Model save

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: zephyr-7b-sft-qlora
+  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. -->
+
+# zephyr-7b-sft-qlora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator 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: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.37.2
+- Pytorch 2.2.0
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 501.0799,
+    "train_samples": 207865,
+    "train_samples_per_second": 0.399,
+    "train_steps_per_second": 0.2
+}

lora_4/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
+  },
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

lora_4/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264fb80c3a7830c9942425211af6bdc69e6bc596276a815cc422cd6c999f2d33
+size 167832240

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 501.0799,
+    "train_samples": 207865,
+    "train_samples_per_second": 0.399,
+    "train_steps_per_second": 0.2
+}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0014344526845781992,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "step": 100,
+      "total_flos": 1.7681317319671808e+16,
+      "train_loss": 0.0,
+      "train_runtime": 501.0799,
+      "train_samples_per_second": 0.399,
+      "train_steps_per_second": 0.2
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.7681317319671808e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}