End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: alexsherstinsky/Mistral-7B-v0.1-sharded
+model-index:
+- name: experiments
+  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. -->
+
+# experiments
+
+This model is a fine-tuned version of [alexsherstinsky/Mistral-7B-v0.1-sharded](https://huggingface.co/alexsherstinsky/Mistral-7B-v0.1-sharded) 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abb121325eec6817da112530f365fc50f11a061a96d5b23e9457ec6dc03ce70
+size 167832240

runs/Feb26_17-04-14_7a7dbca7871b/events.out.tfevents.1708967056.7a7dbca7871b.303.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c50512050a088cc3d8c46970b1c96b3234c858d5a77ec3b929b20b4c1df6284
+size 80810

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4704d6b53f04976383e3f96678f8fe86ad0288da055ac40e29abf31ee86954a
+size 4856