Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: cc-by-nc-4.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+model-index:
+- name: meow
+  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. -->
+
+# meow
+
+This model is a fine-tuned version of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3831
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.3864        | 0.11  | 2    | 2.3831          |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.0
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392f2f865b7c6d3bab112a4d29c7b899eb688f07076135982f3d83f9621e9afd
+size 327208016

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.11,
+    "eval_loss": 2.3830578327178955,
+    "eval_runtime": 21.8336,
+    "eval_samples": 500,
+    "eval_samples_per_second": 22.9,
+    "eval_steps_per_second": 2.885,
+    "train_loss": 3.4910590648651123,
+    "train_runtime": 1414.3444,
+    "train_samples": 9500,
+    "train_samples_per_second": 6.717,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.11,
+    "eval_loss": 2.3830578327178955,
+    "eval_runtime": 21.8336,
+    "eval_samples": 500,
+    "eval_samples_per_second": 22.9,
+    "eval_steps_per_second": 2.885
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% 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": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.11,
+    "train_loss": 3.4910590648651123,
+    "train_runtime": 1414.3444,
+    "train_samples": 9500,
+    "train_samples_per_second": 6.717,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.10778947368421053,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 2.3864,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 2.3830578327178955,
+      "eval_runtime": 22.0897,
+      "eval_samples_per_second": 22.635,
+      "eval_steps_per_second": 2.852,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "step": 2,
+      "total_flos": 1.9781391004729344e+17,
+      "train_loss": 3.4910590648651123,
+      "train_runtime": 1414.3444,
+      "train_samples_per_second": 6.717,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.9781391004729344e+17,
+  "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:a74325f8b8748877c9362cfadd0e5aa940fd12a5c20f182cf3978aeb70c119ec
+size 4728