nroggendorff/vegan-mayo

README.md

@@ -1,15 +1,56 @@
 ---
 license: apache-2.0
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+library_name: peft
 tags:
-  - trl
-  - sft
-  - generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.3
 model-index:
-  - name: mayo
-    results: []
-datasets:
-  - nroggendorff/mayo
-language:
-  - en
----
+- name: mayo
+  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. -->
+
+# mayo
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
+
+## 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 100
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "lm_head",
+    "o_proj",
+    "down_proj",
+    "up_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 sha256:224c1c769cb331d6e03eedcf63f9451ad5b39f0194080a6a0fe46f84827213db
+size 877194832

runs/May29_18-55-08_c64550f2e00b/events.out.tfevents.1717008920.c64550f2e00b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58f475da4c850bd7c18039ea7eaefa0a6c8801cfda7565e9d529b915ad68a5fe
+size 5428

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bdbbd03b50311b3dfc5e216e292580d76a0b1e6347745ef8432f2dbf2b6a507
+oid sha256:72a8e015ba510768438d3f4f897891fcef56ffa2e72e3aaf6668bbdd9f7b853d
 size 4920