phi3-mini-4k-instruct-ru-lora

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: microsoft/Phi-3-mini-4k-instruct
+datasets:
+- generator
+model-index:
+- name: checkpoint_dir
+  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. -->
+
+# 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) on the generator dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.3661
+- eval_runtime: 1167.2302
+- eval_samples_per_second: 0.928
+- eval_steps_per_second: 0.232
+- epoch: 0.3783
+- step: 909
+
+## 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: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 1
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "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_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:fc0986f737cf4e0e81764ecea93a5fc1b00f73e6c6d992d67d57ad49933e5715
+size 50366280

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 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.3661268949508667,
+    "eval_runtime": 129.3698,
+    "eval_samples": 4780,
+    "eval_samples_per_second": 0.928,
+    "eval_steps_per_second": 0.232,
+    "total_flos": 4.955226157508198e+16,
+    "train_loss": 2.0918177352961997,
+    "train_runtime": 4098.0987,
+    "train_samples_per_second": 0.263,
+    "train_steps_per_second": 0.066
+}

eval_results.json

@@ -0,0 +1,4 @@
+{
+    "eval_loss": 1.3661268949508667,
+    "eval_samples": 4780
+}

runs/Jun05_10-56-35_2a47410b93d0/events.out.tfevents.1717585022.2a47410b93d0.277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c2630c8d7be737abd85fb6052ebde43e7f02fd5b9a18775d2c8a272b3d3ec7
+size 8231

runs/Jun05_10-56-35_2a47410b93d0/events.out.tfevents.1717589249.2a47410b93d0.277.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3ecc625d23f529635abcc3441ee03e6cdcfa47dd089a267a03007141b18e94
+size 359

runs/Jun05_10-56-35_2a47410b93d0/events.out.tfevents.1717589451.2a47410b93d0.277.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0808454dbbaab3f617a97f00826d52cd5ccadb1b8c42868ecf0d0b2859fcefb
+size 14900

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 +1,130 @@
+{
+  "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": 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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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": 4.955226157508198e+16,
+    "train_loss": 2.0918177352961997,
+    "train_runtime": 4098.0987,
+    "train_samples_per_second": 0.263,
+    "train_steps_per_second": 0.066
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 269,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07434944237918216,
+      "grad_norm": 2.5,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 2.7059,
+      "step": 20
+    },
+    {
+      "epoch": 0.14869888475836432,
+      "grad_norm": 2.5,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 2.7411,
+      "step": 40
+    },
+    {
+      "epoch": 0.22304832713754646,
+      "grad_norm": 3.078125,
+      "learning_rate": 4.990398100856367e-06,
+      "loss": 2.5655,
+      "step": 60
+    },
+    {
+      "epoch": 0.29739776951672864,
+      "grad_norm": 1.8984375,
+      "learning_rate": 4.821741763807186e-06,
+      "loss": 2.3063,
+      "step": 80
+    },
+    {
+      "epoch": 0.37174721189591076,
+      "grad_norm": 1.7421875,
+      "learning_rate": 4.456204510851957e-06,
+      "loss": 2.1029,
+      "step": 100
+    },
+    {
+      "epoch": 0.44609665427509293,
+      "grad_norm": 1.4453125,
+      "learning_rate": 3.924783462463541e-06,
+      "loss": 1.9675,
+      "step": 120
+    },
+    {
+      "epoch": 0.5204460966542751,
+      "grad_norm": 1.1875,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 1.9171,
+      "step": 140
+    },
+    {
+      "epoch": 0.5947955390334573,
+      "grad_norm": 1.25,
+      "learning_rate": 2.5547908335131704e-06,
+      "loss": 1.8781,
+      "step": 160
+    },
+    {
+      "epoch": 0.6691449814126395,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.832392984146018e-06,
+      "loss": 1.8382,
+      "step": 180
+    },
+    {
+      "epoch": 0.7434944237918215,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.1666074087171628e-06,
+      "loss": 1.8145,
+      "step": 200
+    },
+    {
+      "epoch": 0.8178438661710037,
+      "grad_norm": 1.2890625,
+      "learning_rate": 6.138919252022435e-07,
+      "loss": 1.8354,
+      "step": 220
+    },
+    {
+      "epoch": 0.8921933085501859,
+      "grad_norm": 1.3203125,
+      "learning_rate": 2.2111614344599686e-07,
+      "loss": 1.8125,
+      "step": 240
+    },
+    {
+      "epoch": 0.966542750929368,
+      "grad_norm": 1.453125,
+      "learning_rate": 2.1586978482366072e-08,
+      "loss": 1.8379,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "step": 269,
+      "total_flos": 4.955226157508198e+16,
+      "train_loss": 2.0918177352961997,
+      "train_runtime": 4098.0987,
+      "train_samples_per_second": 0.263,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 269,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.955226157508198e+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:e63a01a0c53e96f07542cafc7e307916f45fc633c8246fa9711cb70d25bf0a46
+size 5112