Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+model-index:
+- name: train_2024-05-29-13-19-55
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-05-29-13-19-55
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the plot_genshin_impact_roleplay_agent_vllm, the genshin_impact_plot_engine_step_inst_short_json and the plot_genshin_impact_roleplay_vllm datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ca37f86325404e766de0f93f674af7e26642ee335bcadd42624773adce7f6d
+size 13648432

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9984317825405125,
+    "total_flos": 4.653204820711244e+18,
+    "train_loss": 1.2595772572973616,
+    "train_runtime": 53380.5541,
+    "train_samples_per_second": 1.075,
+    "train_steps_per_second": 0.067
+}

checkpoint-300/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-300/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80ad57a7111855816468c191e72bd9c464d430fbf96d3922169a751569cf279
+size 13648432

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc2b73c0fa0367cb1987994e210fc87a97328784042f8ae39e2a08307129261
+size 27370618

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df4f8884bda18374787e68fcaa5002d323400aa1725ac97959be586f110df57
+size 1064

checkpoint-300/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
+  }
+}

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-300/trainer_state.json

@@ -0,0 +1,453 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2509147935180345,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004181913225300575,
+      "grad_norm": 3.3295910358428955,
+      "learning_rate": 4.9999760022374266e-05,
+      "loss": 1.8032,
+      "step": 5
+    },
+    {
+      "epoch": 0.00836382645060115,
+      "grad_norm": 2.002122163772583,
+      "learning_rate": 4.999904009410418e-05,
+      "loss": 1.5943,
+      "step": 10
+    },
+    {
+      "epoch": 0.012545739675901725,
+      "grad_norm": 1.9293591976165771,
+      "learning_rate": 4.9997840229011085e-05,
+      "loss": 1.5378,
+      "step": 15
+    },
+    {
+      "epoch": 0.0167276529012023,
+      "grad_norm": 1.936969518661499,
+      "learning_rate": 4.999616045013025e-05,
+      "loss": 1.5856,
+      "step": 20
+    },
+    {
+      "epoch": 0.020909566126502875,
+      "grad_norm": 1.8237314224243164,
+      "learning_rate": 4.9994000789710415e-05,
+      "loss": 1.5066,
+      "step": 25
+    },
+    {
+      "epoch": 0.02509147935180345,
+      "grad_norm": 1.8101543188095093,
+      "learning_rate": 4.9991361289213203e-05,
+      "loss": 1.4499,
+      "step": 30
+    },
+    {
+      "epoch": 0.029273392577104027,
+      "grad_norm": 1.647802710533142,
+      "learning_rate": 4.998824199931228e-05,
+      "loss": 1.4694,
+      "step": 35
+    },
+    {
+      "epoch": 0.0334553058024046,
+      "grad_norm": 1.7077428102493286,
+      "learning_rate": 4.998464297989245e-05,
+      "loss": 1.4945,
+      "step": 40
+    },
+    {
+      "epoch": 0.03763721902770518,
+      "grad_norm": 1.7119005918502808,
+      "learning_rate": 4.998056430004844e-05,
+      "loss": 1.4257,
+      "step": 45
+    },
+    {
+      "epoch": 0.04181913225300575,
+      "grad_norm": 2.0229578018188477,
+      "learning_rate": 4.997600603808359e-05,
+      "loss": 1.4713,
+      "step": 50
+    },
+    {
+      "epoch": 0.04600104547830632,
+      "grad_norm": 1.885362148284912,
+      "learning_rate": 4.997096828150838e-05,
+      "loss": 1.5145,
+      "step": 55
+    },
+    {
+      "epoch": 0.0501829587036069,
+      "grad_norm": 2.0357539653778076,
+      "learning_rate": 4.9965451127038714e-05,
+      "loss": 1.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.054364871928907474,
+      "grad_norm": 1.9780900478363037,
+      "learning_rate": 4.9959454680594086e-05,
+      "loss": 1.412,
+      "step": 65
+    },
+    {
+      "epoch": 0.05854678515420805,
+      "grad_norm": 1.6695700883865356,
+      "learning_rate": 4.995297905729554e-05,
+      "loss": 1.4093,
+      "step": 70
+    },
+    {
+      "epoch": 0.06272869837950862,
+      "grad_norm": 1.9424223899841309,
+      "learning_rate": 4.994602438146344e-05,
+      "loss": 1.4615,
+      "step": 75
+    },
+    {
+      "epoch": 0.0669106116048092,
+      "grad_norm": 1.9082552194595337,
+      "learning_rate": 4.9938590786615126e-05,
+      "loss": 1.4169,
+      "step": 80
+    },
+    {
+      "epoch": 0.07109252483010978,
+      "grad_norm": 1.8944685459136963,
+      "learning_rate": 4.993067841546231e-05,
+      "loss": 1.3064,
+      "step": 85
+    },
+    {
+      "epoch": 0.07527443805541036,
+      "grad_norm": 1.9688103199005127,
+      "learning_rate": 4.992228741990834e-05,
+      "loss": 1.3778,
+      "step": 90
+    },
+    {
+      "epoch": 0.07945635128071092,
+      "grad_norm": 2.0939650535583496,
+      "learning_rate": 4.991341796104534e-05,
+      "loss": 1.3905,
+      "step": 95
+    },
+    {
+      "epoch": 0.0836382645060115,
+      "grad_norm": 1.868986964225769,
+      "learning_rate": 4.9904070209151015e-05,
+      "loss": 1.3723,
+      "step": 100
+    },
+    {
+      "epoch": 0.08782017773131208,
+      "grad_norm": 2.069476842880249,
+      "learning_rate": 4.989424434368549e-05,
+      "loss": 1.4046,
+      "step": 105
+    },
+    {
+      "epoch": 0.09200209095661264,
+      "grad_norm": 2.1500356197357178,
+      "learning_rate": 4.988394055328779e-05,
+      "loss": 1.4319,
+      "step": 110
+    },
+    {
+      "epoch": 0.09618400418191322,
+      "grad_norm": 1.9786696434020996,
+      "learning_rate": 4.987315903577223e-05,
+      "loss": 1.4203,
+      "step": 115
+    },
+    {
+      "epoch": 0.1003659174072138,
+      "grad_norm": 2.035172939300537,
+      "learning_rate": 4.986189999812468e-05,
+      "loss": 1.4046,
+      "step": 120
+    },
+    {
+      "epoch": 0.10454783063251437,
+      "grad_norm": 1.9887930154800415,
+      "learning_rate": 4.985016365649848e-05,
+      "loss": 1.3836,
+      "step": 125
+    },
+    {
+      "epoch": 0.10872974385781495,
+      "grad_norm": 1.8339554071426392,
+      "learning_rate": 4.983795023621041e-05,
+      "loss": 1.3468,
+      "step": 130
+    },
+    {
+      "epoch": 0.11291165708311553,
+      "grad_norm": 2.06648588180542,
+      "learning_rate": 4.982525997173625e-05,
+      "loss": 1.3481,
+      "step": 135
+    },
+    {
+      "epoch": 0.1170935703084161,
+      "grad_norm": 2.1179702281951904,
+      "learning_rate": 4.9812093106706376e-05,
+      "loss": 1.4475,
+      "step": 140
+    },
+    {
+      "epoch": 0.12127548353371667,
+      "grad_norm": 2.1708436012268066,
+      "learning_rate": 4.979844989390104e-05,
+      "loss": 1.3662,
+      "step": 145
+    },
+    {
+      "epoch": 0.12545739675901724,
+      "grad_norm": 2.0533807277679443,
+      "learning_rate": 4.978433059524548e-05,
+      "loss": 1.3856,
+      "step": 150
+    },
+    {
+      "epoch": 0.12963930998431783,
+      "grad_norm": 1.9418696165084839,
+      "learning_rate": 4.976973548180498e-05,
+      "loss": 1.357,
+      "step": 155
+    },
+    {
+      "epoch": 0.1338212232096184,
+      "grad_norm": 2.1071596145629883,
+      "learning_rate": 4.975466483377959e-05,
+      "loss": 1.3613,
+      "step": 160
+    },
+    {
+      "epoch": 0.138003136434919,
+      "grad_norm": 2.3704464435577393,
+      "learning_rate": 4.9739118940498766e-05,
+      "loss": 1.3985,
+      "step": 165
+    },
+    {
+      "epoch": 0.14218504966021955,
+      "grad_norm": 2.1726176738739014,
+      "learning_rate": 4.9723098100415844e-05,
+      "loss": 1.4361,
+      "step": 170
+    },
+    {
+      "epoch": 0.14636696288552012,
+      "grad_norm": 2.608517646789551,
+      "learning_rate": 4.970660262110227e-05,
+      "loss": 1.3565,
+      "step": 175
+    },
+    {
+      "epoch": 0.1505488761108207,
+      "grad_norm": 2.185563564300537,
+      "learning_rate": 4.968963281924173e-05,
+      "loss": 1.2957,
+      "step": 180
+    },
+    {
+      "epoch": 0.15473078933612128,
+      "grad_norm": 1.9632441997528076,
+      "learning_rate": 4.967218902062403e-05,
+      "loss": 1.2833,
+      "step": 185
+    },
+    {
+      "epoch": 0.15891270256142184,
+      "grad_norm": 2.303462028503418,
+      "learning_rate": 4.96542715601389e-05,
+      "loss": 1.3238,
+      "step": 190
+    },
+    {
+      "epoch": 0.16309461578672244,
+      "grad_norm": 2.3211796283721924,
+      "learning_rate": 4.9635880781769495e-05,
+      "loss": 1.3848,
+      "step": 195
+    },
+    {
+      "epoch": 0.167276529012023,
+      "grad_norm": 2.0993776321411133,
+      "learning_rate": 4.961701703858584e-05,
+      "loss": 1.3997,
+      "step": 200
+    },
+    {
+      "epoch": 0.17145844223732357,
+      "grad_norm": 2.210942506790161,
+      "learning_rate": 4.9597680692738056e-05,
+      "loss": 1.334,
+      "step": 205
+    },
+    {
+      "epoch": 0.17564035546262416,
+      "grad_norm": 2.1277225017547607,
+      "learning_rate": 4.957787211544935e-05,
+      "loss": 1.3338,
+      "step": 210
+    },
+    {
+      "epoch": 0.17982226868792472,
+      "grad_norm": 2.287722587585449,
+      "learning_rate": 4.9557591687008966e-05,
+      "loss": 1.3621,
+      "step": 215
+    },
+    {
+      "epoch": 0.1840041819132253,
+      "grad_norm": 2.113842010498047,
+      "learning_rate": 4.9536839796764825e-05,
+      "loss": 1.3808,
+      "step": 220
+    },
+    {
+      "epoch": 0.18818609513852588,
+      "grad_norm": 2.0642735958099365,
+      "learning_rate": 4.951561684311608e-05,
+      "loss": 1.3429,
+      "step": 225
+    },
+    {
+      "epoch": 0.19236800836382645,
+      "grad_norm": 2.2026379108428955,
+      "learning_rate": 4.9493923233505435e-05,
+      "loss": 1.2855,
+      "step": 230
+    },
+    {
+      "epoch": 0.196549921589127,
+      "grad_norm": 2.2843308448791504,
+      "learning_rate": 4.947175938441138e-05,
+      "loss": 1.3432,
+      "step": 235
+    },
+    {
+      "epoch": 0.2007318348144276,
+      "grad_norm": 2.126749038696289,
+      "learning_rate": 4.9449125721340145e-05,
+      "loss": 1.3753,
+      "step": 240
+    },
+    {
+      "epoch": 0.20491374803972817,
+      "grad_norm": 2.514599561691284,
+      "learning_rate": 4.942602267881755e-05,
+      "loss": 1.3101,
+      "step": 245
+    },
+    {
+      "epoch": 0.20909566126502874,
+      "grad_norm": 2.2043542861938477,
+      "learning_rate": 4.940245070038064e-05,
+      "loss": 1.3395,
+      "step": 250
+    },
+    {
+      "epoch": 0.21327757449032933,
+      "grad_norm": 2.152742862701416,
+      "learning_rate": 4.937841023856923e-05,
+      "loss": 1.3188,
+      "step": 255
+    },
+    {
+      "epoch": 0.2174594877156299,
+      "grad_norm": 2.221057415008545,
+      "learning_rate": 4.935390175491716e-05,
+      "loss": 1.4205,
+      "step": 260
+    },
+    {
+      "epoch": 0.2216414009409305,
+      "grad_norm": 2.600109100341797,
+      "learning_rate": 4.932892571994342e-05,
+      "loss": 1.3499,
+      "step": 265
+    },
+    {
+      "epoch": 0.22582331416623105,
+      "grad_norm": 2.2291276454925537,
+      "learning_rate": 4.9303482613143194e-05,
+      "loss": 1.3984,
+      "step": 270
+    },
+    {
+      "epoch": 0.23000522739153162,
+      "grad_norm": 2.338000774383545,
+      "learning_rate": 4.9277572922978586e-05,
+      "loss": 1.344,
+      "step": 275
+    },
+    {
+      "epoch": 0.2341871406168322,
+      "grad_norm": 2.3423988819122314,
+      "learning_rate": 4.925119714686928e-05,
+      "loss": 1.2696,
+      "step": 280
+    },
+    {
+      "epoch": 0.23836905384213278,
+      "grad_norm": 2.433870553970337,
+      "learning_rate": 4.9224355791182955e-05,
+      "loss": 1.3903,
+      "step": 285
+    },
+    {
+      "epoch": 0.24255096706743334,
+      "grad_norm": 2.281836986541748,
+      "learning_rate": 4.919704937122559e-05,
+      "loss": 1.3694,
+      "step": 290
+    },
+    {
+      "epoch": 0.24673288029273394,
+      "grad_norm": 2.2429168224334717,
+      "learning_rate": 4.916927841123159e-05,
+      "loss": 1.3541,
+      "step": 295
+    },
+    {
+      "epoch": 0.2509147935180345,
+      "grad_norm": 2.4559881687164307,
+      "learning_rate": 4.9141043444353674e-05,
+      "loss": 1.3795,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.8792754732702106e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-3000/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-3000/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb5e5fde988ea4cfda33d7cbcd088610df7d27dd16f5a833c54aa850bdb054c
+size 13648432

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7437711b0164ff810c777c9836c97b45eedd0fcd392d3d2c1904af75d5d6cef7
+size 27370618

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f135e1b22e87234f222645117f9175d68cd1910e70c05967a4aa55fa6c28ddaa
+size 1064

checkpoint-3000/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
+  }
+}

checkpoint-3000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-3100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-3100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec50cdc84cca6b2ec13da3d5065b45d3b21bd1f9bd566c130913e0ca4f0f8274
+size 13648432

checkpoint-3100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e49fade1458a2471c7b93bcbed80b983f4cc6a82c5491b0a9ebb2f2e53a958e
+size 27370618

checkpoint-3100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-3100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a68a95b1f6bf06b4f278970fad64d54572b914195a9545eebb93492948effb5c
+size 1064

checkpoint-3100/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
+  }
+}

checkpoint-3100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-3100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad489884f87ec96cc1e49b25622db5c6c3c1eafcad1be5306265a7460b6619a
+size 5304

checkpoint-3200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+---
+
+# 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 0.11.1

checkpoint-3200/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-3200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a951f8b9b15dc78ce75d4190cb26889aed475598350a96bad663e468108323
+size 13648432

checkpoint-3200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6b59ad8a6099e4f94ed92ed7b47e40d47fd2db718a62dcb9f881070d0e29e7
+size 27370618

checkpoint-3200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-3200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79d4f3cf42973cd7abeef7c7fb1765c53e7794d4f608915eef79909aa73841e
+size 1064

checkpoint-3200/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
+  }
+}

checkpoint-3200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404