Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: openchat/openchat_3.5
+tags:
+- generated_from_trainer
+model-index:
+- name: smol-7b
+  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. -->
+
+# smol-7b
+
+This model is a fine-tuned version of [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0409
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0569        | 0.16  | 3    | 2.0409          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openchat/openchat_3.5",
+  "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": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fed70f1cd40a30b5fb26ee553d275112ea4951a505787d2c862ee84f2ce3273
+size 218138576

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.16,
+    "eval_loss": 2.0409016609191895,
+    "eval_runtime": 14.9343,
+    "eval_samples": 500,
+    "eval_samples_per_second": 33.48,
+    "eval_steps_per_second": 4.218,
+    "train_loss": 2.1085566679636636,
+    "train_runtime": 937.9718,
+    "train_samples": 9500,
+    "train_samples_per_second": 10.128,
+    "train_steps_per_second": 0.019
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.16,
+    "eval_loss": 2.0409016609191895,
+    "eval_runtime": 14.9343,
+    "eval_samples": 500,
+    "eval_samples_per_second": 33.48,
+    "eval_steps_per_second": 4.218
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_turn|>",
+  "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 +1,60 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<|end_of_turn|>",
+  "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": 0.16,
+    "train_loss": 2.1085566679636636,
+    "train_runtime": 937.9718,
+    "train_samples": 9500,
+    "train_samples_per_second": 10.128,
+    "train_steps_per_second": 0.019
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1616842105263158,
+  "eval_steps": 500,
+  "global_step": 3,
+  "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": 2.0569,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 2.04089093208313,
+      "eval_runtime": 14.9506,
+      "eval_samples_per_second": 33.444,
+      "eval_steps_per_second": 4.214,
+      "step": 3
+    },
+    {
+      "epoch": 0.16,
+      "step": 3,
+      "total_flos": 1.3928862408769536e+17,
+      "train_loss": 2.1085566679636636,
+      "train_runtime": 937.9718,
+      "train_samples_per_second": 10.128,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.3928862408769536e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09cd699fb67ee24e92dffcdef75093423d6e7c0ae48a109b490fd7b2211f83d
+size 4600