Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+model-index:
+- name: ccai-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. -->
+
+# ccai-sft-qlora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6977
+
+## 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
+- distributed_type: multi-GPU
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6894        | 0.99  | 38   | 0.6977          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5611374073715e196eead4bade0a9e1ec89249054c6b165157399b2abd8de06
+size 83946192

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.99,
+    "eval_loss": 0.6976714730262756,
+    "eval_runtime": 38.3842,
+    "eval_samples": 1156,
+    "eval_samples_per_second": 4.325,
+    "eval_steps_per_second": 0.547,
+    "train_loss": 0.8748512268066406,
+    "train_runtime": 281.6973,
+    "train_samples": 2126,
+    "train_samples_per_second": 1.09,
+    "train_steps_per_second": 0.135
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "eval_loss": 0.6976714730262756,
+    "eval_runtime": 38.3842,
+    "eval_samples": 1156,
+    "eval_samples_per_second": 4.325,
+    "eval_steps_per_second": 0.547
+}

runs/Feb12_11-43-36_a032d39d1c95/events.out.tfevents.1707738312.a032d39d1c95.1286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f993f03170b8cd18b27482ee2a0df178338f511cd60b4b46350f59e2ec137a
+size 4810

runs/Feb12_11-49-28_a032d39d1c95/events.out.tfevents.1707738588.a032d39d1c95.1503.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260c406562d9596f8f1e2c9572ed0d552fe2aff5cb2d396994c0b915bae65f1d
+size 6656

runs/Feb12_11-49-28_a032d39d1c95/events.out.tfevents.1707738908.a032d39d1c95.1503.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d14b31f2750112f103a2f3c12be1dc33195ae7b1bc831c6e94dab032640d085
+size 354

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 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 0.8748512268066406,
+    "train_runtime": 281.6973,
+    "train_samples": 2126,
+    "train_samples_per_second": 1.09,
+    "train_steps_per_second": 0.135
+}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.987012987012987,
+  "eval_steps": 500,
+  "global_step": 38,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 1.8487,
+      "step": 1
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019957341762950344,
+      "loss": 1.5092,
+      "step": 5
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018502171357296144,
+      "loss": 0.9757,
+      "step": 10
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001526432162877356,
+      "loss": 0.8052,
+      "step": 15
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010922683594633021,
+      "loss": 0.768,
+      "step": 20
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.387583338128471e-05,
+      "loss": 0.6994,
+      "step": 25
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.6099108277934103e-05,
+      "loss": 0.7122,
+      "step": 30
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.817435682718096e-06,
+      "loss": 0.6894,
+      "step": 35
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.6976714730262756,
+      "eval_runtime": 38.531,
+      "eval_samples_per_second": 4.308,
+      "eval_steps_per_second": 0.545,
+      "step": 38
+    },
+    {
+      "epoch": 0.99,
+      "step": 38,
+      "total_flos": 1.335946087759872e+16,
+      "train_loss": 0.8748512268066406,
+      "train_runtime": 281.6973,
+      "train_samples_per_second": 1.09,
+      "train_steps_per_second": 0.135
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 38,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 1.335946087759872e+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:dfa9c310ae82441d12d8041258881e8764880cc37ea43bfadedf8c762f92e0b0
+size 4728