Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: GeneZC/MiniChat-1.5-3B
+model-index:
+- name: smol-3b
+  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-3b
+
+This model is a fine-tuned version of [GeneZC/MiniChat-1.5-3B](https://huggingface.co/GeneZC/MiniChat-1.5-3B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.6857
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 11.2151       | 0.16  | 3    | 10.6857         |
+
+
+### Framework versions
+
+- Transformers 4.36.0.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": "GeneZC/MiniChat-1.5-3B",
+  "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 sha256:7e9cf4791a2e2df357dced56426793772f64c259be1987e3e1df3167722bf1eb
+size 151020920

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.16,
+    "eval_loss": 10.685683250427246,
+    "eval_runtime": 8.5427,
+    "eval_samples": 500,
+    "eval_samples_per_second": 58.529,
+    "eval_steps_per_second": 7.375,
+    "train_loss": 11.974308331807455,
+    "train_runtime": 561.6093,
+    "train_samples": 9500,
+    "train_samples_per_second": 16.916,
+    "train_steps_per_second": 0.032
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.16,
+    "eval_loss": 10.685683250427246,
+    "eval_runtime": 8.5427,
+    "eval_samples": 500,
+    "eval_samples_per_second": 58.529,
+    "eval_steps_per_second": 7.375
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae87c0db2b21b0fa3fdc5e19d1f9cea94efb703cc7c6281d8718a6714b3cc2be
+size 748869

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": true,
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.16,
+    "train_loss": 11.974308331807455,
+    "train_runtime": 561.6093,
+    "train_samples": 9500,
+    "train_samples_per_second": 16.916,
+    "train_steps_per_second": 0.032
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "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": 11.2151,
+      "step": 1
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 10.685684204101562,
+      "eval_runtime": 8.5482,
+      "eval_samples_per_second": 58.492,
+      "eval_steps_per_second": 7.37,
+      "step": 3
+    },
+    {
+      "epoch": 0.16,
+      "step": 3,
+      "total_flos": 5.890428031624806e+16,
+      "train_loss": 11.974308331807455,
+      "train_runtime": 561.6093,
+      "train_samples_per_second": 16.916,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5.890428031624806e+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 sha256:90600fa3a2e87daea54dabd03ba3c01b5940247e3b6d164dc381365554986cc6
+size 4728