Upload 14 files

README.md

@@ -1,3 +1,63 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+tags:
+- lora
+- qlora
+- script-writing
+- ads
+- youtube-shorts
+- reels
+- marketing
+- content-creation
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# SireIQ-Scripts 🧠✍️
+
+**SireIQ-Scripts** is an instruction-tuned AI model for generating **viral content scripts**, including:
+- Short-form video scripts (Reels, TikTok, Shorts)
+- Marketing & ad copy
+- Image/video storytelling scripts
+- Hook-based social media content
+
+This model is **fine-tuned using LoRA** on top of **Mistral-7B-Instruct**.
+
+---
+
+## 🔧 Model Details
+
+- **Base Model:** mistralai/Mistral-7B-Instruct-v0.2  
+- **Fine-tuning:** LoRA / QLoRA  
+- **Training Type:** Instruction-following  
+- **Framework:** Hugging Face Transformers  
+- **Environment:** Single GPU (Colab / Ubuntu)
+
+---
+
+## 📥 How to Use
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base_model = "mistralai/Mistral-7B-Instruct-v0.2"
+lora_model = "your-username/SireIQ-Scripts"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(
+    base_model,
+    device_map="auto",
+    load_in_4bit=True
+)
+
+model = PeftModel.from_pretrained(model, lora_model)
+
+prompt = """Write a viral Instagram reel script about AI replacing jobs."""
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=200)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "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 sha256:9bf49fc9e72ee00eae9f6d99d20d50fc747e476a17d65c4e79516e5b53db95d5
+size 13648432

checkpoint-680/README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-v0.1
+- lora
+- transformers
+---
+
+# 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-680/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "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-680/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf49fc9e72ee00eae9f6d99d20d50fc747e476a17d65c4e79516e5b53db95d5
+size 13648432

checkpoint-680/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee46ab549759354660abeafd5d5e80e6fec364199278e92f47b8e8a1966db5cb
+size 27367499

checkpoint-680/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bbb8ab05cfffc5336b2b7ff7c52b82dbd134007a953eda907656635344a54c0
+size 14455

checkpoint-680/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb32bcbaa0fd6a47ff0eb6e13e6e39edaafe04fc5ea70b593a5cbad34069705
+size 1465

checkpoint-680/trainer_state.json

@@ -0,0 +1,510 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 680,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014713996689350745,
+      "grad_norm": 1.3101017475128174,
+      "learning_rate": 9.86764705882353e-05,
+      "loss": 2.9497,
+      "step": 10
+    },
+    {
+      "epoch": 0.02942799337870149,
+      "grad_norm": 1.7666537761688232,
+      "learning_rate": 9.720588235294117e-05,
+      "loss": 2.5707,
+      "step": 20
+    },
+    {
+      "epoch": 0.044141990068052236,
+      "grad_norm": 1.4447238445281982,
+      "learning_rate": 9.573529411764707e-05,
+      "loss": 2.281,
+      "step": 30
+    },
+    {
+      "epoch": 0.05885598675740298,
+      "grad_norm": 1.039144515991211,
+      "learning_rate": 9.426470588235294e-05,
+      "loss": 2.3904,
+      "step": 40
+    },
+    {
+      "epoch": 0.07356998344675372,
+      "grad_norm": 1.2274360656738281,
+      "learning_rate": 9.279411764705884e-05,
+      "loss": 2.5839,
+      "step": 50
+    },
+    {
+      "epoch": 0.08828398013610447,
+      "grad_norm": 1.1105211973190308,
+      "learning_rate": 9.13235294117647e-05,
+      "loss": 2.2987,
+      "step": 60
+    },
+    {
+      "epoch": 0.10299797682545521,
+      "grad_norm": 1.2184361219406128,
+      "learning_rate": 8.98529411764706e-05,
+      "loss": 2.5504,
+      "step": 70
+    },
+    {
+      "epoch": 0.11771197351480596,
+      "grad_norm": 1.1057401895523071,
+      "learning_rate": 8.838235294117647e-05,
+      "loss": 2.4922,
+      "step": 80
+    },
+    {
+      "epoch": 0.1324259702041567,
+      "grad_norm": 1.1191836595535278,
+      "learning_rate": 8.691176470588237e-05,
+      "loss": 2.6277,
+      "step": 90
+    },
+    {
+      "epoch": 0.14713996689350745,
+      "grad_norm": 1.2518597841262817,
+      "learning_rate": 8.544117647058823e-05,
+      "loss": 2.1856,
+      "step": 100
+    },
+    {
+      "epoch": 0.1618539635828582,
+      "grad_norm": 1.2593870162963867,
+      "learning_rate": 8.397058823529412e-05,
+      "loss": 2.39,
+      "step": 110
+    },
+    {
+      "epoch": 0.17656796027220895,
+      "grad_norm": 1.5582458972930908,
+      "learning_rate": 8.25e-05,
+      "loss": 2.2159,
+      "step": 120
+    },
+    {
+      "epoch": 0.1912819569615597,
+      "grad_norm": 1.1720651388168335,
+      "learning_rate": 8.102941176470588e-05,
+      "loss": 2.5332,
+      "step": 130
+    },
+    {
+      "epoch": 0.20599595365091042,
+      "grad_norm": 1.3537250757217407,
+      "learning_rate": 7.955882352941176e-05,
+      "loss": 2.549,
+      "step": 140
+    },
+    {
+      "epoch": 0.22070995034026117,
+      "grad_norm": 1.440487265586853,
+      "learning_rate": 7.808823529411765e-05,
+      "loss": 2.6141,
+      "step": 150
+    },
+    {
+      "epoch": 0.23542394702961192,
+      "grad_norm": 1.2468889951705933,
+      "learning_rate": 7.661764705882354e-05,
+      "loss": 2.1802,
+      "step": 160
+    },
+    {
+      "epoch": 0.25013794371896264,
+      "grad_norm": 1.6108534336090088,
+      "learning_rate": 7.514705882352941e-05,
+      "loss": 2.0655,
+      "step": 170
+    },
+    {
+      "epoch": 0.2648519404083134,
+      "grad_norm": 1.454962968826294,
+      "learning_rate": 7.367647058823531e-05,
+      "loss": 2.3067,
+      "step": 180
+    },
+    {
+      "epoch": 0.27956593709766414,
+      "grad_norm": 1.4071511030197144,
+      "learning_rate": 7.220588235294118e-05,
+      "loss": 2.378,
+      "step": 190
+    },
+    {
+      "epoch": 0.2942799337870149,
+      "grad_norm": 1.7635990381240845,
+      "learning_rate": 7.073529411764707e-05,
+      "loss": 2.6275,
+      "step": 200
+    },
+    {
+      "epoch": 0.30899393047636564,
+      "grad_norm": 1.4291043281555176,
+      "learning_rate": 6.926470588235294e-05,
+      "loss": 1.8871,
+      "step": 210
+    },
+    {
+      "epoch": 0.3237079271657164,
+      "grad_norm": 1.5699518918991089,
+      "learning_rate": 6.779411764705882e-05,
+      "loss": 2.3781,
+      "step": 220
+    },
+    {
+      "epoch": 0.33842192385506714,
+      "grad_norm": 1.5319325923919678,
+      "learning_rate": 6.632352941176471e-05,
+      "loss": 2.1488,
+      "step": 230
+    },
+    {
+      "epoch": 0.3531359205444179,
+      "grad_norm": 1.505298376083374,
+      "learning_rate": 6.485294117647059e-05,
+      "loss": 2.6991,
+      "step": 240
+    },
+    {
+      "epoch": 0.36784991723376864,
+      "grad_norm": 2.733734607696533,
+      "learning_rate": 6.338235294117647e-05,
+      "loss": 2.1978,
+      "step": 250
+    },
+    {
+      "epoch": 0.3825639139231194,
+      "grad_norm": 1.6058900356292725,
+      "learning_rate": 6.191176470588235e-05,
+      "loss": 2.1871,
+      "step": 260
+    },
+    {
+      "epoch": 0.3972779106124701,
+      "grad_norm": 2.072322130203247,
+      "learning_rate": 6.044117647058824e-05,
+      "loss": 2.5621,
+      "step": 270
+    },
+    {
+      "epoch": 0.41199190730182084,
+      "grad_norm": 1.765065312385559,
+      "learning_rate": 5.897058823529412e-05,
+      "loss": 2.1595,
+      "step": 280
+    },
+    {
+      "epoch": 0.4267059039911716,
+      "grad_norm": 1.5139451026916504,
+      "learning_rate": 5.7499999999999995e-05,
+      "loss": 2.2917,
+      "step": 290
+    },
+    {
+      "epoch": 0.44141990068052234,
+      "grad_norm": 1.7041040658950806,
+      "learning_rate": 5.6029411764705884e-05,
+      "loss": 2.4275,
+      "step": 300
+    },
+    {
+      "epoch": 0.4561338973698731,
+      "grad_norm": 1.5826152563095093,
+      "learning_rate": 5.455882352941176e-05,
+      "loss": 2.5011,
+      "step": 310
+    },
+    {
+      "epoch": 0.47084789405922384,
+      "grad_norm": 1.692821979522705,
+      "learning_rate": 5.308823529411765e-05,
+      "loss": 2.3798,
+      "step": 320
+    },
+    {
+      "epoch": 0.4855618907485746,
+      "grad_norm": 1.8263252973556519,
+      "learning_rate": 5.161764705882354e-05,
+      "loss": 2.6645,
+      "step": 330
+    },
+    {
+      "epoch": 0.5002758874379253,
+      "grad_norm": 1.7093111276626587,
+      "learning_rate": 5.0147058823529414e-05,
+      "loss": 2.4835,
+      "step": 340
+    },
+    {
+      "epoch": 0.5149898841272761,
+      "grad_norm": 1.7787758111953735,
+      "learning_rate": 4.86764705882353e-05,
+      "loss": 2.3779,
+      "step": 350
+    },
+    {
+      "epoch": 0.5297038808166268,
+      "grad_norm": 1.7382874488830566,
+      "learning_rate": 4.720588235294118e-05,
+      "loss": 2.3799,
+      "step": 360
+    },
+    {
+      "epoch": 0.5444178775059776,
+      "grad_norm": 1.797096848487854,
+      "learning_rate": 4.573529411764706e-05,
+      "loss": 2.2148,
+      "step": 370
+    },
+    {
+      "epoch": 0.5591318741953283,
+      "grad_norm": 1.781445860862732,
+      "learning_rate": 4.4264705882352944e-05,
+      "loss": 2.0308,
+      "step": 380
+    },
+    {
+      "epoch": 0.5738458708846791,
+      "grad_norm": 2.1444976329803467,
+      "learning_rate": 4.2794117647058827e-05,
+      "loss": 2.2169,
+      "step": 390
+    },
+    {
+      "epoch": 0.5885598675740298,
+      "grad_norm": 1.8745927810668945,
+      "learning_rate": 4.13235294117647e-05,
+      "loss": 1.9554,
+      "step": 400
+    },
+    {
+      "epoch": 0.6032738642633806,
+      "grad_norm": 1.5899605751037598,
+      "learning_rate": 3.985294117647059e-05,
+      "loss": 2.4028,
+      "step": 410
+    },
+    {
+      "epoch": 0.6179878609527313,
+      "grad_norm": 1.9187322854995728,
+      "learning_rate": 3.8382352941176474e-05,
+      "loss": 2.2514,
+      "step": 420
+    },
+    {
+      "epoch": 0.632701857642082,
+      "grad_norm": 1.5589262247085571,
+      "learning_rate": 3.6911764705882356e-05,
+      "loss": 2.343,
+      "step": 430
+    },
+    {
+      "epoch": 0.6474158543314328,
+      "grad_norm": 1.5984998941421509,
+      "learning_rate": 3.544117647058824e-05,
+      "loss": 1.9433,
+      "step": 440
+    },
+    {
+      "epoch": 0.6621298510207835,
+      "grad_norm": 1.9034677743911743,
+      "learning_rate": 3.397058823529412e-05,
+      "loss": 2.2025,
+      "step": 450
+    },
+    {
+      "epoch": 0.6768438477101343,
+      "grad_norm": 1.7389880418777466,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 2.3835,
+      "step": 460
+    },
+    {
+      "epoch": 0.691557844399485,
+      "grad_norm": 1.8547667264938354,
+      "learning_rate": 3.1029411764705886e-05,
+      "loss": 2.2641,
+      "step": 470
+    },
+    {
+      "epoch": 0.7062718410888358,
+      "grad_norm": 1.6838593482971191,
+      "learning_rate": 2.9558823529411766e-05,
+      "loss": 1.8679,
+      "step": 480
+    },
+    {
+      "epoch": 0.7209858377781865,
+      "grad_norm": 2.003615617752075,
+      "learning_rate": 2.8088235294117648e-05,
+      "loss": 2.2402,
+      "step": 490
+    },
+    {
+      "epoch": 0.7356998344675373,
+      "grad_norm": 1.7946232557296753,
+      "learning_rate": 2.661764705882353e-05,
+      "loss": 1.9735,
+      "step": 500
+    },
+    {
+      "epoch": 0.750413831156888,
+      "grad_norm": 1.9260705709457397,
+      "learning_rate": 2.5147058823529413e-05,
+      "loss": 2.3836,
+      "step": 510
+    },
+    {
+      "epoch": 0.7651278278462388,
+      "grad_norm": 1.3813334703445435,
+      "learning_rate": 2.3676470588235295e-05,
+      "loss": 2.4856,
+      "step": 520
+    },
+    {
+      "epoch": 0.7798418245355895,
+      "grad_norm": 1.6835263967514038,
+      "learning_rate": 2.2205882352941178e-05,
+      "loss": 2.3702,
+      "step": 530
+    },
+    {
+      "epoch": 0.7945558212249402,
+      "grad_norm": 2.234776496887207,
+      "learning_rate": 2.073529411764706e-05,
+      "loss": 2.6312,
+      "step": 540
+    },
+    {
+      "epoch": 0.809269817914291,
+      "grad_norm": 1.4896553754806519,
+      "learning_rate": 1.9264705882352943e-05,
+      "loss": 2.2481,
+      "step": 550
+    },
+    {
+      "epoch": 0.8239838146036417,
+      "grad_norm": 1.92662513256073,
+      "learning_rate": 1.7794117647058825e-05,
+      "loss": 1.9659,
+      "step": 560
+    },
+    {
+      "epoch": 0.8386978112929925,
+      "grad_norm": 1.4436355829238892,
+      "learning_rate": 1.6323529411764708e-05,
+      "loss": 2.3563,
+      "step": 570
+    },
+    {
+      "epoch": 0.8534118079823432,
+      "grad_norm": 1.8207820653915405,
+      "learning_rate": 1.4852941176470589e-05,
+      "loss": 2.0522,
+      "step": 580
+    },
+    {
+      "epoch": 0.868125804671694,
+      "grad_norm": 1.8331910371780396,
+      "learning_rate": 1.3382352941176471e-05,
+      "loss": 2.4762,
+      "step": 590
+    },
+    {
+      "epoch": 0.8828398013610447,
+      "grad_norm": 1.7300273180007935,
+      "learning_rate": 1.1911764705882354e-05,
+      "loss": 2.4929,
+      "step": 600
+    },
+    {
+      "epoch": 0.8975537980503955,
+      "grad_norm": 1.7423087358474731,
+      "learning_rate": 1.0441176470588236e-05,
+      "loss": 2.065,
+      "step": 610
+    },
+    {
+      "epoch": 0.9122677947397462,
+      "grad_norm": 1.853888988494873,
+      "learning_rate": 8.970588235294119e-06,
+      "loss": 2.3043,
+      "step": 620
+    },
+    {
+      "epoch": 0.926981791429097,
+      "grad_norm": 1.6552138328552246,
+      "learning_rate": 7.5e-06,
+      "loss": 2.6556,
+      "step": 630
+    },
+    {
+      "epoch": 0.9416957881184477,
+      "grad_norm": 1.6745601892471313,
+      "learning_rate": 6.029411764705883e-06,
+      "loss": 2.3833,
+      "step": 640
+    },
+    {
+      "epoch": 0.9564097848077984,
+      "grad_norm": 1.6154053211212158,
+      "learning_rate": 4.558823529411764e-06,
+      "loss": 2.4859,
+      "step": 650
+    },
+    {
+      "epoch": 0.9711237814971492,
+      "grad_norm": 1.7248449325561523,
+      "learning_rate": 3.0882352941176472e-06,
+      "loss": 2.4022,
+      "step": 660
+    },
+    {
+      "epoch": 0.9858377781864999,
+      "grad_norm": 1.7172226905822754,
+      "learning_rate": 1.6176470588235297e-06,
+      "loss": 2.5658,
+      "step": 670
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.6853206157684326,
+      "learning_rate": 1.4705882352941178e-07,
+      "loss": 2.1013,
+      "step": 680
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 680,
+  "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": 5.941123206453658e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-680/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6282a1de5ad492faabf2254db8e3abd8fd7b3a11a72d08431ad0326216eb30c5
+size 5841

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}