Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- generator
+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.
+It achieves the following results on the evaluation set:
+- Loss: 1.0181
+
+## 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: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9758        | 1.0   | 42   | 1.0181          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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,
+  "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": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_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 sha256:39f03a5d2ae4feb8fa6b78ce63cf4fe8649b5ee02bdd91f549be6182202c4901
+size 83946192

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.935565656994611e+16,
+    "train_loss": 1.0142703553040822,
+    "train_runtime": 423.6882,
+    "train_samples": 500,
+    "train_samples_per_second": 0.788,
+    "train_steps_per_second": 0.099
+}

runs/May14_14-41-08_541c0b3e5c99/events.out.tfevents.1715697678.541c0b3e5c99.191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10298c5ceea3a6fec2da1a5dd9e928be29d7cb9ea31faed3d7c5c727fff9d1b
+size 5184

runs/May14_14-50-33_541c0b3e5c99/events.out.tfevents.1715698243.541c0b3e5c99.191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be545f96a919e93ccd74a38cfbdd8ca90a211a0296574f2b8f545ff0fd62e2df
+size 5184

runs/May14_14-53-10_541c0b3e5c99/events.out.tfevents.1715698408.541c0b3e5c99.8018.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7f68dc187cf56cfd34db6e0c543e9ce7854c0e4ff63e86b8fe7125863dc1a5
+size 7737

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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.935565656994611e+16,
+    "train_loss": 1.0142703553040822,
+    "train_runtime": 423.6882,
+    "train_samples": 500,
+    "train_samples_per_second": 0.788,
+    "train_steps_per_second": 0.099
+}

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 42,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4e-05,
+      "loss": 0.995,
+      "step": 1
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.0002,
+      "loss": 1.11,
+      "step": 5
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.318359375,
+      "learning_rate": 0.0001911228490388136,
+      "loss": 1.0479,
+      "step": 10
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.00016606747233900815,
+      "loss": 0.9913,
+      "step": 15
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00012928227712765504,
+      "loss": 0.9396,
+      "step": 20
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 8.729821802531212e-05,
+      "loss": 0.9968,
+      "step": 25
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.267578125,
+      "learning_rate": 4.756927164427685e-05,
+      "loss": 1.0416,
+      "step": 30
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.251953125,
+      "learning_rate": 1.7149035075615794e-05,
+      "loss": 1.0231,
+      "step": 35
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 1.4384089652291543e-06,
+      "loss": 0.9758,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.0180646181106567,
+      "eval_runtime": 89.6858,
+      "eval_samples_per_second": 3.691,
+      "eval_steps_per_second": 0.468,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "step": 42,
+      "total_flos": 2.935565656994611e+16,
+      "train_loss": 1.0142703553040822,
+      "train_runtime": 423.6882,
+      "train_samples_per_second": 0.788,
+      "train_steps_per_second": 0.099
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 42,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 2.935565656994611e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d09c421049d92f17f63f09979df793b6e4afc44280b5f84050ec6db3f955e02
+size 5048