mistralinstruct-7b-sft-lora

README.md

@@ -0,0 +1,65 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+datasets:
+- generator
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: mistralinstruct-7b-sft-lora
+  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. -->
+
+# mistralinstruct-7b-sft-lora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4251
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.4326        | 0.8807 | 6    | 1.4251          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_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 sha256:3f973ab09f6874d183dbd626377c9be9569d0aa0d5ac0969ad591b1c89c51b78
+size 109086672

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.8807339449541285,
+    "total_flos": 6.764886594315878e+16,
+    "train_loss": 1.4339824716250102,
+    "train_runtime": 610.6947,
+    "train_samples_per_second": 1.428,
+    "train_steps_per_second": 0.01
+}

runs/Jul23_20-52-12_288fdc5fccf2/events.out.tfevents.1721768016.288fdc5fccf2.295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b87a6ce38417ebcee8f15c03ad08942dec3e8654b1b22711e49c692065f0dca
+size 5537

runs/Jul23_20-52-12_288fdc5fccf2/events.out.tfevents.1721768539.288fdc5fccf2.295.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e997614f51582c870da6b04861e69a2ed2899cde20affc6a0bb06dd6ee8041
+size 6151

runs/Jul23_21-24-12_288fdc5fccf2/events.out.tfevents.1721769873.288fdc5fccf2.295.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7b8eece0f14a81faf261fef89a2c2758173f8a08cc6de355b3a17e8523bca4
+size 6175

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.8807339449541285,
+    "total_flos": 6.764886594315878e+16,
+    "train_loss": 1.4339824716250102,
+    "train_runtime": 610.6947,
+    "train_samples_per_second": 1.428,
+    "train_steps_per_second": 0.01
+}

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8807339449541285,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.298828125,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 1.4326,
+      "step": 5
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "eval_loss": 1.4250946044921875,
+      "eval_runtime": 158.8147,
+      "eval_samples_per_second": 5.491,
+      "eval_steps_per_second": 5.491,
+      "step": 6
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "step": 6,
+      "total_flos": 6.764886594315878e+16,
+      "train_loss": 1.4339824716250102,
+      "train_runtime": 610.6947,
+      "train_samples_per_second": 1.428,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.764886594315878e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66207095291eda917acd277d2b7cefabb7a166a1e1564da047c470a1ba15d159
+size 5560