Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+model_name: tinyllama_ft_adapters
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for tinyllama_ft_adapters
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+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
+
+[<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/ysrael-sacramento-universidade-federal-de-sergipe/huggingface/runs/3tw52uiv) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.25.1
+- Transformers: 4.57.1
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## 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 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_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 sha256:503ba742f719356305138472260236ad78a5872a212d60b942236aa460dcab2f
+size 25271744

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- 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 0.18.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503ba742f719356305138472260236ad78a5872a212d60b942236aa460dcab2f
+size 25271744

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654367a4624953f5294716122c04cd93e74897424f8a162ad760363557985025
+size 13686237

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749fa9eed885e9761c9f2e2d2be95a7bd6918ab0b3a60c83e9d5e0a30c63287a
+size 14645

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6aeea0340516bd5f5997d5305f21139fbebc9c31e2729403d472ded814e8e1
+size 1465

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer.model

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

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1034 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.394962626695633,
+      "epoch": 0.01,
+      "grad_norm": 1.5399831533432007,
+      "learning_rate": 0.0001999640276885231,
+      "loss": 1.1668,
+      "mean_token_accuracy": 0.712943273037672,
+      "num_tokens": 13741.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.3466473210602999,
+      "epoch": 0.02,
+      "grad_norm": 0.36063864827156067,
+      "learning_rate": 0.0001998397158750391,
+      "loss": 0.2927,
+      "mean_token_accuracy": 0.8965781725943088,
+      "num_tokens": 27455.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.2937424689531326,
+      "epoch": 0.03,
+      "grad_norm": 0.37266337871551514,
+      "learning_rate": 0.00019962674310846672,
+      "loss": 0.2606,
+      "mean_token_accuracy": 0.9008061692118645,
+      "num_tokens": 41234.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.2808209167793393,
+      "epoch": 0.04,
+      "grad_norm": 0.27206626534461975,
+      "learning_rate": 0.00019932531956721417,
+      "loss": 0.2481,
+      "mean_token_accuracy": 0.903794988244772,
+      "num_tokens": 54985.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.2773130055516958,
+      "epoch": 0.05,
+      "grad_norm": 0.28117620944976807,
+      "learning_rate": 0.00019893574271992527,
+      "loss": 0.2428,
+      "mean_token_accuracy": 0.9048246890306473,
+      "num_tokens": 68751.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.26413619332015514,
+      "epoch": 0.06,
+      "grad_norm": 0.3505501449108124,
+      "learning_rate": 0.00019845839703191414,
+      "loss": 0.2371,
+      "mean_token_accuracy": 0.9083748087286949,
+      "num_tokens": 82480.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.2639918986707926,
+      "epoch": 0.07,
+      "grad_norm": 0.25395262241363525,
+      "learning_rate": 0.00019789375358574422,
+      "loss": 0.2377,
+      "mean_token_accuracy": 0.9053500510752202,
+      "num_tokens": 96205.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.2635627929121256,
+      "epoch": 0.08,
+      "grad_norm": 0.14376139640808105,
+      "learning_rate": 0.00019724236961632662,
+      "loss": 0.2358,
+      "mean_token_accuracy": 0.9064174801111221,
+      "num_tokens": 109895.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.25960039664059875,
+      "epoch": 0.09,
+      "grad_norm": 0.24428832530975342,
+      "learning_rate": 0.00019650488796099668,
+      "loss": 0.2379,
+      "mean_token_accuracy": 0.9064785785973072,
+      "num_tokens": 123640.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.2595285512506962,
+      "epoch": 0.1,
+      "grad_norm": 0.1724952608346939,
+      "learning_rate": 0.00019568203642511092,
+      "loss": 0.2354,
+      "mean_token_accuracy": 0.9069867484271527,
+      "num_tokens": 137353.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.25291610304266215,
+      "epoch": 0.11,
+      "grad_norm": 0.1800571084022522,
+      "learning_rate": 0.00019477462706379115,
+      "loss": 0.235,
+      "mean_token_accuracy": 0.9060277946293354,
+      "num_tokens": 151077.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.25702104307711127,
+      "epoch": 0.12,
+      "grad_norm": 0.17427851259708405,
+      "learning_rate": 0.00019378355538052423,
+      "loss": 0.2356,
+      "mean_token_accuracy": 0.9082058064639569,
+      "num_tokens": 164788.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.2587074598297477,
+      "epoch": 0.13,
+      "grad_norm": 0.17054803669452667,
+      "learning_rate": 0.00019270979944340793,
+      "loss": 0.2348,
+      "mean_token_accuracy": 0.9064028665423394,
+      "num_tokens": 178512.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.25914675910025836,
+      "epoch": 0.14,
+      "grad_norm": 0.16120842099189758,
+      "learning_rate": 0.00019155441891991607,
+      "loss": 0.2338,
+      "mean_token_accuracy": 0.9047428175807,
+      "num_tokens": 192287.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.2529380152001977,
+      "epoch": 0.15,
+      "grad_norm": 0.16467617452144623,
+      "learning_rate": 0.0001903185540311346,
+      "loss": 0.2347,
+      "mean_token_accuracy": 0.9045828722417355,
+      "num_tokens": 205979.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.2500780878588557,
+      "epoch": 0.16,
+      "grad_norm": 0.1401049643754959,
+      "learning_rate": 0.00018900342442650098,
+      "loss": 0.2309,
+      "mean_token_accuracy": 0.9064637362957001,
+      "num_tokens": 219697.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.2511021964251995,
+      "epoch": 0.17,
+      "grad_norm": 0.168861985206604,
+      "learning_rate": 0.00018761032798015736,
+      "loss": 0.2314,
+      "mean_token_accuracy": 0.9074640028178692,
+      "num_tokens": 233423.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.25184259135276077,
+      "epoch": 0.18,
+      "grad_norm": 0.14406900107860565,
+      "learning_rate": 0.00018614063951010582,
+      "loss": 0.2323,
+      "mean_token_accuracy": 0.9075214579701424,
+      "num_tokens": 247144.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.24901060499250888,
+      "epoch": 0.19,
+      "grad_norm": 0.1591574251651764,
+      "learning_rate": 0.00018459580942142858,
+      "loss": 0.2317,
+      "mean_token_accuracy": 0.9085153199732303,
+      "num_tokens": 260891.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.2550090359523892,
+      "epoch": 0.2,
+      "grad_norm": 0.16101697087287903,
+      "learning_rate": 0.00018297736227491362,
+      "loss": 0.2328,
+      "mean_token_accuracy": 0.9064511582255363,
+      "num_tokens": 274588.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.25533046908676627,
+      "epoch": 0.21,
+      "grad_norm": 0.1192241758108139,
+      "learning_rate": 0.00018128689528249705,
+      "loss": 0.2324,
+      "mean_token_accuracy": 0.9066184774041176,
+      "num_tokens": 288330.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.25171877779066565,
+      "epoch": 0.22,
+      "grad_norm": 0.13009631633758545,
+      "learning_rate": 0.0001795260767310078,
+      "loss": 0.2309,
+      "mean_token_accuracy": 0.9080383241176605,
+      "num_tokens": 302064.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.24942271262407303,
+      "epoch": 0.23,
+      "grad_norm": 0.1554691344499588,
+      "learning_rate": 0.00017769664433577002,
+      "loss": 0.2292,
+      "mean_token_accuracy": 0.9099649950861931,
+      "num_tokens": 315757.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.24707860946655275,
+      "epoch": 0.24,
+      "grad_norm": 0.1397477239370346,
+      "learning_rate": 0.0001758004035256878,
+      "loss": 0.2293,
+      "mean_token_accuracy": 0.9071393564343453,
+      "num_tokens": 329421.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.24920556377619504,
+      "epoch": 0.25,
+      "grad_norm": 0.14128848910331726,
+      "learning_rate": 0.00017383922566150466,
+      "loss": 0.229,
+      "mean_token_accuracy": 0.9095418378710747,
+      "num_tokens": 343160.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.24723881762474775,
+      "epoch": 0.26,
+      "grad_norm": 0.12240611761808395,
+      "learning_rate": 0.00017181504618899674,
+      "loss": 0.226,
+      "mean_token_accuracy": 0.9101279228925705,
+      "num_tokens": 356897.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.24775481391698123,
+      "epoch": 0.27,
+      "grad_norm": 0.14189022779464722,
+      "learning_rate": 0.0001697298627289213,
+      "loss": 0.2331,
+      "mean_token_accuracy": 0.9060970209538937,
+      "num_tokens": 370586.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.24812339022755622,
+      "epoch": 0.28,
+      "grad_norm": 0.12337426841259003,
+      "learning_rate": 0.00016758573310560605,
+      "loss": 0.2298,
+      "mean_token_accuracy": 0.9070734873414039,
+      "num_tokens": 384274.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.24800526034086942,
+      "epoch": 0.29,
+      "grad_norm": 0.14418251812458038,
+      "learning_rate": 0.00016538477331612546,
+      "loss": 0.2312,
+      "mean_token_accuracy": 0.906673189997673,
+      "num_tokens": 397966.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.24352597687393426,
+      "epoch": 0.3,
+      "grad_norm": 0.12768541276454926,
+      "learning_rate": 0.00016312915544206653,
+      "loss": 0.2317,
+      "mean_token_accuracy": 0.9085634969174862,
+      "num_tokens": 411674.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.246498416736722,
+      "epoch": 0.31,
+      "grad_norm": 0.12109944969415665,
+      "learning_rate": 0.00016082110550594695,
+      "loss": 0.2297,
+      "mean_token_accuracy": 0.9070726454257965,
+      "num_tokens": 425420.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.24201159030199051,
+      "epoch": 0.32,
+      "grad_norm": 0.11924492567777634,
+      "learning_rate": 0.00015846290127439943,
+      "loss": 0.2302,
+      "mean_token_accuracy": 0.9076045632362366,
+      "num_tokens": 439178.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.24264783263206482,
+      "epoch": 0.33,
+      "grad_norm": 0.13219736516475677,
+      "learning_rate": 0.00015605687001029106,
+      "loss": 0.2279,
+      "mean_token_accuracy": 0.9087240405380725,
+      "num_tokens": 452902.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.23972480706870555,
+      "epoch": 0.34,
+      "grad_norm": 0.11312355846166611,
+      "learning_rate": 0.00015360538617599582,
+      "loss": 0.2228,
+      "mean_token_accuracy": 0.9087543413043022,
+      "num_tokens": 466608.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.23991424571722747,
+      "epoch": 0.35,
+      "grad_norm": 0.11352849751710892,
+      "learning_rate": 0.00015111086909008696,
+      "loss": 0.2304,
+      "mean_token_accuracy": 0.9063730739057064,
+      "num_tokens": 480349.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.24278797972947358,
+      "epoch": 0.36,
+      "grad_norm": 0.10791114717721939,
+      "learning_rate": 0.00014857578053976156,
+      "loss": 0.2305,
+      "mean_token_accuracy": 0.9075991056859494,
+      "num_tokens": 494091.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.2437454979866743,
+      "epoch": 0.37,
+      "grad_norm": 0.11218743026256561,
+      "learning_rate": 0.00014600262235135383,
+      "loss": 0.2302,
+      "mean_token_accuracy": 0.9073912307620049,
+      "num_tokens": 507795.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.24400295298546554,
+      "epoch": 0.38,
+      "grad_norm": 0.1135665699839592,
+      "learning_rate": 0.0001433939339213346,
+      "loss": 0.2294,
+      "mean_token_accuracy": 0.9078077256679535,
+      "num_tokens": 521511.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.2418823266401887,
+      "epoch": 0.39,
+      "grad_norm": 0.10078570991754532,
+      "learning_rate": 0.00014075228971023352,
+      "loss": 0.2295,
+      "mean_token_accuracy": 0.9060509398579597,
+      "num_tokens": 535178.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.2401410521939397,
+      "epoch": 0.4,
+      "grad_norm": 0.10249901562929153,
+      "learning_rate": 0.00013808029670195733,
+      "loss": 0.2288,
+      "mean_token_accuracy": 0.9078609637916089,
+      "num_tokens": 548909.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.24041978865861893,
+      "epoch": 0.41,
+      "grad_norm": 0.10237855464220047,
+      "learning_rate": 0.00013538059183101163,
+      "loss": 0.2276,
+      "mean_token_accuracy": 0.9083370670676232,
+      "num_tokens": 562673.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.24148143101483582,
+      "epoch": 0.42,
+      "grad_norm": 0.12753501534461975,
+      "learning_rate": 0.00013265583938016474,
+      "loss": 0.2299,
+      "mean_token_accuracy": 0.9089422464370728,
+      "num_tokens": 576359.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.24143251981586217,
+      "epoch": 0.43,
+      "grad_norm": 0.08917894214391708,
+      "learning_rate": 0.00012990872835112226,
+      "loss": 0.2273,
+      "mean_token_accuracy": 0.9093300215899944,
+      "num_tokens": 590068.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.23971296865493058,
+      "epoch": 0.44,
+      "grad_norm": 0.10084182024002075,
+      "learning_rate": 0.0001271419698108071,
+      "loss": 0.2254,
+      "mean_token_accuracy": 0.9112895399332046,
+      "num_tokens": 603781.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.24030182063579558,
+      "epoch": 0.45,
+      "grad_norm": 0.08648212254047394,
+      "learning_rate": 0.00012435829421586378,
+      "loss": 0.2297,
+      "mean_token_accuracy": 0.9069390766322613,
+      "num_tokens": 617494.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.23907596711069345,
+      "epoch": 0.46,
+      "grad_norm": 0.09726402163505554,
+      "learning_rate": 0.00012156044871802728,
+      "loss": 0.2272,
+      "mean_token_accuracy": 0.9110749870538711,
+      "num_tokens": 631226.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.24048226717859505,
+      "epoch": 0.47,
+      "grad_norm": 0.1269565373659134,
+      "learning_rate": 0.00011875119445301597,
+      "loss": 0.2263,
+      "mean_token_accuracy": 0.9094365708529949,
+      "num_tokens": 644930.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.2404868735000491,
+      "epoch": 0.48,
+      "grad_norm": 0.13987430930137634,
+      "learning_rate": 0.00011593330381562402,
+      "loss": 0.228,
+      "mean_token_accuracy": 0.9086972288787365,
+      "num_tokens": 658643.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.2410233708098531,
+      "epoch": 0.49,
+      "grad_norm": 0.0858728289604187,
+      "learning_rate": 0.00011310955772370253,
+      "loss": 0.2283,
+      "mean_token_accuracy": 0.9088118858635426,
+      "num_tokens": 672407.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.24116825982928275,
+      "epoch": 0.5,
+      "grad_norm": 0.10033973306417465,
+      "learning_rate": 0.00011028274287372918,
+      "loss": 0.2261,
+      "mean_token_accuracy": 0.9081287659704685,
+      "num_tokens": 686181.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.23781158719211817,
+      "epoch": 0.51,
+      "grad_norm": 0.0920284241437912,
+      "learning_rate": 0.00010745564899067542,
+      "loss": 0.2251,
+      "mean_token_accuracy": 0.910574822127819,
+      "num_tokens": 699910.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.24437603540718555,
+      "epoch": 0.52,
+      "grad_norm": 0.11087141931056976,
+      "learning_rate": 0.00010463106607488464,
+      "loss": 0.2285,
+      "mean_token_accuracy": 0.9092436917126179,
+      "num_tokens": 713591.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.23954443875700235,
+      "epoch": 0.53,
+      "grad_norm": 0.11676358431577682,
+      "learning_rate": 0.0001018117816486787,
+      "loss": 0.2264,
+      "mean_token_accuracy": 0.9098656721413135,
+      "num_tokens": 727279.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.24102531783282757,
+      "epoch": 0.54,
+      "grad_norm": 0.11347582936286926,
+      "learning_rate": 9.900057800540997e-05,
+      "loss": 0.2268,
+      "mean_token_accuracy": 0.9075351029634475,
+      "num_tokens": 740997.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.2425799235701561,
+      "epoch": 0.55,
+      "grad_norm": 0.09372539818286896,
+      "learning_rate": 9.620022946367353e-05,
+      "loss": 0.2261,
+      "mean_token_accuracy": 0.909490604698658,
+      "num_tokens": 754712.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.24178444128483534,
+      "epoch": 0.56,
+      "grad_norm": 0.12750065326690674,
+      "learning_rate": 9.341349962938999e-05,
+      "loss": 0.2263,
+      "mean_token_accuracy": 0.9097795434296131,
+      "num_tokens": 768470.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.23971282187849283,
+      "epoch": 0.57,
+      "grad_norm": 0.1198856458067894,
+      "learning_rate": 9.064313866845983e-05,
+      "loss": 0.2271,
+      "mean_token_accuracy": 0.908038080483675,
+      "num_tokens": 782190.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.23883000295609236,
+      "epoch": 0.58,
+      "grad_norm": 0.09600803256034851,
+      "learning_rate": 8.789188059268165e-05,
+      "loss": 0.228,
+      "mean_token_accuracy": 0.905812531709671,
+      "num_tokens": 795923.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.24229615442454816,
+      "epoch": 0.59,
+      "grad_norm": 0.09378166496753693,
+      "learning_rate": 8.516244056161292e-05,
+      "loss": 0.2291,
+      "mean_token_accuracy": 0.9067122749984264,
+      "num_tokens": 809681.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.24172411523759366,
+      "epoch": 0.6,
+      "grad_norm": 0.10937656462192535,
+      "learning_rate": 8.245751220303495e-05,
+      "loss": 0.2269,
+      "mean_token_accuracy": 0.9078916423022747,
+      "num_tokens": 823381.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.2396618865430355,
+      "epoch": 0.61,
+      "grad_norm": 0.10506117343902588,
+      "learning_rate": 7.977976495466775e-05,
+      "loss": 0.2272,
+      "mean_token_accuracy": 0.9090281568467617,
+      "num_tokens": 837086.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.23965995348989963,
+      "epoch": 0.62,
+      "grad_norm": 0.09030091017484665,
+      "learning_rate": 7.713184142975712e-05,
+      "loss": 0.2259,
+      "mean_token_accuracy": 0.9090517483651638,
+      "num_tokens": 850830.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.24109825491905212,
+      "epoch": 0.63,
+      "grad_norm": 0.08926719427108765,
+      "learning_rate": 7.451635480913441e-05,
+      "loss": 0.23,
+      "mean_token_accuracy": 0.9062697902321816,
+      "num_tokens": 864535.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.24306405633687972,
+      "epoch": 0.64,
+      "grad_norm": 0.09499569982290268,
+      "learning_rate": 7.193588626232272e-05,
+      "loss": 0.2288,
+      "mean_token_accuracy": 0.9066683143377304,
+      "num_tokens": 878242.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.24157419390976428,
+      "epoch": 0.65,
+      "grad_norm": 0.09953978657722473,
+      "learning_rate": 6.939298240023395e-05,
+      "loss": 0.2283,
+      "mean_token_accuracy": 0.9084775008261203,
+      "num_tokens": 891947.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.23758653849363326,
+      "epoch": 0.66,
+      "grad_norm": 0.09636619687080383,
+      "learning_rate": 6.689015276197152e-05,
+      "loss": 0.2257,
+      "mean_token_accuracy": 0.9086615785956382,
+      "num_tokens": 905674.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.23539376221597194,
+      "epoch": 0.67,
+      "grad_norm": 0.08852291852235794,
+      "learning_rate": 6.442986733821805e-05,
+      "loss": 0.2261,
+      "mean_token_accuracy": 0.9083991117775441,
+      "num_tokens": 919369.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.24168960526585578,
+      "epoch": 0.68,
+      "grad_norm": 0.10650154203176498,
+      "learning_rate": 6.201455413365302e-05,
+      "loss": 0.2275,
+      "mean_token_accuracy": 0.9083165325224399,
+      "num_tokens": 933086.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.24350604116916658,
+      "epoch": 0.69,
+      "grad_norm": 0.10696761310100555,
+      "learning_rate": 5.9646596770804984e-05,
+      "loss": 0.2294,
+      "mean_token_accuracy": 0.9081006243824958,
+      "num_tokens": 946807.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.24074853528290988,
+      "epoch": 0.7,
+      "grad_norm": 0.1011936292052269,
+      "learning_rate": 5.7328332137704124e-05,
+      "loss": 0.2242,
+      "mean_token_accuracy": 0.9103688023984432,
+      "num_tokens": 960538.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.24019681774079799,
+      "epoch": 0.71,
+      "grad_norm": 0.13406361639499664,
+      "learning_rate": 5.506204808165578e-05,
+      "loss": 0.2255,
+      "mean_token_accuracy": 0.9098781734704972,
+      "num_tokens": 974218.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.2383977560326457,
+      "epoch": 0.72,
+      "grad_norm": 0.10470221936702728,
+      "learning_rate": 5.284998115141156e-05,
+      "loss": 0.2263,
+      "mean_token_accuracy": 0.9090094104409218,
+      "num_tokens": 988005.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.24030728153884412,
+      "epoch": 0.73,
+      "grad_norm": 0.09950567036867142,
+      "learning_rate": 5.0694314389965483e-05,
+      "loss": 0.2262,
+      "mean_token_accuracy": 0.9077764123678207,
+      "num_tokens": 1001747.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.2383517747744918,
+      "epoch": 0.74,
+      "grad_norm": 0.1046379804611206,
+      "learning_rate": 4.859717518015433e-05,
+      "loss": 0.2255,
+      "mean_token_accuracy": 0.9083648830652237,
+      "num_tokens": 1015426.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.2376708509400487,
+      "epoch": 0.75,
+      "grad_norm": 0.10912368446588516,
+      "learning_rate": 4.656063314518747e-05,
+      "loss": 0.2287,
+      "mean_token_accuracy": 0.906926941126585,
+      "num_tokens": 1029135.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.24110756535083055,
+      "epoch": 0.76,
+      "grad_norm": 0.09701701998710632,
+      "learning_rate": 4.458669810617876e-05,
+      "loss": 0.2272,
+      "mean_token_accuracy": 0.907534234970808,
+      "num_tokens": 1042797.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.24144795462489127,
+      "epoch": 0.77,
+      "grad_norm": 0.09698126465082169,
+      "learning_rate": 4.2677318098695596e-05,
+      "loss": 0.2276,
+      "mean_token_accuracy": 0.9077579878270626,
+      "num_tokens": 1056514.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.2410194795578718,
+      "epoch": 0.78,
+      "grad_norm": 0.09262491017580032,
+      "learning_rate": 4.0834377450283115e-05,
+      "loss": 0.2274,
+      "mean_token_accuracy": 0.9079074241220951,
+      "num_tokens": 1070274.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.2379290260374546,
+      "epoch": 0.79,
+      "grad_norm": 0.08610810339450836,
+      "learning_rate": 3.905969492086041e-05,
+      "loss": 0.2266,
+      "mean_token_accuracy": 0.9089205518364907,
+      "num_tokens": 1083963.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.23869995530694724,
+      "epoch": 0.8,
+      "grad_norm": 0.0876014232635498,
+      "learning_rate": 3.7355021907823975e-05,
+      "loss": 0.2276,
+      "mean_token_accuracy": 0.9091116264462471,
+      "num_tokens": 1097716.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.23918451257050038,
+      "epoch": 0.81,
+      "grad_norm": 0.09547661989927292,
+      "learning_rate": 3.572204071763005e-05,
+      "loss": 0.2271,
+      "mean_token_accuracy": 0.9079934142529964,
+      "num_tokens": 1111428.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.23733678106218575,
+      "epoch": 0.82,
+      "grad_norm": 0.0923481360077858,
+      "learning_rate": 3.416236290556112e-05,
+      "loss": 0.2232,
+      "mean_token_accuracy": 0.9107904858887196,
+      "num_tokens": 1125176.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.2402896758168936,
+      "epoch": 0.83,
+      "grad_norm": 0.08988992869853973,
+      "learning_rate": 3.2677527685315513e-05,
+      "loss": 0.2273,
+      "mean_token_accuracy": 0.9071260102093219,
+      "num_tokens": 1138848.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.24149883706122638,
+      "epoch": 0.84,
+      "grad_norm": 0.11069593578577042,
+      "learning_rate": 3.126900040998926e-05,
+      "loss": 0.2271,
+      "mean_token_accuracy": 0.9076950967311859,
+      "num_tokens": 1152541.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.23676478322595357,
+      "epoch": 0.85,
+      "grad_norm": 0.10589366406202316,
+      "learning_rate": 2.99381711259496e-05,
+      "loss": 0.2266,
+      "mean_token_accuracy": 0.9074639461934566,
+      "num_tokens": 1166218.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.23998944871127606,
+      "epoch": 0.86,
+      "grad_norm": 0.11591170728206635,
+      "learning_rate": 2.8686353201026866e-05,
+      "loss": 0.2291,
+      "mean_token_accuracy": 0.9079932942986488,
+      "num_tokens": 1179979.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.2381745295599103,
+      "epoch": 0.87,
+      "grad_norm": 0.10135681927204132,
+      "learning_rate": 2.7514782028379192e-05,
+      "loss": 0.2252,
+      "mean_token_accuracy": 0.9097053721547127,
+      "num_tokens": 1193705.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.2392121000215411,
+      "epoch": 0.88,
+      "grad_norm": 0.09339557588100433,
+      "learning_rate": 2.642461380730844e-05,
+      "loss": 0.2248,
+      "mean_token_accuracy": 0.9095241233706475,
+      "num_tokens": 1207477.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.23628139793872832,
+      "epoch": 0.89,
+      "grad_norm": 0.10830932855606079,
+      "learning_rate": 2.5416924402231233e-05,
+      "loss": 0.2242,
+      "mean_token_accuracy": 0.9095697320997715,
+      "num_tokens": 1221260.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.23507849648594856,
+      "epoch": 0.9,
+      "grad_norm": 0.10872520506381989,
+      "learning_rate": 2.449270828093054e-05,
+      "loss": 0.2255,
+      "mean_token_accuracy": 0.9113675028085708,
+      "num_tokens": 1234977.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.2417304914444685,
+      "epoch": 0.91,
+      "grad_norm": 0.10437507927417755,
+      "learning_rate": 2.3652877533136153e-05,
+      "loss": 0.2259,
+      "mean_token_accuracy": 0.9102976031601429,
+      "num_tokens": 1248701.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.24325928911566735,
+      "epoch": 0.92,
+      "grad_norm": 0.086408831179142,
+      "learning_rate": 2.289826097040211e-05,
+      "loss": 0.2279,
+      "mean_token_accuracy": 0.90808689519763,
+      "num_tokens": 1262415.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.23895474877208472,
+      "epoch": 0.93,
+      "grad_norm": 0.11185527592897415,
+      "learning_rate": 2.2229603308169898e-05,
+      "loss": 0.2267,
+      "mean_token_accuracy": 0.9084525190293788,
+      "num_tokens": 1276097.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.2378123912960291,
+      "epoch": 0.94,
+      "grad_norm": 0.08577776700258255,
+      "learning_rate": 2.164756443082411e-05,
+      "loss": 0.2255,
+      "mean_token_accuracy": 0.9093322195112705,
+      "num_tokens": 1289845.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.238109921105206,
+      "epoch": 0.95,
+      "grad_norm": 0.10014646500349045,
+      "learning_rate": 2.115271874046628e-05,
+      "loss": 0.2244,
+      "mean_token_accuracy": 0.9077881164848804,
+      "num_tokens": 1303598.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.23693346995860337,
+      "epoch": 0.96,
+      "grad_norm": 0.10954771935939789,
+      "learning_rate": 2.0745554590049352e-05,
+      "loss": 0.2245,
+      "mean_token_accuracy": 0.90839484333992,
+      "num_tokens": 1317339.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.23895396925508977,
+      "epoch": 0.97,
+      "grad_norm": 0.09081379324197769,
+      "learning_rate": 2.0426473801432252e-05,
+      "loss": 0.2264,
+      "mean_token_accuracy": 0.9104941196739673,
+      "num_tokens": 1331040.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.23677602242678403,
+      "epoch": 0.98,
+      "grad_norm": 0.10861524939537048,
+      "learning_rate": 2.019579126883027e-05,
+      "loss": 0.2241,
+      "mean_token_accuracy": 0.9098212897777558,
+      "num_tokens": 1344709.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.23963210433721543,
+      "epoch": 0.99,
+      "grad_norm": 0.09649220108985901,
+      "learning_rate": 2.005373464805244e-05,
+      "loss": 0.2259,
+      "mean_token_accuracy": 0.9081830322742462,
+      "num_tokens": 1358455.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.23944416362792253,
+      "epoch": 1.0,
+      "grad_norm": 0.07573503255844116,
+      "learning_rate": 2.0000444131832763e-05,
+      "loss": 0.226,
+      "mean_token_accuracy": 0.9083718590438365,
+      "num_tokens": 1372207.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000,
+  "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": 8569324782686208.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adec00018a230464b81c3c44eab34296e1e4d5890f3696ab13104c3672bd37df
+size 6289

runs/Nov23_23-48-36_fbeea3a897de/events.out.tfevents.1763941731.fbeea3a897de.527.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63111447f858b61b514a41d1d174e166268819bb3c49431a3ebfa8600d3592d
+size 5628

runs/Nov24_00-02-37_fbeea3a897de/events.out.tfevents.1763942571.fbeea3a897de.7709.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b246c04d0243e067ab191c52f62efec6b0e4b2ac774c4b7180210e1a8a2c085d
+size 44097

special_tokens_map.json

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

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}