d4135e24d5ad668ab9d6882e7e175ee799b2e1629
+size 5585

checkpoint-126/README.md

@@ -0,0 +1,209 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

checkpoint-126/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-126/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a03684361a52556cf07895b28c7947686a09bdf257bb8ed933abb1ed5d2da6
+size 3702168

checkpoint-126/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-126/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389a7d6625f34dad7405081064b825b8a5ddf1b9e5adf836426682f4b984ef02
+size 7474123

checkpoint-126/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad00fc9518626bbc760c098a5a288535f450bc4d16f54228ea4530e53114dfca
+size 14645

checkpoint-126/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61867abcc0b6d6ff603f2c3c19ddad5b21c449015909b37a3032fc292440e363
+size 1465

checkpoint-126/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-126/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.4292277455329896,
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.6307664513587952,
+      "learning_rate": 1.8e-05,
+      "loss": 3.0442886352539062,
+      "mean_token_accuracy": 0.46766130477190015,
+      "num_tokens": 17923.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.444719433784485,
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.6848517656326294,
+      "learning_rate": 3.8e-05,
+      "loss": 3.031746673583984,
+      "mean_token_accuracy": 0.4698774144053459,
+      "num_tokens": 35250.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.457280391301864,
+      "epoch": 1.4337349397590362,
+      "grad_norm": 0.6216166019439697,
+      "learning_rate": 5.8e-05,
+      "loss": 2.976375770568848,
+      "mean_token_accuracy": 0.4719637380196498,
+      "num_tokens": 52238.0,
+      "step": 30
+    },
+    {
+      "entropy": 2.488101828098297,
+      "epoch": 1.9156626506024095,
+      "grad_norm": 0.6543117761611938,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 2.8618513107299806,
+      "mean_token_accuracy": 0.476394709199667,
+      "num_tokens": 69902.0,
+      "step": 40
+    },
+    {
+      "entropy": 2.5051046029115334,
+      "epoch": 2.3855421686746987,
+      "grad_norm": 0.609826922416687,
+      "learning_rate": 9.8e-05,
+      "loss": 2.6897743225097654,
+      "mean_token_accuracy": 0.5106202998222449,
+      "num_tokens": 87116.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.5005000472068786,
+      "epoch": 2.8674698795180724,
+      "grad_norm": 0.553192138671875,
+      "learning_rate": 0.000118,
+      "loss": 2.5065143585205076,
+      "mean_token_accuracy": 0.5546621397137642,
+      "num_tokens": 104703.0,
+      "step": 60
+    },
+    {
+      "entropy": 2.387304954039745,
+      "epoch": 3.337349397590361,
+      "grad_norm": 0.6644495129585266,
+      "learning_rate": 0.000138,
+      "loss": 2.2520526885986327,
+      "mean_token_accuracy": 0.5785491466522217,
+      "num_tokens": 121631.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.0719014376401903,
+      "epoch": 3.819277108433735,
+      "grad_norm": 0.6696016192436218,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.9487775802612304,
+      "mean_token_accuracy": 0.6266681879758835,
+      "num_tokens": 139418.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.6902621189753215,
+      "epoch": 4.289156626506024,
+      "grad_norm": 0.6979990601539612,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 1.5796000480651855,
+      "mean_token_accuracy": 0.702749891158862,
+      "num_tokens": 156093.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.3935824990272523,
+      "epoch": 4.771084337349397,
+      "grad_norm": 0.42392370104789734,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 1.3410226821899414,
+      "mean_token_accuracy": 0.754179036617279,
+      "num_tokens": 173750.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.3122285894858532,
+      "epoch": 5.240963855421687,
+      "grad_norm": 0.34939563274383545,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 1.307413673400879,
+      "mean_token_accuracy": 0.7611884337205154,
+      "num_tokens": 190798.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.3023106366395951,
+      "epoch": 5.72289156626506,
+      "grad_norm": 0.2883418798446655,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 1.283161735534668,
+      "mean_token_accuracy": 0.7624388694763183,
+      "num_tokens": 208403.0,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 126,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 172535400943488.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-126/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4899ce28097fd14703f16d4135e24d5ad668ab9d6882e7e175ee799b2e1629
+size 5585

merged/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

merged/config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

merged/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.0.0"
+}

merged/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef01ea82f3e88a5ac8ee2a63682c6ead8cae6ca597c63f5ad1ec2d2813606df
+size 269060552

merged/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4899ce28097fd14703f16d4135e24d5ad668ab9d6882e7e175ee799b2e1629
+size 5585

training_metrics.json

@@ -0,0 +1,134 @@
+[
+  {
+    "loss": 3.0442886352539062,
+    "grad_norm": 0.6307664513587952,
+    "learning_rate": 1.8e-05,
+    "entropy": 2.4292277455329896,
+    "num_tokens": 17923.0,
+    "mean_token_accuracy": 0.46766130477190015,
+    "epoch": 0.4819277108433735,
+    "step": 10
+  },
+  {
+    "loss": 3.031746673583984,
+    "grad_norm": 0.6848517656326294,
+    "learning_rate": 3.8e-05,
+    "entropy": 2.444719433784485,
+    "num_tokens": 35250.0,
+    "mean_token_accuracy": 0.4698774144053459,
+    "epoch": 0.963855421686747,
+    "step": 20
+  },
+  {
+    "loss": 2.976375770568848,
+    "grad_norm": 0.6216166019439697,
+    "learning_rate": 5.8e-05,
+    "entropy": 2.457280391301864,
+    "num_tokens": 52238.0,
+    "mean_token_accuracy": 0.4719637380196498,
+    "epoch": 1.4337349397590362,
+    "step": 30
+  },
+  {
+    "loss": 2.8618513107299806,
+    "grad_norm": 0.6543117761611938,
+    "learning_rate": 7.800000000000001e-05,
+    "entropy": 2.488101828098297,
+    "num_tokens": 69902.0,
+    "mean_token_accuracy": 0.476394709199667,
+    "epoch": 1.9156626506024095,
+    "step": 40
+  },
+  {
+    "loss": 2.6897743225097654,
+    "grad_norm": 0.609826922416687,
+    "learning_rate": 9.8e-05,
+    "entropy": 2.5051046029115334,
+    "num_tokens": 87116.0,
+    "mean_token_accuracy": 0.5106202998222449,
+    "epoch": 2.3855421686746987,
+    "step": 50
+  },
+  {
+    "loss": 2.5065143585205076,
+    "grad_norm": 0.553192138671875,
+    "learning_rate": 0.000118,
+    "entropy": 2.5005000472068786,
+    "num_tokens": 104703.0,
+    "mean_token_accuracy": 0.5546621397137642,
+    "epoch": 2.8674698795180724,
+    "step": 60
+  },
+  {
+    "loss": 2.2520526885986327,
+    "grad_norm": 0.6644495129585266,
+    "learning_rate": 0.000138,
+    "entropy": 2.387304954039745,
+    "num_tokens": 121631.0,
+    "mean_token_accuracy": 0.5785491466522217,
+    "epoch": 3.337349397590361,
+    "step": 70
+  },
+  {
+    "loss": 1.9487775802612304,
+    "grad_norm": 0.6696016192436218,
+    "learning_rate": 0.00015800000000000002,
+    "entropy": 2.0719014376401903,
+    "num_tokens": 139418.0,
+    "mean_token_accuracy": 0.6266681879758835,
+    "epoch": 3.819277108433735,
+    "step": 80
+  },
+  {
+    "loss": 1.5796000480651855,
+    "grad_norm": 0.6979990601539612,
+    "learning_rate": 0.00017800000000000002,
+    "entropy": 1.6902621189753215,
+    "num_tokens": 156093.0,
+    "mean_token_accuracy": 0.702749891158862,
+    "epoch": 4.289156626506024,
+    "step": 90
+  },
+  {
+    "loss": 1.3410226821899414,
+    "grad_norm": 0.42392370104789734,
+    "learning_rate": 0.00019800000000000002,
+    "entropy": 1.3935824990272523,
+    "num_tokens": 173750.0,
+    "mean_token_accuracy": 0.754179036617279,
+    "epoch": 4.771084337349397,
+    "step": 100
+  },
+  {
+    "loss": 1.307413673400879,
+    "grad_norm": 0.34939563274383545,
+    "learning_rate": 0.00014647231720437686,
+    "entropy": 1.3122285894858532,
+    "num_tokens": 190798.0,
+    "mean_token_accuracy": 0.7611884337205154,
+    "epoch": 5.240963855421687,
+    "step": 110
+  },
+  {
+    "loss": 1.283161735534668,
+    "grad_norm": 0.2883418798446655,
+    "learning_rate": 3.36877341759205e-05,
+    "entropy": 1.3023106366395951,
+    "num_tokens": 208403.0,
+    "mean_token_accuracy": 0.7624388694763183,
+    "epoch": 5.72289156626506,
+    "step": 120
+  },
+  {
+    "train_runtime": 170.6045,
+    "train_samples_per_second": 11.641,
+    "train_steps_per_second": 0.739,
+    "total_flos": 172535400943488.0,
+    "train_loss": 2.1876086053394137,
+    "entropy": 1.289541762808095,
+    "num_tokens": 218484.0,
+    "mean_token_accuracy": 0.76554158459539,
+    "epoch": 6.0,
+    "step": 126
+  }
+]