End of training

README.md

@@ -0,0 +1,57 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: transformers
+model_name: checkpoint_dir
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for checkpoint_dir
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Nataliia767567/checkpoint_dir", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/natalipolyakovska-softserve/huggingface/runs/quti29p3)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.0
+- Transformers: 4.47.1
+- Pytorch: 2.2.2
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "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": [
+    "down_proj",
+    "o_proj",
+    "qkv_proj",
+    "gate_up_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 sha256:8fc0555ab7f5e0a79947dcb4064284ae36cd9b113b0f114189840fb5c5b2a358
+size 100697728

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.519725494403072e+16,
+    "train_loss": 0.958257312485666,
+    "train_runtime": 404.051,
+    "train_samples_per_second": 3.267,
+    "train_steps_per_second": 0.817
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.519725494403072e+16,
+    "train_loss": 0.958257312485666,
+    "train_runtime": 404.051,
+    "train_samples_per_second": 3.267,
+    "train_steps_per_second": 0.817
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 0.36308756470680237,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 1.3855,
+      "step": 20
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.3340895473957062,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 1.3679,
+      "step": 40
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.3473477363586426,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.3813,
+      "step": 60
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.35594913363456726,
+      "learning_rate": 4.965385884295467e-06,
+      "loss": 1.2987,
+      "step": 80
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.39734789729118347,
+      "learning_rate": 4.798150758954164e-06,
+      "loss": 1.237,
+      "step": 100
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.42136889696121216,
+      "learning_rate": 4.501353102310901e-06,
+      "loss": 1.1311,
+      "step": 120
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.557064414024353,
+      "learning_rate": 4.091725435297721e-06,
+      "loss": 1.0763,
+      "step": 140
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.5050609707832336,
+      "learning_rate": 3.5923612809233987e-06,
+      "loss": 0.9135,
+      "step": 160
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.43929287791252136,
+      "learning_rate": 3.0314132238824416e-06,
+      "loss": 0.7968,
+      "step": 180
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.39808526635169983,
+      "learning_rate": 2.440505756134732e-06,
+      "loss": 0.74,
+      "step": 200
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.45625489950180054,
+      "learning_rate": 1.852952387243698e-06,
+      "loss": 0.7124,
+      "step": 220
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.4360494017601013,
+      "learning_rate": 1.301877533199859e-06,
+      "loss": 0.6832,
+      "step": 240
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.38371819257736206,
+      "learning_rate": 8.183490657468687e-07,
+      "loss": 0.6885,
+      "step": 260
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.36575645208358765,
+      "learning_rate": 4.2962680322157335e-07,
+      "loss": 0.6905,
+      "step": 280
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.5191577672958374,
+      "learning_rate": 1.5762568750059604e-07,
+      "loss": 0.6939,
+      "step": 300
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.42232680320739746,
+      "learning_rate": 1.768028831677926e-08,
+      "loss": 0.6645,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "step": 330,
+      "total_flos": 1.519725494403072e+16,
+      "train_loss": 0.958257312485666,
+      "train_runtime": 404.051,
+      "train_samples_per_second": 3.267,
+      "train_steps_per_second": 0.817
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.519725494403072e+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 sha256:24310e9e268e29b36db0c9e81ba1121db50fee4045b249ce0eccd252583b8300
+size 5624