fionazhang/fine-tune-mistral-environment

README.md

@@ -1,3 +1,59 @@
 ---
 license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: fine-tune-mistral-environment
+  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. -->
+
+# fine-tune-mistral-environment
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0377
+
+## 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: 5e-05
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.0a0+git7bcf7da
+- Datasets 2.16.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78b9d57b9db265bbb3a6a7b4c41227a0149d902d4e186f4a2a4a67f9b9491003
+size 23111352

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "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": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ac804f65fce560a2ca2e267c121ed54cb693ce383b73bef020067e34c2a9dc
+size 4664

training_logs.json

@@ -0,0 +1 @@
+[{"loss": 1.9367, "learning_rate": 5e-05, "epoch": 0.06, "step": 10}, {"loss": 2.0026, "learning_rate": 5e-05, "epoch": 0.13, "step": 20}, {"loss": 2.1125, "learning_rate": 5e-05, "epoch": 0.19, "step": 30}, {"loss": 2.9601, "learning_rate": 5e-05, "epoch": 0.26, "step": 40}, {"loss": 1.8848, "learning_rate": 5e-05, "epoch": 0.32, "step": 50}, {"loss": 1.8588, "learning_rate": 5e-05, "epoch": 0.39, "step": 60}, {"loss": 2.1924, "learning_rate": 5e-05, "epoch": 0.45, "step": 70}, {"loss": 2.5077, "learning_rate": 5e-05, "epoch": 0.52, "step": 80}, {"loss": 1.8772, "learning_rate": 5e-05, "epoch": 0.58, "step": 90}, {"loss": 1.8502, "learning_rate": 5e-05, "epoch": 0.65, "step": 100}, {"loss": 2.0774, "learning_rate": 5e-05, "epoch": 0.71, "step": 110}, {"loss": 2.3096, "learning_rate": 5e-05, "epoch": 0.78, "step": 120}, {"loss": 1.8665, "learning_rate": 5e-05, "epoch": 0.84, "step": 130}, {"loss": 1.983, "learning_rate": 5e-05, "epoch": 0.91, "step": 140}, {"loss": 2.1746, "learning_rate": 5e-05, "epoch": 0.97, "step": 150}, {"loss": 2.2051, "learning_rate": 5e-05, "epoch": 1.04, "step": 160}, {"loss": 1.7956, "learning_rate": 5e-05, "epoch": 1.1, "step": 170}, {"loss": 1.8065, "learning_rate": 5e-05, "epoch": 1.17, "step": 180}, {"loss": 2.0293, "learning_rate": 5e-05, "epoch": 1.23, "step": 190}, {"loss": 1.7137, "learning_rate": 5e-05, "epoch": 1.3, "step": 200}, {"loss": 1.7704, "learning_rate": 5e-05, "epoch": 1.36, "step": 210}, {"loss": 1.6424, "learning_rate": 5e-05, "epoch": 1.43, "step": 220}, {"loss": 2.2269, "learning_rate": 5e-05, "epoch": 1.49, "step": 230}, {"loss": 1.8347, "learning_rate": 5e-05, "epoch": 1.56, "step": 240}, {"loss": 1.6955, "learning_rate": 5e-05, "epoch": 1.62, "step": 250}, {"loss": 1.6567, "learning_rate": 5e-05, "epoch": 1.69, "step": 260}, {"loss": 2.0633, "learning_rate": 5e-05, "epoch": 1.75, "step": 270}, {"loss": 1.6374, "learning_rate": 5e-05, "epoch": 1.82, "step": 280}, {"loss": 1.6859, "learning_rate": 5e-05, "epoch": 1.88, "step": 290}, {"loss": 1.7153, "learning_rate": 5e-05, "epoch": 1.95, "step": 300}, {"train_runtime": 82.3289, "train_samples_per_second": 11.199, "train_steps_per_second": 3.741, "total_flos": 4686375447478272.0, "train_loss": 1.9712854670239734, "epoch": 2.0, "step": 308}]