catcch-pilot-model

README.md

@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: huggingface_out
+  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. -->
+
+# huggingface_out
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None 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: 3e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.065
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.9.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e1a5542b0fdc6e2400480c5c68fe61718778d7664abea29ee2cdfa0b814367
+size 436225216

logs/events.out.tfevents.1707369586.rnn.ist.berkeley.edu.19818.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad2e3dc1a0704480b55d384932d4a273b2bbb6298aabd1c24c0410e58d6cd96
+size 5062

logs/events.out.tfevents.1707456185.rnn.ist.berkeley.edu.1554930.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d3a94e3f62b3e8a138b6b7e334566b208fe693a54b09cd65acd5cfc7823235
+size 5730

logs/events.out.tfevents.1707512696.rnn.ist.berkeley.edu.3004003.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f9b0c03d2bc0f1707e39892bc52347df20ce9727e6d5094de0d02b1c2d2e80
+size 5096

logs/events.out.tfevents.1707513744.rnn.ist.berkeley.edu.3066513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca94459d1d5b1e95675020e66665865d8100f8e68793615e57f7f375ea06a195
+size 5096

logs/events.out.tfevents.1707514200.rnn.ist.berkeley.edu.3074602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee89bc9d0bba8ce62b83a8484aceac968f2d39a38dc847b2bdbaf9315569b09
+size 5096

logs/events.out.tfevents.1707514442.rnn.ist.berkeley.edu.3100726.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b46494fded4c35be266b51329ed7dc9d4365089e58b3deb8904e70ccc13acf7
+size 5730

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea1888652f34c4121fd30ef1f6181d4d82293b10863aaec5c21262f34d9c6c6
+size 4664