GOAT-11-15

README.md

@@ -0,0 +1,54 @@
+---
+license: llama2
+base_model: caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16
+tags:
+- generated_from_trainer
+model-index:
+- name: finetunemistral
+  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. -->
+
+# finetunemistral
+
+This model is a fine-tuned version of [caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16](https://huggingface.co/caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16) 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "caisarl76/Mistral-7B-OpenOrca-Guanaco-accu16",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46faa52b617912ccc210166e32325a73043385f5454e16fa265c2471654cd3f9
+size 109097933

emissions.csv

@@ -0,0 +1,3 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2023-11-14T23:06:01,codecarbon,73b6b492-a912-4ad9-a90f-cbc20b4bb354,12622.48070693016,0.6297897035116645,4.989428925535129e-05,90.0,219.70000000000005,47.1240119934082,0.3155527930200103,1.2098474261497183,0.165094099620778,1.690494318790505,United States,USA,massachusetts,,,Linux-5.10.0-21-amd64-x86_64-with-glibc2.31,3.10.13,2.2.3,32,AMD Ryzen Threadripper 2950X 16-Core Processor,1,1 x NVIDIA GeForce RTX 3090,-71.7858,42.2917,125.66403198242188,machine,N,1.0
+2023-11-15T13:11:01,codecarbon,07550c8c-f40b-4bf5-adbc-5301f43b4f9a,12599.973283529282,0.6278761369215906,4.983154509877826e-05,90.0,179.636,47.1240119934082,0.3149898107051846,1.205568608563861,0.16479946519884642,1.6853578844678894,United States,USA,massachusetts,,,Linux-5.10.0-21-amd64-x86_64-with-glibc2.31,3.10.13,2.2.3,32,AMD Ryzen Threadripper 2950X 16-Core Processor,1,1 x NVIDIA GeForce RTX 3090,-71.7858,42.2917,125.66403198242188,machine,N,1.0

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a9bbb2d86624a92fdcd698400e0773f7c6e390827ed5d7a9db34a03fb0f3a9
+size 4027