Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML](https://huggingface.co/Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML) on the pyg3v1 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.035
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "o_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 sha256:93c19929c1d436d32ae030500c9de54560cf7c55bf33407e3b5203b14e48f5e5
+size 376252176

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998410788475947,
+    "total_flos": 4.169463150439039e+18,
+    "train_loss": 1.7876772542090766,
+    "train_runtime": 32508.2013,
+    "train_samples_per_second": 10.84,
+    "train_steps_per_second": 0.169
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998410788475947,
+    "total_flos": 4.169463150439039e+18,
+    "train_loss": 1.7876772542090766,
+    "train_runtime": 32508.2013,
+    "train_samples_per_second": 10.84,
+    "train_steps_per_second": 0.169
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15a398fe01212191ffd9c473111f2ffaf3760dfd57f3e27fbdc88feb7c75728
+size 5304